merge foraneos

descarga_hacia_atras/foraneos/prensaGrafica/prensaGrafica/spiders/noticias.py

@@ -22,6 +22,7 @@ def remove_tags(text):
     return TAG_RE.sub('', text)
 
 DAT_RE = re.compile(r'-\d{8}-')
+RE = re.compile(r'\n\xa0')
 
 
 class ImportantData(scrapy.Item):
@@ -147,6 +148,12 @@ class QuotesSpider(scrapy.Spider):
         for p in response.css('div.news-body').css('p').extract():
             text += remove_tags(p) + "\n"
 
+        if text == '':
+            t = remove_tags(response.xpath('//div[@class="news-body"]').extract_first())
+            res = RE.search(t)
+            if res:
+                text = t[:t.rfind(res.group(0))]
+
         item['text'] = text.strip()
 
         item['url'] = response.url