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:
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):
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
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:
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
'title': 'Russia stages massive WW2 parade despite Western boycott',
},
'playlist_count': 2,
- },{
+ }, {
'url': 'http://www.bbc.com/news/business-28299555',
'info_dict': {
'id': 'business-28299555',
'title': 'Farnborough Airshow: Video highlights',
},
'playlist_count': 9,
- },{
+ }, {
'url': 'http://www.bbc.com/news/world-europe-32041533',
'note': 'Video',
'info_dict': {
'title': 'Aerial footage showed the site of the crash in the Alps - courtesy BFM TV',
'description': 'Germanwings plane crash site in aerial video - Aerial footage showed the site of the crash in the Alps - courtesy BFM TV',
'duration': 47,
+ 'upload_date': '20150324',
+ 'uploader': 'BBC News',
},
'params': {
'skip_download': True,
}
- },{
+ }, {
'url': 'http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu',
'note': 'Video',
'info_dict': {
'id': 'NA',
'ext': 'mp4',
- 'title': 'YPG - Tel Abyad..n tamam. kontrol.m.zde',
+ 'title': 'YPG: Tel Abyad\'\u0131n tamam\u0131 kontrol\xfcm\xfczde',
+ 'description': 'YPG: Tel Abyad\'\u0131n tamam\u0131 kontrol\xfcm\xfczde',
'duration': 47,
+ 'upload_date': '20150615',
+ 'uploader': 'BBC News',
},
'params': {
'skip_download': True,
}
- },{
+ }, {
'url': 'http://www.bbc.com/mundo/video_fotos/2015/06/150619_video_honduras_militares_hospitales_corrupcion_aw',
'note': 'Video',
'info_dict': {
'id': '39275083',
'ext': 'mp4',
- 'title': 'Honduras militariza sus hospitales por nuevo esc.ndalo de corrupci.n',
+ 'title': 'Honduras militariza sus hospitales por nuevo esc\xe1ndalo de corrupci\xf3n',
+ 'description': 'Honduras militariza sus hospitales por nuevo esc\xe1ndalo de corrupci\xf3n',
'duration': 87,
+ 'upload_date': '20150619',
+ 'uploader': 'BBC News',
},
'params': {
'skip_download': True,
pubdate = self._html_search_regex(r'"datePublished":\s*"(\d+-\d+-\d+)', webpage, 'date', default=None)
if pubdate:
- pubdate = pubdate.replace('-','')
+ pubdate = pubdate.replace('-', '')
ret = []
jsent = []
# works with bbc.com/news/something-something-123456 articles
jsent = map(
- lambda m: self._parse_json(m,list_id),
- re.findall(r"data-media-meta='({[^']+})'", webpage)
+ lambda m: self._parse_json(m, list_id),
+ re.findall(r"data-media-meta='({[^']+})'", webpage)
)
if len(jsent) == 0:
- # http://www.bbc.com/news/video_and_audio/international
- # and single-video articles
- masset = self._html_search_regex(r'mediaAssetPage\.init\(\s*({.+?}), "/', webpage, 'mediaassets', default=None)
- if masset:
- jmasset = self._parse_json(masset,list_id)
- for key, val in jmasset.get('videos',{}).items():
- for skey, sval in val.items():
- sval['id'] = skey
- jsent.append(sval)
+ # http://www.bbc.com/news/video_and_audio/international
+ # and single-video articles
+ masset = self._html_search_regex(r'mediaAssetPage\.init\(\s*({.+?}), "/', webpage, 'mediaassets', default=None)
+ if masset:
+ jmasset = self._parse_json(masset, list_id)
+ for key, val in jmasset.get('videos', {}).items():
+ for skey, sval in val.items():
+ sval['id'] = skey
+ jsent.append(sval)
if len(jsent) == 0:
- # stubbornly generic extractor for {json with "image":{allvideoshavethis},etc}
- # in http://www.bbc.com/news/video_and_audio/international
- # prone to breaking if entries have sourceFiles list
