mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
31 lines
1.4 KiB
Plaintext
31 lines
1.4 KiB
Plaintext
from calibre.web.feeds.news import BasicNewsRecipe
|
|
class PC_Arena(BasicNewsRecipe):
|
|
title = u'PCArena'
|
|
oldest_article = 18300
|
|
max_articles_per_feed = 100
|
|
__author__ = 'fenuks'
|
|
description = u'Najnowsze informacje z branży IT - testy, recenzje, aktualności, rankingi, wywiady. Twoje źródło informacji o sprzęcie komputerowym.'
|
|
category = 'IT'
|
|
language = 'pl'
|
|
masthead_url='http://pcarena.pl/public/design/frontend/images/logo.gif'
|
|
cover_url= 'http://pcarena.pl/public/design/frontend/images/logo.gif'
|
|
no_stylesheets = True
|
|
keep_only_tags=[dict(attrs={'class':['artHeader', 'art']})]
|
|
remove_tags=[dict(attrs={'class':'pages'})]
|
|
feeds = [(u'Newsy', u'http://pcarena.pl/misc/rss/news'), (u'Artyku\u0142y', u'http://pcarena.pl/misc/rss/articles')]
|
|
|
|
def append_page(self, soup, appendtag):
|
|
tag=soup.find(name='div', attrs={'class':'pagNum'})
|
|
if tag:
|
|
nexturl=tag.findAll('a')
|
|
tag.extract()
|
|
for nextpage in nexturl[1:]:
|
|
nextpage= 'http://pcarena.pl' + nextpage['href']
|
|
soup2 = self.index_to_soup(nextpage)
|
|
pagetext = soup2.find(attrs={'class':'artBody'})
|
|
pos = len(appendtag.contents)
|
|
appendtag.insert(pos, pagetext)
|
|
|
|
def preprocess_html(self, soup):
|
|
self.append_page(soup, soup.body)
|
|
return soup |