mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-09 03:04:10 -04:00
Various updated Polish recipes
This commit is contained in:
Kovid Goyal
commit
a6acd8c1c9
@ -35,3 +35,7 @@ nbproject/
|
||||
.settings/
|
||||
*.DS_Store
|
||||
calibre_plugins/
|
||||
recipes/.git
|
||||
recipes/.gitignore
|
||||
recipes/README
|
||||
recipes/katalog_egazeciarz.recipe
|
||||
|
||||
@ -2,7 +2,9 @@ import re
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
|
||||
class FocusRecipe(BasicNewsRecipe):
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__author__ = u'intromatyk <intromatyk@gmail.com>'
|
||||
language = 'pl'
|
||||
@ -12,10 +14,10 @@ class FocusRecipe(BasicNewsRecipe):
|
||||
publisher = u'Gruner + Jahr Polska'
|
||||
category = u'News'
|
||||
description = u'Newspaper'
|
||||
category='magazine'
|
||||
cover_url=''
|
||||
remove_empty_feeds= True
|
||||
no_stylesheets=True
|
||||
category = 'magazine'
|
||||
cover_url = ''
|
||||
remove_empty_feeds = True
|
||||
no_stylesheets = True
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 100000
|
||||
recursions = 0
|
||||
@ -27,15 +29,15 @@ class FocusRecipe(BasicNewsRecipe):
|
||||
simultaneous_downloads = 5
|
||||
|
||||
r = re.compile('.*(?P<url>http:\/\/(www.focus.pl)|(rss.feedsportal.com\/c)\/.*\.html?).*')
|
||||
keep_only_tags =[]
|
||||
keep_only_tags.append(dict(name = 'div', attrs = {'id' : 'cll'}))
|
||||
keep_only_tags = []
|
||||
keep_only_tags.append(dict(name='div', attrs={'id': 'cll'}))
|
||||
|
||||
remove_tags =[]
|
||||
remove_tags.append(dict(name = 'div', attrs = {'class' : 'ulm noprint'}))
|
||||
remove_tags.append(dict(name = 'div', attrs = {'class' : 'txb'}))
|
||||
remove_tags.append(dict(name = 'div', attrs = {'class' : 'h2'}))
|
||||
remove_tags.append(dict(name = 'ul', attrs = {'class' : 'txu'}))
|
||||
remove_tags.append(dict(name = 'div', attrs = {'class' : 'ulc'}))
|
||||
remove_tags = []
|
||||
remove_tags.append(dict(name='div', attrs={'class': 'ulm noprint'}))
|
||||
remove_tags.append(dict(name='div', attrs={'class': 'txb'}))
|
||||
remove_tags.append(dict(name='div', attrs={'class': 'h2'}))
|
||||
remove_tags.append(dict(name='ul', attrs={'class': 'txu'}))
|
||||
remove_tags.append(dict(name='div', attrs={'class': 'ulc'}))
|
||||
|
||||
extra_css = '''
|
||||
body {font-family: verdana, arial, helvetica, geneva, sans-serif ;}
|
||||
@ -46,15 +48,14 @@ class FocusRecipe(BasicNewsRecipe):
|
||||
.fot{font-size: x-small; color: #666666;}
|
||||
'''
|
||||
|
||||
|
||||
feeds = [
|
||||
('Nauka', 'http://focus.pl.feedsportal.com/c/32992/f/532693/index.rss'),
|
||||
('Historia', 'http://focus.pl.feedsportal.com/c/32992/f/532694/index.rss'),
|
||||
('Cywilizacja', 'http://focus.pl.feedsportal.com/c/32992/f/532695/index.rss'),
|
||||
('Sport', 'http://focus.pl.feedsportal.com/c/32992/f/532696/index.rss'),
|
||||
('Technika', 'http://focus.pl.feedsportal.com/c/32992/f/532697/index.rss'),
|
||||
('Przyroda', 'http://focus.pl.feedsportal.com/c/32992/f/532698/index.rss'),
