calibre/recipes/conowego_pl.recipe
2012-07-27 01:11:45 +05:30

39 lines
1.9 KiB
Plaintext
Executable File

from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup
class CoNowegoPl(BasicNewsRecipe):
title = u'conowego.pl'
__author__ = 'fenuks'
description = u'Nowy wortal technologiczny oraz gazeta internetowa. Testy najnowszych produktów, fachowe porady i recenzje. U nas znajdziesz wszystko o elektronice użytkowej !'
cover_url = 'http://www.conowego.pl/fileadmin/templates/main/images/logo_top.png'
category = 'IT, news'
language = 'pl'
oldest_article = 7
max_articles_per_feed = 100
no_stylesheets = True
remove_empty_feeds = True
use_embedded_content = False
keep_only_tags = [dict(name='div', attrs={'class':'news_list single_view'})]
remove_tags = [dict(name='div', attrs={'class':['ni_bottom', 'ni_rank', 'ni_date']})]
feeds = [(u'Aktualno\u015bci', u'http://www.conowego.pl/rss/aktualnosci-5/?type=100'), (u'Gaming', u'http://www.conowego.pl/rss/gaming-6/?type=100'), (u'Porady', u'http://www.conowego.pl/rss/porady-3/?type=100'), (u'Testy', u'http://www.conowego.pl/rss/testy-2/?type=100')]
def preprocess_html(self, soup):
for i in soup.findAll('img'):
i.parent.insert(0, BeautifulSoup('<br />'))
i.insert(len(i), BeautifulSoup('<br />'))
self.append_page(soup, soup.body)
return soup
def append_page(self, soup, appendtag):
tag = appendtag.find('div', attrs={'class':'pages'})
if tag:
nexturls=tag.findAll('a')
for nexturl in nexturls[:-1]:
soup2 = self.index_to_soup('http://www.conowego.pl/' + nexturl['href'])
pagetext = soup2.find(attrs={'class':'ni_content'})
pos = len(appendtag.contents)
appendtag.insert(pos, pagetext)
for r in appendtag.findAll(attrs={'class':['pages', 'paginationWrap']}):
r.extract()