crawlers

descarga_hacia_atras/laJornadaBC/laJornadaBC/items.py

@@ -3,12 +3,18 @@
 # 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
 
 
-class LajornadabcItem(scrapy.Item):
+class NoticiasItem(scrapy.Item):
     # define the fields for your item here like:
     # name = scrapy.Field()
-    pass
+    title = scrapy.Field()
+    text = scrapy.Field()
+    date = scrapy.Field()
+    location = scrapy.Field()
+    author = scrapy.Field()
+    topic = scrapy.Field()
+    url = scrapy.Field()

descarga_hacia_atras/laJornadaBC/laJornadaBC/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 LajornadabcSpiderMiddleware(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 LajornadabcSpiderMiddleware(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 LajornadabcSpiderMiddleware(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 LajornadabcSpiderMiddleware(object):
 
     def spider_opened(self, spider):
         spider.logger.info('Spider opened: %s' % spider.name)
+
+
+class LajornadabcDownloaderMiddleware(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/laJornadaBC/laJornadaBC/pipelines.py

@@ -3,9 +3,73 @@
 # 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
+
+
+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()
 
-class LajornadabcPipeline(object):
     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/laJornadaBC/laJornadaBC/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 = 'laJornadaBC'
 
@@ -19,21 +19,21 @@ NEWSPIDER_MODULE = 'laJornadaBC.spiders'
 #USER_AGENT = 'laJornadaBC (+http://www.yourdomain.com)'
 
 # Obey robots.txt rules
-ROBOTSTXT_OBEY = True
+# 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 https://doc.scrapy.org/en/latest/topics/settings.html#download-delay
 # See also autothrottle settings and docs
-#DOWNLOAD_DELAY = 3
+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
+COOKIES_ENABLED = False
 
 # Disable Telnet Console (enabled by default)
 #TELNETCONSOLE_ENABLED = False
@@ -45,31 +45,31 @@ ROBOTSTXT_OBEY = True
 #}
 
 # 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 = {
 #    'laJornadaBC.middlewares.LajornadabcSpiderMiddleware': 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 = {
-#    'laJornadaBC.middlewares.MyCustomDownloaderMiddleware': 543,
+#    'laJornadaBC.middlewares.LajornadabcDownloaderMiddleware': 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
-#ITEM_PIPELINES = {
-#    'laJornadaBC.pipelines.LajornadabcPipeline': 300,
-#}
+# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html
+ITEM_PIPELINES = {
+   'laJornadaBC.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 @@ ROBOTSTXT_OBEY = True
 #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/laJornadaBC/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 = laJornadaBC.settings

descarga_por_dia/expresoChiapas/expresoChiapas/spiders/noticias.py

 # -*- coding: utf-8 -*-
 
-
-"""
-    ===========================================================================
-
-    THIS VERSION OF Expreso Chiapas IS NOW DEPRECATED SINCE THE SITE'S WEB PAGE
-    NO LONGER ALLOWS ACCES BY DAY.
-    THE NEW VERSION CAN BE FOUNd IN THE descarga_hacia_atras FOLDER.
-
-    ===========================================================================
-"""
-
-
 """
 MEDIA:
     Expreso Chiapas, Chiapas
@@ -31,20 +19,7 @@ TAG_RE = re.compile(r'<[^>]+>')
 def remove_tags(text):
     return TAG_RE.sub('', text)
 
-CLEAN_RE = re.compile(r'\A.*?\sl\s')
-
-
-class UTC(tzinfo):
-    """
-    Class for Time Zone
-    """
-    def utcoffset(self, dt):
-        ## Time zone for Chiapas: UTC-6 ##
-        return timedelta(hours=-6)
-
-    def tzname(self, dt):
-        ## Time zone name ##
-        return 'UTC-6'
+# CLEAN_RE = re.compile(r'\A.*?\sl\s')
 
 
 
@@ -56,24 +31,23 @@ class QuotesSpider(scrapy.Spider):
 
 
     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)
+        year = getattr(self, "year", None)
+        month = getattr(self, "month", None)
+        day = getattr(self, "day", None)
 
-        self.baseURL = "http://expresochiapas.com/noticias/" + self.year + "/" + self.month.zfill(2) + "/" + self.day.zfill(2)
+        baseURL = "http://expresochiapas.com/noticias/" + year + "/" + month.zfill(2) + "/" + day.zfill(2)
 
