yt_dlp/extractor/spankwire.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     float_or_none,
   6     int_or_none,
   7     merge_dicts,
   8     str_or_none,
   9     str_to_int,
  10     url_or_none,
  11 )
  12
  13
  14 class SpankwireIE(InfoExtractor):
  15     _VALID_URL = r'''(?x)
  16                     https?://
  17                         (?:www\.)?spankwire\.com/
  18                         (?:
  19                             [^/]+/video|
  20                             EmbedPlayer\.aspx/?\?.*?\bArticleId=
  21                         )
  22                         (?P<id>\d+)
  23                     '''
  24     _EMBED_REGEX = [r'<iframe[^>]+\bsrc=["\'](?P<url>(?:https?:)?//(?:www\.)?spankwire\.com/EmbedPlayer\.aspx/?\?.*?\bArticleId=\d+)']
  25     _TESTS = [{
  26         # download URL pattern: */<height>P_<tbr>K_<video_id>.mp4
  27         'url': 'http://www.spankwire.com/Buckcherry-s-X-Rated-Music-Video-Crazy-Bitch/video103545/',
  28         'md5': '5aa0e4feef20aad82cbcae3aed7ab7cd',
  29         'info_dict': {
  30             'id': '103545',
  31             'ext': 'mp4',
  32             'title': 'Buckcherry`s X Rated Music Video Crazy Bitch',
  33             'description': 'Crazy Bitch X rated music video.',
  34             'duration': 222,
  35             'uploader': 'oreusz',
  36             'uploader_id': '124697',
  37             'timestamp': 1178587885,
  38             'upload_date': '20070508',
  39             'average_rating': float,
  40             'view_count': int,
  41             'comment_count': int,
  42             'age_limit': 18,
  43             'categories': list,
  44             'tags': list,
  45         },
  46     }, {
  47         # download URL pattern: */mp4_<format_id>_<video_id>.mp4
  48         'url': 'http://www.spankwire.com/Titcums-Compiloation-I/video1921551/',
  49         'md5': '09b3c20833308b736ae8902db2f8d7e6',
  50         'info_dict': {
  51             'id': '1921551',
  52             'ext': 'mp4',
  53             'title': 'Titcums Compiloation I',
  54             'description': 'cum on tits',
  55             'uploader': 'dannyh78999',
  56             'uploader_id': '3056053',
  57             'upload_date': '20150822',
  58             'age_limit': 18,
  59         },
  60         'params': {
  61             'proxy': '127.0.0.1:8118'
  62         },
  63         'skip': 'removed',
  64     }, {
  65         'url': 'https://www.spankwire.com/EmbedPlayer.aspx/?ArticleId=156156&autostart=true',
  66         'only_matching': True,
  67     }]
  68
  69     def _real_extract(self, url):
  70         video_id = self._match_id(url)
  71
  72         video = self._download_json(
  73             'https://www.spankwire.com/api/video/%s.json' % video_id, video_id)
  74
  75         title = video['title']
  76
  77         formats = []
  78         videos = video.get('videos')
  79         if isinstance(videos, dict):
  80             for format_id, format_url in videos.items():
  81                 video_url = url_or_none(format_url)
  82                 if not format_url:
  83                     continue
  84                 height = int_or_none(self._search_regex(
  85                     r'(\d+)[pP]', format_id, 'height', default=None))
  86                 m = re.search(
  87                     r'/(?P<height>\d+)[pP]_(?P<tbr>\d+)[kK]', video_url)
  88                 if m:
  89                     tbr = int(m.group('tbr'))
  90                     height = height or int(m.group('height'))
  91                 else:
  92                     tbr = None
  93                 formats.append({
  94                     'url': video_url,
  95                     'format_id': '%dp' % height if height else format_id,
  96                     'height': height,
  97                     'tbr': tbr,
  98                 })
  99         m3u8_url = url_or_none(video.get('HLS'))
 100         if m3u8_url:
 101             formats.extend(self._extract_m3u8_formats(
 102                 m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
 103                 m3u8_id='hls', fatal=False))
 104         self._sort_formats(formats)
 105
 106         view_count = str_to_int(video.get('viewed'))
 107
 108         thumbnails = []
 109         for preference, t in enumerate(('', '2x'), start=0):
 110             thumbnail_url = url_or_none(video.get('poster%s' % t))
 111             if not thumbnail_url:
 112                 continue
 113             thumbnails.append({
 114                 'url': thumbnail_url,
 115                 'preference': preference,
 116             })
 117
 118         def extract_names(key):
 119             entries_list = video.get(key)
 120             if not isinstance(entries_list, list):
 121                 return
 122             entries = []
 123             for entry in entries_list:
 124                 name = str_or_none(entry.get('name'))
 125                 if name:
 126                     entries.append(name)
 127             return entries
 128
 129         categories = extract_names('categories')
 130         tags = extract_names('tags')
 131
 132         uploader = None
 133         info = {}
 134
 135         webpage = self._download_webpage(
 136             'https://www.spankwire.com/_/video%s/' % video_id, video_id,
 137             fatal=False)
 138         if webpage:
 139             info = self._search_json_ld(webpage, video_id, default={})
 140             thumbnail_url = None
 141             if 'thumbnail' in info:
 142                 thumbnail_url = url_or_none(info['thumbnail'])
 143                 del info['thumbnail']
 144             if not thumbnail_url:
 145                 thumbnail_url = self._og_search_thumbnail(webpage)
 146             if thumbnail_url:
 147                 thumbnails.append({
 148                     'url': thumbnail_url,
 149                     'preference': 10,
 150                 })
 151             uploader = self._html_search_regex(
 152                 r'(?s)by\s*<a[^>]+\bclass=["\']uploaded__by[^>]*>(.+?)</a>',
 153                 webpage, 'uploader', fatal=False)
 154             if not view_count:
 155                 view_count = str_to_int(self._search_regex(
 156                     r'data-views=["\']([\d,.]+)', webpage, 'view count',
 157                     fatal=False))
 158
 159         return merge_dicts({
 160             'id': video_id,
 161             'title': title,
 162             'description': video.get('description'),
 163             'duration': int_or_none(video.get('duration')),
 164             'thumbnails': thumbnails,
 165             'uploader': uploader,
 166             'uploader_id': str_or_none(video.get('userId')),
 167             'timestamp': int_or_none(video.get('time_approved_on')),
 168             'average_rating': float_or_none(video.get('rating')),
 169             'view_count': view_count,
 170             'comment_count': int_or_none(video.get('comments')),
 171             'age_limit': 18,
 172             'categories': categories,
 173             'tags': tags,
 174             'formats': formats,
 175         }, info)