upload files

README.md

+Crawlers para medios de información en linea nacionales basados en [Scrapy] (http://scrapy.org/)
+
+Se incluyen los siguientes medios:
+* [La Jornada](http://www.lajornada.unam.mx)
+
+
+	Uso:
+
+	```bash
+	cd laJornada
+	scrapy crawl noticias -t json --nolog -o noticias.json -a year=2016 month=12 day=24
+	```
+* [Diario de Yucatán](http://www.yucatan.com)
+
+
+	Uso:
+
+	```bash
+	cd diarioYucatan
+	scrapy crawl noticias -t json --nolog -o noticias.json -a year=2016 month=12 day=24
+	```
+* [Yucatán al Minuto](http://www.yucatanalminuto.com/)

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

diarioYucatan/diarioYucatan/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 DiarioyucatanPipeline(object):
+    def process_item(self, item, spider):
+        return item

diarioYucatan/diarioYucatan/settings.py

+# -*- coding: utf-8 -*-
+
+# Scrapy settings for diarioYucatan 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 = 'diarioYucatan'
+
+SPIDER_MODULES = ['diarioYucatan.spiders']
+NEWSPIDER_MODULE = 'diarioYucatan.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'diarioYucatan (+http://www.yourdomain.com)'
+
+# 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 = {
+#    'diarioYucatan.middlewares.MyCustomSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'diarioYucatan.middlewares.MyCustomDownloaderMiddleware': 543,
+#}
+
+# Enable or disable extensions
+# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
+#EXTENSIONS = {
+#    'scrapy.telnet.TelnetConsole': None,
+#}
+
+# Configure item pipelines
+# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
+#ITEM_PIPELINES = {
+#    'diarioYucatan.pipelines.SomePipeline': 300,
+#}
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See http://doc.scrapy.org/en/latest/topics/autothrottle.html
+# NOTE: AutoThrottle will honour the standard settings for concurrency and delay
+#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
+# 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'

diarioYucatan/diarioYucatan/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.

diarioYucatan/diarioYucatan/spiders/noticias.py

+import scrapy
+
+
+#scrapy crawl noticias -t json --nolog -o noticias.json -a year=2016 month=12 day=24
+
+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://yucatan.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.pagination").css("a::attr(href)")[-1].extract()
+		pages =  int(pages[pages.rfind('/')+1:])
+		for p in range(0,pages):
+			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.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()
+		item['title'] = response.css("h1.entry-title::text").extract_first()
+		item['date'] = response.css("div.base-box").css("span.entry-date::attr(datetime)").extract_first()
+		item['text'] = response.css("div.entry-content").css("p::text").extract()
+		item['url'] = response.url
+		yield item
+

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

lajornada/laJornadaCrawler.sh

+#!/bin/bash
+
+
+for y in `seq 2010 2016`;
+do
+	if [ ! -d $y ]; then
+	  mkdir -p $y;
+	fi
+	cd $y
+	for m in $(seq -f "%02g" 1 12)
+	do
+		for d in $(seq -f "%02g" 1 31)
+		do
+			scrapy crawl noticias -t json -o - > laJornada_$y-$m-$d.json -a year=$y -a month=$m -a day=$d
+# 			jsonlint-py -f laJornada_$y-$m-$d.json > laJornada_$y-$m-$d.json 
+		done
+	done
+	cd .. 
+done
+

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

lajornada/lajornada/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 LajornadaPipeline(object):
+    def process_item(self, item, spider):
+        return item

lajornada/lajornada/settings.py

+# -*- coding: utf-8 -*-
+
+# Scrapy settings for lajornada 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 = 'lajornada'
+
+SPIDER_MODULES = ['lajornada.spiders']
+NEWSPIDER_MODULE = 'lajornada.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'lajornada (+http://www.yourdomain.com)'
+
+# 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 = {
+#    'lajornada.middlewares.MyCustomSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'lajornada.middlewares.MyCustomDownloaderMiddleware': 543,
+#}
+
+# Enable or disable extensions
+# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
+#EXTENSIONS = {
+#    'scrapy.telnet.TelnetConsole': None,
+#}
+
+# Configure item pipelines
+# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
+#ITEM_PIPELINES = {
+#    'lajornada.pipelines.SomePipeline': 300,
+#}
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See http://doc.scrapy.org/en/latest/topics/autothrottle.html
+# NOTE: AutoThrottle will honour the standard settings for concurrency and delay
+#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
+# 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'

lajornada/lajornada/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.