-        yield scrapy.Request(url=self.baseURL, callback=self.parse)
+        yield scrapy.Request(url=baseURL, callback=self.parse)
 
 
 
     def parse(self, response):
-        for link in response.xpath('//div[@class="mag-box-container"]/ul/li/a/@href').extract():
+        for link in response.css('div.penci-archive__list_posts').css('h2.entry-title > a::attr(href)').extract():
             yield scrapy.Request(url=link, callback=self.parse_item)
 
-        nextPage = response.xpath('//div[@class="pages-nav"]/div').css('span.last-page').xpath('./a/@href').extract_first()
-        if nextPage is not None and nextPage != '':
-            yield scrapy.Request(url=nextPage, callback=self.parse)
+        next_page = response.css('div.nav-links').css('a.next::attr(href)').extract_first()
+        if next_page is not None:
+            yield scrapy.Request(url=next_page, callback=self.parse)
 
 
 
@@ -81,28 +55,24 @@ class QuotesSpider(scrapy.Spider):
         item = NoticiasItem()
         text = ''
 
-        try:
-            ## this date includes time zone ##
-            res = response.xpath('//article[@id="the-post"]/script[@type="application/ld+json"]').extract_first()
-            if res is not None:
-                res = remove_tags(res)
-                jsonObj = json.loads(res)
-                dat = jsonObj['datePublished']
-        except:
-            dat = datetime(int(self.year), int(self.month), int(self.day), tzinfo=self.tz).isoformat("T")
-        item['date'] = dat
+        news_date = response.css('time.entry-date::attr(datetime)').extract_first()
 
-        item['title'] = remove_tags(response.xpath('//div[@class="entry-header"]/h1').extract_first()).strip()
+        title = response.css('h1.entry-title').extract_first()
+        if title is not None: title = remove_tags(title)
 
-        topic = response.xpath('//div[@class="entry-header"]/h5/a').extract_first()
-        if topic is not None:
-            item['topic'] = remove_tags(topic)
+        topic = response.css('div.penci-entry-categories').css('a').extract_first()
+        if topic is not None: topic = remove_tags(topic)
 
-        for p in response.xpath('//div[@class="entry-content entry clearfix"]/p').extract():
+        for p in response.css('div.penci-entry-content > p').extract():
+            p = p.replace("<br>", "\n")
             text += remove_tags(p) + "\n"
-        text = text.strip()
-        item['text'] = CLEAN_RE.sub('', text)
 
-        item['url'] = response.url
+
+        ## News item info ##
+        item['date']  = news_date
+        item['title'] = title
+        item['topic'] = topic
+        item['text']  = text.strip()
+        item['url']   = response.url
 
         yield item

descarga_por_dia/laJornada/laJornada/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_por_dia/laJornada/laJornada/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 LajornadaSpiderMiddleware(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 LajornadaSpiderMiddleware(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 LajornadaSpiderMiddleware(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 LajornadaSpiderMiddleware(object):
 
     def spider_opened(self, spider):
         spider.logger.info('Spider opened: %s' % spider.name)
+
+
+class LajornadaDownloaderMiddleware(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_por_dia/laJornada/laJornada/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_por_dia/laJornada/laJornada/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 = 'laJornada'
 
@@ -25,7 +25,7 @@ NEWSPIDER_MODULE = 'laJornada.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
-#SPIDER_MIDDLEWARES = {
+# See https://doc.scrapy.org/en/latest/topics/spider-middleware.html
+# SPIDER_MIDDLEWARES = {
 #    'laJornada.middlewares.LajornadaSpiderMiddleware': 543,
-#}
+# }
 
 # Enable or disable downloader middlewares
-# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
-#DOWNLOADER_MIDDLEWARES = {
-#    'laJornada.middlewares.MyCustomDownloaderMiddleware': 543,
-#}
+# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
+# DOWNLOADER_MIDDLEWARES = {
+#    'laJornada.middlewares.LajornadaDownloaderMiddleware': 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 = {
    'laJornada.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_por_dia/laJornada/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 = laJornada.settings

descarga_por_dia/porEsto/porEsto/items.py

+# -*- coding: utf-8 -*-
+
+# Define here the models for your scraped items
+#
+# See documentation in:
+# https://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/porEsto/porEsto/middlewares.py

