def get_token(cookie):
'''获取一个页面访问的token, 这里需要之前得到的BAIDUID 这个cookie值
这个token的有效期还不确定.
返回的数据如下:
{"errInfo":{"no": "0"},
"data": {
"rememberedUserName" : "",
"codeString" : "",
"token" : "xxxxx",
"cookie" : "1",
"usernametype":"2",
"spLogin" : "rate",
"disable":"",
"loginrecord":{ 'email':[ ], 'phone':[]}
}}
'''
url = ''.join([
const.PASSPORT_URL,
'?getapi&tpl=pp&apiver=v3',
'&tt=', util.timestamp(),
'&class=login&logintype=basicLogin',
])
headers={
'Cookie': cookie.header_output(),
'Accept': const.ACCEPT_HTML,
'Cache-control': 'max-age=0',
}
req = net.urlopen(url, headers=headers)
if req:
cookie = req.headers.get_all('Set-Cookie')
content_obj = util.json_loads_single(req.data.decode())
if content_obj:
return cookie, content_obj['data']['token']
return None
def rapid_upload(cookie, tokens, source_path, path, upload_mode):
'''快速上传'''
ondup = const.UPLOAD_ONDUP[upload_mode]
if not ondup:
ondup = 'newcopy'
content_length = os.path.getsize(source_path)
assert content_length > RAPIDUPLOAD_THRESHOLD, 'file size is not satisfied!'
dir_name, file_name = os.path.split(path)
content_md5 = hasher.md5(source_path)
slice_md5 = hasher.md5(source_path, 0, RAPIDUPLOAD_THRESHOLD)
url = ''.join([
const.PCS_URL_C,
'file?method=rapidupload&app_id=250528',
'&ondup=newcopy',
'&dir=', encoder.encode_uri_component(dir_name),
'&filename=', encoder.encode_uri_component(file_name),
'&content-length=', str(content_length),
'&content-md5=', content_md5,
'&slice-md5=', slice_md5,
'&path=', encoder.encode_uri_component(path),
'&', cookie.sub_output('BDUSS'),
'&bdstoken=', tokens['bdstoken'],
])
req = net.urlopen(url, headers={'Cookie': cookie.header_output()})
if req:
return json.loads(req.data.decode())
else:
return None
def enable_private_share(cookie, tokens, fid_list, passwd='smfx'):
'''建立新的私密分享.
密码是在本地生成的, 然后上传到服务器.
'''
url = ''.join([
const.PAN_URL,
'share/set?channel=chunlei&clienttype=0&web=1',
'&bdstoken=', tokens['bdstoken'],
'&channel=chunlei&clienttype=0&web=1',
'&appid=250528',
])
data = encoder.encode_uri(''.join([
'fid_list=', str(fid_list),
'&schannel=4&channel_list=[]',
'&pwd=', passwd,
]))
req = net.urlopen(url, headers={
'Cookie': cookie.header_output(),
'Content-type': const.CONTENT_FORM_UTF8,
}, data=data.encode())
if req:
content = req.data
return json.loads(content.decode()), passwd
else:
return None, passwd
def enable_share(cookie, tokens, fid_list):
'''建立新的分享.
fid_list - 是一个list, 里面的每一条都是一个文件的fs_id
一次可以分享同一个目录下的多个文件/目录, 它们会会打包为一个分享链接,
这个分享链接还有一个对应的shareid. 我们可以用uk与shareid来在百度网盘里
面定位到这个分享内容.
@return - 会返回分享链接和shareid.
'''
url = ''.join([
const.PAN_URL,
'share/set?channel=chunlei&clienttype=0&web=1',
'&bdstoken=', tokens['bdstoken'],
])
data = encoder.encode_uri(
'fid_list={0}&schannel=0&channel_list=[]'.format(fid_list))
req = net.urlopen(url, headers={
'Cookie': cookie.header_output(),
'Content-type': const.CONTENT_FORM_UTF8,
}, data=data.encode())
if req:
content = req.data
return json.loads(content.decode())
else:
return None
def get_share_page(url):
'''获取共享页面的文件信息'''
req = net.urlopen(url)
if req:
content = req.data.decode()
match = re.findall('applicationConfig,(.+)\]\);', content)
share_files = {}
if not match:
match = re.findall('viewShareData=(.+");FileUtils.spublic', content)
if not match:
logger.error('get_share_page(): %s, %s' % (url, match))
return None
list_ = json.loads(json.loads(match[0]))
else:
list_ = json.loads(json.loads(match[0]))
if isinstance(list_, dict):
share_files['list'] = [list_, ]
else:
share_files['list'] = list_
id_match = re.findall('FileUtils\.share_id="(\d+)"', content)
uk_match = re.findall('/share/home\?uk=(\d+)" target=', content)
sign_match = re.findall('FileUtils\.share_sign="([^"]+)"', content)
if id_match and uk_match and sign_match:
share_files['share_id'] = id_match[0]
share_files['uk'] = uk_match[0]
share_files['sign'] = sign_match[0]
return share_files
return None
def share_transfer(cookie, tokens, shareid, uk, filelist, dest, upload_mode):
'''
将其他用户的文件保存到自己网盘里.
uk - 其他用户的uk
filelist - 要转移文件的列表, 是绝对路径
'''
ondup = const.UPLOAD_ONDUP[upload_mode]
url = ''.join([
const.PAN_URL,
'share/transfer?app_id=250528&channel=chunlei&clienttype=0&web=1',
'&bdstoken=', tokens['bdstoken'],
'&from=', uk,
'&shareid=', shareid,
'&ondup=', ondup,
'&async=1',
])
data = ''.join([
'path=', encoder.encode_uri_component(dest),
'&filelist=', encoder.encode_uri_component(json.dumps(filelist))
])
req = net.urlopen(url, headers={
'Cookie': cookie.header_output(),
'Content-Type': const.CONTENT_FORM_UTF8
}, data=data.encode())
if req:
content = req.data.decode()
return json.loads(content)
else:
return None
def list_trash(cookie, tokens, path='/', page=1, num=100):
'''获取回收站的信息.
path - 目录的绝对路径, 默认是根目录
page - 页码, 默认是第一页
num - 每页有多少个文件, 默认是100个.