|
||||
('Technologie', 'http://focus.pl.feedsportal.com/c/32992/f/532699/index.rss'),
|
||||
('Nauka', 'http://www.focus.pl/nauka/rss/'),
|
||||
('Historia', 'http://www.focus.pl/historia/rss/'),
|
||||
('Cywilizacja', 'http://www.focus.pl/cywilizacja/rss/'),
|
||||
('Sport', 'http://www.focus.pl/sport/rss/'),
|
||||
('Technika', 'http://www.focus.pl/technika/rss/'),
|
||||
('Przyroda', 'http://www.focus.pl/przyroda/rss/'),
|
||||
('Technologie', 'http://www.focus.pl/gadzety/rss/')
|
||||
]
|
||||
|
||||
def skip_ad_pages(self, soup):
|
||||
@ -65,20 +66,20 @@ class FocusRecipe(BasicNewsRecipe):
|
||||
return None
|
||||
|
||||
def get_cover_url(self):
|
||||
soup=self.index_to_soup('http://www.focus.pl/magazyn/')
|
||||
tag=soup.find(name='div', attrs={'class':'clr fl'})
|
||||
soup = self.index_to_soup('http://www.focus.pl/magazyn/')
|
||||
tag = soup.find(name='div', attrs={'class': 'clr fl'})
|
||||
if tag:
|
||||
self.cover_url='http://www.focus.pl/' + tag.a['href']
|
||||
self.cover_url = 'http://www.focus.pl/' + tag.a['href']
|
||||
return getattr(self, 'cover_url', self.cover_url)
|
||||
|
||||
def print_version(self, url):
|
||||
if url.count ('focus.pl.feedsportal.com'):
|
||||
if url.count('focus.pl.feedsportal.com'):
|
||||
u = url.find('focus0Bpl')
|
||||
u = 'http://www.focus.pl/' + url[u + 11:]
|
||||
u = u.replace('0C', '/')
|
||||
u = u.replace('A', '')
|
||||
u = u.replace ('0E','-')
|
||||
u = u.replace('0E', '-')
|
||||
u = u.replace('/nc/1//story01.htm', '/do-druku/1')
|
||||
else:
|
||||
u = url.replace('/nc/1','/do-druku/1')
|
||||
u = url.replace('/nc/1', '/do-druku/1')
|
||||
return u
|
||||
@ -1,104 +1,107 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
|
||||
class Gazeta_Wyborcza(BasicNewsRecipe):
|
||||
title = u'Gazeta Wyborcza'
|
||||
__author__ = 'fenuks'
|
||||
__author__ = 'fenuks, Artur Stachecki'
|
||||
language = 'pl'
|
||||
description ='news from gazeta.pl'
|
||||
category='newspaper'
|
||||
description = 'news from gazeta.pl'
|
||||
category = 'newspaper'
|
||||
publication_type = 'newspaper'
|
||||
masthead_url='http://bi.gazeta.pl/im/5/10285/z10285445AA.jpg'
|
||||
INDEX='http://wyborcza.pl'
|
||||
remove_empty_feeds= True
|
||||
masthead_url = 'http://bi.gazeta.pl/im/5/10285/z10285445AA.jpg'
|
||||
INDEX = 'http://wyborcza.pl'
|
||||
remove_empty_feeds = True
|
||||
oldest_article = 3
|
||||
max_articles_per_feed = 100
|
||||
remove_javascript=True
|
||||
no_stylesheets=True
|
||||
ignore_duplicate_articles = {'title', 'url'}
|
||||
keep_only_tags = dict(id=['gazeta_article', 'article'])
|
||||
remove_tags_after = dict(id='gazeta_article_share')
|
||||
remove_tags = [dict(attrs={'class':['artReadMore', 'gazeta_article_related_new', 'txt_upl']}), dict(id=['gazeta_article_likes', 'gazeta_article_tools', 'rel', 'gazeta_article_tags', 'gazeta_article_share', 'gazeta_article_brand', 'gazeta_article_miniatures'])]
|
||||
|
||||
remove_javascript = True
|
||||