lajornada/lajornada/spiders/noticias.py

+"""@package laJornada_scrapy
+Crawlwer para la jornada.unam.mx
+uso:
+#scrapy crawl noticias -t json --nolog -o noticias.json -a year=2016 month=12 day=24
+"""
+
+import scrapy
+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 NoticiasSpider(scrapy.Spider):
+	name = "noticias"
+
+	def start_requests(self):

+        """Lista de url a explorar."""
+
+		year = getattr(self, 'year', None)
+		month = getattr(self, 'month', None)
+		day = getattr(self, 'day', None)
+		self.baseURL='http://www.jornada.unam.mx/'+year+'/'+month+'/'+day+'/'
+		urls = [
+		   self.baseURL+"opinion",
+		   self.baseURL+"politica",
+		   self.baseURL+"economia",
+		   self.baseURL+"mundo",
+		   self.baseURL+"estados",
+		   self.baseURL+"capital",
+		   self.baseURL+"sociedad",
+		   self.baseURL+"ciencias",
+		   self.baseURL+"cultura",
+		   self.baseURL+"espectaculos",
+		   self.baseURL+"deporte",
+		]
+		for url in urls:
+			yield scrapy.Request(url=url, callback=self.parse)
+
+	def parse(self, response):
+        """parser principal."""
+
+		item = NoticiasItem()
+		for noticia in response.css('a.cabeza'):
+ 			url = self.baseURL + noticia.css('::attr(href)').extract_first()
+			yield scrapy.Request(url, callback=self.parse_dir_contents)
+
+	def parse_dir_contents(self, response):
+        """Parser para la pagina de cada noticia."""
+
+		item = NoticiasItem()
+		item['title'] = response.css('div.cabeza::text').extract_first()
+		item['url'] = response.url
+		item['author'] = response.css('div.credito-autor::text').extract_first()
+		item['location'] = response.css('p.s-s::text').extract_first()
+		item['text'] = remove_tags( response.css('div.text').extract_first() )
+		item['topic'] = response.css('img.title::attr(title)').extract_first()
+		yield item
+
+

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

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

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

yucatanAlMinuto/yucatanAlMinuto/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 YucatanalminutoPipeline(object):
+    def process_item(self, item, spider):
+        return item

yucatanAlMinuto/yucatanAlMinuto/settings.py

+# -*- coding: utf-8 -*-
+
+# Scrapy settings for yucatanAlMinuto 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 = 'yucatanAlMinuto'
+
+SPIDER_MODULES = ['yucatanAlMinuto.spiders']
+NEWSPIDER_MODULE = 'yucatanAlMinuto.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'yucatanAlMinuto (+http://www.yourdomain.com)'
+
+# 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 = {
+#    'yucatanAlMinuto.middlewares.MyCustomSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'yucatanAlMinuto.middlewares.MyCustomDownloaderMiddleware': 543,
+#}
+
+# Enable or disable extensions
+# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
+#EXTENSIONS = {
+#    'scrapy.telnet.TelnetConsole': None,
+#}
+
+# Configure item pipelines
+# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
+#ITEM_PIPELINES = {
+#    'yucatanAlMinuto.pipelines.SomePipeline': 300,
+#}
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See http://doc.scrapy.org/en/latest/topics/autothrottle.html
+# NOTE: AutoThrottle will honour the standard settings for concurrency and delay
+#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
+# 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'

yucatanAlMinuto/yucatanAlMinuto/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.