PublicMirrors/you-get
1
0
Fork 0
mirror of https://github.com/soimort/you-get.git synced 2025-03-13 03:17:44 +03:00
Code Issues Actions Packages Projects Releases 1 Wiki Activity

Merge branch 'develop' of https://github.com/soimort/you-get into develop

Browse Source
This commit is contained in:
GuanFoxyier 2019-06-17 09:19:20 +08:00
commit c3ef3740f3
3 changed files with 22 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
src/you_get/extractors/sohu.py
View File

@ -15,11 +15,13 @@ Changelog:
new api
'''
def real_url(fileName, key, ch):
url = "https://data.vod.itc.cn/ip?new=" + fileName + "&num=1&key=" + key + "&ch=" + ch + "&pt=1&pg=2&prod=h5n"
return json.loads(get_html(url))['servers'][0]['url']
def sohu_download(url, output_dir = '.', merge = True, info_only = False, extractor_proxy=None, **kwargs):
def sohu_download(url, output_dir='.', merge=True, info_only=False, extractor_proxy=None, **kwargs):
if re.match(r'http://share.vrs.sohu.com', url):
vid = r1('id=(\d+)', url)
else:
@ -27,16 +29,16 @@ def sohu_download(url, output_dir = '.', merge = True, info_only = False, extrac
vid = r1(r'\Wvid\s*[\:=]\s*[\'"]?(\d+)[\'"]?', html)
assert vid
if re.match(r'http[s]://tv.sohu.com/', url):
if extractor_proxy:
set_proxy(tuple(extractor_proxy.split(":")))
info = json.loads(get_decoded_html('http://hot.vrs.sohu.com/vrs_flash.action?vid=%s' % vid))
for qtyp in ["oriVid","superVid","highVid" ,"norVid","relativeId"]:
if extractor_proxy:
set_proxy(tuple(extractor_proxy.split(":")))
info = json.loads(get_decoded_html('http://hot.vrs.sohu.com/vrs_flash.action?vid=%s' % vid))
if info and info.get("data", ""):
for qtyp in ["oriVid", "superVid", "highVid", "norVid", "relativeId"]:
if 'data' in info:
hqvid = info['data'][qtyp]
else:
hqvid = info[qtyp]
if hqvid != 0 and hqvid != vid :
if hqvid != 0 and hqvid != vid:
info = json.loads(get_decoded_html('http://hot.vrs.sohu.com/vrs_flash.action?vid=%s' % hqvid))
if not 'allot' in info:
continue
@ -63,14 +65,15 @@ def sohu_download(url, output_dir = '.', merge = True, info_only = False, extrac
urls = []
data = info['data']
title = data['tvName']
size = sum(map(int,data['clipsBytes']))
size = sum(map(int, data['clipsBytes']))
assert len(data['clipsURL']) == len(data['clipsBytes']) == len(data['su'])
for fileName, key in zip(data['su'], data['ck']):
urls.append(real_url(fileName, key, data['ch']))
print_info(site_info, title, 'mp4', size)
if not info_only:
download_urls(urls, title, 'mp4', size, output_dir, refer = url, merge = merge)
download_urls(urls, title, 'mp4', size, output_dir, refer=url, merge=merge)
site_info = "Sohu.com"
download = sohu_download

16
src/you_get/extractors/youtube.py
View File

@ -216,6 +216,7 @@ class YouTube(VideoExtractor):
self.html5player = 'https://www.youtube.com' + ytplayer_config['assets']['js']
# Workaround: get_video_info returns bad s. Why?
stream_list = ytplayer_config['args']['url_encoded_fmt_stream_map'].split(',')
#stream_list = ytplayer_config['args']['adaptive_fmts'].split(',')
except:
stream_list = video_info['url_encoded_fmt_stream_map'][0].split(',')
if re.search('([^"]*/base\.js)"', video_page):
@ -306,7 +307,8 @@ class YouTube(VideoExtractor):
'url': metadata['url'][0],
'sig': metadata['sig'][0] if 'sig' in metadata else None,
's': metadata['s'][0] if 's' in metadata else None,
'quality': metadata['quality'][0],
'quality': metadata['quality'][0] if 'quality' in metadata else None,
#'quality': metadata['quality_label'][0] if 'quality_label' in metadata else None,
'type': metadata['type'][0],
'mime': metadata['type'][0].split(';')[0],
'container': mime_to_container(metadata['type'][0].split(';')[0]),
@ -433,13 +435,13 @@ class YouTube(VideoExtractor):
dash_mp4_a_url = stream['url']
if 's' in stream:
sig = self.__class__.decipher(self.js, stream['s'])
dash_mp4_a_url += '&signature={}'.format(sig)
dash_mp4_a_url += '&sig={}'.format(sig)
dash_mp4_a_size = stream['clen']
elif stream['type'].startswith('audio/webm'):
dash_webm_a_url = stream['url']
if 's' in stream:
sig = self.__class__.decipher(self.js, stream['s'])
dash_webm_a_url += '&signature={}'.format(sig)
dash_webm_a_url += '&sig={}'.format(sig)
dash_webm_a_size = stream['clen']
for stream in streams: # video
if 'size' in stream:
@ -448,7 +450,7 @@ class YouTube(VideoExtractor):
dash_url = stream['url']
if 's' in stream:
sig = self.__class__.decipher(self.js, stream['s'])
dash_url += '&signature={}'.format(sig)
dash_url += '&sig={}'.format(sig)
dash_size = stream['clen']
itag = stream['itag']
dash_urls = self.__class__.chunk_by_range(dash_url, int(dash_size))
@ -467,7 +469,7 @@ class YouTube(VideoExtractor):
dash_url = stream['url']
if 's' in stream:
sig = self.__class__.decipher(self.js, stream['s'])
dash_url += '&signature={}'.format(sig)
dash_url += '&sig={}'.format(sig)
dash_size = stream['clen']
itag = stream['itag']
audio_url = None
@ -510,13 +512,13 @@ class YouTube(VideoExtractor):
src = self.streams[stream_id]['url']
if self.streams[stream_id]['sig'] is not None:
sig = self.streams[stream_id]['sig']
src += '&signature={}'.format(sig)
src += '&sig={}'.format(sig)
elif self.streams[stream_id]['s'] is not None:
if not hasattr(self, 'js'):
self.js = get_content(self.html5player)
s = self.streams[stream_id]['s']
sig = self.__class__.decipher(self.js, s)
src += '&signature={}'.format(sig)
src += '&sig={}'.format(sig)
self.streams[stream_id]['src'] = [src]
self.streams[stream_id]['size'] = urls_size(self.streams[stream_id]['src'])

2
src/you_get/version.py
View File

@ -1,4 +1,4 @@
#!/usr/bin/env python
script_name = 'you-get'
__version__ = '0.4.1302'
__version__ = '0.4.1314'