Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 10:14:46 -04:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' of https://github.com/unkn0w7n/calibre

Browse Source
This commit is contained in:
Kovid Goyal 2023-10-30 22:11:08 +05:30
commit d62c4be1d2
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 13 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
recipes/financial_times.recipe
View File

@ -1,5 +1,6 @@
import json import json
import re import re
from calibre import browser
from urllib.parse import quote from urllib.parse import quote
from html5_parser import parse from html5_parser import parse
@ -20,6 +21,7 @@ class ft(BasicNewsRecipe):
resolve_internal_links = True resolve_internal_links = True
remove_attributes = ['style', 'width', 'height'] remove_attributes = ['style', 'width', 'height']
masthead_url = 'https://im.ft-static.com/m/img/masthead_main.jpg' masthead_url = 'https://im.ft-static.com/m/img/masthead_main.jpg'
simultaneous_downloads = 1
extra_css = ''' extra_css = '''
.article-info__time-byline {font-size:small; font-weight:bold; } .article-info__time-byline {font-size:small; font-weight:bold; }
@ -38,6 +40,7 @@ class ft(BasicNewsRecipe):
remove_tags = [ remove_tags = [
dict(name='aside', attrs={'class':'n-content-recommended--single-story'}), dict(name='aside', attrs={'class':'n-content-recommended--single-story'}),
dict(attrs={'data-layout-name':'card'}),
classes('in-article-advert') classes('in-article-advert')
] ]
@ -57,13 +60,20 @@ class ft(BasicNewsRecipe):
# return br # return br
def get_browser(self, *args, **kwargs): def get_browser(self, *args, **kwargs):
kwargs['user_agent'] = 'Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)' return self
br = BasicNewsRecipe.get_browser(self, *args, **kwargs)
def clone_browser(self, *args, **kwargs):
return self.get_browser()
def open_novisit(self, *args, **kwargs):
br = browser(user_agent='Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)')
br.addheaders += [ br.addheaders += [
('Referer', 'https://www.google.com/'), ('Referer', 'https://www.google.com/'),
('X-Forwarded-For', '66.249.66.1') ('X-Forwarded-For', '66.249.66.1')
] ]
return br return br.open_novisit(*args, **kwargs)
open = open_novisit
feeds = [ feeds = [
('World', 'https://www.ft.com/world?format=rss'), ('World', 'https://www.ft.com/world?format=rss'),