no_stylesheets = True
|
||||
remove_tags_before = dict(id='k0')
|
||||
remove_tags_after = dict(id='banP4')
|
||||
remove_tags = [dict(name='div', attrs={'class':'rel_box'}), dict(attrs={'class':['date', 'zdjP', 'zdjM', 'pollCont', 'rel_video', 'brand', 'txt_upl']}), dict(name='div', attrs={'id':'footer'})]
|
||||
feeds = [(u'Kraj', u'http://rss.feedsportal.com/c/32739/f/530266/index.rss'), (u'\u015awiat', u'http://rss.feedsportal.com/c/32739/f/530270/index.rss'),
|
||||
(u'Wyborcza.biz', u'http://wyborcza.biz/pub/rss/wyborcza_biz_wiadomosci.htm'),
|
||||
(u'Komentarze', u'http://rss.feedsportal.com/c/32739/f/530312/index.rss'),
|
||||
(u'Kultura', u'http://rss.gazeta.pl/pub/rss/gazetawyborcza_kultura.xml'),
|
||||
(u'Nauka', u'http://rss.feedsportal.com/c/32739/f/530269/index.rss'),
|
||||
(u'Opinie', u'http://rss.gazeta.pl/pub/rss/opinie.xml'),
|
||||
(u'Gazeta \u015awi\u0105teczna', u'http://rss.feedsportal.com/c/32739/f/530431/index.rss'),
|
||||
#(u'Du\u017cy Format', u'http://rss.feedsportal.com/c/32739/f/530265/index.rss'),
|
||||
(u'Witamy w Polsce', u'http://rss.feedsportal.com/c/32739/f/530476/index.rss'),
|
||||
(u'M\u0119ska Muzyka', u'http://rss.feedsportal.com/c/32739/f/530337/index.rss'),
|
||||
(u'Lata Lec\u0105', u'http://rss.feedsportal.com/c/32739/f/530326/index.rss'),
|
||||
(u'Solidarni z Tybetem', u'http://rss.feedsportal.com/c/32739/f/530461/index.rss'),
|
||||
(u'W pon. - \u017bakowski', u'http://rss.feedsportal.com/c/32739/f/530491/index.rss'),
|
||||
(u'We wt. - Kolenda-Zalewska', u'http://rss.feedsportal.com/c/32739/f/530310/index.rss'),
|
||||
(u'\u015aroda w \u015brod\u0119', u'http://rss.feedsportal.com/c/32739/f/530428/index.rss'),
|
||||
(u'W pi\u0105tek - Olejnik', u'http://rss.feedsportal.com/c/32739/f/530364/index.rss')
|
||||
(u'Nauka', u'http://rss.feedsportal.com/c/32739/f/530269/index.rss'), (u'Opinie', u'http://rss.gazeta.pl/pub/rss/opinie.xml'), (u'Gazeta \u015awi\u0105teczna', u'http://rss.feedsportal.com/c/32739/f/530431/index.rss'), (u'Du\u017cy Format', u'http://rss.feedsportal.com/c/32739/f/530265/index.rss'), (u'Witamy w Polsce', u'http://rss.feedsportal.com/c/32739/f/530476/index.rss'), (u'M\u0119ska Muzyka', u'http://rss.feedsportal.com/c/32739/f/530337/index.rss'), (u'Lata Lec\u0105', u'http://rss.feedsportal.com/c/32739/f/530326/index.rss'), (u'Solidarni z Tybetem', u'http://rss.feedsportal.com/c/32739/f/530461/index.rss'), (u'W pon. - \u017bakowski', u'http://rss.feedsportal.com/c/32739/f/530491/index.rss'), (u'We wt. - Kolenda-Zalewska', u'http://rss.feedsportal.com/c/32739/f/530310/index.rss'), (u'\u015aroda w \u015brod\u0119', u'http://rss.feedsportal.com/c/32739/f/530428/index.rss'), (u'W pi\u0105tek - Olejnik', u'http://rss.feedsportal.com/c/32739/f/530364/index.rss'), (u'Nekrologi', u'http://rss.feedsportal.com/c/32739/f/530358/index.rss')
|
||||
]
|
||||
|
||||
def skip_ad_pages(self, soup):
|
||||
tag=soup.find(name='a', attrs={'class':'btn'})
|
||||
