from .common import InfoExtractor
from ..compat import (
- compat_urlparse,
compat_str,
+ compat_urlparse,
)
from ..utils import (
- ExtractorError,
determine_ext,
+ ExtractorError,
find_xpath_attr,
fix_xml_ampersands,
GeoRestrictedError,
+ HEADRequest,
int_or_none,
+ join_nonempty,
parse_duration,
remove_start,
strip_or_none,
+ traverse_obj,
try_get,
unified_strdate,
unified_timestamp,
_GEO_COUNTRIES = ['IT']
_GEO_BYPASS = False
- def _extract_relinker_info(self, relinker_url, video_id):
+ def _extract_relinker_info(self, relinker_url, video_id, audio_only=False):
if not re.match(r'https?://', relinker_url):
return {'formats': [{'url': relinker_url}]}
if (ext == 'm3u8' and platform != 'mon') or (ext == 'f4m' and platform != 'flash'):
continue
- if ext == 'm3u8' or 'format=m3u8' in media_url or platform == 'mon':
+ if ext == 'mp3':
+ formats.append({
+ 'url': media_url,
+ 'vcodec': 'none',
+ 'acodec': 'mp3',
+ 'format_id': 'http-mp3',
+ })
+ break
+ elif ext == 'm3u8' or 'format=m3u8' in media_url or platform == 'mon':
formats.extend(self._extract_m3u8_formats(
media_url, video_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
})
if not formats and geoprotection is True:
- self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
+ self.raise_geo_restricted(countries=self._GEO_COUNTRIES, metadata_available=True)
+
+ if not audio_only:
+ formats.extend(self._create_http_urls(relinker_url, formats))
return dict((k, v) for k, v in {
'is_live': is_live,
'formats': formats,
}.items() if v is not None)
+ def _create_http_urls(self, relinker_url, fmts):
+ _RELINKER_REG = r'https?://(?P<host>[^/]+?)/(?:i/)?(?P<extra>[^/]+?)/(?P<path>.+?)/(?P<id>\d+)(?:_(?P<quality>[\d\,]+))?(?:\.mp4|/playlist\.m3u8).+?'
+ _MP4_TMPL = '%s&overrideUserAgentRule=mp4-%s'
+ _QUALITY = {
+ # tbr: w, h
+ '250': [352, 198],
+ '400': [512, 288],
+ '700': [512, 288],
+ '800': [700, 394],
+ '1200': [736, 414],
+ '1800': [1024, 576],
+ '2400': [1280, 720],
+ '3200': [1440, 810],
+ '3600': [1440, 810],
+ '5000': [1920, 1080],
+ '10000': [1920, 1080],
+ }
+
+ def test_url(url):
+ resp = self._request_webpage(
+ HEADRequest(url), None, headers={'User-Agent': 'Rai'},
+ fatal=False, errnote=False, note=False)
+
+ if resp is False:
+ return False
+
+ if resp.code == 200:
+ return False if resp.url == url else resp.url
+ return None
+
+ # filter out audio-only formats
+ fmts = [f for f in fmts if not f.get('vcodec') == 'none']
+
+ def get_format_info(tbr):
+ import math
+ br = int_or_none(tbr)
+ if len(fmts) == 1 and not br:
+ br = fmts[0].get('tbr')
+ if br > 300:
+ tbr = compat_str(math.floor(br / 100) * 100)
+ else:
+ tbr = '250'
+
+ # try extracting info from available m3u8 formats
+ format_copy = None
+ for f in fmts:
+ if f.get('tbr'):
+ br_limit = math.floor(br / 100)
+ if br_limit - 1 <= math.floor(f['tbr'] / 100) <= br_limit + 1:
+ format_copy = f.copy()
+ return {
+ 'width': format_copy.get('width'),
+ 'height': format_copy.get('height'),
+ 'tbr': format_copy.get('tbr'),
+ 'vcodec': format_copy.get('vcodec'),
+ 'acodec': format_copy.get('acodec'),
+ 'fps': format_copy.get('fps'),
+ 'format_id': 'https-%s' % tbr,
+ } if format_copy else {
+ 'width': _QUALITY[tbr][0],
+ 'height': _QUALITY[tbr][1],
+ 'format_id': 'https-%s' % tbr,
+ 'tbr': int(tbr),
+ }
+
