[extractor/mediaset] Better embed detection and error messages (#5664)

Authored by: nixxo
This commit is contained in:
nixxo 2022-12-09 08:20:37 +01:00 committed by GitHub
parent b05f0a50e0
commit 10dc85924a
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 81 additions and 133 deletions

View File

@ -1547,19 +1547,6 @@ class GenericIE(InfoExtractor):
},
'add_ie': ['WashingtonPost'],
},
{
# Mediaset embed
'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
'info_dict': {
'id': '720642',
'ext': 'mp4',
'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
},
'params': {
'skip_download': True,
},
'add_ie': ['Mediaset'],
},
{
# JOJ.sk embeds
'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',

View File

@ -7,7 +7,6 @@ from ..utils import (
GeoRestrictedError,
int_or_none,
OnDemandPagedList,
parse_qs,
try_get,
urljoin,
update_url_query,
@ -16,20 +15,25 @@ from ..utils import (
class MediasetIE(ThePlatformBaseIE):
_TP_TLD = 'eu'
_VALID_URL = r'''(?x)
_GUID_RE = r'F[0-9A-Z]{15}'
_VALID_URL = rf'''(?x)
(?:
mediaset:|
https?://
(?:\w+\.)+mediaset\.it/
(?:
(?:video|on-demand|movie)/(?:[^/]+/)+[^/]+_|
player/(?:v\d+/)?index\.html\?.*?\bprogramGuid=
player/(?:v\d+/)?index\.html\?\S*?\bprogramGuid=
)
)(?P<id>[0-9A-Z]{16,})
)(?P<id>{_GUID_RE})
'''
_EMBED_REGEX = [
rf'<iframe[^>]+src=[\'"](?P<url>(?:https?:)?//(?:\w+\.)+mediaset\.it/player/(?:v\d+/)?index\.html\?\S*?programGuid={_GUID_RE})[\'"&]'
]
_TESTS = [{
# full episode
'url': 'https://www.mediasetplay.mediaset.it/video/mrwronglezionidamore/episodio-1_F310575103000102',
'url': 'https://mediasetinfinity.mediaset.it/video/mrwronglezionidamore/episodio-1_F310575103000102',
'md5': 'a7e75c6384871f322adb781d3bd72c26',
'info_dict': {
'id': 'F310575103000102',
@ -50,7 +54,7 @@ class MediasetIE(ThePlatformBaseIE):
'chapters': [{'start_time': 0.0, 'end_time': 439.88}, {'start_time': 439.88, 'end_time': 1685.84}, {'start_time': 1685.84, 'end_time': 2682.0}],
},
}, {
'url': 'https://www.mediasetplay.mediaset.it/video/matrix/puntata-del-25-maggio_F309013801000501',
'url': 'https://mediasetinfinity.mediaset.it/video/matrix/puntata-del-25-maggio_F309013801000501',
'md5': '1276f966ac423d16ba255ce867de073e',
'info_dict': {
'id': 'F309013801000501',
@ -71,51 +75,8 @@ class MediasetIE(ThePlatformBaseIE):
'chapters': [{'start_time': 0.0, 'end_time': 3409.08}, {'start_time': 3409.08, 'end_time': 6565.008}],
},
}, {
'url': 'https://www.mediasetplay.mediaset.it/video/cameracafe5/episodio-69-pezzo-di-luna_F303843101017801',
'md5': 'd1650ac9ff944f185556126a736df148',
'info_dict': {
'id': 'F303843101017801',
'ext': 'mp4',
'title': 'Episodio 69 - Pezzo di luna',
'description': 'md5:7c32c8ec4118b72588b9412f11353f73',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 263.008,
'upload_date': '20200902',
'series': 'Camera Café 5',
'timestamp': 1599064700,
'uploader': 'Italia 1',
'uploader_id': 'I1',
'season': 'Season 5',
'episode': 'Episode 178',
'season_number': 5,
'episode_number': 178,
'chapters': [{'start_time': 0.0, 'end_time': 261.88}, {'start_time': 261.88, 'end_time': 263.008}],
},
}, {
'url': 'https://www.mediasetplay.mediaset.it/video/cameracafe5/episodio-51-tu-chi-sei_F303843107000601',
'md5': '567e9ad375b7a27a0e370650f572a1e3',
'info_dict': {
'id': 'F303843107000601',
'ext': 'mp4',
'title': 'Episodio 51 - Tu chi sei?',
'description': 'md5:42ef006e56824cc31787a547590923f4',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 367.021,
'upload_date': '20200902',
'series': 'Camera Café 5',
'timestamp': 1599069817,
'uploader': 'Italia 1',
'uploader_id': 'I1',
'season': 'Season 5',
'episode': 'Episode 6',
'season_number': 5,
'episode_number': 6,
'chapters': [{'start_time': 0.0, 'end_time': 358.68}, {'start_time': 358.68, 'end_time': 367.021}],
},
}, {
# movie
'url': 'https://www.mediasetplay.mediaset.it/movie/selvaggi/selvaggi_F006474501000101',
'md5': '720440187a2ae26af8148eb9e6b901ed',
# DRM
'url': 'https://mediasetinfinity.mediaset.it/movie/selvaggi/selvaggi_F006474501000101',
'info_dict': {
'id': 'F006474501000101',
'ext': 'mp4',
@ -129,70 +90,69 @@ class MediasetIE(ThePlatformBaseIE):
