calibre/recipes/adventure_zone_pl.recipe
Kovid Goyal e8e4246860 ...
2011-12-17 21:32:28 +05:30

50 lines
2.2 KiB
Plaintext

from calibre.web.feeds.news import BasicNewsRecipe
import re
class Adventure_zone(BasicNewsRecipe):
title = u'Adventure Zone'
__author__ = 'fenuks'
description = 'Adventure zone - adventure games from A to Z'
category = 'games'
language = 'pl'
no_stylesheets = True
oldest_article = 20
max_articles_per_feed = 100
use_embedded_content=False
preprocess_regexps = [(re.compile(r"<td class='capmain'>Komentarze</td>", re.IGNORECASE), lambda m: '')]
remove_tags_before= dict(name='td', attrs={'class':'main-bg'})
remove_tags= [dict(name='img', attrs={'alt':'Drukuj'})]
remove_tags_after= dict(id='comments')
extra_css = '.main-bg{text-align: left;} td.capmain{ font-size: 22px; }'
feeds = [(u'Nowinki', u'http://www.adventure-zone.info/fusion/feeds/news.php')]
def parse_feeds (self):
feeds = BasicNewsRecipe.parse_feeds(self)
soup=self.index_to_soup(u'http://www.adventure-zone.info/fusion/feeds/news.php')
tag=soup.find(name='channel')
titles=[]
for r in tag.findAll(name='image'):
r.extract()
art=tag.findAll(name='item')
for i in art:
titles.append(i.title.string)
for feed in feeds:
for article in feed.articles[:]:
article.title=titles[feed.articles.index(article)]
return feeds
def get_cover_url(self):
soup = self.index_to_soup('http://www.adventure-zone.info/fusion/news.php')
cover=soup.find(id='box_OstatninumerAZ')
self.cover_url='http://www.adventure-zone.info/fusion/'+ cover.center.a.img['src']
return getattr(self, 'cover_url', self.cover_url)
def skip_ad_pages(self, soup):
skip_tag = soup.body.find(name='td', attrs={'class':'main-bg'})
skip_tag = skip_tag.findAll(name='a')
for r in skip_tag:
if r.strong:
word=r.strong.string
if word and (('zapowied' in word) or ('recenzj' in word) or ('solucj' in word)):
return self.index_to_soup('http://www.adventure-zone.info/fusion/print.php?type=A&item'+r['href'][r['href'].find('article_id')+7:], raw=True)