mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
47 lines
1.5 KiB
Python
47 lines
1.5 KiB
Python
#!/usr/bin/env python2
|
|
|
|
__license__ = 'GPL v3'
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
|
|
class telepolis(BasicNewsRecipe):
|
|
title = u'Telepolis.pl'
|
|
__author__ = 'Artur Stachecki <artur.stachecki@gmail.com>, Tomasz Długosz <tomek3d@gmail.com>'
|
|
|
|
language = 'pl'
|
|
description = u'Twój telekomunikacyjny serwis informacyjny.'
|
|
masthead_url = 'http://telepolis.pl/i/telepolis-logo2.gif'
|
|
no_stylesheets = True
|
|
use_embedded_content = False
|
|
|
|
feeds = [
|
|
(u'Wiadomości', u'http://www.telepolis.pl/rss,2,5,0.html')
|
|
]
|
|
|
|
keep_only_tags = [
|
|
dict(name='div', attrs={'class': 'flol w510'}),
|
|
dict(name='div', attrs={'class': 'main_tresc'}),
|
|
dict(name='div', attrs={'class': 'main_tresc_news'})
|
|
]
|
|
|
|
def append_page(self, soup, appendtag):
|
|
chpage = appendtag.find(attrs={'class': 'str'})
|
|
if chpage:
|
|
for page in chpage.findAll('a'):
|
|
if page.renderContents() == 'Następna ›':
|
|
break
|
|
soup2 = self.index_to_soup(page['href'])
|
|
pagetext = soup2.find(attrs={'class': 'main_tresc'})
|
|
pos = len(appendtag.contents)
|
|
appendtag.insert(pos, pagetext)
|
|
for r in appendtag.findAll(attrs={'class': 'str'}):
|
|
r.extract()
|
|
|
|
def preprocess_html(self, soup):
|
|
self.append_page(soup, soup.body)
|
|
for image in soup.findAll('img'):
|
|
if 'm.jpg' in image['src']:
|
|
image['src'] = image['src'].replace('m.jpg', '.jpg')
|
|
return soup
|