Merge branch 'dev'

descarga_hacia_atras/elFinanciero/elFinanciero/items.py

+# -*- coding: utf-8 -*-
+
+# Define here the models for your scraped items
+#
+# See documentation in:
+# http://doc.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class NoticiasItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    title = scrapy.Field()
+    text = scrapy.Field()
+    date = scrapy.Field()
+    location = scrapy.Field()
+    author = scrapy.Field()
+    topic = scrapy.Field()
+    url = scrapy.Field()

descarga_hacia_atras/elFinanciero/elFinanciero/middlewares.py

+# -*- coding: utf-8 -*-
+
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# http://doc.scrapy.org/en/latest/topics/spider-middleware.html
+
+from scrapy import signals
+
+
+class ElfinancieroSpiderMiddleware(object):
+    # Not all methods need to be defined. If a method is not defined,
+    # scrapy acts as if the spider middleware does not modify the
+    # passed objects.
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # This method is used by Scrapy to create your spiders.
+        s = cls()
+        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
+        return s
+
+    def process_spider_input(response, spider):
+        # Called for each response that goes through the spider
+        # middleware and into the spider.
+
+        # Should return None or raise an exception.
+        return None
+
+    def process_spider_output(response, result, spider):
+        # Called with the results returned from the Spider, after
+        # it has processed the response.
+
+        # Must return an iterable of Request, dict or Item objects.
+        for i in result:
+            yield i
+
+    def process_spider_exception(response, exception, spider):
+        # Called when a spider or process_spider_input() method
+        # (from other spider middleware) raises an exception.
+
+        # Should return either None or an iterable of Response, dict
+        # or Item objects.
+        pass
+
+    def process_start_requests(start_requests, spider):
+        # Called with the start requests of the spider, and works
+        # similarly to the process_spider_output() method, except
+        # that it doesn’t have a response associated.
+
+        # Must return only requests (not items).
+        for r in start_requests:
+            yield r
+
+    def spider_opened(self, spider):
+        spider.logger.info('Spider opened: %s' % spider.name)

descarga_hacia_atras/elFinanciero/elFinanciero/pipelines.py

+# -*- coding: utf-8 -*-
+
+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html
+
+import json
+from collections import OrderedDict
+
+
+class JsonWriterPipeline(object):
+
+    def __init__(self, filename):
+        self.filename = filename
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # Here you get whatever value was passed through the "filename" command line parameter
+        settings = crawler.settings
+        filename = settings.get('filename')
+
+        # Instantiate the pipeline with the file name
+        return cls(filename)
+
+    def open_spider(self, spider):
+        self.counter = 0
+        self.file = open(self.filename, 'w')
+        self.file.write("[")
+
+    def close_spider(self, spider):
+        self.file.write("]")
+        self.file.close()
+
+    def process_item(self, item, spider):
+        # print("this is my item", item)
+        row = []
+        try:
+            row.append(("date", item['date']))
+        except:
+            pass
+        try:
+            row.append(("topic", item['topic']))
+        except:
+            pass
+        try:
+            row.append(("title", item['title']))
+        except:
+            pass
+        try:
+            row.append(("author", item['author']))
+        except:
+            pass
+        try:
+            row.append(("location", item['location']))
+        except:
+            pass
+        try:
+            row.append(("text", item['text']))
+        except:
+            pass
+        try:
+            row.append(("url", item['url']))
+        except:
+            pass
+
+        line = OrderedDict(row)
+
+        self.counter += 1
+        if self.counter == 1:
+            self.file.write(json.dumps(line))
+        elif self.counter > 1:
+            self.file.write(",\n" + json.dumps(line))
+
+        return item

descarga_hacia_atras/elFinanciero/elFinanciero/settings.py

+# -*- coding: utf-8 -*-
+
+# Scrapy settings for elFinanciero project
+#
+# For simplicity, this file contains only settings considered important or
+# commonly used. You can find more settings consulting the documentation:
+#
+#     http://doc.scrapy.org/en/latest/topics/settings.html
+#     http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#     http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+
+BOT_NAME = 'elFinanciero'
+
+SPIDER_MODULES = ['elFinanciero.spiders']
+NEWSPIDER_MODULE = 'elFinanciero.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'elFinanciero (+http://www.yourdomain.com)'
+
+# Obey robots.txt rules
+# ROBOTSTXT_OBEY = True
+
+# Configure maximum concurrent requests performed by Scrapy (default: 16)
+#CONCURRENT_REQUESTS = 32
+
+# Configure a delay for requests for the same website (default: 0)
+# See http://scrapy.readthedocs.org/en/latest/topics/settings.html#download-delay
+# See also autothrottle settings and docs
+DOWNLOAD_DELAY = 0.5
+# The download delay setting will honor only one of:
+#CONCURRENT_REQUESTS_PER_DOMAIN = 16
+#CONCURRENT_REQUESTS_PER_IP = 16
+
+# Disable cookies (enabled by default)
+COOKIES_ENABLED = False
+
+# Disable Telnet Console (enabled by default)
+#TELNETCONSOLE_ENABLED = False
+
+# Override the default request headers:
+#DEFAULT_REQUEST_HEADERS = {
+#   'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
+#   'Accept-Language': 'en',
+#}
+
+# Enable or disable spider middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+#SPIDER_MIDDLEWARES = {
+#    'elFinanciero.middlewares.ElfinancieroSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'elFinanciero.middlewares.MyCustomDownloaderMiddleware': 543,
+#}
+
+# Enable or disable extensions
+# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
+#EXTENSIONS = {
+#    'scrapy.extensions.telnet.TelnetConsole': None,
+#}
+
+# Configure item pipelines
+# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
+ITEM_PIPELINES = {
+   'elFinanciero.pipelines.JsonWriterPipeline': 300,
+}
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See http://doc.scrapy.org/en/latest/topics/autothrottle.html
+#AUTOTHROTTLE_ENABLED = True
+# The initial download delay
+#AUTOTHROTTLE_START_DELAY = 5
+# The maximum download delay to be set in case of high latencies
+#AUTOTHROTTLE_MAX_DELAY = 60
+# The average number of requests Scrapy should be sending in parallel to
+# each remote server
+#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
+# Enable showing throttling stats for every response received:
+#AUTOTHROTTLE_DEBUG = False
+
+# Enable and configure HTTP caching (disabled by default)
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
+#HTTPCACHE_ENABLED = True
+#HTTPCACHE_EXPIRATION_SECS = 0
+#HTTPCACHE_DIR = 'httpcache'
+#HTTPCACHE_IGNORE_HTTP_CODES = []
+#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'

descarga_hacia_atras/elFinanciero/elFinanciero/spiders/__init__.py

+# This package will contain the spiders of your Scrapy project
+#
+# Please refer to the documentation for information on how to create and manage
+# your spiders.

descarga_hacia_atras/elFinanciero/elFinanciero/spiders/noticias.py

+# -*- coding: utf-8 -*-
+import scrapy, re, json
+from elFinanciero.items import NoticiasItem
+from collections import OrderedDict
+from datetime import datetime, date, timedelta, tzinfo
+
+"""
+MEDIO:
+El Financiero, CDMX
+
+DESCARGA HACIA ATRÁS:
+Este crawler no descarga las noticias de un día específico, sino que descarga las todas las noticias desde
+la fecha más reciente hasta la fecha indicada con los parámetros 'year', 'month', 'day'  
+
+USO:
+scrapy crawl noticias --nolog -s filename=2018-02-06.json -a year=2018 -a month=2 -a day=6
+"""
+
+TAG_RE = re.compile(r'<[^>]+>')
+def remove_tags(text):
+    return TAG_RE.sub('', text)
+
+# LOC_RE = re.compile(r'\n.+?,? ?.+? ?\. ?- ?')
+# G_RE = re.compile(r' ?- ?')
+# EM_RE = re.compile(r'((Email|Correo electr.{1,3}nico|Comentarios?):\s)?[\w.-]+@[\w-]+(\.[a-zA-Z]{2,6}){1,2}\s?')
+# TW_RE = re.compile(r'M.{1,3}s de la P.{1,3}lvora en Twitter: @[\w.%+-]+.', re.I)
+# TW2_RE = re.compile(r'((\| )?Twitter:\s+)?(@[\w.%+-]+.)?', re.I)
+# TAG2_RE = re.compile(r'\ntransition_[^\]]+\]')
+# TAG3_RE = re.compile(r'\[[^\]]+[\]\n]')
+TIME = re.compile(r'\d{1,2}:\d{2} ?[ap]m')
+PUB = re.compile(r'"publishedAt":.*?,')
+
+
+class ImportantData(scrapy.Item):
+    section = scrapy.Field()
+    url1 = scrapy.Field()
+    url2 = scrapy.Field()
+    page = scrapy.Field()
+    res = scrapy.Field()
+
+
+class SectionData(scrapy.Item):
+    section = scrapy.Field()
+
+
+class UTC(tzinfo):
+	"""clase para el 'time zone' (zona horaria)"""
+
+	def utcoffset(self, dt):
+		# zona horaria para aguascalientes (centro de méxico): utc-6
+		return timedelta(hours=-6)
+
+	def tzname(self, dt):
+		# nombre de la zona horaria
+		return 'UTC-6'
+
+
+class QuotesSpider(scrapy.Spider):
+    name = "noticias"
+    newsSet = set()
+
+    def start_requests(self):
+        self.tz = UTC()
+        # year = getattr(self, "year", None)
+        # month = getattr(self, "month", None)
+        # day = getattr(self, "day", None)
+        # self.currentDate = date(int(year), int(month), int(day))
+        self.currentDate = datetime.now().date()
+        # self.currentDate = date(2018, 2, 23)
+
+        self.date_parser = {'enero': 1,      'febrero': 2,  'marzo': 3,      'abril': 4,
+                            'mayo': 5,       'junio': 6,    'julio': 7,      'agosto': 8,
+                            'septiembre': 9, 'octubre': 10, 'noviembre': 11, 'diciembre': 12}
+
+        sectionList = ["economia", "empresas", "nacional", "culturas",
+                       "deportes", "mundo", "bajio", "tech", "ciencia"]
+
+        self.baseURL = "http://www.elfinanciero.com.mx/"
+
+        """
+        Ejemplo de URL para las noticias de días anteriores para la sección Economía:
+        http://api.elfinanciero.com.mx/public/search/typed/?_format=json&json={%22search%22:%22*%22,%22categoriesslug%22:%22economia%22}&type=page&page=2&size=10
+        """
+        self.uri_base = "http://api.elfinanciero.com.mx/public/search/typed/?_format=json&json={%22search%22:%22*%22,%22categoriesslug%22:%22"
+        self.uri_page = "%22}&type=page&page="
+        self.uri_complement = "&size=10"
+
+        for s in sectionList:
+            yield scrapy.Request(url=self.baseURL + s, callback=self.parse)
+
+
+    def parse(self, response):
+        searchData = ImportantData()
+
+        CONTINUE_SEARCHING = True
+        section = response.url[response.url.rfind("/") + 1:]
+
+        for link in response.css('div.is-multiline').css('div.column-box').xpath('./a/@href').extract():
+            if link.find("/") == 0:
+                link = link[1:]
+            yield scrapy.Request(url=self.baseURL + link, callback=self.parse_item)
+
+        newsLinkList = response.xpath('//div[@class="column feed"]/a/@href').extract()
+        newsDateList = response.xpath('//div[@class="column feed"]').css('p.date-time::text').extract()
+        postDict = OrderedDict(zip(newsLinkList, newsDateList))
+
+        for uri in postDict.keys():
+            dt = postDict[uri]
+            res = TIME.match(dt)
+            if res:
+                postDate = datetime.now().date()
+            else:
+                postDate = datetime.strptime(dt, "%d/%m/%Y").date()
+
+            if postDate >= self.currentDate:
+                if uri.find("/") == 0:
+                    uri = uri[1:]
+                yield scrapy.Request(url=self.baseURL + uri, callback=self.parse_item)
+
+            else:
+                CONTINUE_SEARCHING = False
+                break
+
+        if CONTINUE_SEARCHING:
+            page = 2
+            url = self.uri_base + section + self.uri_page + str(page) + self.uri_complement
+            searchData['section'] = section
+            searchData['page'] = page
+            request = scrapy.Request(url=url, callback=self.continue_searching, dont_filter=True)
+            request.meta['item'] = searchData
+            yield request
+
+
+    def continue_searching(self, response):
+        CONTINUE_SEARCHING = True
+        searchData = response.meta['item']
+        REG_EXPR = re.compile(r'"' + re.escape(searchData['section']) + r'\\/.*?"')
+
+        lList = REG_EXPR.findall(response.body)
+        pList = PUB.findall(response.body)
+        linkList = [l.replace("\\", '').replace('"', '') for l in lList]
+        isodateList = [d[d.find(":")+1:].replace('"', '').replace(",", '') for d in pList]
+        postDict = OrderedDict(zip(linkList, [iso[:iso.find("T")] for iso in isodateList]))
+
+        for uri in postDict.keys():
+            dt = postDict[uri]
+            res = TIME.match(dt)
+            if res:
+                postDate = datetime.now().date()
+            else:
+                postDate = datetime.strptime(dt, "%Y-%m-%d").date()
+
+            if postDate >= self.currentDate:
+                if uri.find("/") == 0:
+                    uri = uri[1:]
+                yield scrapy.Request(url=self.baseURL + uri, callback=self.parse_item)
+
+            else:
+                CONTINUE_SEARCHING = False
+                break
+
+        if CONTINUE_SEARCHING:
+            searchData['page'] += 1
+            url = self.uri_base + searchData['section'] + self.uri_page + str(searchData['page']) + self.uri_complement
+            request = scrapy.Request(url=url, callback=self.continue_searching)
+            request.meta['item'] = searchData
+            yield request
+
+
+    def parse_item(self, response):
+        if not response.url in self.newsSet:
+            self.newsSet.add(response.url)
+            item = NoticiasItem()
+            text = ''
+
+            res = remove_tags(response.xpath('//script[@type="application/ld+json"]').extract_first())
+            resDict = json.loads(res)
+            dt = resDict['datePublished']
+            d, t = dt.split()
+            d = map(int, d.split("-"))
+            t = map(int, t.split(":"))
+            dat = date(d[0], d[1], d[2])
+
+            if dat >= self.currentDate:
+                item['date'] = datetime(d[0], d[1], d[2], t[0], t[1], t[2], tzinfo=self.tz).isoformat("T")
+
+                item['title'] = remove_tags(response.css('div.column').css('div.column').css('h1').extract_first()).strip()
+
+                topic = response.xpath('//div[@class="section-line"]').extract_first()
+                if topic is not None:
+                    item['topic'] = remove_tags(topic)
+                else:
+                    item['topic'] = None
+
+                author = response.xpath('//div[@class="note-author"]/a').extract_first()
+                if author is not None:
+                    item['author'] = remove_tags(author)
+
+                for p in response.css('div.content').css('p').extract():
+                    text += remove_tags(p) + '\n'
+
+                # result = LOC_RE.search(text)
+                # if result:
+                #     m = result.group(0)
+                #     location = G_RE.sub('', m).strip()
+                #     if len(location) <= 35:
+                #         item['location'] = location
+                #         text = text[text.find(m)+len(m):]
+
+                # text = EM_RE.sub('', text)
+                # text = TW_RE.sub('', text)
+                # text = TW2_RE.sub('', text)
+                # text = TAG2_RE.sub("\n", text)
+                # text = TAG3_RE.sub('', text)
+                item['text'] = text.strip()
+
+                item['url'] = response.url
+
+                yield item

descarga_hacia_atras/elFinanciero/scrapy.cfg

+# Automatically created by: scrapy startproject
+#
+# For more information about the [deploy] section see:
+# https://scrapyd.readthedocs.org/en/latest/deploy.html
+
+[settings]
+default = elFinanciero.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = elFinanciero

descarga_hacia_atras/solDelCentro/scrapy.cfg

+# Automatically created by: scrapy startproject
+#
+# For more information about the [deploy] section see:
+# https://scrapyd.readthedocs.org/en/latest/deploy.html
+
+[settings]
+default = solDelCentro.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = solDelCentro

descarga_hacia_atras/solDelCentro/solDelCentro/items.py

+# -*- coding: utf-8 -*-
+
+# Define here the models for your scraped items
+#
+# See documentation in:
+# http://doc.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class NoticiasItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    title = scrapy.Field()
+    text = scrapy.Field()
+    date = scrapy.Field()
+    location = scrapy.Field()
+    author = scrapy.Field()
+    topic = scrapy.Field()
+    url = scrapy.Field()

descarga_hacia_atras/solDelCentro/solDelCentro/middlewares.py

+# -*- coding: utf-8 -*-
+
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# http://doc.scrapy.org/en/latest/topics/spider-middleware.html
+
+from scrapy import signals
+
+
+class SoldelcentroSpiderMiddleware(object):
+    # Not all methods need to be defined. If a method is not defined,
+    # scrapy acts as if the spider middleware does not modify the
+    # passed objects.
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # This method is used by Scrapy to create your spiders.
+        s = cls()
+        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
+        return s
+
+    def process_spider_input(response, spider):
+        # Called for each response that goes through the spider
+        # middleware and into the spider.
+
+        # Should return None or raise an exception.
+        return None
+
+    def process_spider_output(response, result, spider):
+        # Called with the results returned from the Spider, after
+        # it has processed the response.
+
+        # Must return an iterable of Request, dict or Item objects.
+        for i in result:
+            yield i
+
+    def process_spider_exception(response, exception, spider):
+        # Called when a spider or process_spider_input() method
+        # (from other spider middleware) raises an exception.
+
+        # Should return either None or an iterable of Response, dict
+        # or Item objects.
+        pass
+
+    def process_start_requests(start_requests, spider):
+        # Called with the start requests of the spider, and works
+        # similarly to the process_spider_output() method, except
+        # that it doesn’t have a response associated.
+
+        # Must return only requests (not items).
+        for r in start_requests:
+            yield r
+
+    def spider_opened(self, spider):
+        spider.logger.info('Spider opened: %s' % spider.name)

descarga_hacia_atras/solDelCentro/solDelCentro/pipelines.py

+# -*- coding: utf-8 -*-
+
+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html
+
+import json
+from collections import OrderedDict
+
+
+class JsonWriterPipeline(object):
+
+    def __init__(self, filename):
+        self.filename = filename
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # Here you get whatever value was passed through the "filename" command line parameter
+        settings = crawler.settings
+        filename = settings.get('filename')
+
+        # Instantiate the pipeline with the file name
+        return cls(filename)
+
+    def open_spider(self, spider):
+        self.counter = 0
+        self.file = open(self.filename, 'w')
+        self.file.write("[")
+
+    def close_spider(self, spider):
+        self.file.write("]")
+        self.file.close()
+
+    def process_item(self, item, spider):
+        # print("this is my item", item)
+        row = []
+        try:
+            row.append(("date", item['date']))
+        except:
+            pass
+        try:
+            row.append(("topic", item['topic']))
+        except:
+            pass
+        try:
+            row.append(("title", item['title']))
+        except:
+            pass
+        try:
+            row.append(("author", item['author']))
+        except:
+            pass
+        try:
+            row.append(("location", item['location']))
+        except:
+            pass
+        try:
+            row.append(("text", item['text']))
+        except:
+            pass
+        try:
+            row.append(("url", item['url']))
+        except:
+            pass
+
+        line = OrderedDict(row)
+
+        self.counter += 1
+        if self.counter == 1:
+            self.file.write(json.dumps(line))
+        elif self.counter > 1:
+            self.file.write(",\n" + json.dumps(line))
+
+        return item

descarga_hacia_atras/solDelCentro/solDelCentro/settings.py

+# -*- coding: utf-8 -*-
+
+# Scrapy settings for solDelCentro project
+#
+# For simplicity, this file contains only settings considered important or
+# commonly used. You can find more settings consulting the documentation:
+#
+#     http://doc.scrapy.org/en/latest/topics/settings.html
+#     http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#     http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+
+BOT_NAME = 'solDelCentro'
+
+SPIDER_MODULES = ['solDelCentro.spiders']
+NEWSPIDER_MODULE = 'solDelCentro.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'solDelCentro (+http://www.yourdomain.com)'
+
+# Obey robots.txt rules
+# ROBOTSTXT_OBEY = True
+
+# Configure maximum concurrent requests performed by Scrapy (default: 16)
+#CONCURRENT_REQUESTS = 32
+
+# Configure a delay for requests for the same website (default: 0)
+# See http://scrapy.readthedocs.org/en/latest/topics/settings.html#download-delay
+# See also autothrottle settings and docs
+DOWNLOAD_DELAY = 0.5
+# The download delay setting will honor only one of:
+#CONCURRENT_REQUESTS_PER_DOMAIN = 16
+#CONCURRENT_REQUESTS_PER_IP = 16
+
+# Disable cookies (enabled by default)
+COOKIES_ENABLED = False
+
+# Disable Telnet Console (enabled by default)
+#TELNETCONSOLE_ENABLED = False
+
+# Override the default request headers:
+#DEFAULT_REQUEST_HEADERS = {
+#   'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
+#   'Accept-Language': 'en',
+#}
+
+# Enable or disable spider middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+#SPIDER_MIDDLEWARES = {
+#    'solDelCentro.middlewares.SoldelcentroSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'solDelCentro.middlewares.MyCustomDownloaderMiddleware': 543,
+#}
+
+# Enable or disable extensions
+# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
+#EXTENSIONS = {
+#    'scrapy.extensions.telnet.TelnetConsole': None,
+#}
+
+# Configure item pipelines
+# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
+ITEM_PIPELINES = {
+   'solDelCentro.pipelines.JsonWriterPipeline': 300,
+}
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See http://doc.scrapy.org/en/latest/topics/autothrottle.html
+#AUTOTHROTTLE_ENABLED = True
+# The initial download delay
+#AUTOTHROTTLE_START_DELAY = 5
+# The maximum download delay to be set in case of high latencies
+#AUTOTHROTTLE_MAX_DELAY = 60
+# The average number of requests Scrapy should be sending in parallel to
+# each remote server
+#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
+# Enable showing throttling stats for every response received:
+#AUTOTHROTTLE_DEBUG = False
+
+# Enable and configure HTTP caching (disabled by default)
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
+#HTTPCACHE_ENABLED = True
+#HTTPCACHE_EXPIRATION_SECS = 0
+#HTTPCACHE_DIR = 'httpcache'
+#HTTPCACHE_IGNORE_HTTP_CODES = []
+#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'

descarga_hacia_atras/solDelCentro/solDelCentro/spiders/__init__.py

+# This package will contain the spiders of your Scrapy project
+#
+# Please refer to the documentation for information on how to create and manage
+# your spiders.

