def get_auth_cookie(cookie):
'''通过重定向获得授权cookie
重定向的链接开头为:
http://pan.baidu.com/disk/home?errno=0&errmsg=Auth%20Login%20Sucess&stoken=xxx
'''
url = ''.join([
const.PASSPORT_LOGIN_V3, 'auth/?return_type=5',
'&tpl=netdisk&u=https%3A%2F%2Fpan.baidu.com%2Fdisk%2Fhome'
])
headers = {
'Cookie': cookie.header_output(),
'Referer': const.PAN_REFERER,
}
req = net.urlopen_without_redirect(url, headers=headers)
if req and req.headers.get("Location"):
redirect_url = req.headers.get("Location")
redirect_req = net.urlopen_without_redirect(
redirect_url, headers={'Cookie': cookie.header_output()})
if redirect_req:
return redirect_req.headers.get_all('Set-Cookie')
else:
return None
else:
return None
def get_download_link(cookie, tokens, path):
'''在下载之前, 要先获取最终的下载链接.
path - 一个文件的绝对路径.
@return red_url, red_url 是重定向后的URL, 如果获取失败,
就返回原来的dlink;
'''
metas = get_metas(cookie, tokens, path)
if (not metas or metas.get('errno', -1) != 0 or 'info' not in metas
or len(metas['info']) != 1):
logger.error('pcs.get_download_link(): %s' % metas)
return None
dlink = metas['info'][0]['dlink']
url = '{0}&cflg={1}'.format(dlink, cookie.get('cflag').value)
req = net.urlopen_without_redirect(url,
headers={
'Cookie':
cookie.sub_output(
'BAIDUID', 'BDUSS', 'cflag'),
'Accept':
const.ACCEPT_HTML,
})
if not req:
return url
else:
return req.getheader('Location', url)
def get_share_uk_and_shareid(cookie, url):
'''从共享链接中提示uk和shareid.
如果共享文件需要输入密码, 就会将need_pwd设为True
如果成功, 返回(need_pwd, uk, shareid)
如果失败, 就返回None
目前支持的链接格式有:
* http://pan.baidu.com/wap/link?uk=202032639&shareid=420754&third=0
* http://pan.baidu.com/share/link?uk=202032639&shareid=420754
* http://pan.baidu.com/s/1i3iQY48
'''
def parse_share_uk(content):
'''代码片段如下:
yunData.SHARE_ID = "677200861";
yunData.SHARE_UK = "1295729848";
'''
uk_reg = re.compile('yunData.SHARE_UK\s*=\s*"(\d+)"')
shareid_reg = re.compile('yunData.SHARE_ID\s*=\s*"(\d+)"')
uk_match = uk_reg.search(content)
shareid_match = shareid_reg.search(content)
if uk_match and shareid_match:
return False, uk_match.group(1), shareid_match.group(1)
else:
return None
def parse_uk_from_url(url):
uk_reg = re.compile('uk=(\d+)')
uk_match = uk_reg.search(url)
shareid_reg = re.compile('shareid=(\d+)')
shareid_match = shareid_reg.search(url)
if not uk_match or not shareid_match:
return '', ''
uk = uk_match.group(1)
shareid = shareid_match.group(1)
return uk, shareid
# 识别加密链接
req = net.urlopen_without_redirect(url,
headers={
'Cookie': cookie.header_output(),
})
if req and req.headers.get('Location'):
init_url = req.headers.get('Location')
if init_url.find('share/init') > -1:
uk, shareid = parse_uk_from_url(init_url)
return True, uk, shareid
# 处理短链接
if url.startswith('http://pan.baidu.com/s/'):
req = net.urlopen(url, headers={
'Cookie': cookie.header_output(),
})
if req:
return parse_share_uk(req.data.decode())
# 处理正常链接
uk, shareid = parse_uk_from_url(url)
return False, uk, shareid
def get_share_uk_and_shareid(cookie, url):
'''从共享链接中提示uk和shareid.
