mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-08 02:34:06 -04:00
Update Geopolityka
Merge branch 'master' of https://github.com/t3d/calibre
This commit is contained in:
Kovid Goyal
commit
325055124c
@ -9,4 +9,4 @@ class BasicUserRecipe1361379046(BasicNewsRecipe):
|
||||
max_articles_per_feed = 100
|
||||
auto_cleanup = True
|
||||
|
||||
feeds = [(u'Rss', u'http://geopolityka.org/index.php?format=feed&type=rss')]
|
||||
feeds = [(u'Rss', u'http://geopolityka.org/component/k2/itemlist?format=feed&moduleID=200')]
|
||||
|
||||
Binary file not shown.
|
Before Width: | Height: | Size: 410 B |
Binary file not shown.
|
Before Width: | Height: | Size: 410 B |
Binary file not shown.
|
Before Width: | Height: | Size: 564 B |
@ -1,66 +0,0 @@
|
||||
#!/usr/bin/env python2
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = u'2010-2015, Tomasz Dlugosz <tomek3d@gmail.com>'
|
||||
'''
|
||||
fakty.interia.pl
|
||||
'''
|
||||
import re
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
|
||||
class InteriaFakty(BasicNewsRecipe):
|
||||
title = u'Interia.pl - Fakty'
|
||||
description = u'Fakty ze strony interia.pl'
|
||||
language = 'pl'
|
||||
oldest_article = 1
|
||||
__author__ = u'Tomasz D\u0142ugosz'
|
||||
no_stylesheets = True
|
||||
remove_javascript = True
|
||||
remove_empty_feeds = True
|
||||
use_embedded_content = False
|
||||
ignore_duplicate_articles = {'title', 'url'}
|
||||
|
||||
feeds = [(u'Kraj', u'http://kanaly.rss.interia.pl/kraj.xml'),
|
||||
(u'\u015awiat', u'http://kanaly.rss.interia.pl/swiat.xml'),
|
||||
(u'Wiadomo\u015bci dnia',
|
||||
u'http://kanaly.rss.interia.pl/fakty.xml'),
|
||||
(u'Przegl\u0105d prasy',
|
||||
u'http://kanaly.rss.interia.pl/przeglad_prasy.xml'),
|
||||
(u'Wywiady', u'http://kanaly.rss.interia.pl/wywiady.xml'),
|
||||
(u'Ciekawostki', u'http://kanaly.rss.interia.pl/ciekawostki.xml')]
|
||||
|
||||
keep_only_tags = [
|
||||
dict(name='h1'),
|
||||
dict(name='div', attrs={'class': ['lead textContent fontSize-medium', 'text textContent fontSize-medium', 'source']})]
|
||||
|
||||
remove_tags = [
|
||||
dict(name='div', attrs={'class': ['embed embedAd', 'REMOVE', 'boxHeader']})]
|
||||
|
||||
preprocess_regexps = [
|
||||
(re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in
|
||||
[
|
||||
(r'embed embed(Left|Right|Center) articleEmbed(Audio|Wideo articleEmbedVideo|ArticleFull|ArticleTitle|ArticleListTitle|AlbumHorizontal)">', lambda match: 'REMOVE">'), # noqa
|
||||
(r'</div> <div class="source">', lambda match: ''),
|
||||
(r'<p><a href="http://forum.interia.pl.*?</a></p>', lambda match: '')
|
||||
]
|
||||
]
|
||||
|
||||
def get_article_url(self, article):
|
||||
link = article.get('link', None)
|
||||
if link and 'galerie' not in link and link.split('/')[-1] == "story01.htm":
|
||||
link = link.split('/')[-2]
|
||||
encoding = {'0B': '.', '0C': '/', '0A': '0', '0F': '=', '0G': '&',
|
||||
'0D': '?', '0E': '-', '0H': ',', '0I': '_', '0N': '.com', '0L': 'http://'}
|
||||
for k, v in encoding.iteritems():
|
||||
link = link.replace(k, v)
|
||||
return link
|
||||
|
||||
def print_version(self, url):
|
||||
chunks = url.split(',')
|
||||
return chunks[0] + '/podglad-wydruku' + ',' + ','.join(chunks[1:])
|
||||
|
||||
extra_css = '''
|
||||
h1 { font-size:130% }
|
||||
div.info { font-style:italic; font-size:70%}
|
||||
'''
|
||||
@ -1,66 +0,0 @@
|
||||
#!/usr/bin/env python2
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = u'2010-2013, Tomasz Dlugosz <tomek3d@gmail.com>'
