diff options
Diffstat (limited to 'youtube_dl/extractor/bbccouk.py')
| -rw-r--r-- | youtube_dl/extractor/bbccouk.py | 47 |
1 files changed, 23 insertions, 24 deletions
diff --git a/youtube_dl/extractor/bbccouk.py b/youtube_dl/extractor/bbccouk.py index 249bc6bbd..b2e5f7418 100644 --- a/youtube_dl/extractor/bbccouk.py +++ b/youtube_dl/extractor/bbccouk.py @@ -130,6 +130,20 @@ class BBCCoUkIE(InfoExtractor): }, 'skip': 'geolocation', }, { + 'url': 'http://www.bbc.co.uk/iplayer/episode/b05zmgwn/royal-academy-summer-exhibition', + 'info_dict': { + 'id': 'b05zmgw1', + 'ext': 'flv', + 'description': 'Kirsty Wark and Morgan Quaintance visit the Royal Academy as it prepares for its annual artistic extravaganza, meeting people who have come together to make the show unique.', + 'title': 'Royal Academy Summer Exhibition', + 'duration': 3540, + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + 'skip': 'geolocation', + }, { 'url': 'http://www.bbc.co.uk/iplayer/playlist/p01dvks4', 'only_matching': True, }, { @@ -196,12 +210,12 @@ class BBCCoUkIE(InfoExtractor): def _extract_video(self, media, programme_id): formats = [] - vbr = int(media.get('bitrate')) + vbr = int_or_none(media.get('bitrate')) vcodec = media.get('encoding') service = media.get('service') - width = int(media.get('width')) - height = int(media.get('height')) - file_size = int(media.get('media_file_size')) + width = int_or_none(media.get('width')) + height = int_or_none(media.get('height')) + file_size = int_or_none(media.get('media_file_size')) for connection in self._extract_connections(media): conn_formats = self._extract_connection(connection, programme_id) for format in conn_formats: @@ -218,7 +232,7 @@ class BBCCoUkIE(InfoExtractor): def _extract_audio(self, media, programme_id): formats = [] - abr = int(media.get('bitrate')) + abr = int_or_none(media.get('bitrate')) acodec = media.get('encoding') service = media.get('service') for connection in self._extract_connections(media): @@ -237,26 +251,11 @@ class BBCCoUkIE(InfoExtractor): for connection in self._extract_connections(media): captions = self._download_xml(connection.get('href'), programme_id, 'Downloading captions') lang = captions.get('{http://www.w3.org/XML/1998/namespace}lang', 'en') - ps = captions.findall('./{0}body/{0}div/{0}p'.format('{http://www.w3.org/2006/10/ttaf1}')) - srt = '' - - def _extract_text(p): - if p.text is not None: - stripped_text = p.text.strip() - if stripped_text: - return stripped_text - return ' '.join(span.text.strip() for span in p.findall('{http://www.w3.org/2006/10/ttaf1}span')) - for pos, p in enumerate(ps): - srt += '%s\r\n%s --> %s\r\n%s\r\n\r\n' % (str(pos), p.get('begin'), p.get('end'), _extract_text(p)) subtitles[lang] = [ { 'url': connection.get('href'), 'ext': 'ttml', }, - { - 'data': srt, - 'ext': 'srt', - }, ] return subtitles @@ -267,7 +266,7 @@ class BBCCoUkIE(InfoExtractor): programme_id, 'Downloading media selection XML') except ExtractorError as ee: if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403: - media_selection = xml.etree.ElementTree.fromstring(ee.cause.read().encode('utf-8')) + media_selection = xml.etree.ElementTree.fromstring(ee.cause.read().decode('utf-8')) else: raise @@ -301,7 +300,7 @@ class BBCCoUkIE(InfoExtractor): if kind != 'programme' and kind != 'radioProgramme': continue programme_id = item.get('vpid') - duration = int(item.get('duration')) + duration = int_or_none(item.get('duration')) formats, subtitles = self._download_media_selector(programme_id) return programme_id, title, description, duration, formats, subtitles except ExtractorError as ee: @@ -333,7 +332,7 @@ class BBCCoUkIE(InfoExtractor): 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')) + duration = int_or_none(item.get('duration')) formats, subtitles = self._download_media_selector(programme_id) return programme_id, title, description, duration, formats, subtitles @@ -362,7 +361,7 @@ class BBCCoUkIE(InfoExtractor): formats, subtitles = self._download_media_selector(programme_id) title = self._og_search_title(webpage) description = self._search_regex( - r'<p class="medium-description">([^<]+)</p>', + r'<p class="[^"]*medium-description[^"]*">([^<]+)</p>', webpage, 'description', fatal=False) else: programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id) |