Nueva versión.

README.md

@@ -51,6 +51,16 @@ Se incluyen los siguientes medios:
 	scrapy crawl noticias -t json --nolog -o noticias.json -a year=2017 -a month=3 -a day=26
 	```
 	No se encontró notas antes del 2013.11.04.
+* [La Jornada (Nueva versión)](http://www.jornada.unam.mx)
+
+	Nueva versión del Crawler de La Jornada
+	Uso:
+
+	```bash
+	cd laJornada
+	scrapy crawl noticias -t json --nolog -o noticias.json -a year=2017 -a month=4 -a day=23
+	```
+	No se encontró notas antes del 2005.02.01.
 * [La Jornada Aguascalientes](http://www.lja.mx/)
 
 

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/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 LajornadaSpiderMiddleware(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)

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)'
+
+# 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 = {
+#    'laJornada.middlewares.LajornadaSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'laJornada.middlewares.MyCustomDownloaderMiddleware': 543,
+#}
+
+# 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 = {
+#    'laJornada.pipelines.LajornadaPipeline': 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'

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

+from datetime import date
+import scrapy
+
+
+# scrapy crawl noticias -t json --nolog -o noticias.json -a year=2017 -a month=3 -a day=22
+
+import re
+
+TAG_RE = re.compile(r'<[^>]+>')
+def remove_tags(text):
+    return TAG_RE.sub('', text)
+
+
+class NoticiasItem(scrapy.Item):
+    title = scrapy.Field()
+    text = scrapy.Field()
+    date = scrapy.Field()
+    location = scrapy.Field()
+    author = scrapy.Field()
+    topic = scrapy.Field()
+    url = scrapy.Field()
+
+
+class QuotesSpider(scrapy.Spider):
+	name = "noticias"
+	def start_requests(self):
+		self.year = getattr(self, 'year', None)
+		self.month = getattr(self, 'month', None)
+		self.day = getattr(self, 'day', None)
+		self.baseURL='http://www.jornada.unam.mx/'+self.year+'/'+self.month.zfill(2)+'/'+self.day.zfill(2)+'/'
+		
+		comparison_date = date(2009, 2, 15)
+		requested_date = date(int(self.year), int(self.month), int(self.day))
+
+		section_list = ['opinion', 'politica', 'economia', 'mundo', 'estados', 'ciencias',
+						'capital', 'sociedad', 'cultura', 'espectaculos', 'deportes']
+
+		for section in section_list:
+			# para la fecha 2009.02.15 o menores, se tiene una estructura determinada de página
+			# para las fechas mayores a esa la estructura cambia
+			if ( requested_date <= comparison_date ):
+				yield scrapy.Request(url=self.baseURL+section, callback=self.parse)
+			else:
+				yield scrapy.Request(url=self.baseURL+section, callback=self.parse_2)
+
+
+	def parse(self, response):
+		if ( response.url[:response.url.rfind('/')+1] == self.baseURL ):   # verifica que se conserva la misma URL base
+			section = response.url[response.url.rfind('/')+1:]
+			if ( section == 'opinion' ):   # la sección 'opinión' tiene una estructura diferente a las demás
+				path_list = ['//*[@id="columnas"]/p/a/@href',
+							 '//*[@id="opinion"]/p/a/@href']
+			else:
+				path_list = ['//*[@id="article_list"]/h2/a/@href',
+						 	 '//*[@id="article_list"]/h3/a/@href']
+
+			for path in path_list:
+				for link in response.xpath(path).extract():
+					yield scrapy.Request(url=self.baseURL+link, callback=self.parse_item)
+
+
+	def parse_2(self, response):
+		if ( response.url[:response.url.rfind('/')+1] == self.baseURL ):
+			path_list = ['//*[@class="itemfirst"]/div/a/@href', '//*[@class="item start"]/div/a/@href',
+						 '//*[@class="item"]/div/a/@href']
+
+			for path in path_list:
+				for link in response.xpath(path).extract():
+					yield scrapy.Request(url=self.baseURL+link, callback=self.parse_item_2)
+
+
+	def parse_item(self, response):
+		item = NoticiasItem()
+		text = ''
+		item['date'] = self.year+'-'+self.month.zfill(2)+'-'+self.day.zfill(2)
+		title = response.xpath('//*[@class="documentContent"]/h1[@class="title"]/text()').extract()
+		if ( len(title) > 0 ):
+			item['title'] = title[0]
+		else:
+			item['title'] = response.xpath('//*[@class="documentContent"]/h1/text()').extract_first()
+		item['topic'] = response.xpath('//*[@id="portal-breadcrumbs"]/a[2]/text()').extract()
+		for paragraph in response.xpath('//*[@class="documentContent"]/p/text()').extract():
+			text += paragraph
+		item['text'] = text
+		item['url'] = response.url
+		# print item['title']
+		yield item
+
+
+	def parse_item_2(self, response):
+		item = NoticiasItem()
+		text = ''
+		path_list = ['//*[@class="col"]/p', '//*[@class="col col1"]/p', '//*[@class="col col2"]/p']
+		
+		item['date'] = self.year+'-'+self.month.zfill(2)+'-'+self.day.zfill(2)
+		item['title'] = remove_tags(response.xpath('//*[@class="cabeza"]').extract_first())
+		item['topic'] = response.xpath('//*[@class="breadcrumb gui"]/span[2]/a/text()').extract()
+
+		for path in path_list: 
+			for paragraph in response.xpath(path).extract():
+				text += remove_tags(paragraph)
+		item['text'] = text
+		item['url'] = response.url
+		# print item['title']
+		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