Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/vidme.py

   1 from __future__ import unicode_literals
   2
   3 import itertools
   4
   5 from .common import InfoExtractor
   6 from ..compat import (
   7     compat_HTTPError,
   8     compat_str,
   9 )
  10 from ..utils import (
  11     ExtractorError,
  12     int_or_none,
  13     float_or_none,
  14     parse_iso8601,
  15 )
  16
  17
  18 class VidmeIE(InfoExtractor):
  19     IE_NAME = 'vidme'
  20     _VALID_URL = r'https?://vid\.me/(?:e/)?(?P<id>[\da-zA-Z]{,5})(?:[^\da-zA-Z]|$)'
  21     _TESTS = [{
  22         'url': 'https://vid.me/QNB',
  23         'md5': 'f42d05e7149aeaec5c037b17e5d3dc82',
  24         'info_dict': {
  25             'id': 'QNB',
  26             'ext': 'mp4',
  27             'title': 'Fishing for piranha - the easy way',
  28             'description': 'source: https://www.facebook.com/photo.php?v=312276045600871',
  29             'thumbnail': r're:^https?://.*\.jpg',
  30             'timestamp': 1406313244,
  31             'upload_date': '20140725',
  32             'age_limit': 0,
  33             'duration': 119.92,
  34             'view_count': int,
  35             'like_count': int,
  36             'comment_count': int,
  37         },
  38     }, {
  39         'url': 'https://vid.me/Gc6M',
  40         'md5': 'f42d05e7149aeaec5c037b17e5d3dc82',
  41         'info_dict': {
  42             'id': 'Gc6M',
  43             'ext': 'mp4',
  44             'title': 'O Mere Dil ke chain - Arnav and Khushi VM',
  45             'thumbnail': r're:^https?://.*\.jpg',
  46             'timestamp': 1441211642,
  47             'upload_date': '20150902',
  48             'uploader': 'SunshineM',
  49             'uploader_id': '3552827',
  50             'age_limit': 0,
  51             'duration': 223.72,
  52             'view_count': int,
  53             'like_count': int,
  54             'comment_count': int,
  55         },
  56         'params': {
  57             'skip_download': True,
  58         },
  59     }, {
  60         # tests uploader field
  61         'url': 'https://vid.me/4Iib',
  62         'info_dict': {
  63             'id': '4Iib',
  64             'ext': 'mp4',
  65             'title': 'The Carver',
  66             'description': 'md5:e9c24870018ae8113be936645b93ba3c',
  67             'thumbnail': r're:^https?://.*\.jpg',
  68             'timestamp': 1433203629,
  69             'upload_date': '20150602',
  70             'uploader': 'Thomas',
  71             'uploader_id': '109747',
  72             'age_limit': 0,
  73             'duration': 97.859999999999999,
  74             'view_count': int,
  75             'like_count': int,
  76             'comment_count': int,
  77         },
  78         'params': {
  79             'skip_download': True,
  80         },
  81     }, {
  82         # nsfw test from http://naked-yogi.tumblr.com/post/118312946248/naked-smoking-stretching
  83         'url': 'https://vid.me/e/Wmur',
  84         'info_dict': {
  85             'id': 'Wmur',
  86             'ext': 'mp4',
  87             'title': 'naked smoking & stretching',
  88             'thumbnail': r're:^https?://.*\.jpg',
  89             'timestamp': 1430931613,
  90             'upload_date': '20150506',
  91             'uploader': 'naked-yogi',
  92             'uploader_id': '1638622',
  93             'age_limit': 18,
  94             'duration': 653.26999999999998,
  95             'view_count': int,
  96             'like_count': int,
  97             'comment_count': int,
  98         },
  99         'params': {
 100             'skip_download': True,
 101         },
 102     }, {
 103         # nsfw, user-disabled
 104         'url': 'https://vid.me/dzGJ',
 105         'only_matching': True,
 106     }, {
 107         # suspended
 108         'url': 'https://vid.me/Ox3G',
 109         'only_matching': True,
 110     }, {
 111         # deleted
 112         'url': 'https://vid.me/KTPm',
 113         'only_matching': True,
 114     }, {
 115         # no formats in the API response
 116         'url': 'https://vid.me/e5g',
 117         'info_dict': {
 118             'id': 'e5g',
 119             'ext': 'mp4',
 120             'title': 'Video upload (e5g)',
 121             'thumbnail': r're:^https?://.*\.jpg',
 122             'timestamp': 1401480195,
 123             'upload_date': '20140530',
 124             'uploader': None,
 125             'uploader_id': None,
 126             'age_limit': 0,
 127             'duration': 483,
 128             'view_count': int,
 129             'like_count': int,
 130             'comment_count': int,
 131         },
 132         'params': {
 133             'skip_download': True,
 134         },
 135     }]
 136
 137     def _real_extract(self, url):
 138         video_id = self._match_id(url)
 139
 140         try:
 141             response = self._download_json(
 142                 'https://api.vid.me/videoByUrl/%s' % video_id, video_id)
 143         except ExtractorError as e:
 144             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400:
 145                 response = self._parse_json(e.cause.read(), video_id)
 146             else:
 147                 raise
 148
 149         error = response.get('error')
 150         if error:
 151             raise ExtractorError(
 152                 '%s returned error: %s' % (self.IE_NAME, error), expected=True)
 153
 154         video = response['video']
 155
 156         if video.get('state') == 'deleted':
 157             raise ExtractorError(
 158                 'Vidme said: Sorry, this video has been deleted.',
 159                 expected=True)
 160
