mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-09 03:04:10 -04:00
pull from trunk
This commit is contained in:
Kovid Goyal
commit
b0c46114b4
BIN
resources/images/news/fronda.png
Normal file
BIN
resources/images/news/fronda.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 646 B |
BIN
resources/images/news/gazeta_pomorska.png
Normal file
BIN
resources/images/news/gazeta_pomorska.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 323 B |
BIN
resources/images/news/legeartis.png
Normal file
BIN
resources/images/news/legeartis.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 634 B |
Binary file not shown.
|
Before Width: | Height: | Size: 1.4 KiB After Width: | Height: | Size: 1017 B |
BIN
resources/images/news/rmf24_ESKN.png
Normal file
BIN
resources/images/news/rmf24_ESKN.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 722 B |
BIN
resources/images/news/rmf24_fakty.png
Normal file
BIN
resources/images/news/rmf24_fakty.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 722 B |
104
resources/recipes/gazeta_pomorska.recipe
Normal file
104
resources/recipes/gazeta_pomorska.recipe
Normal file
@ -0,0 +1,104 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
# # Przed uzyciem przeczytaj komentarz w sekcji "feeds"
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = u'2010, Richard z forum.eksiazki.org'
|
||||
'''pomorska.pl'''
|
||||
|
||||
import re
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class GazetaPomorska(BasicNewsRecipe):
|
||||
title = u'Gazeta Pomorska'
|
||||
publisher = u'Gazeta Pomorska'
|
||||
description = u'Kujawy i Pomorze - wiadomo\u015bci'
|
||||
language = 'pl'
|
||||
__author__ = u'Richard z forum.eksiazki.org'
|
||||
# # (dziekuje t3d z forum.eksiazki.org za testy)
|
||||
oldest_article = 2
|
||||
max_articles_per_feed = 20
|
||||
no_stylesheets = True
|
||||
remove_javascript = True
|
||||
preprocess_regexps = [
|
||||
(re.compile(r'<a href="http://maps.google[^>]*>[^<]*</a>\.*', re.DOTALL|re.IGNORECASE), lambda m: ''),
|
||||
(re.compile(r'[<Bb >]*Poznaj opinie[^<]*[</Bb >]*[^<]*<a href[^>]*>[^<]*</a>\.*', re.DOTALL|re.IGNORECASE), lambda m: ''),
|
||||
(re.compile(r'[<Bb >]*Przeczytaj[^<]*[</Bb >]*[^<]*<a href[^>]*>[^<]*</a>\.*', re.DOTALL|re.IGNORECASE), lambda m: ''),
|
||||
(re.compile(r'[<Bb >]*Wi.cej informacji[^<]*[</Bb >]*[^<]*<a href[^>]*>[^<]*</a>\.*', re.DOTALL|re.IGNORECASE), lambda m: ''),
|
||||
(re.compile(r'<a href[^>]*>[<Bb >]*Wideo[^<]*[</Bb >]*[^<]*</a>\.*', re.DOTALL|re.IGNORECASE), lambda m: ''),
|
||||
(re.compile(r'<a href[^>]*>[<Bb >]*KLIKNIJ TUTAJ[^<]*[</Bb >]*[^<]*</a>\.*', re.DOTALL|re.IGNORECASE), lambda m: '')
|
||||
]
