Ajustes por cambios en la página.

otros_sitios/laJornadaSanLuis/laJornadaSanLuis/spiders/noticias.py

@@ -35,7 +35,7 @@ class QuotesSpider(scrapy.Spider):
 
 
 	def parse(self, response):
-		pagination = response.xpath('//div[@class="pagination"]/a/@href').extract()
+		pagination = response.xpath('//div[@class="pages"]/a/@href').extract()
 		if ( len(pagination) > 0 ):
 			pagination = pagination[-1].strip('/')
 			pages = int(pagination[pagination.rfind('/')+1:])
@@ -49,7 +49,7 @@ class QuotesSpider(scrapy.Spider):
 
 
 	def parse_page(self, response):
-		for link in response.xpath('//*[@class="post_title"]/h3/a/@href').extract():
+		for link in response.xpath('//*[@class="post-title"]/h2/a/@href').extract():
 			yield scrapy.Request(url=link, callback=self.parse_item)
 
 
@@ -57,8 +57,8 @@ class QuotesSpider(scrapy.Spider):
 		item = NoticiasItem()
 		text = ''
 		item['date'] = response.xpath('//meta[@property="article:published_time"]/@content').extract_first()
-		item['title'] = response.css('h2.entry-title::text').extract_first()
-		item['topic'] = response.xpath('//span[@class="meta-cat"]/a/text()').extract()
+		item['title'] = response.css('h1.entry-title::text').extract_first()
+		item['topic'] = response.xpath('//ul[@class="post-categories"]/li/a/text()').extract()
 		for paragraph in response.xpath('//p[@style="text-align: justify;"]/text()').extract():
 			text += remove_tags(paragraph) + '\n'
 		item['text'] = text