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

recipes: fix tvn24.recipe

Browse Source
This commit is contained in:
Tomasz Długosz 2016-10-09 21:20:10 +02:00
parent b379327190
commit 11d9fe6805
1 changed files with 13 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
recipes/tvn24.recipe
View File

@ -9,29 +9,31 @@ class tvn24(BasicNewsRecipe):
description = u'Sport, Biznes, Gospodarka, Informacje, Wiadomości Zawsze aktualne wiadomości z Polski i ze świata'
category = 'news'
language = 'pl'
cover_url = 'http://www.qzdrowiu.pl/Upload/KnowQZdrowiu_PressOffice/TVN24_logo_575702b7-edce-4b6f-a41b-4395f9456f96_ff6d6ccf-528a-4b94-9e61-2fed727aba35.png' # noqa
cover_url = 'http://ncplus.pl/~/media/n/npl/kanaly/logo%20na%20strony%20kanalow/tvn24-630.png' # noqa
extra_css = 'ul {list-style: none; padding: 0; margin: 0;} li {float: left;margin: 0 0.15em;}'
remove_empty_feeds = True
remove_javascript = True
no_stylesheets = True
keep_only_tags = [
# dict(name='h1', attrs={'class':'size38 mt20 pb20'}),
dict(name='div', attrs={'class': 'mainContainer'}),
# dict(name='p'),
# dict(attrs={'class':['size18 mt10 mb15', 'bold topicSize1', 'fromUsers content', 'textArticleDefault']})
dict(name='article',attrs={'class':'mb20'})
]
remove_tags = [
dict(attrs={'class': ['commentsInfo', 'textSize', 'related newsNews align-right', 'box', 'watchMaterial text', 'related galleryGallery align-center', 'advert block-alignment-right', 'userActions', 'socialBookmarks', 'im yourArticle fl', 'dynamicButton addComment fl', 'innerArticleModule onRight cols externalContent', 'thumbsGallery', 'relatedObject customBlockquote align-right', 'lead', 'mainRightColumn', 'articleDateContainer borderGreyBottom', 'socialMediaContainer onRight loaded', 'quizContent', 'twitter', 'facebook', 'googlePlus', 'share', 'voteResult', 'reportTitleBar bgBlue_v4 mb15', 'innerVideoModule center']}), # noqa
dict(name='article', attrs={'class': [
'singleArtPhotoCenter', 'singleArtPhotoRight', 'singleArtPhotoLeft']}),
dict(attrs={'class': ['commentsInfo', 'textSize', 'related newsNews align-right', 'box', 'watchMaterial text', 'related galleryGallery align-center', 'advert block-alignment-right', 'userActions', 'socialBookmarks', 'im yourArticle fl', 'dynamicButton addComment fl', 'thumbsGallery', 'relatedObject customBlockquote align-right', 'lead', 'mainRightColumn', 'articleDateContainer borderGreyBottom', 'socialMediaContainer onRight loaded', 'quizContent', 'twitter', 'facebook', 'googlePlus', 'share', 'voteResult', 'reportTitleBar bgBlue_v4 mb15', 'innerVideoModule center']}), # noqa
dict(name='aside'),
dict(name='figure'),
dict(name='section', attrs={
'id': ['forum', 'innerArticle', 'quiz toCenter', 'mb20']}),
dict(name='div', attrs={
'class': 'socialMediaContainer big p20 mb20 borderGrey loaded'})
'id': ['forum', 'innerArticle', 'quiz toCenter', 'mb20']})
]
remove_tags_after = [dict(name='li', attrs={'class': 'share'})]
feeds = [(u'Najnowsze', u'http://www.tvn24.pl/najnowsze.xml'), ]
def get_article_url(self, article):
link = article.get('link')
# following websites are linked in aforementioned feeds, but have different layout not compatible with this recipe
banned = ['tvnwarszawa.pl','tvnmeteo.pl','szklokontaktowe.tvn24.pl','tvn24bis.pl']
if not any(x in link for x in banned):
return link
def preprocess_html(self, soup):
for alink in soup.findAll('a'):
if alink.string is not None: