1
0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-06-27 17:08:32 +00:00
This commit is contained in:
D Trombett 2025-06-17 11:56:04 +02:00 committed by GitHub
commit 5a2911cb31
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -1,61 +1,46 @@
import re import json
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import int_or_none, js_to_json
base_url,
determine_ext,
int_or_none,
url_basename,
urljoin,
)
class GediDigitalIE(InfoExtractor): class GediDigitalIE(InfoExtractor):
_VALID_URL = r'''(?x:(?P<base_url>(?:https?:)//video\. _VALID_URL = r'''(?x:(?:https?:)//(?:\w+\.)?
(?: (?:
(?: repubblica
(?:espresso\.)?repubblica |lastampa
|lastampa |ilsecoloxix
|ilsecoloxix |huffingtonpost
|huffingtonpost )\.it/[^?]+(?:/video/(?P<slug>[a-z0-9_-]+)-|/)(?P<id>\d+))'''
)|
(?:
iltirreno
|messaggeroveneto
|ilpiccolo
|gazzettadimantova
|mattinopadova
|laprovinciapavese
|tribunatreviso
|nuovavenezia
|gazzettadimodena
|lanuovaferrara
|corrierealpi
|lasentinella
)\.gelocal
)\.it(?:/[^/]+){2,4}/(?P<id>\d+))(?:$|[?&].*))'''
_EMBED_REGEX = [rf'''(?x)
(?:
data-frame-src=|
<iframe[^\n]+src=
)
(["'])(?P<url>{_VALID_URL})\1''']
_TESTS = [{ _TESTS = [{
'url': 'https://video.lastampa.it/politica/il-paradosso-delle-regionali-la-lega-vince-ma-sembra-aver-perso/121559/121683', 'url': 'https://video.lastampa.it/politica/il-paradosso-delle-regionali-la-lega-vince-ma-sembra-aver-perso/121559/121683',
'md5': '84658d7fb9e55a6e57ecc77b73137494', 'md5': '6d1238ab5f4753b6f3d9eb396bff8ea3',
'info_dict': { 'info_dict': {
'id': '121683', 'id': '121683',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Il paradosso delle Regionali: ecco perché la Lega vince ma sembra aver perso', 'title': 'Il paradosso delle Regionali: ecco perché la Lega vince ma sembra aver perso',
'description': 'md5:de7f4d6eaaaf36c153b599b10f8ce7ca', 'description': 'md5:fad65b086b8b23fd4db66dc1f7a530f9',
'thumbnail': r're:^https://www\.repstatic\.it/video/photo/.+?-thumb-full-.+?\.jpg$', 'thumbnail': r're:^https://www\.repstatic\.it/video/photo/.+?-thumb-full-.+?\.jpg$',
'duration': 125, 'duration': 125,
'uploader_id': '6210505280001',
}, },
}, { }, {
'url': 'https://video.huffingtonpost.it/embed/politica/cotticelli-non-so-cosa-mi-sia-successo-sto-cercando-di-capire-se-ho-avuto-un-malore/29312/29276?responsive=true&el=video971040871621586700', 'url': 'https://www.repubblica.it/video/tv/2023/10/25/video/maurizio_molinari_israele_sotto_shock_per_le_parole_del_segretario_generale_dellonu-422547542',
'md5': '3cdb25ee59373cb326dd402c7e18490f',
'info_dict': {
'id': '422547542',
'ext': 'mp4',
'display_id': 'maurizio_molinari_israele_sotto_shock_per_le_parole_del_segretario_generale_dellonu',
'title': 'Maurizio Molinari: "Israele sotto shock per le parole del segretario generale dell\'Onu"',
'uploader_id': '6210505280001',
'duration': 89,
'thumbnail': 'https://www.repstatic.it/video/photo/2023/10/25/918897/918897-thumb-full-720-molinari_porta_a_porta_24_10_23.jpg',
},
}, {
'url': 'https://roma.repubblica.it/cronaca/2025/05/22/video/giornata_biodiversita_mattarella_si_improvvisa_giardiniere_annaffia_una_piantina_a_castelporziano-424598388/',
'only_matching': True, 'only_matching': True,
}, { }, {
'url': 'https://video.espresso.repubblica.it/embed/tutti-i-video/01-ted-villa/14772/14870&width=640&height=360', 'url': 'https://video.huffingtonpost.it/embed/politica/cotticelli-non-so-cosa-mi-sia-successo-sto-cercando-di-capire-se-ho-avuto-un-malore/29312/29276?responsive=true&el=video971040871621586700',
