[vk] fix extraction for inline only videos(fixes #16923)

This commit is contained in:
Remita Amine 2018-07-26 07:24:46 +01:00
parent b5dec62ca6
commit ad1bc71a8a

View File

@ -17,6 +17,7 @@
int_or_none, int_or_none,
orderedSet, orderedSet,
remove_start, remove_start,
str_or_none,
str_to_int, str_to_int,
unescapeHTML, unescapeHTML,
unified_timestamp, unified_timestamp,
@ -106,10 +107,10 @@ class VKIE(VKBaseIE):
'ext': 'mp4', 'ext': 'mp4',
'title': 'ProtivoGunz - Хуёвая песня', 'title': 'ProtivoGunz - Хуёвая песня',
'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*', 'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*',
'uploader_id': '-77521',
'duration': 195, 'duration': 195,
'timestamp': 1329060660, 'timestamp': 1329049880,
'upload_date': '20120212', 'upload_date': '20120212',
'view_count': int,
}, },
}, },
{ {
@ -118,12 +119,12 @@ class VKIE(VKBaseIE):
'info_dict': { 'info_dict': {
'id': '165548505', 'id': '165548505',
'ext': 'mp4', 'ext': 'mp4',
'uploader': 'Tom Cruise',
'title': 'No name', 'title': 'No name',
'uploader': 'Tom Cruise',
'uploader_id': '205387401',
'duration': 9, 'duration': 9,
'timestamp': 1374374880, 'timestamp': 1374364108,
'upload_date': '20130721', 'upload_date': '20130720',
'view_count': int,
} }
}, },
{ {
@ -207,10 +208,10 @@ class VKIE(VKBaseIE):
'id': 'V3K4mi0SYkc', 'id': 'V3K4mi0SYkc',
'ext': 'webm', 'ext': 'webm',
'title': "DSWD Awards 'Children's Joy Foundation, Inc.' Certificate of Registration and License to Operate", 'title': "DSWD Awards 'Children's Joy Foundation, Inc.' Certificate of Registration and License to Operate",
'description': 'md5:d9903938abdc74c738af77f527ca0596', 'description': 'md5:bf9c26cfa4acdfb146362682edd3827a',
'duration': 178, 'duration': 179,
'upload_date': '20130116', 'upload_date': '20130116',
'uploader': "Children's Joy Foundation", 'uploader': "Children's Joy Foundation Inc.",
'uploader_id': 'thecjf', 'uploader_id': 'thecjf',
'view_count': int, 'view_count': int,
}, },
@ -222,6 +223,7 @@ class VKIE(VKBaseIE):
'id': 'k3lz2cmXyRuJQSjGHUv', 'id': 'k3lz2cmXyRuJQSjGHUv',
'ext': 'mp4', 'ext': 'mp4',
'title': 'md5:d52606645c20b0ddbb21655adaa4f56f', 'title': 'md5:d52606645c20b0ddbb21655adaa4f56f',
# TODO: fix test by fixing dailymotion description extraction
'description': 'md5:c651358f03c56f1150b555c26d90a0fd', 'description': 'md5:c651358f03c56f1150b555c26d90a0fd',
'uploader': 'AniLibria.Tv', 'uploader': 'AniLibria.Tv',
'upload_date': '20160914', 'upload_date': '20160914',
@ -241,9 +243,12 @@ class VKIE(VKBaseIE):
'ext': 'mp4', 'ext': 'mp4',
'title': 'S-Dance, репетиции к The way show', 'title': 'S-Dance, репетиции к The way show',
'uploader': 'THE WAY SHOW | 17 апреля', 'uploader': 'THE WAY SHOW | 17 апреля',
'timestamp': 1454870100, 'uploader_id': '-110305615',
'timestamp': 1454859345,
'upload_date': '20160207', 'upload_date': '20160207',
'view_count': int, },
'params': {
'skip_download': True,
}, },
}, },
{ {
@ -296,7 +301,7 @@ def _real_extract(self, url):
video_id = mobj.group('videoid') video_id = mobj.group('videoid')
if video_id: if video_id:
info_url = 'https://vk.com/al_video.php?act=show&al=1&module=video&video=%s' % video_id info_url = 'https://vk.com/al_video.php?act=show_inline&al=1&video=' + video_id
# Some videos (removed?) can only be downloaded with list id specified # Some videos (removed?) can only be downloaded with list id specified
list_id = mobj.group('list_id') list_id = mobj.group('list_id')
if list_id: if list_id:
@ -346,6 +351,9 @@ def _real_extract(self, url):
r'<!>This video is no longer available, because its author has been blocked.': r'<!>This video is no longer available, because its author has been blocked.':
'Video %s is no longer available, because its author has been blocked.', 'Video %s is no longer available, because its author has been blocked.',
r'<!>This video is no longer available, because it has been deleted.':
'Video %s is no longer available, because it has been deleted.',
} }
for error_re, error_msg in ERRORS.items(): for error_re, error_msg in ERRORS.items():
@ -394,7 +402,8 @@ def _real_extract(self, url):
if not data: if not data:
data = self._parse_json( data = self._parse_json(
self._search_regex( self._search_regex(
r'<!json>\s*({.+?})\s*<!>', info_page, 'json', default='{}'), [r'<!json>\s*({.+?})\s*<!>', r'<!json>\s*({.+})'],
info_page, 'json', default='{}'),
video_id) video_id)
if data: if data:
data = data['player']['params'][0] data = data['player']['params'][0]
@ -416,7 +425,7 @@ def _real_extract(self, url):
timestamp = unified_timestamp(self._html_search_regex( timestamp = unified_timestamp(self._html_search_regex(
r'class=["\']mv_info_date[^>]+>([^<]+)(?:<|from)', info_page, r'class=["\']mv_info_date[^>]+>([^<]+)(?:<|from)', info_page,
'upload date', fatal=False)) 'upload date', default=None)) or int_or_none(data.get('date'))
view_count = str_to_int(self._search_regex( view_count = str_to_int(self._search_regex(
r'class=["\']mv_views_count[^>]+>\s*([\d,.]+)', r'class=["\']mv_views_count[^>]+>\s*([\d,.]+)',
@ -454,9 +463,12 @@ def _real_extract(self, url):
'title': title, 'title': title,
'thumbnail': data.get('jpg'), 'thumbnail': data.get('jpg'),
'uploader': data.get('md_author'), 'uploader': data.get('md_author'),
'uploader_id': str_or_none(data.get('author_id')),
'duration': data.get('duration'), 'duration': data.get('duration'),
'timestamp': timestamp, 'timestamp': timestamp,
'view_count': view_count, 'view_count': view_count,
'like_count': int_or_none(data.get('liked')),
'dislike_count': int_or_none(data.get('nolikes')),
'is_live': is_live, 'is_live': is_live,
} }