'uploader_id': 'B6',
'chapters': [{'start_time': 0.0, 'end_time': 1938.56}, {'start_time': 1938.56, 'end_time': 5233.01}],
},
'params': {
'ignore_no_formats_error': True,
},
'expected_warnings': [
'None of the available releases match the specified AssetType, ProtectionScheme, and/or Format preferences',
'Content behind paywall and DRM',
],
'skip': True,
}, {
# clip
'url': 'https://www.mediasetplay.mediaset.it/video/gogglebox/un-grande-classico-della-commedia-sexy_FAFU000000661680',
# old domain
'url': 'https://www.mediasetplay.mediaset.it/video/mrwronglezionidamore/episodio-1_F310575103000102',
'only_matching': True,
}, {
# iframe simple
# iframe
'url': 'https://static3.mediasetplay.mediaset.it/player/index.html?appKey=5ad3966b1de1c4000d5cec48&programGuid=FAFU000000665924&id=665924',
'only_matching': True,
}, {
# iframe twitter (from http://www.wittytv.it/se-prima-mi-fidavo-zero/)
'url': 'https://static3.mediasetplay.mediaset.it/player/index.html?appKey=5ad3966b1de1c4000d5cec48&programGuid=FAFU000000665104&id=665104',
'only_matching': True,
}, {
# embedUrl (from https://www.wittytv.it/amici/est-ce-que-tu-maimes-gabriele-5-dicembre-copia/)
'url': 'https://static3.mediasetplay.mediaset.it/player/v2/index.html?partnerId=wittytv&configId=&programGuid=FD00000000153323&autoplay=true&purl=http://www.wittytv.it/amici/est-ce-que-tu-maimes-gabriele-5-dicembre-copia/',
'only_matching': True,
}, {
'url': 'mediaset:FAFU000000665924',
'only_matching': True,
}, {
'url': 'https://www.mediasetplay.mediaset.it/video/mediasethaacuoreilfuturo/palmieri-alicudi-lisola-dei-tre-bambini-felici--un-decreto-per-alicudi-e-tutte-le-microscuole_FD00000000102295',
'only_matching': True,
}, {
'url': 'https://www.mediasetplay.mediaset.it/video/cherryseason/anticipazioni-degli-episodi-del-23-ottobre_F306837101005C02',
'only_matching': True,
}, {
'url': 'https://www.mediasetplay.mediaset.it/video/tg5/ambiente-onda-umana-per-salvare-il-pianeta_F309453601079D01',
'only_matching': True,
}, {
'url': 'https://www.mediasetplay.mediaset.it/video/grandefratellovip/benedetta-una-doccia-gelata_F309344401044C135',
'only_matching': True,
}, {
'url': 'https://www.mediasetplay.mediaset.it/movie/herculeslaleggendahainizio/hercules-la-leggenda-ha-inizio_F305927501000102',
'only_matching': True,
}, {
'url': 'https://mediasetinfinity.mediaset.it/video/braveandbeautiful/episodio-113_F310948005000402',
'only_matching': True,
}, {
'url': 'https://static3.mediasetplay.mediaset.it/player/v2/index.html?partnerId=wittytv&configId=&programGuid=FD00000000153323',
'only_matching': True,
}]
def _extract_from_webpage(self, url, webpage):
def _program_guid(qs):
return qs.get('programGuid', [None])[0]
for mobj in re.finditer(
r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//(?:www\.)?video\.mediaset\.it/player/playerIFrame(?:Twitter)?\.shtml.*?)\1',
webpage):
embed_url = mobj.group('url')
embed_qs = parse_qs(embed_url)
program_guid = _program_guid(embed_qs)
if program_guid:
yield self.url_result(embed_url)
continue
video_id = embed_qs.get('id', [None])[0]
if not video_id:
continue
urlh = self._request_webpage(embed_url, video_id, note='Following embed URL redirect')
embed_url = urlh.geturl()
program_guid = _program_guid(parse_qs(embed_url))
if program_guid:
yield self.url_result(embed_url)
_WEBPAGE_TESTS = [{
# Mediaset embed
'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
'info_dict': {
'id': 'FD00000000004929',
'ext': 'mp4',
'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
'duration': 67.013,
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'Mediaset Play',
'uploader_id': 'QY',
'upload_date': '20201005',
'timestamp': 1601866168,
'chapters': [],
},
'params': {
'skip_download': True,
}
}, {
# WittyTV embed
'url': 'https://www.wittytv.it/mauriziocostanzoshow/ultima-puntata-venerdi-25-novembre/',
'info_dict': {
'id': 'F312172801000801',
'ext': 'mp4',
'title': 'Ultima puntata - Venerdì 25 novembre',
'description': 'Una serata all\'insegna della musica e del buonumore ma non priva di spunti di riflessione',
'duration': 6203.01,