|
||||
|
||||
feeds = [
|
||||
# # Tutaj jest wymieniona lista kategorii jakie mozemy otrzymywac z Gazety
|
||||
# # Pomorskiej, po jednej kategorii w wierszu. Jesli na poczatku danego wiersza
|
||||
# # znajduje sie jeden znak "#", oznacza to ze kategoria jest zakomentowana
|
||||
# # i nie bedziemy jej otrzymywac. Jesli chcemy ja otrzymywac nalezy usunac
|
||||
# # znak # z jej wiersza.
|
||||
# # Jesli subskrybujemy wiecej niz jedna kategorie, na koncu wiersza z kazda
|
||||
# # kategoria musi sie znajdowac niezakomentowany przecinek, z wyjatkiem
|
||||
# # ostatniego wiersza - ma byc bez przecinka na koncu.
|
||||
# # Rekomendowane opcje wyboru kategorii:
|
||||
# # 1. PomorskaRSS - wiadomosci kazdego typu, lub
|
||||
# # 2. Region + wybrane miasta, lub
|
||||
# # 3. Wiadomosci tematyczne.
|
||||
# # Lista kategorii:
|
||||
|
||||
# # PomorskaRSS - wiadomosci kazdego typu, zakomentuj znakiem "#"
|
||||
# # przed odkomentowaniem wiadomosci wybranego typu:
|
||||
(u'PomorskaRSS', u'http://www.pomorska.pl/rss.xml')
|
||||
|
||||
# # wiadomosci z regionu nie przypisane do okreslonego miasta:
|
||||
# (u'Region', u'http://www.pomorska.pl/region.xml'),
|
||||
|
||||
# # wiadomosci przypisane do miast:
|
||||
# (u'Bydgoszcz', u'http://www.pomorska.pl/bydgoszcz.xml'),
|
||||
# (u'Nak\u0142o', u'http://www.pomorska.pl/naklo.xml'),
|
||||
# (u'Koronowo', u'http://www.pomorska.pl/koronowo.xml'),
|
||||
# (u'Solec Kujawski', u'http://www.pomorska.pl/soleckujawski.xml'),
|
||||
# (u'Grudzi\u0105dz', u'http://www.pomorska.pl/grudziadz.xml'),
|
||||
# (u'Inowroc\u0142aw', u'http://www.pomorska.pl/inowroclaw.xml'),
|
||||
# (u'Toru\u0144', u'http://www.pomorska.pl/torun.xml'),
|
||||
# (u'W\u0142oc\u0142awek', u'http://www.pomorska.pl/wloclawek.xml'),
|
||||
# (u'Aleksandr\u00f3w Kujawski', u'http://www.pomorska.pl/aleksandrow.xml'),
|
||||
# (u'Brodnica', u'http://www.pomorska.pl/brodnica.xml'),
|
||||
# (u'Che\u0142mno', u'http://www.pomorska.pl/chelmno.xml'),
|
||||
# (u'Chojnice', u'http://www.pomorska.pl/chojnice.xml'),
|
||||
# (u'Ciechocinek', u'http://www.pomorska.pl/ciechocinek.xml'),
|
||||
# (u'Golub Dobrzy\u0144', u'http://www.pomorska.pl/golubdobrzyn.xml'),
|
||||
# (u'Mogilno', u'http://www.pomorska.pl/mogilno.xml'),
|
||||
# (u'Radziej\u00f3w', u'http://www.pomorska.pl/radziejow.xml'),
|
||||
# (u'Rypin', u'http://www.pomorska.pl/rypin.xml'),
|
||||
# (u'S\u0119p\u00f3lno', u'http://www.pomorska.pl/sepolno.xml'),
|
||||
# (u'\u015awiecie', u'http://www.pomorska.pl/swiecie.xml'),
|
||||
# (u'Tuchola', u'http://www.pomorska.pl/tuchola.xml'),
|
||||
# (u'\u017bnin', u'http://www.pomorska.pl/znin.xml')
|
||||
|
||||
# # wiadomosci tematyczne (redundancja z region/miasta):
|
||||
# (u'Sport', u'http://www.pomorska.pl/sport.xml'),
|
||||
# (u'Zdrowie', u'http://www.pomorska.pl/zdrowie.xml'),
|
||||
# (u'Auto', u'http://www.pomorska.pl/moto.xml'),
|
||||
# (u'Dom', u'http://www.pomorska.pl/dom.xml'),
|
||||
# (u'Reporta\u017c', u'http://www.pomorska.pl/reportaz.xml'),
|
||||
# (u'Gospodarka', u'http://www.pomorska.pl/gospodarka.xml')
|
||||
]
|
||||
|
||||
keep_only_tags = [dict(name='div', attrs={'id':'article'})]
|
||||
|
||||
remove_tags = [
|
||||
dict(name='p', attrs={'id':'articleTags'}),
|
||||
dict(name='div', attrs={'id':'articleEpaper'}),
|
||||
dict(name='div', attrs={'id':'articleConnections'}),
|
||||
dict(name='div', attrs={'class':'articleFacts'}),
|
||||
dict(name='div', attrs={'id':'articleExternalLink'}),
|
||||
dict(name='div', attrs={'id':'articleMultimedia'}),
|
||||
dict(name='div', attrs={'id':'articleGalleries'}),
|
||||
dict(name='div', attrs={'id':'articleAlarm'}),
|
||||
dict(name='div', attrs={'id':'adholder_srodek1'}),
|
||||
dict(name='div', attrs={'id':'articleVideo'}),
|
||||
dict(name='a', attrs={'name':'fb_share'})]
|
||||
|
||||
extra_css = '''h1 { font-size: 1.4em; }
|
||||
h2 { font-size: 1.0em; }'''
|
||||
|
||||
|
||||
@ -1,35 +0,0 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2010, Tomasz Dlugosz <tomek3d@gmail.com>'
|
||||
'''
|
||||
nczas.com
|
||||
'''
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
#
|
||||
|
||||
class NCzas(BasicNewsRecipe):
|
||||
title = u'Najwy\u017cszy Czas!'
