]>
jfr.im git - yt-dlp.git/blob - youtube_dlc/extractor/spankwire.py
1 from __future__
import unicode_literals
5 from .common
import InfoExtractor
16 class SpankwireIE(InfoExtractor
):
19 (?:www\.)?spankwire\.com/
22 EmbedPlayer\.aspx/?\?.*?\bArticleId=
27 # download URL pattern: */<height>P_<tbr>K_<video_id>.mp4
28 'url': 'http://www.spankwire.com/Buckcherry-s-X-Rated-Music-Video-Crazy-Bitch/video103545/',
29 'md5': '5aa0e4feef20aad82cbcae3aed7ab7cd',
33 'title': 'Buckcherry`s X Rated Music Video Crazy Bitch',
34 'description': 'Crazy Bitch X rated music video.',
37 'uploader_id': '124697',
38 'timestamp': 1178587885,
39 'upload_date': '20070508',
40 'average_rating': float,
48 # download URL pattern: */mp4_<format_id>_<video_id>.mp4
49 'url': 'http://www.spankwire.com/Titcums-Compiloation-I/video1921551/',
50 'md5': '09b3c20833308b736ae8902db2f8d7e6',
54 'title': 'Titcums Compiloation I',
55 'description': 'cum on tits',
56 'uploader': 'dannyh78999',
57 'uploader_id': '3056053',
58 'upload_date': '20150822',
62 'proxy': '127.0.0.1:8118'
66 'url': 'https://www.spankwire.com/EmbedPlayer.aspx/?ArticleId=156156&autostart=true',
67 'only_matching': True,
71 def _extract_urls(webpage
):
73 r
'<iframe[^>]+\bsrc=["\']((?
:https?
:)?
//(?
:www\
.)?spankwire\
.com
/EmbedPlayer\
.aspx
/?
\?.*?
\bArticleId
=\d
+)',
76 def _real_extract(self, url):
77 video_id = self._match_id(url)
79 video = self._download_json(
80 'https
://www
.spankwire
.com
/api
/video
/%s.json
' % video_id, video_id)
82 title = video['title
']
85 videos = video.get('videos
')
86 if isinstance(videos, dict):
87 for format_id, format_url in videos.items():
88 video_url = url_or_none(format_url)
91 height = int_or_none(self._search_regex(
92 r'(\d
+)[pP
]', format_id, 'height
', default=None))
94 r'/(?P
<height
>\d
+)[pP
]_(?P
<tbr
>\d
+)[kK
]', video_url)
96 tbr = int(m.group('tbr
'))
97 height = height or int(m.group('height
'))
102 'format_id
': '%dp
' % height if height else format_id,
106 m3u8_url = url_or_none(video.get('HLS
'))
108 formats.extend(self._extract_m3u8_formats(
109 m3u8_url, video_id, 'mp4
', entry_protocol='m3u8_native
',
110 m3u8_id='hls
', fatal=False))
111 self._sort_formats(formats, ('height
', 'tbr
', 'width
', 'format_id
'))
113 view_count = str_to_int(video.get('viewed
'))
116 for preference, t in enumerate(('', '2x
'), start=0):
117 thumbnail_url = url_or_none(video.get('poster
%s' % t))
118 if not thumbnail_url:
121 'url
': thumbnail_url,
122 'preference
': preference,
125 def extract_names(key):
126 entries_list = video.get(key)
127 if not isinstance(entries_list, list):
130 for entry in entries_list:
131 name = str_or_none(entry.get('name
'))
136 categories = extract_names('categories
')
137 tags = extract_names('tags
')
142 webpage = self._download_webpage(
143 'https
://www
.spankwire
.com
/_
/video
%s/' % video_id, video_id,
146 info = self._search_json_ld(webpage, video_id, default={})
148 if 'thumbnail
' in info:
149 thumbnail_url = url_or_none(info['thumbnail
'])
150 del info['thumbnail
']
151 if not thumbnail_url:
152 thumbnail_url = self._og_search_thumbnail(webpage)
155 'url
': thumbnail_url,
158 uploader = self._html_search_regex(
159 r'(?s
)by\s
*<a
[^
>]+\bclass
=["\']uploaded__by[^>]*>(.+?)</a>',
160 webpage, 'uploader', fatal=False)
162 view_count = str_to_int(self._search_regex(
163 r'data-views=["\']([\d
,.]+)', webpage, 'view count
',
169 'description
': video.get('description
'),
170 'duration
': int_or_none(video.get('duration
')),
171 'thumbnails
': thumbnails,
172 'uploader
': uploader,
173 'uploader_id
': str_or_none(video.get('userId
')),
174 'timestamp
': int_or_none(video.get('time_approved_on
')),
175 'average_rating
': float_or_none(video.get('rating
')),
176 'view_count
': view_count,
177 'comment_count
': int_or_none(video.get('comments
')),
179 'categories
': categories,