descarga_hacia_atras/solDelCentro/solDelCentro/spiders/noticias.py

+# -*- coding: utf-8 -*-
+import scrapy, re
+from solDelCentro.items import NoticiasItem
+from datetime import datetime, date, timedelta, tzinfo
+
+"""
+MEDIO:
+El Sol del Centro, Aguascalientes
+
+DESCARGA HACIA ATRÁS:
+Este crawler no descarga las noticias de un día específico, sino que descarga las todas las noticias desde
+la fecha más reciente hasta la fecha indicada con los parámetros 'year', 'month', 'day'  
+
+USO:
+scrapy crawl noticias --nolog -s filename=2018-02-03.json -a year=2018 -a month=2 -a day=3
+"""
+
+TAG_RE = re.compile(r'<[^>]+>')
+def remove_tags(text):
+    return TAG_RE.sub('', text)
+
+# LOC_RE = re.compile(r'\n.+?,? ?.+? ?\. ?- ?')
+# G_RE = re.compile(r' ?- ?')
+# EM_RE = re.compile(r'((Email|Correo electr.{1,3}nico|Comentarios?):\s)?[\w.-]+@[\w-]+(\.[a-zA-Z]{2,6}){1,2}\s?')
+# TW_RE = re.compile(r'M.{1,3}s de la P.{1,3}lvora en Twitter: @[\w.%+-]+.', re.I)
+# TW2_RE = re.compile(r'((\| )?Twitter:\s+)?(@[\w.%+-]+.)?', re.I)
+# TAG2_RE = re.compile(r'\ntransition_[^\]]+\]')
+# TAG3_RE = re.compile(r'\[[^\]]+[\]\n]')
+
+
+class ImportantData(scrapy.Item):
+    section = scrapy.Field()
+    url1 = scrapy.Field()
+    url2 = scrapy.Field()
+    page = scrapy.Field()
+    res = scrapy.Field()
+
+
+class SectionData(scrapy.Item):
+    section = scrapy.Field()
+
+
+class UTC(tzinfo):
+	"""clase para el 'time zone' (zona horaria)"""
+
+	def utcoffset(self, dt):
+		# zona horaria para aguascalientes (centro de méxico): utc-6
+		return timedelta(hours=-6)
+
+	def tzname(self, dt):
+		# nombre de la zona horaria
+		return 'UTC-6'
+
+
+class QuotesSpider(scrapy.Spider):
+    name = "noticias"
+
+    def start_requests(self):
+        self.tz = UTC()
+        year = getattr(self, "year", None)
+        month = getattr(self, "month", None)
+        day = getattr(self, "day", None)
+        self.currentDate = date(int(year), int(month), int(day))
+
+        self.date_parser = {'enero': 1,      'febrero': 2,  'marzo': 3,      'abril': 4,
+                            'mayo': 5,       'junio': 6,    'julio': 7,      'agosto': 8,
+                            'septiembre': 9, 'octubre': 10, 'noviembre': 11, 'diciembre': 12}
+
+        self.link_parser = {"local_1": "https://www.elsoldelcentro.com.mx/wp-admin/admin-ajax.php?action=alm_query_posts&query_type=standard&nonce=9598a706d3&repeater=default&theme_repeater=null&cta=&comments=&post_type%5B%5D=post&post_format=&category=local&category__not_in=&tag=&tag__not_in=&taxonomy=&taxonomy_terms=&taxonomy_operator=&taxonomy_relation=&meta_key=&meta_value=&meta_compare=&meta_relation=&meta_type=&author=&year=&month=&day=&post_status=&order=DESC&orderby=date&post__in=&post__not_in=&exclude=&search=&custom_args=&posts_per_page=5&page=",
+                            "local_2": "&offset=10&preloaded=false&seo_start_page=1&paging=false&previous_post=false&previous_post_id=&previous_post_taxonomy=&lang=&slug=local&canonical_url=https%3A%2F%2Fwww.elsoldelcentro.com.mx%2Flocal",
+                            "policia_1": "https://www.elsoldelcentro.com.mx/wp-admin/admin-ajax.php?action=alm_query_posts&query_type=standard&nonce=9598a706d3&repeater=default&theme_repeater=null&cta=&comments=&post_type%5B%5D=post&post_format=&category=policia&category__not_in=&tag=&tag__not_in=&taxonomy=&taxonomy_terms=&taxonomy_operator=&taxonomy_relation=&meta_key=&meta_value=&meta_compare=&meta_relation=&meta_type=&author=&year=&month=&day=&post_status=&order=DESC&orderby=date&post__in=&post__not_in=&exclude=&search=&custom_args=&posts_per_page=5&page=",
+                            "policia_2": "&offset=10&preloaded=false&seo_start_page=1&paging=false&previous_post=false&previous_post_id=&previous_post_taxonomy=&lang=&slug=policia&canonical_url=https%3A%2F%2Fwww.elsoldelcentro.com.mx%2Fpolicia",
+                            "mexico_1": "https://www.elsoldelcentro.com.mx/wp-admin/admin-ajax.php?action=alm_query_posts&query_type=standard&nonce=9598a706d3&repeater=default&theme_repeater=null&cta=&comments=&post_type%5B%5D=post&post_format=&category=mexico&category__not_in=&tag=&tag__not_in=&taxonomy=&taxonomy_terms=&taxonomy_operator=&taxonomy_relation=&meta_key=&meta_value=&meta_compare=&meta_relation=&meta_type=&author=&year=&month=&day=&post_status=&order=DESC&orderby=date&post__in=&post__not_in=&exclude=&search=&custom_args=&posts_per_page=5&page=",
+                            "mexico_2": "&offset=10&preloaded=false&seo_start_page=1&paging=false&previous_post=false&previous_post_id=&previous_post_taxonomy=&lang=&slug=mexico&canonical_url=https%3A%2F%2Fwww.elsoldelcentro.com.mx%2Fmexico",
+                            "republica_1": "https://www.elsoldelcentro.com.mx/wp-admin/admin-ajax.php?action=alm_query_posts&query_type=standard&nonce=9598a706d3&repeater=default&theme_repeater=null&cta=&comments=&post_type%5B%5D=post&post_format=&category=republica&category__not_in=&tag=&tag__not_in=&taxonomy=&taxonomy_terms=&taxonomy_operator=&taxonomy_relation=&meta_key=&meta_value=&meta_compare=&meta_relation=&meta_type=&author=&year=&month=&day=&post_status=&order=DESC&orderby=date&post__in=&post__not_in=&exclude=&search=&custom_args=&posts_per_page=5&page=",
+                            "republica_2": "&offset=10&preloaded=false&seo_start_page=1&paging=false&previous_post=false&previous_post_id=&previous_post_taxonomy=&lang=&slug=republica&canonical_url=https%3A%2F%2Fwww.elsoldelcentro.com.mx%2Frepublica",
+                            "mundo_1": "https://www.elsoldelcentro.com.mx/wp-admin/admin-ajax.php?action=alm_query_posts&query_type=standard&nonce=9598a706d3&repeater=default&theme_repeater=null&cta=&comments=&post_type%5B%5D=post&post_format=&category=mundo&category__not_in=&tag=&tag__not_in=&taxonomy=&taxonomy_terms=&taxonomy_operator=&taxonomy_relation=&meta_key=&meta_value=&meta_compare=&meta_relation=&meta_type=&author=&year=&month=&day=&post_status=&order=DESC&orderby=date&post__in=&post__not_in=&exclude=&search=&custom_args=&posts_per_page=5&page=",
+                            "mundo_2": "&offset=10&preloaded=false&seo_start_page=1&paging=false&previous_post=false&previous_post_id=&previous_post_taxonomy=&lang=&slug=mundo&canonical_url=https%3A%2F%2Fwww.elsoldelcentro.com.mx%2Fmundo",
+                            "finanzas_1": "https://www.elsoldelcentro.com.mx/wp-admin/admin-ajax.php?action=alm_query_posts&query_type=standard&nonce=9598a706d3&repeater=default&theme_repeater=null&cta=&comments=&post_type%5B%5D=post&post_format=&category=finanzas&category__not_in=&tag=&tag__not_in=&taxonomy=&taxonomy_terms=&taxonomy_operator=&taxonomy_relation=&meta_key=&meta_value=&meta_compare=&meta_relation=&meta_type=&author=&year=&month=&day=&post_status=&order=DESC&orderby=date&post__in=&post__not_in=&exclude=&search=&custom_args=&posts_per_page=5&page=",
+                            "finanzas_2": "&offset=10&preloaded=false&seo_start_page=1&paging=false&previous_post=false&previous_post_id=&previous_post_taxonomy=&lang=&slug=finanzas&canonical_url=https%3A%2F%2Fwww.elsoldelcentro.com.mx%2Ffinanzas",
+                            "deportes_1": "https://www.elsoldelcentro.com.mx/wp-admin/admin-ajax.php?action=alm_query_posts&query_type=standard&nonce=c070e82ff5&repeater=default&theme_repeater=null&cta=&comments=&post_type%5B%5D=post&post_format=&category=deportes&category__not_in=&tag=&tag__not_in=&taxonomy=&taxonomy_terms=&taxonomy_operator=&taxonomy_relation=&meta_key=&meta_value=&meta_compare=&meta_relation=&meta_type=&author=&year=&month=&day=&post_status=&order=DESC&orderby=date&post__in=&post__not_in=&exclude=&search=&custom_args=&posts_per_page=5&page=",
+                            "deportes_2": "&offset=10&preloaded=false&seo_start_page=1&paging=false&previous_post=false&previous_post_id=&previous_post_taxonomy=&lang=&slug=deportes&canonical_url=https%3A%2F%2Fwww.elsoldelcentro.com.mx%2Fdeportes",
+                            "espectaculos_1": "https://www.elsoldelcentro.com.mx/wp-admin/admin-ajax.php?action=alm_query_posts&query_type=standard&nonce=9598a706d3&repeater=default&theme_repeater=null&cta=&comments=&post_type%5B%5D=post&post_format=&category=espectaculos&category__not_in=&tag=&tag__not_in=&taxonomy=&taxonomy_terms=&taxonomy_operator=&taxonomy_relation=&meta_key=&meta_value=&meta_compare=&meta_relation=&meta_type=&author=&year=&month=&day=&post_status=&order=DESC&orderby=date&post__in=&post__not_in=&exclude=&search=&custom_args=&posts_per_page=5&page=",
+                            "espectaculos_2": "&offset=10&preloaded=false&seo_start_page=1&paging=false&previous_post=false&previous_post_id=&previous_post_taxonomy=&lang=&slug=espectaculos&canonical_url=https%3A%2F%2Fwww.elsoldelcentro.com.mx%2Fespectaculos",
+                            "columna_1": "https://www.elsoldelcentro.com.mx/wp-admin/admin-ajax.php?action=alm_query_posts&query_type=standard&nonce=9598a706d3&repeater=default&theme_repeater=null&cta=&comments=&post_type%5B%5D=columnas&post_format=&category=&category__not_in=&tag=&tag__not_in=&taxonomy=&taxonomy_terms=&taxonomy_operator=&taxonomy_relation=&meta_key=&meta_value=&meta_compare=&meta_relation=&meta_type=&author=&year=&month=&day=&post_status=&order=DESC&orderby=date&post__in=&post__not_in=&exclude=&search=&custom_args=&posts_per_page=5&page=",
+                            "columna_2": "&offset=10&preloaded=false&seo_start_page=1&paging=false&previous_post=false&previous_post_id=&previous_post_taxonomy=&lang=&slug=columnas&canonical_url=https%3A%2F%2Fwww.elsoldelcentro.com.mx%2Fcolumna"}
+
+        sectionList = ["local", "policia", "mexico", "republica", "mundo",
+                       "finanzas", "deportes", "espectaculos", "columna"]
+
+        baseURL = "https://www.elsoldelcentro.com.mx/"
+
+        for s in sectionList:
+            yield scrapy.Request(url=baseURL + s, callback=self.parse)
+
+
+    def parse(self, response):
+        searchData = ImportantData()
+        newsSection = SectionData()
+
+        CONTINUE_SEARCHING = True
+        section = response.url[response.url.rfind("/") + 1:]
+        newsSection['section'] = section
+
+        for post in response.xpath('//div[@class="col-xs-12 col-md-12 col-lg-8 col-izq"]').css('article'):
+            res = post.css('time::attr(datetime)').extract_first()
+
+            if res is not None:
+                d = res.split()[0]
+                d = map(int, d.split("-"))
+                postDate = date(d[0], d[1], d[2])
+
+                if postDate >= self.currentDate:
+                    link = post.css('div.tit-nota').xpath('./h2/a/@href').extract_first()
+                    req = scrapy.Request(url=link, callback=self.parse_item)
+                    req.meta['item'] = newsSection
+                    yield req
+
+                else:
+                    CONTINUE_SEARCHING = False
+                    break
+
+        if CONTINUE_SEARCHING:
+            url1 = self.link_parser[section + "_1"]
+            url2 = self.link_parser[section + "_2"]
+            page = 0
+            url = url1 + str(page) + url2
+            searchData['section'] = section
+            searchData['url1'] = url1
+            searchData['url2'] = url2
+            searchData['page'] = page
+            searchData['res'] = response.url + "/"
+            request = scrapy.Request(url=url, callback=self.continue_searching, dont_filter=True)
+            request.meta['item'] = searchData
+            yield request
+
+
+    def continue_searching(self, response):
+        newsSection = SectionData()
+        searchData = response.meta['item']
+
+        CONTINUE_SEARCHING = True
+        res = searchData['res']
+        newsSection['section'] = searchData['section']
+        dateList = response.xpath('//p[@class=\'\\"entry-meta\\"\']').extract()
+        titleList = response.xpath('//li/h3/a/@href').extract()
+
+        if len(dateList) > 0:
+            for i in range(0, len(dateList)):
+                d = dateList[i]
+                d = remove_tags(d).replace(",", '').split()
+                postDate = date(int(d[2]), self.date_parser[d[0].lower()], int(d[1]))
+
+                if postDate >= self.currentDate:
+                    l = titleList[i]
+                    l = l[l.rfind("/")+1:-2]
+                    link = res + l
+                    req = scrapy.Request(url=link, callback=self.parse_item)
+                    req.meta['item'] = newsSection
+                    yield req
+
+                else:
+                    CONTINUE_SEARCHING = False
+                    break
+
+        else:
+            CONTINUE_SEARCHING = False
+
+
+        if CONTINUE_SEARCHING:
+            url1 = searchData['url1']
+            url2 = searchData['url2']
+            searchData['page'] += 1
+            page = searchData['page']
+            request = scrapy.Request(url=url1 + str(page) + url2, callback=self.continue_searching)
+            request.meta['item'] = searchData
+            yield request
+
+
+    # def parse_page(self, response):
+    #     print "URL: " + response.url
+
+
+    def parse_item(self, response):
+        item = NoticiasItem()
+        newsSection = response.meta['item']
+        text = ''
+
+        res = response.css('div.info-creditos-notas').css('time::attr(datetime)').extract_first()
+        d,t = res.split()
+        d = map(int, d.split("-"))
+        t = map(int, t.split(":"))
+        dat = datetime(d[0], d[1], d[2], t[0], t[1], 0, tzinfo=self.tz).isoformat("T")
+        item['date'] = dat
+
+        item['title'] = remove_tags(response.css('div.col-xs-12').xpath('./h1').extract_first()).strip()
+
+        topic = response.xpath('//div[@class="info-creditos-notas"]/ul/li[@class="seccion"]/a/text()').extract_first()
+        if topic is None:
+            topic = newsSection['section'].capitalize()
+        item['topic'] = topic
+
+        for p in response.css('div.col-xs-12').css('p').extract():
+            text += remove_tags(p) + "\n"
+
+        # result = LOC_RE.search(text)
+        # if result:
+        #     m = result.group(0)
+        #     location = G_RE.sub('', m).strip()
+        #     if len(location) <= 35:
+        #         item['location'] = location
+        #         text = text[text.find(m)+len(m):]
+
+        # text = EM_RE.sub('', text)
+        # text = TW_RE.sub('', text)
+        # text = TW2_RE.sub('', text)
+        # text = TAG2_RE.sub("\n", text)
+        # text = TAG3_RE.sub('', text)
+        item['text'] = text.strip()
+
+        item['url'] = response.url
+
+        yield item

descarga_por_dia/despertarOaxaca/despertarOaxaca/items.py

+# -*- coding: utf-8 -*-
+
+# Define here the models for your scraped items
+#
+# See documentation in:
+# http://doc.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class NoticiasItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    title = scrapy.Field()
+    text = scrapy.Field()
+    date = scrapy.Field()
+    location = scrapy.Field()
+    author = scrapy.Field()
+    topic = scrapy.Field()
+    url = scrapy.Field()

descarga_por_dia/despertarOaxaca/despertarOaxaca/middlewares.py

+# -*- coding: utf-8 -*-
+
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# http://doc.scrapy.org/en/latest/topics/spider-middleware.html
+
+from scrapy import signals
+
+
+class DespertaroaxacaSpiderMiddleware(object):
+    # Not all methods need to be defined. If a method is not defined,
+    # scrapy acts as if the spider middleware does not modify the
+    # passed objects.
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # This method is used by Scrapy to create your spiders.
+        s = cls()
+        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
+        return s
+
+    def process_spider_input(response, spider):
+        # Called for each response that goes through the spider
+        # middleware and into the spider.
+
+        # Should return None or raise an exception.
+        return None
+
+    def process_spider_output(response, result, spider):
+        # Called with the results returned from the Spider, after
+        # it has processed the response.
+
+        # Must return an iterable of Request, dict or Item objects.
+        for i in result:
+            yield i
+
+    def process_spider_exception(response, exception, spider):
+        # Called when a spider or process_spider_input() method
+        # (from other spider middleware) raises an exception.
+
+        # Should return either None or an iterable of Response, dict
+        # or Item objects.
+        pass
+
+    def process_start_requests(start_requests, spider):
+        # Called with the start requests of the spider, and works
+        # similarly to the process_spider_output() method, except
+        # that it doesn’t have a response associated.
+
+        # Must return only requests (not items).
+        for r in start_requests:
+            yield r
+
+    def spider_opened(self, spider):
+        spider.logger.info('Spider opened: %s' % spider.name)