回收站里面的文件会被保存10天, 10天后会自动被清空.
回收站里面的文件不占用用户的存储空间.
'''
url = ''.join([
const.PAN_API_URL,
'recycle/list?channel=chunlei&clienttype=0&web=1',
'&num=', str(num),
'&t=', util.timestamp(),
'&dir=', encoder.encode_uri_component(path),
'&t=', util.latency(),
'&order=time&desc=1',
'&_=', util.timestamp(),
'&bdstoken=', tokens['bdstoken'],
])
req = net.urlopen(url, headers={'Cookie': cookie.header_output()})
if req:
content = req.data
return json.loads(content.decode())
else:
return None
def list_share_files(cookie, tokens, uk, shareid, dirname, page=1):
'''列举出用户共享的某一个目录中的文件信息
这个对所有用户都有效
uk - user key
shareid - 共享文件的ID值
dirname - 共享目录, 如果dirname为None, 说明这有可能是一个单独共享的文件,
这里, 需要调用list_share_single_file()
'''
if not dirname:
return list_share_single_file(cookie, tokens, uk, shareid)
url = ''.join([
const.PAN_URL,
'share/list?channel=chunlei&clienttype=0&web=1&num=50',
'&t=', util.timestamp(),
'&page=', str(page),
'&dir=', encoder.encode_uri_component(dirname),
'&t=', util.latency(),
'&shareid=', shareid,
'&order=time&desc=1',
'&uk=', uk,
'&_=', util.timestamp(),
'&bdstoken=', tokens['bdstoken'],
])
req = net.urlopen(url, headers={
'Cookie': cookie.header_output(),
'Referer': const.SHARE_REFERER,
})
if req:
content = req.data
info = json.loads(content.decode())
if info['errno'] == 0:
return info['list']
return list_share_single_file(cookie, tokens, uk, shareid)
def list_share(cookie, tokens, uk, page=1):
'''获取用户已经共享的所有文件的信息
uk - user key
page - 页数, 默认为第一页.
num - 一次性获取的共享文件的数量, 默认为100个.
'''
num = 100
start = 100 * (page - 1)
url = ''.join([
const.PAN_URL,
'pcloud/feed/getsharelist?',
'&t=', util.timestamp(),
'&categor=0&auth_type=1&request_location=share_home',
'&start=', str(start),
'&limit=', str(num),
'&query_uk=', str(uk),
'&channel=chunlei&clienttype=0&web=1',
'&bdstoken=', tokens['bdstoken'],
])
req = net.urlopen(url, headers={
'Cookie': cookie.header_output(),
'Referer': const.SHARE_REFERER,
})
if req:
content = req.data
return json.loads(content.decode())
else:
return None
def list_share_path(cookie, tokens, uk, path, share_id, page):
'''列举出用户共享的某一个目录中的文件信息
uk - user key
path - 共享目录
share_id - 共享文件的ID值
'''
url = ''.join([
const.PAN_URL,
'share/list?channel=chunlei&clienttype=0&web=1&num=100',
'&t=', util.timestamp(),
'&page=', str(page),
'&dir=', encoder.encode_uri_component(path),
'&t=', util.latency(),
'&shareid=', share_id,
'&order=time&desc=1',
'&uk=', uk,
'&_=', util.timestamp(),
'&bdstoken=', tokens['bdstoken'],
])
req = net.urlopen(url, headers={
'Cookie': cookie.header_output(),
'Referer': const.SHARE_REFERER,
})
if req:
content = req.data
return json.loads(content.decode())
else:
return None
def get_metas(cookie, tokens, filelist, dlink=True):
'''获取多个文件的metadata.
filelist - 一个list, 里面是每个文件的绝对路径.
也可以是一个字符串, 只包含一个文件的绝对路径.
dlink - 是否包含下载链接, 默认为True, 包含.
@return 包含了文件的下载链接dlink, 通过它可以得到最终的下载链接.
'''
if isinstance(filelist, str):
filelist = [filelist, ]
url = ''.join([
const.PAN_API_URL,
'filemetas?channel=chunlei&clienttype=0&web=1',
'&bdstoken=', tokens['bdstoken'],
])
if dlink:
data = ('dlink=1&target=' +
encoder.encode_uri_component(json.dumps(filelist)))
else:
data = ('dlink=0&target=' +
encoder.encode_uri_component(json.dumps(filelist)))
req = net.urlopen(url, headers={
'Cookie': cookie.sub_output('BDUSS'),
'Content-type': const.CONTENT_FORM,
}, data=data.encode())
if req:
content = req.data
return json.loads(content.decode())
else:
return None
def verify_share_password(uk, shareid, pwd, vcode=''):
'''验证共享文件的密码.
如果密码正确, 会在返回的请求头里加入一个cookie: BDCLND
pwd - 四位的明文密码
vcode - 验证码; 目前还不支持
'''
url = ''.join([
const.PAN_URL,
'share/verify?&clienttype=0&web=1&channel=chunlei',
'&shareid=', shareid,
'&uk=', uk,
])
data = 'pwd={0}&vcode={1}'.format(pwd, vcode)
req = net.urlopen(url, data=data.encode())
if req:
content = req.data.decode()
info = json.loads(content)
errno = info.get('errno', 1)
if errno == 0:
return req.headers.get_all('Set-Cookie')
elif errno in (-19, -62, -63):
pass # TODO: need verify code
return None
def cloud_query_magnetinfo(cookie, tokens, source_url, save_path):
'''获取磁链的信息.
