1
0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-09 12:42:28 +01:00
yt-dlp/yt_dlp/extractor/mediaset.py

356 lines
15 KiB
Python
Raw Normal View History

2017-05-02 16:17:15 +02:00
# coding: utf-8
from __future__ import unicode_literals
import functools
2017-05-14 01:28:40 +02:00
import re
from .theplatform import ThePlatformBaseIE
2017-05-02 16:17:15 +02:00
from ..utils import (
ExtractorError,
GeoRestrictedError,
int_or_none,
OnDemandPagedList,
2021-08-22 21:02:00 +02:00
parse_qs,
try_get,
urljoin,
update_url_query,
2017-05-02 16:17:15 +02:00
)
class MediasetIE(ThePlatformBaseIE):
_TP_TLD = 'eu'
_VALID_URL = r'''(?x)
2017-05-14 01:28:40 +02:00
(?:
mediaset:|
https?://
(?:(?:www|static3)\.)?mediasetplay\.mediaset\.it/
2017-05-14 01:28:40 +02:00
(?:
2021-01-01 13:26:37 +01:00
(?:video|on-demand|movie)/(?:[^/]+/)+[^/]+_|
player/index\.html\?.*?\bprogramGuid=
2017-05-14 01:28:40 +02:00
)
)(?P<id>[0-9A-Z]{16,})
'''
2017-05-02 16:17:15 +02:00
_TESTS = [{
# full episode
'url': 'https://www.mediasetplay.mediaset.it/video/mrwronglezionidamore/episodio-1_F310575103000102',
'md5': 'a7e75c6384871f322adb781d3bd72c26',
2017-05-02 16:17:15 +02:00
'info_dict': {
'id': 'F310575103000102',
2017-05-02 16:17:15 +02:00
'ext': 'mp4',
'title': 'Episodio 1',
'description': 'md5:e8017b7d7194e9bfb75299c2b8d81e02',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 2682.0,
'upload_date': '20210530',
'series': 'Mr Wrong - Lezioni d\'amore',
'timestamp': 1622413946,
'uploader': 'Canale 5',
'uploader_id': 'C5',
'season': 'Season 1',
'episode': 'Episode 1',
'season_number': 1,
'episode_number': 1,
'chapters': [{'start_time': 0.0, 'end_time': 439.88}, {'start_time': 439.88, 'end_time': 1685.84}, {'start_time': 1685.84, 'end_time': 2682.0}],
},
2018-06-18 11:50:06 +02:00
}, {
'url': 'https://www.mediasetplay.mediaset.it/video/matrix/puntata-del-25-maggio_F309013801000501',
'md5': '1276f966ac423d16ba255ce867de073e',
2018-06-18 11:50:06 +02:00
'info_dict': {
'id': 'F309013801000501',
2018-06-18 11:50:06 +02:00
'ext': 'mp4',
'title': 'Puntata del 25 maggio',
'description': 'md5:ee2e456e3eb1dba5e814596655bb5296',
2018-06-18 11:50:06 +02:00
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 6565.008,
'upload_date': '20200903',
2018-06-18 11:50:06 +02:00
'series': 'Matrix',
'timestamp': 1599172492,
'uploader': 'Canale 5',
'uploader_id': 'C5',
'season': 'Season 5',
'episode': 'Episode 5',
'season_number': 5,
'episode_number': 5,
'chapters': [{'start_time': 0.0, 'end_time': 3409.08}, {'start_time': 3409.08, 'end_time': 6565.008}],
2018-06-18 11:50:06 +02:00
},
}, {
'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',
'info_dict': {
'id': 'F006474501000101',
'ext': 'mp4',
'title': 'Selvaggi',
'description': 'md5:cfdedbbfdd12d4d0e5dcf1fa1b75284f',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 5233.01,
'upload_date': '20210729',
'timestamp': 1627594716,
'uploader': 'Cine34',
'uploader_id': 'B6',
'chapters': [{'start_time': 0.0, 'end_time': 1938.56}, {'start_time': 1938.56, 'end_time': 5233.01}],
},
2017-05-02 16:17:15 +02:00
}, {
# clip
'url': 'https://www.mediasetplay.mediaset.it/video/gogglebox/un-grande-classico-della-commedia-sexy_FAFU000000661680',
'only_matching': True,
2017-05-02 16:17:15 +02:00
}, {
# iframe simple
'url': 'https://static3.mediasetplay.mediaset.it/player/index.html?appKey=5ad3966b1de1c4000d5cec48&programGuid=FAFU000000665924&id=665924',
'only_matching': True,
2017-05-02 16:17:15 +02:00
}, {
# 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,
2017-05-14 01:28:40 +02:00
}, {
'url': 'mediaset:FAFU000000665924',
2017-05-14 01:28:40 +02:00
'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,
2021-01-01 13:26:37 +01:00
}, {
'url': 'https://www.mediasetplay.mediaset.it/movie/herculeslaleggendahainizio/hercules-la-leggenda-ha-inizio_F305927501000102',
'only_matching': True,
2017-05-02 16:17:15 +02:00
}]
@staticmethod
def _extract_urls(ie, webpage):
def _qs(url):
2021-08-22 21:02:00 +02:00
return parse_qs(url)
def _program_guid(qs):
return qs.get('programGuid', [None])[0]
entries = []
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 = _qs(embed_url)
program_guid = _program_guid(embed_qs)
if program_guid:
entries.append(embed_url)
continue
video_id = embed_qs.get('id', [None])[0]
if not video_id:
continue
urlh = ie._request_webpage(
embed_url, video_id, note='Following embed URL redirect')
embed_url = urlh.geturl()
program_guid = _program_guid(_qs(embed_url))
if program_guid:
entries.append(embed_url)
return entries
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)):
