calibre/recipes/film_web.recipe
Kovid Goyal 567040ee1e Perform PEP8 compliance checks on the entire codebase
Some bits of PEP 8 are turned off via setup.cfg
2016-07-29 21:25:17 +05:30

74 lines
3.8 KiB
Plaintext

import re
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup
class FilmWebPl(BasicNewsRecipe):
title = u'FilmWeb'
__author__ = 'fenuks'
description = 'Filmweb.pl - Filmy takie jak Ty Filmweb to największy i najczęściej odwiedzany polski serwis filmowy. Największa baza filmów, seriali i aktorów, repertuar kin i tv, ...' # noqa
cover_url = 'http://gfx.filmweb.pl/n/logo-filmweb-bevel.jpg'
category = 'movies'
language = 'pl'
index = 'http://www.filmweb.pl'
oldest_article = 8
max_articles_per_feed = 100
no_stylesheets = True
remove_empty_feeds = True
ignore_duplicate_articles = {'title', 'url'}
remove_javascript = True
preprocess_regexps = [(re.compile(u'\(kliknij\,\ aby powiększyć\)', re.IGNORECASE), lambda m: ''), (re.compile(
ur'(<br ?/?>\s*?<br ?/?>\s*?)+', re.IGNORECASE), lambda m: '<br />')] # (re.compile(ur' | ', re.IGNORECASE), lambda m: '')]
extra_css = '.hdrBig {font-size:22px;} ul {list-style-type:none; padding: 0; margin: 0;}'
remove_attributes = ['style', ]
keep_only_tags = [dict(attrs={'class': ['hdr hdr-super', 'newsContent']})]
feeds = [(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:
return self.index_to_soup(skip_tag['href'], raw=True)
def postprocess_html(self, soup, first_fetch):
for r in soup.findAll(attrs={'class': 'singlephoto'}):
r['style'] = 'float:left; margin-right: 10px;'
return soup
def preprocess_html(self, soup):
for a in soup('a'):
if a.has_key('href') and 'http://' not in a['href'] and 'https://' not in a['href']: # noqa
a['href'] = self.index + a['href'] # noqa
for i in soup.findAll('a', attrs={'class': 'fn'}):
i.insert(len(i), BeautifulSoup('<br />'))
for i in soup.findAll('sup'):
if not i.string or i.string.startswith('(kliknij'):
i.extract()
for r in soup.findAll(id=re.compile('photo-\d+')):
r.extract()
for r in soup.findAll(style=re.compile('float: ?left')):
r['class'] = 'singlephoto'
return soup