crawlers

descarga_hacia_atras/diarioDeChiapas/diarioDeChiapas/spiders/noticias.py

@@ -5,13 +5,15 @@ MEDIA:
     Diario de Chiapas, Chiapas
 
 USAGE
-    $ cd diarioDeChiapas
+    $ cd diarioDeChiapas/
     ------------------------------------------------------------------------------------------------------------
     ## Get all the news from the most current to the oldest. It's necessary to use the parse_date_files.py file
     for the news contained in noticias.json being splitted into files by date. ##
+    
     $ scrapy crawl noticias --nolog -s filename=noticias.json
     ------------------------------------------------------------------------------------------------------------
     ## Get all the news from the most current to a specific date. ##
+    
     $ scrapy crawl noticias --nolog -s filename=2018-08-30.json -a year=2018 -a month=8 -a day=30
 """
 

descarga_hacia_atras/foraneos/prensaHn/prensaHn/items.py

@@ -3,7 +3,7 @@
 # Define here the models for your scraped items
 #
 # See documentation in:
-# http://doc.scrapy.org/en/latest/topics/items.html
+# https://doc.scrapy.org/en/latest/topics/items.html
 
 import scrapy
 

descarga_hacia_atras/foraneos/prensaHn/prensaHn/middlewares.py

@@ -3,7 +3,7 @@
 # Define here the models for your spider middleware
 #
 # See documentation in:
-# http://doc.scrapy.org/en/latest/topics/spider-middleware.html
+# https://doc.scrapy.org/en/latest/topics/spider-middleware.html
 
 from scrapy import signals
 
@@ -20,14 +20,14 @@ class PrensahnSpiderMiddleware(object):
         crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
         return s
 
-    def process_spider_input(response, spider):
+    def process_spider_input(self, 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):
+    def process_spider_output(self, response, result, spider):
         # Called with the results returned from the Spider, after
         # it has processed the response.
 
@@ -35,7 +35,7 @@ class PrensahnSpiderMiddleware(object):
         for i in result:
             yield i
 
-    def process_spider_exception(response, exception, spider):
+    def process_spider_exception(self, response, exception, spider):
         # Called when a spider or process_spider_input() method
         # (from other spider middleware) raises an exception.
 
@@ -43,7 +43,7 @@ class PrensahnSpiderMiddleware(object):
         # or Item objects.
         pass
 
-    def process_start_requests(start_requests, spider):
+    def process_start_requests(self, 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.
@@ -54,3 +54,50 @@ class PrensahnSpiderMiddleware(object):
 
     def spider_opened(self, spider):
         spider.logger.info('Spider opened: %s' % spider.name)
+
+
+class PrensahnDownloaderMiddleware(object):
+    # Not all methods need to be defined. If a method is not defined,
+    # scrapy acts as if the downloader 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_request(self, request, spider):
+        # Called for each request that goes through the downloader
+        # middleware.
+
+        # Must either:
+        # - return None: continue processing this request
+        # - or return a Response object
+        # - or return a Request object
+        # - or raise IgnoreRequest: process_exception() methods of
+        #   installed downloader middleware will be called
+        return None
+
+    def process_response(self, request, response, spider):
+        # Called with the response returned from the downloader.
+
+        # Must either;
+        # - return a Response object
+        # - return a Request object
+        # - or raise IgnoreRequest
+        return response
+
+    def process_exception(self, request, exception, spider):
+        # Called when a download handler or a process_request()
+        # (from other downloader middleware) raises an exception.
+
+        # Must either:
+        # - return None: continue processing this exception
+        # - return a Response object: stops process_exception() chain
+        # - return a Request object: stops process_exception() chain
+        pass
+
+    def spider_opened(self, spider):
+        spider.logger.info('Spider opened: %s' % spider.name)

descarga_hacia_atras/foraneos/prensaHn/prensaHn/pipelines.py

@@ -3,7 +3,7 @@
 # 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
+# See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html
 
 import json
 from collections import OrderedDict

descarga_hacia_atras/foraneos/prensaHn/prensaHn/settings.py

@@ -5,9 +5,9 @@
 # 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
+#     https://doc.scrapy.org/en/latest/topics/settings.html
+#     https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
+#     https://doc.scrapy.org/en/latest/topics/spider-middleware.html
 
 BOT_NAME = 'prensaHn'
 
@@ -25,7 +25,7 @@ NEWSPIDER_MODULE = 'prensaHn.spiders'
 #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 https://doc.scrapy.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:
@@ -45,31 +45,31 @@ COOKIES_ENABLED = False
 #}
 
 # Enable or disable spider middlewares
-# See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+# See https://doc.scrapy.org/en/latest/topics/spider-middleware.html
 #SPIDER_MIDDLEWARES = {
 #    'prensaHn.middlewares.PrensahnSpiderMiddleware': 543,
 #}
 
 # Enable or disable downloader middlewares
-# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
 #DOWNLOADER_MIDDLEWARES = {
-#    'prensaHn.middlewares.MyCustomDownloaderMiddleware': 543,
+#    'prensaHn.middlewares.PrensahnDownloaderMiddleware': 543,
 #}
 