tag = soup.find(name='a', attrs={'class': 'btn'})
|
||||
if tag:
|
||||
new_soup=self.index_to_soup(tag['href'], raw=True)
|
||||
new_soup = self.index_to_soup(tag['href'], raw=True)
|
||||
return new_soup
|
||||
|
||||
|
||||
def append_page(self, soup, appendtag):
|
||||
loop=False
|
||||
tag = soup.find('div', attrs={'id':'Str'})
|
||||
if appendtag.find('div', attrs={'id':'Str'}):
|
||||
nexturl=tag.findAll('a')
|
||||
appendtag.find('div', attrs={'id':'Str'}).extract()
|
||||
loop=True
|
||||
loop = False
|
||||
tag = soup.find('div', attrs={'id': 'Str'})
|
||||
if appendtag.find('div', attrs={'id': 'Str'}):
|
||||
nexturl = tag.findAll('a')
|
||||
appendtag.find('div', attrs={'id': 'Str'}).extract()
|
||||
loop = True
|
||||
if appendtag.find(id='source'):
|
||||
appendtag.find(id='source').extract()
|
||||
while loop:
|
||||
loop=False
|
||||
loop = False
|
||||
for link in nexturl:
|
||||
if u'następne' in link.string:
|
||||
url= self.INDEX + link['href']
|
||||
url = self.INDEX + link['href']
|
||||
soup2 = self.index_to_soup(url)
|
||||
pagetext = soup2.find(id='artykul')
|
||||
pos = len(appendtag.contents)
|
||||
appendtag.insert(pos, pagetext)
|
||||
tag = soup2.find('div', attrs={'id':'Str'})
|
||||
nexturl=tag.findAll('a')
|
||||
loop=True
|
||||
tag = soup2.find('div', attrs={'id': 'Str'})
|
||||
nexturl = tag.findAll('a')
|
||||
loop = True
|
||||
|
||||
def gallery_article(self, appendtag):
|
||||
tag=appendtag.find(id='container_gal')
|
||||
tag = appendtag.find(id='container_gal')
|
||||
if tag:
|
||||
nexturl=appendtag.find(id='gal_btn_next').a['href']
|
||||
nexturl = appendtag.find(id='gal_btn_next').a['href']
|
||||
appendtag.find(id='gal_navi').extract()
|
||||
while nexturl:
|
||||
soup2=self.index_to_soup(nexturl)
|
||||
pagetext=soup2.find(id='container_gal')
|
||||
nexturl=pagetext.find(id='gal_btn_next')
|
||||
soup2 = self.index_to_soup(nexturl)
|
||||
pagetext = soup2.find(id='container_gal')
|
||||
nexturl = pagetext.find(id='gal_btn_next')
|
||||
if nexturl:
|
||||
nexturl=nexturl.a['href']
|
||||
nexturl = nexturl.a['href']
|
||||
pos = len(appendtag.contents)
|
||||
appendtag.insert(pos, pagetext)
|
||||
rem=appendtag.find(id='gal_navi')
|
||||
rem = appendtag.find(id='gal_navi')
|
||||
if rem:
|
||||
rem.extract()
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
if soup.find(attrs={'class': 'piano_btn_1'}):
|
||||
return None
|
||||
else:
|
||||
self.append_page(soup, soup.body)
|
||||
if soup.find(id='container_gal'):
|
||||
self.gallery_article(soup.body)
|
||||
return soup
|
||||
|
||||
def print_version(self, url):
|
||||
if 'http://wyborcza.biz/biznes/' not in url:
|
||||
return url
|
||||
if url.count('rss.feedsportal.com'):
|
||||
u = url.find('wyborcza0Bpl')
|
||||
u = 'http://www.wyborcza.pl/' + url[u + 11:]
|
||||
u = u.replace('0C', '/')
|
||||
u = u.replace('A', '')
|
||||
u = u.replace('0E', '-')
|
||||
u = u.replace('0H', ',')
|
||||
u = u.replace('0I', '_')
|
||||
u = u.replace('0B', '.')
