mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-09 03:04:10 -04:00
New and updated Polish news sources
This commit is contained in:
Kovid Goyal
commit
264753bdb9
BIN
recipes/icons/kdefamily_pl.png
Normal file
BIN
recipes/icons/kdefamily_pl.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 857 B |
BIN
recipes/icons/km_blog.png
Normal file
BIN
recipes/icons/km_blog.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 532 B |
@ -1,23 +1,24 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = u'2010, Tomasz Dlugosz <tomek3d@gmail.com>'
|
||||
__copyright__ = u'2010-2013, 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 = 7
|
||||
oldest_article = 1
|
||||
__author__ = u'Tomasz D\u0142ugosz'
|
||||
simultaneous_downloads = 2
|
||||
no_stylesheets = True
|
||||
remove_javascript = True
|
||||
max_articles_per_feed = 100
|
||||
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'),
|
||||
@ -26,14 +27,36 @@ class InteriaFakty(BasicNewsRecipe):
|
||||
(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='div', attrs={'id':'article'})]
|
||||
keep_only_tags = [
|
||||
dict(name='h1'),
|
||||
dict(name='div', attrs={'class': ['lead textContent', 'text textContent', 'source']})]
|
||||
|
||||
remove_tags = [
|
||||
dict(name='div', attrs={'class':'box fontSizeSwitch'}),
|
||||
dict(name='div', attrs={'class':'clear'}),
|
||||
dict(name='div', attrs={'class':'embed embedLeft articleEmbedArticleList articleEmbedArticleListTitle'}),
|
||||
dict(name='span', attrs={'class':'keywords'})]
|
||||
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">'),
|
||||
(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 = '''
|
||||
h2 { font-size: 1.2em; }
|
||||
'''
|
||||
h1 { font-size:130% }
|
||||
div.info { font-style:italic; font-size:70%}
|
||||
'''
|
||||
|
||||
@ -1,7 +1,7 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = u'2010, Tomasz Dlugosz <tomek3d@gmail.com>'
|
||||
__copyright__ = u'2010-2013, Tomasz Dlugosz <tomek3d@gmail.com>'
|
||||
'''
|
||||
sport.interia.pl
|
||||
'''
|
||||
@ -13,61 +13,51 @@ class InteriaSport(BasicNewsRecipe):
|
||||
title = u'Interia.pl - Sport'
|
||||
description = u'Sport ze strony interia.pl'
|
||||
language = 'pl'
|
||||
oldest_article = 7
|
||||
oldest_article = 1
|
||||
__author__ = u'Tomasz D\u0142ugosz'
|
||||
simultaneous_downloads = 3
|
||||
no_stylesheets = True
|
||||
remove_javascript = True
|
||||
max_articles_per_feed = 100
|
||||
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'Siatk\xf3wka', u'http://kanaly.rss.interia.pl/siatkowka.xml'),
|
||||
(u'Koszyk\xf3wka', u'http://kanaly.rss.interia.pl/koszykowka.xml'),
|
||||
(u'NBA', u'http://kanaly.rss.interia.pl/nba.xml'),
|
||||
(u'Kolarstwo', u'http://kanaly.rss.interia.pl/kolarstwo.xml'),
|
||||
(u'\u017bu\u017cel', u'http://kanaly.rss.interia.pl/zuzel.xml'),
|
||||
(u'Tenis', u'http://kanaly.rss.interia.pl/tenis.xml')]
|
||||
|
||||
keep_only_tags = [dict(name='div', attrs={'id':'article'})]
|
||||
keep_only_tags = [
|
||||
dict(name='h1'),
|
||||
dict(name='div', attrs={'class': ['lead textContent', 'text textContent', 'source']})]
|
||||
|
||||
remove_tags = [dict(name='div', attrs={'class':'object gallery'}),
|
||||
dict(name='div', attrs={'class':'box fontSizeSwitch'})]
|
||||
|
||||
