aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorSergey M․ <dstftw@gmail.com>2018-01-13 19:36:26 +0700
committerSergey M․ <dstftw@gmail.com>2018-01-13 19:38:58 +0700
commitdf16e645f60def2b5e1cf88d74164d6ced0d5651 (patch)
treea999f24a69347ddcc536e12ae167be8c884e1483
parentd4aedca3bd82288c802d4d766d5542bfcec4a91a (diff)
downloadyoutube-dl-df16e645f60def2b5e1cf88d74164d6ced0d5651.zip
youtube-dl-df16e645f60def2b5e1cf88d74164d6ced0d5651.tar.gz
youtube-dl-df16e645f60def2b5e1cf88d74164d6ced0d5651.tar.bz2
[gamestar] Fix issues (closes #15179)
-rw-r--r--youtube_dl/extractor/gamestar.py61
1 files changed, 32 insertions, 29 deletions
diff --git a/youtube_dl/extractor/gamestar.py b/youtube_dl/extractor/gamestar.py
index 7ce2f15..f00dab2 100644
--- a/youtube_dl/extractor/gamestar.py
+++ b/youtube_dl/extractor/gamestar.py
@@ -1,6 +1,8 @@
# coding: utf-8
from __future__ import unicode_literals
+import re
+
from .common import InfoExtractor
from ..utils import (
int_or_none,
@@ -9,33 +11,34 @@ from ..utils import (
class GameStarIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?game(?:pro|star)\.de/videos/.*,(?P<id>[0-9]+)\.html'
- _TESTS = [
- {
- 'url': 'http://www.gamestar.de/videos/trailer,3/hobbit-3-die-schlacht-der-fuenf-heere,76110.html',
- 'md5': 'ee782f1f8050448c95c5cacd63bc851c',
- 'info_dict': {
- 'id': '76110',
- 'ext': 'mp4',
- '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...',
- 'thumbnail': r're:^https?://.*\.jpg$',
- 'timestamp': 1406542380,
- 'upload_date': '20140728',
- 'duration': 17,
- }
- },
- {
- 'url': 'http://www.gamepro.de/videos/top-10-indie-spiele-fuer-nintendo-switch-video-tolle-nindies-games-zum-download,95316.html',
- 'only_matching': True,
- },
- ]
+ _VALID_URL = r'https?://(?:www\.)?game(?P<site>pro|star)\.de/videos/.*,(?P<id>[0-9]+)\.html'
+ _TESTS = [{
+ 'url': 'http://www.gamestar.de/videos/trailer,3/hobbit-3-die-schlacht-der-fuenf-heere,76110.html',
+ 'md5': 'ee782f1f8050448c95c5cacd63bc851c',
+ 'info_dict': {
+ 'id': '76110',
+ 'ext': 'mp4',
+ 'title': 'Hobbit 3: Die Schlacht der Fünf Heere - Teaser-Trailer zum dritten Teil',
+ 'description': 'Der Teaser-Trailer zu Hobbit 3: Die Schlacht der Fünf Heere zeigt einige Szenen aus dem dritten Teil der Saga und kündigt den...',
+ 'thumbnail': r're:^https?://.*\.jpg$',
+ 'timestamp': 1406542380,
+ 'upload_date': '20140728',
+ '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.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):
- video_id = self._match_id(url)
- webpage = self._download_webpage(url, video_id)
+ mobj = re.match(self._VALID_URL, url)
+ 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,
# while _search_json_ld finds only the first one
@@ -43,17 +46,17 @@ class GameStarIE(InfoExtractor):
r'(?s)<script[^>]+type=(["\'])application/ld\+json\1[^>]*>(?P<json_ld>[^<]+VideoObject[^<]+)</script>',
webpage, 'JSON-LD', group='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'], ' - GamePro')
+ info_dict['title'] = remove_end(
+ info_dict['title'], ' - Game%s' % site.title())
view_count = int_or_none(json_ld.get('interactionCount'))
comment_count = int_or_none(self._html_search_regex(
- r'<span>Kommentare</span><span class="count">\(([0-9]+)\)</span>',
- webpage, 'comment_count', fatal=False))
+ r'<span>Kommentare</span>\s*<span[^>]+class=["\']count[^>]+>\s*\(\s*([0-9]+)',
+ webpage, 'comment count', fatal=False))
info_dict.update({
'id': video_id,
- 'url': url,
+ 'url': 'http://gamestar.de/_misc/videos/portal/getVideoUrl.cfm?premium=0&videoId=' + video_id,
'ext': 'mp4',
'view_count': view_count,
'comment_count': comment_count