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

   1 import re
   2 import json
   3 import xml.etree.ElementTree
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     compat_urlparse,
   8     compat_urllib_parse,
   9     determine_ext,
  10     unified_strdate,
  11 )
  12
  13
  14 class NHLIE(InfoExtractor):
  15     IE_NAME = u'nhl.com'
  16     _VALID_URL = r'https?://video(?P<team>\.[^.]*)?\.nhl\.com/videocenter/console\?.*?(?<=[?&])id=(?P<id>\d+)'
  17
  18     _TEST = {
  19         u'url': u'http://video.canucks.nhl.com/videocenter/console?catid=6?id=453614',
  20         u'file': u'453614.mp4',
  21         u'info_dict': {
  22             u'title': u'Quick clip: Weise 4-3 goal vs Flames',
  23             u'description': u'Dale Weise scores his first of the season to put the Canucks up 4-3.',
  24             u'duration': 18,
  25             u'upload_date': u'20131006',
  26         },
  27     }
  28
  29     def _real_extract(self, url):
  30         mobj = re.match(self._VALID_URL, url)
  31         video_id = mobj.group('id')
  32         json_url = 'http://video.nhl.com/videocenter/servlets/playlist?ids=%s&format=json' % video_id
  33         info_json = self._download_webpage(json_url, video_id,
  34             u'Downloading info json')
  35         info_json = info_json.replace('\\\'', '\'')
  36         info = json.loads(info_json)[0]
  37
  38         initial_video_url = info['publishPoint']
  39         data = compat_urllib_parse.urlencode({
  40             'type': 'fvod',
  41             'path': initial_video_url.replace('.mp4', '_sd.mp4'),
  42         })
  43         path_url = 'http://video.nhl.com/videocenter/servlets/encryptvideopath?' + data
  44         path_response = self._download_webpage(path_url, video_id,
  45             u'Downloading final video url')
  46         path_doc = xml.etree.ElementTree.fromstring(path_response)
  47         video_url = path_doc.find('path').text
  48
  49         join = compat_urlparse.urljoin
  50         return {
  51             'id': video_id,
  52             'title': info['name'],
  53             'url': video_url,
  54             'ext': determine_ext(video_url),
  55             'description': info['description'],
  56             'duration': int(info['duration']),
  57             'thumbnail': join(join(video_url, '/u/'), info['bigImage']),
  58             'upload_date': unified_strdate(info['releaseDate'].split('.')[0]),
  59         }