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 )
   8 from ..compat import (
   9    compat_urllib_request
  10 )
  11
  12
  13 class ViddlerIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?viddler\.com/(?:v|embed|player)/(?P<id>[a-z0-9]+)'
  15     _TESTS = [{
  16         "url": "http://www.viddler.com/v/43903784",
  17         'md5': 'ae43ad7cb59431ce043f0ff7fa13cbf4',
  18         'info_dict': {
  19             'id': '43903784',
  20             'ext': 'mp4',
  21             "title": "Video Made Easy",
  22             'description': 'You don\'t need to be a professional to make high-quality video content. Viddler provides some quick and easy tips on how to produce great video content with limited resources. ',
  23             "uploader": "viddler",
  24             'timestamp': 1335371429,
  25             'upload_date': '20120425',
  26             "duration": 100.89,
  27             'thumbnail': 're:^https?://.*\.jpg$',
  28             'view_count': int,
  29             'categories': ['video content', 'high quality video', 'video made easy', 'how to produce video with limited resources', 'viddler'],
  30         }
  31     }, {
  32         "url": "http://www.viddler.com/v/4d03aad9/",
  33         "file": "4d03aad9.mp4",
  34         "md5": "faa71fbf70c0bee7ab93076fd007f4b0",
  35         "info_dict": {
  36             'upload_date': '20150126',
  37             'uploader': 'deadspin',
  38             'id': '4d03aad9',
  39             'timestamp': 1422285291,
  40             'title': 'WALL-TO-GORTAT',
  41         }
  42     }, {
  43         "url": "http://www.viddler.com/player/221ebbbd/0/",
  44         "file": "221ebbbd.mp4",
  45         "md5": "0defa2bd0ea613d14a6e9bd1db6be326",
  46         "info_dict": {
  47             'upload_date': '20140929',
  48             'uploader': 'BCLETeens',
  49             'id': '221ebbbd',
  50             'timestamp': 1411997190,
  51             'title': 'LETeens-Grammar-snack-third-conditional',
  52             'description': ' '
  53         }
  54     }]
  55
  56     def _real_extract(self, url):
  57         video_id = self._match_id(url)
  58
  59         json_url = (
  60             'http://api.viddler.com/api/v2/viddler.videos.getPlaybackDetails.json?video_id=%s&key=v0vhrt7bg2xq1vyxhkct' %
  61             video_id)
  62         headers = {'Referer': 'http://static.cdn-ec.viddler.com/js/arpeggio/v2/embed.html'}
  63         request = compat_urllib_request.Request(json_url, None, headers)
  64         data = self._download_json(request, video_id)['video']
  65
  66         formats = []
  67         for filed in data['files']:
  68             if filed.get('status', 'ready') != 'ready':
  69                 continue
  70             f = {
  71                 'format_id': filed['profile_id'],
  72                 'format_note': filed['profile_name'],
  73                 'url': self._proto_relative_url(filed['url']),
  74                 'width': int_or_none(filed.get('width')),
  75                 'height': int_or_none(filed.get('height')),
  76                 'filesize': int_or_none(filed.get('size')),
  77                 'ext': filed.get('ext'),
  78                 'source_preference': -1,
  79             }
  80             formats.append(f)
  81
  82             if filed.get('cdn_url'):
  83                 f = f.copy()
  84                 f['url'] = self._proto_relative_url(filed['cdn_url'], 'http:')
  85                 f['format_id'] = filed['profile_id'] + '-cdn'
  86                 f['source_preference'] = 1
  87                 formats.append(f)
  88
  89             if filed.get('html5_video_source'):
  90                 f = f.copy()
  91                 f['url'] = self._proto_relative_url(
  92                     filed['html5_video_source'])
  93                 f['format_id'] = filed['profile_id'] + '-html5'
  94                 f['source_preference'] = 0
  95                 formats.append(f)
  96         self._sort_formats(formats)
  97
  98         categories = [
  99             t.get('text') for t in data.get('tags', []) if 'text' in t]
 100
 101         return {
 102             '_type': 'video',
 103             'id': video_id,
 104             'title': data['title'],
 105             'formats': formats,
 106             'description': data.get('description'),
 107             'timestamp': int_or_none(data.get('upload_time')),
 108             'thumbnail': self._proto_relative_url(data.get('thumbnail_url')),
 109             'uploader': data.get('author'),
 110             'duration': float_or_none(data.get('length')),
 111             'view_count': int_or_none(data.get('view_count')),
 112             'categories': categories,
 113         }