descarga_por_dia/despertarOaxaca/despertarOaxaca/pipelines.py

+# -*- coding: utf-8 -*-
+
+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html
+
+import json
+from collections import OrderedDict
+
+
+class JsonWriterPipeline(object):
+
+    def __init__(self, filename):
+        self.filename = filename
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # Here you get whatever value was passed through the "filename" command line parameter
+        settings = crawler.settings
+        filename = settings.get('filename')
+
+        # Instantiate the pipeline with the file name
+        return cls(filename)
+
+    def open_spider(self, spider):
+        self.counter = 0
+        self.file = open(self.filename, 'w')
+        self.file.write("[")
+
+    def close_spider(self, spider):
+        self.file.write("]")
+        self.file.close()
+
+    def process_item(self, item, spider):
+        # print("this is my item", item)
+        row = []
+        try:
+            row.append(("date", item['date']))
+        except:
+            pass
+        try:
+            row.append(("topic", item['topic']))
+        except:
+            pass
+        try:
+            row.append(("title", item['title']))
+        except:
+            pass
+        try:
+            row.append(("author", item['author']))
+        except:
+            pass
+        try:
+            row.append(("location", item['location']))
+        except:
+            pass
+        try:
+            row.append(("text", item['text']))
+        except:
+            pass
+        try:
+            row.append(("url", item['url']))
+        except:
+            pass
+
+        line = OrderedDict(row)
+
+        self.counter += 1
+        if self.counter == 1:
+            self.file.write(json.dumps(line))
+        elif self.counter > 1:
+            self.file.write(",\n" + json.dumps(line))
+
+        return item

descarga_por_dia/despertarOaxaca/despertarOaxaca/settings.py

+# -*- coding: utf-8 -*-
+
+# Scrapy settings for despertarOaxaca project
+#
+# For simplicity, this file contains only settings considered important or
+# commonly used. You can find more settings consulting the documentation:
+#
+#     http://doc.scrapy.org/en/latest/topics/settings.html
+#     http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#     http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+
+BOT_NAME = 'despertarOaxaca'
+
+SPIDER_MODULES = ['despertarOaxaca.spiders']
+NEWSPIDER_MODULE = 'despertarOaxaca.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'despertarOaxaca (+http://www.yourdomain.com)'
+
+# Obey robots.txt rules
+# ROBOTSTXT_OBEY = True
+
+# Configure maximum concurrent requests performed by Scrapy (default: 16)
+#CONCURRENT_REQUESTS = 32
+
+# Configure a delay for requests for the same website (default: 0)
+# See http://scrapy.readthedocs.org/en/latest/topics/settings.html#download-delay
+# See also autothrottle settings and docs
+DOWNLOAD_DELAY = 0.5
+# The download delay setting will honor only one of:
+#CONCURRENT_REQUESTS_PER_DOMAIN = 16
+#CONCURRENT_REQUESTS_PER_IP = 16
+
+# Disable cookies (enabled by default)
+COOKIES_ENABLED = False
+
+# Disable Telnet Console (enabled by default)
+#TELNETCONSOLE_ENABLED = False
+
+# Override the default request headers:
+#DEFAULT_REQUEST_HEADERS = {
+#   'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
+#   'Accept-Language': 'en',
+#}
+
+# Enable or disable spider middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+#SPIDER_MIDDLEWARES = {
+#    'despertarOaxaca.middlewares.DespertaroaxacaSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'despertarOaxaca.middlewares.MyCustomDownloaderMiddleware': 543,
+#}
+
+# Enable or disable extensions
+# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
+#EXTENSIONS = {
+#    'scrapy.extensions.telnet.TelnetConsole': None,
+#}
+
+# Configure item pipelines
+# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
+ITEM_PIPELINES = {
+   'despertarOaxaca.pipelines.JsonWriterPipeline': 300,
+}
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See http://doc.scrapy.org/en/latest/topics/autothrottle.html
+#AUTOTHROTTLE_ENABLED = True
+# The initial download delay
+#AUTOTHROTTLE_START_DELAY = 5
+# The maximum download delay to be set in case of high latencies
+#AUTOTHROTTLE_MAX_DELAY = 60
+# The average number of requests Scrapy should be sending in parallel to
+# each remote server
+#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
+# Enable showing throttling stats for every response received:
+#AUTOTHROTTLE_DEBUG = False
+
+# Enable and configure HTTP caching (disabled by default)
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
+#HTTPCACHE_ENABLED = True
+#HTTPCACHE_EXPIRATION_SECS = 0
+#HTTPCACHE_DIR = 'httpcache'
+#HTTPCACHE_IGNORE_HTTP_CODES = []
+#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'

descarga_por_dia/despertarOaxaca/despertarOaxaca/spiders/__init__.py

+# This package will contain the spiders of your Scrapy project
+#
+# Please refer to the documentation for information on how to create and manage
+# your spiders.

descarga_por_dia/despertarOaxaca/despertarOaxaca/spiders/noticias.py

+# -*- coding: utf-8 -*-
+import scrapy, re
+from despertarOaxaca.items import NoticiasItem
+
+"""
+MEDIO:
+El Despertar de Oaxaca
+USO:
+scrapy crawl noticias --nolog -s filename=2018-02-04.json -a year=2018 -a month=2 -a day=4
+"""
+
+TAG_RE = re.compile(r'<[^>]+>')
+def remove_tags(text):
+    return TAG_RE.sub('', text)
+
+# LOC_RE = re.compile(r'\n.+?,? ?.+? ?\. ?- ?')
+# G_RE = re.compile(r' ?- ?')
+# EM_RE = re.compile(r'((Email|Correo electr.{1,3}nico|Comentarios?):\s)?[\w.-]+@[\w-]+(\.[a-zA-Z]{2,6}){1,2}\s?')
+# TW_RE = re.compile(r'M.{1,3}s de la P.{1,3}lvora en Twitter: @[\w.%+-]+.', re.I)
+# TW2_RE = re.compile(r'((\| )?Twitter:\s+)?(@[\w.%+-]+.)?', re.I)
+# TAG2_RE = re.compile(r'\ntransition_[^\]]+\]')
+# TAG3_RE = re.compile(r'\[[^\]]+[\]\n]')
+
+class QuotesSpider(scrapy.Spider):
+    name = "noticias"
+
+    def start_requests(self):
+        year = getattr(self, "year", None)
+        month = getattr(self, "month", None)
+        day = getattr(self, "day", None)
+
+        self.baseURL = "http://despertardeoaxaca.com/" + year + "/" + month.zfill(2) + "/" + day.zfill(2)
+
+        yield scrapy.Request(url=self.baseURL, callback=self.parse)
+
+
+    def parse(self, response):
+        yield scrapy.Request(url=response.url, callback=self.parse_page, dont_filter=True)
+
+        pagination = response.xpath('//div[@class="post-pagination cat-"]/a/@href').extract()
+        if len(pagination) > 0:
+            pagination = pagination[-1].strip('/')
+            pages = int(pagination[pagination.rfind('/') + 1:])
+
+            for page in range(1, pages):
+                yield scrapy.Request(url=self.baseURL + '/page/' + str(page + 1), callback=self.parse_page)
+
+
+    def parse_page(self, response):
+        for post in response.xpath('//div[@class="articles"]').css('div.cnt'):
+            item = NoticiasItem()
+
+            topic = post.css('span.category').xpath('./a').extract_first()
+            if topic is not None:
+                item['topic'] = remove_tags(topic)
+
+            link = post.css('h3').xpath('./a/@href').extract_first()
+            request = scrapy.Request(url=link, callback=self.parse_item)
+            request.meta['item'] = item
+            yield request
+
+
+    def parse_item(self, response):
+        item = response.meta['item']
+        text = ''
+
+        "La fecha obtenida ya incluye formato y zona horaria"
+        item['date'] = response.xpath('//meta[@property="article:published_time"]/@content').extract_first()
+        item['title'] = remove_tags(response.css('article.article-post').xpath('./header/h1').extract_first()).strip()
+
+        for p in response.xpath('//div[@class="article-post-content"]').css('p').extract():
+            text += remove_tags(p) + "\n"
+
+        # result = LOC_RE.search(text)
+        # if result:
+        #     m = result.group(0)
+        #     location = G_RE.sub('', m).strip()
+        #     if len(location) <= 35:
+        #         item['location'] = location
+        #         text = text[text.find(m)+len(m):]
+
+        # text = EM_RE.sub('', text)
+        # text = TW_RE.sub('', text)
+        # text = TW2_RE.sub('', text)
+        # text = TAG2_RE.sub("\n", text)
+        # text = TAG3_RE.sub('', text)
+        item['text'] = text.strip()
+
+        item['url'] = response.url
+
+        yield item

descarga_por_dia/despertarOaxaca/scrapy.cfg

+# Automatically created by: scrapy startproject
+#
+# For more information about the [deploy] section see:
+# https://scrapyd.readthedocs.org/en/latest/deploy.html
+
+[settings]
+default = despertarOaxaca.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = despertarOaxaca

descarga_por_dia/elIndependiente/elIndependiente/items.py

+# -*- coding: utf-8 -*-
+
+# Define here the models for your scraped items
+#
+# See documentation in:
+# http://doc.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class NoticiasItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    title = scrapy.Field()
+    text = scrapy.Field()
+    date = scrapy.Field()
+    location = scrapy.Field()
+    author = scrapy.Field()
+    topic = scrapy.Field()
+    url = scrapy.Field()

descarga_por_dia/elIndependiente/elIndependiente/middlewares.py

+# -*- coding: utf-8 -*-
+
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# http://doc.scrapy.org/en/latest/topics/spider-middleware.html
+
+from scrapy import signals
+
+
+class ElindependienteSpiderMiddleware(object):
+    # Not all methods need to be defined. If a method is not defined,
+    # scrapy acts as if the spider middleware does not modify the
+    # passed objects.
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # This method is used by Scrapy to create your spiders.
+        s = cls()
+        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
+        return s
+
+    def process_spider_input(response, spider):
+        # Called for each response that goes through the spider
+        # middleware and into the spider.
+
+        # Should return None or raise an exception.
+        return None
+
+    def process_spider_output(response, result, spider):
+        # Called with the results returned from the Spider, after
+        # it has processed the response.
+
+        # Must return an iterable of Request, dict or Item objects.
+        for i in result:
+            yield i
+
+    def process_spider_exception(response, exception, spider):
+        # Called when a spider or process_spider_input() method
+        # (from other spider middleware) raises an exception.
+
+        # Should return either None or an iterable of Response, dict
+        # or Item objects.
+        pass
+
+    def process_start_requests(start_requests, spider):
+        # Called with the start requests of the spider, and works
+        # similarly to the process_spider_output() method, except
+        # that it doesn’t have a response associated.
+
+        # Must return only requests (not items).
+        for r in start_requests:
+            yield r
+
+    def spider_opened(self, spider):
+        spider.logger.info('Spider opened: %s' % spider.name)

descarga_por_dia/elIndependiente/elIndependiente/pipelines.py

+# -*- coding: utf-8 -*-
+
+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html
+
+import json
+from collections import OrderedDict
+
+
+class JsonWriterPipeline(object):
+
+    def __init__(self, filename):
+        self.filename = filename
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # Here you get whatever value was passed through the "filename" command line parameter
+        settings = crawler.settings
+        filename = settings.get('filename')
+
+        # Instantiate the pipeline with the file name
+        return cls(filename)
+
+    def open_spider(self, spider):
+        self.counter = 0
+        self.file = open(self.filename, 'w')
+        self.file.write("[")
+
+    def close_spider(self, spider):
+        self.file.write("]")
+        self.file.close()
+
+    def process_item(self, item, spider):
+        # print("this is my item", item)
+        row = []
+        try:
+            row.append(("date", item['date']))
+        except:
+            pass
+        try:
+            row.append(("topic", item['topic']))
+        except:
+            pass
+        try:
+            row.append(("title", item['title']))
+        except:
+            pass
+        try:
+            row.append(("author", item['author']))
+        except:
+            pass
+        try:
+            row.append(("location", item['location']))
+        except:
+            pass
+        try:
+            row.append(("text", item['text']))
+        except:
+            pass
+        try:
+            row.append(("url", item['url']))
+        except:
+            pass
+
+        line = OrderedDict(row)
+
+        self.counter += 1
+        if self.counter == 1:
+            self.file.write(json.dumps(line))
+        elif self.counter > 1:
+            self.file.write(",\n" + json.dumps(line))
+
+        return item

descarga_por_dia/elIndependiente/elIndependiente/settings.py

+# -*- coding: utf-8 -*-
+
+# Scrapy settings for elIndependiente project
+#
+# For simplicity, this file contains only settings considered important or
+# commonly used. You can find more settings consulting the documentation:
+#
+#     http://doc.scrapy.org/en/latest/topics/settings.html
+#     http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#     http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+
+BOT_NAME = 'elIndependiente'
+
+SPIDER_MODULES = ['elIndependiente.spiders']
+NEWSPIDER_MODULE = 'elIndependiente.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'elIndependiente (+http://www.yourdomain.com)'
+
+# Obey robots.txt rules
+# ROBOTSTXT_OBEY = True
+
+# Configure maximum concurrent requests performed by Scrapy (default: 16)
+#CONCURRENT_REQUESTS = 32
+
+# Configure a delay for requests for the same website (default: 0)
+# See http://scrapy.readthedocs.org/en/latest/topics/settings.html#download-delay
+# See also autothrottle settings and docs
+DOWNLOAD_DELAY = 0.5
+# The download delay setting will honor only one of:
+#CONCURRENT_REQUESTS_PER_DOMAIN = 16
+#CONCURRENT_REQUESTS_PER_IP = 16
+
+# Disable cookies (enabled by default)
+COOKIES_ENABLED = False
+
+# Disable Telnet Console (enabled by default)
+#TELNETCONSOLE_ENABLED = False
+
+# Override the default request headers:
+#DEFAULT_REQUEST_HEADERS = {
+#   'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
+#   'Accept-Language': 'en',
+#}
+
+# Enable or disable spider middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+#SPIDER_MIDDLEWARES = {
+#    'elIndependiente.middlewares.ElindependienteSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'elIndependiente.middlewares.MyCustomDownloaderMiddleware': 543,
+#}
+
+# Enable or disable extensions
+# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
+#EXTENSIONS = {
+#    'scrapy.extensions.telnet.TelnetConsole': None,
+#}
+
+# Configure item pipelines
+# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
+ITEM_PIPELINES = {
+   'elIndependiente.pipelines.JsonWriterPipeline': 300,
+}
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See http://doc.scrapy.org/en/latest/topics/autothrottle.html
+#AUTOTHROTTLE_ENABLED = True
+# The initial download delay
+#AUTOTHROTTLE_START_DELAY = 5
+# The maximum download delay to be set in case of high latencies
+#AUTOTHROTTLE_MAX_DELAY = 60
+# The average number of requests Scrapy should be sending in parallel to
+# each remote server
+#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
+# Enable showing throttling stats for every response received:
+#AUTOTHROTTLE_DEBUG = False
+
+# Enable and configure HTTP caching (disabled by default)
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
+#HTTPCACHE_ENABLED = True
+#HTTPCACHE_EXPIRATION_SECS = 0
+#HTTPCACHE_DIR = 'httpcache'
+#HTTPCACHE_IGNORE_HTTP_CODES = []
+#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'

descarga_por_dia/elIndependiente/elIndependiente/spiders/__init__.py

+# This package will contain the spiders of your Scrapy project
+#
+# Please refer to the documentation for information on how to create and manage
+# your spiders.

descarga_por_dia/elIndependiente/elIndependiente/spiders/noticias.py

+# -*- coding: utf-8 -*-
+import scrapy, re
+from elIndependiente.items import NoticiasItem
+
+"""
+MEDIO:
+El Independiente, Michoacán
+USO:
+scrapy crawl noticias --nolog -s filename=2018-02-01.json -a year=2018 -a month=2 -a day=1
+"""
+
+TAG_RE = re.compile(r'<[^>]+>')
+def remove_tags(text):
+    return TAG_RE.sub('', text)
+
+# LOC_RE = re.compile(r'\n.+?,? ?.+? ?\. ?- ?')
+# G_RE = re.compile(r' ?- ?')
+# EM_RE = re.compile(r'((Email|Correo electr.{1,3}nico|Comentarios?):\s)?[\w.-]+@[\w-]+(\.[a-zA-Z]{2,6}){1,2}\s?')
+# TW_RE = re.compile(r'M.{1,3}s de la P.{1,3}lvora en Twitter: @[\w.%+-]+.', re.I)
+# TW2_RE = re.compile(r'((\| )?Twitter:\s+)?(@[\w.%+-]+.)?', re.I)
+# TAG2_RE = re.compile(r'\ntransition_[^\]]+\]')
+# TAG3_RE = re.compile(r'\[[^\]]+[\]\n]')
+
+class QuotesSpider(scrapy.Spider):
+    name = "noticias"
+
+    def start_requests(self):
+        year = getattr(self, "year", None)
+        month = getattr(self, "month", None)
+        day = getattr(self, "day", None)
+
+        self.baseURL = "http://www.el-independiente.com.mx/" + year + "/" + month.zfill(2) + "/" + day.zfill(2)
+
+        yield scrapy.Request(url=self.baseURL, callback=self.parse)
+
+
+    def parse(self, response):
+        yield scrapy.Request(url=response.url, callback=self.parse_page, dont_filter=True)
+
+        pagination = response.xpath('//div[@class="pagination"]/a/@href').extract()
+        if len(pagination) > 0:
+            pagination = pagination[-1].strip('/')
+            pages = int(pagination[pagination.rfind('/') + 1:])
+
+            for page in range(1, pages):
+                yield scrapy.Request(url=self.baseURL + '/page/' + str(page + 1), callback=self.parse_page)
+
+
+    def parse_page(self, response):
+        for link in response.xpath('//div[@class="main-col"]/div/div[@class="bp-entry"]/div/h2/a/@href').extract():
+            yield scrapy.Request(url=link, callback=self.parse_item)
+
+
+    def parse_item(self, response):
+        item = NoticiasItem()
+        text = ''
+
+        "La fecha obtenida ya incluye formato y zona horaria"
+        item['date'] = response.xpath('//meta[@itemprop="datePublished"]/@content').extract_first()
+        item['title'] = remove_tags(response.xpath('//h1[@class="post-tile entry-title"]').extract_first()).strip()
+
+        topic = response.xpath('//div[@class="breadcrumbs-plus"]/span/a/span/text()').extract()[-1]
+        item['topic'] = topic
+
+        paragraph = response.xpath('//div[@class="pf-content"]/p').extract()
+        paragraph.extend(response.xpath('//div[@class="pf-content"]/ul/li').extract())
+        for p in paragraph:
+            p = remove_tags(p)
+            if p != "Borrar":
+                text += p + "\n"
+
+        # result = LOC_RE.search(text)
+        # if result:
+        #     m = result.group(0)
+        #     location = G_RE.sub('', m).strip()
+        #     if len(location) <= 35:
+        #         item['location'] = location
+        #         text = text[text.find(m)+len(m):]
+
+        # text = EM_RE.sub('', text)
+        # text = TW_RE.sub('', text)
+        # text = TW2_RE.sub('', text)
+        # text = TAG2_RE.sub("\n", text)
+        # text = TAG3_RE.sub('', text)
+        item['text'] = text.strip()
+
+        item['url'] = response.url
+
+        yield item

descarga_por_dia/elIndependiente/scrapy.cfg

+# Automatically created by: scrapy startproject
+#
+# For more information about the [deploy] section see:
+# https://scrapyd.readthedocs.org/en/latest/deploy.html
+
+[settings]
+default = elIndependiente.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = elIndependiente

descarga_por_dia/elValle/elValle/items.py

+# -*- coding: utf-8 -*-
+
+# Define here the models for your scraped items
+#
+# See documentation in:
+# http://doc.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class NoticiasItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    title = scrapy.Field()
+    text = scrapy.Field()
+    date = scrapy.Field()
+    location = scrapy.Field()
+    author = scrapy.Field()
+    topic = scrapy.Field()
+    url = scrapy.Field()

