Se agregan: al chile, grillo porteño, la verdad yucatan, mi punto de vista,...

Se agregan: al chile, grillo porteño, la verdad yucatan, mi punto de vista, notisureste, sona 89.3, yucatan a la mano, yucatan ahora, yucatan al minuto.

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

alChile/alChile/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 AlchileSpiderMiddleware(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)

alChile/alChile/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 AlchilePipeline(object):
+    def process_item(self, item, spider):
+        return item

alChile/alChile/settings.py

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

alChile/alChile/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.

alChile/alChile/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://alchile.com.mx/'+year+'/'+month+'/'+day
+		urls = [
+			self.baseURL,
+                ]
+		for url in urls:
+			yield scrapy.Request(url=url, callback=self.parse)
+
+	def parse(self, response):
+		pages = response.css('div.page-nav').css('a.last::attr(href)').extract_first().strip('/')
+		pages =  int(pages[pages.rfind('/')+1:])
+		for p in range(0,pages):
+			if ( p == 0 ):
+				yield scrapy.Request(url=response.url+"/page/"+str(p+1), callback=self.parse_page, dont_filter=True)
+			else:
+				yield scrapy.Request(url=response.url+"/page/"+str(p+1), callback=self.parse_page)
+
+	def parse_page(self, response):
+		for link in response.css('div.td-block-span6').css('h3.entry-title').css('a::attr(href)').extract():
+			yield scrapy.Request(url=link, callback=self.parse_item)
+
+	def parse_item(self, response):
+		item = NoticiasItem()
+		item['title'] = response.css('header.td-post-title').css('h1.entry-title::text').extract_first()
+		item['date'] = response.css('span.td-post-date').css('time.entry-date::attr(datetime)').extract_first()
+		item['topic'] = response.css('div.td-post-header').css('a::text').extract_first()
+		item['text'] = response.css('div.td-post-content').css('p::text').extract()
+		item['url'] = response.url
+		print item['title']
+		yield item
+

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

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

grilloPorteno/grilloPorteno/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 GrilloportenoSpiderMiddleware(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)

grilloPorteno/grilloPorteno/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 GrilloportenoPipeline(object):
+    def process_item(self, item, spider):
+        return item

grilloPorteno/grilloPorteno/settings.py

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

grilloPorteno/grilloPorteno/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.

grilloPorteno/grilloPorteno/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://grilloporteno.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.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)
+
+	def parse_page(self, response):
+		for link in response.css('div.bp-head').css('h2').css('a::attr(href)').extract():
+		 	yield scrapy.Request(url=link, callback=self.parse_item)
+
+	def parse_item(self, response):
+		item = NoticiasItem()
+		text = ''
+		item['title'] = response.xpath('/html/body/div/div[2]/div[4]/div[1]/div[1]/div[2]/h1/text()').extract_first()
+		item['date'] = response.css('div.mom-post-meta').css('span').css('time::attr(datetime)').extract_first()
+		item['topic'] = response.css('div.breadcrumbs-plus').css('span').css('a::attr(title)').extract_first()
+		for paragraph in response.css('div.entry-content').css('p').extract():
+			text += remove_tags(paragraph) + '\n'
+		item['text'] = text
+		item['url'] = response.url
+		print item['title']
+		yield item
+

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

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

laVerdadYuc/laVerdadYuc/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 LaverdadyucSpiderMiddleware(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)

laVerdadYuc/laVerdadYuc/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 LaverdadyucPipeline(object):
+    def process_item(self, item, spider):
+        return item

laVerdadYuc/laVerdadYuc/settings.py

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

laVerdadYuc/laVerdadYuc/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.

laVerdadYuc/laVerdadYuc/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://laverdadnoticias.com/'+year+'/'+month+'/'+day
+		urls = [
+			self.baseURL,
+                ]
+		for url in urls:
+			yield scrapy.Request(url=url, callback=self.parse)
+
+	def parse(self, response):
+		pages = response.css("div.pagination_div").css("a::attr(href)")[-2].extract().strip('/')
+		pages =  int(pages[pages.rfind('/')+1:])
+		for p in range(0,pages):
+			if ( p == 0 ):
+				yield scrapy.Request(url=response.url+"/page/"+str(p+1), callback=self.parse_page, dont_filter=True)
+			else:
+				yield scrapy.Request(url=response.url+"/page/"+str(p+1), callback=self.parse_page)
+
+	def parse_page(self, response):
+		linkList = response.css("div.cp-post-content").css("h3").css("a::attr(href)").extract()
+		for link in range(0,len(linkList)-3):
+			yield scrapy.Request(url=linkList[link], callback=self.parse_item)
+
+	def parse_item(self, response):
+		item = NoticiasItem()
+		item['title'] = response.css("div.cp-post-content").css("h1").css("a::text").extract_first()
+		print item['title']
+		item['date'] = response.xpath("//meta[@property=$val]/@content", val="article:published_time").extract()
+		item['text'] = remove_tags( response.css("div.cp-post-content").css("p").extract_first() )
+		item['url'] = response.url
+		yield item
\ No newline at end of file

