清华大佬耗费三个月吐血整理的几百G的资源,免费分享!....>>>
这是一个python通过urllib直接登陆网站,并处理网站的session和cookie
import cookielib, urllib, urllib2 login = 'ismellbacon123@yahoo.com' password = 'login' # Enable cookie support for urllib2 cookiejar = cookielib.CookieJar() urlOpener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cookiejar)) # Send login/password to the site and get the session cookie values = {'login':login, 'password':password } data = urllib.urlencode(values) request = urllib2.Request("http://www.imdb.com/register/login", data) url = urlOpener.open(request) # Our cookiejar automatically receives the cookies page = url.read(500000) # Make sure we are logged in by checking the presence of the cookie "id". # (which is the cookie containing the session identifier.) if not 'id' in [cookie.name for cookie in cookiejar]: raise ValueError, "Login failed with login=%s, password=%s" % (login,password) print "We are logged in !" # Make another request with our session cookie # (Our urlOpener automatically uses cookies from our cookiejar) url = urlOpener.open('http://imdb.com/find?s=all&q=grave') page = url.read(200000)