如果共享文件需要输入密码, 就会将need_pwd设为True
如果成功, 返回(need_pwd, uk, shareid)
如果失败, 就返回None
目前支持的链接格式有:
* http://pan.baidu.com/wap/link?uk=202032639&shareid=420754&third=0
* http://pan.baidu.com/share/link?uk=202032639&shareid=420754
* http://pan.baidu.com/s/1i3iQY48
'''
def parse_share_uk(content):
'''代码片段如下:
yunData.SHARE_ID = "677200861";
yunData.SHARE_UK = "1295729848";
'''
uk_reg = re.compile('yunData.SHARE_UK\s*=\s*"(\d+)"')
shareid_reg = re.compile('yunData.SHARE_ID\s*=\s*"(\d+)"')
uk_match = uk_reg.search(content)
shareid_match = shareid_reg.search(content)
if uk_match and shareid_match:
return False, uk_match.group(1), shareid_match.group(1)
else:
return None
def parse_uk_from_url(url):
uk_reg = re.compile('uk=(\d+)')
uk_match = uk_reg.search(url)
shareid_reg = re.compile('shareid=(\d+)')
shareid_match = shareid_reg.search(url)
if not uk_match or not shareid_match:
return '', ''
uk = uk_match.group(1)
shareid = shareid_match.group(1)
return uk, shareid
# 识别加密链接
req = net.urlopen_without_redirect(url, headers={
'Cookie': cookie.header_output(),
})
if req and req.headers.get('Location'):
init_url = req.headers.get('Location')
if init_url.find('share/init') > -1:
uk, shareid = parse_uk_from_url(init_url)
return True, uk, shareid
# 处理短链接
if url.startswith('http://pan.baidu.com/s/'):
req = net.urlopen(url, headers={
'Cookie': cookie.header_output(),
})
if req:
return parse_share_uk(req.data.decode())
# 处理正常链接
uk, shareid = parse_uk_from_url(url)
return False, uk, shareid
def wap_signin(cookie, form):
'''进行WAP登录认证'''
url = 'http://wappass.baidu.com/passport/login'
req = net.urlopen_without_redirect(url, headers={
'Cookie': cookie.header_output(),
'Content-Type': const.CONTENT_FORM,
'Referer': url,
}, data=parse.urlencode(form).encode())
if req:
return req.headers.get_all('Set-Cookie')
else:
return None
def wap_signin(cookie, form):
'''进行WAP登录认证'''
url = 'http://wappass.baidu.com/passport/login'
req = net.urlopen_without_redirect(url,
headers={
'Cookie': cookie.header_output(),
'Content-Type': const.CONTENT_FORM,
'Referer': url,
},
data=parse.urlencode(form).encode())
if req:
return req.headers.get_all('Set-Cookie')
else:
return None
def stream_download(cookie, tokens, path):
'''下载流媒体文件.
path - 流文件的绝对路径.
'''
url = ''.join([
const.PCS_URL_D,
'file?method=download',
'&path=', encoder.encode_uri_component(path),
'&app_id=250528',
])
req = net.urlopen_without_redirect(url, headers=
{'Cookie': cookie.header_output()})
if req:
return req
else:
return None
def stream_download(cookie, tokens, path):
'''下载流媒体文件.
path - 流文件的绝对路径.
'''
url = ''.join([
const.PCS_URL_D,
'file?method=download',
'&path=', encoder.encode_uri_component(path),
'&app_id=250528',
])
req = net.urlopen_without_redirect(url, headers=
{'Cookie': cookie.header_output()})
if req:
return req
else:
return None
def stream_download(cookie, tokens, path):
print(
'/usr/local/lib/python3.4/dist-packages/bcloud/pcs.py:stream_download 696'
)
'''下载流媒体文件.
path - 流文件的绝对路径.