|
||||
u = u.replace('/1,', '/2029020,')
|
||||
u = u.replace('/story01.htm', '')
|
||||
print(u)
|
||||
return u
|
||||
elif 'http://wyborcza.pl/1' in url:
|
||||
return url.replace('http://wyborcza.pl/1', 'http://wyborcza.pl/2029020')
|
||||
else:
|
||||
return url.replace('http://wyborcza.biz/biznes/1', 'http://wyborcza.biz/biznes/2029020')
|
||||
|
||||
def get_cover_url(self):
|
||||
soup = self.index_to_soup('http://wyborcza.pl/0,76762,3751429.html')
|
||||
cover=soup.find(id='GWmini2')
|
||||
soup = self.index_to_soup('http://wyborcza.pl/'+ cover.contents[3].a['href'])
|
||||
self.cover_url='http://wyborcza.pl' + soup.img['src']
|
||||
cover = soup.find(id='GWmini2')
|
||||
soup = self.index_to_soup('http://wyborcza.pl/' + cover.contents[3].a['href'])
|
||||
self.cover_url = 'http://wyborcza.pl' + soup.img['src']
|
||||
return getattr(self, 'cover_url', self.cover_url)
|
||||
|
||||
@ -4,7 +4,7 @@ from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
class FocusRecipe(BasicNewsRecipe):
|
||||
__license__ = 'GPL v3'
|
||||
__author__ = u'intromatyk <intromatyk@gmail.com>'
|
||||
__author__ = u'Artur Stachecki <artur.stachecki@gmail.com>'
|
||||
language = 'pl'
|
||||
version = 1
|
||||
|
||||
|
||||
@ -34,16 +34,20 @@ class RzeczpospolitaRecipe(BasicNewsRecipe):
|
||||
keep_only_tags.append(dict(name = 'div', attrs = {'id' : 'story'}))
|
||||
|
||||
remove_tags =[]
|
||||
remove_tags.append(dict(name = 'div', attrs = {'class' : 'articleLeftBox'}))
|
||||
remove_tags.append(dict(name = 'div', attrs = {'class' : 'socialNewTools'}))
|
||||
remove_tags.append(dict(name = 'div', attrs = {'id' : 'socialTools'}))
|
||||
remove_tags.append(dict(name = 'div', attrs = {'class' : 'articleToolBoxTop'}))
|
||||
remove_tags.append(dict(name = 'div', attrs = {'class' : 'clr'}))
|
||||
remove_tags.append(dict(name = 'div', attrs = {'id' : 'recommendations'}))
|
||||
remove_tags.append(dict(name = 'div', attrs = {'id' : 'editorPicks'}))
|
||||
remove_tags.append(dict(name = 'div', attrs = {'class' : 'editorPicks'}))
|
||||
remove_tags.append(dict(name = 'div', attrs = {'class' : 'editorPicks editorPicksFirst'}))
|
||||
remove_tags.append(dict(name = 'div', attrs = {'id' : 'articleCopyrightText'}))
|
||||
remove_tags.append(dict(name = 'div', attrs = {'id' : 'articleCopyrightButton'}))
|
||||
remove_tags.append(dict(name = 'div', attrs = {'class' : 'articleToolBoxBottom'}))
|
||||
remove_tags.append(dict(name = 'div', attrs = {'class' : 'more'}))
|
||||
remove_tags.append(dict(name = 'div', attrs = {'class' : 'addRecommendation'}))
|
||||
remove_tags.append(dict(name = 'h3', attrs = {'id' : 'tags'}))
|
||||
|
||||
extra_css = '''
|
||||
body {font-family: verdana, arial, helvetica, geneva, sans-serif ;}
|
||||
@ -67,3 +71,4 @@ class RzeczpospolitaRecipe(BasicNewsRecipe):
|
||||
|