|
||||
description = u'Najwy\u017cszy Czas!\nwydanie internetowe'
|
||||
__author__ = u'Tomasz D\u0142ugosz'
|
||||
language = 'pl'
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 100
|
||||
no_stylesheets = True
|
||||
cover_url = 'http://nczas.com/wp-content/themes/default/grafika/logo.png'
|
||||
|
||||
keep_only_tags = [dict(name='div', attrs={'class':'trescartykulu'})]
|
||||
|
||||
feeds = [(u'Najwy\u017cszy Czas!', u'http://nczas.com/feed/')]
|
||||
|
||||
def postprocess_html(self, soup, first):
|
||||
|
||||
for tag in soup.findAll(name= 'img', alt=""):
|
||||
tag.extract()
|
||||
|
||||
for item in soup.findAll(align = "right"):
|
||||
del item['align']
|
||||
|
||||
return soup
|
||||
46
resources/recipes/rmf24_ESKN.recipe
Normal file
46
resources/recipes/rmf24_ESKN.recipe
Normal file
@ -0,0 +1,46 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = u'2010, Tomasz Dlugosz <tomek3d@gmail.com>'
|
||||
'''
|
||||
rmf24.pl
|
||||
'''
|
||||
|
||||
import re
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class RMF24_ESKN(BasicNewsRecipe):
|
||||
title = u'Rmf24.pl - Ekonomia Sport Kultura Nauka'
|
||||
description = u'Ekonomia, sport, kultura i nauka ze strony rmf24.pl'
|
||||
language = 'pl'
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 100
|
||||
__author__ = u'Tomasz D\u0142ugosz'
|
||||
no_stylesheets = True
|
||||
remove_javascript = True
|
||||
|
||||
feeds = [(u'Ekonomia', u'http://www.rmf24.pl/ekonomia/feed'),
|
||||
(u'Sport', u'http://www.rmf24.pl/sport/feed'),
|
||||
(u'Kultura', u'http://www.rmf24.pl/kultura/feed'),
|
||||
(u'Nauka', u'http://www.rmf24.pl/nauka/feed')]
|
||||
|
||||
keep_only_tags = [dict(name='div', attrs={'class':'box articleSingle print'})]
|
||||
|
||||
remove_tags = [
|
||||
dict(name='div', attrs={'class':'toTop'}),
|
||||
dict(name='div', attrs={'class':'category'}),
|
||||
dict(name='div', attrs={'class':'REMOVE'}),
|
||||
dict(name='div', attrs={'class':'embed embedAd'})]
|
||||
|
||||
extra_css = '''
|
||||
h1 { font-size: 1.2em; }
|
||||
'''
|
||||
|
||||
preprocess_regexps = [
|
||||
(re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in
|
||||
[
|
||||
(r'<h2>Zdj.cie</h2>', lambda match: ''),
|
||||
(r'embed embed(Left|Right|Center) articleEmbed(Audio|Wideo articleEmbedVideo|ArticleFull|ArticleTitle|ArticleListTitle|AlbumHorizontal)">', lambda match: 'REMOVE">'),
|
||||
(r'<a href="http://www.facebook.com/pages/RMF24pl/.*?>RMF24.pl</a> on Facebook</div>', lambda match: '</div>')
|
||||
]
|
||||
]
|
||||
44
resources/recipes/rmf24_fakty.recipe
Normal file
44
resources/recipes/rmf24_fakty.recipe
Normal file
@ -0,0 +1,44 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = u'2010, Tomasz Dlugosz <tomek3d@gmail.com>'
|
||||
'''
|
||||
rmf24.pl
|
||||
'''
|
||||
|
||||
import re
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class RMF24(BasicNewsRecipe):
|
||||
title = u'Rmf24.pl - Fakty'
|
||||
description = u'Fakty ze strony rmf24.pl'
|
||||
language = 'pl'
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 100
|
||||
__author__ = u'Tomasz D\u0142ugosz'
|
||||
no_stylesheets = True
|
||||
remove_javascript = True
|
||||
|
||||
feeds = [(u'Kraj', u'http://www.rmf24.pl/fakty/polska/feed'),
|
||||
(u'\u015awiat', u'http://www.rmf24.pl/fakty/swiat/feed')]
|
||||
|
||||
keep_only_tags = [dict(name='div', attrs={'class':'box articleSingle print'})]
|
||||
|
||||
remove_tags = [
|
||||
dict(name='div', attrs={'id':'adBox625'}),
|
||||
dict(name='div', attrs={'class':'toTop'}),
|
||||
dict(name='div', attrs={'class':'category'}),
|
||||
dict(name='div', attrs={'class':'REMOVE'}),
|
||||
dict(name='div', attrs={'class':'embed embedAd'})]
|
||||
|
||||
extra_css = '''
|
||||
h1 { font-size: 1.2em; }
|
||||
'''
|
||||
preprocess_regexps = [
|
||||
(re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in
|
||||
[
|
||||
(r'<h2>Zdj.cie</h2>', lambda match: ''),
|
||||
(r'embed embed(Left|Right|Center) articleEmbed(Audio|Wideo articleEmbedVideo|ArticleFull|ArticleTitle|ArticleListTitle|AlbumHorizontal)">', lambda match: 'REMOVE">'),
|
||||
(r'<a href="http://www.facebook.com/pages/RMF24pl/.*?>RMF24.pl</a> on Facebook</div>', lambda match: '</div>')
|
||||
]
|
||||
]
|
||||
Loading…
x
Reference in New Issue
Block a user