+ loc = test_url(_MP4_TMPL % (relinker_url, '*'))
+ if not isinstance(loc, compat_str):
+ return []
+
+ mobj = re.match(
+ _RELINKER_REG,
+ test_url(relinker_url) or '')
+ if not mobj:
+ return []
+
+ available_qualities = mobj.group('quality').split(',') if mobj.group('quality') else ['*']
+ available_qualities = [i for i in available_qualities if i]
+
+ formats = []
+ for q in available_qualities:
+ fmt = {
+ 'url': _MP4_TMPL % (relinker_url, q),
+ 'protocol': 'https',
+ 'ext': 'mp4',
+ }
+ fmt.update(get_format_info(q))
+ formats.append(fmt)
+ return formats
+
@staticmethod
def _extract_subtitles(url, video_data):
STL_EXT = 'stl'
'id': 'cb27157f-9dd0-4aee-b788-b1f67643a391',
'ext': 'mp4',
'title': 'Report del 07/04/2014',
- 'alt_title': 'St 2013/14 - Espresso nel caffè - 07/04/2014',
+ 'alt_title': 'St 2013/14 - Report - Espresso nel caffè - 07/04/2014',
'description': 'md5:d730c168a58f4bb35600fc2f881ec04e',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'Rai Gulp',
'series': 'Report',
'season': '2013/14',
'subtitles': {
- 'it': 'count:2',
+ 'it': 'count:4',
},
},
'params': {
'skip_download': True,
},
+ }, {
+ # 1080p direct mp4 url
+ 'url': 'https://www.raiplay.it/video/2021/11/Blanca-S1E1-Senza-occhi-b1255a4a-8e72-4a2f-b9f3-fc1308e00736.html',
+ 'md5': 'aeda7243115380b2dd5e881fd42d949a',
+ 'info_dict': {
+ 'id': 'b1255a4a-8e72-4a2f-b9f3-fc1308e00736',
+ 'ext': 'mp4',
+ 'title': 'Blanca - S1E1 - Senza occhi',
+ 'alt_title': 'St 1 Ep 1 - Blanca - Senza occhi',
+ 'description': 'md5:75f95d5c030ec8bac263b1212322e28c',
+ 'thumbnail': r're:^https?://.*\.jpg$',
+ 'uploader': 'Rai 1',
+ 'duration': 6493,
+ 'series': 'Blanca',
+ 'season': 'Season 1',
+ },
}, {
'url': 'http://www.raiplay.it/video/2016/11/gazebotraindesi-efebe701-969c-4593-92f3-285f0d1ce750.html?',
'only_matching': True,
}]
def _real_extract(self, url):
- base, video_id = re.match(self._VALID_URL, url).groups()
+ base, video_id = self._match_valid_url(url).groups()
media = self._download_json(
base + '.json', video_id, 'Downloading video JSON')
- if not self.params.get('allow_unplayable_formats'):
+ if not self.get_param('allow_unplayable_formats'):
if try_get(
media,
(lambda x: x['rights_management']['rights']['drm'],
lambda x: x['program_info']['rights_management']['rights']['drm']),
dict):
- raise ExtractorError('This video is DRM protected.', expected=True)
+ self.report_drm(video_id)
title = media['name']
video = media['video']
program_info = media.get('program_info') or {}
season = media.get('season')
+ alt_title = join_nonempty(media.get('subtitle'), media.get('toptitle'), delim=' - ')
+
info = {
'id': remove_start(media.get('id'), 'ContentItem-') or video_id,
'display_id': video_id,
- 'title': self._live_title(title) if relinker_info.get(
- 'is_live') else title,
- 'alt_title': strip_or_none(media.get('subtitle')),
+ 'title': title,
+ 'alt_title': strip_or_none(alt_title),
'description': media.get('description'),
'uploader': strip_or_none(media.get('channel')),
'creator': strip_or_none(media.get('editor') or None),
class RaiPlayPlaylistIE(InfoExtractor):
- _VALID_URL = r'(?P<base>https?://(?:www\.)?raiplay\.it/programmi/(?P<id>[^/?#&]+))'
+ _VALID_URL = r'(?P<base>https?://(?:www\.)?raiplay\.it/programmi/(?P<id>[^/?#&]+))(?:/(?P<extra_id>[^?#&]+))?'