- jsent = map(
- lambda m: self._parse_json(m,list_id),
- re.findall(r"({[^{}]+image\":{[^}]+}[^}]+})", webpage)
- )
+ # stubbornly generic extractor for {json with "image":{allvideoshavethis},etc}
+ # in http://www.bbc.com/news/video_and_audio/international
+ # prone to breaking if entries have sourceFiles list
+ jsent = map(
+ lambda m: self._parse_json(m, list_id),
+ re.findall(r"({[^{}]+image\":{[^}]+}[^}]+})", webpage)
+ )
if len(jsent) == 0:
- raise ExtractorError('No video found', expected=True)
+ raise ExtractorError('No video found', expected=True)
for jent in jsent:
programme_id = jent.get('externalId')
xml_url = jent.get('href')
- title = jent.get('caption',list_title)
+ title = jent.get('caption', '')
+ if title == '':
+ title = list_title
duration = parse_duration(jent.get('duration'))
- description = list_title + ' - ' + jent.get('caption','')
+ description = list_title
+ if jent.get('caption', '') != '':
+ description += ' - ' + jent.get('caption')
thumbnail = None
- if jent.has_key('image'):
- thumbnail=jent['image'].get('href')
+ if jent.get('image') is not None:
+ thumbnail = jent['image'].get('href')
formats = []
subtitles = []
if programme_id:
- formats, subtitles = self._download_media_selector(programme_id)
- elif jent.has_key('sourceFiles'):
- # mediaselector not used at
- # http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu
- for key, val in jent['sourceFiles'].items():
- formats.append( {
- 'ext': val.get('encoding'),
- 'url': val.get('url'),
- 'filesize': int(val.get('filesize')),
- 'format_id': key
- } )
+ formats, subtitles = self._download_media_selector(programme_id)
+ elif jent.get('sourceFiles') is not None:
+ # mediaselector not used at
+ # http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu
+ for key, val in jent['sourceFiles'].items():
+ formats.append({
+ 'ext': val.get('encoding'),
+ 'url': val.get('url'),
+ 'filesize': int(val.get('filesize')),
+ 'format_id': key
+ })
elif xml_url:
- # Cheap fallback
- # http://playlists.bbc.co.uk/news/(list_id)[ABC..]/playlist.sxml
- xml = self._download_webpage(xml_url, programme_id, 'Downloading playlist.sxml for externalId (fallback)')
- programme_id = self._search_regex(r'<mediator [^>]*identifier="(.+?)"', xml, 'playlist.sxml (externalId fallback)')
- formats, subtitles = self._download_media_selector(programme_id)
+ # Cheap fallback
+ # http://playlists.bbc.co.uk/news/(list_id)[ABC..]/playlist.sxml
+ xml = self._download_webpage(xml_url, programme_id, 'Downloading playlist.sxml for externalId (fallback)')
+ programme_id = self._search_regex(r'<mediator [^>]*identifier="(.+?)"', xml, 'playlist.sxml (externalId fallback)')
+ formats, subtitles = self._download_media_selector(programme_id)
if len(formats) == 0:
- raise ExtractorError('unsupported json media entry.\n '+str(jent)+'\n')
-
+ raise ExtractorError('unsupported json media entry.\n ' + str(jent) + '\n')
+
self._sort_formats(formats)
- ret.append( {
- 'id': jent.get('programme_id',jent.get('id')),
+ id = jent.get('id') if programme_id is None else programme_id
+ if id is None:
+ id = 'NA'
+
+ ret.append({
+ 'id': id,
'uploader': 'BBC News',
'upload_date': pubdate,
'title': title,
'duration': duration,
'formats': formats,
'subtitles': subtitles,
- } )
+ })
if len(ret) > 0:
- return self.playlist_result(ret, list_id, list_title)
+ return self.playlist_result(ret, list_id, list_title)
raise ExtractorError('No video found', expected=True)
projects / youtube-dl / blobdiff