Se corrigió errores. Se agregó 3 periódicos.

README.md

-Crawlers para medios de información en linea nacionales basados en [Scrapy] (http://scrapy.org/)
+Crawlers para medios de información en linea nacionales basados en [Scrapy](http://scrapy.org/)
 
 Se incluyen los siguientes medios:
 * [La Jornada](http://www.jornada.unam.mx)
@@ -10,7 +10,7 @@ Se incluyen los siguientes medios:
 	cd lajornada
 	scrapy crawl noticias -t json --nolog -o noticias.json -a year=2016 -a month=12 -a day=24
 	```
-* [Diario de Yucatán](http://www.yucatan.com)
+* [Diario de Yucatán](http://yucatan.com.mx/)
 
 
 	Uso:
@@ -40,6 +40,16 @@ Se incluyen los siguientes medios:
 	Ejecutado el 2017.03.29.
 	Se bajaron notas en el rango del 2014.06.01 hasta el 2017.03.29 a las 15:30 hrs.
 	No se encontró notas antes del 2014.06.01.
+* [Desde el Balcón](http://www.desdeelbalcon.com/)
+
+
+	Uso:
+
+	```bash
+	cd desdeElBalcon
+	scrapy crawl noticias -t json --nolog -o noticias.json -a year=2017 -a month=3 -a day=30
+	```
+	No se encontró notas antes del 2014.01.11.
 * [El Grillo Porteño](http://grilloporteno.com/)
 
 
@@ -72,6 +82,16 @@ Se incluyen los siguientes medios:
 	scrapy crawl noticias -t json --nolog -o noticias.json -a year=2017 -a month=3 -a day=28
 	```
 	No se encontró notas antes del 2008.10.04.
+* [Notirivas](http://gruporivas.com.mx/notirivas/)
+
+
+	Uso:
+
+	```bash
+	cd notirivas
+	scrapy crawl noticias -t json --nolog -o noticias.json -a year=2017 -a month=3 -a day=30
+	```
+	No se encontró notas antes del 2016.11.22.
 * [Notisureste](http://www.notisureste.com/)
 
 
@@ -112,12 +132,13 @@ Se incluyen los siguientes medios:
 	scrapy crawl noticias -t json --nolog -o noticias.json -a year=2017 -a month=3 -a day=25
 	```
 	No se encontró notas antes del 2014.12.01.
-* [Yucatán Ahora](http://yucatanahora.com/)
+* [Yucatán en Corto](http://florcastillo.mx/noticias/)
 
 
 	Uso:
 
 	```bash
-	cd yucatanAhora
-	scrapy crawl noticias -t json --nolog -o noticias.json -a year=2017 -a month=3 -a day=24
+	cd yucatanEnCorto
+	scrapy crawl noticias -t json --nolog -o noticias.json -a year=2017 -a month=3 -a day=29
 	```
+	No se encontró notas antes del 2011.04.02.

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

desdeElBalcon/desdeElBalcon/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 DesdeelbalconSpiderMiddleware(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)

desdeElBalcon/desdeElBalcon/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 DesdeelbalconPipeline(object):
+    def process_item(self, item, spider):
+        return item

desdeElBalcon/desdeElBalcon/settings.py

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

desdeElBalcon/desdeElBalcon/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.