+# -*- coding: utf-8 -*-
+
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# https://doc.scrapy.org/en/latest/topics/spider-middleware.html
+
+from scrapy import signals
+
+
+class PorestoSpiderMiddleware(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(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(self, 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(self, 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(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.
+
+        # 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)
+
+
+class PorestoDownloaderMiddleware(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_por_dia/porEsto/porEsto/pipelines.py

+# -*- coding: utf-8 -*-
+
+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: https://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/porEsto/porEsto/settings.py

+# -*- coding: utf-8 -*-
+
+# Scrapy settings for porEsto project
+#
+# For simplicity, this file contains only settings considered important or
+# commonly used. You can find more settings consulting the documentation:
+#
+#     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 = 'porEsto'
+
+SPIDER_MODULES = ['porEsto.spiders']
+NEWSPIDER_MODULE = 'porEsto.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'porEsto (+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 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:
+#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 https://doc.scrapy.org/en/latest/topics/spider-middleware.html
+#SPIDER_MIDDLEWARES = {
+#    'porEsto.middlewares.PorestoSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'porEsto.middlewares.PorestoDownloaderMiddleware': 543,
+#}
+
+# Enable or disable extensions
+# See https://doc.scrapy.org/en/latest/topics/extensions.html
+#EXTENSIONS = {
+#    'scrapy.extensions.telnet.TelnetConsole': None,
+#}
+
+# Configure item pipelines
+# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html
+ITEM_PIPELINES = {
+   'porEsto.pipelines.JsonWriterPipeline': 300,
+}
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See https://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 https://doc.scrapy.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/porEsto/porEsto/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/porEsto/porEsto/spiders/noticias.py

+# -*- coding: utf-8 -*-
+
+"""
+MEDIA:
+    Por Esto!, Yucatán
+USAGE:
+    ## Get all the news from a specific date. ##
+    ---------------------------------------------------------------------------------------------
+    $ cd porEsto/
+    $ scrapy crawl noticias --nolog -s filename=2018-08-22.json -a year=2018 -a month=8 -a day=22
+"""
+
+import scrapy, re, json
+from porEsto.items import NoticiasItem
+from datetime import datetime, timedelta, tzinfo
+
+
+TAG_RE = re.compile(r'<[^>]+>')
+def remove_tags(text):
+    return TAG_RE.sub('', text)
+
+
+
+class QuotesSpider(scrapy.Spider):
+    """
+    Basic Scrapy Spider class
+    """
+    name = "noticias"
+
+
+    def start_requests(self):
+        year = getattr(self, "year", None)
+        month = getattr(self, "month", None)
+        day = getattr(self, "day", None)
+
+        baseURL = "http://www.poresto.net/" + year + "/" + month.zfill(2) + "/" + day.zfill(2) + "/"
+
+        yield scrapy.Request(url=baseURL, callback=self.parse)
+
+
+
+    def parse(self, response):
+        for link in response.css('div.jeg_inner_content').css('h3.jeg_post_title > a::attr(href)').extract():
+            yield scrapy.Request(url=link, callback=self.parse_item)
+
+        next_page = response.css('div.jeg_navigation').css('a.next::attr(href)').extract_first()
+        if next_page is not None:
+            yield scrapy.Request(url=next_page, callback=self.parse)
+
+
+
+    def parse_item(self, response):
+        item = NoticiasItem()
+        text = ''
+
+        news_date = response.xpath('//meta[@property="article:published_time"]/@content').extract_first()
+
+        title = response.css('h1.jeg_post_title').extract_first()
+        if title is not None: title = remove_tags(title)
+
+        topic = response.css('div.jeg_meta_category > span > a').extract_first()
+        if topic is not None: topic = remove_tags(topic)
+
+        for p in response.css('div.entry-content').css('p').extract():
+            text += remove_tags(p) + "\n"
+
+        if text == '':
+            text = response.css('div.entry-content').css('div.content-inner').extract_first()
+            text.replace("<br>", '')
+            text = remove_tags(text)
+
+
+        ## News item info ##
+        item['date']  = news_date
+        item['title'] = title
+        item['topic'] = topic
+        item['text']  = text.strip()
+        item['url']   = response.url
+
+        yield item

descarga_por_dia/porEsto/scrapy.cfg

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