python3模拟百度登录并实现百度贴吧签到示例分享(百度贴吧自动签到)

baiduclient.py

import urllib.parse
import gzip
import json
import re
from http.client import httpconnection
from htmlutils import tiebaparser
import httputils as utils

# 请求头
headers = dict()
headers["connection"] = "keep-alive"
headers["cache-control"] = "max-age=0"
headers["accept"] = "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8"
headers["user-agent"] = "mozilla/5.0 (windows nt 6.1; wow64) applewebkit/537.36 (khtml, like gecko) chrome/32.0.1700.107 safari/537.36"
headers["content-type"] = "application/x-www-form-urlencoded"
headers["accept-encoding"] = "gzip,deflate,sdch"
headers["accept-language"] = "zh-cn,zh;q=0.8"
headers["cookie"] = ""

# cookie
cookies = list()

# 个人信息
userinfo = {}

def login(account, password):
    '''登录'''
    global cookies
    headers["host"] = "wappass.baidu.com"
    body = "username={0}&password={1}&submit=%e7%99%bb%e5%bd%95&quick_user=0&isphone=0&sp_login=waprate&uname_login=&loginmerge=1&vcodestr=&u=http%253a%252f%252fwap.baidu.com%253fuid%253d1392873796936_247&skin=default_v2&tpl=&ssid=&from=&uid=1392873796936_247&pu=&tn=&bdcm=3f7d51b436d12f2e83389b504fc2d56285356820&type=&bd_page_type="
    body = body.format(account, password)
    conn = httpconnection("wappass.baidu.com", 80)
    conn.request("post", "/passport/login", body, headers)
    resp = conn.getresponse()
    cookies += utils.getcookiesfromheaders(resp.getheaders())
    utils.savecookies(headers, cookies)
    # 登录成功会返回302
    return true if resp.code == 302 else false
   

def gettiebalist():
    '''获取已关注的贴吧列表'''
    conn = httpconnection("tieba.baidu.com", 80)
    conn.request("get", "/mo/m?tn=bdfbw&tab=favorite", "", headers)
    resp = conn.getresponse()   
    tiebaparser = tiebaparser()
    tiebaparser.feed(resp.read().decode())
    tblist = tiebaparser.gettiebalist()
    return tblist
   

def getsigninfo(tiebaname):
    '''获取贴吧签到信息'''
    querystr = urllib.parse.urlencode({"kw":tiebaname, "ie":"utf-8", "t":0.571444})
    conn = httpconnection("tieba.baidu.com", 80)
    conn.request("get", "/sign/loadmonth?" + querystr, "", headers)
    data = gzip.decompress(conn.getresponse().read()).decode("gbk")
    signinfo = json.loads(data)
    return signinfo

    
tbspattern = re.compile('"tbs" value=".{20,35}"')

def signin(tiebaname):
    '''签到'''
    # 获取页面中的参数tbs
    conn1 = httpconnection("tieba.baidu.com", 80)
    querystr1 = urllib.parse.urlencode({"kw": tiebaname})
    conn1.request("get", "/mo/m?" + querystr1, "", headers)
    html = conn1.getresponse().read().decode()
    tbs = tbspattern.search(html).group(0)[13:-1]
    # 签到
    conn2 = httpconnection("tieba.baidu.com", 80)
    body = urllib.parse.urlencode({"kw":tiebaname, "tbs":tbs, "ie":"utf-8"})
    conn2.request("post", "/sign/add" , body , headers)
    resp2 = conn2.getresponse()
    data = json.loads((gzip.decompress(resp2.read())).decode())
    return data
   

def getuserinfo():
    '''获取个人信息'''
    headers.pop("host")
    conn = httpconnection("tieba.baidu.com", 80)
    conn.request("get", "/f/user/json_userinfo", "", headers)
    resp = conn.getresponse()
    data = gzip.decompress(resp.read()).decode("gbk")
    global userinfo
    userinfo = json.loads(data)

if __name__ == "__main__":
    account = input("请输入帐号:")
    password = input("请输入密码:")

    ok = login(account, password)
    if ok:
        getuserinfo()
        print(userinfo["data"]["user_name_weak"] + "~~~登录成功", end="\n------\n")
        for tb in gettiebalist():
            print(tb + "吧:")
            signinfo = signin(tb)
            if signinfo["no"] != 0:
                print("签到失败!")
                print(signinfo["error"])
            else:
                print("签到成功!")
                print("签到天数:" + str(signinfo["data"]["uinfo"]["cout_total_sing_num"]))
                print("连续签到天数:" + str(signinfo["data"]["uinfo"]["cont_sign_num"]))
            print("------")
    else:
        print("登录失败")

htmlutils.py

'''
created on 2014-2-20

@author: vincent
'''

from html.parser import htmlparser

class tiebaparser(htmlparser):
    def __init__(self):
        htmlparser.__init__(self)
        self.tiebalist = list()
        self.flag = false

    def gettiebalist(self):
        return self.tiebalist

    def handle_starttag(self, tag, attrs):
        if tag == "a":
            for name , value in attrs:
                if name == "href" and "m?kw=" in value:
                    self.flag = true

    def handle_data(self, data):
        if self.flag:
            self.tiebalist.append(data)
            self.flag = false

httputils.py

'''
created on 2014-2-20

@author: vincent
'''
def getcookiesfromheaders(headers):
    '''从http响应中获取所有cookie'''
    cookies = list()
    for header in headers:
        if "set-cookie" in header:
            cookie = header[1].split(";")[0]
            cookies.append(cookie)
    return cookies

def savecookies(headers, cookies):
    '''保存cookies'''
    for cookie in cookies:
        headers["cookie"] += cookie + ";"

def getcookievalue(cookies, cookiename):
    '''从cookies中获取指定cookie的值'''
    for cookie in cookies:
        if cookiename in cookie:
            index = cookie.index("=") + 1
            value = cookie[index:]
            return value

def parsequerystring(querystring):
    '''解析查询串'''
    result = dict()
    strs = querystring.split("&")
    for s in strs:
        name = s.split("=")[0]
        value = s.split("=")[1]
        result[name] = value
    return result