'only_matching': True, 'only_matching': True,
}, { }, {
'url': 'https://video.repubblica.it/motori/record-della-pista-a-spa-francorchamps-la-pagani-huayra-roadster-bc-stupisce/367415/367963', 'url': 'https://video.repubblica.it/motori/record-della-pista-a-spa-francorchamps-la-pagani-huayra-roadster-bc-stupisce/367415/367963',
@ -63,136 +48,57 @@ class GediDigitalIE(InfoExtractor):
}, { }, {
'url': 'https://video.ilsecoloxix.it/sport/cassani-e-i-brividi-azzurri-ai-mondiali-di-imola-qui-mi-sono-innamorato-del-ciclismo-da-ragazzino-incredibile-tornarci-da-ct/66184/66267', 'url': 'https://video.ilsecoloxix.it/sport/cassani-e-i-brividi-azzurri-ai-mondiali-di-imola-qui-mi-sono-innamorato-del-ciclismo-da-ragazzino-incredibile-tornarci-da-ct/66184/66267',
'only_matching': True, 'only_matching': True,
}, {
'url': 'https://video.iltirreno.gelocal.it/sport/dentro-la-notizia-ferrari-cosa-succede-a-maranello/141059/142723',
'only_matching': True,
}, {
'url': 'https://video.messaggeroveneto.gelocal.it/locale/maria-giovanna-elmi-covid-vaccino/138155/139268',
'only_matching': True,
}, {
'url': 'https://video.ilpiccolo.gelocal.it/dossier/big-john/dinosauro-big-john-al-via-le-visite-guidate-a-trieste/135226/135751',
'only_matching': True,
}, {
'url': 'https://video.gazzettadimantova.gelocal.it/locale/dal-ponte-visconteo-di-valeggio-l-and-8217sos-dei-ristoratori-aprire-anche-a-cena/137310/137818',
'only_matching': True,
}, {
'url': 'https://video.mattinopadova.gelocal.it/dossier/coronavirus-in-veneto/covid-a-vo-un-anno-dopo-un-cuore-tricolore-per-non-dimenticare/138402/138964',
'only_matching': True,
}, {
'url': 'https://video.laprovinciapavese.gelocal.it/locale/mede-zona-rossa-via-alle-vaccinazioni-per-gli-over-80/137545/138120',
'only_matching': True,
}, {
'url': 'https://video.tribunatreviso.gelocal.it/dossier/coronavirus-in-veneto/ecco-le-prima-vaccinazioni-di-massa-nella-marca/134485/135024',
'only_matching': True,
}, {
'url': 'https://video.nuovavenezia.gelocal.it/locale/camion-troppo-alto-per-il-ponte-ferroviario-perde-il-carico/135734/136266',
'only_matching': True,
}, {
'url': 'https://video.gazzettadimodena.gelocal.it/locale/modena-scoperta-la-proteina-che-predice-il-livello-di-gravita-del-covid/139109/139796',
'only_matching': True,
}, {
'url': 'https://video.lanuovaferrara.gelocal.it/locale/due-bombole-di-gpl-aperte-e-abbandonate-i-vigili-bruciano-il-gas/134391/134957',
'only_matching': True,
}, {
'url': 'https://video.corrierealpi.gelocal.it/dossier/cortina-2021-i-mondiali-di-sci-alpino/mondiali-di-sci-il-timelapse-sulla-splendida-olympia/133760/134331',
'only_matching': True,
}, {
'url': 'https://video.lasentinella.gelocal.it/locale/vestigne-centra-un-auto-e-si-ribalta/138931/139466',
'only_matching': True,
}, {
'url': 'https://video.espresso.repubblica.it/tutti-i-video/01-ted-villa/14772',
'only_matching': True,
}] }]
@staticmethod
def _sanitize_urls(urls):
# add protocol if missing
for i, e in enumerate(urls):
if e.startswith('//'):
urls[i] = f'https:{e}'
# clean iframes urls
for i, e in enumerate(urls):
urls[i] = urljoin(base_url(e), url_basename(e))
return urls
@classmethod
def _extract_embed_urls(cls, url, webpage):
return cls._sanitize_urls(tuple(super()._extract_embed_urls(url, webpage)))
@staticmethod
def _clean_formats(formats):
format_urls = set()
clean_formats = []
for f in formats:
if f['url'] not in format_urls:
if f.get('audio_ext') != 'none' and not f.get('acodec'):
continue
format_urls.add(f['url'])