descarga_por_dia/elValle/elValle/middlewares.py

+# -*- coding: utf-8 -*-
+
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# http://doc.scrapy.org/en/latest/topics/spider-middleware.html
+
+from scrapy import signals
+
+
+class ElvalleSpiderMiddleware(object):
+    # Not all methods need to be defined. If a method is not defined,
+    # scrapy acts as if the spider middleware does not modify the
+    # passed objects.
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # This method is used by Scrapy to create your spiders.
+        s = cls()
+        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
+        return s
+
+    def process_spider_input(response, spider):
+        # Called for each response that goes through the spider
+        # middleware and into the spider.
+
+        # Should return None or raise an exception.
+        return None
+
+    def process_spider_output(response, result, spider):
+        # Called with the results returned from the Spider, after
+        # it has processed the response.
+
+        # Must return an iterable of Request, dict or Item objects.
+        for i in result:
+            yield i
+
+    def process_spider_exception(response, exception, spider):
+        # Called when a spider or process_spider_input() method
+        # (from other spider middleware) raises an exception.
+
+        # Should return either None or an iterable of Response, dict
+        # or Item objects.
+        pass
+
+    def process_start_requests(start_requests, spider):
+        # Called with the start requests of the spider, and works
+        # similarly to the process_spider_output() method, except
+        # that it doesn’t have a response associated.
+
+        # Must return only requests (not items).
+        for r in start_requests:
+            yield r
+
+    def spider_opened(self, spider):
+        spider.logger.info('Spider opened: %s' % spider.name)

descarga_por_dia/elValle/elValle/pipelines.py

+# -*- coding: utf-8 -*-
+
+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html
+
+import json
+from collections import OrderedDict
+
+
+class JsonWriterPipeline(object):
+
+    def __init__(self, filename):
+        self.filename = filename
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # Here you get whatever value was passed through the "filename" command line parameter
+        settings = crawler.settings
+        filename = settings.get('filename')
+
+        # Instantiate the pipeline with the file name
+        return cls(filename)
+
+    def open_spider(self, spider):
+        self.counter = 0
+        self.file = open(self.filename, 'w')
+        self.file.write("[")
+
+    def close_spider(self, spider):
+        self.file.write("]")
+        self.file.close()
+
+    def process_item(self, item, spider):
+        # print("this is my item", item)
+        row = []
+        try:
+            row.append(("date", item['date']))
+        except:
+            pass
+        try:
+            row.append(("topic", item['topic']))
+        except:
+            pass
+        try:
+            row.append(("title", item['title']))
+        except:
+            pass
+        try:
+            row.append(("author", item['author']))
+        except:
+            pass
+        try:
+            row.append(("location", item['location']))
+        except:
+            pass
+        try:
+            row.append(("text", item['text']))
+        except:
+            pass
+        try:
+            row.append(("url", item['url']))
+        except:
+            pass
+
+        line = OrderedDict(row)
+
+        self.counter += 1
+        if self.counter == 1:
+            self.file.write(json.dumps(line))
+        elif self.counter > 1:
+            self.file.write(",\n" + json.dumps(line))
+
+        return item

descarga_por_dia/elValle/elValle/settings.py

+# -*- coding: utf-8 -*-
+
+# Scrapy settings for elValle project
+#
+# For simplicity, this file contains only settings considered important or
+# commonly used. You can find more settings consulting the documentation:
+#
+#     http://doc.scrapy.org/en/latest/topics/settings.html
+#     http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#     http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+
+BOT_NAME = 'elValle'
+
+SPIDER_MODULES = ['elValle.spiders']
+NEWSPIDER_MODULE = 'elValle.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'elValle (+http://www.yourdomain.com)'
+
+# Obey robots.txt rules
+# ROBOTSTXT_OBEY = True
+
+# Configure maximum concurrent requests performed by Scrapy (default: 16)
+#CONCURRENT_REQUESTS = 32
+
+# Configure a delay for requests for the same website (default: 0)
+# See http://scrapy.readthedocs.org/en/latest/topics/settings.html#download-delay
+# See also autothrottle settings and docs
+DOWNLOAD_DELAY = 0.5
+# The download delay setting will honor only one of:
+#CONCURRENT_REQUESTS_PER_DOMAIN = 16
+#CONCURRENT_REQUESTS_PER_IP = 16
+
+# Disable cookies (enabled by default)
+COOKIES_ENABLED = False
+
+# Disable Telnet Console (enabled by default)
+#TELNETCONSOLE_ENABLED = False
+
+# Override the default request headers:
+#DEFAULT_REQUEST_HEADERS = {
+#   'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
+#   'Accept-Language': 'en',
+#}
+
+# Enable or disable spider middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+#SPIDER_MIDDLEWARES = {
+#    'elValle.middlewares.ElvalleSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'elValle.middlewares.MyCustomDownloaderMiddleware': 543,
+#}
+
+# Enable or disable extensions
+# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
+#EXTENSIONS = {
+#    'scrapy.extensions.telnet.TelnetConsole': None,
+#}
+
+# Configure item pipelines
+# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
+ITEM_PIPELINES = {
+   'elValle.pipelines.JsonWriterPipeline': 300,
+}
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See http://doc.scrapy.org/en/latest/topics/autothrottle.html
+#AUTOTHROTTLE_ENABLED = True
+# The initial download delay
+#AUTOTHROTTLE_START_DELAY = 5
+# The maximum download delay to be set in case of high latencies
+#AUTOTHROTTLE_MAX_DELAY = 60
+# The average number of requests Scrapy should be sending in parallel to
+# each remote server
+#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
+# Enable showing throttling stats for every response received:
+#AUTOTHROTTLE_DEBUG = False
+
+# Enable and configure HTTP caching (disabled by default)
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
+#HTTPCACHE_ENABLED = True
+#HTTPCACHE_EXPIRATION_SECS = 0
+#HTTPCACHE_DIR = 'httpcache'
+#HTTPCACHE_IGNORE_HTTP_CODES = []
+#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'

descarga_por_dia/elValle/elValle/spiders/__init__.py

+# This package will contain the spiders of your Scrapy project
+#
+# Please refer to the documentation for information on how to create and manage
+# your spiders.

descarga_por_dia/elValle/elValle/spiders/noticias.py

+# -*- coding: utf-8 -*-
+import scrapy, re
+from elValle.items import NoticiasItem
+
+"""
+MEDIO:
+El Valle, Edo. Méx.
+USO:
+scrapy crawl noticias --nolog -s filename=2018-02-01.json -a year=2018 -a month=2 -a day=1
+"""
+
+TAG_RE = re.compile(r'<[^>]+>')
+def remove_tags(text):
+    return TAG_RE.sub('', text)
+
+LOC_RE = re.compile(r'\n.+?,? ?.+? ?\. ?- ?')
+G_RE = re.compile(r' ?- ?')
+LOC2_RE = re.compile(r'\n.+?, ?.+? ?\.? ?- ?')
+G2_RE = re.compile(r' ?\.? ?- ?')
+# EM_RE = re.compile(r'((Email|Correo electr.{1,3}nico|Comentarios?):\s)?[\w.-]+@[\w-]+(\.[a-zA-Z]{2,6}){1,2}\s?')
+# TW_RE = re.compile(r'M.{1,3}s de la P.{1,3}lvora en Twitter: @[\w.%+-]+.', re.I)
+# TW2_RE = re.compile(r'((\| )?Twitter:\s+)?(@[\w.%+-]+.)?', re.I)
+# TAG2_RE = re.compile(r'\ntransition_[^\]]+\]')
+# TAG3_RE = re.compile(r'\[[^\]]+[\]\n]')
+
+class QuotesSpider(scrapy.Spider):
+    name = "noticias"
+
+    def start_requests(self):
+        year = getattr(self, "year", None)
+        month = getattr(self, "month", None)
+        day = getattr(self, "day", None)
+
+        self.baseURL = "http://elvalle.com.mx/" + year + "/" + month.zfill(2) + "/" + day.zfill(2)
+
+        yield scrapy.Request(url=self.baseURL, callback=self.parse)
+
+
+    def parse(self, response):
+        yield scrapy.Request(url=response.url, callback=self.parse_page, dont_filter=True)
+
+        nextPage = response.xpath('//a[@class="next page-numbers"]/@href').extract_first()
+        if nextPage is not None:
+            yield scrapy.Request(url=nextPage, callback=self.parse)
+
+
+    def parse_page(self, response):
+        for link in response.xpath('//ul[@class="bk-blog-content clearfix"]/li/div/div/h4/a/@href').extract():
+            yield scrapy.Request(url=link, callback=self.parse_item)
+
+
+    def parse_item(self, response):
+        item = NoticiasItem()
+        text = ''
+
+        "La fecha obtenida ya incluye formato y zona horaria"
+        item['date'] = response.xpath('//meta[@itemprop="datePublished"]/@content').extract_first()
+        item['title'] = remove_tags(response.xpath('//h1[@itemprop="headline"]').extract_first()).strip()
+
+        item['topic'] = response.xpath('//div[@class="s-post-header container"]/div[@class="meta"]/div[@class="post-category"]/a/text()').extract_first()
+
+        for p in response.xpath('//div[@class="article-content clearfix"]/p').extract():
+            p = remove_tags(p)
+            p = p.replace(u'\u2013', "-")
+            p = p.replace(u'\u2014', "-")
+            text += p + "\n"
+
+        text = "\n" + text
+        result = LOC_RE.search(text)
+        if result:
+            m = result.group(0)
+            location = G_RE.sub('', m).strip()
+            if len(location) <= 35:
+                item['location'] = location
+                text = text[text.find(m)+len(m):]
+        else:
+            result = LOC2_RE.search(text)
+            if result:
+                m = result.group(0)
+                location = G2_RE.sub('', m).strip()
+                if len(location) <= 35:
+                    item['location'] = location
+                    text = text[text.find(m) + len(m):]
+
+        # text = EM_RE.sub('', text)
+        # text = TW_RE.sub('', text)
+        # text = TW2_RE.sub('', text)
+        # text = TAG2_RE.sub("\n", text)
+        # text = TAG3_RE.sub('', text)
+        item['text'] = text.strip()
+
+        item['url'] = response.url
+
+        yield item

descarga_por_dia/elValle/scrapy.cfg

+# Automatically created by: scrapy startproject
+#
+# For more information about the [deploy] section see:
+# https://scrapyd.readthedocs.org/en/latest/deploy.html
+
+[settings]
+default = elValle.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = elValle

descarga_por_dia/marca/marca/items.py

+# -*- coding: utf-8 -*-
+
+# Define here the models for your scraped items
+#
+# See documentation in:
+# http://doc.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class NoticiasItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    title = scrapy.Field()
+    text = scrapy.Field()
+    date = scrapy.Field()
+    location = scrapy.Field()
+    author = scrapy.Field()
+    topic = scrapy.Field()
+    url = scrapy.Field()

descarga_por_dia/marca/marca/middlewares.py

+# -*- coding: utf-8 -*-
+
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# http://doc.scrapy.org/en/latest/topics/spider-middleware.html
+
+from scrapy import signals
+
+
+class MarcaSpiderMiddleware(object):
+    # Not all methods need to be defined. If a method is not defined,
+    # scrapy acts as if the spider middleware does not modify the
+    # passed objects.
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # This method is used by Scrapy to create your spiders.
+        s = cls()
+        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
+        return s
+
+    def process_spider_input(response, spider):
+        # Called for each response that goes through the spider
+        # middleware and into the spider.
+
+        # Should return None or raise an exception.
+        return None
+
+    def process_spider_output(response, result, spider):
+        # Called with the results returned from the Spider, after
+        # it has processed the response.
+
+        # Must return an iterable of Request, dict or Item objects.
+        for i in result:
+            yield i
+
+    def process_spider_exception(response, exception, spider):
+        # Called when a spider or process_spider_input() method
+        # (from other spider middleware) raises an exception.
+
+        # Should return either None or an iterable of Response, dict
+        # or Item objects.
+        pass
+
+    def process_start_requests(start_requests, spider):
+        # Called with the start requests of the spider, and works
+        # similarly to the process_spider_output() method, except
+        # that it doesn’t have a response associated.
+
+        # Must return only requests (not items).
+        for r in start_requests:
+            yield r
+
+    def spider_opened(self, spider):
+        spider.logger.info('Spider opened: %s' % spider.name)

descarga_por_dia/marca/marca/pipelines.py

+# -*- coding: utf-8 -*-
+
+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html
+
+import json
+from collections import OrderedDict
+
+
+class JsonWriterPipeline(object):
+
+    def __init__(self, filename):
+        self.filename = filename
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # Here you get whatever value was passed through the "filename" command line parameter
+        settings = crawler.settings
+        filename = settings.get('filename')
+
+        # Instantiate the pipeline with the file name
+        return cls(filename)
+
+    def open_spider(self, spider):
+        self.counter = 0
+        self.file = open(self.filename, 'w')
+        self.file.write("[")
+
+    def close_spider(self, spider):
+        self.file.write("]")
+        self.file.close()
+
+    def process_item(self, item, spider):
+        # print("this is my item", item)
+        row = []
+        try:
+            row.append(("date", item['date']))
+        except:
+            pass
+        try:
+            row.append(("topic", item['topic']))
+        except:
+            pass
+        try:
+            row.append(("title", item['title']))
+        except:
+            pass
+        try:
+            row.append(("author", item['author']))
+        except:
+            pass
+        try:
+            row.append(("location", item['location']))
+        except:
+            pass
+        try:
+            row.append(("text", item['text']))
+        except:
+            pass
+        try:
+            row.append(("url", item['url']))
+        except:
+            pass
+
+        line = OrderedDict(row)
+
+        self.counter += 1
+        if self.counter == 1:
+            self.file.write(json.dumps(line))
+        elif self.counter > 1:
+            self.file.write(",\n" + json.dumps(line))
+
+        return item

descarga_por_dia/marca/marca/settings.py

+# -*- coding: utf-8 -*-
+
+# Scrapy settings for marca project
+#
+# For simplicity, this file contains only settings considered important or
+# commonly used. You can find more settings consulting the documentation:
+#
+#     http://doc.scrapy.org/en/latest/topics/settings.html
+#     http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#     http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+
+BOT_NAME = 'marca'
+
+SPIDER_MODULES = ['marca.spiders']
+NEWSPIDER_MODULE = 'marca.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'marca (+http://www.yourdomain.com)'
+
+# Obey robots.txt rules
+# ROBOTSTXT_OBEY = True
+
+# Configure maximum concurrent requests performed by Scrapy (default: 16)
+#CONCURRENT_REQUESTS = 32
+
+# Configure a delay for requests for the same website (default: 0)
+# See http://scrapy.readthedocs.org/en/latest/topics/settings.html#download-delay
+# See also autothrottle settings and docs
+DOWNLOAD_DELAY = 0.5
+# The download delay setting will honor only one of:
+#CONCURRENT_REQUESTS_PER_DOMAIN = 16
+#CONCURRENT_REQUESTS_PER_IP = 16
+
+# Disable cookies (enabled by default)
+COOKIES_ENABLED = False
+
+# Disable Telnet Console (enabled by default)
+#TELNETCONSOLE_ENABLED = False
+
+# Override the default request headers:
+#DEFAULT_REQUEST_HEADERS = {
+#   'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
+#   'Accept-Language': 'en',
+#}
+
+# Enable or disable spider middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+#SPIDER_MIDDLEWARES = {
+#    'marca.middlewares.MarcaSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'marca.middlewares.MyCustomDownloaderMiddleware': 543,
+#}
+
+# Enable or disable extensions
+# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
+#EXTENSIONS = {
+#    'scrapy.extensions.telnet.TelnetConsole': None,
+#}
+
+# Configure item pipelines
+# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
+ITEM_PIPELINES = {
+   'marca.pipelines.JsonWriterPipeline': 300,
+}
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See http://doc.scrapy.org/en/latest/topics/autothrottle.html
+#AUTOTHROTTLE_ENABLED = True
+# The initial download delay
+#AUTOTHROTTLE_START_DELAY = 5
+# The maximum download delay to be set in case of high latencies
+#AUTOTHROTTLE_MAX_DELAY = 60
+# The average number of requests Scrapy should be sending in parallel to
+# each remote server
+#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
+# Enable showing throttling stats for every response received:
+#AUTOTHROTTLE_DEBUG = False
+
+# Enable and configure HTTP caching (disabled by default)
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
+#HTTPCACHE_ENABLED = True
+#HTTPCACHE_EXPIRATION_SECS = 0
+#HTTPCACHE_DIR = 'httpcache'
+#HTTPCACHE_IGNORE_HTTP_CODES = []
+#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'

descarga_por_dia/marca/marca/spiders/__init__.py

+# This package will contain the spiders of your Scrapy project
+#
+# Please refer to the documentation for information on how to create and manage
+# your spiders.

descarga_por_dia/marca/marca/spiders/noticias.py

+# -*- coding: utf-8 -*-
+import scrapy, re
+from marca.items import NoticiasItem
+from datetime import datetime, timedelta, tzinfo
+
+"""
+MEDIO:
+Marca, Oaxaca
+USO:
+scrapy crawl noticias --nolog -s filename=2018-02-04.json -a year=2018 -a month=2 -a day=4
+"""
+
+TAG_RE = re.compile(r'<[^>]+>')
+def remove_tags(text):
+    return TAG_RE.sub('', text)
+
+# LOC_RE = re.compile(r'\n.+?,? ?.+? ?\. ?- ?')
+# G_RE = re.compile(r' ?- ?')
+# EM_RE = re.compile(r'((Email|Correo electr.{1,3}nico|Comentarios?):\s)?[\w.-]+@[\w-]+(\.[a-zA-Z]{2,6}){1,2}\s?')
+# TW_RE = re.compile(r'M.{1,3}s de la P.{1,3}lvora en Twitter: @[\w.%+-]+.', re.I)
+# TW2_RE = re.compile(r'((\| )?Twitter:\s+)?(@[\w.%+-]+.)?', re.I)
+# TAG2_RE = re.compile(r'\ntransition_[^\]]+\]')
+# TAG3_RE = re.compile(r'\[[^\]]+[\]\n]')
+
+
+class UTC(tzinfo):
+    """clase para el 'time zone' (zona horaria)"""
+
+    def utcoffset(self, dt):
+        # zona horaria para oaxaca: utc-6
+        return timedelta(hours=-6)
+
+    def tzname(self, dt):
+        # nombre de la zona horaria
+        return 'UTC-6'
+
+
+class QuotesSpider(scrapy.Spider):
+    name = "noticias"
+
+    def start_requests(self):
+        self.tz = UTC()
+        self.year = getattr(self, "year", None)
+        self.month = getattr(self, "month", None)
+        self.day = getattr(self, "day", None)
+        self.date_parser = {"enero": 1,      "febrero": 2,  "marzo": 3,      "abril": 4,
+                            "mayo": 5,       "junio": 6,    "julio": 7,      "agosto": 8,
+                            "septiembre": 9, "octubre": 10, "noviembre": 11, "diciembre": 12}
+
+        self.baseURL = "http://www.diariomarca.com.mx/" + self.year + "/" + self.month.zfill(2) + "/" + self.day.zfill(2)
+
+        yield scrapy.Request(url=self.baseURL, callback=self.parse)
+
+
+    def parse(self, response):
+        yield scrapy.Request(url=response.url, callback=self.parse_page, dont_filter=True)
+
+        pagination = response.xpath('//div[@class="nav-links"]/a/@href').extract()
+        if len(pagination) > 0:
+            pagination = pagination[-2].strip('/')
+            pages = int(pagination[pagination.rfind('/') + 1:])
+
+            for page in range(1, pages):
+                yield scrapy.Request(url=self.baseURL + '/page/' + str(page + 1), callback=self.parse_page)
+
+
+    def parse_page(self, response):
+        for link in response.xpath('//div[@class="posts-inner layout-list"]').css('h1.entry-title').xpath('./a/@href').extract():
+            yield scrapy.Request(url=link, callback=self.parse_item)
+
+
+    def parse_item(self, response):
+        item = NoticiasItem()
+        text = ''
+
+        try:
+            d = response.xpath('//span[@class="posted-on"]/a/span').extract()[-1]
+            d = d.replace(",", '').split()
+            dat = datetime(int(d[2]), self.date_parser[d[1].lower()], int(d[0]), tzinfo=self.tz).isoformat("T")
+        except:
+            dat = datetime(int(self.year), int(self.month), int(self.day), tzinfo=self.tz).isoformat("T")
+        item['date'] = dat
+
+        item['title'] = remove_tags(response.xpath('//header[@class="entry-header"]/h1').extract_first()).strip()
+
+        topic = response.xpath('//span[@class="cat-links"]/a').extract_first()
+        if topic is not None:
+            item['topic'] = remove_tags(topic)
+
+        for p in response.css('div.entry-content').css('p').extract():
+            text += remove_tags(p) + "\n"
+
+        # result = LOC_RE.search(text)
+        # if result:
+        #     m = result.group(0)
+        #     location = G_RE.sub('', m).strip()
+        #     if len(location) <= 35:
+        #         item['location'] = location
+        #         text = text[text.find(m)+len(m):]
+
+        # text = EM_RE.sub('', text)
+        # text = TW_RE.sub('', text)
+        # text = TW2_RE.sub('', text)
+        # text = TAG2_RE.sub("\n", text)
+        # text = TAG3_RE.sub('', text)
+        item['text'] = text.strip()
+
+        item['url'] = response.url
+
+        yield item

