Various Polish news sources by fenuks

This commit is contained in:
Kovid Goyal 2011-12-17 22:39:34 +05:30
parent 2de126e308
commit b833605f57
11 changed files with 144 additions and 0 deletions

19
recipes/biolog_pl.recipe Normal file
View File

@ -0,0 +1,19 @@
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
from calibre.web.feeds.news import BasicNewsRecipe
class Biolog_pl(BasicNewsRecipe):
title = u'Biolog.pl'
oldest_article = 7
max_articles_per_feed = 100
remove_empty_feeds=True
__author__ = 'fenuks'
description = u'Przyrodnicze aktualności ze świata nauki (codziennie aktualizowane), kurs biologii, testy i sprawdziany, forum dyskusyjne.'
category = 'biology'
language = 'pl'
cover_url='http://www.biolog.pl/naukowy,portal,biolog.png'
no_stylesheets = True
#keeps_only_tags=[dict(id='main')]
remove_tags_before=dict(id='main')
remove_tags_after=dict(name='a', attrs={'name':'komentarze'})
remove_tags=[dict(name='img', attrs={'alt':'Komentarze'})]
feeds = [(u'Wszystkie', u'http://www.biolog.pl/backend.php'), (u'Medycyna', u'http://www.biolog.pl/medycyna-rss.php'), (u'Ekologia', u'http://www.biolog.pl/rss-ekologia.php'), (u'Genetyka i biotechnologia', u'http://www.biolog.pl/rss-biotechnologia.php'), (u'Botanika', u'http://www.biolog.pl/rss-botanika.php'), (u'Le\u015bnictwo', u'http://www.biolog.pl/rss-lesnictwo.php'), (u'Zoologia', u'http://www.biolog.pl/rss-zoologia.php')]

View File

@ -0,0 +1,22 @@
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
from calibre.web.feeds.news import BasicNewsRecipe
class Computerworld_pl(BasicNewsRecipe):
title = u'Computerworld.pl'
__author__ = 'fenuks'
description = u'Serwis o IT w przemyśle, finansach, handlu, administracji oraz rynku IT i telekomunikacyjnym - wiadomości, opinie, analizy, porady prawne'
category = 'IT'
language = 'pl'
no_stylesheets=True
oldest_article = 7
max_articles_per_feed = 100
keep_only_tags=[dict(name='div', attrs={'id':'s'})]
remove_tags_after=dict(name='div', attrs={'class':'rMobi'})
remove_tags=[dict(name='div', attrs={'class':['nnav', 'rMobi']}), dict(name='table', attrs={'class':'ramka_slx'})]
feeds = [(u'Wiadomo\u015bci', u'http://rssout.idg.pl/cw/news_iso.xml')]
def get_cover_url(self):
soup = self.index_to_soup('http://www.computerworld.pl/')
cover=soup.find(name='img', attrs={'class':'prawo'})
self.cover_url=cover['src']
return getattr(self, 'cover_url', self.cover_url)

