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

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..compat import (
   5     compat_urllib_parse_urlencode,
   6     compat_urlparse,
   7 )
   8 from ..utils import (
   9     float_or_none,
  10     int_or_none,
  11     sanitized_Request,
  12 )
  13
  14
  15 class ViddlerIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:www\.)?viddler\.com/(?:v|embed|player)/(?P<id>[a-z0-9]+)'
  17     _TESTS = [{
  18         'url': 'http://www.viddler.com/v/43903784',
  19         'md5': '9eee21161d2c7f5b39690c3e325fab2f',
  20         'info_dict': {
  21             'id': '43903784',
  22             'ext': 'mov',
  23             'title': 'Video Made Easy',
  24             'description': 'md5:6a697ebd844ff3093bd2e82c37b409cd',
  25             'uploader': 'viddler',
  26             'timestamp': 1335371429,
  27             'upload_date': '20120425',
  28             'duration': 100.89,
  29             'thumbnail': 're:^https?://.*\.jpg$',
  30             'view_count': int,
  31             'comment_count': int,
  32             'categories': ['video content', 'high quality video', 'video made easy', 'how to produce video with limited resources', 'viddler'],
  33         }
  34     }, {
  35         'url': 'http://www.viddler.com/v/4d03aad9/',
  36         'md5': 'f12c5a7fa839c47a79363bfdf69404fb',
  37         'info_dict': {
  38             'id': '4d03aad9',
  39             'ext': 'ts',
  40             'title': 'WALL-TO-GORTAT',
  41             'upload_date': '20150126',
  42             'uploader': 'deadspin',
  43             'timestamp': 1422285291,
  44             'view_count': int,
  45             'comment_count': int,
  46         }
  47     }, {
  48         'url': 'http://www.viddler.com/player/221ebbbd/0/',
  49         'md5': '740511f61d3d1bb71dc14a0fe01a1c10',
  50         'info_dict': {
  51             'id': '221ebbbd',
  52             'ext': 'mov',
  53             'title': 'LETeens-Grammar-snack-third-conditional',
  54             'description': ' ',
  55             'upload_date': '20140929',
  56             'uploader': 'BCLETeens',
  57             'timestamp': 1411997190,
  58             'view_count': int,
  59             'comment_count': int,
  60         }
  61     }, {
  62         # secret protected
  63         'url': 'http://www.viddler.com/v/890c0985?secret=34051570',
  64         'info_dict': {
  65             'id': '890c0985',
  66             'ext': 'mp4',
  67             'title': 'Complete Property Training - Traineeships',
  68             'description': ' ',
  69             'upload_date': '20130606',
  70             'uploader': 'TiffanyBowtell',
  71             'timestamp': 1370496993,
  72             'view_count': int,
  73             'comment_count': int,
  74         },
  75         'params': {
  76             'skip_download': True,
  77         },
  78     }]
  79
  80     def _real_extract(self, url):
  81         video_id = self._match_id(url)
  82
  83         query = {
  84             'video_id': video_id,
  85             'key': 'v0vhrt7bg2xq1vyxhkct',
  86         }
  87
  88         qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
  89         secret = qs.get('secret', [None])[0]
  90         if secret:
  91             query['secret'] = secret
  92
  93         headers = {'Referer': 'http://static.cdn-ec.viddler.com/js/arpeggio/v2/embed.html'}
  94         request = sanitized_Request(
  95             'http://api.viddler.com/api/v2/viddler.videos.getPlaybackDetails.json?%s'
  96             % compat_urllib_parse_urlencode(query), None, headers)
  97         data = self._download_json(request, video_id)['video']
  98
  99         formats = []
 100         for filed in data['files']:
 101             if filed.get('status', 'ready') != 'ready':
 102                 continue
 103             format_id = filed.get('profile_id') or filed['profile_name']
 104             f = {
 105                 'format_id': format_id,
 106                 'format_note': filed['profile_name'],
 107                 'url': self._proto_relative_url(filed['url']),
 108                 'width': int_or_none(filed.get('width')),
 109                 'height': int_or_none(filed.get('height')),
 110                 'filesize': int_or_none(filed.get('size')),
 111                 'ext': filed.get('ext'),
 112                 'source_preference': -1,
 113             }
 114             formats.append(f)
 115
 116             if filed.get('cdn_url'):
 117                 f = f.copy()
 118                 f['url'] = self._proto_relative_url(filed['cdn_url'], 'http:')
 119                 f['format_id'] = format_id + '-cdn'
 120                 f['source_preference'] = 1
 121                 formats.append(f)
 122
 123             if filed.get('html5_video_source'):
 124                 f = f.copy()
 125                 f['url'] = self._proto_relative_url(filed['html5_video_source'])
 126                 f['format_id'] = format_id + '-html5'
 127                 f['source_preference'] = 0
 128                 formats.append(f)
 129         self._sort_formats(formats)
 130
 131         categories = [
 132             t.get('text') for t in data.get('tags', []) if 'text' in t]
 133
 134         return {
 135             'id': video_id,
 136             'title': data['title'],
 137             'formats': formats,
 138             'description': data.get('description'),
 139             'timestamp': int_or_none(data.get('upload_time')),
 140             'thumbnail': self._proto_relative_url(data.get('thumbnail_url')),
 141             'uploader': data.get('author'),
 142             'duration': float_or_none(data.get('length')),
 143             'view_count': int_or_none(data.get('view_count')),
 144             'comment_count': int_or_none(data.get('comment_count')),
 145             'categories': categories,
 146         }