desdeElBalcon/desdeElBalcon/spiders/noticias.py

+import scrapy
+
+#scrapy crawl noticias -t json --nolog -o noticias.json -a year=2017 -a month=3 -a day=22
+
+import re
+
+TAG_RE = re.compile(r'<[^>]+>')
+def remove_tags(text):
+    return TAG_RE.sub('', text)
+
+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.desdeelbalcon.com/'+year+'/'+month+'/'+day
+		urls = [
+			self.baseURL,
+                ]
+		for url in urls:
+			yield scrapy.Request(url=url, callback=self.parse)
+
+	def parse(self, response):
+		pagination = response.xpath('//div[@id="content"]/div[3]/a/@href').extract()
+		if ( len(pagination) > 0 ):
+			pagination = pagination[-2].strip('/')
+			pages = int(pagination[pagination.rfind('/')+1:])
+			for page in range(0, pages):
+				if ( page == 0 ):
+					yield scrapy.Request(url=response.url, callback=self.parse_page, dont_filter=True)
+				else:
+					yield scrapy.Request(url=response.url+"/page/"+str(page+1), callback=self.parse_page)
+		else:
+			yield scrapy.Request(url=response.url, callback=self.parse_page, dont_filter=True)
+
+	def parse_page(self, response):
+		item = NoticiasItem()
+		for post in response.xpath('//ul[@class="archivepost"]/li'):
+			item['date'] = post.css('p.meta::text').extract_first()[4:18]
+			item['topic'] = post.xpath('./p/a/text()').extract()
+			request = scrapy.Request(url=post.xpath('./h2/a/@href').extract_first(), callback=self.parse_item)
+			request.meta['item'] = item
+			yield request
+
+	def parse_item(self, response):
+		text = ''
+		item = response.meta['item']
+		item['title'] = response.xpath('//h1[@class="post entry-title"]/a/text()').extract_first()
+		for paragraph in response.xpath('//div[@itemprop="text"]/p').extract():
+			text += remove_tags(paragraph) + '\n'
+		item['text'] = text
+		item['url'] = response.url
+		print item['title']
+		yield item
+

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

laVerdadYuc/laVerdadYuc/spiders/noticias.py

@@ -46,8 +46,8 @@ class QuotesSpider(scrapy.Spider):
 	def parse_page(self, response):
 		item = NoticiasItem()
 		for post in response.css('div.col-md-12').css('div.cp-post-content'):
-			item['author'] = post.css('ul.cp-post-tools').xpath('./li[2]/text()').extract_first()
 			item['topic'] = post.css('ul.cp-post-tools').css('li').css('a::attr(title)').extract()
+			item['author'] = post.css('ul.cp-post-tools').xpath('./li[2]/text()').extract_first()
 			request = scrapy.Request(url=post.xpath('./h3/a/@href').extract_first(), callback=self.parse_item)
 			request.meta['item'] = item
 			yield request

miPuntoDeVista/miPuntoDeVista/spiders/noticias.py

@@ -9,13 +9,13 @@ def remove_tags(text):
    return TAG_RE.sub('', text)
 
 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()
+    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"
@@ -26,7 +26,7 @@ class QuotesSpider(scrapy.Spider):
 		self.baseURL='http://www.mipuntodevista.com.mx/'+year+'/'+month+'/'+day
 		urls = [
 			self.baseURL,
-             ]
+               ]
 		for url in urls:
 			yield scrapy.Request(url=url, callback=self.parse)
 

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

notirivas/notirivas/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 NotirivasSpiderMiddleware(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)

notirivas/notirivas/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 NotirivasPipeline(object):
+    def process_item(self, item, spider):
+        return item

notirivas/notirivas/settings.py

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

notirivas/notirivas/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.

notirivas/notirivas/spiders/noticias.py

+import scrapy
+
+#scrapy crawl noticias -t json --nolog -o noticias.json -a year=2017 -a month=3 -a day=22
+
+import re
+
+TAG_RE = re.compile(r'<[^>]+>')
+def remove_tags(text):
+   return TAG_RE.sub('', text)
+
+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):
+		self.year = getattr(self, 'year', None)
+		self.month = getattr(self, 'month', None)
+		self.day = getattr(self, 'day', None)
+		self.baseURL='http://gruporivas.com.mx/notirivas/'+self.year+'/'+self.month+'/'+self.day
+		urls = [
+			self.baseURL,
+               ]
+		for url in urls:
+			yield scrapy.Request(url=url, callback=self.parse)
+
+	def parse(self, response):
+		pagination = response.css('div.bdaia-pagination').css('a::attr(href)').extract()
+		if ( len(pagination) > 0 ):
+			pagination = pagination[-2].strip('/')
+			pages = int(pagination[pagination.rfind('/')+1:])
+			for page in range(0, pages):
+				if ( page == 0 ):
+					yield scrapy.Request(url=response.url, callback=self.parse_page, dont_filter=True)
+				else:
+					yield scrapy.Request(url=response.url+"page/"+str(page+1), callback=self.parse_page)
+		else:
+			yield scrapy.Request(url=response.url, callback=self.parse_page, dont_filter=True)
+
+	def parse_page(self, response):
+		for link in response.xpath('//article/header/h2/a/@href').extract():
+		 	yield scrapy.Request(url=link, callback=self.parse_item)
+
+	def parse_item(self, response):
+		item = NoticiasItem()
+		text = ''
+		item['title'] = response.css('h1.post-title').xpath('./span/text()').extract_first()
+		item['date'] = self.year+'-'+self.month+'-'+self.day
+		item['topic'] = response.css('div.bdaia-category').xpath('./a/text()').extract_first()
+		for paragraph in response.css('div.bdaia-post-content').css('p').extract():
+			text += remove_tags(paragraph) + '\n'
+		item['text'] = text
+		item['url'] = response.url
+		print item['title']
+		yield item
+

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

notisureste/notisureste/spiders/noticias.py

@@ -9,13 +9,13 @@ def remove_tags(text):
         return TAG_RE.sub('', text)
 
 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()
+    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"
@@ -31,13 +31,15 @@ class QuotesSpider(scrapy.Spider):
 			yield scrapy.Request(url=url, callback=self.parse)
 
 	def parse(self, response):
-		pages = response.css('div.page-nav').css('a.last::attr(title)').extract_first()
-		if ( pages ):
-			for p in range(0,int(pages)):
-				if ( p == 0 ):
-					yield scrapy.Request(url=response.url+"/page/"+str(p+1), callback=self.parse_page, dont_filter=True)
+		pagination = response.css('div.page-nav').css('a::attr(href)').extract()
+		if ( len(pagination) > 0 ):
+			pagination = pagination[-2].strip('/')
+			pages = int(pagination[pagination.rfind('/')+1:])
+			for page in range(0,int(pages)):
+				if ( page == 0 ):
+					yield scrapy.Request(url=response.url, callback=self.parse_page, dont_filter=True)
 				else:
-					yield scrapy.Request(url=response.url+"/page/"+str(p+1), callback=self.parse_page)
+					yield scrapy.Request(url=response.url+"page/"+str(page+1), callback=self.parse_page)
 		else:
 			yield scrapy.Request(url=response.url, callback=self.parse_page, dont_filter=True)
 
@@ -47,10 +49,14 @@ class QuotesSpider(scrapy.Spider):
 
 	def parse_item(self, response):
 		item = NoticiasItem()
+		text = ''
 		item['title'] = response.css('div.td-post-header').css('h1.entry-title::text').extract_first()
 		item['date'] = response.css('div.td-post-header').css('span.td-post-date').css('time::attr(datetime)').extract_first()
-		item['text'] = response.css('div.td-post-content').css('p::text').extract() #probar con for
 		item['url'] = response.url
+		item['topic'] = response.xpath('//ul[@class="td-category"]/li/a/text()').extract()
+		for paragraph in response.css('div.td-post-content').css('p').extract():
+			text += remove_tags(paragraph) + '\n'
+		item['text'] = text
 		print item['title']
 		yield item
 

puntoMedio/puntoMedio/spiders/noticias.py

@@ -6,7 +6,7 @@ import re
 
 TAG_RE = re.compile(r'<[^>]+>')
 def remove_tags(text):
-        return TAG_RE.sub('', text)
+    return TAG_RE.sub('', text)
 
 class NoticiasItem(scrapy.Item):
     title = scrapy.Field()

sona893/sona893/spiders/noticias.py

@@ -6,16 +6,16 @@ import re
 
 TAG_RE = re.compile(r'<[^>]+>')
 def remove_tags(text):
-        return TAG_RE.sub('', text)
+    return TAG_RE.sub('', text)
 
 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()
+    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"
@@ -31,20 +31,29 @@ class QuotesSpider(scrapy.Spider):
 			yield scrapy.Request(url=url, callback=self.parse)
 
 	def parse(self, response):
-		pagination = response.css('div.pagination').css('a::attr(href)')[-1].extract().strip('/')
-		pages = int(pagination[pagination.rfind('/')+1:])
-		for page in range(0, pages):
-			if ( page == 0 ):
-				yield scrapy.Request(url=response.url, callback=self.parse_page, dont_filter=True)
-			else:
-				yield scrapy.Request(url=response.url+"page/"+str(page+1), callback=self.parse_page)
+		pagination = response.css('div.pagination').css('a::attr(href)').extract()
+		if ( len(pagination) > 0 ):
+			pagination = pagination[-1].strip('/')
+			pages = int(pagination[pagination.rfind('/')+1:])
+			for page in range(0, pages):
+				if ( page == 0 ):
+					yield scrapy.Request(url=response.url, callback=self.parse_page, dont_filter=True)
+				else:
+					yield scrapy.Request(url=response.url+"page/"+str(page+1), callback=self.parse_page)
+		else:
+			yield scrapy.Request(url=response.url, callback=self.parse_page, dont_filter=True)
 
 	def parse_page(self, response):
-		for link in response.css('div.mosaicflow').css('h1').css('a::attr(href)').extract():
