mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-09 03:04:10 -04:00
Update FilmWed and Fdb.pl
Merge branch 'master' of https://github.com/t3d/calibre
This commit is contained in:
Kovid Goyal
commit
8f8a5f7561
@ -1,45 +0,0 @@
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
|
||||
|
||||
class Adventure_zone(BasicNewsRecipe):
|
||||
title = u'Adventure Zone'
|
||||
__author__ = 'fenuks'
|
||||
description = u'Czytaj więcej o przygodzie - codzienne nowinki. Szukaj u nas solucji i poradników, czytaj recenzje i zapowiedzi. Także galeria, pliki oraz forum dla wszystkich fanów gier przygodowych.' # noqa
|
||||
category = 'games'
|
||||
language = 'pl'
|
||||
BASEURL = 'http://www.adventure-zone.info/fusion/'
|
||||
no_stylesheets = True
|
||||
extra_css = '.image {float: left; margin-right: 5px;}'
|
||||
oldest_article = 20
|
||||
max_articles_per_feed = 100
|
||||
cover_url = 'http://www.adventure-zone.info/inne/logoaz_2012.png'
|
||||
remove_attributes = ['style']
|
||||
use_embedded_content = False
|
||||
keep_only_tags = [dict(attrs={'class': 'content'})]
|
||||
remove_tags = [dict(attrs={'class': 'footer'})]
|
||||
feeds = [(u'Nowinki', u'http://www.adventure-zone.info/fusion/rss/index.php')]
|
||||
|
||||
_trigger_words = ('zapowied', 'recenzj', 'solucj', 'poradnik')
|
||||
|
||||
@staticmethod
|
||||
def _is_linked_text(title):
|
||||
return 'zapowied' in title or 'recenz' in title or 'solucj' in title or 'poradnik' in title
|
||||
|
||||
def skip_ad_pages(self, soup):
|
||||
skip_tag = soup.body.find(attrs={'class':'subject'})
|
||||
skip_tag = skip_tag.findAll(name='a', href=True)
|
||||
title = soup.title.renderContents().decode('utf-8').lower()
|
||||
if self._is_linked_text(title):
|
||||
for r in skip_tag:
|
||||
word = r.renderContents().decode('utf-8')
|
||||
if not word:
|
||||
continue
|
||||
word = word.lower()
|
||||
if self._is_linked_text(word):
|
||||
return self.index_to_soup(self.BASEURL+r['href'], raw=True)
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
for link in soup.findAll('a', href=True):
|
||||
if not link['href'].startswith('http'):
|
||||
link['href'] = self.BASEURL + link['href']
|
||||
return soup
|
||||
@ -9,7 +9,7 @@ class FDBPl(BasicNewsRecipe):
|
||||
category = 'film'
|
||||
language = 'pl'
|
||||
extra_css = '.options-left > li {display: inline;} em {display: block;}'
|
||||
cover_url = 'http://fdb.pl/assets/fdb2/logo.png'
|
||||
cover_url = 'https://i1.fdbimg.pl/hygg2xp1/480x300_magq39.jpg'
|
||||
use_embedded_content = False
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 100
|
||||
@ -19,25 +19,25 @@ class FDBPl(BasicNewsRecipe):
|
||||
remove_attributes = ['style', 'font']
|
||||
ignore_duplicate_articles = {'title', 'url'}
|
||||
|
||||
keep_only_tags = [dict(attrs={'class': 'news-item news-first'})]
|
||||
keep_only_tags = [dict(attrs={'class': ['row justify-content-center', 'figure']})]
|
||||
remove_tags = [
|
||||
dict(attrs={'class': ['dig dig-first', 'ads clearfix', 'comments']})]
