crawlers

descarga_por_dia/campecheHoy/campecheHoy/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 CampechehoyItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    pass

descarga_por_dia/campecheHoy/campecheHoy/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 CampechehoySpiderMiddleware(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/campecheHoy/campecheHoy/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
+
+
+class CampechehoyPipeline(object):
+    def process_item(self, item, spider):
+        return item

descarga_por_dia/campecheHoy/campecheHoy/settings.py

+# -*- coding: utf-8 -*-
+
+# Scrapy settings for campecheHoy 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 = 'campecheHoy'
+
+SPIDER_MODULES = ['campecheHoy.spiders']
+NEWSPIDER_MODULE = 'campecheHoy.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'campecheHoy (+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 = {
+#    'campecheHoy.middlewares.CampechehoySpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'campecheHoy.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 = {
+#    'campecheHoy.pipelines.CampechehoyPipeline': 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/campecheHoy/campecheHoy/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/campecheHoy/campecheHoy/spiders/noticias.py

+import scrapy, re
+
+"""
+MEDIO:
+Campeche Hoy, Campeche
+USO:
+scrapy crawl noticias -t json --nolog -o noticias.json -a year=2018 -a month=1 -a day=17
+"""
+
+TAG_RE = re.compile(r'<[^>]+>')
+def remove_tags(text):
+    return TAG_RE.sub('', text)
+
+TRASH_RE = re.compile(r'<.*?>.*</.*?>\s?')
+
+
+class NoticiasItem(scrapy.Item):
+    title = scrapy.Field()
+    text = scrapy.Field()
+    date = scrapy.Field()
+    location = scrapy.Field()
+    author = scrapy.Field()
+    topic = scrapy.Field()
+    url = scrapy.Field()
+
+
+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://campechehoy.mx/" + year + "/" + month + "/" + day
+
+        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('//*[@class="page-nav td-pb-padding-side"]/a/@href').extract()
+        if pagination is not None and len(pagination) > 0:
+            pages = pagination[-2].rstrip("/")
+            pages = int(pages[pages.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('//*[@class="td-pb-span8 td-main-content"]').css('h3').css('a::attr(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/h1[@class="entry-title"]').extract_first())
+        try:
+            topic = response.xpath('//*[@class="td-post-source-tags td-pb-padding-side"]/ul/li/a/text()').extract()[1]
+        except:
+            topic = response.xpath('//*[@class="td-post-source-tags td-pb-padding-side"]/ul/li/a/text()').extract_first()
+        item['topic'] = topic
+
+        for p in response.xpath('//*[@class="td-post-content td-pb-padding-side"]/p').extract():
+            p = remove_tags(p)
+            p = p.replace("&lt;", "<")
+            p = p.replace("&gt;", ">")
+            text += remove_tags(p) + "\n"
+        item['text'] = text
+
+        item['url'] = response.url
+
+        yield item

descarga_por_dia/campecheHoy/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 = campecheHoy.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = campecheHoy

descarga_por_dia/heraldoAgs/heraldoAgs/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 HeraldoagsItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    pass

descarga_por_dia/heraldoAgs/heraldoAgs/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 HeraldoagsSpiderMiddleware(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/heraldoAgs/heraldoAgs/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
+
+
+class HeraldoagsPipeline(object):
+    def process_item(self, item, spider):
+        return item

descarga_por_dia/heraldoAgs/heraldoAgs/settings.py

+# -*- coding: utf-8 -*-
+
+# Scrapy settings for heraldoAgs 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 = 'heraldoAgs'
+
+SPIDER_MODULES = ['heraldoAgs.spiders']
+NEWSPIDER_MODULE = 'heraldoAgs.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'heraldoAgs (+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 = 3
+# 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 = {
+#    'heraldoAgs.middlewares.HeraldoagsSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'heraldoAgs.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 = {
+#    'heraldoAgs.pipelines.HeraldoagsPipeline': 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/heraldoAgs/heraldoAgs/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/heraldoAgs/heraldoAgs/spiders/noticias.py

