bbc.py: correct syntax

This commit is contained in:
fnord 2015-07-17 02:47:02 -05:00
parent 36da48798a
commit a3bfddfa5e

View file

@ -397,14 +397,14 @@ class BBCNewsIE(BBCCoUkIE):
'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': {
@ -419,7 +419,7 @@ class BBCNewsIE(BBCCoUkIE):
'params': {
'skip_download': True,
}
},{
}, {
'url': 'http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu',
'note': 'Video',
'info_dict': {
@ -434,7 +434,7 @@ class BBCNewsIE(BBCCoUkIE):
'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': {
@ -459,14 +459,14 @@ def _real_extract(self, url):
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),
lambda m: self._parse_json(m, list_id),
re.findall(r"data-media-meta='({[^']+})'", webpage)
)
@ -475,8 +475,8 @@ def _real_extract(self, url):
# 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():
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)
@ -486,7 +486,7 @@ def _real_extract(self, url):
# 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),
lambda m: self._parse_json(m, list_id),
re.findall(r"({[^{}]+image\":{[^}]+}[^}]+})", webpage)
)
@ -497,7 +497,7 @@ def _real_extract(self, url):
programme_id = jent.get('externalId')
xml_url = jent.get('href')
title = jent.get('caption','')
title = jent.get('caption', '')
if title == '':
title = list_title
@ -506,24 +506,24 @@ def _real_extract(self, url):
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'):
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( {
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
@ -532,15 +532,15 @@ def _real_extract(self, url):
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)
id = jent.get('id') if programme_id == None else programme_id
if id == None:
id = jent.get('id') if programme_id is None else programme_id
if id is None:
id = 'NA'
ret.append( {
ret.append({
'id': id,
'uploader': 'BBC News',
'upload_date': pubdate,
@ -550,7 +550,7 @@ def _real_extract(self, url):
'duration': duration,
'formats': formats,
'subtitles': subtitles,
} )
})
if len(ret) > 0:
return self.playlist_result(ret, list_id, list_title)