Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 10:14:46 -04:00
Code Issues Packages Projects Releases Wiki Activity

partial fix for telepolis_pl

Browse Source
This commit is contained in:
Tomasz Długosz 2013-03-04 23:44:07 +01:00
parent 59d17954f2
commit c8fe13195c
1 changed files with 9 additions and 49 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

58
recipes/telepolis_pl.recipe
View File

@ -8,60 +8,20 @@ import re
class telepolis(BasicNewsRecipe):
title = u'Telepolis.pl'
__author__ = 'Artur Stachecki <artur.stachecki@gmail.com>'
__author__ = 'Artur Stachecki <artur.stachecki@gmail.com>, Tomasz Długosz <tomek3d@gmail.com>'
language = 'pl'
description = u'Twój telekomunikacyjny serwis informacyjny.\
Codzienne informacje, testy i artykuły,\
promocje, baza telefonów oraz centrum rozrywki'
oldest_article = 7
description = u'Twój telekomunikacyjny serwis informacyjny.'
masthead_url = 'http://telepolis.pl/i/telepolis-logo2.gif'
max_articles_per_feed = 100
simultaneous_downloads = 5
remove_javascript = True
no_stylesheets = True
use_embedded_content = False
remove_tags = []
remove_tags.append(dict(attrs={'alt': 'TELEPOLIS.pl'}))
preprocess_regexps = [(re.compile(r'<: .*? :>'),
lambda match: ''),
(re.compile(r'<b>Zobacz:</b>.*?</a>', re.DOTALL),
lambda match: ''),
(re.compile(r'<-ankieta.*?>'),
lambda match: ''),
(re.compile(r'\(Q\!\)'),
lambda match: ''),
(re.compile(r'\(plik.*?\)'),
lambda match: ''),
(re.compile(r'<br.*?><br.*?>', re.DOTALL),
lambda match: '')
]
extra_css = '''.tb { font-weight: bold; font-size: 20px;}'''
feeds = [
(u'Wiadomości', u'http://www.telepolis.pl/rss/news.php'),
(u'Artykuły', u'http://www.telepolis.pl/rss/artykuly.php')
(u'Wiadomości', u'http://www.telepolis.pl/rss/news.php')#,
#(u'Artykuły', u'http://www.telepolis.pl/rss/artykuly.php')
]
def print_version(self, url):
if 'news.php' in url:
print_url = url.replace('news.php', 'news_print.php')
else:
print_url = url.replace('artykuly.php', 'art_print.php')
return print_url
def preprocess_html(self, soup):
for image in soup.findAll('img'):
if 'm.jpg' in image['src']:
image_big = image['src']
image_big = image_big.replace('m.jpg', '.jpg')
image['src'] = image_big
logo = soup.find('tr')
logo.extract()
for tag in soup.findAll('tr'):
for strings in ['Wiadomość wydrukowana', 'copyright']:
if strings in self.tag_to_string(tag):
tag.extract()
return self.adeify_images(soup)
keep_only_tags = [
dict(name='div', attrs={'class':'flol w510'}),
dict(name='div', attrs={'class':'main_tresc_news'})
]