video.attrib['src'] = re.sub(r'(https?://vod05)t(-mediaset-it\.akamaized\.net/.+?.mpd)\?.+', r'\1\2', video.attrib['src'])
return super(MediasetIE, self)._parse_smil_formats(smil, smil_url, video_id, namespace, f4m_params, transform_rtmp_url)
def _check_drm_formats(self, tp_formats, video_id):
has_nondrm, drm_manifest = False, ''
for f in tp_formats:
if '_sampleaes/' in (f.get('manifest_url') or ''):
drm_manifest = drm_manifest or f['manifest_url']
f['has_drm'] = True
if not f.get('has_drm') and f.get('manifest_url'):
has_nondrm = True
nodrm_manifest = re.sub(r'_sampleaes/(\w+)_fp_', r'/\1_no_', drm_manifest)
if has_nondrm or nodrm_manifest == drm_manifest:
return
tp_formats.extend(self._extract_m3u8_formats(
nodrm_manifest, video_id, m3u8_id='hls', fatal=False) or [])
2017-05-02 16:17:15 +02:00
def _real_extract(self, url):
guid = self._match_id(url)
tp_path = 'PR1GhC/media/guid/2702976343/' + guid
info = self._extract_theplatform_metadata(tp_path, guid)
2017-05-02 16:17:15 +02:00
formats = []
subtitles = {}
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'):
try:
tp_formats, tp_subtitles = self._extract_theplatform_smil(
update_url_query('http://link.theplatform.%s/s/%s' % (self._TP_TLD, tp_path), {
'mbr': 'true',
'formats': f,
'assetTypes': asset_type,
}), guid, 'Downloading %s SMIL data' % (f.split('+')[0]))
except ExtractorError as e:
if not geo_e and isinstance(e, GeoRestrictedError):
geo_e = e
if not first_e:
first_e = e
continue
self._check_drm_formats(tp_formats, guid)
formats.extend(tp_formats)
subtitles = self._merge_subtitles(subtitles, tp_subtitles)
# check for errors and report them
if (first_e or geo_e) and not formats:
raise geo_e or first_e
self._sort_formats(formats)
2017-05-02 16:17:15 +02:00
feed_data = self._download_json(
'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 {}
thumbnails = feed_data.get('thumbnails') or {}
thumbnail = None
for key, value in thumbnails.items():
if key.startswith('image_keyframe_poster-'):
thumbnail = value.get('url')
break
info.update({
'description': info.get('description') or feed_data.get('description') or feed_data.get('longDescription'),
'uploader': publish_info.get('description'),
'uploader_id': publish_info.get('channel'),
'view_count': int_or_none(feed_data.get('mediasetprogram$numberOfViews')),
'thumbnail': thumbnail,
})
2017-05-02 16:17:15 +02:00
if feed_data.get('programType') == 'episode':
info.update({
'episode_number': int_or_none(
feed_data.get('tvSeasonEpisodeNumber')),
'season_number': int_or_none(
feed_data.get('tvSeasonNumber')),
'series': feed_data.get('mediasetprogram$brandTitle'),
})
info.update({
'id': guid,
'formats': formats,
'subtitles': subtitles,
})
return info
class MediasetShowIE(MediasetIE):
_VALID_URL = r'''(?x)
(?:
https?://
(?:(?:www|static3)\.)?mediasetplay\.mediaset\.it/
(?:
(?:fiction|programmi-tv|serie-tv|kids)/(?:.+?/)?
(?:[a-z-]+)_SE(?P<id>\d{12})
(?:,ST(?P<st>\d{12}))?
(?:,sb(?P<sb>\d{9}))?$
)
)
'''
_TESTS = [{
# TV Show webpage (general webpage)
'url': 'https://www.mediasetplay.mediaset.it/programmi-tv/leiene/leiene_SE000000000061',
'info_dict': {
'id': '000000000061',
'title': 'Le Iene',
},
'playlist_mincount': 7,
}, {
# TV Show webpage (specific season)
'url': 'https://www.mediasetplay.mediaset.it/programmi-tv/leiene/leiene_SE000000000061,ST000000002763',
'info_dict': {
'id': '000000002763',
'title': 'Le Iene',
},
'playlist_mincount': 7,
}, {
# TV Show specific playlist (with multiple pages)
'url': 'https://www.mediasetplay.mediaset.it/programmi-tv/leiene/iservizi_SE000000000061,ST000000002763,sb100013375',
'info_dict': {
'id': '100013375',
'title': 'I servizi',
},
'playlist_mincount': 50,
}]
_BY_SUBBRAND = 'https://feed.entertainment.tv.theplatform.eu/f/PR1GhC/mediaset-prod-all-programs-v2?byCustomValue={subBrandId}{%s}&sort=:publishInfo_lastPublished|desc,tvSeasonEpisodeNumber|desc&range=%d-%d'
_PAGE_SIZE = 25
def _fetch_page(self, sb, page):
lower_limit = page * self._PAGE_SIZE + 1
upper_limit = lower_limit + self._PAGE_SIZE - 1
content = self._download_json(
self._BY_SUBBRAND % (sb, lower_limit, upper_limit), sb)
for entry in content.get('entries') or []:
yield self.url_result(
'mediaset:' + entry['guid'],
playlist_title=entry['mediasetprogram$subBrandDescription'])
def _real_extract(self, url):
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))
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))
return self.playlist_result(entries, st or playlist_id, title)
entries = OnDemandPagedList(
functools.partial(self._fetch_page, sb),
self._PAGE_SIZE)
title = try_get(entries, lambda x: x[0]['playlist_title'])
return self.playlist_result(entries, sb, title)