yt_dlp/extractor/viddler.py

   1 from __future__ import unicode_literals
   2
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     float_or_none,
   7     int_or_none,
   8 )
   9
  10
  11 class ViddlerIE(InfoExtractor):
  12     _VALID_URL = r'https?://(?:www\.)?viddler\.com/(?:v|embed|player)/(?P<id>[a-z0-9]+)(?:.+?\bsecret=(\d+))?'
  13     _TESTS = [{
  14         'url': 'http://www.viddler.com/v/43903784',
  15         'md5': '9eee21161d2c7f5b39690c3e325fab2f',
  16         'info_dict': {
  17             'id': '43903784',
  18             'ext': 'mov',
  19             'title': 'Video Made Easy',
  20             'description': 'md5:6a697ebd844ff3093bd2e82c37b409cd',
  21             'uploader': 'viddler',
  22             'timestamp': 1335371429,
  23             'upload_date': '20120425',
  24             'duration': 100.89,
  25             'thumbnail': r're:^https?://.*\.jpg$',
  26             'view_count': int,
  27             'comment_count': int,
  28             'categories': ['video content', 'high quality video', 'video made easy', 'how to produce video with limited resources', 'viddler'],
  29         }
  30     }, {
  31         'url': 'http://www.viddler.com/v/4d03aad9/',
  32         'md5': 'f12c5a7fa839c47a79363bfdf69404fb',
  33         'info_dict': {
  34             'id': '4d03aad9',
  35             'ext': 'ts',
  36             'title': 'WALL-TO-GORTAT',
  37             'upload_date': '20150126',
  38             'uploader': 'deadspin',
  39             'timestamp': 1422285291,
  40             'view_count': int,
  41             'comment_count': int,
  42         }
  43     }, {
  44         'url': 'http://www.viddler.com/player/221ebbbd/0/',
  45         'md5': '740511f61d3d1bb71dc14a0fe01a1c10',
  46         'info_dict': {
  47             'id': '221ebbbd',
  48             'ext': 'mov',
  49             'title': 'LETeens-Grammar-snack-third-conditional',
  50             'description': ' ',
  51             'upload_date': '20140929',
  52             'uploader': 'BCLETeens',
  53             'timestamp': 1411997190,
  54             'view_count': int,
  55             'comment_count': int,
  56         }
  57     }, {
  58         # secret protected
  59         'url': 'http://www.viddler.com/v/890c0985?secret=34051570',
  60         'info_dict': {
  61             'id': '890c0985',
  62             'ext': 'mp4',
  63             'title': 'Complete Property Training - Traineeships',
  64             'description': ' ',
  65             'upload_date': '20130606',
  66             'uploader': 'TiffanyBowtell',
  67             'timestamp': 1370496993,
  68             'view_count': int,
  69             'comment_count': int,
  70         },
  71         'params': {
  72             'skip_download': True,
  73         },
  74     }]
  75
  76     def _real_extract(self, url):
  77         video_id, secret = self._match_valid_url(url).groups()
  78
  79         query = {
  80             'video_id': video_id,
  81             'key': 'v0vhrt7bg2xq1vyxhkct',
  82         }
  83         if secret:
  84             query['secret'] = secret
  85
  86         data = self._download_json(
  87             'http://api.viddler.com/api/v2/viddler.videos.getPlaybackDetails.json',
  88             video_id, headers={'Referer': url}, query=query)['video']
  89
  90         formats = []
  91         for filed in data['files']:
  92             if filed.get('status', 'ready') != 'ready':
  93                 continue
  94             format_id = filed.get('profile_id') or filed['profile_name']
  95             f = {
  96                 'format_id': format_id,
  97                 'format_note': filed['profile_name'],
  98                 'url': self._proto_relative_url(filed['url']),
  99                 'width': int_or_none(filed.get('width')),
 100                 'height': int_or_none(filed.get('height')),
 101                 'filesize': int_or_none(filed.get('size')),
 102                 'ext': filed.get('ext'),
 103                 'source_preference': -1,
 104             }
 105             formats.append(f)
 106
 107             if filed.get('cdn_url'):
 108                 f = f.copy()
 109                 f['url'] = self._proto_relative_url(filed['cdn_url'], 'http:')
 110                 f['format_id'] = format_id + '-cdn'
 111                 f['source_preference'] = 1
 112                 formats.append(f)
 113
 114             if filed.get('html5_video_source'):
 115                 f = f.copy()
 116                 f['url'] = self._proto_relative_url(filed['html5_video_source'])
 117                 f['format_id'] = format_id + '-html5'
 118                 f['source_preference'] = 0
 119                 formats.append(f)
 120         self._sort_formats(formats)
 121
 122         categories = [
 123             t.get('text') for t in data.get('tags', []) if 'text' in t]
 124
 125         return {
 126             'id': video_id,
 127             'title': data['title'],
 128             'formats': formats,
 129             'description': data.get('description'),
 130             'timestamp': int_or_none(data.get('upload_time')),
 131             'thumbnail': self._proto_relative_url(data.get('thumbnail_url')),
 132             'uploader': data.get('author'),
 133             'duration': float_or_none(data.get('length')),
 134             'view_count': int_or_none(data.get('view_count')),
 135             'comment_count': int_or_none(data.get('comment_count')),
 136             'categories': categories,
 137         }