_TESTS = [{
- 'url': 'http://www.raiplay.it/programmi/nondirloalmiocapo/',
+ 'url': 'https://www.raiplay.it/programmi/nondirloalmiocapo/',
'info_dict': {
'id': 'nondirloalmiocapo',
'title': 'Non dirlo al mio capo',
'description': 'md5:98ab6b98f7f44c2843fd7d6f045f153b',
},
'playlist_mincount': 12,
+ }, {
+ 'url': 'https://www.raiplay.it/programmi/nondirloalmiocapo/episodi/stagione-2/',
+ 'info_dict': {
+ 'id': 'nondirloalmiocapo',
+ 'title': 'Non dirlo al mio capo - Stagione 2',
+ 'description': 'md5:98ab6b98f7f44c2843fd7d6f045f153b',
+ },
+ 'playlist_mincount': 12,
}]
def _real_extract(self, url):
- base, playlist_id = re.match(self._VALID_URL, url).groups()
+ base, playlist_id, extra_id = self._match_valid_url(url).groups()
program = self._download_json(
base + '.json', playlist_id, 'Downloading program JSON')
+ if extra_id:
+ extra_id = extra_id.upper().rstrip('/')
+
+ playlist_title = program.get('name')
entries = []
for b in (program.get('blocks') or []):
for s in (b.get('sets') or []):
+ if extra_id:
+ if extra_id != join_nonempty(
+ b.get('name'), s.get('name'), delim='/').replace(' ', '-').upper():
+ continue
+ playlist_title = join_nonempty(playlist_title, s.get('name'), delim=' - ')
+
s_id = s.get('id')
if not s_id:
continue
video_id=RaiPlayIE._match_id(video_url)))
return self.playlist_result(
- entries, playlist_id, program.get('name'),
+ entries, playlist_id, playlist_title,
try_get(program, lambda x: x['program_info']['description']))
+class RaiPlaySoundIE(RaiBaseIE):
+ _VALID_URL = r'(?P<base>https?://(?:www\.)?raiplaysound\.it/.+?-(?P<id>%s))\.(?:html|json)' % RaiBaseIE._UUID_RE
+ _TESTS = [{
+ 'url': 'https://www.raiplaysound.it/audio/2021/12/IL-RUGGITO-DEL-CONIGLIO-1ebae2a7-7cdb-42bb-842e-fe0d193e9707.html',
+ 'md5': '8970abf8caf8aef4696e7b1f2adfc696',
+ 'info_dict': {
+ 'id': '1ebae2a7-7cdb-42bb-842e-fe0d193e9707',
+ 'ext': 'mp3',
+ 'title': 'Il Ruggito del Coniglio del 10/12/2021',
+ 'description': 'md5:2a17d2107e59a4a8faa0e18334139ee2',
+ 'thumbnail': r're:^https?://.*\.jpg$',
+ 'uploader': 'rai radio 2',
+ 'duration': 5685,
+ 'series': 'Il Ruggito del Coniglio',
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ }]
+
+ def _real_extract(self, url):
+ base, audio_id = self._match_valid_url(url).group('base', 'id')
+ media = self._download_json(f'{base}.json', audio_id, 'Downloading audio JSON')
+ uid = try_get(media, lambda x: remove_start(remove_start(x['uniquename'], 'ContentItem-'), 'Page-'))
+
+ info = {}
+ formats = []
+ relinkers = set(traverse_obj(media, (('downloadable_audio', 'audio', ('live', 'cards', 0, 'audio')), 'url')))
+ for r in relinkers:
+ info = self._extract_relinker_info(r, audio_id, True)
+ formats.extend(info.get('formats'))
+
+ date_published = try_get(media, (lambda x: f'{x["create_date"]} {x.get("create_time") or ""}',
+ lambda x: x['live']['create_date']))
+
+ podcast_info = traverse_obj(media, 'podcast_info', ('live', 'cards', 0)) or {}
+ thumbnails = [{
+ 'url': urljoin(url, thumb_url),
+ } for thumb_url in (podcast_info.get('images') or {}).values() if thumb_url]
+
+ return {
+ **info,
+ 'id': uid or audio_id,
+ 'display_id': audio_id,
+ 'title': traverse_obj(media, 'title', 'episode_title'),
+ 'alt_title': traverse_obj(media, ('track_info', 'media_name')),
+ 'description': media.get('description'),
+ 'uploader': traverse_obj(media, ('track_info', 'channel'), expected_type=strip_or_none),
+ 'creator': traverse_obj(media, ('track_info', 'editor'), expected_type=strip_or_none),
+ 'timestamp': unified_timestamp(date_published),
+ 'thumbnails': thumbnails,
+ 'series': podcast_info.get('title'),
+ 'season_number': int_or_none(media.get('season')),
+ 'episode': media.get('episode_title'),
+ 'episode_number': int_or_none(media.get('episode')),
+ 'formats': formats,
+ }
+
+
+class RaiPlaySoundLiveIE(RaiPlaySoundIE):
+ _VALID_URL = r'(?P<base>https?://(?:www\.)?raiplaysound\.it/(?P<id>[^/?#&]+)$)'
+ _TESTS = [{
+ 'url': 'https://www.raiplaysound.it/radio2',
+ 'info_dict': {
+ 'id': 'b00a50e6-f404-4af6-8f8c-ff3b9af73a44',
+ 'display_id': 'radio2',
+ 'ext': 'mp4',
+ 'title': 'Rai Radio 2',
+ 'uploader': 'rai radio 2',
+ 'creator': 'raiplaysound',
+ 'is_live': True,
+ },
+ 'params': {
+ 'skip_download': 'live',
+ },
+ }]
+
+
+class RaiPlaySoundPlaylistIE(InfoExtractor):
+ _VALID_URL = r'(?P<base>https?://(?:www\.)?raiplaysound\.it/(?:programmi|playlist|audiolibri)/(?P<id>[^/?#&]+))(?:/(?P<extra_id>[^?#&]+))?'
