crawlers

descarga_por_dia/edoMexDia/edoMexDia/spiders/noticias.py

@@ -35,9 +35,10 @@ class QuotesSpider(scrapy.Spider):
         self.year = getattr(self, "year", None)
         self.month = getattr(self, "month", None)
         self.day = getattr(self, "day", None)
-        self.date_parser = {'january': 1,   'february': 2, 'march': 3,     'april': 4,
-                            'may': 5,       'june': 6,     'july': 7,      'august': 8,
-                            'september': 9, 'october': 10, 'november': 11, 'december': 12}
+
+        self.date_parser = {"january": 1,   "february": 2, "march": 3,     "april": 4,
+                            "may": 5,       "june": 6,     "july": 7,      "august": 8,
+                            "september": 9, "october": 10, "november": 11, "december": 12}
 
         self.baseURL = "http://www.edomexaldia.com.mx/" + self.year + "/" + self.month.zfill(2) + "/" + self.day.zfill(2)
 
@@ -80,6 +81,7 @@ class QuotesSpider(scrapy.Spider):
         item['date'] = dat
 
         item['title'] = remove_tags(response.xpath('//div[@id="main"]/div/h1').extract_first()).strip()
+        item['topic'] = None
 
         author = response.xpath('//span[@class="post_author_author"]').extract_first()
         if author is not None and author != '':