在新建磁链任务时, 要先获取这个磁链的信息, 比如里面包含哪些文件, 文件的名
称与大小等.
source_url - 磁链的url, 以magent:开头.
save_path - 保存到哪个目录
'''
url = ''.join([
const.PAN_URL,
'rest/2.0/services/cloud_dl?channel=chunlei&clienttype=0&web=1',
'&bdstoken=', tokens['bdstoken'],
])
data = ''.join([
'method=query_magnetinfo&app_id=250528',
'&source_url=', encoder.encode_uri_component(source_url),
'&save_path=', encoder.encode_uri_component(save_path),
'&type=4',
])
req = net.urlopen(url, headers={'Cookie': cookie.header_output()},
data=data.encode())
if req:
content = req.data
return json.loads(content.decode())
else:
return None
def check_login(cookie, tokens, username):
'''进行登录验证, 主要是在服务器上验证这个帐户的状态.
如果帐户不存在, 或者帐户异常, 就不需要再进行最后一步的登录操作了.
这一步有可能需要输入验证码.
返回的信息如下:
{"errInfo":{ "no": "0" }, "data": { "codeString" : "", "vcodetype" : "" }}
'''
url = ''.join([
const.PASSPORT_URL,
'?logincheck',
'&token=', tokens['token'],
'&tpl=mm&apiver=v3',
'&tt=', util.timestamp(),
'&username='******'&isphone=false',
])
headers={
'Cookie': cookie.header_output(),
'Referer': const.REFERER,
}
req = net.urlopen(url, headers=headers)
if req:
ubi = req.headers.get_all('Set-Cookie')
return ubi, json.loads(req.data.decode())
else:
return None
def refresh_signin_vcode(cookie, tokens, vcodetype):
'''刷新验证码.
vcodetype - 在调用check_login()时返回的vcodetype.
'''
url = ''.join([
const.PASSPORT_BASE,
'v2/?reggetcodestr',
'&token=', tokens['token'],
'&tpl=pp&apiver=v3',
'&tt=', util.timestamp(),
'&fr=ligin',
'&vcodetype=', encoder.encode_uri(vcodetype),
])
headers={
'Cookie': cookie.header_output(),
'Referer': const.REFERER,
}
logger.debug('refresh vcode url: %s' % url)
req = net.urlopen(url, headers=headers)
if req:
try:
data = req.data.decode('gbk')
logger.debug('refresh vcode: %s' % data)
return json.loads(data)
except ValueError:
logger.error(traceback.format_exc())
return None
def get_category(cookie, tokens, category, page=1):
'''获取一个分类中的所有文件信息, 比如音乐/图片
目前的有分类有:
视频 - 1
音乐 - 2
图片 - 3
文档 - 4
应用 - 5
其它 - 6
BT种子 - 7
'''
timestamp = util.timestamp()
url = ''.join([
const.PAN_API_URL,
'categorylist?channel=chunlei&clienttype=0&web=1',
'&category=', str(category),
'&pri=-1&num=100',
'&t=', timestamp,
'&page=', str(page),
'&order=time&desc=1',
'&_=', timestamp,
'&bdstoken=', cookie.get('STOKEN').value,
])
req = net.urlopen(url, headers={'Cookie': cookie.header_output()})
if req:
content = req.data
return json.loads(content.decode())
else:
return None
def post_login(cookie, token, username, password, rsakey, verifycode='',
codestring=''):
'''登录验证.
password - 使用RSA加密后的base64字符串
rsakey - 与public_key相匹配的rsakey
verifycode - 验证码, 默认为空
@return (status, info). 其中, status表示返回的状态:
0 - 正常, 这里, info里面存放的是auth_cookie
-1 - 未知异常
4 - 密码错误
257 - 需要输入验证码, 此时info里面存放着(vcodetype, codeString))
'''
url = const.PASSPORT_LOGIN
data = ''.join([
'staticpage=https%3A%2F%2Fpassport.baidu.com%2Fstatic%2Fpasspc-account%2Fhtml%2Fv3Jump.html&charset=UTF-8',
'&token=', token,
'&tpl=pp&subpro=&apiver=v3',
'&tt=', util.timestamp(),
'&codestring=', codestring,
'&safeflg=0&u=https%3A%2F%2Fpassport.baidu.com%2F&isPhone=',
'&quick_user=0&logintype=basicLogin&logLoginType=pc_loginBasic&idc=',
'&loginmerge=true',
'&username='******'&password='******'&verifycode=', verifycode,
'&mem_pass=on',
'&rsakey=', rsakey,
'&crypttype=12&ppui_logintime=',get_ppui_logintime(),
'&callback=parent.bd__pcbs__m8g1kg',
])
logger.debug('auth.post_login: %s' % data)
headers={
'Cookie': cookie.header_output(),
'Content-Type': const.CONTENT_FORM,
'Referer': const.REFERER,
'Connection': 'Keep-Alive',
}
req = net.urlopen(url, headers=headers, data=data.encode())
if req:
auth_cookie = req.headers.get_all('Set-Cookie')
resp_content= req.data.decode()
match = re.findall('"(err_no[^"]+)"', resp_content)
if len(match) != 1:
return (-1, None)
query = dict(urllib.parse.parse_qsl(match[0]))
err_no = int(query.get('err_no', '-1'))
if err_no == 0:
return (0, auth_cookie)
if err_no != 257:
return (err_no, None)
vcodetype = query.get('vcodetype', '')
codeString = query.get('codeString', '')
if vcodetype and codeString:
return (257, (vcodetype, codeString))
return (-1, None)
else:
return (-1, None)
return (-1, None)
def dump_image(url, filepath):
req = net.urlopen(url)
if not req or not req.data:
logger.warn('update_liststore_image(), failed to request %s' % url)
return False
with open(filepath, 'wb') as fh:
fh.write(req.data)
return True
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_BAIDUID():
'''获取一个cookie - BAIDUID.
