| 1 |
import re |
| 2 |
|
| 3 |
from calibre.web.feeds.news import BasicNewsRecipe |
| 4 |
|
| 5 |
|
| 6 |
class FilmWebPl(BasicNewsRecipe): |
| 7 |
title = 'FilmWeb' |
| 8 |
__author__ = 'fenuks' |
| 9 |
description = 'Filmweb.pl - Filmy takie jak Ty Filmweb to największy i najczęściej odwiedzany polski serwis filmowy.' |
| 10 |
cover_url = 'https://1.fwcdn.pl/an/np/49468/2018/15037.2.jpg' |
| 11 |
category = 'movies' |
| 12 |
language = 'pl' |
| 13 |
index = 'https://www.filmweb.pl' |
| 14 |
oldest_article = 8 |
| 15 |
max_articles_per_feed = 100 |
| 16 |
no_stylesheets = True |
| 17 |
remove_empty_feeds = True |
| 18 |
ignore_duplicate_articles = {'title', 'url'} |
| 19 |
remove_javascript = True |
| 20 |
use_embedded_content = False |
| 21 |
extra_css = ( |
| 22 |
'.hdrBig {font-size:22px;} ul {list-style-type:none;} ' |
| 23 |
'ul.inline > li {display: inline;} ' |
| 24 |
'ul.sep-line > li + li::before {content: " | "} ' |
| 25 |
'ul.inline {padding:0px;} .vertical-align {display: inline-block;}' |
| 26 |
) |
| 27 |
preprocess_regexps = [ |
| 28 |
(re.compile(r'<body.+?</head>', re.DOTALL), lambda match: ''), # fix malformed HTML with 2 body tags... |
| 29 |
(re.compile('(?:<sup>)?\\(kliknij\\,\\ aby powiększyć\\)(?:</sup>)?', re.IGNORECASE), lambda m: ''), # noqa: RUF039 |
| 30 |
(re.compile(type('')(r'(<br ?/?>\s*?<br ?/?>\s*?)+'), re.IGNORECASE), lambda m: '<br />'), |
| 31 |
] |
| 32 |
remove_tags = [ |
| 33 |
dict(attrs={'class': ['infoParent', 'likeBar', 'droptions-box pull-right', 'photoDesc', 'imageLicense', 'play big', 'shadow embed__icon--svg']}) |
| 34 |
] |
| 35 |
remove_attributes = [ |
| 36 |
'style', |
| 37 |
] |
| 38 |
keep_only_tags = [dict(attrs={'class': ['newsHdr hdrWithAuthor ', 'reviewHdr', 'newsContent newsPage', 'newsContent', 'hdr hdr-mega']})] |
| 39 |
feeds = [ |
| 40 |
('Filmy', 'https://www.filmweb.pl/feed/news/category/film'), |
| 41 |
('Seriale', 'https://www.filmweb.pl/feed/news/category/serial'), |
| 42 |
('Box office', 'https://www.filmweb.pl/feed/news/category/boxoffice'), |
| 43 |
('Telewizja', 'https://www.filmweb.pl/feed/news/category/tv'), |
| 44 |
('Festiwale, nagrody i przeglądy', 'https://www.filmweb.pl/feed/news/category/festival'), |
| 45 |
('Multimedia', 'https://www.filmweb.pl/feed/news/category/multimedia'), |
| 46 |
('Dystrybucja dvd/blu-ray', 'https://www.filmweb.pl/feed/news/category/dvd'), |
| 47 |
('Gry wideo', 'https://www.filmweb.pl/feed/news/category/game'), |
| 48 |
('Różne', 'https://www.filmweb.pl/feed/news/category/other'), |
| 49 |
('Recenzje redakcji', 'https://www.filmweb.pl/feed/reviews/latest'), |
| 50 |
('Recenzje użytkowników', 'https://www.filmweb.pl/feed/user-reviews/latest'), |
| 51 |
] |
| 52 |
|
| 53 |
def preprocess_html(self, soup): |
| 54 |
for a in soup('a', href=True): |
| 55 |
if 'https://' not in a['href']: |
| 56 |
a['href'] = self.index + a['href'] |
| 57 |
|
| 58 |
return soup |