Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Use the browser not urllib directly

Browse Source
This commit is contained in:
Kovid Goyal 2015-08-23 08:34:19 +05:30
parent a93c1d397b
commit 53d452ae52
1 changed files with 13 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
recipes/clarin.recipe
View File

@ -41,16 +41,16 @@ class Clarin(BasicNewsRecipe):
remove_attributes = ['lang']
feeds = [
(u'Pagina principal', u'http://www.clarin.com/rss/' )
,(u'Politica' , u'http://www.clarin.com/rss/politica/' )
,(u'Deportes' , u'http://www.clarin.com/rss/deportes/' )
,(u'Mundo' , u'http://www.clarin.com/rss/mundo/' )
,(u'iEco' , u'http://www.ieco.clarin.com/rss/' )
(u'Pagina principal', u'http://www.clarin.com/rss/')
,(u'Politica' , u'http://www.clarin.com/rss/politica/')
,(u'Deportes' , u'http://www.clarin.com/rss/deportes/')
,(u'Mundo' , u'http://www.clarin.com/rss/mundo/')
,(u'iEco' , u'http://www.ieco.clarin.com/rss/')
,(u'Espectaculos' , u'http://www.clarin.com/rss/espectaculos/')
,(u'Sociedad' , u'http://www.clarin.com/rss/sociedad/' )
,(u'Ciudades' , u'http://www.clarin.com/rss/ciudades/' )
,(u'Policiales' , u'http://www.clarin.com/rss/policiales/' )
,(u'Internet' , u'http://www.clarin.com/rss/internet/' )
,(u'Sociedad' , u'http://www.clarin.com/rss/sociedad/')
,(u'Ciudades' , u'http://www.clarin.com/rss/ciudades/')
,(u'Policiales' , u'http://www.clarin.com/rss/policiales/')
,(u'Internet' , u'http://www.clarin.com/rss/internet/')
]
def print_version(self, url):
@ -60,20 +60,18 @@ class Clarin(BasicNewsRecipe):
return article.get('guid', None)
def get_cover_url(self):
import urllib2
from datetime import datetime, timedelta
br = self.cloned_browser
dat = datetime.now()
for x in (0,1):
stg = dat.strftime("%Y%m%d")
cover_url = "http://tapas.clarin.com/tapa/{}/{}/{}/{}_thumb.jpg".format(stg[:4],stg[4:6],stg[6:8],stg)
req = urllib2.Request(cover_url)
try:
resp = urllib2.urlopen(req)
br.open(cover_url)
break
except urllib2.URLError, e:
if e.code == 404: # today's cover not published yet, look for yesterday's cover
except Exception as e:
if hasattr(e, 'getcode') and e.getcode() == 404:
dat = dat - timedelta(days=1)
cover_url = None
return cover_url