Update Helsingin Sanomat

This commit is contained in:
Kovid Goyal 2017-01-01 19:20:13 +05:30
parent f6c52c3d20
commit 6756388c24

View File

@ -1,6 +1,11 @@
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 AdvancedUserRecipe1298137661(BasicNewsRecipe): class AdvancedUserRecipe1298137661(BasicNewsRecipe):
title = u'Helsingin Sanomat' title = u'Helsingin Sanomat'
__author__ = 'oneillpt' __author__ = 'oneillpt'
@ -9,15 +14,21 @@ class AdvancedUserRecipe1298137661(BasicNewsRecipe):
max_articles_per_feed = 100 max_articles_per_feed = 100
no_stylesheets = True no_stylesheets = True
remove_javascript = True remove_javascript = True
conversion_options = { keep_only_tags = [
'linearize_tables': True classes('article-title single-article'),
} ]
keep_only_tags = [dict(name='div', attrs={'id': 'main-content'}), remove_tags = [
dict(name='div', attrs={'class': 'contentNewsArticle'})] dict(attrs={'class':['hidden print-url', 'article-paywall']}),
dict(style=lambda x: x and 'height: 0' in x),
]
feeds = [(u'Uutiset - HS.fi', u'http://www.hs.fi/uutiset/rss/'), (u'Politiikka - HS.fi', u'http://www.hs.fi/politiikka/rss/'), feeds = [
(u'Ulkomaat - HS.fi', u'http://www.hs.fi/ulkomaat/rss/'), (u'Kulttuuri - HS.fi', (u'Uutiset - HS.fi', u'http://www.hs.fi/uutiset/rss/'),
u'http://www.hs.fi/kulttuuri/rss/'), ]
(u'Kirjat - HS.fi', u'http://www.hs.fi/kulttuuri/kirjat/rss/'), (u'Elokuvat - HS.fi',
u'http://www.hs.fi/kulttuuri/elokuvat/rss/') def preprocess_html(self, soup):
] for tag in soup.findAll(attrs={'data-mfp-src':True}):
tag.name = 'img'
tag['src'] = tag['data-mfp-src']
tag['style'] = 'display:block'
return soup