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

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

miPuntoDeVista/miPuntoDeVista/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 MipuntodevistaSpiderMiddleware(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)

miPuntoDeVista/miPuntoDeVista/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 MipuntodevistaPipeline(object):
+    def process_item(self, item, spider):
+        return item

miPuntoDeVista/miPuntoDeVista/settings.py

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

miPuntoDeVista/miPuntoDeVista/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.

miPuntoDeVista/miPuntoDeVista/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.mipuntodevista.com.mx/'+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.page-nav').css('a::attr(href)')[-1].extract().strip('/')
+		if ( pagination ):
+			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('h3.entry-title').css('a::attr(href)').extract():
+		 	yield scrapy.Request(url=link, callback=self.parse_item)
+
+	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['author'] = response.css('div.td-post-author-name').css('a::text').extract_first()
+		for paragraph in response.css('div.td-post-content').css('p').extract():
+			text += remove_tags(paragraph) + '\n'
+		item['text'] = text
+		item['url'] = response.url
+		print item['title']
+		yield item
+

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

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

notisureste/notisureste/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 NotisuresteSpiderMiddleware(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)

notisureste/notisureste/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 NotisurestePipeline(object):
+    def process_item(self, item, spider):
+        return item

notisureste/notisureste/settings.py

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

notisureste/notisureste/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.

notisureste/notisureste/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.notisureste.com/'+year+'/'+month+'/'+day
+		urls = [
+			self.baseURL,
+                ]
+		for url in urls:
+			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)
+				else:
+					yield scrapy.Request(url=response.url+"/page/"+str(p+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.td-ss-main-content').css('h3.entry-title').css('a::attr(href)').extract():
+			yield scrapy.Request(url=link, callback=self.parse_item)
+
+	def parse_item(self, response):
+		item = NoticiasItem()
+		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
+		print item['title']
+		yield item
+

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

sona893/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 = sona893.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = sona893

sona893/sona893/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 Sona893Item(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    pass

sona893/sona893/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 Sona893SpiderMiddleware(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)

sona893/sona893/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 Sona893Pipeline(object):
+    def process_item(self, item, spider):
+        return item

sona893/sona893/settings.py

+# -*- coding: utf-8 -*-
+
+# Scrapy settings for sona893 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 = 'sona893'
+
+SPIDER_MODULES = ['sona893.spiders']
+NEWSPIDER_MODULE = 'sona893.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'sona893 (+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 = {
+#    'sona893.middlewares.Sona893SpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'sona893.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 = {
+#    'sona893.pipelines.Sona893Pipeline': 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'

sona893/sona893/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.

sona893/sona893/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://sona893.fm/'+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)')[-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)
+
+	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)
+
+	def parse_item(self, response):
+		item = NoticiasItem()
+		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()
+		for paragraph in response.css('div.single_text').css('p').extract():
+			text += remove_tags(paragraph) + '\n'
+		item['text'] = text
+		item['url'] = response.url
+		print item['title']
+		yield item
+

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

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

yucatanALaMano/yucatanALaMano/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 YucatanalamanoSpiderMiddleware(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)

yucatanALaMano/yucatanALaMano/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 YucatanalamanoPipeline(object):
+    def process_item(self, item, spider):
+        return item

yucatanALaMano/yucatanALaMano/settings.py

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

yucatanALaMano/yucatanALaMano/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.

yucatanALaMano/yucatanALaMano/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.yucatanalamano.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.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)
+
+	def parse_page(self, response):
+		for link in response.css('div.bp-head').css('h2').css('a::attr(href)').extract():
+		 	yield scrapy.Request(url=link, callback=self.parse_item)
+
+	def parse_item(self, response):
+		item = NoticiasItem()
+		text = ''
+		item['title'] = response.css('div.main_container').css('h1.post-tile::text').extract_first()
+		item['date'] = response.css('div.mom-post-meta').css('span').css('time::attr(datetime)').extract_first()
+		item['topic'] = response.css('div.breadcrumbs-plus').css('span').css('a::attr(title)').extract_first()
+		for paragraph in response.css('div.entry-content').css('p').extract():
+			text += remove_tags(paragraph) + '\n'
+		item['text'] = text
+		item['url'] = response.url
+		print item['title']
+		yield item
+

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

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