根据sessionId下载验证码,通过人工方式识别
import urllib2
def get_captcha(captchaUrl, sessionIdKey, sessionIdValue):
"""获得验证码图片
通过fiddler分析验证码请求时需要携带的cookie,通常验证码是与某个sessionid绑定的
Args:
captchaUrl: 验证码地址
sessionIdKey: session key
sessionIdValue: session value
"""
req = urllib2.Request(captchaUrl)
req.add_header("Cookie","%s=%s" % (sessionIdKey,sessionIdValue))
res = urllib2.urlopen(req)
picture = res.read()
imgpath = "captcha.gif"
with open(imgpath,"wb") as fp:
fp.write(picture)
# 请输入验证码
captchaValue = raw_input("please input captcha:")
return captchaValue