sjw
/
yt-dlp
mirror of https://github.com/yt-dlp/yt-dlp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

add regex for video webpage url

This commit is contained in:
EGA-SUPREMO 2024-05-19 11:53:01 -04:00
parent 4070c00ba7
commit 151b383fe1
1 changed files with 14 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
yt_dlp/extractor/cablecasttv.py
View File

@ -13,35 +13,28 @@ class CableCastTVIE(InfoExtractor):
'ext': 'mp4',
'title': 'Village Board Meeting 4/24/24',
},
}, {
'url': 'https://fyptt.to/10382/beautiful-livestream-tits-and-nipples-slip-from-girls-who-loves-talking-with-their-viewers/',
'only_matching': True,
}, {
'url': 'https://fyptt.to/120/small-tits-fit-blonde-dancing-naked-at-the-front-door-on-tiktok',
'only_matching': True,
}, {
'url': 'https://fkbae.to/18',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
with open('output.txt', 'w', encoding='utf-8') as file:
file.write(webpage)
url_video_webpage = self._html_search_regex(r'<iframe[^>]*class=\"trms-player\"[^>]*src=\"([^\"]+)\"', webpage, 'url_video_webpage')
webpage_video = self._download_webpage(url_video_webpage, video_id)
video_url = self._html_search_regex(r'"([^\"]*\.m3u8)"', webpage_video, 'video URL')
print(video_url)
formats = []
format_url = self._html_search_regex(r'"embedURL":"([^"]+)"', webpage, 'video URL')
format_url = re.sub(r'\\', '', format_url)
formats.extend(self._extract_m3u8_formats(video_url, video_id, ext='mp4', m3u8_id='hls'))
print(formats)
#format_url = re.sub(r'\\', '', format_url)
webpage_video = self._download_webpage(format_url, video_id)
match = re.search(r'(https:\/\/[^"]+\.mp4)', webpage_video)
format_url = match.group(1)
formats.append({
'url': format_url,
'format_id': 'default',
})
title = self._html_search_regex(r'<span class="fl-heading-text">(.+?)</span>', webpage, 'title')
title = self._html_search_regex(r'<title>(.+?)</title>', webpage, 'title')
# base_url = re.search(r'^(https?://[a-zA-Z0-9_-]+\.to)', url).group(1)
# http_headers = {'Referer': base_url}