+import scrapy, re
+
+"""
+MEDIO:
+El Heraldo, Aguascalientes
+USO:
+scrapy crawl noticias -t json --nolog -o noticias.json -a year=2017 -a month=3 -a day=5
+"""
+
+TAG_RE = re.compile(r'<[^>]+>')
+def remove_tags(text):
+    return TAG_RE.sub('', text)
+
+LOC_RE = re.compile(r'.+?(\d?\d-?[a-zA-Z]+)?\s?\.-\s?')
+DAT_RE = re.compile(r'\s?(\d?\d-?[a-zA-Z]+)?\s?\.-\s?')
+
+
+class NoticiasItem(scrapy.Item):
+    title = scrapy.Field()
+    text = scrapy.Field()
+    date = scrapy.Field()
+    location = scrapy.Field()
+    author = scrapy.Field()
+    topic = scrapy.Field()
+    url = scrapy.Field()
+
+
+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.heraldo.mx/" + year + "/" + month + "/" + day
+
+        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)
+
+        lastPage = response.xpath('//*[@class="page-nav td-pb-padding-side"]/a[@class="last"]/text()').extract_first()
+        if lastPage is not None and lastPage != '':
+            lastPage = int(lastPage)
+            for page in range(1,lastPage):
+                yield scrapy.Request(url=self.baseURL + "/page/" + str(page+1), callback=self.parse_page)
+
+
+    def parse_page(self, response):
+        for link in response.xpath('//*[@class="td-block-row"]').css('h3').css('a::attr(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('//time[@class="entry-date updated td-module-date"]/@datetime').extract_first()
+        item['title'] = remove_tags(response.xpath('//header[@class="td-post-title"]/h1').extract_first())
+        item['topic'] = response.xpath('//ul[@class="td-category"]/li/a/text()').extract_first()
+
+        author = response.xpath('//pre[@style="text-align: justify;"]/text()').extract_first()
+        if author is not None and author != '':
+            item['author'] = " ".join(author.split("\n")[0].split())
+
+        bodyText = response.xpath('//*[@class="td-post-content"]/p').extract()
+        for i in range(0, len(bodyText)):
+            p = remove_tags(bodyText[i])
+            if i <= 1:
+                p = p.lstrip()
+                result = LOC_RE.match(p)
+                if result:
+                    item['location'] = DAT_RE.sub('', result.group(0))
+                    p = LOC_RE.sub('', p)
+
+            text += p + "\n"
+        item['text'] = text
+
+        item['url'] = response.url
+
+        yield item

descarga_por_dia/heraldoAgs/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 = heraldoAgs.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = heraldoAgs

descarga_por_dia/tribunaCabos/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 = tribunaCabos.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = tribunaCabos

descarga_por_dia/tribunaCabos/tribunaCabos/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 TribunacabosItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    pass

descarga_por_dia/tribunaCabos/tribunaCabos/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 TribunacabosSpiderMiddleware(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/tribunaCabos/tribunaCabos/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
+
+
+class TribunacabosPipeline(object):
+    def process_item(self, item, spider):
+        return item

descarga_por_dia/tribunaCabos/tribunaCabos/settings.py

+# -*- coding: utf-8 -*-
+
+# Scrapy settings for tribunaCabos 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 = 'tribunaCabos'
+
+SPIDER_MODULES = ['tribunaCabos.spiders']
+NEWSPIDER_MODULE = 'tribunaCabos.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'tribunaCabos (+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 = {
+#    'tribunaCabos.middlewares.TribunacabosSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'tribunaCabos.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 = {
+#    'tribunaCabos.pipelines.TribunacabosPipeline': 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/tribunaCabos/tribunaCabos/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/tribunaCabos/tribunaCabos/spiders/noticias.py

