calibre/recipes/gram_pl.recipe
2019-03-22 23:47:49 +05:30

53 lines
2.3 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
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.findAll('a', href=True):
if 'http://' not in a['href'] and 'https://' not in a['href']: # noqa
a['href'] = self.index + a['href']
tag = soup.find(name='span', attrs={'class': 'platforma'})
if tag:
tag.name = 'p'
return soup