'''
url = ''.join([
const.PCS_URL_D,
'file?method=download',
'&path=',
encoder.encode_uri_component(path),
'&app_id=250528',
])
req = net.urlopen_without_redirect(
url, headers={'Cookie': cookie.header_output()})
if req:
return req
else:
return None
def get_download_link(cookie, tokens, path):
'''在下载之前, 要先获取最终的下载链接.
path - 一个文件的绝对路径.
@return red_url, red_url 是重定向后的URL, 如果获取失败,
就返回原来的dlink;
'''
metas = get_metas(cookie, tokens, path)
if (not metas or metas.get('errno', 1) != 0 or
'info' not in metas or len(metas['info']) != 1):
return None
dlink = metas['info'][0]['dlink']
url = '{0}&cflg={1}'.format(dlink, cookie.get('cflag').value)
req = net.urlopen_without_redirect(url, headers={
'Cookie': cookie.sub_output('BAIDUID', 'BDUSS', 'cflag'),
'Accept': const.ACCEPT_HTML,
})
if not req:
return url
else:
return req.getheader('Location', url)
def get_share_uk_and_shareid(cookie, url):
'''从共享链接中提取uk和shareid.
目前支持的链接格式有:
* http(s)://pan.baidu.com/wap/link?uk=202032639&shareid=420754&third=0
* http(s)://pan.baidu.com/share/link?uk=202032639&shareid=420754
* http(s)://pan.baidu.com/wap/init?surl=pMi4xab
* http(s)://pan.baidu.com/share/init?surl=pMi4xab
* http(s)://pan.baidu.com/s/1i3iQY48
有三种返回值: (need_pwd, surl), (need_pwd, surl, uk, shareid)和None
如果共享文件需要输入密码, 就会将need_pwd设为True
如果链接属于第三种或第四种, 返回(True, surl), 需要验证密码后才能提取uk和shareid
如果是其他链接, 返回(need_pwd, surl, uk, shareid)
如果失败, 就返回None
'''
def parse_share_uk(content):
uk_reg = re.compile(',"uk":(\d+),')
shareid_reg = re.compile(',"shareid":(\d+),')
uk_match = uk_reg.search(content)
shareid_match = shareid_reg.search(content)
if uk_match and shareid_match:
return uk_match.group(1), shareid_match.group(1)
else:
return None, None
def parse_share_uk_from_url(url):
uk_reg = re.compile('uk=(\d+)')
uk_match = uk_reg.search(url)
shareid_reg = re.compile('shareid=(\d+)')
shareid_match = shareid_reg.search(url)
if not uk_match or not shareid_match:
return '', ''
uk = uk_match.group(1)
shareid = shareid_match.group(1)
return uk, shareid
def parse_surl(url):
surl_reg1 = re.compile('surl=(.+)')
surl_match1 = surl_reg1.search(url)
surl_reg2 = re.compile('/s/(.+)')
surl_match2 = surl_reg2.search(url)
if surl_match1:
return surl_match1.group(1)
elif surl_match2:
return surl_match2.group(1)
else:
return None
# 处理重定向
MAX_REDIRECT = 5
for i in range(0, MAX_REDIRECT):
req = net.urlopen_without_redirect(url,
headers={
'Cookie':
cookie.header_output(),
})
if req:
if (req.status == 301
or req.status == 302) and req.headers.get('Location'):
url = req.headers.get('Location')
continue
break
# 处理加密链接
if url.find('share/init') > -1 or url.find('wap/init') > -1:
if url.find('init?surl') > -1:
surl = parse_surl(url)
return True, surl
else:
uk, shareid = parse_share_uk_from_url(url)
return True, None, uk, shareid
# 处理短链接
if url.startswith('http://pan.baidu.com/s/') or url.startswith(
'https://pan.baidu.com/s/'):
surl = parse_surl(url)
req = net.urlopen(url, headers={
'Cookie': cookie.header_output(),
})
if req:
uk, shareid = parse_share_uk(req.data.decode())
return False, surl, uk, shareid
# 处理其他链接
surl = parse_surl(url)
uk, shareid = parse_share_uk_from_url(url)
return False, surl, uk, shareid
