[MangoTV] Improve extractor (#2971)

Authored by: hatienl0i261299
This commit is contained in:
Ha Tien Loi 2022-03-10 04:54:26 +07:00 committed by GitHub
parent 10331a2672
commit 33b8c411bc
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

View File

@ -13,12 +13,15 @@
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
int_or_none, int_or_none,
try_get,
url_or_none,
) )
class MGTVIE(InfoExtractor): class MGTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:w(?:ww)?\.)?mgtv\.com/(v|b)/(?:[^/]+/)*(?P<id>\d+)\.html' _VALID_URL = r'https?://(?:w(?:ww)?\.)?mgtv\.com/(v|b)/(?:[^/]+/)*(?P<id>\d+)\.html'
IE_DESC = '芒果TV' IE_DESC = '芒果TV'
IE_NAME = 'MangoTV'
_TESTS = [{ _TESTS = [{
'url': 'http://www.mgtv.com/v/1/290525/f/3116640.html', 'url': 'http://www.mgtv.com/v/1/290525/f/3116640.html',
@ -30,6 +33,32 @@ class MGTVIE(InfoExtractor):
'duration': 7461, 'duration': 7461,
'thumbnail': r're:^https?://.*\.jpg$', 'thumbnail': r're:^https?://.*\.jpg$',
}, },
}, {
'url': 'https://w.mgtv.com/b/427837/15588271.html',
'info_dict': {
'id': '15588271',
'ext': 'mp4',
'title': '春日迟迟再出发 沉浸版',
'description': 'md5:a7a05a05b1aa87bd50cae619b19bbca6',
'thumbnail': r're:^https?://.+\.jpg',
'duration': 4026,
},
}, {
'url': 'https://w.mgtv.com/b/333652/7329822.html',
'info_dict': {
'id': '7329822',
'ext': 'mp4',
'title': '拜托,请你爱我',
'description': 'md5:cd81be6499bafe32e4d143abd822bf9c',
'thumbnail': r're:^https?://.+\.jpg',
'duration': 2656,
},
}, {
'url': 'https://w.mgtv.com/b/427837/15591647.html',
'only_matching': True,
}, {
'url': 'https://w.mgtv.com/b/388252/15634192.html?fpa=33318&fpos=4&lastp=ch_home',
'only_matching': True,
}, { }, {
'url': 'http://www.mgtv.com/b/301817/3826653.html', 'url': 'http://www.mgtv.com/b/301817/3826653.html',
'only_matching': True, 'only_matching': True,
@ -40,12 +69,14 @@ class MGTVIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
tk2 = base64.urlsafe_b64encode(b'did=%s|pno=1030|ver=0.3.0301|clit=%d' % (compat_str(uuid.uuid4()).encode(), time.time()))[::-1] tk2 = base64.urlsafe_b64encode(
f'did={compat_str(uuid.uuid4()).encode()}|pno=1030|ver=0.3.0301|clit={int(time.time())}'.encode())[::-1]
try: try:
api_data = self._download_json( api_data = self._download_json(
'https://pcweb.api.mgtv.com/player/video', video_id, query={ 'https://pcweb.api.mgtv.com/player/video', video_id, query={
'tk2': tk2, 'tk2': tk2,
'video_id': video_id, 'video_id': video_id,
'type': 'pch5'
}, headers=self.geo_verification_headers())['data'] }, headers=self.geo_verification_headers())['data']
except ExtractorError as e: except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
@ -61,6 +92,7 @@ def _real_extract(self, url):
'pm2': api_data['atc']['pm2'], 'pm2': api_data['atc']['pm2'],
'tk2': tk2, 'tk2': tk2,
'video_id': video_id, 'video_id': video_id,
'src': 'intelmgtv',
}, headers=self.geo_verification_headers())['data'] }, headers=self.geo_verification_headers())['data']
stream_domain = stream_data['stream_domain'][0] stream_domain = stream_data['stream_domain'][0]
@ -71,7 +103,7 @@ def _real_extract(self, url):
continue continue
format_data = self._download_json( format_data = self._download_json(
stream_domain + stream_path, video_id, stream_domain + stream_path, video_id,
note='Download video info for format #%d' % idx) note=f'Download video info for format #{idx}')
format_url = format_data.get('info') format_url = format_data.get('info')
if not format_url: if not format_url:
continue continue
@ -79,7 +111,7 @@ def _real_extract(self, url):
r'_(\d+)_mp4/', format_url, 'tbr', default=None)) r'_(\d+)_mp4/', format_url, 'tbr', default=None))
formats.append({ formats.append({
'format_id': compat_str(tbr or idx), 'format_id': compat_str(tbr or idx),
'url': format_url, 'url': url_or_none(format_url),
'ext': 'mp4', 'ext': 'mp4',
'tbr': tbr, 'tbr': tbr,
'protocol': 'm3u8_native', 'protocol': 'm3u8_native',
@ -97,4 +129,25 @@ def _real_extract(self, url):
'description': info.get('desc'), 'description': info.get('desc'),
'duration': int_or_none(info.get('duration')), 'duration': int_or_none(info.get('duration')),
'thumbnail': info.get('thumb'), 'thumbnail': info.get('thumb'),
'subtitles': self.extract_subtitles(video_id, stream_domain),
} }
def _get_subtitles(self, video_id, domain):
info = self._download_json(f'https://pcweb.api.mgtv.com/video/title?videoId={video_id}',
video_id, fatal=False) or {}
subtitles = {}
for sub in try_get(info, lambda x: x['data']['title']) or []:
url_sub = sub.get('url')
if not url_sub:
continue
locale = sub.get('captionCountrySimpleName')
sub = self._download_json(f'{domain}{url_sub}', video_id, fatal=False,
note=f'Download subtitle for locale {sub.get("name")} ({locale})') or {}
sub_url = url_or_none(sub.get('info'))
if not sub_url:
continue
subtitles.setdefault(locale or 'en', []).append({
'url': sub_url,
'ext': 'srt'
})
return subtitles