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'Canale 5',
'uploader_id': 'C5',
'upload_date': '20221126',
'timestamp': 1669428689,
'chapters': list,
'series': 'Maurizio Costanzo Show',
'season': 'Season 12',
'season_number': 12,
'episode': 'Episode 8',
'episode_number': 8,
},
'params': {
'skip_download': True,
}
}]
def _parse_smil_formats(self, smil, smil_url, video_id, namespace=None, f4m_params=None, transform_rtmp_url=None):
for video in smil.findall(self._xpath_ns('.//video', namespace)):
@ -217,7 +177,7 @@ class MediasetIE(ThePlatformBaseIE):
def _real_extract(self, url):
guid = self._match_id(url)
tp_path = 'PR1GhC/media/guid/2702976343/' + guid
tp_path = f'PR1GhC/media/guid/2702976343/{guid}'
info = self._extract_theplatform_metadata(tp_path, guid)
formats = []
@ -225,15 +185,17 @@ class MediasetIE(ThePlatformBaseIE):
first_e = geo_e = None
asset_type = 'geoNo:HD,browser,geoIT|geoNo:HD,geoIT|geoNo:SD,browser,geoIT|geoNo:SD,geoIT|geoNo|HD|SD'
# TODO: fixup ISM+none manifest URLs
for f in ('MPEG4', 'M3U'):
for f in ('MPEG4', 'MPEG-DASH', 'M3U'):
try:
tp_formats, tp_subtitles = self._extract_theplatform_smil(
update_url_query('http://link.theplatform.%s/s/%s' % (self._TP_TLD, tp_path), {
update_url_query(f'http://link.theplatform.{self._TP_TLD}/s/{tp_path}', {
'mbr': 'true',
'formats': f,
'assetTypes': asset_type,
}), guid, 'Downloading %s SMIL data' % (f.split('+')[0]))
}), guid, f'Downloading {f.split("+")[0]} SMIL data')
except ExtractorError as e:
if e.orig_msg == 'None of the available releases match the specified AssetType, ProtectionScheme, and/or Format preferences':
e.orig_msg = 'This video is DRM protected'
if not geo_e and isinstance(e, GeoRestrictedError):
geo_e = e
if not first_e:
@ -248,7 +210,7 @@ class MediasetIE(ThePlatformBaseIE):
raise geo_e or first_e
feed_data = self._download_json(
'https://feed.entertainment.tv.theplatform.eu/f/PR1GhC/mediaset-prod-all-programs-v2/guid/-/' + guid,
f'https://feed.entertainment.tv.theplatform.eu/f/PR1GhC/mediaset-prod-all-programs-v2/guid/-/{guid}',
guid, fatal=False)
if feed_data:
publish_info = feed_data.get('mediasetprogram$publishInfo') or {}
@ -299,23 +261,23 @@ class MediasetShowIE(MediasetIE): # XXX: Do not subclass from concrete IE
'''
_TESTS = [{
# TV Show webpage (general webpage)
'url': 'https://www.mediasetplay.mediaset.it/programmi-tv/leiene/leiene_SE000000000061',
'url': 'https://mediasetinfinity.mediaset.it/programmi-tv/leiene/leiene_SE000000000061',
'info_dict': {
'id': '000000000061',
'title': 'Le Iene',
'title': 'Le Iene 2022/2023',
},
'playlist_mincount': 7,
'playlist_mincount': 6,
}, {
# TV Show webpage (specific season)
'url': 'https://www.mediasetplay.mediaset.it/programmi-tv/leiene/leiene_SE000000000061,ST000000002763',
'url': 'https://mediasetinfinity.mediaset.it/programmi-tv/leiene/leiene_SE000000000061,ST000000002763',
'info_dict': {
'id': '000000002763',
'title': 'Le Iene',
'title': 'Le Iene 2021/2022',
},
'playlist_mincount': 7,
}, {
# TV Show specific playlist (with multiple pages)
'url': 'https://www.mediasetplay.mediaset.it/programmi-tv/leiene/iservizi_SE000000000061,ST000000002763,sb100013375',
'url': 'https://mediasetinfinity.mediaset.it/programmi-tv/leiene/iservizi_SE000000000061,ST000000002763,sb100013375',
'info_dict': {
'id': '100013375',
'title': 'I servizi',
@ -340,10 +302,9 @@ class MediasetShowIE(MediasetIE): # XXX: Do not subclass from concrete IE
playlist_id, st, sb = self._match_valid_url(url).group('id', 'st', 'sb')
if not sb:
page = self._download_webpage(url, st or playlist_id)
entries = [self.url_result(urljoin('https://www.mediasetplay.mediaset.it', url))
entries = [self.url_result(urljoin('https://mediasetinfinity.mediaset.it', url))
for url in re.findall(r'href="([^<>=]+SE\d{12},ST\d{12},sb\d{9})">[^<]+<', page)]
title = (self._html_search_regex(r'(?s)<h1[^>]*>(.+?)</h1>', page, 'title', default=None)
or self._og_search_title(page))
title = self._html_extract_title(page).split('|')[0].strip()
return self.playlist_result(entries, st or playlist_id, title)
entries = OnDemandPagedList(