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