[rts] Add more formats and audio support (Closes #2689)

This commit is contained in:
Sergey M․ 2014-04-04 20:41:41 +07:00
parent e3ced9ed61
commit 6344fa04bb

View File

@ -9,14 +9,16 @@
parse_duration,
parse_iso8601,
unescapeHTML,
compat_str,
)
class RTSIE(InfoExtractor):
IE_DESC = 'RTS.ch'
_VALID_URL = r'^https?://(?:www\.)?rts\.ch/archives/tv/[^/]+/(?P<id>[0-9]+)-.*?\.html'
_VALID_URL = r'^https?://(?:www\.)?rts\.ch/(?:[^/]+/){2,}(?P<id>[0-9]+)-.*?\.html'
_TEST = {
_TESTS = [
{
'url': 'http://www.rts.ch/archives/tv/divers/3449373-les-enfants-terribles.html',
'md5': '753b877968ad8afaeddccc374d4256a5',
'info_dict': {
@ -30,25 +32,110 @@ class RTSIE(InfoExtractor):
'timestamp': -40280400,
'thumbnail': 're:^https?://.*\.image'
},
}
},
{
'url': 'http://www.rts.ch/emissions/passe-moi-les-jumelles/5624067-entre-ciel-et-mer.html',
'md5': 'c197f0b2421995c63a64cc73d800f42e',
'info_dict': {
'id': '5738317',
'ext': 'mp4',
'duration': 55,
'title': 'Bande de lancement de Passe-moi les jumelles',
'description': '',
'uploader': 'Passe-moi les jumelles',
'upload_date': '20140404',
'timestamp': 1396635300,
'thumbnail': 're:^https?://.*\.image'
},
},
{
'url': 'http://www.rts.ch/video/sport/hockey/5745975-1-2-kloten-fribourg-5-2-second-but-pour-gotteron-par-kwiatowski.html',
'md5': 'b4326fecd3eb64a458ba73c73e91299d',
'info_dict': {
'id': '5745975',
'ext': 'mp4',
'duration': 48,
'title': '1/2, Kloten - Fribourg (5-2): second but pour Gottéron par Kwiatowski',
'description': 'Hockey - Playoff',
'uploader': 'Hockey',
'upload_date': '20140403',
'timestamp': 1396556882,
'thumbnail': 're:^https?://.*\.image'
},
'skip': 'Blocked outside Switzerland',
},
{
'url': 'http://www.rts.ch/video/info/journal-continu/5745356-londres-cachee-par-un-epais-smog.html',
'md5': '9bb06503773c07ce83d3cbd793cebb91',
'info_dict': {
'id': '5745356',
'ext': 'mp4',
'duration': 33,
'title': 'Londres cachée par un épais smog',
'description': 'Un important voile de smog recouvre Londres depuis mercredi, provoqué par la pollution et du sable du Sahara.',
'uploader': 'Le Journal en continu',
'upload_date': '20140403',
'timestamp': 1396537322,
'thumbnail': 're:^https?://.*\.image'
},
},
{
'url': 'http://www.rts.ch/audio/couleur3/programmes/la-belle-video-de-stephane-laurenceau/5706148-urban-hippie-de-damien-krisl-03-04-2014.html',
'md5': 'dd8ef6a22dff163d063e2a52bc8adcae',
'info_dict': {
'id': '5706148',
'ext': 'mp3',
'duration': 123,
'title': '"Urban Hippie", de Damien Krisl',
'description': 'Des Hippies super glam.',
'upload_date': '20140403',
'timestamp': 1396551600,
},
},
]
def _real_extract(self, url):
m = re.match(self._VALID_URL, url)
video_id = m.group('id')
all_info = self._download_json(
def download_json(video_id):
return self._download_json(
'http://www.rts.ch/a/%s.html?f=json/article' % video_id, video_id)
info = all_info['video']['JSONinfo']
all_info = download_json(video_id)
# video_id extracted out of URL is not always a real id
if 'video' not in all_info and 'audio' not in all_info:
page = self._download_webpage(url, video_id)
video_id = self._html_search_regex(r'<(?:video|audio) data-id="(\d+)"', page, 'video id')
all_info = download_json(video_id)
info = all_info['video']['JSONinfo'] if 'video' in all_info else all_info['audio']
upload_timestamp = parse_iso8601(info.get('broadcast_date'))
duration = parse_duration(info.get('duration'))
duration = info.get('duration') or info.get('cutout') or info.get('cutduration')
if isinstance(duration, compat_str):
duration = parse_duration(duration)
view_count = info.get('plays')
thumbnail = unescapeHTML(info.get('preview_image_url'))
def extract_bitrate(url):
return int_or_none(self._search_regex(
r'-([0-9]+)k\.', url, 'bitrate', default=None))
formats = [{
'format_id': fid,
'url': furl,
'tbr': int_or_none(self._search_regex(
r'-([0-9]+)k\.', furl, 'bitrate', default=None)),
'tbr': extract_bitrate(furl),
} for fid, furl in info['streams'].items()]
if 'media' in info:
formats.extend([{
'format_id': '%s-%sk' % (media['ext'], media['rate']),
'url': 'http://download-video.rts.ch/%s' % media['url'],
'tbr': media['rate'] or extract_bitrate(media['url']),
} for media in info['media'] if media.get('rate')])
self._sort_formats(formats)
return {
@ -57,6 +144,7 @@ def _real_extract(self, url):
'title': info['title'],
'description': info.get('intro'),
'duration': duration,
'view_count': view_count,
'uploader': info.get('programName'),
'timestamp': upload_timestamp,
'thumbnail': thumbnail,