这里, 我们访问百度首页, 返回的response header里面有我们需要的cookie
'''
req = net.urlopen(const.REFERER)
if req:
return req.headers.get_all('Set-Cookie')
else:
return None
def get_user_uk(cookie, tokens):
'''获取用户的uk'''
url = 'http://yun.baidu.com'
req = net.urlopen(url, headers={'Cookie': cookie.header_output()})
if req:
content = req.data.decode()
match = re.findall('/share/home\?uk=(\d+)" target=', content)
if len(match) == 1:
return match[0]
return None
def get_bdstoken(cookie):
'''从/disk/home页面获取bdstoken等token信息
这些token对于之后的请求非常重要.
'''
url = const.PAN_REFERER
req = net.urlopen(url, headers={'Cookie': cookie.header_output()})
if req:
return parse_bdstoken(req.data.decode())
else:
return None
def get_wap_signin_vcode(cookie, codeString):
'''获取wap登录时的验证码'''
url = 'http://wappass.baidu.com/cgi-bin/genimage?' + codeString
req = net.urlopen(url, headers={
'Cookie': cookie.header_output(),
'Referer': 'http://wappass.badu.com',
})
if req:
return req.data
else:
return None
def get_wap_passport():
'''WAP登录.
返回cookie和登录form'''
url = 'http://wappass.baidu.com/passport'
req = net.urlopen(url)
if req:
return (req.headers.get_all('Set-Cookie'),
parse_wap_passport(req.data.decode()))
else:
return None, None
def get_user_uk(cookie, tokens):
'''获取用户的uk'''
url = 'http://yun.baidu.com'
req = net.urlopen(url, headers={'Cookie': cookie.header_output()})
if req:
content = req.data.decode()
match = re.findall(',\"uk\":(\d+),', content)
if len(match) == 1:
return match[0]
else:
logger.warn('pcs.get_user_uk(), failed to parse uk, %s' % url)
return None
def cloud_add_bt_task(cookie,
tokens,
source_url,
save_path,
selected_idx,
file_sha1='',
vcode='',
vcode_input=''):
'''新建一个BT类的离线下载任务, 包括magent磁链.
source_path - BT种子所在的绝对路径
save_path - 下载的文件要存放到的目录
selected_idx - BT种子中, 包含若干个文件, 这里, 来指定要下载哪些文件,
从1开始计数.
file_sha1 - BT种子的sha1值, 如果是magent的话, 这个sha1值可以为空
vcode - 验证码的vcode
vcode_input - 用户输入的四位验证码
'''
url = ''.join([
const.PAN_URL,
'rest/2.0/services/cloud_dl?channel=chunlei&clienttype=0&web=1',
'&bdstoken=',
tokens['bdstoken'],
])
type_ = '2'
url_type = 'source_path'
if source_url.startswith('magnet:'):
type_ = '4'
url_type = 'source_url'
if not save_path.endswith('/'):
save_path = save_path + '/'
data = [
'method=add_task&app_id=250528', '&file_sha1=', file_sha1,
'&save_path=',
encoder.encode_uri_component(save_path), '&selected_idx=',
','.join(str(i) for i in selected_idx), '&task_from=1', '&t=',
util.timestamp(), '&', url_type, '=',
encoder.encode_uri_component(source_url), '&type=', type_
]
if vcode:
data.append('&input=')
data.append(vcode_input)
data.append('&vcode=')
data.append(vcode)
data = ''.join(data)
req = net.urlopen(url,
headers={'Cookie': cookie.header_output()},
data=data.encode())
if req:
content = req.data
return json.loads(content.decode())
else:
return None
def get_quota(cookie, tokens):
'''获取当前的存储空间的容量信息.'''
url = ''.join([
const.PAN_API_URL,
'quota?channel=chunlei&clienttype=0&web=1',
'&t=', util.timestamp(),
])
req = net.urlopen(url, headers={'Cookie': cookie.header_output()})
if req:
content = req.data
return json.loads(content.decode())
else:
return None
def get_quota(cookie, tokens):
'''获取当前的存储空间的容量信息.'''
url = ''.join([
const.PAN_API_URL,
'quota?channel=chunlei&clienttype=0&web=1',
'&t=', util.timestamp(),
])
req = net.urlopen(url, headers={'Cookie': cookie.header_output()})
if req:
content = req.data
return json.loads(content.decode())
else:
return None
def get_bdstoken(cookie):
'''从/disk/home页面获取bdstoken等token信息
这些token对于之后的请求非常重要.
'''
url = const.PAN_REFERER
req = net.urlopen(url,
headers={'Cookie': cookie.header_output()},
cookie=cookie)
if req:
return parse_bdstoken(req.data.decode())
else:
return None
def list_share_single_file(cookie, tokens, uk, shareid, surl):
'''获取单独共享出来的文件.