|
||||
dict(attrs={'class': ['news-footer infinite-scroll-breakepoit', 'list-inline text-muted m-0']})]
|
||||
feeds = []
|
||||
|
||||
def parse_index(self):
|
||||
feeds = []
|
||||
feeds.append((u'Wiadomości', self.get_articles(
|
||||
'http://fdb.pl/wiadomosci?page={0}', 2)))
|
||||
'https://fdb.pl/wiadomosci?page={0}', 2)))
|
||||
return feeds
|
||||
|
||||
def get_articles(self, url, pages=1):
|
||||
articles = []
|
||||
for nr in range(1, pages + 1):
|
||||
soup = self.index_to_soup(url.format(nr))
|
||||
for tag in soup.findAll(attrs={'class': 'news-item clearfix'}):
|
||||
node = tag.find('h2')
|
||||
for tag in soup.findAll(attrs={'class': 'col-xs-6 col-sm-4 col-md-4 col-lg-3'}):
|
||||
node = tag.find('h5')
|
||||
title = node.a.string
|
||||
url = 'http://fdb.pl' + node.a['href']
|
||||
url = node.a['href']
|
||||
date = ''
|
||||
articles.append({'title': title,
|
||||
'url': url,
|
||||
|
||||
@ -6,10 +6,10 @@ class FilmWebPl(BasicNewsRecipe):
|
||||
title = 'FilmWeb'
|
||||
__author__ = 'fenuks'
|
||||
description = u'Filmweb.pl - Filmy takie jak Ty Filmweb to największy i najczęściej odwiedzany polski serwis filmowy.'
|
||||
cover_url = 'http://1.fwcdn.pl/an/867323/63321_1.11.jpg'
|
||||
cover_url = 'https://1.fwcdn.pl/an/np/49468/2018/15037.2.jpg'
|
||||
category = 'movies'
|
||||
language = 'pl'
|
||||
index = 'http://www.filmweb.pl'
|
||||
index = 'https://www.filmweb.pl'
|
||||
oldest_article = 8
|
||||
max_articles_per_feed = 100
|
||||
no_stylesheets = True
|
||||
@ -28,25 +28,23 @@ class FilmWebPl(BasicNewsRecipe):
|
||||
remove_tags = [dict(attrs={'class':['infoParent', 'likeBar',
|
||||
'droptions-box pull-right', 'photoDesc', 'imageLicense', 'play big', 'shadow embed__icon--svg']})]
|
||||
remove_attributes = ['style',]
|
||||
keep_only_tags = [dict(attrs={'class': ['newsHdr hdrWithAuthor ', 'reviewHdr', 'newsContent newsPage', 'newsContent']})]
|
||||
# remove_tags_before = dict(attrs={'class': 'hdr hdr-mega'})
|
||||
# remove_tags_after = dict(attrs={'class': 'newsContent'})
|
||||
feeds = [(u'Filmy', u'http://www.filmweb.pl/feed/news/category/film'),
|
||||
(u'Seriale', u'http://www.filmweb.pl/feed/news/category/serial'),
|
||||
(u'Box office', u'http://www.filmweb.pl/feed/news/category/boxoffice'),
|
||||
(u'Telewizja', u'http://www.filmweb.pl/feed/news/category/tv'),
|
||||
(u'Festiwale, nagrody i przeglądy', u'http://www.filmweb.pl/feed/news/category/festival'),
|
||||
(u'Multimedia', u'http://www.filmweb.pl/feed/news/category/multimedia'),
|
||||
(u'Dystrybucja dvd/blu-ray', u'http://www.filmweb.pl/feed/news/category/dvd'),
|
||||
(u'Gry wideo', u'http://www.filmweb.pl/feed/news/category/game'),
|
||||
(u'Różne', u'http://www.filmweb.pl/feed/news/category/other'),
|
||||
(u'Recenzje redakcji', u'http://www.filmweb.pl/feed/reviews/latest'),
|
||||
(u'Recenzje użytkowników', u'http://www.filmweb.pl/feed/user-reviews/latest')
|
||||
keep_only_tags = [dict(attrs={'class': ['newsHdr hdrWithAuthor ', 'reviewHdr', 'newsContent newsPage', 'newsContent', 'hdr hdr-mega']})]
|
||||
feeds = [(u'Filmy', u'https://www.filmweb.pl/feed/news/category/film'),
|
||||
(u'Seriale', u'https://www.filmweb.pl/feed/news/category/serial'),
|
||||
(u'Box office', u'https://www.filmweb.pl/feed/news/category/boxoffice'),
|
||||
(u'Telewizja', u'https://www.filmweb.pl/feed/news/category/tv'),
|
||||
(u'Festiwale, nagrody i przeglądy', u'https://www.filmweb.pl/feed/news/category/festival'),
|
||||
(u'Multimedia', u'https://www.filmweb.pl/feed/news/category/multimedia'),
|
||||
(u'Dystrybucja dvd/blu-ray', u'https://www.filmweb.pl/feed/news/category/dvd'),
|
||||
(u'Gry wideo', u'https://www.filmweb.pl/feed/news/category/game'),
|
||||
(u'Różne', u'https://www.filmweb.pl/feed/news/category/other'),
|
||||
(u'Recenzje redakcji', u'https://www.filmweb.pl/feed/reviews/latest'),
|
||||
(u'Recenzje użytkowników', u'https://www.filmweb.pl/feed/user-reviews/latest')
|
||||
]
|
||||
|
||||
def preprocess_html(self, soup):
|
||||
for a in soup('a', href=True):
|
||||
if 'http://' not in a['href'] and 'https://' not in a['href']:
|
||||
if 'https://' not in a['href']:
|
||||
a['href'] = self.index + a['href']
|
||||
|
||||
return soup
|
||||
|
||||
@ -1,43 +0,0 @@
|
||||
#!/usr/bin/env python2
|
||||
|
||||
__license__ = 'GPL v3'
|
||||
__copyright__ = u'2010-2011, Tomasz Dlugosz <tomek3d@gmail.com>'
|
||||
'''
|
||||
frazpc.pl
|
||||
'''
|
||||
|
||||
from calibre.web.feeds.news import BasicNewsRecipe
|
||||
import re
|
||||
|
||||
|
||||
class FrazPC(BasicNewsRecipe):
|
||||
title = u'frazpc.pl'
|
||||
publisher = u'frazpc.pl'
|
||||
description = u'Tw\xf3j Vortal Technologiczny'
|
||||
language = 'pl'
|
||||
__author__ = u'Tomasz D\u0142ugosz'
|
||||
oldest_article = 7
|
||||
max_articles_per_feed = 100
|
||||
use_embedded_content = False
|
||||
no_stylesheets = True
|
||||
remove_empty_feeds = True
|
||||
cover_url = 'http://www.frazpc.pl/images/logo.png'
|
||||
feeds = [
|
||||
(u'Aktualno\u015bci', u'http://www.frazpc.pl/feed/aktualnosci'),
|
||||
(u'Artyku\u0142y', u'http://www.frazpc.pl/feed/artykuly')
|
||||
]
|
||||
|
||||
keep_only_tags = [dict(name='div', attrs={'class': 'article'})]
|
||||
|
||||
remove_tags = [
|
||||
dict(name='div', attrs={'class': 'title-wrapper'}),
|
||||
dict(name='p', attrs={'class': 'tags'}),
|
||||
dict(name='p', attrs={'class': 'article-links'}),
|
||||
dict(name='div', attrs={'class': 'comments_box'})
|
||||
]
|
||||
|
||||
remove_tags_after = dict(name='div', attrs={'class': 'content'})
|
||||
preprocess_regexps = [(re.compile(
|
||||
r'\| <a href="#comments">Komentarze \([0-9]*\)</a>'), lambda match: '')]
|
||||
|
||||
remove_attributes = ['width', 'height']
|
||||
Binary file not shown.
|
Before Width: | Height: | Size: 791 B |
Binary file not shown.
|
Before Width: | Height: | Size: 1.6 KiB After Width: | Height: | Size: 454 B |
Binary file not shown.
|
Before Width: | Height: | Size: 271 B |
Loading…
x
Reference in New Issue
Block a user