calibre/recipes/cgm_pl.recipe
2011-09-21 10:50:11 -06:00

40 lines
2.1 KiB
Plaintext

from calibre.web.feeds.news import BasicNewsRecipe
class CGM(BasicNewsRecipe):
title = u'CGM'
oldest_article = 7
__author__ = 'fenuks'
description = u'Codzienna Gazeta Muzyczna'
cover_url = 'http://www.krafcy.com/foto/tinymce/Image/cgm%281%29.jpg'
category = 'music'
language = 'pl'
use_embedded_content = False
max_articles_per_feed = 100
no_stylesheers=True
extra_css = 'div {color:black;} strong {color:black;} span {color:black;} p {color:black;}'
remove_tags_before=dict(id='mainContent')
remove_tags_after=dict(name='div', attrs={'class':'fbContainer'})
remove_tags=[dict(name='div', attrs={'class':'fbContainer'}),
dict(name='p', attrs={'class':['tagCloud', 'galleryAuthor']}),
dict(id=['movieShare', 'container'])]
feeds = [(u'Informacje', u'http://www.cgm.pl/rss.xml'), (u'Polecamy', u'http://www.cgm.pl/rss,4,news.xml'),
(u'Recenzje', u'http://www.cgm.pl/rss,1,news.xml')]
def preprocess_html(self, soup):
ad=soup.findAll('img')
for r in ad:
if '/_vault/_article_photos/5841.jpg' in r['src'] or '_vault/_article_photos/5807.jpg' in r['src'] or 'article_photos/5841.jpg' in r['src'] or 'article_photos/5825.jpg' in r['src'] or '_article_photos/5920.jpg' in r['src'] or '_article_photos/5919.jpg' in r['src'] or '_article_photos/5918.jpg' in r['src'] or '_article_photos/5914.jpg' in r['src'] or '_article_photos/5911.jpg' in r['src'] or '_article_photos/5923.jpg' in r['src'] or '_article_photos/5921.jpg' in r['src']:
ad[ad.index(r)].extract()
gallery=soup.find('div', attrs={'class':'galleryFlash'})
if gallery:
img=gallery.find('embed')
if img:
img=img['src'][35:]
img='http://www.cgm.pl/_vault/_gallery/_photo/'+img
param=gallery.findAll(name='param')
for i in param:
i.extract()
gallery.contents[1].name='img'
gallery.contents[1]['src']=img
return soup