||||
return start + '/' + index + '?print=tak'
|
||||
|
||||
|
||||
|
||||
@ -1,34 +1,55 @@
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
from calibre.utils.magick import Image
|
||||
class tvn24(BasicNewsRecipe):
|
||||
title = u'TVN24'
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 100
|
||||
__author__ = 'fenuks'
|
||||
__author__ = 'fenuks, Artur Stachecki'
|
||||
description = u'Sport, Biznes, Gospodarka, Informacje, Wiadomości Zawsze aktualne wiadomości z Polski i ze świata'
|
||||
category = 'news'
|
||||
language = 'pl'
|
||||
#masthead_url= 'http://www.tvn24.pl/_d/topmenu/logo2.gif'
|
||||
cover_url= 'http://www.userlogos.org/files/logos/Struna/TVN24.jpg'
|
||||
extra_css = 'ul {list-style:none;} \
|
||||
li {list-style:none; float: left; margin: 0 0.15em;} \
|
||||
h2 {font-size: medium} \
|
||||
.date60m {float: left; margin: 0 10px 0 5px;}'
|
||||
masthead_url= 'http://www.tvn24.pl/_d/topmenu/logo2.gif'
|
||||
cover_url= 'http://www.tvn24.pl/_d/topmenu/logo2.gif'
|
||||
extra_css= 'ul {list-style: none; padding: 0; margin: 0;} li {float: left;margin: 0 0.15em;}'
|
||||
remove_empty_feeds = True
|
||||
remove_javascript = True
|
||||
no_stylesheets = True
|
||||
use_embedded_content = False
|
||||
ignore_duplicate_articles = {'title', 'url'}
|
||||
keep_only_tags=[dict(name='h1', attrs={'class':['size30 mt10 pb10', 'size38 mt10 pb15']}), dict(name='figure', attrs={'class':'articleMainPhoto articleMainPhotoWide'}), dict(name='article', attrs={'class':['mb20', 'mb20 textArticleDefault']}), dict(name='ul', attrs={'class':'newsItem'})]
|
||||
remove_tags = [dict(name='aside', attrs={'class':['innerArticleModule onRight cols externalContent', 'innerArticleModule center']}), dict(name='div', attrs={'class':['thumbsGallery', 'articleTools', 'article right rd7', 'heading', 'quizContent']}), dict(name='a', attrs={'class':'watchMaterial text'}), dict(name='section', attrs={'class':['quiz toCenter', 'quiz toRight']})]
|
||||
|
||||
feeds = [(u'Najnowsze', u'http://www.tvn24.pl/najnowsze.xml'),
|
||||
(u'Polska', u'www.tvn24.pl/polska.xml'), (u'\u015awiat', u'http://www.tvn24.pl/swiat.xml'), (u'Sport', u'http://www.tvn24.pl/sport.xml'), (u'Biznes', u'http://www.tvn24.pl/biznes.xml'), (u'Meteo', u'http://www.tvn24.pl/meteo.xml'), (u'Micha\u0142ki', u'http://www.tvn24.pl/michalki.xml'), (u'Kultura', u'http://www.tvn24.pl/kultura.xml')]
|
||||
keep_only_tags=[
|
||||
# dict(name='h1', attrs={'class':'size38 mt20 pb20'}),
|
||||
dict(name='div', attrs={'class':'mainContainer'}),
|
||||
# dict(name='p'),
|
||||
# dict(attrs={'class':['size18 mt10 mb15', 'bold topicSize1', 'fromUsers content', 'textArticleDefault']})
|
||||
]
|
||||
remove_tags=[
|
||||
