administration/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-13 20:53:06 +00:00
Code Issues Projects Releases Wiki Activity

[fptplay] Fix metadata extraction (#3218)

Browse Source 
Authored by: hatienl0i261299
This commit is contained in:
Ha Tien Loi 2022-04-06 15:52:08 +07:00 committed by GitHub
parent 8973767198
commit 42a4f21a03
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 28 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

37
yt_dlp/extractor/fptplay.py
View File

@ -7,12 +7,14 @@ import urllib.parse
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
clean_html,
join_nonempty, join_nonempty,
strip_or_none,
) )
class FptplayIE(InfoExtractor): class FptplayIE(InfoExtractor):
_VALID_URL = r'https?://fptplay\.vn/(?P<type>xem-video)/[^/]+\-(?P<id>\w+)(?:/tap-(?P<episode>[^/]+)?/?(?:[?#]|$)|)' _VALID_URL = r'https?://fptplay\.vn/xem-video/[^/]+\-(?P<id>\w+)(?:/tap-(?P<episode>\d+)?/?(?:[?#]|$)|)'
_GEO_COUNTRIES = ['VN'] _GEO_COUNTRIES = ['VN']
IE_NAME = 'fptplay' IE_NAME = 'fptplay'
IE_DESC = 'fptplay.vn' IE_DESC = 'fptplay.vn'
@ -22,7 +24,7 @@ class FptplayIE(InfoExtractor):
'info_dict': { 'info_dict': {
'id': '621a123016f369ebbde55945', 'id': '621a123016f369ebbde55945',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Nhân Duyên Đại Nhân Xin Dừng Bước - Ms. Cupid In Love', 'title': 'Nhân Duyên Đại Nhân Xin Dừng Bước - Tập 1A',
'description': 'md5:23cf7d1ce0ade8e21e76ae482e6a8c6c', 'description': 'md5:23cf7d1ce0ade8e21e76ae482e6a8c6c',
}, },
}, { }, {
@ -31,25 +33,42 @@ class FptplayIE(InfoExtractor):
'info_dict': { 'info_dict': {
'id': '61f3aa8a6b3b1d2e73c60eb5', 'id': '61f3aa8a6b3b1d2e73c60eb5',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Má Tôi Là Đại Gia - 3', 'title': 'Má Tôi Là Đại Gia - Tập 3',
'description': 'md5:ff8ba62fb6e98ef8875c42edff641d1c', 'description': 'md5:ff8ba62fb6e98ef8875c42edff641d1c',
}, },
}, {
'url': 'https://fptplay.vn/xem-video/lap-toi-do-giam-under-the-skin-6222d9684ec7230fa6e627a2/tap-4',
'md5': 'bcb06c55ec14786d7d4eda07fa1ccbb9',
'info_dict': {
'id': '6222d9684ec7230fa6e627a2',
'ext': 'mp4',
'title': 'Lạp Tội Đồ Giám - Tập 2B',
'description': 'md5:e5a47e9d35fbf7e9479ca8a77204908b',
},
}, { }, {
'url': 'https://fptplay.vn/xem-video/nha-co-chuyen-hi-alls-well-ends-well-1997-6218995f6af792ee370459f0', 'url': 'https://fptplay.vn/xem-video/nha-co-chuyen-hi-alls-well-ends-well-1997-6218995f6af792ee370459f0',
'only_matching': True, 'only_matching': True,
}] }]
def _real_extract(self, url): def _real_extract(self, url):
type_url, video_id, episode = self._match_valid_url(url).group('type', 'id', 'episode') video_id, slug_episode = self._match_valid_url(url).group('id', 'episode')
webpage = self._download_webpage(url, video_id=video_id, fatal=False) webpage = self._download_webpage(url, video_id=video_id, fatal=False) or ''
info = self._download_json(self.get_api_with_st_token(video_id, episode or 0), video_id) title = self._search_regex(
r'(?s)<h4\s+class="mb-1 text-2xl text-white"[^>]*>(.+)</h4>', webpage, 'title', fatal=False)
real_episode = slug_episode if not title else self._search_regex(
r'<p.+title="(?P<episode>[^">]+)"\s+class="epi-title active"', webpage, 'episode', fatal=False)
title = strip_or_none(title) or self._html_search_meta(('og:title', 'twitter:title'), webpage)
info = self._download_json(
self.get_api_with_st_token(video_id, int(slug_episode) - 1 if slug_episode else 0), video_id)
formats, subtitles = self._extract_m3u8_formats_and_subtitles(info['data']['url'], video_id, 'mp4') formats, subtitles = self._extract_m3u8_formats_and_subtitles(info['data']['url'], video_id, 'mp4')
self._sort_formats(formats) self._sort_formats(formats)
return { return {
'id': video_id, 'id': video_id,
'title': join_nonempty( 'title': join_nonempty(title, real_episode, delim=' - '),
self._html_search_meta(('og:title', 'twitter:title'), webpage), episode, delim=' - '), 'description': (
'description': self._html_search_meta(['og:description', 'twitter:description'], webpage), clean_html(self._search_regex(r'<p\s+class="overflow-hidden"[^>]*>(.+)</p>', webpage, 'description'))
or self._html_search_meta(('og:description', 'twitter:description'), webpage)),
'formats': formats, 'formats': formats,
'subtitles': subtitles, 'subtitles': subtitles,
} }