noticiero en linea

descarga_por_dia/noticieroLinea/noticieroLinea/spiders/noticias.py

@@ -8,15 +8,18 @@ Noticiero en Línea, Colima
 USO:
 scrapy crawl noticias --nolog -s filename=2018-01-03.json -a year=2018 -a month=1 -a day=3
 """
-
+from dateparser import parse
 TAG_RE = re.compile(r'<[^>]+>')
-def remove_tags(text):
-    return TAG_RE.sub('', text)
-
 LOC_RE = re.compile(r'\A.+?(\d{1,2}[\s-][a-zA-Z]+[\s-]\d{4})?\s?\.\s?-\s?', re.S)
 G_RE = re.compile(r'\s?-\s?')
 E_RE = re.compile(r'\(Con informaci.*?\)\.?')
 
+#-------------------------------------------------------------------------------
+def remove_tags(text):
+    return TAG_RE.sub('', text)
+#-------------------------------------------------------------------------------
+
+
 class QuotesSpider(scrapy.Spider):
     name = "noticias"
 
@@ -44,7 +47,8 @@ class QuotesSpider(scrapy.Spider):
         text = ''
 
         "La fecha obtenida ya incluye formato y zona horaria"
-        item['date'] = response.xpath('//meta[@property="article:published_time"]/@content').extract_first()
+        date = response.css("span.entry-meta-date::text").get().lower()
+        item['date'] = parse(date, date_formats=["%d %B, %Y"]).isoformat()#response.xpath('//meta[@property="article:published_time"]/@content').extract_first()
         item['title'] = remove_tags(response.xpath('//h1[@class="entry-title"]').extract_first()).strip()
 
         item['topic'] = response.xpath('//*[@class="entry-tags clearfix"]/a/text()').extract_first()