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
'''
def parse_share_page(content):
tree = html.fromstring(content)
script_sel = CSS('script')
scripts = script_sel(tree)
for script in scripts:
if script.text and (script.text.find('yunData.setData') > -1
or script.text.find('window.yunData') > -1):
break
else:
logger.warn('pcs.parse_share_page: failed to get filelist, %s',
url)
return None
type1 = ',"third":0,"bdstoken":'
type2 = ',"uk":'
start = script.text.find('"file_list":')
end = script.text.find(type1)
if start == -1: return None
if end == -1:
end = script.text.find(type2)
if end == -1:
return None
json_str = script.text[start + 12:end]
try:
return json.loads(json_str)
except ValueError:
logger.warn(traceback.format_exc())
return None
url = ''.join([const.PAN_URL, 'wap/link', '?third=0'])
if surl:
url = '{0}&surl={1}'.format(url, surl)
else:
url = '{0}&uk={1}&shareid={2}'.format(url, uk, shareid)
req = net.urlopen(url,
headers={
'Cookie': cookie.header_output(),
'Referer': const.SHARE_REFERER,
})
if req:
return parse_share_page(req.data.decode())
else:
return None
def get_bdstoken(cookie):
print(
'/usr/local/lib/python3.4/dist-packages/bcloud/auth.py:get_bdstoken 281'
)
'''从/disk/home页面获取bdstoken等token信息
这些token对于之后的请求非常重要.
'''
url = const.PAN_REFERER
req = net.urlopen(url, headers={'Cookie': cookie.header_output()})
if req:
return parse_bdstoken(req.data.decode())
else:
return None
def get_user_uk(cookie, tokens):
print(
'/usr/local/lib/python3.4/dist-packages/bcloud/pcs.py:get_user_uk 42')
'''获取用户的uk'''
url = 'http://yun.baidu.com'
req = net.urlopen(url, headers={'Cookie': cookie.header_output()})
if req:
content = req.data.decode()
match = re.findall('/share/home\?uk=(\d+)" target=', content)
if len(match) == 1:
return match[0]
else:
logger.warn('pcs.get_user_uk(), failed to parse uk, %s' % url)
return None
def list_share_single_file(cookie, tokens, uk, shareid):
'''获取单独共享出来的文件.
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
'''
def parse_share_page(content):
tree = html.fromstring(content)
script_sel = CSS('script')
scripts = script_sel(tree)
for script in scripts:
if (script.text and (script.text.find('viewsingle_param') > -1 or
script.text.find('mpan.viewlist_param') > -1)):
break
else:
logger.warn('pcs.parse_share_page: failed to get filelist, %s', url)
return None
start = script.text.find('viewsingle_param.list=JSON.parse(')
end = script.text.find(');mpan.viewsingle_param.username')
if start == -1 or end == -1:
start = script.text.find('listArr:JSON.parse(')
end = script.text.find('),rootPath:')
if start == -1 or end == -1:
return None
else:
json_str = script.text[start+19:end]
else:
json_str = script.text[start+33:end]
try:
return json.loads(json.loads(json_str))
except ValueError:
logger.warn(traceback.format_exc())
return None
url = ''.join([
const.PAN_URL, 'wap/link',
'?shareid=', shareid,
'&uk=', uk,
'&third=0',
])
req = net.urlopen(url, headers={
'Cookie': cookie.header_output(),
'Referer': const.SHARE_REFERER,
})
if req:
return parse_share_page(req.data.decode())
else:
return None
def list_share_single_file(cookie, tokens, uk, shareid):
'''获取单独共享出来的文件.
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
'''
def parse_share_page(content):
tree = html.fromstring(content)
script_sel = CSS('script')
scripts = script_sel(tree)
for script in scripts:
if (script.text and (script.text.find('viewsingle_param') > -1 or
script.text.find('mpan.viewlist_param') > -1)):
break
else:
logger.warn('pcs.parse_share_page: failed to get filelist, %s', url)
return None
start = script.text.find('viewsingle_param.list=JSON.parse(')
end = script.text.find(');mpan.viewsingle_param.username')
if start == -1 or end == -1:
start = script.text.find('listArr:JSON.parse(')
end = script.text.find('),rootPath:')
if start == -1 or end == -1:
return None
else:
json_str = script.text[start+19:end]
else:
json_str = script.text[start+33:end]
try:
return json.loads(json.loads(json_str))
except ValueError:
logger.warn(traceback.format_exc())
return None
url = ''.join([
const.PAN_URL, 'wap/link',
'?shareid=', shareid,
'&uk=', uk,
'&third=0',
])
req = net.urlopen(url, headers={
'Cookie': cookie.header_output(),
'Referer': const.SHARE_REFERER,
})
if req:
return parse_share_page(req.data.decode())
else:
return None
def cloud_add_link_task(cookie,
tokens,
source_url,
save_path,
vcode='',
vcode_input=''):
'''新建离线下载任务.
source_url - 可以是http/https/ftp等一般的链接
可以是eMule这样的链接
path - 要保存到哪个目录, 比如 /Music/, 以/开头, 以/结尾的绝对路径.
'''
url = ''.join([
const.PAN_URL,
'rest/2.0/services/cloud_dl?channel=chunlei',
'&clienttype=',
const.PC_CLIENT_TYPE,
'&web=1',
'&bdstoken=',
tokens['bdstoken'],
])
type_ = ''
if source_url.startswith('ed2k'):
type_ = '&type=3'
if not save_path.endswith('/'):
save_path = save_path + '/'
data = [
'method=add_task&app_id=250528',
'&source_url=',
encoder.encode_uri_component(source_url),
'&save_path=',
encoder.encode_uri_component(save_path),
'&type=',
type_,
]
if vcode:
data.append('&input=')
data.append(vcode_input)
data.append('&vcode=')
data.append(vcode)
data = ''.join(data)
req = net.urlopen(url,
headers={'Cookie': cookie.header_output()},
data=data.encode())
if req:
content = req.data
return json.loads(content.decode())
else:
return None
def send_sms(cookie, tokens):
'''要求百度向绑定的手机号上发一条包含验证码的短信'''
url = ''.join([
const.PASSPORT_BASE,
'v2/sapi/authwidgetverify',
'?authtoken=',
tokens['authtoken'],
'&type=mobile&jsonp=1&apiver=v3&verifychannel=&action=send',
'&vcode=&needsid=&rsakey=&subpro=',
])
req = net.urlopen(url, headers={'Cookie': cookie.header_output()})
if req:
return json.loads(req.data.decode())
else:
return None
def cloud_clear_task(cookie, tokens):
'''清空离线下载的历史(已经完成或者取消的).'''
