github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

[gamestar] Fix issues (closes #15179)

Browse source
This commit is contained in:
Sergey M․ 2018-01-13 19:36:26 +07:00
parent d4aedca3bd
commit df16e645f6
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 32 additions and 29 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

61
youtube_dl/extractor/gamestar.py
View file

@ -1,6 +1,8 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
int_or_none, int_or_none,
@ -9,33 +11,34 @@
class GameStarIE(InfoExtractor): class GameStarIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?game(?:pro|star)\.de/videos/.*,(?P<id>[0-9]+)\.html' _VALID_URL = r'https?://(?:www\.)?game(?P<site>pro|star)\.de/videos/.*,(?P<id>[0-9]+)\.html'
_TESTS = [ _TESTS = [{
{ 'url': 'http://www.gamestar.de/videos/trailer,3/hobbit-3-die-schlacht-der-fuenf-heere,76110.html',
'url': 'http://www.gamestar.de/videos/trailer,3/hobbit-3-die-schlacht-der-fuenf-heere,76110.html', 'md5': 'ee782f1f8050448c95c5cacd63bc851c',
'md5': 'ee782f1f8050448c95c5cacd63bc851c', 'info_dict': {
'info_dict': { 'id': '76110',
'id': '76110', 'ext': 'mp4',
'ext': 'mp4', 'title': 'Hobbit 3: Die Schlacht der Fünf Heere - Teaser-Trailer zum dritten Teil',
'title': 'Hobbit 3: Die Schlacht der Fünf Heere - Teaser-Trailer zum dritten Teil', 'description': 'Der Teaser-Trailer zu Hobbit 3: Die Schlacht der Fünf Heere zeigt einige Szenen aus dem dritten Teil der Saga und kündigt den...',
'description': 'Der Teaser-Trailer zu Hobbit 3: Die Schlacht der Fünf Heere zeigt einige Szenen aus dem dritten Teil der Saga und kündigt den...', 'thumbnail': r're:^https?://.*\.jpg$',
'thumbnail': r're:^https?://.*\.jpg$', 'timestamp': 1406542380,
'timestamp': 1406542380, 'upload_date': '20140728',
'upload_date': '20140728', 'duration': 17,
'duration': 17, }
} }, {
}, 'url': 'http://www.gamepro.de/videos/top-10-indie-spiele-fuer-nintendo-switch-video-tolle-nindies-games-zum-download,95316.html',
{ 'only_matching': True,
'url': 'http://www.gamepro.de/videos/top-10-indie-spiele-fuer-nintendo-switch-video-tolle-nindies-games-zum-download,95316.html', }, {
'only_matching': True, 'url': 'http://www.gamestar.de/videos/top-10-indie-spiele-fuer-nintendo-switch-video-tolle-nindies-games-zum-download,95316.html',
}, 'only_matching': True,
] }]
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) mobj = re.match(self._VALID_URL, url)
webpage = self._download_webpage(url, video_id) site = mobj.group('site')
video_id = mobj.group('id')
url = 'http://gamestar.de/_misc/videos/portal/getVideoUrl.cfm?premium=0&videoId=' + video_id webpage = self._download_webpage(url, video_id)
# TODO: there are multiple ld+json objects in the webpage, # TODO: there are multiple ld+json objects in the webpage,
# while _search_json_ld finds only the first one # while _search_json_ld finds only the first one
@ -43,17 +46,17 @@ def _real_extract(self, url):
r'(?s)<script[^>]+type=(["\'])application/ld\+json\1[^>]*>(?P<json_ld>[^<]+VideoObject[^<]+)</script>', r'(?s)<script[^>]+type=(["\'])application/ld\+json\1[^>]*>(?P<json_ld>[^<]+VideoObject[^<]+)</script>',
webpage, 'JSON-LD', group='json_ld'), video_id) webpage, 'JSON-LD', group='json_ld'), video_id)
info_dict = self._json_ld(json_ld, video_id) info_dict = self._json_ld(json_ld, video_id)
info_dict['title'] = remove_end(info_dict['title'], ' - GameStar') info_dict['title'] = remove_end(
info_dict['title'] = remove_end(info_dict['title'], ' - GamePro') info_dict['title'], ' - Game%s' % site.title())
view_count = int_or_none(json_ld.get('interactionCount')) view_count = int_or_none(json_ld.get('interactionCount'))
comment_count = int_or_none(self._html_search_regex( comment_count = int_or_none(self._html_search_regex(
r'<span>Kommentare</span><span class="count">\(([0-9]+)\)</span>', r'<span>Kommentare</span>\s*<span[^>]+class=["\']count[^>]+>\s*\(\s*([0-9]+)',
webpage, 'comment_count', fatal=False)) webpage, 'comment count', fatal=False))
info_dict.update({ info_dict.update({
'id': video_id, 'id': video_id,
'url': url, 'url': 'http://gamestar.de/_misc/videos/portal/getVideoUrl.cfm?premium=0&videoId=' + video_id,
'ext': 'mp4', 'ext': 'mp4',
'view_count': view_count, 'view_count': view_count,
'comment_count': comment_count 'comment_count': comment_count