_ Git - youtube-dl/blob - youtube_dl/extractor/viddler.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     float_or_none,
   6     int_or_none,
   7     sanitized_Request,
   8 )
   9
  10
  11 class ViddlerIE(InfoExtractor):
  12     _VALID_URL = r'https?://(?:www\.)?viddler\.com/(?:v|embed|player)/(?P<id>[a-z0-9]+)'
  13     _TESTS = [{
  14         'url': 'http://www.viddler.com/v/43903784',
  15         'md5': 'ae43ad7cb59431ce043f0ff7fa13cbf4',
  16         'info_dict': {
  17             'id': '43903784',
  18             'ext': 'mp4',
  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': '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': 'faa71fbf70c0bee7ab93076fd007f4b0',
  33         'info_dict': {
  34             'id': '4d03aad9',
  35             'ext': 'mp4',
  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': '0defa2bd0ea613d14a6e9bd1db6be326',
  46         'info_dict': {
  47             'id': '221ebbbd',
  48             'ext': 'mp4',
  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
  59     def _real_extract(self, url):
  60         video_id = self._match_id(url)
  61
  62         json_url = (
  63             'http://api.viddler.com/api/v2/viddler.videos.getPlaybackDetails.json?video_id=%s&key=v0vhrt7bg2xq1vyxhkct' %
  64             video_id)
  65         headers = {'Referer': 'http://static.cdn-ec.viddler.com/js/arpeggio/v2/embed.html'}
  66         request = sanitized_Request(json_url, None, headers)
  67         data = self._download_json(request, video_id)['video']
  68
  69         formats = []
  70         for filed in data['files']:
  71             if filed.get('status', 'ready') != 'ready':
  72                 continue
  73             format_id = filed.get('profile_id') or filed['profile_name']
  74             f = {
  75                 'format_id': format_id,
  76                 'format_note': filed['profile_name'],
  77                 'url': self._proto_relative_url(filed['url']),
  78                 'width': int_or_none(filed.get('width')),
  79                 'height': int_or_none(filed.get('height')),
  80                 'filesize': int_or_none(filed.get('size')),
  81                 'ext': filed.get('ext'),
  82                 'source_preference': -1,
  83             }
  84             formats.append(f)
  85
  86             if filed.get('cdn_url'):
  87                 f = f.copy()
  88                 f['url'] = self._proto_relative_url(filed['cdn_url'], 'http:')
  89                 f['format_id'] = format_id + '-cdn'
  90                 f['source_preference'] = 1
  91                 formats.append(f)
  92
  93             if filed.get('html5_video_source'):
  94                 f = f.copy()
  95                 f['url'] = self._proto_relative_url(filed['html5_video_source'])
  96                 f['format_id'] = format_id + '-html5'
  97                 f['source_preference'] = 0
  98                 formats.append(f)
  99         self._sort_formats(formats)
 100
 101         categories = [
 102             t.get('text') for t in data.get('tags', []) if 'text' in t]
 103
 104         return {
 105             'id': video_id,
 106             'title': data['title'],
 107             'formats': formats,
 108             'description': data.get('description'),
 109             'timestamp': int_or_none(data.get('upload_time')),
 110             'thumbnail': self._proto_relative_url(data.get('thumbnail_url')),
 111             'uploader': data.get('author'),
 112             'duration': float_or_none(data.get('length')),
 113             'view_count': int_or_none(data.get('view_count')),
 114             'comment_count': int_or_none(data.get('comment_count')),
 115             'categories': categories,
 116         }