dict(attrs={'class':['commentsInfo', 'textSize', 'related newsNews align-right', 'box', 'watchMaterial text', 'related galleryGallery align-center', 'advert block-alignment-right', 'userActions', 'socialBookmarks', 'im yourArticle fl', 'dynamicButton addComment fl', 'innerArticleModule onRight cols externalContent', 'thumbsGallery', 'relatedObject customBlockquote align-right', 'lead', 'mainRightColumn', 'articleDateContainer borderGreyBottom', 'socialMediaContainer onRight loaded', 'quizContent', 'twitter', 'facebook', 'googlePlus', 'share', 'voteResult', 'reportTitleBar bgBlue_v4 mb15', 'innerVideoModule center']}),
|
||||
dict(name='article', attrs={'class':['singleArtPhotoCenter', 'singleArtPhotoRight', 'singleArtPhotoLeft']}),
|
||||
dict(name='section', attrs={'id':['forum', 'innerArticle', 'quiz toCenter', 'mb20']}),
|
||||
dict(name='div', attrs={'class':'socialMediaContainer big p20 mb20 borderGrey loaded'})
|
||||
]
|
||||
remove_tags_after=[dict(name='li', attrs={'class':'share'})]
|
||||
feeds = [(u'Najnowsze', u'http://www.tvn24.pl/najnowsze.xml'), ]
|
||||
#(u'Polska', u'www.tvn24.pl/polska.xml'), (u'\u015awiat', u'http://www.tvn24.pl/swiat.xml'), (u'Sport', u'http://www.tvn24.pl/sport.xml'), (u'Biznes', u'http://www.tvn24.pl/biznes.xml'), (u'Meteo', u'http://www.tvn24.pl/meteo.xml'), (u'Micha\u0142ki', u'http://www.tvn24.pl/michalki.xml'), (u'Kultura', u'http://www.tvn24.pl/kultura.xml')]
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
for item in soup.findAll(style=True):
|
||||
del item['style']
|
||||
tag = soup.find(name='ul', attrs={'class':'newsItem'})
|
||||
if tag:
|
||||
tag.name='div'
|
||||
tag.li.name='div'
|
||||
return soup
|
||||
|
||||
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
|
||||
|
||||
def postprocess_html(self, soup, first):
|
||||
#process all the images
|
||||
for tag in soup.findAll(lambda tag: tag.name.lower()=='img' and tag.has_key('src')):
|
||||
iurl = tag['src']
|
||||
img = Image()
|
||||
img.open(iurl)
|
||||
if img < 0:
|
||||
raise RuntimeError('Out of memory')
|
||||
img.type = "GrayscaleType"
|
||||
img.save(iurl)
|
||||
return soup
|
||||
|
||||
@ -3,6 +3,8 @@
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = '2010, matek09, matek09@gmail.com'
|
||||
__copyright__ = 'Modified 2011, Mariusz Wolek <mariusz_dot_wolek @ gmail dot com>'
|
||||
__copyright__ = 'Modified 2012, Artur Stachecki <artur.stachecki@gmail.com>'
|
||||
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
import re
|
||||
@ -11,7 +13,7 @@ class Wprost(BasicNewsRecipe):
|
||||
EDITION = 0
|
||||
FIND_LAST_FULL_ISSUE = True
|
||||
EXCLUDE_LOCKED = True
|
||||
ICO_BLOCKED = 'http://www.wprost.pl/G/icons/ico_blocked.gif'
|
||||
ICO_BLOCKED = 'http://www.wprost.pl/G/layout2/ico_blocked.png'
|
||||
|
||||
title = u'Wprost'
|
||||
__author__ = 'matek09'
|
||||
@ -20,6 +22,7 @@ class Wprost(BasicNewsRecipe):
|
||||
no_stylesheets = True
|
||||
language = 'pl'
