detalles

descarga_por_dia/laJornadaGro/laJornadaGro/spiders/noticias.py

@@ -97,6 +97,8 @@ class QuotesSpider(scrapy.Spider):
 		if title is not None:
 			title = title.replace('\n','')
 			title = title.replace('\t','')
+			title = title.lstrip()
+			title = title.rstrip()
 			item['title'] = title
 		
 		item['topic'] = response.xpath('//*[@class="itemCategory"]/a/text()').extract_first()

descarga_por_dia/laRazon/laRazon/spiders/noticias.py

@@ -61,7 +61,10 @@ class QuotesSpider(scrapy.Spider):
 		item['date'] = d
 
 		item['topic'] = response.xpath('//*[@class="entry-crumbs"]/span/a[@class="entry-crumb"]/text()').extract()[2]
-		item['title'] = response.xpath('//*[@class="td-post-header"]/header/h1/text()').extract_first()
+		ti = response.xpath('//*[@class="td-post-header"]/header/h1/text()').extract_first()
+		if ti is None:
+			ti = response.xpath('//header[@class="td-post-title"]/h1/text()').extract_first()
+		item['title'] = ti
 		
 		for p in response.xpath('//*[@class="td-post-content"]/p').extract():
 			text += remove_tags(p) + '\n'