clean_formats.append(f)
formats[:] = clean_formats
def _real_extract(self, url): def _real_extract(self, url):
video_id, url = self._match_valid_url(url).group('id', 'base_url') video_id, slug = self._match_valid_url(url).group('id', 'slug')
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
title = self._html_search_meta( data = self._search_json(
['twitter:title', 'og:title'], webpage, fatal=True) r'BrightcoveVideoPlayerOptions\s*=', webpage, 'Brightcove video player options', video_id, transform_source=js_to_json,
player_data = re.findall( )
r"PlayerFactory\.setParam\('(?P<type>format|param)',\s*'(?P<name>[^']+)',\s*'(?P<val>[^']+)'\);", streams = json.loads(data['videoSrc'])
webpage)
formats = [] formats = []
duration = thumb = None for stream in streams:
for t, n, v in player_data: if isinstance(stream, str):
if t == 'format': continue
if n in ('video-hds-vod-ec', 'video-hls-vod-ec', 'video-viralize', 'video-youtube-pfp'): if stream['type'] == 'video/mp4':
continue bitrate = self._search_regex(r'video-rrtv-(\d+)', stream['src'], 'vbr', None)
elif n.endswith('-vod-ak'): formats.append({
formats.extend(self._extract_akamai_formats( 'format_id': f'mp4-{bitrate}' if bitrate else 'mp4',
v, video_id, {'http': 'media.gedidigital.it'})) 'url': stream['src'],
else: 'ext': 'mp4',
ext = determine_ext(v) 'vcodec': 'avc1',
if ext == 'm3u8': 'acodec': 'mp4a',
formats.extend(self._extract_m3u8_formats( 'vbr': int_or_none(bitrate),
v, video_id, 'mp4', 'm3u8_native', m3u8_id=n, fatal=False)) })
continue elif stream['type'] == 'application/x-mpegURL':
f = { new_formats = self._extract_m3u8_formats(stream['src'], video_id)
'format_id': n, for fmt in new_formats:
'url': v, fmt.setdefault('vbr', int_or_none(self._search_regex(r'/hls/_(\d+)/', fmt['url'], 'vbr', None)))
} formats.extend(new_formats)
if ext == 'mp3': elif stream['type'] == 'audio/mp3':
abr = int_or_none(self._search_regex( bitrate = self._search_regex(r'mp3-audio-(\d+)', stream['src'], 'vbr', None)
r'-mp3-audio-(\d+)', v, 'abr', default=None)) formats.append({
f.update({ 'format_id': f'mp3-{bitrate}' if bitrate else 'mp3',
'abr': abr, 'url': stream['src'],
'tbr': abr, 'ext': 'mp3',
'acodec': ext, 'acodec': 'mp3',
'vcodec': 'none', 'abr': int_or_none(bitrate),
}) 'tbr': int_or_none(bitrate),
else: })
mobj = re.match(r'^video-rrtv-(\d+)(?:-(\d+))?$', n) else:
if mobj: formats.append({
f.update({ 'format_id': stream['type'],
'height': int(mobj.group(1)), 'url': stream['src'],
'vbr': int_or_none(mobj.group(2)), })
})
if not f.get('vbr'):
f['vbr'] = int_or_none(self._search_regex(
r'-video-rrtv-(\d+)', v, 'abr', default=None))
formats.append(f)
elif t == 'param':
if n in ['image_full', 'image']:
thumb = v
elif n == 'videoDuration':
duration = int_or_none(v)
self._clean_formats(formats)
return { return {
'id': video_id, 'id': video_id,
'title': title, 'display_id': slug,
'description': self._html_search_meta( 'title': data.get('videoTitle') or self._html_search_meta(['twitter:title', 'og:title'], webpage),
['twitter:description', 'og:description', 'description'], webpage), 'description': self._html_search_meta(['twitter:description', 'og:description', 'description'], webpage, default=None),
'thumbnail': thumb or self._og_search_thumbnail(webpage),
'formats': formats, 'formats': formats,
'duration': duration, 'thumbnail': data.get('posterSrc') or self._og_search_thumbnail(webpage),
'uploader_id': data.get('accountId'),
'duration': int_or_none(data.get('videoLenght')),
} }