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

Better workaround for wsj free index page getting stuck

Browse Source
This commit is contained in:
Kovid Goyal 2021-09-17 08:22:55 +05:30
parent 1b6faaa3bc
commit 93a8e83b93
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
2 changed files with 24 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
recipes/wsj.recipe
View File

@ -6,6 +6,7 @@ from __future__ import absolute_import, division, print_function, unicode_litera
import json, time, random
from base64 import standard_b64encode
from datetime import date, timedelta
from mechanize import Request
@ -97,8 +98,7 @@ class WSJ(BasicNewsRecipe):
def get_browser_for_wsj(self, *a, **kw):
br = BasicNewsRecipe.get_browser(self, *a, **kw)
if needs_subscription:
br.set_cookie('wsjregion', 'na,us', '.wsj.com')
br.set_cookie('wsjregion', 'na,us', '.wsj.com')
br.set_cookie('gdprApplies', 'false', '.wsj.com')
br.set_cookie('ccpaApplies', 'false', '.wsj.com')
return br
@ -167,6 +167,16 @@ class WSJ(BasicNewsRecipe):
def get_browser(self, *a, **kw):
br = self.get_browser_for_wsj(*a, **kw)
res = br.open(self.WSJ_ITP)
url = res.geturl()
if '/20210913/' in url:
today = date.today()
q = today.isoformat().replace('-', '')
try:
res = br.open(url.replace('/20210913/', '/' + q + '/'))
except Exception:
today -= timedelta(days=1)
q = today.isoformat().replace('-', '')
res = br.open(url.replace('/20210913/', '/' + q + '/'))
self.log('Print edition resolved url:', res.geturl())
self.wsj_itp_page = res.read()
return br

14
recipes/wsj_free.recipe
View File

@ -6,6 +6,7 @@ from __future__ import absolute_import, division, print_function, unicode_litera
import json, time, random
from base64 import standard_b64encode
from datetime import date, timedelta
from mechanize import Request
@ -97,8 +98,7 @@ class WSJ(BasicNewsRecipe):
def get_browser_for_wsj(self, *a, **kw):
br = BasicNewsRecipe.get_browser(self, *a, **kw)
if needs_subscription:
br.set_cookie('wsjregion', 'na,us', '.wsj.com')
br.set_cookie('wsjregion', 'na,us', '.wsj.com')
br.set_cookie('gdprApplies', 'false', '.wsj.com')
br.set_cookie('ccpaApplies', 'false', '.wsj.com')
return br
@ -167,6 +167,16 @@ class WSJ(BasicNewsRecipe):
def get_browser(self, *a, **kw):
br = self.get_browser_for_wsj(*a, **kw)
res = br.open(self.WSJ_ITP)
url = res.geturl()
if '/20210913/' in url:
today = date.today()
q = today.isoformat().replace('-', '')
try:
res = br.open(url.replace('/20210913/', '/' + q + '/'))
except Exception:
today -= timedelta(days=1)
q = today.isoformat().replace('-', '')
res = br.open(url.replace('/20210913/', '/' + q + '/'))
self.log('Print edition resolved url:', res.geturl())
self.wsj_itp_page = res.read()
return br