descarga_por_dia/marca/scrapy.cfg

+# Automatically created by: scrapy startproject
+#
+# For more information about the [deploy] section see:
+# https://scrapyd.readthedocs.org/en/latest/deploy.html
+
+[settings]
+default = marca.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = marca

descarga_por_dia/noticiasBahia/noticiasBahia/items.py

+# -*- coding: utf-8 -*-
+
+# Define here the models for your scraped items
+#
+# See documentation in:
+# http://doc.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class NoticiasItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    title = scrapy.Field()
+    text = scrapy.Field()
+    date = scrapy.Field()
+    location = scrapy.Field()
+    author = scrapy.Field()
+    topic = scrapy.Field()
+    url = scrapy.Field()

descarga_por_dia/noticiasBahia/noticiasBahia/middlewares.py

+# -*- coding: utf-8 -*-
+
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# http://doc.scrapy.org/en/latest/topics/spider-middleware.html
+
+from scrapy import signals
+
+
+class NoticiasbahiaSpiderMiddleware(object):
+    # Not all methods need to be defined. If a method is not defined,
+    # scrapy acts as if the spider middleware does not modify the
+    # passed objects.
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # This method is used by Scrapy to create your spiders.
+        s = cls()
+        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
+        return s
+
+    def process_spider_input(response, spider):
+        # Called for each response that goes through the spider
+        # middleware and into the spider.
+
+        # Should return None or raise an exception.
+        return None
+
+    def process_spider_output(response, result, spider):
+        # Called with the results returned from the Spider, after
+        # it has processed the response.
+
+        # Must return an iterable of Request, dict or Item objects.
+        for i in result:
+            yield i
+
+    def process_spider_exception(response, exception, spider):
+        # Called when a spider or process_spider_input() method
+        # (from other spider middleware) raises an exception.
+
+        # Should return either None or an iterable of Response, dict
+        # or Item objects.
+        pass
+
+    def process_start_requests(start_requests, spider):
+        # Called with the start requests of the spider, and works
+        # similarly to the process_spider_output() method, except
+        # that it doesn’t have a response associated.
+
+        # Must return only requests (not items).
+        for r in start_requests:
+            yield r
+
+    def spider_opened(self, spider):
+        spider.logger.info('Spider opened: %s' % spider.name)

descarga_por_dia/noticiasBahia/noticiasBahia/pipelines.py

+# -*- coding: utf-8 -*-
+
+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html
+
+import json
+from collections import OrderedDict
+
+
+class JsonWriterPipeline(object):
+
+    def __init__(self, filename):
+        self.filename = filename
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # Here you get whatever value was passed through the "filename" command line parameter
+        settings = crawler.settings
+        filename = settings.get('filename')
+
+        # Instantiate the pipeline with the file name
+        return cls(filename)
+
+    def open_spider(self, spider):
+        self.counter = 0
+        self.file = open(self.filename, 'w')
+        self.file.write("[")
+
+    def close_spider(self, spider):
+        self.file.write("]")
+        self.file.close()
+
+    def process_item(self, item, spider):
+        # print("this is my item", item)
+        row = []
+        try:
+            row.append(("date", item['date']))
+        except:
+            pass
+        try:
+            row.append(("topic", item['topic']))
+        except:
+            pass
+        try:
+            row.append(("title", item['title']))
+        except:
+            pass
+        try:
+            row.append(("author", item['author']))
+        except:
+            pass
+        try:
+            row.append(("location", item['location']))
+        except:
+            pass
+        try:
+            row.append(("text", item['text']))
+        except:
+            pass
+        try:
+            row.append(("url", item['url']))
+        except:
+            pass
+
+        line = OrderedDict(row)
+
+        self.counter += 1
+        if self.counter == 1:
+            self.file.write(json.dumps(line))
+        elif self.counter > 1:
+            self.file.write(",\n" + json.dumps(line))
+
+        return item

descarga_por_dia/noticiasBahia/noticiasBahia/settings.py

+# -*- coding: utf-8 -*-
+
+# Scrapy settings for noticiasBahia project
+#
+# For simplicity, this file contains only settings considered important or
+# commonly used. You can find more settings consulting the documentation:
+#
+#     http://doc.scrapy.org/en/latest/topics/settings.html
+#     http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#     http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+
+BOT_NAME = 'noticiasBahia'
+
+SPIDER_MODULES = ['noticiasBahia.spiders']
+NEWSPIDER_MODULE = 'noticiasBahia.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'noticiasBahia (+http://www.yourdomain.com)'
+
+# Obey robots.txt rules
+# ROBOTSTXT_OBEY = True
+
+# Configure maximum concurrent requests performed by Scrapy (default: 16)
+#CONCURRENT_REQUESTS = 32
+
+# Configure a delay for requests for the same website (default: 0)
+# See http://scrapy.readthedocs.org/en/latest/topics/settings.html#download-delay
+# See also autothrottle settings and docs
+DOWNLOAD_DELAY = 0.5
+# The download delay setting will honor only one of:
+#CONCURRENT_REQUESTS_PER_DOMAIN = 16
+#CONCURRENT_REQUESTS_PER_IP = 16
+
+# Disable cookies (enabled by default)
+COOKIES_ENABLED = False
+
+# Disable Telnet Console (enabled by default)
+#TELNETCONSOLE_ENABLED = False
+
+# Override the default request headers:
+#DEFAULT_REQUEST_HEADERS = {
+#   'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
+#   'Accept-Language': 'en',
+#}
+
+# Enable or disable spider middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+#SPIDER_MIDDLEWARES = {
+#    'noticiasBahia.middlewares.NoticiasbahiaSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'noticiasBahia.middlewares.MyCustomDownloaderMiddleware': 543,
+#}
+
+# Enable or disable extensions
+# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
+#EXTENSIONS = {
+#    'scrapy.extensions.telnet.TelnetConsole': None,
+#}
+
+# Configure item pipelines
+# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
+ITEM_PIPELINES = {
+   'noticiasBahia.pipelines.JsonWriterPipeline': 300,
+}
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See http://doc.scrapy.org/en/latest/topics/autothrottle.html
+#AUTOTHROTTLE_ENABLED = True
+# The initial download delay
+#AUTOTHROTTLE_START_DELAY = 5
+# The maximum download delay to be set in case of high latencies
+#AUTOTHROTTLE_MAX_DELAY = 60
+# The average number of requests Scrapy should be sending in parallel to
+# each remote server
+#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
+# Enable showing throttling stats for every response received:
+#AUTOTHROTTLE_DEBUG = False
+
+# Enable and configure HTTP caching (disabled by default)
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
+#HTTPCACHE_ENABLED = True
+#HTTPCACHE_EXPIRATION_SECS = 0
+#HTTPCACHE_DIR = 'httpcache'
+#HTTPCACHE_IGNORE_HTTP_CODES = []
+#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'

descarga_por_dia/noticiasBahia/noticiasBahia/spiders/__init__.py

+# This package will contain the spiders of your Scrapy project
+#
+# Please refer to the documentation for information on how to create and manage
+# your spiders.

descarga_por_dia/noticiasBahia/noticiasBahia/spiders/noticias.py

+# -*- coding: utf-8 -*-
+import scrapy, re
+from noticiasBahia.items import NoticiasItem
+from datetime import datetime, timedelta, tzinfo
+
+"""
+MEDIO:
+Noticias de la Bahía, Nayarit
+USO:
+scrapy crawl noticias --nolog -s filename=2018-02-01.json -a year=2018 -a month=2 -a day=1
+"""
+
+TAG_RE = re.compile(r'<[^>]+>')
+def remove_tags(text):
+    return TAG_RE.sub('', text)
+
+# LOC_RE = re.compile(r'\n.+?,? ?.+? ?\. ?- ?')
+# G_RE = re.compile(r' ?- ?')
+# EM_RE = re.compile(r'((Email|Correo electr.{1,3}nico|Comentarios?):\s)?[\w.-]+@[\w-]+(\.[a-zA-Z]{2,6}){1,2}\s?')
+# TW_RE = re.compile(r'M.{1,3}s de la P.{1,3}lvora en Twitter: @[\w.%+-]+.', re.I)
+# TW2_RE = re.compile(r'((\| )?Twitter:\s+)?(@[\w.%+-]+.)?', re.I)
+# TAG2_RE = re.compile(r'\ntransition_[^\]]+\]')
+# TAG3_RE = re.compile(r'\[[^\]]+[\]\n]')
+
+
+class UTC(tzinfo):
+    """clase para el 'time zone' (zona horaria)"""
+
+    def utcoffset(self, dt):
+        # zona horaria para nayarit: utc-7
+        return timedelta(hours=-7)
+
+    def tzname(self, dt):
+        # nombre de la zona horaria
+        return 'UTC-6'
+
+
+class QuotesSpider(scrapy.Spider):
+    name = "noticias"
+
+    def start_requests(self):
+        self.tz = UTC()
+        self.year = getattr(self, "year", None)
+        self.month = getattr(self, "month", None)
+        self.day = getattr(self, "day", None)
+        self.date_parser = {"enero": 1,      "febrero": 2,  "marzo": 3,      "abril": 4,
+                            "mayo": 5,       "junio": 6,    "julio": 7,      "agosto": 8,
+                            "septiembre": 9, "octubre": 10, "noviembre": 11, "diciembre": 12}
+
+        self.baseURL = "https://noticiasdelabahia.com/" + self.year + "/" + self.month.zfill(2) + "/" + self.day.zfill(2)
+
+        yield scrapy.Request(url=self.baseURL, callback=self.parse)
+
+
+    def parse(self, response):
+        yield scrapy.Request(url=response.url, callback=self.parse_page, dont_filter=True)
+
+        nextPage = response.xpath('//div[@class="pagination clearfix"]/a[@class="older-posts"]/@href').extract_first()
+        if nextPage is not None:
+            yield scrapy.Request(url=nextPage, callback=self.parse)
+
+
+    def parse_page(self, response):
+        for link in response.xpath('//div[@class="row default-layout"]/article/h2/a/@href').extract():
+            yield scrapy.Request(url=link, callback=self.parse_item)
+
+
+    def parse_item(self, response):
+        item = NoticiasItem()
+        text = ''
+
+        d = response.xpath('//span[@class="date"]').extract_first()
+        d = remove_tags(d).strip().replace(",", '').split()
+        try:
+            dat = datetime(int(d[2]), self.date_parser[d[1].lower()], int(d[0]), tzinfo=self.tz).isoformat("T")
+        except:
+            dat = datetime(int(self.year), int(self.month), int(self.day), tzinfo=self.tz).isoformat("T")
+        item['date'] = dat
+
+        item['title'] = remove_tags(response.xpath('//h1[@class="title"]').extract_first()).strip()
+
+        topic = response.xpath('//div[@class="category-list"]/ul/li/a').extract_first()
+        if topic is not None:
+            item['topic'] = remove_tags(topic).strip()
+
+        author = response.xpath('//span[@class="author"]').extract_first()
+        if author is not None:
+            item['author'] = remove_tags(author).strip()
+
+        for p in response.xpath('//div[@class="post-entry"]/p').extract():
+            text += remove_tags(p) + "\n"
+
+        # result = LOC_RE.search(text)
+        # if result:
+        #     m = result.group(0)
+        #     location = G_RE.sub('', m).strip()
+        #     if len(location) <= 35:
+        #         item['location'] = location
+        #         text = text[text.find(m)+len(m):]
+
+        # text = EM_RE.sub('', text)
+        # text = TW_RE.sub('', text)
+        # text = TW2_RE.sub('', text)
+        # text = TAG2_RE.sub("\n", text)
+        # text = TAG3_RE.sub('', text)
+        item['text'] = text.strip()
+
+        item['url'] = response.url
+
+        yield item

descarga_por_dia/noticiasBahia/scrapy.cfg

+# Automatically created by: scrapy startproject
+#
+# For more information about the [deploy] section see:
+# https://scrapyd.readthedocs.org/en/latest/deploy.html
+
+[settings]
+default = noticiasBahia.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = noticiasBahia

descarga_por_dia/opinionPuebla/opinionPuebla/items.py

+# -*- coding: utf-8 -*-
+
+# Define here the models for your scraped items
+#
+# See documentation in:
+# http://doc.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class NoticiasItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    title = scrapy.Field()
+    text = scrapy.Field()
+    date = scrapy.Field()
+    location = scrapy.Field()
+    author = scrapy.Field()
+    topic = scrapy.Field()
+    url = scrapy.Field()

descarga_por_dia/opinionPuebla/opinionPuebla/middlewares.py

+# -*- coding: utf-8 -*-
+
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# http://doc.scrapy.org/en/latest/topics/spider-middleware.html
+
+from scrapy import signals
+
+
+class OpinionpueblaSpiderMiddleware(object):
+    # Not all methods need to be defined. If a method is not defined,
+    # scrapy acts as if the spider middleware does not modify the
+    # passed objects.
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # This method is used by Scrapy to create your spiders.
+        s = cls()
+        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
+        return s
+
+    def process_spider_input(response, spider):
+        # Called for each response that goes through the spider
+        # middleware and into the spider.
+
+        # Should return None or raise an exception.
+        return None
+
+    def process_spider_output(response, result, spider):
+        # Called with the results returned from the Spider, after
+        # it has processed the response.
+
+        # Must return an iterable of Request, dict or Item objects.
+        for i in result:
+            yield i
+
+    def process_spider_exception(response, exception, spider):
+        # Called when a spider or process_spider_input() method
+        # (from other spider middleware) raises an exception.
+
+        # Should return either None or an iterable of Response, dict
+        # or Item objects.
+        pass
+
+    def process_start_requests(start_requests, spider):
+        # Called with the start requests of the spider, and works
+        # similarly to the process_spider_output() method, except
+        # that it doesn’t have a response associated.
+
+        # Must return only requests (not items).
+        for r in start_requests:
+            yield r
+
+    def spider_opened(self, spider):
+        spider.logger.info('Spider opened: %s' % spider.name)

descarga_por_dia/opinionPuebla/opinionPuebla/pipelines.py

+# -*- coding: utf-8 -*-
+
+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html
+
+import json
+from collections import OrderedDict
+
+
+class JsonWriterPipeline(object):
+
+    def __init__(self, filename):
+        self.filename = filename
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # Here you get whatever value was passed through the "filename" command line parameter
+        settings = crawler.settings
+        filename = settings.get('filename')
+
+        # Instantiate the pipeline with the file name
+        return cls(filename)
+
+    def open_spider(self, spider):
+        self.counter = 0
+        self.file = open(self.filename, 'w')
+        self.file.write("[")
+
+    def close_spider(self, spider):
+        self.file.write("]")
+        self.file.close()
+
+    def process_item(self, item, spider):
+        # print("this is my item", item)
+        row = []
+        try:
+            row.append(("date", item['date']))
+        except:
+            pass
+        try:
+            row.append(("topic", item['topic']))
+        except:
+            pass
+        try:
+            row.append(("title", item['title']))
+        except:
+            pass
+        try:
+            row.append(("author", item['author']))
+        except:
+            pass
+        try:
+            row.append(("location", item['location']))
+        except:
+            pass
+        try:
+            row.append(("text", item['text']))
+        except:
+            pass
+        try:
+            row.append(("url", item['url']))
+        except:
+            pass
+
+        line = OrderedDict(row)
+
+        self.counter += 1
+        if self.counter == 1:
+            self.file.write(json.dumps(line))
+        elif self.counter > 1:
+            self.file.write(",\n" + json.dumps(line))
+
+        return item

descarga_por_dia/opinionPuebla/opinionPuebla/settings.py

+# -*- coding: utf-8 -*-
+
+# Scrapy settings for opinionPuebla project
+#
+# For simplicity, this file contains only settings considered important or
+# commonly used. You can find more settings consulting the documentation:
+#
+#     http://doc.scrapy.org/en/latest/topics/settings.html
+#     http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#     http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+
+BOT_NAME = 'opinionPuebla'
+
+SPIDER_MODULES = ['opinionPuebla.spiders']
+NEWSPIDER_MODULE = 'opinionPuebla.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'opinionPuebla (+http://www.yourdomain.com)'
+
+# Obey robots.txt rules
+# ROBOTSTXT_OBEY = True
+
+# Configure maximum concurrent requests performed by Scrapy (default: 16)
+#CONCURRENT_REQUESTS = 32
+
+# Configure a delay for requests for the same website (default: 0)
+# See http://scrapy.readthedocs.org/en/latest/topics/settings.html#download-delay
+# See also autothrottle settings and docs
+DOWNLOAD_DELAY = 0.5
+# The download delay setting will honor only one of:
+#CONCURRENT_REQUESTS_PER_DOMAIN = 16
+#CONCURRENT_REQUESTS_PER_IP = 16
+
+# Disable cookies (enabled by default)
+COOKIES_ENABLED = False
+
+# Disable Telnet Console (enabled by default)
+#TELNETCONSOLE_ENABLED = False
+
+# Override the default request headers:
+#DEFAULT_REQUEST_HEADERS = {
+#   'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
+#   'Accept-Language': 'en',
+#}
+
+# Enable or disable spider middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+#SPIDER_MIDDLEWARES = {
+#    'opinionPuebla.middlewares.OpinionpueblaSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'opinionPuebla.middlewares.MyCustomDownloaderMiddleware': 543,
+#}
+
+# Enable or disable extensions
+# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
+#EXTENSIONS = {
+#    'scrapy.extensions.telnet.TelnetConsole': None,
+#}
+
+# Configure item pipelines
+# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
+ITEM_PIPELINES = {
+   'opinionPuebla.pipelines.JsonWriterPipeline': 300,
+}
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See http://doc.scrapy.org/en/latest/topics/autothrottle.html
+#AUTOTHROTTLE_ENABLED = True
+# The initial download delay
+#AUTOTHROTTLE_START_DELAY = 5
+# The maximum download delay to be set in case of high latencies
+#AUTOTHROTTLE_MAX_DELAY = 60
+# The average number of requests Scrapy should be sending in parallel to
+# each remote server
+#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
+# Enable showing throttling stats for every response received:
+#AUTOTHROTTLE_DEBUG = False
+
+# Enable and configure HTTP caching (disabled by default)
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
+#HTTPCACHE_ENABLED = True
+#HTTPCACHE_EXPIRATION_SECS = 0
+#HTTPCACHE_DIR = 'httpcache'
+#HTTPCACHE_IGNORE_HTTP_CODES = []
+#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'

descarga_por_dia/opinionPuebla/opinionPuebla/spiders/__init__.py

+# This package will contain the spiders of your Scrapy project
+#
+# Please refer to the documentation for information on how to create and manage
+# your spiders.

descarga_por_dia/opinionPuebla/opinionPuebla/spiders/noticias.py

+# -*- coding: utf-8 -*-
+import scrapy, re
+from opinionPuebla.items import NoticiasItem
+from datetime import datetime, date, timedelta, tzinfo
+
+"""
+MEDIO:
+La Opinión de Puebla
+USO:
+scrapy crawl noticias --nolog -s filename=2018-02-04.json -a year=2018 -a month=2 -a day=4
+"""
+
+TAG_RE = re.compile(r'<[^>]+>')
+def remove_tags(text):
+    return TAG_RE.sub('', text)
+
+# LOC_RE = re.compile(r'\n.+?,? ?.+? ?\. ?- ?')
+# G_RE = re.compile(r' ?- ?')
+# EM_RE = re.compile(r'((Email|Correo electr.{1,3}nico|Comentarios?):\s)?[\w.-]+@[\w-]+(\.[a-zA-Z]{2,6}){1,2}\s?')
+# TW_RE = re.compile(r'M.{1,3}s de la P.{1,3}lvora en Twitter: @[\w.%+-]+.', re.I)
+# TW2_RE = re.compile(r'((\| )?Twitter:\s+)?(@[\w.%+-]+.)?', re.I)
+# TAG2_RE = re.compile(r'\ntransition_[^\]]+\]')
+# TAG3_RE = re.compile(r'\[[^\]]+[\]\n]')
+
+
+class UTC(tzinfo):
+	"""clase para el 'time zone' (zona horaria)"""
+
+	def utcoffset(self, dt):
+		# zona horaria para puebla: utc-6
+		return timedelta(hours=-6)
+
+	def tzname(self, dt):
+		# nombre de la zona horaria
+		return 'UTC-6'
+
+
+class QuotesSpider(scrapy.Spider):
+    name = "noticias"
+
+    def start_requests(self):
+        self.tz = UTC()
+        self.year = getattr(self, "year", None)
+        self.month = getattr(self, "month", None)
+        self.day = getattr(self, "day", None)
+
+        self.date_parser = {"enero": 1,      "febrero": 2,  "marzo": 3,      "abril": 4,
+                            "mayo": 5,       "junio": 6,    "julio": 7,      "agosto": 8,
+                            "septiembre": 9, "octubre": 10, "noviembre": 11, "diciembre": 12}
+
+        self.baseURL = "http://www.laopinionpuebla.com/" + self.year + "/" + self.month.zfill(2) + "/" + self.day.zfill(2)
+
+        yield scrapy.Request(url=self.baseURL, callback=self.parse)
+
+
+    def parse(self, response):
+        yield scrapy.Request(url=response.url, callback=self.parse_page, dont_filter=True)
+
+        pagination = response.xpath('//ul[@class="page-numbers"]/li/a/@href').extract()
+        if len(pagination) > 0:
+            pagination = pagination[-1]
+            pages = int(pagination[pagination.rfind("=") + 1:])
+
+            for page in range(1, pages):
+                yield scrapy.Request(url=self.baseURL + '/page/' + str(page + 1), callback=self.parse_page)
+
+
+    def parse_page(self, response):
+        for link in response.xpath('//div[@id="content"]').css('h2').xpath('./a/@href').extract():
+            yield scrapy.Request(url=link, callback=self.parse_item)
+
+
+    def parse_item(self, response):
+        item = NoticiasItem()
+        text = ''
+        CHANGE_HOUR = False
+
+        try:
+            res = response.xpath('//ul[@class="post-meta post"]/li[@class="date"]').extract_first()
+            res = remove_tags(res)
+            if res.rfind("pm") > -1: CHANGE_HOUR = True
+            res = res.replace(" am", '').replace(" pm", '').replace(",", '').split()
+            t = map(int, res[-1].split(":"))
+            if CHANGE_HOUR: t[0] += 12
+            del res[-1]
+            d = res
+            dat = datetime(int(d[2]), self.date_parser[d[1].lower()], int(d[0]), t[0], t[1], 0, tzinfo=self.tz).isoformat("T")
+        except:
+            dat = datetime(int(self.year), int(self.month), int(self.day), tzinfo=self.tz).isoformat("T")
+        item['date'] = dat
+
+        item['title'] = remove_tags(response.xpath('//div[@id="content"]').css('h1.post-heading').extract_first()).strip()
+
+        topic = response.css('ul.post-meta').css('li.cat').css('a').extract_first()
+        if topic is not None:
+            item['topic'] = remove_tags(topic)
+
+        for p in response.xpath('//div[@class="post-content"]').css('p').extract():
+            text += remove_tags(p) + "\n"
+
+        # result = LOC_RE.search(text)
+        # if result:
+        #     m = result.group(0)
+        #     location = G_RE.sub('', m).strip()
+        #     if len(location) <= 35:
+        #         item['location'] = location
+        #         text = text[text.find(m)+len(m):]
+
+        # text = EM_RE.sub('', text)
+        # text = TW_RE.sub('', text)
+        # text = TW2_RE.sub('', text)
+        # text = TAG2_RE.sub("\n", text)
+        # text = TAG3_RE.sub('', text)
+        item['text'] = text.strip()
+
+        item['url'] = response.url
+
+        yield item

descarga_por_dia/opinionPuebla/scrapy.cfg

+# Automatically created by: scrapy startproject
+#
+# For more information about the [deploy] section see:
+# https://scrapyd.readthedocs.org/en/latest/deploy.html
+
+[settings]
+default = opinionPuebla.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = opinionPuebla

descarga_por_dia/periodicoEnfoque/periodicoEnfoque/items.py

+# -*- coding: utf-8 -*-
+
+# Define here the models for your scraped items
+#
+# See documentation in:
+# http://doc.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class NoticiasItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    title = scrapy.Field()
+    text = scrapy.Field()
+    date = scrapy.Field()
+    location = scrapy.Field()
+    author = scrapy.Field()
+    topic = scrapy.Field()
+    url = scrapy.Field()

descarga_por_dia/periodicoEnfoque/periodicoEnfoque/middlewares.py

+# -*- coding: utf-8 -*-
+
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# http://doc.scrapy.org/en/latest/topics/spider-middleware.html
+
+from scrapy import signals
+
+
+class PeriodicoenfoqueSpiderMiddleware(object):
+    # Not all methods need to be defined. If a method is not defined,
+    # scrapy acts as if the spider middleware does not modify the
+    # passed objects.
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # This method is used by Scrapy to create your spiders.
+        s = cls()
+        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
+        return s
+
+    def process_spider_input(response, spider):
+        # Called for each response that goes through the spider
+        # middleware and into the spider.
+
+        # Should return None or raise an exception.
+        return None
+
+    def process_spider_output(response, result, spider):
+        # Called with the results returned from the Spider, after
+        # it has processed the response.
+
+        # Must return an iterable of Request, dict or Item objects.
+        for i in result:
+            yield i
+
+    def process_spider_exception(response, exception, spider):
+        # Called when a spider or process_spider_input() method
+        # (from other spider middleware) raises an exception.
+
+        # Should return either None or an iterable of Response, dict
+        # or Item objects.
+        pass
+
+    def process_start_requests(start_requests, spider):
+        # Called with the start requests of the spider, and works
+        # similarly to the process_spider_output() method, except
+        # that it doesn’t have a response associated.
+
+        # Must return only requests (not items).
+        for r in start_requests:
+            yield r
+
+    def spider_opened(self, spider):
+        spider.logger.info('Spider opened: %s' % spider.name)

descarga_por_dia/periodicoEnfoque/periodicoEnfoque/pipelines.py

+# -*- coding: utf-8 -*-
+
+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html
+
+import json
+from collections import OrderedDict
+
+
+class JsonWriterPipeline(object):
+
+    def __init__(self, filename):
+        self.filename = filename
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # Here you get whatever value was passed through the "filename" command line parameter
+        settings = crawler.settings
+        filename = settings.get('filename')
+
+        # Instantiate the pipeline with the file name
+        return cls(filename)
+
+    def open_spider(self, spider):
+        self.counter = 0
+        self.file = open(self.filename, 'w')
+        self.file.write("[")
+
+    def close_spider(self, spider):
+        self.file.write("]")
+        self.file.close()
+
+    def process_item(self, item, spider):
+        # print("this is my item", item)
+        row = []
+        try:
+            row.append(("date", item['date']))
+        except:
+            pass
+        try:
+            row.append(("topic", item['topic']))
+        except:
+            pass
+        try:
+            row.append(("title", item['title']))
+        except:
+            pass
+        try:
+            row.append(("author", item['author']))
+        except:
+            pass
+        try:
+            row.append(("location", item['location']))
+        except:
+            pass
+        try:
+            row.append(("text", item['text']))
+        except:
+            pass
+        try:
+            row.append(("url", item['url']))
+        except:
+            pass
+
+        line = OrderedDict(row)
+
+        self.counter += 1
+        if self.counter == 1:
+            self.file.write(json.dumps(line))
+        elif self.counter > 1:
+            self.file.write(",\n" + json.dumps(line))
+
+        return item

descarga_por_dia/periodicoEnfoque/periodicoEnfoque/settings.py

+# -*- coding: utf-8 -*-
+
+# Scrapy settings for periodicoEnfoque project
+#
+# For simplicity, this file contains only settings considered important or
+# commonly used. You can find more settings consulting the documentation:
+#
+#     http://doc.scrapy.org/en/latest/topics/settings.html
+#     http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#     http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+
+BOT_NAME = 'periodicoEnfoque'
+
+SPIDER_MODULES = ['periodicoEnfoque.spiders']
+NEWSPIDER_MODULE = 'periodicoEnfoque.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'periodicoEnfoque (+http://www.yourdomain.com)'
+
+# Obey robots.txt rules
+# ROBOTSTXT_OBEY = True
+
+# Configure maximum concurrent requests performed by Scrapy (default: 16)
+#CONCURRENT_REQUESTS = 32
+
+# Configure a delay for requests for the same website (default: 0)
+# See http://scrapy.readthedocs.org/en/latest/topics/settings.html#download-delay
+# See also autothrottle settings and docs
+DOWNLOAD_DELAY = 0.5
+# The download delay setting will honor only one of:
+#CONCURRENT_REQUESTS_PER_DOMAIN = 16
+#CONCURRENT_REQUESTS_PER_IP = 16
+
+# Disable cookies (enabled by default)
+COOKIES_ENABLED = False
+
+# Disable Telnet Console (enabled by default)
+#TELNETCONSOLE_ENABLED = False
+
+# Override the default request headers:
+#DEFAULT_REQUEST_HEADERS = {
+#   'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
+#   'Accept-Language': 'en',
+#}
+
+# Enable or disable spider middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+#SPIDER_MIDDLEWARES = {
+#    'periodicoEnfoque.middlewares.PeriodicoenfoqueSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'periodicoEnfoque.middlewares.MyCustomDownloaderMiddleware': 543,
+#}
+
+# Enable or disable extensions
+# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
+#EXTENSIONS = {
+#    'scrapy.extensions.telnet.TelnetConsole': None,
+#}
+
+# Configure item pipelines
+# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
+ITEM_PIPELINES = {
+   'periodicoEnfoque.pipelines.JsonWriterPipeline': 300,
+}
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See http://doc.scrapy.org/en/latest/topics/autothrottle.html
+#AUTOTHROTTLE_ENABLED = True
+# The initial download delay
+#AUTOTHROTTLE_START_DELAY = 5
+# The maximum download delay to be set in case of high latencies
+#AUTOTHROTTLE_MAX_DELAY = 60
+# The average number of requests Scrapy should be sending in parallel to
+# each remote server
+#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
+# Enable showing throttling stats for every response received:
+#AUTOTHROTTLE_DEBUG = False
+
+# Enable and configure HTTP caching (disabled by default)
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
+#HTTPCACHE_ENABLED = True
+#HTTPCACHE_EXPIRATION_SECS = 0
+#HTTPCACHE_DIR = 'httpcache'
+#HTTPCACHE_IGNORE_HTTP_CODES = []
+#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'

descarga_por_dia/periodicoEnfoque/periodicoEnfoque/spiders/__init__.py

+# This package will contain the spiders of your Scrapy project
+#
+# Please refer to the documentation for information on how to create and manage
+# your spiders.

descarga_por_dia/periodicoEnfoque/periodicoEnfoque/spiders/noticias.py

+# -*- coding: utf-8 -*-
+import scrapy, re
+from periodicoEnfoque.items import NoticiasItem
+from datetime import datetime, date, timedelta, tzinfo
+
+"""
+MEDIO:
+Periódico Enfoque Informativo, Nayarit
+USO:
+scrapy crawl noticias --nolog -s filename=2018-02-04.json -a year=2018 -a month=2 -a day=4
+"""
+
+TAG_RE = re.compile(r'<[^>]+>')
+def remove_tags(text):
+    return TAG_RE.sub('', text)
+
+# LOC_RE = re.compile(r'\n.+?,? ?.+? ?\. ?- ?')
+# G_RE = re.compile(r' ?- ?')
+# EM_RE = re.compile(r'((Email|Correo electr.{1,3}nico|Comentarios?):\s)?[\w.-]+@[\w-]+(\.[a-zA-Z]{2,6}){1,2}\s?')
+# TW_RE = re.compile(r'M.{1,3}s de la P.{1,3}lvora en Twitter: @[\w.%+-]+.', re.I)
+# TW2_RE = re.compile(r'((\| )?Twitter:\s+)?(@[\w.%+-]+.)?', re.I)
+# TAG2_RE = re.compile(r'\ntransition_[^\]]+\]')
+# TAG3_RE = re.compile(r'\[[^\]]+[\]\n]')
+
+
+class UTC(tzinfo):
+	"""clase para el 'time zone' (zona horaria)"""
+
+	def utcoffset(self, dt):
+		# zona horaria para nayarit: utc-7
+		return timedelta(hours=-7)
+
+	def tzname(self, dt):
+		# nombre de la zona horaria
+		return 'UTC-6'
+
+
+class QuotesSpider(scrapy.Spider):
+    name = "noticias"
+
+    def start_requests(self):
+        self.tz = UTC()
+        self.year = getattr(self, "year", None)
+        self.month = getattr(self, "month", None)
+        self.day = getattr(self, "day", None)
+
+        self.baseURL = "https://enfoquenayarit.com/" + self.year + "/" + self.month.zfill(2) + "/" + self.day.zfill(2)
+
+        yield scrapy.Request(url=self.baseURL, callback=self.parse)
+
+
+    def parse(self, response):
+        yield scrapy.Request(url=response.url, callback=self.parse_page, dont_filter=True)
+
+        nextPage = response.xpath('//div[@class="post_pagination"]/a[@class="next page-numbers"]/@href').extract_first()
+        if nextPage is not None:
+            yield scrapy.Request(url=nextPage, callback=self.parse)
+
+
+    def parse_page(self, response):
+        for link in response.xpath('//div[@class="wa-block-news-recent"]').css('h3').css('a::attr(href)').extract():
+            yield scrapy.Request(url=link, callback=self.parse_item)
+
+
+    def parse_item(self, response):
+        item = NoticiasItem()
+        text = ''
+
+        try:
+            res = response.xpath('//div[@class="entry-meta"]').css('time::attr(datetime)').extract_first()
+            d,t = res.split()
+            d = map(int, d.split("-"))
+            t = map(int, t.split(":"))
+            dat = datetime(d[0], d[1], d[2], t[0], t[1], t[2], tzinfo=self.tz).isoformat("T")
+        except:
+            dat = datetime(int(self.year), int(self.month), int(self.day), tzinfo=self.tz).isoformat("T")
+        item['date'] = dat
+
+        item['title'] = remove_tags(response.xpath('//div[@class="wa-post-header"]/div/h1[@class="entry-title"]/a').extract_first()).strip()
+
+        item['topic'] = response.xpath('//ul[@class="wa-ul-breadcumb"]/li/a/text()').extract()[-1]
+
+        author = response.xpath('//span[@itemprop="author"]/text()').extract_first()
+        if author is not None:
+            item['author'] = author
+
+        for p in response.xpath('//div[@class="entry-content"]').css('p').extract():
+            text += remove_tags(p) + "\n"
+
+        # result = LOC_RE.search(text)
+        # if result:
+        #     m = result.group(0)
+        #     location = G_RE.sub('', m).strip()
+        #     if len(location) <= 35:
+        #         item['location'] = location
+        #         text = text[text.find(m)+len(m):]
+
+        # text = EM_RE.sub('', text)
+        # text = TW_RE.sub('', text)
+        # text = TW2_RE.sub('', text)
+        # text = TAG2_RE.sub("\n", text)
+        # text = TAG3_RE.sub('', text)
+        item['text'] = text.strip()
+
+        item['url'] = response.url
+
+        yield item

descarga_por_dia/periodicoEnfoque/scrapy.cfg

+# Automatically created by: scrapy startproject
+#
+# For more information about the [deploy] section see:
+# https://scrapyd.readthedocs.org/en/latest/deploy.html
+
+[settings]
+default = periodicoEnfoque.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = periodicoEnfoque

descarga_por_dia/periodicoExpress/periodicoExpress/items.py

+# -*- coding: utf-8 -*-
+
+# Define here the models for your scraped items
+#
+# See documentation in:
+# http://doc.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class NoticiasItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    title = scrapy.Field()
+    text = scrapy.Field()
+    date = scrapy.Field()
+    location = scrapy.Field()
+    author = scrapy.Field()
+    topic = scrapy.Field()
+    url = scrapy.Field()

descarga_por_dia/periodicoExpress/periodicoExpress/middlewares.py

+# -*- coding: utf-8 -*-
+
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# http://doc.scrapy.org/en/latest/topics/spider-middleware.html
+
+from scrapy import signals
+
+
+class PeriodicoexpressSpiderMiddleware(object):
+    # Not all methods need to be defined. If a method is not defined,
+    # scrapy acts as if the spider middleware does not modify the
+    # passed objects.
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # This method is used by Scrapy to create your spiders.
+        s = cls()
+        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
+        return s
+
+    def process_spider_input(response, spider):
+        # Called for each response that goes through the spider
+        # middleware and into the spider.
+
+        # Should return None or raise an exception.
+        return None
+
+    def process_spider_output(response, result, spider):
+        # Called with the results returned from the Spider, after
+        # it has processed the response.
+
+        # Must return an iterable of Request, dict or Item objects.
+        for i in result:
+            yield i
+
+    def process_spider_exception(response, exception, spider):
+        # Called when a spider or process_spider_input() method
+        # (from other spider middleware) raises an exception.
+
+        # Should return either None or an iterable of Response, dict
+        # or Item objects.
+        pass
+
+    def process_start_requests(start_requests, spider):
+        # Called with the start requests of the spider, and works
+        # similarly to the process_spider_output() method, except
+        # that it doesn’t have a response associated.
+
+        # Must return only requests (not items).
+        for r in start_requests:
+            yield r
+
+    def spider_opened(self, spider):
+        spider.logger.info('Spider opened: %s' % spider.name)

descarga_por_dia/periodicoExpress/periodicoExpress/pipelines.py

+# -*- coding: utf-8 -*-
+
+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html
+
+import json
+from collections import OrderedDict
+
+
+class JsonWriterPipeline(object):
+
+    def __init__(self, filename):
+        self.filename = filename
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # Here you get whatever value was passed through the "filename" command line parameter
+        settings = crawler.settings
+        filename = settings.get('filename')
+
+        # Instantiate the pipeline with the file name
+        return cls(filename)
+
+    def open_spider(self, spider):
+        self.counter = 0
+        self.file = open(self.filename, 'w')
+        self.file.write("[")
+
+    def close_spider(self, spider):
+        self.file.write("]")
+        self.file.close()
+
+    def process_item(self, item, spider):
+        # print("this is my item", item)
+        row = []
+        try:
+            row.append(("date", item['date']))
+        except:
+            pass
+        try:
+            row.append(("topic", item['topic']))
+        except:
+            pass
+        try:
+            row.append(("title", item['title']))
+        except:
+            pass
+        try:
+            row.append(("author", item['author']))
+        except:
+            pass
+        try:
+            row.append(("location", item['location']))
+        except:
+            pass
+        try:
+            row.append(("text", item['text']))
+        except:
+            pass
+        try:
+            row.append(("url", item['url']))
+        except:
+            pass
+
+        line = OrderedDict(row)
+
+        self.counter += 1
+        if self.counter == 1:
+            self.file.write(json.dumps(line))
+        elif self.counter > 1:
+            self.file.write(",\n" + json.dumps(line))
+
+        return item

descarga_por_dia/periodicoExpress/periodicoExpress/settings.py

+# -*- coding: utf-8 -*-
+
+# Scrapy settings for periodicoExpress project
+#
+# For simplicity, this file contains only settings considered important or
+# commonly used. You can find more settings consulting the documentation:
+#
+#     http://doc.scrapy.org/en/latest/topics/settings.html
+#     http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#     http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+
+BOT_NAME = 'periodicoExpress'
+
+SPIDER_MODULES = ['periodicoExpress.spiders']
+NEWSPIDER_MODULE = 'periodicoExpress.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'periodicoExpress (+http://www.yourdomain.com)'
+
+# Obey robots.txt rules
+# ROBOTSTXT_OBEY = True
+
+# Configure maximum concurrent requests performed by Scrapy (default: 16)
+#CONCURRENT_REQUESTS = 32
+
+# Configure a delay for requests for the same website (default: 0)
+# See http://scrapy.readthedocs.org/en/latest/topics/settings.html#download-delay
+# See also autothrottle settings and docs
+DOWNLOAD_DELAY = 0.5
+# The download delay setting will honor only one of:
+#CONCURRENT_REQUESTS_PER_DOMAIN = 16
+#CONCURRENT_REQUESTS_PER_IP = 16
+
+# Disable cookies (enabled by default)
+COOKIES_ENABLED = False
+
+# Disable Telnet Console (enabled by default)
+#TELNETCONSOLE_ENABLED = False
+
+# Override the default request headers:
+#DEFAULT_REQUEST_HEADERS = {
+#   'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
+#   'Accept-Language': 'en',
+#}
+
+# Enable or disable spider middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+#SPIDER_MIDDLEWARES = {
+#    'periodicoExpress.middlewares.PeriodicoexpressSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'periodicoExpress.middlewares.MyCustomDownloaderMiddleware': 543,
+#}
+
+# Enable or disable extensions
+# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
+#EXTENSIONS = {
+#    'scrapy.extensions.telnet.TelnetConsole': None,
+#}
+
+# Configure item pipelines
+# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
+ITEM_PIPELINES = {
+   'periodicoExpress.pipelines.JsonWriterPipeline': 300,
+}
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See http://doc.scrapy.org/en/latest/topics/autothrottle.html
+#AUTOTHROTTLE_ENABLED = True
+# The initial download delay
+#AUTOTHROTTLE_START_DELAY = 5
+# The maximum download delay to be set in case of high latencies
+#AUTOTHROTTLE_MAX_DELAY = 60
+# The average number of requests Scrapy should be sending in parallel to
+# each remote server
+#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
+# Enable showing throttling stats for every response received:
+#AUTOTHROTTLE_DEBUG = False
+
+# Enable and configure HTTP caching (disabled by default)
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
+#HTTPCACHE_ENABLED = True
+#HTTPCACHE_EXPIRATION_SECS = 0
+#HTTPCACHE_DIR = 'httpcache'
+#HTTPCACHE_IGNORE_HTTP_CODES = []
+#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'

descarga_por_dia/periodicoExpress/periodicoExpress/spiders/__init__.py

+# This package will contain the spiders of your Scrapy project
+#
+# Please refer to the documentation for information on how to create and manage
+# your spiders.

