|
马上注册,结交更多好友,享用更多功能^_^
您需要 登录 才可以下载或查看,没有账号?立即注册
x
- # -- coding:gbk --
- import re
- import urllib.request
- import urllib.parse
- import http.cookiejar
-
- loginurl = urllib.request.Request('https://accounts.douban.com/passport/login', headers={'User-agent': 'Mozilla/5.0'})
- cookie = http.cookiejar.CookieJar()
- opener = urllib.request.build_opener(urllib.request.HTTPCookieProcessor(cookie))
-
- data = {
- "form_email":"your email",
- "form_password":"your password",
- "source":"index_nav"
- }
- data = {}
- data['form_email'] = 'sxxxx'
- data['form_password'] = 'suxxxxxx'
- data['source'] = 'index_nav'
-
- #从首页提交登录
- response=opener.open(loginurl, urllib.parse.urlencode(data).encode('utf-8'))
-
- #验证成功跳转至登录页
- if response.geturl() == "https://accounts.douban.com/passport/login":
- html=response.read().decode('utf-8')
-
- #验证码图片地址
- imgurl=re.search('<img id="captcha_image" src="(.+?)" alt="captcha" class="captcha_image"/>', html)
- if imgurl:
- url=imgurl.group(1)
- #将图片保存至同目录下
- res=urllib.request.urlretrieve(url, 'v.jpg')
- #获取captcha-id参数
- captcha=re.search('<input type="hidden" name="captcha-id" value="(.+?)"/>' ,html)
- if captcha:
- vcode=input('请输入图片上的验证码:')
- params["captcha-solution"] = vcode
- params["captcha-id"] = captcha.group(1)
- params["user_login"] = "登录"
- #提交验证码验证
- response=opener.open(loginurl, urllib.parse.urlencode(params).encode('utf-8'))
- ''' 登录成功跳转至首页 '''
- if response.geturl() == "https://www.douban.com/":
- print('login success ! ')
- else:
- print('Failed')
- else:
- print('3')
- else:
- print(2)
- else:
- print(1)
复制代码
为什么获取不了imgurl?
本帖最后由 1q23w31 于 2020-8-7 21:03 编辑
哪有验证码?代码过时了吧
|
|