from calibre.web.feeds.news import BasicNewsRecipe class Filmweb_pl(BasicNewsRecipe): title = u'FilmWeb' __author__ = 'fenuks' description = 'FilmWeb - biggest polish movie site' cover_url = 'http://userlogos.org/files/logos/crudus/filmweb.png' category = 'movies' language = 'pl' oldest_article = 8 max_articles_per_feed = 100 no_stylesheets= True extra_css = '.hdrBig {font-size:22px;}' remove_tags= [dict(name='div', attrs={'class':['recommendOthers']}), dict(name='ul', attrs={'class':'fontSizeSet'})] keep_only_tags= [dict(name='h1', attrs={'class':'hdrBig'}), dict(name='div', attrs={'class':['newsInfo', 'reviewContent fontSizeCont description']})] feeds = [(u'Wszystkie newsy', u'http://www.filmweb.pl/feed/news/latest'), (u'News / Filmy w produkcji', 'http://www.filmweb.pl/feed/news/category/filminproduction'), (u'News / Festiwale, nagrody i przeglądy', u'http://www.filmweb.pl/feed/news/category/festival'), (u'News / Seriale', u'http://www.filmweb.pl/feed/news/category/serials'), (u'News / Box office', u'http://www.filmweb.pl/feed/news/category/boxoffice'), (u'News / Multimedia', u'http://www.filmweb.pl/feed/news/category/multimedia'), (u'News / Dystrybucja dvd / blu-ray', u'http://www.filmweb.pl/feed/news/category/video'), (u'News / Dystrybucja kinowa', u'http://www.filmweb.pl/feed/news/category/cinema'), (u'News / off', u'http://www.filmweb.pl/feed/news/category/off'), (u'News / Gry wideo', u'http://www.filmweb.pl/feed/news/category/game'), (u'News / Organizacje branżowe', u'http://www.filmweb.pl/feed/news/category/organizations'), (u'News / Internet', u'http://www.filmweb.pl/feed/news/category/internet'), (u'News / Różne', u'http://www.filmweb.pl/feed/news/category/other'), (u'News / Kino polskie', u'http://www.filmweb.pl/feed/news/category/polish.cinema'), (u'News / Telewizja', u'http://www.filmweb.pl/feed/news/category/tv'), (u'Recenzje redakcji', u'http://www.filmweb.pl/feed/reviews/latest'), (u'Recenzje użytkowników', u'http://www.filmweb.pl/feed/user-reviews/latest')] def skip_ad_pages(self, soup): skip_tag = soup.find('a', attrs={'class':'welcomeScreenButton'}) if skip_tag is not None: self.log.warn('skip_tag') self.log.warn(skip_tag) return self.index_to_soup(skip_tag['href'], raw=True)