extra_css = '''
|
||||
.articleDate {
|
||||
font-size: 0.5em;
|
||||
color: black;
|
||||
}
|
||||
|
||||
.articleFoto {
|
||||
display: block;
|
||||
font-family: sans;
|
||||
font-size: 0.5em;
|
||||
text-indent: 0
|
||||
color: black;
|
||||
}
|
||||
|
||||
.articleText {
|
||||
display: block;
|
||||
margin-bottom: 1em;
|
||||
margin-left: 0;
|
||||
margin-right: 0;
|
||||
margin-top: 1em
|
||||
color: black;
|
||||
}
|
||||
|
||||
.articleLead {
|
||||
font-size: 1.2em;
|
||||
}
|
||||
'''
|
||||
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: ''),
|
||||
# FIXME
|
||||
#(r'(<div id="newsAddContent">)(.*?)(<a href=".*">)(.*?)(</a>)', lambda match: '\1\2\4'),
|
||||
(r'<p>(<i>)?<b>(ZOBACZ|CZYTAJ) T.*?</div>', lambda match: '</div>')
|
||||
(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">'),
|
||||
(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%}
|
||||
'''
|
||||
|
||||
36
recipes/km_blog.recipe
Normal file
36
recipes/km_blog.recipe
Normal file
@ -0,0 +1,36 @@
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__author__ = 'teepel <teepel44@gmail.com>, Artur Stachecki <artur.stachecki@gmail.com>'
|
||||
|
||||
'''
|
||||
korwin-mikke.pl/blog
|
||||
'''
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class km_blog(BasicNewsRecipe):
|
||||
title = u'Korwin-Mikke Blog'
|
||||
__author__ = 'teepel <teepel44@gmail.com>'
|
||||
language = 'pl'
|
||||
description ='Wiadomości z bloga korwin-mikke.pl/blog'
|
||||
INDEX='http://korwin-mikke.pl/blog'
|
||||
remove_empty_feeds= True
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 100
|
||||
remove_javascript=True
|
||||
no_stylesheets=True
|
||||
remove_empty_feeds = True
|
||||
|
||||
feeds = [(u'blog', u'http://korwin-mikke.pl/blog/rss')]
|
||||
|
||||
keep_only_tags =[]
|
||||
#this line should show title of the article, but it doesnt work
|
||||
keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'posts view'}))
|
||||
keep_only_tags.append(dict(name = 'div', attrs = {'class' : 'text'}))
|
||||
keep_only_tags.append(dict(name = 'h1'))
|
||||
|
||||
remove_tags =[]
|
||||
remove_tags.append(dict(name = 'p', attrs = {'class' : 'float_right'}))
|
||||
remove_tags.append(dict(name = 'p', attrs = {'class' : 'date'}))
|
||||
|
||||
remove_tags_after=[(dict(name = 'div', attrs = {'class': 'text'}))]
|
||||
26
recipes/trystero.recipe
Normal file
26
recipes/trystero.recipe
Normal file
@ -0,0 +1,26 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = u'2013, Tomasz Dlugosz <tomek3d@gmail.com>'
|
||||
|
||||
'''
|
||||
trystero.pl
|
||||
'''
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class trystero(BasicNewsRecipe):
|
||||
title = 'Trystero'
|
||||
__author__ = u'Tomasz D\u0142ugosz'
|
||||
language = 'pl'
|
||||
description =u'Trystero.pl jest niezależnym blogiem finansowym. Publikowane na nim teksty dotyczą rynku kapitałowego, ekonomii, gospodarki i życia społecznego – w takiej mniej więcej kolejności.'
|
||||
oldest_article = 7
|
||||
remove_javascript=True
|
||||
no_stylesheets=True
|
||||
|
||||
feeds = [(u'Newsy', u'http://www.trystero.pl/feed')]
|
||||
|
||||
keep_only_tags = [
|
||||
dict(name='h1'),
|
||||
dict(name='div', attrs={'class': ['post-content']})]
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user