yt_dlp/extractor/viddler.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     float_or_none,
   4     int_or_none,
   5 )
   6
   7
   8 class ViddlerIE(InfoExtractor):
   9     _VALID_URL = r'https?://(?:www\.)?viddler\.com/(?:v|embed|player)/(?P<id>[a-z0-9]+)(?:.+?\bsecret=(\d+))?'
  10     _EMBED_REGEX = [r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1']
  11
  12     _TESTS = [{
  13         'url': 'http://www.viddler.com/v/43903784',
  14         'md5': '9eee21161d2c7f5b39690c3e325fab2f',
  15         'info_dict': {
  16             'id': '43903784',
  17             'ext': 'mov',
  18             'title': 'Video Made Easy',
  19             'description': 'md5:6a697ebd844ff3093bd2e82c37b409cd',
  20             'uploader': 'viddler',
  21             'timestamp': 1335371429,
  22             'upload_date': '20120425',
  23             'duration': 100.89,
  24             'thumbnail': r're:^https?://.*\.jpg$',
  25             'view_count': int,
  26             'comment_count': int,
  27             'categories': ['video content', 'high quality video', 'video made easy', 'how to produce video with limited resources', 'viddler'],
  28         },
  29     }, {
  30         'url': 'http://www.viddler.com/v/4d03aad9/',
  31         'md5': 'f12c5a7fa839c47a79363bfdf69404fb',
  32         'info_dict': {
  33             'id': '4d03aad9',
  34             'ext': 'ts',
  35             'title': 'WALL-TO-GORTAT',
  36             'upload_date': '20150126',
  37             'uploader': 'deadspin',
  38             'timestamp': 1422285291,
  39             'view_count': int,
  40             'comment_count': int,
  41         },
  42     }, {
  43         'url': 'http://www.viddler.com/player/221ebbbd/0/',
  44         'md5': '740511f61d3d1bb71dc14a0fe01a1c10',
  45         'info_dict': {
  46             'id': '221ebbbd',
  47             'ext': 'mov',
  48             'title': 'LETeens-Grammar-snack-third-conditional',
  49             'description': ' ',
  50             'upload_date': '20140929',
  51             'uploader': 'BCLETeens',
  52             'timestamp': 1411997190,
  53             'view_count': int,
  54             'comment_count': int,
  55         },
  56     }, {
  57         # secret protected
  58         'url': 'http://www.viddler.com/v/890c0985?secret=34051570',
  59         'info_dict': {
  60             'id': '890c0985',
  61             'ext': 'mp4',
  62             'title': 'Complete Property Training - Traineeships',
  63             'description': ' ',
  64             'upload_date': '20130606',
  65             'uploader': 'TiffanyBowtell',
  66             'timestamp': 1370496993,
  67             'view_count': int,
  68             'comment_count': int,
  69         },
  70         'params': {
  71             'skip_download': True,
  72         },
  73     }]
  74
  75     def _real_extract(self, url):
  76         video_id, secret = self._match_valid_url(url).groups()
  77
  78         query = {
  79             'video_id': video_id,
  80             'key': 'v0vhrt7bg2xq1vyxhkct',
  81         }
  82         if secret:
  83             query['secret'] = secret
  84
  85         data = self._download_json(
  86             'http://api.viddler.com/api/v2/viddler.videos.getPlaybackDetails.json',
  87             video_id, headers={'Referer': url}, query=query)['video']
  88
  89         formats = []
  90         for filed in data['files']:
  91             if filed.get('status', 'ready') != 'ready':
  92                 continue
  93             format_id = filed.get('profile_id') or filed['profile_name']
  94             f = {
  95                 'format_id': format_id,
  96                 'format_note': filed['profile_name'],
  97                 'url': self._proto_relative_url(filed['url']),
  98                 'width': int_or_none(filed.get('width')),
  99                 'height': int_or_none(filed.get('height')),
 100                 'filesize': int_or_none(filed.get('size')),
 101                 'ext': filed.get('ext'),
 102                 'source_preference': -1,
 103             }
 104             formats.append(f)
 105
 106             if filed.get('cdn_url'):
 107                 f = f.copy()
 108                 f['url'] = self._proto_relative_url(filed['cdn_url'], 'http:')
 109                 f['format_id'] = format_id + '-cdn'
 110                 f['source_preference'] = 1
 111                 formats.append(f)
 112
 113             if filed.get('html5_video_source'):
 114                 f = f.copy()
 115                 f['url'] = self._proto_relative_url(filed['html5_video_source'])
 116                 f['format_id'] = format_id + '-html5'
 117                 f['source_preference'] = 0
 118                 formats.append(f)
 119
 120         categories = [
 121             t.get('text') for t in data.get('tags', []) if 'text' in t]
 122
 123         return {
 124             'id': video_id,
 125             'title': data['title'],
 126             'formats': formats,
 127             'description': data.get('description'),
 128             'timestamp': int_or_none(data.get('upload_time')),
 129             'thumbnail': self._proto_relative_url(data.get('thumbnail_url')),
 130             'uploader': data.get('author'),
 131             'duration': float_or_none(data.get('length')),
 132             'view_count': int_or_none(data.get('view_count')),
 133             'comment_count': int_or_none(data.get('comment_count')),
 134             'categories': categories,
 135         }