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 Krytyka Polityczna

Browse Source
This commit is contained in:
Tomasz Długosz 2019-10-16 01:04:29 +02:00
parent 7d54f6325d
commit dd7f03b859
1 changed files with 7 additions and 31 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
recipes/kp.recipe
View File

@ -11,43 +11,19 @@ class KrytykaPolitycznaRecipe(BasicNewsRecipe):
category = u'News'
description = u' Lewicowe pismo zaangażowane w bieg spraw publicznych w Polsce.'
cover_url = ''
masthead_url = 'https://krytykapolityczna.pl/file/2015/09/krytyka-logo.png'
remove_empty_feeds = True
no_stylesheets = True
oldest_article = 7
max_articles_per_feed = 100000
max_articles_per_feed = 50
recursions = 0
no_stylesheets = True
remove_javascript = True
simultaneous_downloads = 3
keep_only_tags = []
keep_only_tags.append(dict(name='h1', attrs={'class': 'print-title'}))
keep_only_tags.append(dict(name='div', attrs={'class': 'print-content'}))
keep_only_tags = [(dict(name='h1')),
(dict(name='div', attrs={'class': ['entry-meta','post-preview','entry-details', 'entry-content']}))]
remove_tags = []
remove_tags.append(dict(attrs={'class': ['field field-type-text field-field-story-switch', 'field field-type-filefield field-field-story-temp',
'field field-type-text field-field-story-author', 'field field-type-text field-field-story-lead-switch']}))
remove_tags = [(dict(attrs={'class': ['_ning_zone_inner','book-item site-commerc','wp-embedded-content',
'read-also','meta-date-modified updated', 'textwidget']}))]
extra_css = '''
body {font-family: verdana, arial, helvetica, geneva, sans-serif ;}
td.contentheading{font-size: large; font-weight: bold;}
'''
feeds = [
('Wszystkie', 'http://www.krytykapolityczna.pl/rss.xml')
]
def print_version(self, url):
soup = self.index_to_soup(url)
print_ico = soup.find(attrs={'class': 'print-page'})
print_uri = print_ico['href']
self.log('PRINT', print_uri)
return 'http://www.krytykapolityczna.pl/' + print_uri
def preprocess_html(self, soup):
for alink in soup.findAll('a'):
if alink.string is not None:
tstr = alink.string
alink.replaceWith(tstr)
return soup
feeds = [('Wszystkie', 'https://www.krytykapolityczna.pl/rss')]