crawlers

descarga_por_dia/unoMasUno/unoMasUno/spiders/noticias.py

@@ -41,9 +41,9 @@ class QuotesSpider(scrapy.Spider):
 		year = getattr(self, 'year', None)
 		month = getattr(self, 'month', None)
 		day = getattr(self, 'day', None)
-		self.date_parser = {'enero': 1,      'febrero': 2,  'marzo': 3,     'abril': 4,
-												'mayo': 5,       'junio': 6,    'julio': 7,     'agosto': 8,
-												'septiembre': 9, 'octubre': 10, 'noviembre': 11, 'diciembre': 12}
+		self.date_parser = {'enero': 1,      'febrero': 2,  'marzo': 3,      'abril': 4,
+							'mayo': 5,       'junio': 6,    'julio': 7,      'agosto': 8,
+							'septiembre': 9, 'octubre': 10, 'noviembre': 11, 'diciembre': 12}
 		
 		self.baseURL='http://www.unomasuno.com.mx/'+year+'/'+month+'/'+day
 		

descarga_por_mes/proceso/proceso/spiders/noticias.py

@@ -45,8 +45,8 @@ class QuotesSpider(scrapy.Spider):
 		month = getattr(self, 'month', None)
 		# day = getattr(self, 'day', None)
 		parse_month = {'1': 'enero',       '2': 'febrero',  '3': 'marzo',      '4': 'abril',
-									 '5': 'mayo',        '6': 'junio',    '7': 'julio',      '8': 'agosto',
-									 '9': 'septiembre', '10': 'octubre', '11': 'noviembre', '12': 'diciembre'}
+					   '5': 'mayo',        '6': 'junio',    '7': 'julio',      '8': 'agosto',
+					   '9': 'septiembre', '10': 'octubre', '11': 'noviembre', '12': 'diciembre'}
 		
 		self.date = parse_month[month]+' de '+year
 

descarga_por_rss/elFinanciero/elFinanciero/items.py

+# -*- coding: utf-8 -*-
+
+# Define here the models for your scraped items
+#
+# See documentation in:
+# http://doc.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class ElfinancieroItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    pass

descarga_por_rss/elFinanciero/elFinanciero/middlewares.py

+# -*- coding: utf-8 -*-
+
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# http://doc.scrapy.org/en/latest/topics/spider-middleware.html
+
+from scrapy import signals
+
+
+class ElfinancieroSpiderMiddleware(object):
+    # Not all methods need to be defined. If a method is not defined,
+    # scrapy acts as if the spider middleware does not modify the
+    # passed objects.
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # This method is used by Scrapy to create your spiders.
+        s = cls()
+        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
+        return s
+
+    def process_spider_input(response, spider):
+        # Called for each response that goes through the spider
+        # middleware and into the spider.
+
+        # Should return None or raise an exception.
+        return None
+
+    def process_spider_output(response, result, spider):
+        # Called with the results returned from the Spider, after
+        # it has processed the response.
+
+        # Must return an iterable of Request, dict or Item objects.
+        for i in result:
+            yield i
+
+    def process_spider_exception(response, exception, spider):
+        # Called when a spider or process_spider_input() method
+        # (from other spider middleware) raises an exception.
+
+        # Should return either None or an iterable of Response, dict
+        # or Item objects.
+        pass
+
+    def process_start_requests(start_requests, spider):
+        # Called with the start requests of the spider, and works
+        # similarly to the process_spider_output() method, except
+        # that it doesn’t have a response associated.
+
+        # Must return only requests (not items).
+        for r in start_requests:
+            yield r
+
+    def spider_opened(self, spider):
+        spider.logger.info('Spider opened: %s' % spider.name)

descarga_por_rss/elFinanciero/elFinanciero/pipelines.py

+# -*- coding: utf-8 -*-
+
+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html
+
+
+class ElfinancieroPipeline(object):
+    def process_item(self, item, spider):
+        return item

descarga_por_rss/elFinanciero/elFinanciero/settings.py

+# -*- coding: utf-8 -*-
+
+# Scrapy settings for elFinanciero project
+#
+# For simplicity, this file contains only settings considered important or
+# commonly used. You can find more settings consulting the documentation:
+#
+#     http://doc.scrapy.org/en/latest/topics/settings.html
+#     http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#     http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+
+BOT_NAME = 'elFinanciero'
+
+SPIDER_MODULES = ['elFinanciero.spiders']
+NEWSPIDER_MODULE = 'elFinanciero.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'elFinanciero (+http://www.yourdomain.com)'
+
+# Obey robots.txt rules
+ROBOTSTXT_OBEY = True
+
+# Configure maximum concurrent requests performed by Scrapy (default: 16)
+#CONCURRENT_REQUESTS = 32
+
+# Configure a delay for requests for the same website (default: 0)
+# See http://scrapy.readthedocs.org/en/latest/topics/settings.html#download-delay
+# See also autothrottle settings and docs
+#DOWNLOAD_DELAY = 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 = {
+#    'elFinanciero.middlewares.ElfinancieroSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'elFinanciero.middlewares.MyCustomDownloaderMiddleware': 543,
+#}
+
+# Enable or disable extensions
+# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
+#EXTENSIONS = {
+#    'scrapy.extensions.telnet.TelnetConsole': None,
+#}
+
+# Configure item pipelines
+# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
+#ITEM_PIPELINES = {
+#    'elFinanciero.pipelines.ElfinancieroPipeline': 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_rss/elFinanciero/elFinanciero/spiders/__init__.py

+# This package will contain the spiders of your Scrapy project
+#
+# Please refer to the documentation for information on how to create and manage
+# your spiders.

descarga_por_rss/elFinanciero/elFinanciero/spiders/noticias.py

+import scrapy, re
+from datetime import datetime, timedelta, tzinfo
+
+'''
+scrapy crawl noticias -t json --nolog -o noticias.json
+'''
+
+TAG_RE = re.compile(r'<[^>]+>')
+
+def remove_tags(text):
+    return TAG_RE.sub('', text)
+
+
+class UTC(tzinfo):
+	"""clase para el 'time zone' (zona horaria)"""
+
+	def utcoffset(self, dt):
+		# zona horaria para hidalgo (centro de mexico): utc-6
+		return timedelta(hours=-6)
+
+	def tzname(self, dt):
+		# nombre de la zona horaria
+		return 'UTC-6'
+
+
+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.tz = UTC()
+        self.date_parser = {'enero': 1,      'febrero': 2,  'marzo': 3,      'abril': 4,
+                            'mayo': 5,       'junio': 6,    'julio': 7,      'agosto': 8,
+                            'septiembre': 9, 'octubre': 10, 'noviembre': 11, 'diciembre': 12}
+
+        self.baseURL = 'http://www.elfinanciero.com.mx/rss'
+        yield scrapy.Request(url=self.baseURL, callback=self.parse)
+
+
+    def parse(self, response):
+        for link in response.xpath('//link/text()').extract()[1:]:
+            yield scrapy.Request(url=link, callback=self.parse_item)
+
+
+    def parse_item(self, response):
+        item = NoticiasItem()
+        text = ''
+
+        d = response.xpath('//*[@class="details-box"]/input[@id="publicado"]/@value').extract_first()
+        d = d.replace('/',' ').replace(':',' ').split(' ')
+        item['date'] = datetime(int(d[2]), self.date_parser[d[1].lower()], int(d[0]), int(d[3]), int(d[4]), tzinfo=self.tz).isoformat('T')
+        item['topic'] = response.xpath('//*[@class="article-title"]/span/text()').extract_first()
+        item['title'] = response.xpath('//*[@class="title"]/h1/text()').extract_first()
+        for p in response.xpath('//*[@class="article-paragraphs"]/p').extract():
+            text += remove_tags(p) + '\n'
+        item['text'] = text
+        item['author'] = response.xpath('//*[@class="details-box"]/input[@id="editor"]/@value').extract_first()
+        item['url'] = response.url
+
+        # print item['title']
+        yield item
+

descarga_por_rss/elFinanciero/scrapy.cfg

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

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

descarga_por_rss/elUniversal/elUniversal/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 EluniversalSpiderMiddleware(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_rss/elUniversal/elUniversal/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 EluniversalPipeline(object):
+    def process_item(self, item, spider):
+        return item

descarga_por_rss/elUniversal/elUniversal/settings.py

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

+import scrapy, re
+
+'''
+scrapy crawl noticias -t json --nolog -o noticias.json
+'''
+
+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.baseURL = 'http://www.eluniversal.com.mx/rss.xml'
+        yield scrapy.Request(url=self.baseURL, callback=self.parse)
+
+    def parse(self, response):
+        for link in response.xpath('//link/text()').extract()[1:]:
+            yield scrapy.Request(url=link, callback=self.parse_item)
+
+    def parse_item(self, response):
+        item = NoticiasItem()
+        text = ''
+
+        item['date'] = response.xpath('//meta[@property="article:published_time"]/@content').extract_first()
+        item['topic'] = response.xpath('//*[@class="breadcrumb"]/span/a/text()').extract()[-2]
+        item['title'] = response.xpath('//*[@class="pane-content"]/h1/text()').extract_first()
+        for p in response.xpath('//*[@class="pane-content"]/div/p').extract():
+            text += remove_tags(p) + '\n'
+        item['text'] = text
+        item['location'] = response.xpath('//*[@class="field field-name-field-lugar field-type-text field-label-hidden"]/text()').extract_first()
+        item['author'] = response.xpath('//*[@class="field-items"]/div/text()').extract_first()
+        item['url'] = response.url
+
+        # print item['title']
+        yield item
+