|
||||
'''
|
||||
sport.interia.pl
|
||||
'''
|
||||
|
||||
import re
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
|
||||
class InteriaSport(BasicNewsRecipe):
|
||||
title = u'Interia.pl - Sport'
|
||||
description = u'Sport ze strony interia.pl'
|
||||
language = 'pl'
|
||||
oldest_article = 1
|
||||
__author__ = u'Tomasz D\u0142ugosz'
|
||||
no_stylesheets = True
|
||||
remove_javascript = True
|
||||
remove_empty_feeds = True
|
||||
use_embedded_content = False
|
||||
ignore_duplicate_articles = {'title', 'url'}
|
||||
|
||||
feeds = [(u'Wydarzenia sportowe', u'http://kanaly.rss.interia.pl/sport.xml'),
|
||||
(u'Pi\u0142ka no\u017cna',
|
||||
u'http://kanaly.rss.interia.pl/pilka_nozna.xml'),
|
||||
(u'Koszyk\xf3wka', u'http://kanaly.rss.interia.pl/koszykowka.xml'),
|
||||
(u'Tenis', u'http://kanaly.rss.interia.pl/tenis.xml')]
|
||||
|
||||
keep_only_tags = [
|
||||
dict(name='h1'),
|
||||
dict(name='div', attrs={'class': ['lead textContent', 'text textContent', 'source']})]
|
||||
|
||||
remove_tags = [
|
||||
dict(name='div', attrs={'class': ['embed embedAd', 'REMOVE', 'boxHeader']})]
|
||||
|
||||
preprocess_regexps = [
|
||||
(re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in
|
||||
[
|
||||
(r'<p><a href.*?</a></p>', lambda match: ''),
|
||||
(r'<p>(<i>)?<b>(ZOBACZ|CZYTAJ) T.*?</div>', lambda match: '</div>'),
|
||||
(r'embed embed(Left|Right|Center) articleEmbed(Audio|Wideo articleEmbedVideo|ArticleFull|ArticleTitle|ArticleListTitle|AlbumHorizontal)">', lambda match: 'REMOVE">'), # noqa
|
||||
(r'</div> <div class="source">', lambda match: ''),
|
||||
(r'<p><a href="http://forum.interia.pl.*?</a></p>', lambda match: '')
|
||||
]
|
||||
]
|
||||
|
||||
def get_article_url(self, article):
|
||||
link = article.get('link', None)
|
||||
if link and 'galerie' not in link and link.split('/')[-1] == "story01.htm":
|
||||
link = link.split('/')[-2]
|
||||
encoding = {'0B': '.', '0C': '/', '0A': '0', '0F': '=', '0G': '&',
|
||||
'0D': '?', '0E': '-', '0H': ',', '0I': '_', '0N': '.com', '0L': 'http://'}
|
||||
for k, v in encoding.iteritems():
|
||||
link = link.replace(k, v)
|
||||
return link
|
||||
|
||||
def print_version(self, url):
|
||||
chunks = url.split(',')
|
||||
return chunks[0] + '/podglad-wydruku' + ',' + ','.join(chunks[1:])
|
||||
|
||||
extra_css = '''
|
||||
h1 { font-size:130% }
|
||||
div.info { font-style:italic; font-size:70%}
|
||||
'''
|
||||
@ -1,28 +0,0 @@
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = 'MrStefan'
|
||||
|
||||
'''
|
||||
www.ittechblog.pl
|
||||
'''
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
|
||||
class ittechblog(BasicNewsRecipe):
|
||||
title = u'IT techblog'
|
||||
__author__ = 'MrStefan <mrstefaan@gmail.com>'
|
||||
language = 'pl'
|
||||
description = u'Na naszym blogu technologicznym znajdziesz między innymi: testy sprzętu, najnowsze startupy, technologiczne nowinki, felietony tematyczne.'
|
||||
extra_css = '.cover > img {display:block;}'
|
||||
remove_empty_feeds = True
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 100
|
||||
remove_javascript = True
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
|
||||
keep_only_tags = [dict(attrs={'class': 'box'})]
|
||||
remove_tags = [dict(name='aside'), dict(
|
||||
attrs={'class': ['tags', 'counter', 'twitter-share-button']})]
|
||||
|
||||
feeds = [(u'Artykuły', u'http://feeds.feedburner.com/ITTechBlog?format=xml')]
|
||||
Loading…
x
Reference in New Issue
Block a user