 161         if video.get('state') in ('user-disabled', 'suspended'):
 162             raise ExtractorError(
 163                 'Vidme said: This video has been suspended either due to a copyright claim, '
 164                 'or for violating the terms of use.',
 165                 expected=True)
 166
 167         formats = []
 168         for f in video.get('formats', []):
 169             format_url = f.get('uri')
 170             if not format_url or not isinstance(format_url, compat_str):
 171                 continue
 172             format_type = f.get('type')
 173             if format_type == 'dash':
 174                 formats.extend(self._extract_mpd_formats(
 175                     format_url, video_id, mpd_id='dash', fatal=False))
 176             elif format_type == 'hls':
 177                 formats.extend(self._extract_m3u8_formats(
 178                     format_url, video_id, 'mp4', entry_protocol='m3u8_native',
 179                     m3u8_id='hls', fatal=False))
 180             else:
 181                 formats.append({
 182                     'format_id': f.get('type'),
 183                     'url': format_url,
 184                     'width': int_or_none(f.get('width')),
 185                     'height': int_or_none(f.get('height')),
 186                     'preference': 0 if f.get('type', '').endswith(
 187                         'clip') else 1,
 188                 })
 189
 190         if not formats and video.get('complete_url'):
 191             formats.append({
 192                 'url': video.get('complete_url'),
 193                 'width': int_or_none(video.get('width')),
 194                 'height': int_or_none(video.get('height')),
 195             })
 196
 197         self._sort_formats(formats)
 198
 199         title = video['title']
 200         description = video.get('description')
 201         thumbnail = video.get('thumbnail_url')
 202         timestamp = parse_iso8601(video.get('date_created'), ' ')
 203         uploader = video.get('user', {}).get('username')
 204         uploader_id = video.get('user', {}).get('user_id')
 205         age_limit = 18 if video.get('nsfw') is True else 0
 206         duration = float_or_none(video.get('duration'))
 207         view_count = int_or_none(video.get('view_count'))
 208         like_count = int_or_none(video.get('likes_count'))
 209         comment_count = int_or_none(video.get('comment_count'))
 210
 211         return {
 212             'id': video_id,
 213             'title': title or 'Video upload (%s)' % video_id,
 214             'description': description,
 215             'thumbnail': thumbnail,
 216             'uploader': uploader,
 217             'uploader_id': uploader_id,
 218             'age_limit': age_limit,
 219             'timestamp': timestamp,
 220             'duration': duration,
 221             'view_count': view_count,
 222             'like_count': like_count,
 223             'comment_count': comment_count,
 224             'formats': formats,
 225         }
 226
 227
 228 class VidmeListBaseIE(InfoExtractor):
 229     # Max possible limit according to https://docs.vid.me/#api-Videos-List
 230     _LIMIT = 100
 231
 232     def _entries(self, user_id, user_name):
 233         for page_num in itertools.count(1):
 234             page = self._download_json(
 235                 'https://api.vid.me/videos/%s?user=%s&limit=%d&offset=%d'
 236                 % (self._API_ITEM, user_id, self._LIMIT, (page_num - 1) * self._LIMIT),
 237                 user_name, 'Downloading user %s page %d' % (self._API_ITEM, page_num))
 238
 239             videos = page.get('videos', [])
 240             if not videos:
 241                 break
 242
 243             for video in videos:
 244                 video_url = video.get('full_url') or video.get('embed_url')
 245                 if video_url:
 246                     yield self.url_result(video_url, VidmeIE.ie_key())
 247
 248             total = int_or_none(page.get('page', {}).get('total'))
 249             if total and self._LIMIT * page_num >= total:
 250                 break
 251
 252     def _real_extract(self, url):
 253         user_name = self._match_id(url)
 254
 255         user_id = self._download_json(
 256             'https://api.vid.me/userByUsername?username=%s' % user_name,
 257             user_name)['user']['user_id']
 258
 259         return self.playlist_result(
 260             self._entries(user_id, user_name), user_id,
 261             '%s - %s' % (user_name, self._TITLE))
 262
 263
 264 class VidmeUserIE(VidmeListBaseIE):
 265     IE_NAME = 'vidme:user'
 266     _VALID_URL = r'https?://vid\.me/(?:e/)?(?P<id>[\da-zA-Z_-]{6,})(?!/likes)(?:[^\da-zA-Z_-]|$)'
 267     _API_ITEM = 'list'
 268     _TITLE = 'Videos'
 269     _TESTS = [{
 270         'url': 'https://vid.me/MasakoX',
 271         'info_dict': {
 272             'id': '16112341',
 273             'title': 'MasakoX - %s' % _TITLE,
 274         },
 275         'playlist_mincount': 191,
 276     }, {
 277         'url': 'https://vid.me/unsQuare_netWork',
 278         'only_matching': True,
 279     }]
 280
 281
 282 class VidmeUserLikesIE(VidmeListBaseIE):
 283     IE_NAME = 'vidme:user:likes'
 284     _VALID_URL = r'https?://vid\.me/(?:e/)?(?P<id>[\da-zA-Z_-]{6,})/likes'
 285     _API_ITEM = 'likes'
 286     _TITLE = 'Likes'
 287     _TESTS = [{
 288         'url': 'https://vid.me/ErinAlexis/likes',
 289         'info_dict': {
 290             'id': '6483530',
 291             'title': 'ErinAlexis - %s' % _TITLE,
 292         },
 293         'playlist_mincount': 415,
 294     }, {
 295         'url': 'https://vid.me/Kaleidoscope-Ish/likes',
 296         'only_matching': True,
 297     }]