PublicMirrors/you-get
1
0
Fork 0
mirror of https://github.com/soimort/you-get.git synced 2025-02-11 20:52:31 +03:00
Code Issues Actions Packages Projects Releases 1 Wiki Activity

Merge branch 'develop' into develop

Browse Source
This commit is contained in:
Rokic 2016-04-04 02:01:40 +08:00
commit 8b9cf16a1e
2 changed files with 19 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
src/you_get/extractors/bilibili.py
View File

@ -127,7 +127,8 @@ def bilibili_download(url, output_dir='.', merge=True, info_only=False, **kwargs
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>([^<>]+)</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)
elif 'playlist' in kwargs and kwargs['playlist']:
else:
# multi-P # multi-P
cids = [] cids = []
pages = re.findall('<option value=\'([^\']*)\'', html) pages = re.findall('<option value=\'([^\']*)\'', html)
@ -140,15 +141,18 @@ def bilibili_download(url, output_dir='.', merge=True, info_only=False, **kwargs
if flashvars: if flashvars:
t, cid = flashvars.split('=', 1) t, cid = flashvars.split('=', 1)
cids.append(cid.split('&')[0]) cids.append(cid.split('&')[0])
# no multi-P
if not pages:
cids = [cid]
titles = [r1(r'<option value=.* selected>(.+)</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],
titles[i], titles[i],
output_dir=output_dir, output_dir=output_dir,
merge=merge, merge=merge,
info_only=info_only) info_only=info_only)
else:
title = r1(r'<option value=.* selected>(.+)</option>', html) or title
bilibili_download_by_cid(cid, title, output_dir=output_dir, merge=merge, info_only=info_only)
elif t == 'vid': elif t == 'vid':
sina_download_by_vid(cid, title=title, output_dir=output_dir, merge=merge, info_only=info_only) sina_download_by_vid(cid, title=title, output_dir=output_dir, merge=merge, info_only=info_only)
@ -169,14 +173,6 @@ def bilibili_download(url, output_dir='.', merge=True, info_only=False, **kwargs
with open(os.path.join(output_dir, title + '.cmt.xml'), 'w', encoding='utf-8') as x: with open(os.path.join(output_dir, title + '.cmt.xml'), 'w', encoding='utf-8') as x:
x.write(xml) x.write(xml)
def bilibili_download_playlist(url, output_dir='.', merge=True, info_only=False, **kwargs):
bilibili_download(url,
output_dir=output_dir,
merge=merge,
info_only=info_only,
playlist=True,
**kwargs)
site_info = "bilibili.com" site_info = "bilibili.com"
download = bilibili_download download = bilibili_download
download_playlist = bilibili_download_playlist download_playlist = bilibili_download

11
src/you_get/extractors/embed.py
View File

@ -4,6 +4,7 @@ from ..common import *
from .iqiyi import iqiyi_download_by_vid from .iqiyi import iqiyi_download_by_vid
from .le import letvcloud_download_by_vu from .le import letvcloud_download_by_vu
from .netease import netease_download
from .qq import qq_download_by_vid from .qq import qq_download_by_vid
from .sina import sina_download_by_vid from .sina import sina_download_by_vid
from .tudou import tudou_download_by_id from .tudou import tudou_download_by_id
@ -36,10 +37,13 @@ yinyuetai_embed_patterns = [ 'player\.yinyuetai\.com/video/swf/(\d+)' ]
iqiyi_embed_patterns = [ 'player\.video\.qiyi\.com/([^/]+)/[^/]+/[^/]+/[^/]+\.swf[^"]+tvId=(\d+)' ] iqiyi_embed_patterns = [ 'player\.video\.qiyi\.com/([^/]+)/[^/]+/[^/]+/[^/]+\.swf[^"]+tvId=(\d+)' ]
netease_embed_patterns = [ '(http://\w+\.163\.com/movie/[^\'"]+)' ]
def embed_download(url, output_dir = '.', merge = True, info_only = False ,**kwargs): def embed_download(url, output_dir = '.', merge = True, info_only = False ,**kwargs):
content = get_content(url) content = get_content(url, headers=fake_headers)
found = False found = False
title = match1(content, '<title>([^<>]+)</title>') title = match1(content, '<title>([^<>]+)</title>')
vids = matchall(content, youku_embed_patterns) vids = matchall(content, youku_embed_patterns)
for vid in set(vids): for vid in set(vids):
found = True found = True
@ -60,6 +64,11 @@ def embed_download(url, output_dir = '.', merge = True, info_only = False ,**kwa
found = True found = True
iqiyi_download_by_vid((vid[1], vid[0]), title=title, output_dir=output_dir, merge=merge, info_only=info_only) iqiyi_download_by_vid((vid[1], vid[0]), title=title, output_dir=output_dir, merge=merge, info_only=info_only)
urls = matchall(content, netease_embed_patterns)
for url in urls:
found = True
netease_download(url, title=title, output_dir=output_dir, merge=merge, info_only=info_only)
if not found: if not found:
raise NotImplementedError(url) raise NotImplementedError(url)