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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import json
   5 import re
   6
   7 from .common import InfoExtractor
   8 from ..utils import (
   9     HEADRequest,
  10     unified_strdate,
  11 )
  12
  13
  14 class ORFIE(InfoExtractor):
  15     _VALID_URL = r'https?://tvthek\.orf\.at/(?:programs/.+?/episodes|topics/.+?|program/[^/]+)/(?P<id>\d+)'
  16
  17     _TEST = {
  18         'url': 'http://tvthek.orf.at/program/matinee-Was-Sie-schon-immer-ueber-Klassik-wissen-wollten/7317210/Was-Sie-schon-immer-ueber-Klassik-wissen-wollten/7319746/Was-Sie-schon-immer-ueber-Klassik-wissen-wollten/7319747',
  19         'file': '7319747.mp4',
  20         'md5': 'bd803c5d8c32d3c64a0ea4b4eeddf375',
  21         'info_dict': {
  22             'title': 'Was Sie schon immer über Klassik wissen wollten',
  23             'description': 'md5:0ddf0d5f0060bd53f744edaa5c2e04a4',
  24             'duration': 3508,
  25             'upload_date': '20140105',
  26         },
  27         'skip': 'Blocked outside of Austria',
  28     }
  29
  30     def _real_extract(self, url):
  31         mobj = re.match(self._VALID_URL, url)
  32         playlist_id = mobj.group('id')
  33         webpage = self._download_webpage(url, playlist_id)
  34
  35         data_json = self._search_regex(
  36             r'initializeAdworx\((.+?)\);\n', webpage, 'video info')
  37         all_data = json.loads(data_json)
  38         sdata = all_data[0]['values']['segments']
  39
  40         def quality_to_int(s):
  41             m = re.search('([0-9]+)', s)
  42             if m is None:
  43                 return -1
  44             return int(m.group(1))
  45
  46         entries = []
  47         for sd in sdata:
  48             video_id = sd['id']
  49             formats = [{
  50                 'preference': -10 if fd['delivery'] == 'hls' else None,
  51                 'format_id': '%s-%s-%s' % (
  52                     fd['delivery'], fd['quality'], fd['quality_string']),
  53                 'url': fd['src'],
  54                 'protocol': fd['protocol'],
  55                 'quality': quality_to_int(fd['quality']),
  56             } for fd in sd['playlist_item_array']['sources']]
  57
  58             # Check for geoblocking.
  59             # There is a property is_geoprotection, but that's always false
  60             geo_str = sd.get('geoprotection_string')
  61             if geo_str:
  62                 try:
  63                     http_url = next(
  64                         f['url']
  65                         for f in formats
  66                         if re.match(r'^https?://.*\.mp4$', f['url']))
  67                 except StopIteration:
  68                     pass
  69                 else:
  70                     req = HEADRequest(http_url)
  71                     self._request_webpage(
  72                         req, video_id,
  73                         note='Testing for geoblocking',
  74                         errnote=((
  75                             'This video seems to be blocked outside of %s. '
  76                             'You may want to try the streaming-* formats.')
  77                             % geo_str),
  78                         fatal=False)
  79
  80             self._sort_formats(formats)
  81
  82             upload_date = unified_strdate(sd['created_date'])
  83             entries.append({
  84                 '_type': 'video',
  85                 'id': video_id,
  86                 'title': sd['header'],
  87                 'formats': formats,
  88                 'description': sd.get('description'),
  89                 'duration': int(sd['duration_in_seconds']),
  90                 'upload_date': upload_date,
  91                 'thumbnail': sd.get('image_full_url'),
  92             })
  93
  94         return {
  95             '_type': 'playlist',
  96             'entries': entries,
  97             'id': playlist_id,
  98         }