descarga_por_dia/periodicoExpress/periodicoExpress/spiders/noticias.py

+# -*- coding: utf-8 -*-
+import scrapy, re
+from periodicoExpress.items import NoticiasItem
+
+"""
+MEDIO:
+Periódico Express, Nayarit
+USO:
+scrapy crawl noticias --nolog -s filename=2018-02-04.json -a year=2018 -a month=2 -a day=4
+"""
+
+TAG_RE = re.compile(r'<[^>]+>')
+def remove_tags(text):
+    return TAG_RE.sub('', text)
+
+# LOC_RE = re.compile(r'\n.+?,? ?.+? ?\. ?- ?')
+# G_RE = re.compile(r' ?- ?')
+# EM_RE = re.compile(r'((Email|Correo electr.{1,3}nico|Comentarios?):\s)?[\w.-]+@[\w-]+(\.[a-zA-Z]{2,6}){1,2}\s?')
+# TW_RE = re.compile(r'M.{1,3}s de la P.{1,3}lvora en Twitter: @[\w.%+-]+.', re.I)
+# TW2_RE = re.compile(r'((\| )?Twitter:\s+)?(@[\w.%+-]+.)?', re.I)
+# TAG2_RE = re.compile(r'\ntransition_[^\]]+\]')
+# TAG3_RE = re.compile(r'\[[^\]]+[\]\n]')
+
+class QuotesSpider(scrapy.Spider):
+    name = "noticias"
+
+    def start_requests(self):
+        year = getattr(self, "year", None)
+        month = getattr(self, "month", None)
+        day = getattr(self, "day", None)
+
+        self.baseURL = "http://www.periodicoexpress.com.mx/" + year + "/" + month.zfill(2) + "/" + day.zfill(2)
+
+        yield scrapy.Request(url=self.baseURL, callback=self.parse)
+
+
+    def parse(self, response):
+        yield scrapy.Request(url=response.url, callback=self.parse_page, dont_filter=True)
+
+        nextPage = response.xpath('//div[@class="nav-load"]/a/@href').extract_first()
+        if nextPage is None:
+            nextPage = response.xpath('//div[@class="nav-previous"]/a/@href').extract_first()
+        if nextPage is not None:
+            yield scrapy.Request(url=nextPage, callback=self.parse)
+
+
+    def parse_page(self, response):
+        for link in response.xpath('//div[@id="agnes-list-feed"]').css('h2.entry-title').xpath('./a/@href').extract():
+            yield scrapy.Request(url=link, callback=self.parse_item)
+
+
+    def parse_item(self, response):
+        item = NoticiasItem()
+        text = ''
+
+        "La fecha obtenida ya incluye formato y zona horaria"
+        item['date'] = response.xpath('//div[@class="entry-meta"]/a/time[@class="entry-date published"]/@datetime').extract_first()
+        item['title'] = remove_tags(response.xpath('//h2[@class="entry-title"]/a').extract_first()).strip()
+
+        topic = response.xpath('//div[@class="agnes-color-cat color-cats"]/a').extract_first()
+        if topic is not None:
+            item['topic'] = remove_tags(topic)
+
+        for p in response.xpath('//div[@class="entry-content"]').css('p').extract():
+            text += remove_tags(p) + "\n"
+
+        # result = LOC_RE.search(text)
+        # if result:
+        #     m = result.group(0)
+        #     location = G_RE.sub('', m).strip()
+        #     if len(location) <= 35:
+        #         item['location'] = location
+        #         text = text[text.find(m)+len(m):]
+
+        # text = EM_RE.sub('', text)
+        # text = TW_RE.sub('', text)
+        # text = TW2_RE.sub('', text)
+        # text = TAG2_RE.sub("\n", text)
+        # text = TAG3_RE.sub('', text)
+        item['text'] = text.strip()
+
+        item['url'] = response.url
+
+        yield item

descarga_por_dia/periodicoExpress/scrapy.cfg

+# Automatically created by: scrapy startproject
+#
+# For more information about the [deploy] section see:
+# https://scrapyd.readthedocs.org/en/latest/deploy.html
+
+[settings]
+default = periodicoExpress.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = periodicoExpress

descarga_por_dia/redCrucero/redCrucero/items.py

+# -*- coding: utf-8 -*-
+
+# Define here the models for your scraped items
+#
+# See documentation in:
+# http://doc.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class NoticiasItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    title = scrapy.Field()
+    text = scrapy.Field()
+    date = scrapy.Field()
+    location = scrapy.Field()
+    author = scrapy.Field()
+    topic = scrapy.Field()
+    url = scrapy.Field()

descarga_por_dia/redCrucero/redCrucero/middlewares.py

+# -*- coding: utf-8 -*-
+
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# http://doc.scrapy.org/en/latest/topics/spider-middleware.html
+
+from scrapy import signals
+
+
+class RedcruceroSpiderMiddleware(object):
+    # Not all methods need to be defined. If a method is not defined,
+    # scrapy acts as if the spider middleware does not modify the
+    # passed objects.
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # This method is used by Scrapy to create your spiders.
+        s = cls()
+        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
+        return s
+
+    def process_spider_input(response, spider):
+        # Called for each response that goes through the spider
+        # middleware and into the spider.
+
+        # Should return None or raise an exception.
+        return None
+
+    def process_spider_output(response, result, spider):
+        # Called with the results returned from the Spider, after
+        # it has processed the response.
+
+        # Must return an iterable of Request, dict or Item objects.
+        for i in result:
+            yield i
+
+    def process_spider_exception(response, exception, spider):
+        # Called when a spider or process_spider_input() method
+        # (from other spider middleware) raises an exception.
+
+        # Should return either None or an iterable of Response, dict
+        # or Item objects.
+        pass
+
+    def process_start_requests(start_requests, spider):
+        # Called with the start requests of the spider, and works
+        # similarly to the process_spider_output() method, except
+        # that it doesn’t have a response associated.
+
+        # Must return only requests (not items).
+        for r in start_requests:
+            yield r
+
+    def spider_opened(self, spider):
+        spider.logger.info('Spider opened: %s' % spider.name)

descarga_por_dia/redCrucero/redCrucero/pipelines.py

+# -*- coding: utf-8 -*-
+
+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html
+
+import json
+from collections import OrderedDict
+
+
+class JsonWriterPipeline(object):
+
+    def __init__(self, filename):
+        self.filename = filename
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # Here you get whatever value was passed through the "filename" command line parameter
+        settings = crawler.settings
+        filename = settings.get('filename')
+
+        # Instantiate the pipeline with the file name
+        return cls(filename)
+
+    def open_spider(self, spider):
+        self.counter = 0
+        self.file = open(self.filename, 'w')
+        self.file.write("[")
+
+    def close_spider(self, spider):
+        self.file.write("]")
+        self.file.close()
+
+    def process_item(self, item, spider):
+        # print("this is my item", item)
+        row = []
+        try:
+            row.append(("date", item['date']))
+        except:
+            pass
+        try:
+            row.append(("topic", item['topic']))
+        except:
+            pass
+        try:
+            row.append(("title", item['title']))
+        except:
+            pass
+        try:
+            row.append(("author", item['author']))
+        except:
+            pass
+        try:
+            row.append(("location", item['location']))
+        except:
+            pass
+        try:
+            row.append(("text", item['text']))
+        except:
+            pass
+        try:
+            row.append(("url", item['url']))
+        except:
+            pass
+
+        line = OrderedDict(row)
+
+        self.counter += 1
+        if self.counter == 1:
+            self.file.write(json.dumps(line))
+        elif self.counter > 1:
+            self.file.write(",\n" + json.dumps(line))
+
+        return item

descarga_por_dia/redCrucero/redCrucero/settings.py

+# -*- coding: utf-8 -*-
+
+# Scrapy settings for redCrucero project
+#
+# For simplicity, this file contains only settings considered important or
+# commonly used. You can find more settings consulting the documentation:
+#
+#     http://doc.scrapy.org/en/latest/topics/settings.html
+#     http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#     http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+
+BOT_NAME = 'redCrucero'
+
+SPIDER_MODULES = ['redCrucero.spiders']
+NEWSPIDER_MODULE = 'redCrucero.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'redCrucero (+http://www.yourdomain.com)'
+
+# Obey robots.txt rules
+# ROBOTSTXT_OBEY = True
+
+# Configure maximum concurrent requests performed by Scrapy (default: 16)
+#CONCURRENT_REQUESTS = 32
+
+# Configure a delay for requests for the same website (default: 0)
+# See http://scrapy.readthedocs.org/en/latest/topics/settings.html#download-delay
+# See also autothrottle settings and docs
+DOWNLOAD_DELAY = 0.5
+# The download delay setting will honor only one of:
+#CONCURRENT_REQUESTS_PER_DOMAIN = 16
+#CONCURRENT_REQUESTS_PER_IP = 16
+
+# Disable cookies (enabled by default)
+COOKIES_ENABLED = False
+
+# Disable Telnet Console (enabled by default)
+#TELNETCONSOLE_ENABLED = False
+
+# Override the default request headers:
+#DEFAULT_REQUEST_HEADERS = {
+#   'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
+#   'Accept-Language': 'en',
+#}
+
+# Enable or disable spider middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+#SPIDER_MIDDLEWARES = {
+#    'redCrucero.middlewares.RedcruceroSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'redCrucero.middlewares.MyCustomDownloaderMiddleware': 543,
+#}
+
+# Enable or disable extensions
+# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
+#EXTENSIONS = {
+#    'scrapy.extensions.telnet.TelnetConsole': None,
+#}
+
+# Configure item pipelines
+# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
+ITEM_PIPELINES = {
+   'redCrucero.pipelines.JsonWriterPipeline': 300,
+}
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See http://doc.scrapy.org/en/latest/topics/autothrottle.html
+#AUTOTHROTTLE_ENABLED = True
+# The initial download delay
+#AUTOTHROTTLE_START_DELAY = 5
+# The maximum download delay to be set in case of high latencies
+#AUTOTHROTTLE_MAX_DELAY = 60
+# The average number of requests Scrapy should be sending in parallel to
+# each remote server
+#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
+# Enable showing throttling stats for every response received:
+#AUTOTHROTTLE_DEBUG = False
+
+# Enable and configure HTTP caching (disabled by default)
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
+#HTTPCACHE_ENABLED = True
+#HTTPCACHE_EXPIRATION_SECS = 0
+#HTTPCACHE_DIR = 'httpcache'
+#HTTPCACHE_IGNORE_HTTP_CODES = []
+#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'

descarga_por_dia/redCrucero/redCrucero/spiders/__init__.py

+# This package will contain the spiders of your Scrapy project
+#
+# Please refer to the documentation for information on how to create and manage
+# your spiders.

descarga_por_dia/redCrucero/redCrucero/spiders/noticias.py

+# -*- coding: utf-8 -*-
+import scrapy, re
+from redCrucero.items import NoticiasItem
+
+"""
+MEDIO:
+Red Crucero, Nuevo León
+USO:
+scrapy crawl noticias --nolog -s filename=2018-02-04.json -a year=2018 -a month=2 -a day=4
+"""
+
+TAG_RE = re.compile(r'<[^>]+>')
+def remove_tags(text):
+    return TAG_RE.sub('', text)
+
+# LOC_RE = re.compile(r'\n.+?,? ?.+? ?\. ?- ?')
+# G_RE = re.compile(r' ?- ?')
+# EM_RE = re.compile(r'((Email|Correo electr.{1,3}nico|Comentarios?):\s)?[\w.-]+@[\w-]+(\.[a-zA-Z]{2,6}){1,2}\s?')
+# TW_RE = re.compile(r'M.{1,3}s de la P.{1,3}lvora en Twitter: @[\w.%+-]+.', re.I)
+# TW2_RE = re.compile(r'((\| )?Twitter:\s+)?(@[\w.%+-]+.)?', re.I)
+# TAG2_RE = re.compile(r'\ntransition_[^\]]+\]')
+# TAG3_RE = re.compile(r'\[[^\]]+[\]\n]')
+
+class QuotesSpider(scrapy.Spider):
+    name = "noticias"
+
+    def start_requests(self):
+        year = getattr(self, "year", None)
+        month = getattr(self, "month", None)
+        day = getattr(self, "day", None)
+
+        baseURL = "http://www.red-crucero.com/news/" + year + "/" + month.zfill(2) + "/" + day.zfill(2)
+
+        yield scrapy.Request(url=baseURL, callback=self.parse)
+
+
+    def parse(self, response):
+        yield scrapy.Request(url=response.url, callback=self.parse_page, dont_filter=True)
+
+        nextPage = response.xpath('//div[@class="nav-previous"]/a/@href').extract_first()
+        if nextPage is not None:
+            yield scrapy.Request(url=nextPage, callback=self.parse)
+
+
+    def parse_page(self, response):
+        for link in response.xpath('//div[@id="primary"]').css('h2.entry-title').xpath('./a/@href').extract():
+            yield scrapy.Request(url=link, callback=self.parse_item)
+
+
+    def parse_item(self, response):
+        item = NoticiasItem()
+        text = ''
+
+        "La fecha obtenida ya incluye formato y zona horaria"
+        item['date'] = response.xpath('//span[@class="posted-on"]/a/time/@datetime').extract_first()
+        item['title'] = remove_tags(response.xpath('//header[@class="entry-header"]/h1').extract_first()).strip()
+
+        topic = response.xpath('//span[@class="cat-links"]/a/text()').extract_first()
+        if topic is not None:
+            item['topic'] = topic
+
+        author = response.xpath('//span[@class="author vcard"]/a').extract_first()
+        if author is not None:
+            author = remove_tags(author).replace("por ", '')
+            item['author'] = author
+
+        for p in response.xpath('//div[@class="entry-content"]').css('p').extract():
+            text += remove_tags(p) + "\n"
+
+        # result = LOC_RE.search(text)
+        # if result:
+        #     m = result.group(0)
+        #     location = G_RE.sub('', m).strip()
+        #     if len(location) <= 35:
+        #         item['location'] = location
+        #         text = text[text.find(m)+len(m):]
+
+        # text = EM_RE.sub('', text)
+        # text = TW_RE.sub('', text)
+        # text = TW2_RE.sub('', text)
+        # text = TAG2_RE.sub("\n", text)
+        # text = TAG3_RE.sub('', text)
+        item['text'] = text.strip()
+
+        item['url'] = response.url
+
+        yield item

descarga_por_dia/redCrucero/scrapy.cfg

+# Automatically created by: scrapy startproject
+#
+# For more information about the [deploy] section see:
+# https://scrapyd.readthedocs.org/en/latest/deploy.html
+
+[settings]
+default = redCrucero.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = redCrucero

descarga_por_dia/sintesis/scrapy.cfg

+# Automatically created by: scrapy startproject
+#
+# For more information about the [deploy] section see:
+# https://scrapyd.readthedocs.org/en/latest/deploy.html
+
+[settings]
+default = sintesis.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = sintesis

descarga_por_dia/sintesis/sintesis/items.py

+# -*- coding: utf-8 -*-
+
+# Define here the models for your scraped items
+#
+# See documentation in:
+# http://doc.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class NoticiasItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    title = scrapy.Field()
+    text = scrapy.Field()
+    date = scrapy.Field()
+    location = scrapy.Field()
+    author = scrapy.Field()
+    topic = scrapy.Field()
+    url = scrapy.Field()

descarga_por_dia/sintesis/sintesis/middlewares.py

+# -*- coding: utf-8 -*-
+
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# http://doc.scrapy.org/en/latest/topics/spider-middleware.html
+
+from scrapy import signals
+
+
+class SintesisSpiderMiddleware(object):
+    # Not all methods need to be defined. If a method is not defined,
+    # scrapy acts as if the spider middleware does not modify the
+    # passed objects.
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # This method is used by Scrapy to create your spiders.
+        s = cls()
+        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
+        return s
+
+    def process_spider_input(response, spider):
+        # Called for each response that goes through the spider
+        # middleware and into the spider.
+
+        # Should return None or raise an exception.
+        return None
+
+    def process_spider_output(response, result, spider):
+        # Called with the results returned from the Spider, after
+        # it has processed the response.
+
+        # Must return an iterable of Request, dict or Item objects.
+        for i in result:
+            yield i
+
+    def process_spider_exception(response, exception, spider):
+        # Called when a spider or process_spider_input() method
+        # (from other spider middleware) raises an exception.
+
+        # Should return either None or an iterable of Response, dict
+        # or Item objects.
+        pass
+
+    def process_start_requests(start_requests, spider):
+        # Called with the start requests of the spider, and works
+        # similarly to the process_spider_output() method, except
+        # that it doesn’t have a response associated.
+
+        # Must return only requests (not items).
+        for r in start_requests:
+            yield r
+
+    def spider_opened(self, spider):
+        spider.logger.info('Spider opened: %s' % spider.name)

descarga_por_dia/sintesis/sintesis/pipelines.py

+# -*- coding: utf-8 -*-
+
+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html
+
+import json
+from collections import OrderedDict
+
+
+class JsonWriterPipeline(object):
+
+    def __init__(self, filename):
+        self.filename = filename
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # Here you get whatever value was passed through the "filename" command line parameter
+        settings = crawler.settings
+        filename = settings.get('filename')
+
+        # Instantiate the pipeline with the file name
+        return cls(filename)
+
+    def open_spider(self, spider):
+        self.counter = 0
+        self.file = open(self.filename, 'w')
+        self.file.write("[")
+
+    def close_spider(self, spider):
+        self.file.write("]")
+        self.file.close()
+
+    def process_item(self, item, spider):
+        # print("this is my item", item)
+        row = []
+        try:
+            row.append(("date", item['date']))
+        except:
+            pass
+        try:
+            row.append(("topic", item['topic']))
+        except:
+            pass
+        try:
+            row.append(("title", item['title']))
+        except:
+            pass
+        try:
+            row.append(("author", item['author']))
+        except:
+            pass
+        try:
+            row.append(("location", item['location']))
+        except:
+            pass
+        try:
+            row.append(("text", item['text']))
+        except:
+            pass
+        try:
+            row.append(("url", item['url']))
+        except:
+            pass
+
+        line = OrderedDict(row)
+
+        self.counter += 1
+        if self.counter == 1:
+            self.file.write(json.dumps(line))
+        elif self.counter > 1:
+            self.file.write(",\n" + json.dumps(line))
+
+        return item

descarga_por_dia/sintesis/sintesis/settings.py

+# -*- coding: utf-8 -*-
+
+# Scrapy settings for sintesis project
+#
+# For simplicity, this file contains only settings considered important or
+# commonly used. You can find more settings consulting the documentation:
+#
+#     http://doc.scrapy.org/en/latest/topics/settings.html
+#     http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#     http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+
+BOT_NAME = 'sintesis'
+
+SPIDER_MODULES = ['sintesis.spiders']
+NEWSPIDER_MODULE = 'sintesis.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'sintesis (+http://www.yourdomain.com)'
+
+# Obey robots.txt rules
+# ROBOTSTXT_OBEY = True
+
+# Configure maximum concurrent requests performed by Scrapy (default: 16)
+#CONCURRENT_REQUESTS = 32
+
+# Configure a delay for requests for the same website (default: 0)
+# See http://scrapy.readthedocs.org/en/latest/topics/settings.html#download-delay
+# See also autothrottle settings and docs
+DOWNLOAD_DELAY = 0.5
+# The download delay setting will honor only one of:
+#CONCURRENT_REQUESTS_PER_DOMAIN = 16
+#CONCURRENT_REQUESTS_PER_IP = 16
+
+# Disable cookies (enabled by default)
+COOKIES_ENABLED = False
+
+# Disable Telnet Console (enabled by default)
+#TELNETCONSOLE_ENABLED = False
+
+# Override the default request headers:
+#DEFAULT_REQUEST_HEADERS = {
+#   'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
+#   'Accept-Language': 'en',
+#}
+
+# Enable or disable spider middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+#SPIDER_MIDDLEWARES = {
+#    'sintesis.middlewares.SintesisSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'sintesis.middlewares.MyCustomDownloaderMiddleware': 543,
+#}
+
+# Enable or disable extensions
+# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
+#EXTENSIONS = {
+#    'scrapy.extensions.telnet.TelnetConsole': None,
+#}
+
+# Configure item pipelines
+# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
+ITEM_PIPELINES = {
+   'sintesis.pipelines.JsonWriterPipeline': 300,
+}
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See http://doc.scrapy.org/en/latest/topics/autothrottle.html
+#AUTOTHROTTLE_ENABLED = True
+# The initial download delay
+#AUTOTHROTTLE_START_DELAY = 5
+# The maximum download delay to be set in case of high latencies
+#AUTOTHROTTLE_MAX_DELAY = 60
+# The average number of requests Scrapy should be sending in parallel to
+# each remote server
+#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
+# Enable showing throttling stats for every response received:
+#AUTOTHROTTLE_DEBUG = False
+
+# Enable and configure HTTP caching (disabled by default)
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
+#HTTPCACHE_ENABLED = True
+#HTTPCACHE_EXPIRATION_SECS = 0
+#HTTPCACHE_DIR = 'httpcache'
+#HTTPCACHE_IGNORE_HTTP_CODES = []
+#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'

descarga_por_dia/sintesis/sintesis/spiders/__init__.py

+# This package will contain the spiders of your Scrapy project
+#
+# Please refer to the documentation for information on how to create and manage
+# your spiders.