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

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

descarga_por_rss/excelsior/excelsior/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 ExcelsiorSpiderMiddleware(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_rss/excelsior/excelsior/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 ExcelsiorPipeline(object):
+    def process_item(self, item, spider):
+        return item

descarga_por_rss/excelsior/excelsior/settings.py

+# -*- coding: utf-8 -*-
+
+# Scrapy settings for excelsior 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 = 'excelsior'
+
+SPIDER_MODULES = ['excelsior.spiders']
+NEWSPIDER_MODULE = 'excelsior.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'excelsior (+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 = {
+#    'excelsior.middlewares.ExcelsiorSpiderMiddleware': 543,
+    'scrapy_splash.SplashDeduplicateArgsMiddleware': 100,
+}
+
+# Enable or disable downloader middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+DOWNLOADER_MIDDLEWARES = {
+#    'excelsior.middlewares.MyCustomDownloaderMiddleware': 543,
+    'scrapy_splash.SplashCookiesMiddleware': 723,
+	'scrapy_splash.SplashMiddleware': 725,
+	'scrapy.downloadermiddlewares.httpcompression.HttpCompressionMiddleware': 810,
+}
+
+# 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 = {
+#    'excelsior.pipelines.ExcelsiorPipeline': 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'
+HTTPCACHE_STORAGE = 'scrapy_splash.SplashAwareFSCacheStorage'
+
+SPLASH_URL = 'http://localhost:8050/'
+
+DUPEFILTER_CLASS = 'scrapy_splash.SplashAwareDupeFilter'

descarga_por_rss/excelsior/excelsior/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_rss/excelsior/excelsior/spiders/noticias.py

+import scrapy, re
+from datetime import datetime, date, timedelta, tzinfo
+from scrapy_splash import SplashRequest
+
+"""
+Para este sitio se hace uso de 'scrapy-splash' porque el contenido es cargado a traves de javascript
+
+USO:
+scrapy crawl noticias -t json --nolog -o noticias.json
+"""
+
+TAG_RE = re.compile(r'<[^>]+>')
+
+
+def remove_tags(text):
+    return TAG_RE.sub('', text)
+
+
+class UTC(tzinfo):
+    """clase para el 'time zone' (zona horaria)"""
+
+    def utcoffset(self, dt):
+        # zona horaria para el centro de mexico: utc-6
+        return timedelta(hours=-6)
+
+    def tzname(self, dt):
+        # nombre de la zona horaria
+        return 'UTC-6'
+
+
+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.tz = UTC()
+        parse_month = {'1': 'enero',       '2': 'febrero',  '3': 'marzo',      '4': 'abril',
+                       '5': 'mayo',        '6': 'junio',    '7': 'julio',      '8': 'agosto',
+                       '9': 'septiembre', '10': 'octubre', '11': 'noviembre', '12': 'diciembre'}
+
+        self.baseURL = 'http://www.excelsior.com.mx/rss.xml'
+        # yield scrapy.Request(url=self.baseURL, callback=self.parse)
+        yield SplashRequest(url=self.baseURL, callback=self.parse, endpoint='render.html', args={'wait': 0.5})
+
+    # def parse(self, response):
+    #     for post in response.css('div.catpor-box'):
+    #         post_date = post.xpath('./div/span[@class="catpor-published clearfix"]/text()').extract_first()
+    #         post_date = post_date[post_date.find('d') + 3:]
+    #
+    #         if post_date == self.date:
+    #             link = post.xpath('./div/div/a/@href').extract_first()
+    #             yield scrapy.Request(url=link, callback=self.parse_2)
+
+    def parse(self, response):
+        print 'hey'
+        print response.url
+        print response.body
+        print response.xpath('//link').extract()[1:]
+        # for link in response.xpath('//*[@class="post-container clearfix"]/h2/a/@href').extract():
+        #     # yield scrapy.Request(url=link, callback=self.parse_item)
+        #     yield SplashRequest(url=link, callback=self.parse_item, endpoint='render.html', args={'wait': 0.5})
+
+    # def parse_item(self, response):
+    #     item = NoticiasItem()
+    #     text = ''
+    #
+    #     d = response.xpath('//div[@id="primary"]/div/div/div/div/span[@class="published"]/text()').extract_first()
+    #     d, t = d.split(' ')
+    #     d = map(int, d.split('-'))
+    #     t = map(int, t.split(':'))
+    #     d = datetime(d[0], d[1], d[2], t[0], t[1], t[2], tzinfo=self.tz).isoformat('T')
+    #     item['date'] = d
+    #
+    #     item['title'] = response.xpath('//div[@id="primary"]/div/h1/text()').extract_first()
+    #     item['topic'] = response.xpath('//span[@class="entry-categories"]/text()').extract_first()
+    #
+    #     for paragraph in response.xpath('//div[@id="primary"]/div/div/div/div[@class="entry-content"]/div/p').extract():
+    #         text += remove_tags(paragraph) + '\n'
+    #     item['text'] = text
+    #     item['url'] = response.url
+    #
+    #     # print item['title']
+    #     yield item
+

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