PublicMirrors/you-get
1
0
Fork 0
mirror of https://github.com/soimort/you-get.git synced 2025-02-03 08:43:58 +03:00
Code Issues Actions Packages Projects Releases 1 Wiki Activity

[bilibili] video title may have space around

Browse Source
This commit is contained in:
chinat 2016-07-27 13:42:06 +08:00
parent 80a8265a49
commit fbf5c491aa
1 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
src/you_get/extractors/bilibili.py
View File

@ -125,8 +125,8 @@ def bilibili_download(url, output_dir='.', merge=True, info_only=False, **kwargs
url = r1(r'"([^"]+)" class="v-av-link"', html) url = r1(r'"([^"]+)" class="v-av-link"', html)
html = get_content(url) html = get_content(url)
title = r1_of([r'<meta name="title" content="([^<>]{1,999})" />', title = r1_of([r'<meta name="title" content="\s*([^<>]{1,999})\s*" />',
r'<h1[^>]*>([^<>]+)</h1>'], html) r'<h1[^>]*>\s*([^<>]+)\s*</h1>'], html)
if title: if title:
title = unescape_html(title) title = unescape_html(title)
title = escape_file_path(title) title = escape_file_path(title)
@ -139,14 +139,14 @@ def bilibili_download(url, output_dir='.', merge=True, info_only=False, **kwargs
cid = cid.split('&')[0] cid = cid.split('&')[0]
if t == 'cid': if t == 'cid':
if re.match(r'https?://live\.bilibili\.com/', url): if re.match(r'https?://live\.bilibili\.com/', url):
title = r1(r'<title>([^<>]+)</title>', html) title = r1(r'<title>\s*([^<>]+)\s*</title>', html)
bilibili_live_download_by_cid(cid, title, output_dir=output_dir, merge=merge, info_only=info_only) bilibili_live_download_by_cid(cid, title, output_dir=output_dir, merge=merge, info_only=info_only)
else: else:
# multi-P # multi-P
cids = [] cids = []
pages = re.findall('<option value=\'([^\']*)\'', html) pages = re.findall('<option value=\'([^\']*)\'', html)
titles = re.findall('<option value=.*>(.+)</option>', html) titles = re.findall('<option value=.*>\s*(.+)\s*</option>', html)
for i, page in enumerate(pages): for i, page in enumerate(pages):
html = get_html("http://www.bilibili.com%s" % page) html = get_html("http://www.bilibili.com%s" % page)
flashvars = r1_of([r'(cid=\d+)', flashvars = r1_of([r'(cid=\d+)',
@ -163,7 +163,7 @@ def bilibili_download(url, output_dir='.', merge=True, info_only=False, **kwargs
# no multi-P # no multi-P
if not pages: if not pages:
cids = [cid] cids = [cid]
titles = [r1(r'<option value=.* selected>(.+)</option>', html) or title] titles = [r1(r'<option value=.* selected>\s*(.+)\s*</option>', html) or title]
for i in range(len(cids)): for i in range(len(cids)):
bilibili_download_by_cid(cids[i], bilibili_download_by_cid(cids[i],