auto sign on baidu tieba

tieba.py

# -*- coding:utf-8 -*-

import requests
import re

__author__ = 'Jux.Liu'
# 修改自己的cooki
cookie = ''

# 构建请求头数据
headers = {
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
    'Accept-Encoding': 'gzip, deflate, sdch',
    'Accept-Language': 'zh-CN,zh;q=0.8,en;q=0.6',
    'Cache-Control': 'max-age=0',
    'Connection': 'keep-alive',
    'Cookie': cookie,
    'DNT': '1',
    'Host': 'tieba.baidu.com',
    'Upgrade-Insecure-Requests': '1',
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.99 Safari/537.36'
}


# 获取关注贴吧列表
def find_kw(headers):
    page_count = 1
    kw_list = []
    while 1:
        like_url = 'http://tieba.baidu.com/f/like/mylike?&pn={}'.format(page_count)
        like_html = requests.get(url=like_url, headers=headers).text
        re_kw = re.compile(r'<a href="/f\?kw=(.+?)" title="(.+?)"')
        temp_kw = re_kw.findall(like_html)
        if not temp_kw:
            break
        if not kw_list:
            kw_list = temp_kw
        else:
            kw_list += temp_kw
        page_count += 1

    print('我喜欢的{}个贴吧:'.format(len(kw_list)))
    if kw_list:
        for i in kw_list:
            kw = i[0]
            title = i[1]
            sign(title, kw, headers)


# 签到
def sign(title, kw, headers):
    sign_url = 'http://tieba.baidu.com/mo/m?kw={}'.format(kw)
    sign_html = requests.get(url=sign_url, headers=headers).text
    re_fid = re.compile(r'<input type="hidden" name="fid" value="(.+?)"\/>')
    # print 're_fid:\t', re_fid
    fid_l = re.findall(re_fid, sign_html)
    if len(fid_l) < 1:
        print('{}\t\t错误'.format(title))
    else:
        fid = fid_l[0]
        # print 'fid:\t', fid
        re_tbs = re.compile(r'<input type="hidden" name="tbs" value="(.+?)"\/>')
        # print 're_tbs:\t', re_tbs
        tbs = re.findall(re_tbs, sign_html)[0]
        # print 'tbs:\t', tbs
        re_sign = re.compile(r'</td><td style="text-align:right;"><span >已签到</span>')
        # print 're_sign:\t', re_sign
        sign = re.findall(re_sign, sign_html)
        # print 'sign:\t', sign
        data = {
            'tbs': tbs,
            'fid': fid,
            'kw': kw
        }
        if sign:
            print('{}\t\t已签'.format(title))
        else:
            print('{}\t\t签到成功'.format(title))
            sign_url = 'http://tieba.baidu.com/mo/q---C367D41E4214449AC861EDF6CE73CD4E%3AFG%3D1--1-3-0--2--wapp_1443524105422_889/sign?tbs={}&fid={}+&kw={}'.format(
                tbs, fid, kw)
            sign_html = requests.get(url=sign_url, headers=headers, data=data)


if __name__ == '__main__':
    find_kw(headers)