Browse Source

[bbccouk] Switch to new JSON playlist format (Closes #4588)

totalwebcasting
Sergey M․ 10 years ago
parent
commit
ae6986fb89
1 changed files with 68 additions and 27 deletions
  1. +68
    -27
      youtube_dl/extractor/bbccouk.py

+ 68
- 27
youtube_dl/extractor/bbccouk.py View File

@ -71,7 +71,20 @@ class BBCCoUkIE(SubtitlesInfoExtractor):
'skip_download': True, 'skip_download': True,
}, },
'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only', 'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only',
},
}, {
'url': 'http://www.bbc.co.uk/programmes/b04v20dw',
'info_dict': {
'id': 'b04v209v',
'ext': 'flv',
'title': 'Pete Tong, The Essential New Tune Special',
'description': "Pete has a very special mix - all of 2014's Essential New Tunes!",
'duration': 10800,
},
'params': {
# rtmp download
'skip_download': True,
}
}
] ]
def _extract_asx_playlist(self, connection, programme_id): def _extract_asx_playlist(self, connection, programme_id):
@ -203,6 +216,59 @@ class BBCCoUkIE(SubtitlesInfoExtractor):
return formats, subtitles return formats, subtitles
def _download_playlist(self, playlist_id):
try:
playlist = self._download_json(
'http://www.bbc.co.uk/programmes/%s/playlist.json' % playlist_id,
playlist_id, 'Downloading playlist JSON')
version = playlist.get('defaultAvailableVersion')
if version:
smp_config = version['smpConfig']
title = smp_config['title']
description = smp_config['summary']
for item in smp_config['items']:
kind = item['kind']
if kind != 'programme' and kind != 'radioProgramme':
continue
programme_id = item.get('vpid')
duration = int(item.get('duration'))
formats, subtitles = self._download_media_selector(programme_id)
return programme_id, title, description, duration, formats, subtitles
except ExtractorError as ee:
if not isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404:
raise
# fallback to legacy playlist
playlist = self._download_xml(
'http://www.bbc.co.uk/iplayer/playlist/%s' % playlist_id,
playlist_id, 'Downloading legacy playlist XML')
no_items = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}noItems')
if no_items is not None:
reason = no_items.get('reason')
if reason == 'preAvailability':
msg = 'Episode %s is not yet available' % playlist_id
elif reason == 'postAvailability':
msg = 'Episode %s is no longer available' % playlist_id
elif reason == 'noMedia':
msg = 'Episode %s is not currently available' % playlist_id
else:
msg = 'Episode %s is not available: %s' % (playlist_id, reason)
raise ExtractorError(msg, expected=True)
for item in self._extract_items(playlist):
kind = item.get('kind')
if kind != 'programme' and kind != 'radioProgramme':
continue
title = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}title').text
description = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}summary').text
programme_id = item.get('identifier')
duration = int(item.get('duration'))
formats, subtitles = self._download_media_selector(programme_id)
return programme_id, title, description, duration, formats, subtitles
def _real_extract(self, url): def _real_extract(self, url):
group_id = self._match_id(url) group_id = self._match_id(url)
@ -219,32 +285,7 @@ class BBCCoUkIE(SubtitlesInfoExtractor):
duration = player['duration'] duration = player['duration']
formats, subtitles = self._download_media_selector(programme_id) formats, subtitles = self._download_media_selector(programme_id)
else: else:
playlist = self._download_xml(
'http://www.bbc.co.uk/iplayer/playlist/%s' % group_id,
group_id, 'Downloading playlist XML')
no_items = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}noItems')
if no_items is not None:
reason = no_items.get('reason')
if reason == 'preAvailability':
msg = 'Episode %s is not yet available' % group_id
elif reason == 'postAvailability':
msg = 'Episode %s is no longer available' % group_id
elif reason == 'noMedia':
msg = 'Episode %s is not currently available' % group_id
else:
msg = 'Episode %s is not available: %s' % (group_id, reason)
raise ExtractorError(msg, expected=True)
for item in self._extract_items(playlist):
kind = item.get('kind')
if kind != 'programme' and kind != 'radioProgramme':
continue
title = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}title').text
description = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}summary').text
programme_id = item.get('identifier')
duration = int(item.get('duration'))
formats, subtitles = self._download_media_selector(programme_id)
programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id)
if self._downloader.params.get('listsubtitles', False): if self._downloader.params.get('listsubtitles', False):
self._list_available_subtitles(programme_id, subtitles) self._list_available_subtitles(programme_id, subtitles)


Loading…
Cancel
Save