+ _TESTS = [{
+ 'url': 'https://www.raiplaysound.it/programmi/ilruggitodelconiglio',
+ 'info_dict': {
+ 'id': 'ilruggitodelconiglio',
+ 'title': 'Il Ruggito del Coniglio',
+ 'description': 'md5:1bbaf631245a7ab1ec4d9fbb3c7aa8f3',
+ },
+ 'playlist_mincount': 65,
+ }, {
+ 'url': 'https://www.raiplaysound.it/programmi/ilruggitodelconiglio/puntate/prima-stagione-1995',
+ 'info_dict': {
+ 'id': 'ilruggitodelconiglio_puntate_prima-stagione-1995',
+ 'title': 'Prima Stagione 1995',
+ },
+ 'playlist_count': 1,
+ }]
+
+ def _real_extract(self, url):
+ base, playlist_id, extra_id = self._match_valid_url(url).group('base', 'id', 'extra_id')
+ url = f'{base}.json'
+ program = self._download_json(url, playlist_id, 'Downloading program JSON')
+
+ if extra_id:
+ extra_id = extra_id.rstrip('/')
+ playlist_id += '_' + extra_id.replace('/', '_')
+ path = next(c['path_id'] for c in program.get('filters') or [] if extra_id in c.get('weblink'))
+ program = self._download_json(
+ urljoin('https://www.raiplaysound.it', path), playlist_id, 'Downloading program secondary JSON')
+
+ entries = [
+ self.url_result(urljoin(base, c['path_id']), ie=RaiPlaySoundIE.ie_key())
+ for c in traverse_obj(program, 'cards', ('block', 'cards')) or []
+ if c.get('path_id')]
+
+ return self.playlist_result(entries, playlist_id, program.get('title'),
+ traverse_obj(program, ('podcast_info', 'description')))
+
+
class RaiIE(RaiBaseIE):
_VALID_URL = r'https?://[^/]+\.(?:rai\.(?:it|tv)|rainews\.it)/.+?-(?P<id>%s)(?:-.+?)?\.html' % RaiBaseIE._UUID_RE
_TESTS = [{
}, {
# with ContentItem in og:url
'url': 'http://www.rai.it/dl/RaiTV/programmi/media/ContentItem-efb17665-691c-45d5-a60c-5301333cbb0c.html',
- 'md5': '6865dd00cf0bbf5772fdd89d59bd768a',
+ 'md5': '06345bd97c932f19ffb129973d07a020',
'info_dict': {
'id': 'efb17665-691c-45d5-a60c-5301333cbb0c',
'ext': 'mp4',
'params': {
'skip_download': True,
},
- }, {
- # ContentItem in iframe (see #12652) and subtitle at 'subtitlesUrl' key
- 'url': 'http://www.presadiretta.rai.it/dl/portali/site/puntata/ContentItem-3ed19d13-26c2-46ff-a551-b10828262f1b.html',
- 'info_dict': {
- 'id': '1ad6dc64-444a-42a4-9bea-e5419ad2f5fd',
- 'ext': 'mp4',
- 'title': 'Partiti acchiappavoti - Presa diretta del 13/09/2015',
- 'description': 'md5:d291b03407ec505f95f27970c0b025f4',
- 'upload_date': '20150913',
- 'subtitles': {
- 'it': 'count:2',
- },
- },
- 'params': {
- 'skip_download': True,
- },
}, {
# Direct MMS URL
'url': 'http://www.rai.it/dl/RaiTV/programmi/media/ContentItem-b63a4089-ac28-48cf-bca5-9f5b5bc46df5.html',
projects / yt-dlp.git / blobdiff