url = ''.join([
const.PAN_URL,
'rest/2.0/services/cloud_dl?method=clear_task&app_id=250528',
'&channel=chunlei&clienttype=0&web=1',
'&t=', util.timestamp(),
'&bdstoken=', tokens['bdstoken'],
])
req = net.urlopen(url, headers={'Cookie': cookie.header_output()})
if req:
content = req.data
return json.loads(content.decode())
else:
return None
def get_quota(cookie, tokens):
print('/usr/local/lib/python3.4/dist-packages/bcloud/pcs.py:get_quota 28')
'''获取当前的存储空间的容量信息.'''
url = ''.join([
const.PAN_API_URL,
'quota?channel=chunlei&clienttype=0&web=1',
'&t=',
util.timestamp(),
])
req = net.urlopen(url, headers={'Cookie': cookie.header_output()})
if req:
content = req.data
return json.loads(content.decode())
else:
return None
def cloud_clear_task(cookie, tokens):
'''清空离线下载的历史(已经完成或者取消的).'''
url = ''.join([
const.PAN_URL,
'rest/2.0/services/cloud_dl?method=clear_task&app_id=250528',
'&channel=chunlei&clienttype=0&web=1',
'&t=', util.timestamp(),
'&bdstoken=', tokens['bdstoken'],
])
req = net.urlopen(url, headers={'Cookie': cookie.header_output()})
if req:
content = req.data
return json.loads(content.decode())
else:
return None
def get_BAIDUID():
'''获取一个cookie - BAIDUID.
这里, 我们访问百度首页, 返回的response header里面有我们需要的cookie
'''
url = ''.join([
const.PASSPORT_URL,
'?getapi&tpl=mn&apiver=v3',
'&tt=', util.timestamp(),
'&class=login&logintype=basicLogin',
])
req = net.urlopen(url, headers={'Referer': ''})
if req:
return req.headers.get_all('Set-Cookie')
else:
return None
def cloud_add_bt_task(cookie, tokens, source_url, save_path, selected_idx,
file_sha1='', vcode='', vcode_input=''):
'''新建一个BT类的离线下载任务, 包括magent磁链.
source_path - BT种子所在的绝对路径
save_path - 下载的文件要存放到的目录
selected_idx - BT种子中, 包含若干个文件, 这里, 来指定要下载哪些文件,
从1开始计数.
file_sha1 - BT种子的sha1值, 如果是magent的话, 这个sha1值可以为空
vcode - 验证码的vcode
vcode_input - 用户输入的四位验证码
'''
url = ''.join([
const.PAN_URL,
'rest/2.0/services/cloud_dl?channel=chunlei&clienttype=0&web=1',
'&bdstoken=', tokens['bdstoken'],
])
type_ = '2'
url_type = 'source_path'
if source_url.startswith('magnet:'):
type_ = '4'
url_type = 'source_url'
if not save_path.endswith('/'):
save_path = save_path + '/'
data = [
'method=add_task&app_id=250528',
'&file_sha1=', file_sha1,
'&save_path=', encoder.encode_uri_component(save_path),
'&selected_idx=', ','.join(str(i) for i in selected_idx),
'&task_from=1',
'&t=', util.timestamp(),
'&', url_type, '=', encoder.encode_uri_component(source_url),
'&type=', type_
]
if vcode:
data.append('&input=')
data.append(vcode_input)
data.append('&vcode=')
data.append(vcode)
data = ''.join(data)
req = net.urlopen(url, headers={'Cookie': cookie.header_output()},
data=data.encode())
if req:
content = req.data
return json.loads(content.decode())
else:
return None
def clear_trash(cookie, tokens):
'''清空回收站, 将里面的所有文件都删除.'''
url = ''.join([
const.PAN_API_URL,
'recycle/clear?channel=chunlei&clienttype=0&web=1',
'&t=', util.timestamp(),
'&bdstoken=', tokens['bdstoken'],
])
# 使用POST方式发送命令, 但data为空.
req = net.urlopen(url, headers={
'Cookie': cookie.header_output(),
}, data=''.encode())
if req:
content = req.data
return json.loads(content.decode())
else:
return None
def list_inbox(cookie, tokens, start=0, limit=20):
'''获取收件箱里的文件信息.'''
url = ''.join([
const.PAN_URL,
'inbox/object/list?type=1',
'&start=', str(start),
'&limit=', str(limit),
'&_=', util.timestamp(),
'&channel=chunlei&clienttype=0&web=1',
'&bdstoken=', tokens['bdstoken'],
])
req = net.urlopen(url, headers={'Cookie': cookie.header_output()})
if req:
content = req.data
return json.loads(content.decode())
else:
return None
def list_share_files(cookie, tokens, uk, shareid, dirname, page=1):
print(
'/usr/local/lib/python3.4/dist-packages/bcloud/pcs.py:list_share_files 105'
)
'''列举出用户共享的某一个目录中的文件信息
这个对所有用户都有效
uk - user key
shareid - 共享文件的ID值
dirname - 共享目录, 如果dirname为None, 说明这有可能是一个单独共享的文件,
这里, 需要调用list_share_single_file()
'''
if not dirname:
return list_share_single_file(cookie, tokens, uk, shareid)
url = ''.join([
const.PAN_URL,
'share/list?channel=chunlei&clienttype=0&web=1&num=50',
'&t=',
util.timestamp(),
'&page=',
str(page),
'&dir=',
encoder.encode_uri_component(dirname),
'&t=',
util.latency(),
'&shareid=',
shareid,
'&order=time&desc=1',
'&uk=',
uk,
'&_=',
util.timestamp(),
'&bdstoken=',
tokens['bdstoken'],
])
req = net.urlopen(url,
headers={
'Cookie': cookie.header_output(),
'Referer': const.SHARE_REFERER,
})
if req:
content = req.data
info = json.loads(content.decode())
if info['errno'] == 0:
return info['list']
return list_share_single_file(cookie, tokens, uk, shareid)
def clear_trash(cookie, tokens):
'''清空回收站, 将里面的所有文件都删除.'''