descarga_por_dia/sintesis/sintesis/spiders/noticias.py

+# -*- coding: utf-8 -*-
+import scrapy, re
+from sintesis.items import NoticiasItem
+
+"""
+MEDIO:
+Síntesis, Puebla
+USO:
+scrapy crawl noticias --nolog -s filename=2018-02-04.json -a year=2018 -a month=2 -a day=4
+"""
+
+TAG_RE = re.compile(r'<[^>]+>')
+def remove_tags(text):
+    return TAG_RE.sub('', text)
+
+# LOC_RE = re.compile(r'\n.+?,? ?.+? ?\. ?- ?')
+# G_RE = re.compile(r' ?- ?')
+# EM_RE = re.compile(r'((Email|Correo electr.{1,3}nico|Comentarios?):\s)?[\w.-]+@[\w-]+(\.[a-zA-Z]{2,6}){1,2}\s?')
+# TW_RE = re.compile(r'M.{1,3}s de la P.{1,3}lvora en Twitter: @[\w.%+-]+.', re.I)
+# TW2_RE = re.compile(r'((\| )?Twitter:\s+)?(@[\w.%+-]+.)?', re.I)
+# TAG2_RE = re.compile(r'\ntransition_[^\]]+\]')
+# TAG3_RE = re.compile(r'\[[^\]]+[\]\n]')
+
+class QuotesSpider(scrapy.Spider):
+    name = "noticias"
+
+    def start_requests(self):
+        year = getattr(self, "year", None)
+        month = getattr(self, "month", None)
+        day = getattr(self, "day", None)
+
+        self.baseURL = "https://www.sintesis.mx/" + year + "/" + month.zfill(2) + "/" + day.zfill(2)
+
+        yield scrapy.Request(url=self.baseURL, callback=self.parse)
+
+
+    def parse(self, response):
+        yield scrapy.Request(url=response.url, callback=self.parse_page, dont_filter=True)
+
+        pagination = response.css('div.page-nav').xpath('./a/@href').extract()
+        if len(pagination) > 0:
+            pagination = pagination[-2].strip('/')
+            pages = int(pagination[pagination.rfind('/') + 1:])
+
+            for page in range(1, pages):
+                yield scrapy.Request(url=self.baseURL + '/page/' + str(page + 1), callback=self.parse_page)
+
+
+    def parse_page(self, response):
+        for link in response.xpath('//div[@class="td-ss-main-content"]').css('h3.entry-title').xpath('./a/@href').extract():
+            yield scrapy.Request(url=link, callback=self.parse_item)
+
+
+    def parse_item(self, response):
+        item = NoticiasItem()
+        text = ''
+
+        "La fecha obtenida ya incluye formato y zona horaria"
+        item['date'] = response.xpath('//span[@class="td-post-date"]/time/@datetime').extract_first()
+        item['title'] = remove_tags(response.xpath('//header[@class="td-post-title"]/h1').extract_first()).strip()
+
+        topic = response.xpath('//ul[@class="td-category"]/li/a').extract_first()
+        if topic is not None:
+            item['topic'] = remove_tags(topic)
+
+        author = response.xpath('//div[@class="td-post-author-name"]/a').extract_first()
+        if author is not None:
+            item['author'] = remove_tags(author)
+
+        for p in response.xpath('//div[@class="td-post-content"]').css('p').extract():
+            text += remove_tags(p) + "\n"
+
+        # result = LOC_RE.search(text)
+        # if result:
+        #     m = result.group(0)
+        #     location = G_RE.sub('', m).strip()
+        #     if len(location) <= 35:
+        #         item['location'] = location
+        #         text = text[text.find(m)+len(m):]
+
+        # text = EM_RE.sub('', text)
+        # text = TW_RE.sub('', text)
+        # text = TW2_RE.sub('', text)
+        # text = TAG2_RE.sub("\n", text)
+        # text = TAG3_RE.sub('', text)
+        item['text'] = text.strip()
+
+        item['url'] = response.url
+
+        yield item

descarga_por_dia/tiempoDigital/scrapy.cfg

+# Automatically created by: scrapy startproject
+#
+# For more information about the [deploy] section see:
+# https://scrapyd.readthedocs.org/en/latest/deploy.html
+
+[settings]
+default = tiempoDigital.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = tiempoDigital

descarga_por_dia/tiempoDigital/tiempoDigital/items.py

+# -*- coding: utf-8 -*-
+
+# Define here the models for your scraped items
+#
+# See documentation in:
+# http://doc.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class NoticiasItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    title = scrapy.Field()
+    text = scrapy.Field()
+    date = scrapy.Field()
+    location = scrapy.Field()
+    author = scrapy.Field()
+    topic = scrapy.Field()
+    url = scrapy.Field()

descarga_por_dia/tiempoDigital/tiempoDigital/middlewares.py

+# -*- coding: utf-8 -*-
+
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# http://doc.scrapy.org/en/latest/topics/spider-middleware.html
+
+from scrapy import signals
+
+
+class TiempodigitalSpiderMiddleware(object):
+    # Not all methods need to be defined. If a method is not defined,
+    # scrapy acts as if the spider middleware does not modify the
+    # passed objects.
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # This method is used by Scrapy to create your spiders.
+        s = cls()
+        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
+        return s
+
+    def process_spider_input(response, spider):
+        # Called for each response that goes through the spider
+        # middleware and into the spider.
+
+        # Should return None or raise an exception.
+        return None
+
+    def process_spider_output(response, result, spider):
+        # Called with the results returned from the Spider, after
+        # it has processed the response.
+
+        # Must return an iterable of Request, dict or Item objects.
+        for i in result:
+            yield i
+
+    def process_spider_exception(response, exception, spider):
+        # Called when a spider or process_spider_input() method
+        # (from other spider middleware) raises an exception.
+
+        # Should return either None or an iterable of Response, dict
+        # or Item objects.
+        pass
+
+    def process_start_requests(start_requests, spider):
+        # Called with the start requests of the spider, and works
+        # similarly to the process_spider_output() method, except
+        # that it doesn’t have a response associated.
+
+        # Must return only requests (not items).
+        for r in start_requests:
+            yield r
+
+    def spider_opened(self, spider):
+        spider.logger.info('Spider opened: %s' % spider.name)

descarga_por_dia/tiempoDigital/tiempoDigital/pipelines.py

+# -*- coding: utf-8 -*-
+
+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html
+
+import json
+from collections import OrderedDict
+
+
+class JsonWriterPipeline(object):
+
+    def __init__(self, filename):
+        self.filename = filename
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # Here you get whatever value was passed through the "filename" command line parameter
+        settings = crawler.settings
+        filename = settings.get('filename')
+
+        # Instantiate the pipeline with the file name
+        return cls(filename)
+
+    def open_spider(self, spider):
+        self.counter = 0
+        self.file = open(self.filename, 'w')
+        self.file.write("[")
+
+    def close_spider(self, spider):
+        self.file.write("]")
+        self.file.close()
+
+    def process_item(self, item, spider):
+        # print("this is my item", item)
+        row = []
+        try:
+            row.append(("date", item['date']))
+        except:
+            pass
+        try:
+            row.append(("topic", item['topic']))
+        except:
+            pass
+        try:
+            row.append(("title", item['title']))
+        except:
+            pass
+        try:
+            row.append(("author", item['author']))
+        except:
+            pass
+        try:
+            row.append(("location", item['location']))
+        except:
+            pass
+        try:
+            row.append(("text", item['text']))
+        except:
+            pass
+        try:
+            row.append(("url", item['url']))
+        except:
+            pass
+
+        line = OrderedDict(row)
+
+        self.counter += 1
+        if self.counter == 1:
+            self.file.write(json.dumps(line))
+        elif self.counter > 1:
+            self.file.write(",\n" + json.dumps(line))
+
+        return item

descarga_por_dia/tiempoDigital/tiempoDigital/settings.py

+# -*- coding: utf-8 -*-
+
+# Scrapy settings for tiempoDigital project
+#
+# For simplicity, this file contains only settings considered important or
+# commonly used. You can find more settings consulting the documentation:
+#
+#     http://doc.scrapy.org/en/latest/topics/settings.html
+#     http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#     http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+
+BOT_NAME = 'tiempoDigital'
+
+SPIDER_MODULES = ['tiempoDigital.spiders']
+NEWSPIDER_MODULE = 'tiempoDigital.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'tiempoDigital (+http://www.yourdomain.com)'
+
+# Obey robots.txt rules
+# ROBOTSTXT_OBEY = True
+
+# Configure maximum concurrent requests performed by Scrapy (default: 16)
+#CONCURRENT_REQUESTS = 32
+
+# Configure a delay for requests for the same website (default: 0)
+# See http://scrapy.readthedocs.org/en/latest/topics/settings.html#download-delay
+# See also autothrottle settings and docs
+DOWNLOAD_DELAY = 1.5
+# The download delay setting will honor only one of:
+#CONCURRENT_REQUESTS_PER_DOMAIN = 16
+#CONCURRENT_REQUESTS_PER_IP = 16
+
+# Disable cookies (enabled by default)
+COOKIES_ENABLED = False
+
+# Disable Telnet Console (enabled by default)
+#TELNETCONSOLE_ENABLED = False
+
+# Override the default request headers:
+#DEFAULT_REQUEST_HEADERS = {
+#   'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
+#   'Accept-Language': 'en',
+#}
+
+# Enable or disable spider middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+#SPIDER_MIDDLEWARES = {
+#    'tiempoDigital.middlewares.TiempodigitalSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'tiempoDigital.middlewares.MyCustomDownloaderMiddleware': 543,
+#}
+
+# Enable or disable extensions
+# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
+#EXTENSIONS = {
+#    'scrapy.extensions.telnet.TelnetConsole': None,
+#}
+
+# Configure item pipelines
+# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
+ITEM_PIPELINES = {
+   'tiempoDigital.pipelines.JsonWriterPipeline': 300,
+}
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See http://doc.scrapy.org/en/latest/topics/autothrottle.html
+#AUTOTHROTTLE_ENABLED = True
+# The initial download delay
+#AUTOTHROTTLE_START_DELAY = 5
+# The maximum download delay to be set in case of high latencies
+#AUTOTHROTTLE_MAX_DELAY = 60
+# The average number of requests Scrapy should be sending in parallel to
+# each remote server
+#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
+# Enable showing throttling stats for every response received:
+#AUTOTHROTTLE_DEBUG = False
+
+# Enable and configure HTTP caching (disabled by default)
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
+#HTTPCACHE_ENABLED = True
+#HTTPCACHE_EXPIRATION_SECS = 0
+#HTTPCACHE_DIR = 'httpcache'
+#HTTPCACHE_IGNORE_HTTP_CODES = []
+#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'

descarga_por_dia/tiempoDigital/tiempoDigital/spiders/__init__.py

+# This package will contain the spiders of your Scrapy project
+#
+# Please refer to the documentation for information on how to create and manage
+# your spiders.

descarga_por_dia/tiempoDigital/tiempoDigital/spiders/noticias.py

+# -*- coding: utf-8 -*-
+import scrapy, re
+from tiempoDigital.items import NoticiasItem
+
+"""
+MEDIO:
+Tiempo Digital, Oaxaca
+USO:
+scrapy crawl noticias --nolog -s filename=2018-02-04.json -a year=2018 -a month=2 -a day=4
+"""
+
+TAG_RE = re.compile(r'<[^>]+>')
+def remove_tags(text):
+    return TAG_RE.sub('', text)
+
+# LOC_RE = re.compile(r'\n.+?,? ?.+? ?\. ?- ?')
+# G_RE = re.compile(r' ?- ?')
+# EM_RE = re.compile(r'((Email|Correo electr.{1,3}nico|Comentarios?):\s)?[\w.-]+@[\w-]+(\.[a-zA-Z]{2,6}){1,2}\s?')
+# TW_RE = re.compile(r'M.{1,3}s de la P.{1,3}lvora en Twitter: @[\w.%+-]+.', re.I)
+# TW2_RE = re.compile(r'((\| )?Twitter:\s+)?(@[\w.%+-]+.)?', re.I)
+# TAG2_RE = re.compile(r'\ntransition_[^\]]+\]')
+# TAG3_RE = re.compile(r'\[[^\]]+[\]\n]')
+
+class QuotesSpider(scrapy.Spider):
+    name = "noticias"
+
+    def start_requests(self):
+        year = getattr(self, "year", None)
+        month = getattr(self, "month", None)
+        day = getattr(self, "day", None)
+
+        self.baseURL = "http://tiempodigital.mx/" + year + "/" + month.zfill(2) + "/" + day.zfill(2)
+
+        yield scrapy.Request(url=self.baseURL, callback=self.parse)
+
+
+    def parse(self, response):
+        yield scrapy.Request(url=response.url, callback=self.parse_page, dont_filter=True)
+
+        pagination = response.css('div.page-nav').xpath('./a/@href').extract()
+        if len(pagination) > 0:
+            try:
+                pagination = pagination[-2]
+            except:
+                pagination = pagination[-1]
+            pagination = pagination.strip('/')
+            pages = int(pagination[pagination.rfind('/') + 1:])
+
+            for page in range(1, pages):
+                yield scrapy.Request(url=self.baseURL + '/page/' + str(page + 1), callback=self.parse_page)
+
+
+    def parse_page(self, response):
+        for post in response.xpath('//div[@class="td-ss-main-content"]').css('div.item-details'):
+            item = NoticiasItem()
+
+            topic = post.css('div.td-module-meta-info').xpath('./a').extract_first()
+            if topic is not None:
+                item['topic'] = remove_tags(topic)
+            else:
+                item['topic'] = None
+            author = post.css('div.td-module-meta-info').xpath('./span[@class="td-post-author-name"]/a').extract_first()
+            if author is not None:
+                item['author'] = remove_tags(author)
+
+            link = post.css('h3.entry-title').xpath('./a/@href').extract_first()
+            request = scrapy.Request(url=link, callback=self.parse_item)
+            request.meta['item'] = item
+            yield request
+
+
+    def parse_item(self, response):
+        item = response.meta['item']
+        text = ''
+
+        "La fecha obtenida ya incluye formato y zona horaria"
+        item['date'] = response.xpath('//span[@class="td-post-date"]/time/@datetime').extract_first()
+        item['title'] = remove_tags(response.xpath('//header[@class="td-post-title"]/h1').extract_first()).strip()
+
+        for p in response.xpath('//div[@class="td-post-content"]').css('p').extract():
+            text += remove_tags(p) + "\n"
+
+        # result = LOC_RE.search(text)
+        # if result:
+        #     m = result.group(0)
+        #     location = G_RE.sub('', m).strip()
+        #     if len(location) <= 35:
+        #         item['location'] = location
+        #         text = text[text.find(m)+len(m):]
+
+        # text = EM_RE.sub('', text)
+        # text = TW_RE.sub('', text)
+        # text = TW2_RE.sub('', text)
+        # text = TAG2_RE.sub("\n", text)
+        # text = TAG3_RE.sub('', text)
+        item['text'] = text.strip()
+
+        item['url'] = response.url
+
+        yield item

parse_date_files2.py

+import json, os, sys
+from datetime import datetime
+from collections import OrderedDict
+
+"""
+Uso:
+python parse_date_files.py <nombre_del_crawler>
+
+Ej.
+python parse_date_files.py laJornadaBC2
+"""
+
+def dictRowGenerator(line):
+    row = []
+
+    try:
+        row.append(("date", line['date']))
+    except:
+        pass
+    try:
+        row.append(("topic", line['topic']))
+    except:
+        pass
+    try:
+        row.append(("title", line['title']))
+    except:
+        pass
+    try:
+        row.append(("author", line['author']))
+    except:
+        pass
+    try:
+        row.append(("location", line['location']))
+    except:
+        pass
+    try:
+        row.append(("url", line['url']))
+    except:
+        pass
+    try:
+        row.append(("text", line['text']))
+    except:
+        pass
+
+    return row
+
+
+download_type = 'descarga_hacia_atras'
+this_file_path = os.path.dirname(os.path.realpath(__file__))
+json_file_path = this_file_path+'/'+download_type+'/'+sys.argv[1]
+destination_path = this_file_path+'/'+sys.argv[1]
+
+json_file = json.loads(open(json_file_path+'/noticias.json').read())
+date_set = set()
+urlSet = set()
+
+for news in json_file:
+    if news['date'] is not None:
+        news_date = news['date'][:news['date'].rfind('T')]
+        if len(news_date) > 10:
+            news_date = news['date'][:news['date'].rfind(' ')]
+
+        if not news_date in date_set:
+            date_set.add(news_date)
+            print(news_date)
+
+            try:
+                export_file = open(destination_path+'/'+news_date[:4]+'/'+news_date+'.json', 'a')
+            except:
+                os.makedirs(destination_path+'/'+news_date[:4])
+                export_file = open(destination_path+'/'+news_date[:4]+'/'+news_date+'.json', 'a')
+
+            counter = 0
+            export_file.write("[")
+
+            for line in json_file:
+                if line['date'] is not None:
+                    line_date = line['date'][:line['date'].rfind('T')]
+                    if len(line_date) > 10:
+                        line_date = line['date'][:line['date'].rfind(' ')]
+
+                    if not line['url'] in urlSet and line_date == news_date:
+                        urlSet.add(line['url'])
+                        counter += 1
+
+                        auxRow = dictRowGenerator(line)
+                        row = OrderedDict(auxRow)
+                        if counter == 1:
+                            export_file.write(json.dumps(row))
+                        elif counter > 1:
+                            export_file.write(",\n" + json.dumps(row))
+
+            export_file.write("]")
+            export_file.close()
+