View File

@ -0,0 +1,58 @@
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
from calibre.web.feeds.news import BasicNewsRecipe
import re
class Dziennik_pl(BasicNewsRecipe):
title = u'Dziennik.pl'
__author__ = 'fenuks'
description = u'Wiadomości z kraju i ze świata. Wiadomości gospodarcze. Znajdziesz u nas informacje, wydarzenia, komentarze, opinie.'
category = 'newspaper'
language = 'pl'
cover_url='http://6.s.dziennik.pl/images/og_dziennik.jpg'
no_stylesheets = True
oldest_article = 7
max_articles_per_feed = 100
remove_javascript=True
remove_empty_feeds=True
preprocess_regexps = [(re.compile("Komentarze:"), lambda m: '')]
keep_only_tags=[dict(id='article')]
remove_tags=[dict(name='div', attrs={'class':['art_box_dodatki', 'new_facebook_icons2', 'leftArt', 'article_print', 'quiz-widget']}), dict(name='a', attrs={'class':'komentarz'})]
feeds = [(u'Wszystko', u'http://rss.dziennik.pl/Dziennik-PL/'),
(u'Wiadomości', u'http://rss.dziennik.pl/Dziennik-Wiadomosci'),
(u'Gospodarka', u'http://rss.dziennik.pl/Dziennik-Gospodarka'),
(u'Kobieta', u'http://rss.dziennik.pl/Dziennik-Kobieta'),
(u'Auto', u'http://rss.dziennik.pl/Dziennik-Auto'),
(u'Rozrywka', u'http://rss.dziennik.pl/Dziennik-Rozrywka'),
(u'Film', u'http://rss.dziennik.pl/Dziennik-Film'),
(u'Muzyka' , u'http://rss.dziennik.pl/Dziennik-Muzyka'),
(u'Kultura', u'http://rss.dziennik.pl/Dziennik-Kultura'),
(u'Nauka', u'http://rss.dziennik.pl/Dziennik-Nauka'),
(u'Podróże', u'http://rss.dziennik.pl/Dziennik-Podroze/'),
(u'Nieruchomości', u'http://rss.dziennik.pl/Dziennik-Nieruchomosci')]
def append_page(self, soup, appendtag):
tag=soup.find('a', attrs={'class':'page_next'})
if tag:
appendtag.find('div', attrs={'class':'article_paginator'}).extract()
while tag:
soup2= self.index_to_soup(tag['href'])
tag=soup2.find('a', attrs={'class':'page_next'})
if not tag:
for r in appendtag.findAll('div', attrs={'class':'art_src'}):
r.extract()
pagetext = soup2.find(name='div', attrs={'class':'article_body'})
for dictionary in self.remove_tags:
v=pagetext.findAll(name=dictionary['name'], attrs=dictionary['attrs'])
for delete in v:
delete.extract()
pos = len(appendtag.contents)
appendtag.insert(pos, pagetext)
if appendtag.find('div', attrs={'class':'article_paginator'}):
appendtag.find('div', attrs={'class':'article_paginator'}).extract()
def preprocess_html(self, soup):
self.append_page(soup, soup.body)
return soup

16
recipes/emuzica_pl.recipe Normal file
View File

@ -0,0 +1,16 @@
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
from calibre.web.feeds.news import BasicNewsRecipe
class eMuzyka(BasicNewsRecipe):
title = u'eMuzyka'
__author__ = 'fenuks'
description = u'Emuzyka to największa i najpopularniejsza strona o muzyce w Polsce'
category = 'music'
language = 'pl'
cover_url='http://s.emuzyka.pl/img/emuzyka_invert_small.jpg'
no_stylesheets = True
oldest_article = 7
max_articles_per_feed = 100
keep_only_tags=[dict(name='div', attrs={'id':'news_container'}), dict(name='h3'), dict(name='div', attrs={'class':'review_text'})]
remove_tags=[dict(name='span', attrs={'id':'date'})]
feeds = [(u'Aktualno\u015bci', u'http://www.emuzyka.pl/rss.php?f=1'), (u'Recenzje', u'http://www.emuzyka.pl/rss.php?f=2')]

BIN
recipes/icons/biolog_pl.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 1.2 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 373 B

Binary file not shown.

After

Width:  |  Height:  |  Size: 481 B

Binary file not shown.

After

Width:  |  Height:  |  Size: 1.2 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 15 KiB

View File

@ -0,0 +1,14 @@
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
from calibre.web.feeds.news import BasicNewsRecipe
class Kosmonauta(BasicNewsRecipe):
title = u'Kosmonauta.net'
__author__ = 'fenuks'
description = u'polskojęzyczny portal w całości dedykowany misjom kosmicznym i badaniom kosmosu.'
category = 'astronomy'
language = 'pl'
cover_url='http://bi.gazeta.pl/im/4/10393/z10393414X,Kosmonauta-net.jpg'
no_stylesheets = True
oldest_article = 7
max_articles_per_feed = 100
feeds = [(u'Kosmonauta.net', u'http://www.kosmonauta.net/index.php/feed/rss.html')]

View File

@ -0,0 +1,15 @@
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
from calibre.web.feeds.news import BasicNewsRecipe
class Mlody_technik(BasicNewsRecipe):
title = u'Mlody technik'
__author__ = 'fenuks'
description = u'Młody technik'
category = 'science'
language = 'pl'
cover_url='http://science-everywhere.pl/wp-content/uploads/2011/10/mt12.jpg'
no_stylesheets = True
oldest_article = 7
max_articles_per_feed = 100
#keep_only_tags=[dict(id='container')]
feeds = [(u'Artyku\u0142y', u'http://www.mt.com.pl/feed')]