youtube_dl/extractor/viddler.py

   1 import json
   2 import re
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     determine_ext,
   7 )
   8
   9
  10 class ViddlerIE(InfoExtractor):
  11     _VALID_URL = r'(?P<domain>https?://(?:www\.)?viddler.com)/(?:v|embed|player)/(?P<id>[a-z0-9]+)'
  12     _TEST = {
  13         u"url": u"http://www.viddler.com/v/43903784",
  14         u'file': u'43903784.mp4',
  15         u'md5': u'fbbaedf7813e514eb7ca30410f439ac9',
  16         u'info_dict': {
  17             u"title": u"Video Made Easy",
  18             u"uploader": u"viddler",
  19             u"duration": 100.89,
  20         }
  21     }
  22
  23     def _real_extract(self, url):
  24         mobj = re.match(self._VALID_URL, url)
  25         video_id = mobj.group('id')
  26
  27         embed_url = mobj.group('domain') + u'/embed/' + video_id
  28         webpage = self._download_webpage(embed_url, video_id)
  29
  30         video_sources_code = self._search_regex(
  31             r"(?ms)sources\s*:\s*(\{.*?\})", webpage, u'video URLs')
  32         video_sources = json.loads(video_sources_code.replace("'", '"'))
  33
  34         formats = [{
  35             'url': video_url,
  36             'format': format_id,
  37         } for video_url, format_id in video_sources.items()]
  38
  39         title = self._html_search_regex(
  40             r"title\s*:\s*'([^']*)'", webpage, u'title')
  41         uploader = self._html_search_regex(
  42             r"authorName\s*:\s*'([^']*)'", webpage, u'uploader', fatal=False)
  43         duration_s = self._html_search_regex(
  44             r"duration\s*:\s*([0-9.]*)", webpage, u'duration', fatal=False)
  45         duration = float(duration_s) if duration_s else None
  46         thumbnail = self._html_search_regex(
  47             r"thumbnail\s*:\s*'([^']*)'",
  48             webpage, u'thumbnail', fatal=False)
  49
  50         info = {
  51             '_type': 'video',
  52             'id': video_id,
  53             'title': title,
  54             'thumbnail': thumbnail,
  55             'uploader': uploader,
  56             'duration': duration,
  57             'formats': formats,
  58         }
  59
  60         # TODO: Remove when #980 has been merged
  61         info['formats'][-1]['ext'] = determine_ext(info['formats'][-1]['url'])
  62         info.update(info['formats'][-1])
  63
  64         return info