[srgssr] change the url chortcut, fix image extraction ,add a test and extract format id

This commit is contained in:
remitamine 2015-10-14 10:40:54 +01:00
parent 05ad5409b4
commit e09f58b3bc

View file

@ -12,7 +12,7 @@
class SRGSSRIE(InfoExtractor): class SRGSSRIE(InfoExtractor):
_VALID_URL = r'(?:https?://tp\.srgssr\.ch/p(?:/[^/]+)+\?urn=)?urn:(?P<bu>srf|rts|rsi|rtr|swi):(?:[^:]+:)?(?P<type>video|audio):(?P<id>[0-9a-f\-]{36}|\d+)' _VALID_URL = r'(?:https?://tp\.srgssr\.ch/p(?:/[^/]+)+\?urn=urn|srgssr):(?P<bu>srf|rts|rsi|rtr|swi):(?:[^:]+:)?(?P<type>video|audio):(?P<id>[0-9a-f\-]{36}|\d+)'
_ERRORS = { _ERRORS = {
'AGERATING12': 'To protect children under the age of 12, this video is only available between 8 p.m. and 6 a.m.', 'AGERATING12': 'To protect children under the age of 12, this video is only available between 8 p.m. and 6 a.m.',
@ -44,11 +44,12 @@ def _real_extract(self, url):
timestamp = parse_iso8601(created_date) timestamp = parse_iso8601(created_date)
thumbnails = [] thumbnails = []
for image in media_data['Image']['ImageRepresentations']['ImageRepresentation']: if 'Image' in media_data:
thumbnails.append({ for image in media_data['Image']['ImageRepresentations']['ImageRepresentation']:
'id': image.get('id'), thumbnails.append({
'url': image['url'], 'id': image.get('id'),
}) 'url': image['url'],
})
preference = qualities(['LQ', 'MQ', 'SD', 'HQ', 'HD']) preference = qualities(['LQ', 'MQ', 'SD', 'HQ', 'HD'])
formats = [] formats = []
@ -70,16 +71,17 @@ def _real_extract(self, url):
if asset_url.startswith('rtmp'): if asset_url.startswith('rtmp'):
ext = self._search_regex(r'([a-z0-9]+):[^/]+', asset_url, 'ext') ext = self._search_regex(r'([a-z0-9]+):[^/]+', asset_url, 'ext')
formats.append({ formats.append({
'format_id': asset['@quality'],
'url': asset_url, 'url': asset_url,
'preference': preference(asset['@quality']), 'preference': preference(asset['@quality']),
'ext': ext, 'ext': ext,
}) })
downloads = media_data.get('Downloads') if 'Downloads' in media_data:
if downloads: for source in media_data['Downloads']['Download']:
for source in downloads['Download']:
for asset in source['url']: for asset in source['url']:
formats.append({ formats.append({
'format_id': asset['@quality'],
'url': asset['text'], 'url': asset['text'],
'preference': preference(asset['@quality']) 'preference': preference(asset['@quality'])
}) })
@ -120,8 +122,21 @@ class SRGSSRPlayIE(InfoExtractor):
'description': 'md5:88604432b60d5a38787f152dec89cd56', 'description': 'md5:88604432b60d5a38787f152dec89cd56',
'timestamp': 1373493600, 'timestamp': 1373493600,
}, },
},{
'url': 'http://www.rtr.ch/play/radio/actualitad/audio/saira-tujetsch-tuttina-cuntinuar-cun-sedrun-muster-turissem?id=63cb0778-27f8-49af-9284-8c7a8c6d15fc',
'info_dict': {
'id': '63cb0778-27f8-49af-9284-8c7a8c6d15fc',
'ext': 'mp3',
'upload_date': '20151013',
'title': 'Saira: Tujetsch - tuttina cuntinuar cun Sedrun Mustér Turissem',
'timestamp': 1444750398,
},
'params': {
# rtmp download
'skip_download': True,
},
}] }]
def _real_extract(self, url): def _real_extract(self, url):
bu, media_type, media_id = re.match(self._VALID_URL, url).groups() bu, media_type, media_id = re.match(self._VALID_URL, url).groups()
return self.url_result('urn:%s:%s:%s' % (bu[:3], media_type, media_id), 'SRGSSR') return self.url_result('srgssr:%s:%s:%s' % (bu[:3], media_type, media_id), 'SRGSSR')