PublicMirrors/you-get
1
0
Fork 0
mirror of https://github.com/soimort/you-get.git synced 2025-02-03 00:33:58 +03:00
Code Issues Actions Packages Projects Releases 1 Wiki Activity

[universal] update

Browse Source
This commit is contained in:
Mort Yao 2019-04-29 00:29:28 +02:00
parent ad08f82a1a
commit b746ac01c9
No known key found for this signature in database
GPG Key ID: 07DA00CB78203251
1 changed files with 27 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

46
src/you_get/extractors/universal.py
View File

@ -33,27 +33,35 @@ def universal_download(url, output_dir='.', merge=True, info_only=False, **kwarg
meta_videos = re.findall(r'<meta property="og:video:url" content="([^"]*)"', page) meta_videos = re.findall(r'<meta property="og:video:url" content="([^"]*)"', page)
if meta_videos: if meta_videos:
for meta_video in meta_videos: try:
meta_video_url = unescape_html(meta_video) for meta_video in meta_videos:
type_, ext, size = url_info(meta_video_url) meta_video_url = unescape_html(meta_video)
print_info(site_info, page_title, type_, size) type_, ext, size = url_info(meta_video_url)
if not info_only: print_info(site_info, page_title, type_, size)
download_urls([meta_video_url], page_title, if not info_only:
ext, size, download_urls([meta_video_url], page_title,
output_dir=output_dir, merge=merge, ext, size,
faker=True) output_dir=output_dir, merge=merge,
return faker=True)
except:
pass
else:
return
hls_urls = re.findall(r'(https?://[^;"\'\\]+' + '\.m3u8?' + hls_urls = re.findall(r'(https?://[^;"\'\\]+' + '\.m3u8?' +
r'[^;"\'\\]*)', page) r'[^;"\'\\]*)', page)
if hls_urls: if hls_urls:
for hls_url in hls_urls: try:
type_, ext, size = url_info(hls_url) for hls_url in hls_urls:
print_info(site_info, page_title, type_, size) type_, ext, size = url_info(hls_url)
if not info_only: print_info(site_info, page_title, type_, size)
download_url_ffmpeg(url=hls_url, title=page_title, if not info_only:
ext='mp4', output_dir=output_dir) download_url_ffmpeg(url=hls_url, title=page_title,
return ext='mp4', output_dir=output_dir)
except:
pass
else:
return
# most common media file extensions on the Internet # most common media file extensions on the Internet
media_exts = ['\.flv', '\.mp3', '\.mp4', '\.webm', media_exts = ['\.flv', '\.mp3', '\.mp4', '\.webm',
@ -67,12 +75,12 @@ def universal_download(url, output_dir='.', merge=True, info_only=False, **kwarg
urls = [] urls = []
for i in media_exts: for i in media_exts:
urls += re.findall(r'(https?://[^ ;&"\'\\]+' + i + r'[^ ;&"\'\\]*)', page) urls += re.findall(r'(https?://[^ ;&"\'\\<>]+' + i + r'[^ ;&"\'\\<>]*)', page)
p_urls = re.findall(r'(https?%3A%2F%2F[^;&"]+' + i + r'[^;&"]*)', page) p_urls = re.findall(r'(https?%3A%2F%2F[^;&"]+' + i + r'[^;&"]*)', page)
urls += [parse.unquote(url) for url in p_urls] urls += [parse.unquote(url) for url in p_urls]
q_urls = re.findall(r'(https?:\\\\/\\\\/[^ ;"\']+' + i + r'[^ ;"\']*)', page) q_urls = re.findall(r'(https?:\\\\/\\\\/[^ ;"\'<>]+' + i + r'[^ ;"\'<>]*)', page)
urls += [url.replace('\\\\/', '/') for url in q_urls] urls += [url.replace('\\\\/', '/') for url in q_urls]
# a link href to an image is often an interesting one # a link href to an image is often an interesting one