[bbccouk] Fix extraction (#4104, #4214)

This commit is contained in:
Sergey M․ 2014-11-30 22:37:56 +06:00
parent 283ac8d592
commit c056efa2e3
1 changed files with 81 additions and 41 deletions

View File

@ -1,9 +1,11 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re import re
import xml.etree.ElementTree
from .subtitles import SubtitlesInfoExtractor from .subtitles import SubtitlesInfoExtractor
from ..utils import ExtractorError from ..utils import ExtractorError
from ..compat import compat_HTTPError
class BBCCoUkIE(SubtitlesInfoExtractor): class BBCCoUkIE(SubtitlesInfoExtractor):
@ -55,7 +57,22 @@ 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/iplayer/episode/p026c7jt/tomorrows-worlds-the-unearthly-history-of-science-fiction-2-invasion',
'info_dict': {
'id': 'b03k3pb7',
'ext': 'flv',
'title': "Tomorrow's Worlds: The Unearthly History of Science Fiction",
'description': '2. Invasion',
'duration': 3600,
},
'params': {
# rtmp download
'skip_download': True,
},
'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only',
},
] ]
def _extract_asx_playlist(self, connection, programme_id): def _extract_asx_playlist(self, connection, programme_id):
@ -102,6 +119,10 @@ class BBCCoUkIE(SubtitlesInfoExtractor):
return playlist.findall('./{http://bbc.co.uk/2008/emp/playlist}item') return playlist.findall('./{http://bbc.co.uk/2008/emp/playlist}item')
def _extract_medias(self, media_selection): def _extract_medias(self, media_selection):
error = media_selection.find('./{http://bbc.co.uk/2008/mp/mediaselection}error')
if error is not None:
raise ExtractorError(
'%s returned error: %s' % (self.IE_NAME, error.get('id')), expected=True)
return media_selection.findall('./{http://bbc.co.uk/2008/mp/mediaselection}media') return media_selection.findall('./{http://bbc.co.uk/2008/mp/mediaselection}media')
def _extract_connections(self, media): def _extract_connections(self, media):
@ -158,54 +179,73 @@ class BBCCoUkIE(SubtitlesInfoExtractor):
subtitles[lang] = srt subtitles[lang] = srt
return subtitles return subtitles
def _real_extract(self, url): def _download_media_selector(self, programme_id):
mobj = re.match(self._VALID_URL, url) try:
group_id = mobj.group('id') media_selection = self._download_xml(
'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s' % programme_id,
webpage = self._download_webpage(url, group_id, 'Downloading video page') programme_id, 'Downloading media selection XML')
if re.search(r'id="emp-error" class="notinuk">', webpage): except ExtractorError as ee:
raise ExtractorError('Currently BBC iPlayer TV programmes are available to play in the UK only', if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
expected=True) media_selection = xml.etree.ElementTree.fromstring(ee.cause.read().encode('utf-8'))
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
else: else:
msg = 'Episode %s is not available: %s' % (group_id, reason) raise
raise ExtractorError(msg, expected=True)
formats = [] formats = []
subtitles = None subtitles = None
for item in self._extract_items(playlist): for media in self._extract_medias(media_selection):
kind = item.get('kind') kind = media.get('kind')
if kind != 'programme' and kind != 'radioProgramme': if kind == 'audio':
continue formats.extend(self._extract_audio(media, programme_id))
title = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}title').text elif kind == 'video':
description = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}summary').text formats.extend(self._extract_video(media, programme_id))
elif kind == 'captions':
subtitles = self._extract_captions(media, programme_id)
programme_id = item.get('identifier') return formats, subtitles
duration = int(item.get('duration'))
media_selection = self._download_xml( def _real_extract(self, url):
'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s' % programme_id, group_id = self._match_id(url)
programme_id, 'Downloading media selection XML')
for media in self._extract_medias(media_selection): webpage = self._download_webpage(url, group_id, 'Downloading video page')
kind = media.get('kind')
if kind == 'audio': programme_id = self._search_regex(
formats.extend(self._extract_audio(media, programme_id)) r'"vpid"\s*:\s*"([\da-z]{8})"', webpage, 'vpid', fatal=False)
elif kind == 'video': if programme_id:
formats.extend(self._extract_video(media, programme_id)) player = self._download_json(
elif kind == 'captions': 'http://www.bbc.co.uk/iplayer/episode/%s.json' % group_id,
subtitles = self._extract_captions(media, programme_id) group_id)['jsConf']['player']
title = player['title']
description = player['subtitle']
duration = player['duration']
formats, subtitles = self._download_media_selector(programme_id)
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)
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)