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
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
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]
else:
logger.warn("pcs.get_user_uk(), failed to parse uk, %s" % url)
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]
else:
logger.warn('pcs.get_user_uk(), failed to parse uk, %s' % url)
return None