url = ''.join([
const.PAN_API_URL,
'recycle/clear?channel=chunlei&clienttype=0&web=1',
'&t=', util.timestamp(),
'&bdstoken=', tokens['bdstoken'],
])
# 使用POST方式发送命令, 但data为空.
req = net.urlopen(url, headers={
'Cookie': cookie.header_output(),
}, data=''.encode())
if req:
content = req.data
return json.loads(content.decode())
else:
return None
def get_sign_and_timestamp(cookie):
'''获得部分API需要的timestamp和sign参数.'''
req = net.urlopen(const.PAN_URL,
headers={'Cookie': cookie.header_output()})
if req:
content = req.data.decode()
sign1_match = re.findall('"sign1":"(.+)","sign2"', content)
sign3_match = re.findall('"sign3":"(.+)","timestamp"', content)
timestamp_match = re.findall(',"timestamp":(\d+)', content)
if len(sign1_match) == 1 and len(sign3_match) == 1 and len(
timestamp_match) == 1:
timestamp = int(timestamp_match[0])
sign1 = sign1_match[0]
sign3 = sign3_match[0]
sign = util.RC4_encrypt(sign3, sign1)
if sign:
return sign, timestamp
return None, None
def get_user_info(tokens, uk):
'''获取用户的部分信息.
比如头像, 用户名, 自我介绍, 粉丝数等.
这个接口可用于查询任何用户的信息, 只要知道他/她的uk.
'''
url = ''.join([
const.PAN_URL,
'pcloud/user/getinfo?channel=chunlei&clienttype=0&web=1',
'&bdstoken=', tokens['bdstoken'],
'&query_uk=', uk,
'&t=', util.timestamp(),
])
req = net.urlopen(url)
if req:
info = json.loads(req.data.decode())
if info and info['errno'] == 0:
return info['user_info']
return None
def get_signin_vcode(cookie, codeString):
'''获取登录时的验证码图片.
codeString - 调用check_login()时返回的codeString.
'''
url = ''.join([
const.PASSPORT_BASE,
'cgi-bin/genimage?',
codeString,
])
headers={
'Cookie': cookie.header_output(),
'Referer': const.REFERER,
}
req = net.urlopen(url, headers=headers)
if req:
return req.data
else:
return None
def get_streaming_playlist(cookie, path, video_type='M3U8_AUTO_480'):
'''获取流媒体(通常是视频)的播放列表.
默认得到的是m3u8格式的播放列表, 因为它最通用.
path - 视频的绝对路径
video_type - 视频格式, 可以根据网速及片源, 选择不同的格式.
'''
url = ''.join([
const.PCS_URL,
'file?method=streaming',
'&path=', encoder.encode_uri_component(path),
'&type=', video_type,
'&app_id=250528',
])
req = net.urlopen(url, headers={'Cookie': cookie.header_output()})
if req:
return req.data
else:
return None
def get_BAIDUID():
print(
'/usr/local/lib/python3.4/dist-packages/bcloud/auth.py:get_BAIDUID 28')
'''获取一个cookie - BAIDUID.
这里, 我们访问百度首页, 返回的response header里面有我们需要的cookie
'''
url = ''.join([
const.PASSPORT_URL,
'?getapi&tpl=mn&apiver=v3',
'&tt=',
util.timestamp(),
'&class=login&logintype=basicLogin',
])
req = net.urlopen(url, headers={'Referer': ''})
if req:
return req.headers.get_all('Set-Cookie')
else:
return None
def unzip_view(cookie,
tokens,
path,
subpath="/",
start=0,
limit=100,
return_path=False):
'''查看压缩包的文件列表
path - 压缩包的绝对路径（支持2GB以内的rar,zip压缩包）
subpath - 压缩包内的相对路径，默认是根目录“/”
start - 从第几个文件开始
limit - 一次最大列出文件数
'''
url = ''.join([
const.PAN_API_URL,
'unzip/list?app_id=250528&channel=chunlei&clienttype=0&web=1&appid=250528',
'&path=',
encoder.encode_uri_component(path),
'&subpath=',
encoder.encode_uri_component(subpath),
'&start=',
str(start),
'&limit=',
str(limit),
'&bdstoken=',
tokens['bdstoken'],
])
req = net.urlopen(url,
headers={
'Cookie': cookie.header_output(),
'Referer': const.SHARE_REFERER,
})
if req:
content = json.loads(req.data.decode())
else:
content = None
if return_path:
return content, path
else:
return content
def get_public_key(cookie, tokens):
'''获取RSA公钥, 这个用于加密用户的密码
返回的数据如下:
{"errno":'0',"msg":'',"pubkey":'-----BEGIN PUBLIC KEY-----\nMIGfMA0GCSqGSIb3DQEBAQUAA4GNADCBiQKBgQDk\/ufXg3IBW8+h5i8L8NoXUzcN\nMeKrh4zEupGBkyrURIPUXKDFLWjrv4n2j3RpMZ8GQn\/ETcfoIHGBoCUKJWcfcvmi\nG+OkYeqT6zyJasF0OlKesKfz0fGogMtdCQ6Kqq7X2vrzBPL+4SNU2wgU31g\/tVZl\n3zy5qAsBFkC70vs5FQIDAQAB\n-----END PUBLIC KEY-----\n',"key":'lwCISJnvs7HRNCTxpX7vi25bV9YslF2J'}
'''
url = ''.join([
const.PASSPORT_BASE, 'v2/getpublickey',
'?token=', tokens['token'],
'&tpl=pp&apiver=v3&tt=', util.timestamp(),
])
headers={
'Cookie': cookie.header_output(),
'Referer': const.REFERER,
}
req = net.urlopen(url, headers=headers)
if req:
data = req.data
return util.json_loads_single(req.data.decode())
return None
def cloud_query_sinfo(cookie, tokens, source_path):
'''获取网盘中种子的信息, 比如里面的文件名, 文件大小等.