-		 	yield scrapy.Request(url=link, callback=self.parse_item)
+		item = NoticiasItem()
+		for post in response.css('div.mosaicflow').css('div.post'):
+			item['topic'] = post.css('a.custom_cat_class_Kesha::text').extract_first()
+			item['author'] = post.css('div.cat_author::text').extract_first()
+			request = scrapy.Request(url=post.xpath('./h1/a/@href').extract_first(), callback=self.parse_item)
+			request.meta['item'] = item
+			yield request
 
 	def parse_item(self, response):
-		item = NoticiasItem()
+		item = response.meta['item']
 		text = ''
 		item['title'] = response.css('div.single_title').css('h1::text').extract_first()
 		item['date'] = response.xpath('/html/head/meta[10]').css('::attr(content)').extract_first()

yucatanALaMano/yucatanALaMano/spiders/noticias.py

@@ -6,16 +6,16 @@ import re
 
 TAG_RE = re.compile(r'<[^>]+>')
 def remove_tags(text):
-        return TAG_RE.sub('', text)
+    return TAG_RE.sub('', text)
 
 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()
+    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"
@@ -31,13 +31,17 @@ class QuotesSpider(scrapy.Spider):
 			yield scrapy.Request(url=url, callback=self.parse)
 
 	def parse(self, response):
-		pagination = response.css('div.pagination').css('a::attr(href)')[-1].extract().strip('/')
-		pages = int(pagination[pagination.rfind('/')+1:])
-		for page in range(0, pages):
-			if ( page == 0 ):
-				yield scrapy.Request(url=response.url, callback=self.parse_page, dont_filter=True)
-			else:
-				yield scrapy.Request(url=response.url+"page/"+str(page+1), callback=self.parse_page)
+		pagination = response.css('div.pagination').css('a::attr(href)').extract()
+		if ( len(pagination) > 0 ):
+			pagination = pagination[-1].strip('/')
+			pages = int(pagination[pagination.rfind('/')+1:])
+			for page in range(0, pages):
+				if ( page == 0 ):
+					yield scrapy.Request(url=response.url, callback=self.parse_page, dont_filter=True)
+				else:
+					yield scrapy.Request(url=response.url+"/page/"+str(page+1), callback=self.parse_page)
+		else:
+			yield scrapy.Request(url=response.url, callback=self.parse_page, dont_filter=True)
 
 	def parse_page(self, response):
 		for link in response.css('div.bp-head').css('h2').css('a::attr(href)').extract():

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

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

yucatanEnCorto/yucatanEnCorto/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 YucatanencortoSpiderMiddleware(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)

yucatanEnCorto/yucatanEnCorto/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 YucatanencortoPipeline(object):
+    def process_item(self, item, spider):
+        return item

yucatanEnCorto/yucatanEnCorto/settings.py

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

yucatanEnCorto/yucatanEnCorto/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.

yucatanEnCorto/yucatanEnCorto/spiders/noticias.py

+import scrapy
+
+#scrapy crawl noticias -t json --nolog -o noticias.json -a year=2017 -a month=3 -a day=22
+
+import re
+
+TAG_RE = re.compile(r'<[^>]+>')
+def remove_tags(text):
+   return TAG_RE.sub('', text)
+
+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://florcastillo.mx/noticias/'+year+'/'+month+'/'+day
+		urls = [
+			self.baseURL,
+               ]
+		for url in urls:
+			yield scrapy.Request(url=url, callback=self.parse)
+
+	def parse(self, response):
+		pagination = response.css('div.pagination').css('a::attr(href)').extract()
+		if ( len(pagination) > 0 ):
+			pagination = pagination[-1]
+			pages = int(pagination[pagination.rfind('/')+1:])
+			for page in range(0, pages):
+				if ( page == 0 ):
+					yield scrapy.Request(url=response.url, callback=self.parse_page, dont_filter=True)
+				else:
+					yield scrapy.Request(url=response.url+"/page/"+str(page+1), callback=self.parse_page)
+		else:
+			yield scrapy.Request(url=response.url, callback=self.parse_page, dont_filter=True)
+
+	def parse_page(self, response):
+		for link in response.css('div.list-block').xpath('./h3/a/@href').extract():
+		 	yield scrapy.Request(url=link, callback=self.parse_item)
+
+	def parse_item(self, response):
+		item = NoticiasItem()
+		text = ''
+		item['title'] = response.css('div.post-title').css('h1.entry-title::text').extract_first()
+		item['date'] = response.xpath('//meta[@property="article:published_time"]/@content').extract_first()
+		item['topic'] = response.xpath('//ul[@id="tpcrn-breadcrumbs"]/li[2]/a/text()').extract_first()[:-2]
+		for paragraph in response.css('div.post_content').css('p').extract():
+			text += remove_tags(paragraph) + '\n'
+		item['text'] = text
+		item['url'] = response.url
+		print item['title']
+		yield item
+