Ajustes.

lajornada/lajornada/spiders/noticias.py

@@ -7,10 +7,14 @@ uso:
 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()
@@ -20,6 +24,7 @@ class NoticiasItem(scrapy.Item):
 	topic = scrapy.Field()
 	url = scrapy.Field()
 
+
 class NoticiasSpider(scrapy.Spider):
 	name = "noticias"
 
@@ -32,20 +37,21 @@ class NoticiasSpider(scrapy.Spider):
 		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",
+		   # 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."""
 		
@@ -54,6 +60,7 @@ class NoticiasSpider(scrapy.Spider):
 			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."""
 		
@@ -65,5 +72,3 @@ class NoticiasSpider(scrapy.Spider):
 		item['text'] = remove_tags( response.css('div.text').extract_first() )
 		item['topic'] = response.css('img.title::attr(title)').extract_first()
 		yield item
\ No newline at end of file
-
-