]>
jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/spankwire.py
3 from .common
import InfoExtractor
14 class SpankwireIE(InfoExtractor
):
17 (?:www\.)?spankwire\.com/
20 EmbedPlayer\.aspx/?\?.*?\bArticleId=
25 # download URL pattern: */<height>P_<tbr>K_<video_id>.mp4
26 'url': 'http://www.spankwire.com/Buckcherry-s-X-Rated-Music-Video-Crazy-Bitch/video103545/',
27 'md5': '5aa0e4feef20aad82cbcae3aed7ab7cd',
31 'title': 'Buckcherry`s X Rated Music Video Crazy Bitch',
32 'description': 'Crazy Bitch X rated music video.',
35 'uploader_id': '124697',
36 'timestamp': 1178587885,
37 'upload_date': '20070508',
38 'average_rating': float,
46 # download URL pattern: */mp4_<format_id>_<video_id>.mp4
47 'url': 'http://www.spankwire.com/Titcums-Compiloation-I/video1921551/',
48 'md5': '09b3c20833308b736ae8902db2f8d7e6',
52 'title': 'Titcums Compiloation I',
53 'description': 'cum on tits',
54 'uploader': 'dannyh78999',
55 'uploader_id': '3056053',
56 'upload_date': '20150822',
60 'proxy': '127.0.0.1:8118'
64 'url': 'https://www.spankwire.com/EmbedPlayer.aspx/?ArticleId=156156&autostart=true',
65 'only_matching': True,
69 def _extract_urls(webpage
):
71 r
'<iframe[^>]+\bsrc=["\']((?
:https?
:)?
//(?
:www\
.)?spankwire\
.com
/EmbedPlayer\
.aspx
/?
\?.*?
\bArticleId
=\d
+)',
74 def _real_extract(self, url):
75 video_id = self._match_id(url)
77 video = self._download_json(
78 'https
://www
.spankwire
.com
/api
/video
/%s.json
' % video_id, video_id)
80 title = video['title
']
83 videos = video.get('videos
')
84 if isinstance(videos, dict):
85 for format_id, format_url in videos.items():
86 video_url = url_or_none(format_url)
89 height = int_or_none(self._search_regex(
90 r'(\d
+)[pP
]', format_id, 'height
', default=None))
92 r'/(?P
<height
>\d
+)[pP
]_(?P
<tbr
>\d
+)[kK
]', video_url)
94 tbr = int(m.group('tbr
'))
95 height = height or int(m.group('height
'))
100 'format_id
': '%dp
' % height if height else format_id,
104 m3u8_url = url_or_none(video.get('HLS
'))
106 formats.extend(self._extract_m3u8_formats(
107 m3u8_url, video_id, 'mp4
', entry_protocol='m3u8_native
',
108 m3u8_id='hls
', fatal=False))
109 self._sort_formats(formats)
111 view_count = str_to_int(video.get('viewed
'))
114 for preference, t in enumerate(('', '2x
'), start=0):
115 thumbnail_url = url_or_none(video.get('poster
%s' % t))
116 if not thumbnail_url:
119 'url
': thumbnail_url,
120 'preference
': preference,
123 def extract_names(key):
124 entries_list = video.get(key)
125 if not isinstance(entries_list, list):
128 for entry in entries_list:
129 name = str_or_none(entry.get('name
'))
134 categories = extract_names('categories
')
135 tags = extract_names('tags
')
140 webpage = self._download_webpage(
141 'https
://www
.spankwire
.com
/_
/video
%s/' % video_id, video_id,
144 info = self._search_json_ld(webpage, video_id, default={})
146 if 'thumbnail
' in info:
147 thumbnail_url = url_or_none(info['thumbnail
'])
148 del info['thumbnail
']
149 if not thumbnail_url:
150 thumbnail_url = self._og_search_thumbnail(webpage)
153 'url
': thumbnail_url,
156 uploader = self._html_search_regex(
157 r'(?s
)by\s
*<a
[^
>]+\bclass
=["\']uploaded__by[^>]*>(.+?)</a>',
158 webpage, 'uploader', fatal=False)
160 view_count = str_to_int(self._search_regex(
161 r'data-views=["\']([\d
,.]+)', webpage, 'view count
',
167 'description
': video.get('description
'),
168 'duration
': int_or_none(video.get('duration
')),
169 'thumbnails
': thumbnails,
170 'uploader
': uploader,
171 'uploader_id
': str_or_none(video.get('userId
')),
172 'timestamp
': int_or_none(video.get('time_approved_on
')),
173 'average_rating
': float_or_none(video.get('rating
')),
174 'view_count
': view_count,
175 'comment_count
': int_or_none(video.get('comments
')),
177 'categories
': categories,