crawlers

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