source_path - BT种子的绝对路径.
'''
url = ''.join([
const.PAN_URL,
'rest/2.0/services/cloud_dl?channel=chunlei&clienttype=0&web=1',
'&method=query_sinfo&app_id=250528',
'&bdstoken=', tokens['bdstoken'],
'&source_path=', encoder.encode_uri_component(source_path),
'&type=2',
'&t=', util.timestamp(),
])
req = net.urlopen(url, headers={'Cookie': cookie.header_output()})
if req:
content = req.data
return json.loads(content.decode())
else:
return None
def delete_files(cookie, tokens, filelist):
'''批量删除文件/目录.
filelist - 待删除的文件/目录列表, 绝对路径
'''
url = ''.join([
const.PAN_API_URL,
'filemanager?channel=chunlei&clienttype=0&web=1&opera=delete',
'&bdstoken=', tokens['bdstoken'],
])
data = 'filelist=' + encoder.encode_uri_component(json.dumps(filelist))
req = net.urlopen(url, headers={
'Content-type': const.CONTENT_FORM_UTF8,
'Cookie': cookie.header_output(),
}, data=data.encode())
if req:
content = req.data
return json.loads(content.decode())
else:
return None
def cloud_list_task(cookie, tokens, start=0):
'''获取当前离线下载的任务信息
start - 从哪个任务开始, 从0开始计数, 会获取这50条任务信息
'''
url = ''.join([
const.PAN_URL,
'rest/2.0/services/cloud_dl?channel=chunlei&clienttype=0&web=1',
'&bdstoken=', tokens['bdstoken'],
'&need_task_info=1&status=255',
'&start=', str(start),
'&limit=50&method=list_task&app_id=250528',
'&t=', util.timestamp(),
])
req = net.urlopen(url, headers={'Cookie': cookie.header_output()})
if req:
content = req.data
return json.loads(content.decode())
else:
return None
def cloud_delete_task(cookie, tokens, task_id):
'''删除一个离线下载任务, 不管这个任务是否已完成下载.
同时还会把它从下载列表中删除.
'''
url = ''.join([
const.PAN_URL,
'rest/2.0/services/cloud_dl',
'?bdstoken=', tokens['bdstoken'],
'&task_id=', str(task_id),
'&method=delete_task&app_id=250528',
'&t=', util.timestamp(),
'&channel=chunlei&clienttype=0&web=1',
])
req = net.urlopen(url, headers={'Cookie': cookie.header_output()})
if req:
content = req.data
return json.loads(content.decode())
else:
return None
def disable_share(cookie, tokens, shareid_list):
'''取消分享.
shareid_list 是一个list, 每一项都是一个shareid
'''
url = ''.join([
const.PAN_URL,
'share/cancel?channel=chunlei&clienttype=0&web=1',
'&bdstoken=', tokens['bdstoken'],
])
data = 'shareid_list=' + encoder.encode_uri(json.dumps(shareid_list))
req = net.urlopen(url, headers={
'Cookie': cookie.header_output(),
'Content-type': const.CONTENT_FORM_UTF8,
}, data=data.encode())
if req:
content = req.data
return json.loads(content.decode())
else:
return None
def share_transfer(cookie, tokens, shareid, uk, filelist, dest, upload_mode):
print(
'/usr/local/lib/python3.4/dist-packages/bcloud/pcs.py:share_transfer 342'
)
'''
将其他用户的文件保存到自己网盘里.
uk - 其他用户的uk
filelist - 要转移文件的列表, 是绝对路径
'''
ondup = const.UPLOAD_ONDUP[upload_mode]
url = ''.join([
const.PAN_URL,
'share/transfer?app_id=250528&channel=chunlei&clienttype=0&web=1',
'&bdstoken=',
tokens['bdstoken'],
'&from=',
uk,
'&shareid=',
shareid,
'&ondup=',
ondup,
'&async=1',
])
data = ''.join([
'path=',
encoder.encode_uri_component(dest), '&filelist=',
encoder.encode_uri_component(json.dumps(filelist))
])
req = net.urlopen(url,
headers={
'Cookie': cookie.header_output(),
'Content-Type': const.CONTENT_FORM_UTF8
},
data=data.encode())
if req:
content = req.data.decode()
return json.loads(content)
else:
return None
def get_UBI(cookie, tokens):
'''检查登录历史, 可以获得一个Cookie - UBI.
返回的信息类似于:
{"errInfo":{ "no": "0" }, "data": {'displayname':['*****@*****.**']}}
'''
url = ''.join([
const.PASSPORT_URL,
'?loginhistory',
'&token=', tokens['token'],
'&tpl=pp&apiver=v3',
'&tt=', util.timestamp(),
])
headers={
'Cookie': cookie.header_output(),
'Referer': const.REFERER,
}
req = net.urlopen(url, headers=headers)
if req:
return req.headers.get_all('Set-Cookie')
else:
return None