Skip to content

crawlersNoticias
crawlersNoticias
Commit 26b8186c authored by Renán Sosa Guillen's avatar Renán Sosa Guillen
Browse files
Options

Ajustes.

parent 5079a7b9
Hide whitespace changes
Inline Side-by-side
Showing with 10 additions and 10 deletions
lajornada/lajornada/spiders/noticias.py
View file @ 26b8186c
...@@ -37,16 +37,16 @@ class NoticiasSpider(scrapy.Spider): ...@@ -37,16 +37,16 @@ class NoticiasSpider(scrapy.Spider):
self.baseURL='http://www.jornada.unam.mx/'+year+'/'+month+'/'+day+'/' self.baseURL='http://www.jornada.unam.mx/'+year+'/'+month+'/'+day+'/'
urls = [ urls = [
self.baseURL+"opinion", self.baseURL+"opinion",
# self.baseURL+"politica", self.baseURL+"politica",
# self.baseURL+"economia", self.baseURL+"economia",
# self.baseURL+"mundo", self.baseURL+"mundo",
# self.baseURL+"estados", self.baseURL+"estados",
# self.baseURL+"capital", self.baseURL+"capital",
# self.baseURL+"sociedad", self.baseURL+"sociedad",
# self.baseURL+"ciencias", self.baseURL+"ciencias",
# self.baseURL+"cultura", self.baseURL+"cultura",
# self.baseURL+"espectaculos", self.baseURL+"espectaculos",
# self.baseURL+"deporte", self.baseURL+"deporte",
] ]
for url in urls: for url in urls:
yield scrapy.Request(url=url, callback=self.parse) yield scrapy.Request(url=url, callback=self.parse)
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment