crawlers

descarga_por_dia/laJornadaZac/laJornadaZac/spiders/noticias.py

@@ -6,16 +6,18 @@ import re
 
 TAG_RE = re.compile(r'<[^>]+>')
 def remove_tags(text):
-    return TAG_RE.sub('', 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()
+	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"
@@ -26,10 +28,11 @@ class QuotesSpider(scrapy.Spider):
 		self.baseURL='http://ljz.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.xpath('//div[@class="pagination"]/a/@href').extract()
 		if ( len(pagination) > 0 ):
@@ -43,14 +46,16 @@ class QuotesSpider(scrapy.Spider):
 		else:
 			yield scrapy.Request(url=response.url, callback=self.parse_page, dont_filter=True)
 
+
 	def parse_page(self, response):
 		for link in response.xpath('//h2[@class="cat-list-title"]/a/@href').extract():
 			yield scrapy.Request(url=link, callback=self.parse_item)
 
+
 	def parse_item(self, response):
 		item = NoticiasItem()
 		text = ''
-		item['date'] = response.xpath('//time[@class="entry-date updated"]/@datetime').extract_first()
+		item['date'] = response.xpath('//*[@class="entry-post-meta"]').css('time::attr(content)').extract_first()
 		item['title'] = response.xpath('//h1[@class="entry-title"]/text()').extract_first()
 		item['topic'] = response.xpath('//*[@class="entry-cat"]/a/text()').extract_first()