0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-25 02:45:12 +00:00
yt-dlp/yt_dlp/extractor/sixplay.py

120 lines
4.9 KiB
Python
Raw Normal View History

from .common import InfoExtractor
from ..utils import (
determine_ext,
2017-02-08 16:15:39 +00:00
int_or_none,
2021-08-22 19:02:00 +00:00
parse_qs,
2017-02-08 16:15:39 +00:00
qualities,
try_get,
)
class SixPlayIE(InfoExtractor):
IE_NAME = '6play'
_VALID_URL = r'(?:6play:|https?://(?:www\.)?(?P<domain>6play\.fr|rtlplay\.be|play\.rtl\.hr|rtlmost\.hu)/.+?-c_)(?P<id>[0-9]+)'
_TESTS = [{
'url': 'https://www.6play.fr/minute-par-minute-p_9533/le-but-qui-a-marque-lhistoire-du-football-francais-c_12041051',
'md5': '31fcd112637baa0c2ab92c4fcd8baf27',
'info_dict': {
'id': '12041051',
'ext': 'mp4',
'title': 'Le but qui a marqué l\'histoire du football français !',
'description': 'md5:b59e7e841d646ef1eb42a7868eb6a851',
2017-02-08 16:15:39 +00:00
},
}, {
'url': 'https://www.rtlplay.be/rtl-info-13h-p_8551/les-titres-du-rtlinfo-13h-c_12045869',
'only_matching': True,
2018-08-21 17:06:27 +00:00
}, {
'url': 'https://play.rtl.hr/pj-masks-p_9455/epizoda-34-sezona-1-catboyevo-cudo-na-dva-kotaca-c_11984989',
'only_matching': True,
}, {
'url': 'https://www.rtlmost.hu/megtorve-p_14167/megtorve-6-resz-c_12397787',
'only_matching': True,
}]
def _real_extract(self, url):
domain, video_id = self._match_valid_url(url).groups()
service, consumer_name = {
'6play.fr': ('6play', 'm6web'),
'rtlplay.be': ('rtlbe_rtl_play', 'rtlbe'),
2018-08-21 17:06:27 +00:00
'play.rtl.hr': ('rtlhr_rtl_play', 'rtlhr'),
'rtlmost.hu': ('rtlhu_rtl_most', 'rtlhu'),
}.get(domain, ('6play', 'm6web'))
2017-02-08 16:15:39 +00:00
data = self._download_json(
f'https://pc.middleware.6play.fr/6play/v2/platforms/m6group_web/services/{service}/videos/clip_{video_id}',
video_id, headers={
'x-customer-name': consumer_name,
}, query={
2017-02-08 16:15:39 +00:00
'csa': 5,
'with': 'clips',
})
clip_data = data['clips'][0]
title = clip_data['title']
urls = []
quality_key = qualities(['lq', 'sd', 'hq', 'hd'])
formats = []
subtitles = {}
assets = clip_data.get('assets') or []
for asset in assets:
2017-02-08 16:15:39 +00:00
asset_url = asset.get('full_physical_path')
protocol = asset.get('protocol')
2019-04-27 09:32:53 +00:00
if not asset_url or ((protocol == 'primetime' or asset.get('type') == 'usp_hlsfp_h264') and not ('_drmnp.ism/' in asset_url or '_unpnp.ism/' in asset_url)) or asset_url in urls:
continue
urls.append(asset_url)
2017-02-08 16:15:39 +00:00
container = asset.get('video_container')
ext = determine_ext(asset_url)
if protocol == 'http_subtitle' or ext == 'vtt':
subtitles.setdefault('fr', []).append({'url': asset_url})
continue
2017-02-08 16:15:39 +00:00
if container == 'm3u8' or ext == 'm3u8':
if protocol == 'usp':
2021-08-22 19:02:00 +00:00
if parse_qs(asset_url).get('token', [None])[0]:
2018-06-19 09:35:42 +00:00
urlh = self._request_webpage(
asset_url, video_id, fatal=False,
headers=self.geo_verification_headers())
if not urlh:
continue
asset_url = urlh.url
asset_url = asset_url.replace('_drmnp.ism/', '_unpnp.ism/')
2018-11-19 17:15:51 +00:00
for i in range(3, 0, -1):
asset_url = asset_url.replace('_sd1/', f'_sd{i}/')
2018-11-19 17:15:51 +00:00
m3u8_formats = self._extract_m3u8_formats(
asset_url, video_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False)
formats.extend(m3u8_formats)
formats.extend(self._extract_mpd_formats(
asset_url.replace('.m3u8', '.mpd'),
video_id, mpd_id='dash', fatal=False))
if m3u8_formats:
break
else:
formats.extend(self._extract_m3u8_formats(
asset_url, video_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
2017-02-08 16:15:39 +00:00
elif container == 'mp4' or ext == 'mp4':
quality = asset.get('video_quality')
formats.append({
2017-02-08 16:15:39 +00:00
'url': asset_url,
'format_id': quality,
'quality': quality_key(quality),
'ext': ext,
})
2017-02-08 16:15:39 +00:00
def get(getter):
for src in (data, clip_data):
v = try_get(src, getter, str)
2017-02-08 16:15:39 +00:00
if v:
return v
return {
'id': video_id,
2017-02-08 16:15:39 +00:00
'title': title,
'description': get(lambda x: x['description']),
'duration': int_or_none(clip_data.get('duration')),
'series': get(lambda x: x['program']['title']),
'formats': formats,
'subtitles': subtitles,
}