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

Update Bangkok Post

Browse Source 
Fixes #1661925 [No news content when fetching news from Bangkok Post & The Nation](https://bugs.launchpad.net/calibre/+bug/1661925)
This commit is contained in:
Kovid Goyal 2017-02-05 13:45:47 +05:30
parent fcc7de203a
commit be6a1e9921
1 changed files with 14 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
recipes/bangkokpost.recipe
View File

@ -1,6 +1,12 @@
from calibre.web.feeds.news import BasicNewsRecipe from calibre.web.feeds.news import BasicNewsRecipe
def classes(classes):
q = frozenset(classes.split(' '))
return dict(attrs={
'class': lambda x: x and frozenset(x.split()).intersection(q)})
class BangkokPostRecipe(BasicNewsRecipe): class BangkokPostRecipe(BasicNewsRecipe):
__license__ = 'GPL v3' __license__ = 'GPL v3'
__author__ = 'kwetal' __author__ = 'kwetal'
@ -40,15 +46,12 @@ class BangkokPostRecipe(BasicNewsRecipe):
feeds.append((u'Life', u'http://www.bangkokpost.com/rss/data/life.xml')) feeds.append((u'Life', u'http://www.bangkokpost.com/rss/data/life.xml'))
feeds.append((u'Tech', u'http://www.bangkokpost.com/rss/data/tect.xml')) feeds.append((u'Tech', u'http://www.bangkokpost.com/rss/data/tect.xml'))
keep_only_tags = [] keep_only_tags = [
keep_only_tags.append(dict(name='div', attrs={'class': 'entry'})) dict(itemprop='headline'),
classes('articleContents'),
]
remove_tags = [] def print_version(self, url):
remove_tags.append(dict(name='div', attrs={'class': 'article-features'})) if '.com/vdo/' in url:
remove_tags.append(dict(name='div', attrs={'class': 'socialBookmark'})) url = None
remove_tags.append(dict(name='div', attrs={'id': 'main-sns'})) return url
# Their YouTube movies are displayed in an iframe, if you want those you will have to parse the articles by hand.
# Setting self.recursion to 1, which might resolve this, makes calibre
# downloading a lot of PDF files, which will cause a very, very very, long
# download time
remove_tags.append(dict(name='iframe'))