 # Enable or disable extensions
-# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
+# See https://doc.scrapy.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
+# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html
 ITEM_PIPELINES = {
    'prensaHn.pipelines.JsonWriterPipeline': 300,
 }
 
 # Enable and configure the AutoThrottle extension (disabled by default)
-# See http://doc.scrapy.org/en/latest/topics/autothrottle.html
+# See https://doc.scrapy.org/en/latest/topics/autothrottle.html
 #AUTOTHROTTLE_ENABLED = True
 # The initial download delay
 #AUTOTHROTTLE_START_DELAY = 5
@@ -82,7 +82,7 @@ ITEM_PIPELINES = {
 #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
+# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
 #HTTPCACHE_ENABLED = True
 #HTTPCACHE_EXPIRATION_SECS = 0
 #HTTPCACHE_DIR = 'httpcache'

descarga_hacia_atras/foraneos/prensaHn/scrapy.cfg

 # Automatically created by: scrapy startproject
 #
 # For more information about the [deploy] section see:
-# https://scrapyd.readthedocs.org/en/latest/deploy.html
+# https://scrapyd.readthedocs.io/en/latest/deploy.html
 
 [settings]
 default = prensaHn.settings

descarga_hacia_atras/heraldoChihuahua/heraldoChihuahua/spiders/noticias.py

@@ -5,13 +5,15 @@ MEDIA:
     El Heraldo de Chihuahua, Chihuahua
 
 USAGE
-    $ cd heraldoChihuahua
+    $ cd heraldoChihuahua/
     ------------------------------------------------------------------------------------------------------------
     ## Get all the news from the most current to the oldest. It's necessary to use the parse_date_files.py file
     for the news contained in noticias.json being splitted into files by date. ##
+    
     $ scrapy crawl noticias --nolog -s filename=noticias.json
     ------------------------------------------------------------------------------------------------------------
     ## Get all the news from the most current to a specific date. ##
+    
     $ scrapy crawl noticias --nolog -s filename=2018-08-30.json -a year=2018 -a month=8 -a day=30
 """
 

descarga_hacia_atras/laJornadaMaya/laJornadaMaya/spiders/noticias.py

@@ -67,8 +67,7 @@ class QuotesSpider(scrapy.Spider):
                 request.meta['item'] = flow_info
                 yield request
 
-        else:
-            if year is None and month is None and day is None:
+        elif year is None and month is None and day is None:
             self.stop_date = None
             
             for s in section_list:

descarga_hacia_atras/tintaFresca/tintaFresca/spiders/noticias.py

@@ -5,13 +5,15 @@ MEDIA:
     Tinta Fresca, Chiapas
 
 USAGE
-    $ cd tintaFresca
+    $ cd tintaFresca/
     ------------------------------------------------------------------------------------------------------------
     ## Get all the news from the most current to the oldest. It's necessary to use the parse_date_files.py file
     for the news contained in noticias.json being splitted into files by date. ##
+    
     $ scrapy crawl noticias --nolog -s filename=noticias.json
     ------------------------------------------------------------------------------------------------------------
     ## Get all the news from the most current to a specific date. ##
+    
     $ scrapy crawl noticias --nolog -s filename=2018-08-30.json -a year=2018 -a month=8 -a day=30
 """
 
@@ -69,8 +71,8 @@ class QuotesSpider(scrapy.Spider):
 
         baseURL = "http://tintafresca.com.mx/"
 
-        # section_list = ["letras_en_su_tinta/page1/", "tgz/page1/", "patria_chica/page1/", "hecho_en_chiapas/page1/", "show/page1/", "rafaga/page1/"]
-        section_list = ["tgz/page1/", "patria_chica/page1/", "hecho_en_chiapas/page1/", "show/page1/"]
+        section_list = ["letras_en_su_tinta/page1/", "tgz/page1/", "patria_chica/page1/", "hecho_en_chiapas/page1/", "show/page1/", "rafaga/page1/"]
+        # section_list = ["tgz/page1/", "patria_chica/page1/", "hecho_en_chiapas/page1/", "show/page1/"]
 
         self.month_parser = dict(Enero='01', Febrero='02', Marzo='03',      Abril='04',   Mayo='05',      Junio='06',
                                  Julio='07', Agosto='08',  Septiembre='09', Octubre='10', Noviembre='11', Diciembre='12')

descarga_por_dia/cuartoPoder/cuartoPoder/spiders/noticias.py

@@ -76,7 +76,7 @@ class QuotesSpider(scrapy.Spider):
         flow_info = response.meta['item']
 
         for link in response.css('ul.news-list').xpath('./li/h5/a/@href').extract():
-            to_next_page = True
+            flow_info['to_next_page'] = True
             news_link = self.baseURL + link
             
             yield scrapy.Request(url=news_link, callback=self.parse_item)
@@ -102,7 +102,7 @@ class QuotesSpider(scrapy.Spider):
         news_date = datetime(int(self.year), int(self.month), int(self.day), tzinfo=self.tz).isoformat("T")
 
         title = response.css('div.post-title').css('h1').extract_first()
-        if title is not None : remove_tags(title)
+        if title is not None : title = remove_tags(title)
 
         topic = response.css('div.big-title').xpath('./h2/a/span').extract_first()
         if topic is not None : topic = remove_tags(topic)