mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-09-29 15:31:08 -04:00
49 lines
2.2 KiB
Plaintext
49 lines
2.2 KiB
Plaintext
from calibre.web.feeds.news import BasicNewsRecipe
|
|
from calibre.ebooks.BeautifulSoup import BeautifulSoup
|
|
|
|
class Gram_pl(BasicNewsRecipe):
|
|
title = u'Gram.pl'
|
|
__author__ = 'fenuks'
|
|
description = u'Serwis społecznościowy o grach: recenzje, newsy, zapowiedzi, encyklopedia gier, forum. Gry PC, PS3, X360, PS Vita, sprzęt dla graczy.'
|
|
category = 'games'
|
|
language = 'pl'
|
|
oldest_article = 8
|
|
index='http://www.gram.pl'
|
|
max_articles_per_feed = 100
|
|
ignore_duplicate_articles = {'title', 'url'}
|
|
no_stylesheets= True
|
|
remove_empty_feeds = True
|
|
#extra_css = 'h2 {font-style: italic; font-size:20px;} .picbox div {float: left;}'
|
|
cover_url=u'http://www.gram.pl/www/01/img/grampl_zima.png'
|
|
keep_only_tags= [dict(id='articleModule')]
|
|
remove_tags = [dict(attrs={'class':['breadCrump', 'dymek', 'articleFooter', 'twitter-share-button']}), dict(name='aside'), dict(id='metaColumn')]
|
|
feeds = [(u'Informacje', u'http://www.gram.pl/feed_news.asp'),
|
|
(u'Publikacje', u'http://www.gram.pl/feed_news.asp?type=articles')
|
|
]
|
|
|
|
def parse_feeds (self):
|
|
feeds = BasicNewsRecipe.parse_feeds(self)
|
|
for feed in feeds:
|
|
for article in feed.articles[:]:
|
|
if 'REKLAMA SKLEP' in article.title.upper() or u'ARTYKUŁ:' in article.title.upper():
|
|
feed.articles.remove(article)
|
|
return feeds
|
|
|
|
|
|
def preprocess_html(self, soup):
|
|
tag=soup.find(name='div', attrs={'class':'summary'})
|
|
if tag:
|
|
tag.find(attrs={'class':'pros'}).insert(0, BeautifulSoup('<h2>Plusy:</h2>').h2)
|
|
tag.find(attrs={'class':'cons'}).insert(0, BeautifulSoup('<h2>Minusy:</h2>').h2)
|
|
tag = soup.find(name='section', attrs={'class':'cenzurka'})
|
|
if tag:
|
|
rate = tag.p.img['data-ocena']
|
|
tag.p.img.extract()
|
|
tag.p.insert(len(tag.p.contents)-2, BeautifulSoup('<h2>Ocena: {0}</h2>'.format(rate)).h2)
|
|
for a in soup('a'):
|
|
if a.has_key('href') and 'http://' not in a['href'] and 'https://' not in a['href']:
|
|
a['href']=self.index + a['href']
|
|
tag=soup.find(name='span', attrs={'class':'platforma'})
|
|
if tag:
|
|
tag.name = 'p'
|
|
return soup |