Python第一战实例

按某一关键字爬取相关的微信公众号

# -*- coding: utf-8 -*-
"""
日期：2019-6-29
作者：SuperMary
功能：获取某一关键词的公众号
"""
import requests
import random
import time
import warnings

# 模拟浏览器的请求参数
URL = "https://mp.weixin.qq.com/cgi-bin/searchbiz"
Cookie = "noticeLoginFlag=1; remember_acct=349257312%40qq.com; ua_id=1N57cCDXn9T5pQJOAAAAAKQDrCK1DVt_NYTV1_XNW0w=; pgv_pvi=9636206592; noticeLoginFlag=1; mm_lang=zh_CN; pgv_pvid=4703926742; pac_uid=0_0ee28f94e380a; openid2ticket_oW3PwswIGm2EcjSUjE5CjlRnK2LU=h7cRCcAHvtk9AKaK4NKFvo5xY5EFrCxFkcW1daAuuqs=; remember_acct=sujing0913%40163.com; ptui_loginuin=349257312@qq.com; RK=AQSVwvn4a5; ptcz=f3101f74771270cd300f377ed9f4c0a1471815466c27992782ad39e7af8b19d5; tvfe_boss_uuid=576abc8408ab5c22; pgv_si=s6497839104; uuid=b161d801457244ea83c67f8eb37983dc; data_bizuin=3018879835; bizuin=3257228887; data_ticket=N3HbSVHlS+2XBgzjC2F9Bg3I7NHEUZJHg0mR9PMxOAao39d9+82Q694hoomwXeyP; slave_sid=Q2J2Z204NUJmdXpmajUzQm1INEd2SVFwWkZGU3F5OXQ2Nkx1cTBtVUt2XzFHTTJmbWlkMVBJNjZjZFRMNHFJaEVQWkFoN3lHWXk5R1ZuVWtHQ2NlNlZuUV83ZDFRdHRzdEV1bEdIa3pvSzBmUFdaaXJ6QXZCVTNrR2NSbTZUVWx0eEUxUVJFRzB6dWF3RjN4; slave_user=gh_e9824d9bf4d9; xid=5abb4eb1762673d6b1b5a01c78982e28"
User_Agent = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.103 Safari/537.36"
Token = "1486999690"


class WxLinkList:

    def __init__(self, query_str, num, filename):
        self.num = num
        self.query = query_str
        self.filename = filename
        warnings.filterwarnings('ignore')

    # 根据某一查询词获取的公众号
    def get_public_info(self, begin_num):
        headers = {
            "Cookie": Cookie,
            "User-Agent": User_Agent,
        }

        params_public = {
            "action": "search_biz",
            "token": Token,
            "lang": "zh_CN",
            "charset": "GBK",
            "f": "json",
            "ajax": "1",
            "begin": str(begin_num),
            "count": "10",
            "query": self.query,
        }

        content = requests.get(URL, headers=headers, params=params_public, verify=False).json()
        wx_public_info = content["list"]
        return wx_public_info

    # 获取某一关键词的所有公众号
    def get_all_public(self):
        page = self.num // 10
        file = open(self.filename, 'a')
        for i in range(0, page):
            print("\n第%s页：" % (i + 1))

            wait_time = random.randint(10, 65)
            print("等待%s秒。。。。。。" % wait_time)
            time.sleep(wait_time)

            begin_num = i * 10
            try:
                res_all = self.get_public_info(begin_num)
                res_len = len(res_all)
                for i in range(0, res_len):
                    temp_info = "公众号：%s, FakeID：%s" % (res_all[i]["nickname"], res_all[i]["fakeid"])
                    print(temp_info)
                    file.write(str(temp_info) + '\n')

            except:
                wait_time = random.randint(10, 65)
                print("等待%s秒。。。。。。" % wait_time)
                time.sleep(wait_time)
                break
        file.close()


if __name__ == "__main__":
    # 初始执行等待时间，避免频繁重新启动程序，被公众号平台检测为恶意攻击而封号或者暂停查询功能
    start_wait_time = 20
    print("等待%i秒，避免频繁操作被封号" % start_wait_time)
    time.sleep(20)

    # 设置爬取关键词，爬取总数，存储文件路径
    query_content = "Python"
    total_num =10
    filename = './Python_list.txt'

    # 创建类实例，执行主函数
    test = WxLinkList(query_content, total_num, filename)
    test.get_all_public()