MarcoBuster/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-01 00:52:58 +01:00
Code Issues Projects Releases Wiki Activity

bbc.py: correct syntax

Browse Source
This commit is contained in:
fnord 2015-07-17 02:47:02 -05:00
parent 36da48798a
commit a3bfddfa5e
1 changed files with 53 additions and 53 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

104
youtube_dl/extractor/bbc.py
View File

@ -397,14 +397,14 @@ class BBCNewsIE(BBCCoUkIE):
'title': 'Russia stages massive WW2 parade despite Western boycott', 'title': 'Russia stages massive WW2 parade despite Western boycott',
}, },
'playlist_count': 2, 'playlist_count': 2,
},{ }, {
'url': 'http://www.bbc.com/news/business-28299555', 'url': 'http://www.bbc.com/news/business-28299555',
'info_dict': { 'info_dict': {
'id': 'business-28299555', 'id': 'business-28299555',
'title': 'Farnborough Airshow: Video highlights', 'title': 'Farnborough Airshow: Video highlights',
}, },
'playlist_count': 9, 'playlist_count': 9,
},{ }, {
'url': 'http://www.bbc.com/news/world-europe-32041533', 'url': 'http://www.bbc.com/news/world-europe-32041533',
'note': 'Video', 'note': 'Video',
'info_dict': { 'info_dict': {
@ -419,7 +419,7 @@ class BBCNewsIE(BBCCoUkIE):
'params': { 'params': {
'skip_download': True, 'skip_download': True,
} }
},{ }, {
'url': 'http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu', 'url': 'http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu',
'note': 'Video', 'note': 'Video',
'info_dict': { 'info_dict': {
@ -434,7 +434,7 @@ class BBCNewsIE(BBCCoUkIE):
'params': { 'params': {
'skip_download': True, 'skip_download': True,
} }
},{ }, {
'url': 'http://www.bbc.com/mundo/video_fotos/2015/06/150619_video_honduras_militares_hospitales_corrupcion_aw', 'url': 'http://www.bbc.com/mundo/video_fotos/2015/06/150619_video_honduras_militares_hospitales_corrupcion_aw',
'note': 'Video', 'note': 'Video',
'info_dict': { 'info_dict': {
@ -459,88 +459,88 @@ def _real_extract(self, url):
pubdate = self._html_search_regex(r'"datePublished":\s*"(\d+-\d+-\d+)', webpage, 'date', default=None) pubdate = self._html_search_regex(r'"datePublished":\s*"(\d+-\d+-\d+)', webpage, 'date', default=None)
if pubdate: if pubdate:
pubdate = pubdate.replace('-','') pubdate = pubdate.replace('-', '')
ret = [] ret = []
jsent = [] jsent = []
# works with bbc.com/news/something-something-123456 articles # works with bbc.com/news/something-something-123456 articles
jsent = map( jsent = map(
lambda m: self._parse_json(m,list_id), lambda m: self._parse_json(m, list_id),
re.findall(r"data-media-meta='({[^']+})'", webpage) re.findall(r"data-media-meta='({[^']+})'", webpage)
) )
if len(jsent) == 0: if len(jsent) == 0:
# http://www.bbc.com/news/video_and_audio/international # http://www.bbc.com/news/video_and_audio/international
# and single-video articles # and single-video articles
masset = self._html_search_regex(r'mediaAssetPage\.init\(\s*({.+?}), "/', webpage, 'mediaassets', default=None) masset = self._html_search_regex(r'mediaAssetPage\.init\(\s*({.+?}), "/', webpage, 'mediaassets', default=None)
if masset: if masset:
jmasset = self._parse_json(masset,list_id) jmasset = self._parse_json(masset, list_id)
for key, val in jmasset.get('videos',{}).items(): for key, val in jmasset.get('videos', {}).items():
for skey, sval in val.items(): for skey, sval in val.items():
sval['id'] = skey sval['id'] = skey
jsent.append(sval) jsent.append(sval)
if len(jsent) == 0: if len(jsent) == 0:
# stubbornly generic extractor for {json with "image":{allvideoshavethis},etc} # stubbornly generic extractor for {json with "image":{allvideoshavethis},etc}
# in http://www.bbc.com/news/video_and_audio/international # in http://www.bbc.com/news/video_and_audio/international
# prone to breaking if entries have sourceFiles list # prone to breaking if entries have sourceFiles list
jsent = map( jsent = map(
lambda m: self._parse_json(m,list_id), lambda m: self._parse_json(m, list_id),
re.findall(r"({[^{}]+image\":{[^}]+}[^}]+})", webpage) re.findall(r"({[^{}]+image\":{[^}]+}[^}]+})", webpage)
) )
if len(jsent) == 0: if len(jsent) == 0:
raise ExtractorError('No video found', expected=True) raise ExtractorError('No video found', expected=True)
for jent in jsent: for jent in jsent:
programme_id = jent.get('externalId') programme_id = jent.get('externalId')
xml_url = jent.get('href') xml_url = jent.get('href')
title = jent.get('caption','') title = jent.get('caption', '')
if title == '': if title == '':
title = list_title title = list_title
duration = parse_duration(jent.get('duration')) duration = parse_duration(jent.get('duration'))
description = list_title description = list_title
if jent.get('caption', '') != '': if jent.get('caption', '') != '':
description += ' - ' + jent.get('caption') description += ' - ' + jent.get('caption')
thumbnail = None thumbnail = None
if jent.has_key('image'): if jent.get('image') is not None:
thumbnail=jent['image'].get('href') thumbnail = jent['image'].get('href')
formats = [] formats = []
subtitles = [] subtitles = []
if programme_id: if programme_id:
formats, subtitles = self._download_media_selector(programme_id) formats, subtitles = self._download_media_selector(programme_id)
elif jent.has_key('sourceFiles'): elif jent.get('sourceFiles') is not None:
# mediaselector not used at # mediaselector not used at
# http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu # http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu
for key, val in jent['sourceFiles'].items(): for key, val in jent['sourceFiles'].items():
formats.append( { formats.append({
'ext': val.get('encoding'), 'ext': val.get('encoding'),
'url': val.get('url'), 'url': val.get('url'),
'filesize': int(val.get('filesize')), 'filesize': int(val.get('filesize')),
'format_id': key 'format_id': key
} ) })
elif xml_url: elif xml_url:
# Cheap fallback # Cheap fallback
# http://playlists.bbc.co.uk/news/(list_id)[ABC..]/playlist.sxml # 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)') 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)') programme_id = self._search_regex(r'<mediator [^>]*identifier="(.+?)"', xml, 'playlist.sxml (externalId fallback)')
formats, subtitles = self._download_media_selector(programme_id) formats, subtitles = self._download_media_selector(programme_id)
if len(formats) == 0: 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) self._sort_formats(formats)
id = jent.get('id') if programme_id == None else programme_id id = jent.get('id') if programme_id is None else programme_id
if id == None: if id is None:
id = 'NA' id = 'NA'
ret.append( { ret.append({
'id': id, 'id': id,
'uploader': 'BBC News', 'uploader': 'BBC News',
'upload_date': pubdate, 'upload_date': pubdate,
@ -550,8 +550,8 @@ def _real_extract(self, url):
'duration': duration, 'duration': duration,
'formats': formats, 'formats': formats,
'subtitles': subtitles, 'subtitles': subtitles,
} ) })
if len(ret) > 0: 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) raise ExtractorError('No video found', expected=True)