|
||||
remove_javascript = True
|
||||
recursions = 0
|
||||
|
||||
remove_tags_before = dict(dict(name = 'div', attrs = {'id' : 'print-layer'}))
|
||||
remove_tags_after = dict(dict(name = 'div', attrs = {'id' : 'print-layer'}))
|
||||
@ -35,13 +38,15 @@ class Wprost(BasicNewsRecipe):
|
||||
(re.compile(r'\<td\>\<tr\>\<\/table\>'), lambda match: ''),
|
||||
(re.compile(r'\<table .*?\>'), lambda match: ''),
|
||||
(re.compile(r'\<tr>'), lambda match: ''),
|
||||
(re.compile(r'\<td .*?\>'), lambda match: '')]
|
||||
(re.compile(r'\<td .*?\>'), lambda match: ''),
|
||||
(re.compile(r'\<div id="footer"\>.*?\</footer\>'), lambda match: '')]
|
||||
|
||||
remove_tags =[]
|
||||
remove_tags.append(dict(name = 'div', attrs = {'class' : 'def element-date'}))
|
||||
remove_tags.append(dict(name = 'div', attrs = {'class' : 'def silver'}))
|
||||
remove_tags.append(dict(name = 'div', attrs = {'id' : 'content-main-column-right'}))
|
||||
|
||||
|
||||
extra_css = '''
|
||||
.div-header {font-size: x-small; font-weight: bold}
|
||||
'''
|
||||
@ -59,27 +64,26 @@ class Wprost(BasicNewsRecipe):
|
||||
a = 0
|
||||
if self.FIND_LAST_FULL_ISSUE:
|
||||
ico_blocked = soup.findAll('img', attrs={'src' : self.ICO_BLOCKED})
|
||||
a = ico_blocked[-1].findNext('a', attrs={'title' : re.compile('Zobacz spis tre.ci')})
|
||||
a = ico_blocked[-1].findNext('a', attrs={'title' : re.compile(r'Spis *', re.IGNORECASE | re.DOTALL)})
|
||||
else:
|
||||
a = soup.find('a', attrs={'title' : re.compile('Zobacz spis tre.ci')})
|
||||
a = soup.find('a', attrs={'title' : re.compile(r'Spis *', re.IGNORECASE | re.DOTALL)})
|
||||
self.EDITION = a['href'].replace('/tygodnik/?I=', '')
|
||||
self.EDITION_SHORT = a['href'].replace('/tygodnik/?I=15', '')
|
||||
self.cover_url = a.img['src']
|
||||
|
||||
|
||||
|
||||
def parse_index(self):
|
||||
self.find_last_issue()
|
||||
soup = self.index_to_soup('http://www.wprost.pl/tygodnik/?I=' + self.EDITION)
|
||||
feeds = []
|
||||
for main_block in soup.findAll(attrs={'class':'main-block-s3 s3-head head-red3'}):
|
||||
for main_block in soup.findAll(attrs={'id': 'content-main-column-element-content'}):
|
||||
articles = list(self.find_articles(main_block))
|
||||
if len(articles) > 0:
|
||||
section = self.tag_to_string(main_block)
|
||||
section = self.tag_to_string(main_block.find('h3'))
|
||||
feeds.append((section, articles))
|
||||
return feeds
|
||||
|
||||
def find_articles(self, main_block):
|
||||
for a in main_block.findAllNext( attrs={'style':['','padding-top: 15px;']}):
|
||||
for a in main_block.findAll('a'):
|
||||
if a.name in "td":
|
||||
break
|
||||
if self.EXCLUDE_LOCKED & self.is_blocked(a):
|
||||
@ -91,3 +95,4 @@ class Wprost(BasicNewsRecipe):
|
||||
'description' : ''
|
||||
}
|
||||
|
||||
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user