+import scrapy, re
+
+"""
+MEDIO:
+Tribuna de los Cabos, Baja California Sur
+USO:
+scrapy crawl noticias -t json --nolog -o noticias.json -a year=2017 -a month=3 -a day=5
+"""
+
+TAG_RE = re.compile(r'<[^>]+>')
+def remove_tags(text):
+    return TAG_RE.sub('', text)
+
+""" Regular expression for parsing location """
+# LOC_RE = re.compile(ur'.+,\s+\d?\d\s+[a-zA-Z]+\.?\s\([^\)]+\)\s?\.-?\u2013?\s?', re.UNICODE)
+LOC_RE = re.compile(ur'.+?(\d?\d[\s-][a-zA-Z]+)?\s?(\([^\)]+\))?\s?\.[\u2013-]\s?', re.UNICODE)
+DAT_RE = re.compile(ur',?\s?(\d?\d[\s-][a-zA-Z]+)?\s?(\([^\)]+\))?\s?\.[\u2013-]\s?', re.UNICODE)
+DAT2_RE = re.compile(r',?\sa\s\d{1,2}\sde\s[a-zA-Z]+\sde\s\d{4}')
+
+
+# def parseLocation(p, sign):
+#     p = p.split(sign)
+#     location = p[0].strip()
+#     del p[0]
+#     for j in range(0, len(p)):
+#         p[j] = p[j].lstrip(" ")
+#         p[j] = p[j].rstrip(" ")
+#
+#     p = " ".join(p)
+#     return p, location
+
+
+class NoticiasItem(scrapy.Item):
+    title = scrapy.Field()
+    text = scrapy.Field()
+    date = scrapy.Field()
+    location = scrapy.Field()
+    author = scrapy.Field()
+    topic = scrapy.Field()
+    url = scrapy.Field()
+
+
+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.tribunadeloscabos.com.mx/" + year + "/" + month + "/" + day
+
+        yield scrapy.Request(url=self.baseURL, callback=self.parse)
+
+
+    def parse(self, response):
+        for link in response.xpath('//*[@id="content"]').css('h2').css('a::attr(href)').extract():
+            yield scrapy.Request(url=link, callback=self.parse_item)
+
+        previousPage = response.xpath('//li[@class="previous"]/a/@href').extract_first()
+        yield scrapy.Request(url=previousPage, callback=self.parse)
+
+
+    def parse_item(self, response):
+        item = NoticiasItem()
+        text = ''
+
+        "La fecha obtenida ya incluye formato y zona horaria"
+        item['date'] = response.xpath('//time[@class="entry-date published"]/@datetime').extract_first()
+        item['title'] = remove_tags(response.xpath('//header[@class="entry-header"]/h1').extract_first()).strip()
+        item['topic'] = response.xpath('//*[@class="above-entry-meta"]/span/a/text()').extract_first()
+
+        author = response.xpath('//span[@class="author vcard"]/a/text()').extract_first()
+        if author is not None and author != '':
+            item['author'] = author
+
+        bodyText = response.xpath('//*[@class="entry-content clearfix"]/p').extract()
+        for i in range(0, len(bodyText)):
+            p = remove_tags(bodyText[i])
+            if i <= 1:
+                p = p.lstrip()
+                result = LOC_RE.match(p)
+                if result:
+                    loc = DAT_RE.sub('', result.group(0))
+                    item['location'] = DAT2_RE.sub('', loc)
+                    p = LOC_RE.sub('', p)
+
+            text += p + "\n"
+        # for i in range(0, len(bodyText)):
+        #     p = remove_tags(bodyText[i])
+        #     if i == 0:
+        #         sign = u'.\u2013'
+        #         limit = 35
+        #         n = p.count(sign)
+        #         if n == 0:
+        #             sign = ".-"
+        #             limit = 30
+        #             n = p.count(sign)
+        #         if n > 0 and len(p.split(sign)[0]) <= limit:
+        #             loc = p.split(sign)
+        #             if len(loc[0].split(",")[0]) <= 20:
+        #                 p = loc
+        #                 loc = p[0].split(",")
+        #                 item['location'] = loc[0].strip()
+        #                 # item['location'] = item['location'].rstrip()
+        #                 del p[0]
+        #                 for j in range(0, len(p)):
+        #                     p[j] = p[j].lstrip(" ")
+        #                     p[j] = p[j].rstrip(" ")
+        #                 p = " ".join(p)
+        #
+        #     text += p + "\n"
+        item['text'] = text
+
+        item['url'] = response.url
+
+        yield item
+
+