python爬虫+网页版微信实时获取消息程序

最新推荐文章于 2024-08-13 23:57:44 发布

YuvalCheung

最新推荐文章于 2024-08-13 23:57:44 发布

阅读量4.3k

点赞数 1

分类专栏：爬虫

本文链接：https://blog.csdn.net/qq_34769201/article/details/104455488

版权

爬虫专栏收录该内容

3 篇文章 0 订阅

订阅专栏

项目需求：

目的是24小时爬取各种软件的讯息并且以一种统一的方式集中发送给自己。

实现方法：

利用python的requests库以及wxpy库，前者用来爬取网页，后者用来将爬到的内容发送给自己。

程序介绍：

需要的库：

import wxpy #用来登录网页版微信并发信息
import requests #用来爬取网页
import json #方便处理数据结构
import time #设定爬取时间
from bs4 import BeautifulSoup #分析静态网页

爬取网页的函数：

def get_url(url, kv):
    try:
        r = requests.get(url, headers=kv)#爬取网页并获取内容
        r.raise_for_status()
        return r
    except:
        return 0

爬取雪球：
通过打开需要爬取的个人主页，获取其实时更新的动态，先找到需要爬取的内容所在的地方。
在这里插入图片描述
然后记录下url和header信息：

保存多名用户的信息。

url_xueqiu = []
headers_xueqiu = []
url_xueqiu.append("https://xueqiu.com/v4/statuses/user_timeline.json?page=1&user_id=3072042836")
url_xueqiu.append("https://xueqiu.com/v4/statuses/user_timeline.json?page=1&user_id=3801921172")
url_xueqiu.append("https://xueqiu.com/v4/statuses/user_timeline.json?page=1&user_id=1314783718")
headers_xueqiu.append({'Referer': 'https://xueqiu.com/u/3072042836',
                       'User-Agent': 'Mozilla/5.0',
                       'cookie': 'aliyungf_tc=AQAAAKd7yFTFjAoAtcKEdSDxLV5FCp46; acw_tc=2760821a15820984687844418edc2e869d8485911ed7c90640c4ba33632f81; s=dx11t858l7; xq_a_token=b2f87b997a1558e1023f18af36cab23af8d202ea; xq_r_token=823123c3118be244b35589176a5974c844687d5e; xq_id_token=eyJ0eXAiOiJKV1QiLCJhbGciOiJSUzI1NiJ9.eyJ1aWQiOi0xLCJpc3MiOiJ1YyIsImV4cCI6MTU4MzE0MzIwMCwiY3RtIjoxNTgyMDk4NDI5MjU0LCJjaWQiOiJkOWQwbjRBWnVwIn0.OuUax528Ug96Mv18JXYbgemPn4dZbo3coZmcmHu49DG3xX4Esf3xtJZzfyq9_S3Uame_Euq47p4XL-xuqG3nmS0zN5SOrRCf2g6WFMQAzIXAOyqQIHGvZn3EnZ-dkElXNi_5QUNG8Uvu_HL6_9KAdaQryU5Kn8Tkkzu3xd05sbxy9WT_qEZe6Fega2Sjh2GlwO-k7FsvkBJcbkFlKTmZnk6HaqrPVlIrMlV6C5X2QPZEYFXq5RiRkEpkVwh9SaG3_UwI8kbGI_ggKF7aPpc48aV-ZxCsZhbV8kLkJ96vZlm4ZP18AeYjZpEA5thAjOhjYjDOpjWIAE0iC-eEAgpO2g; u=181582098495409; cookiesu=181582098495409; Hm_lvt_1db88642e346389874251b5a1eded6e3=1582098497; device_id=f3bae24173cc39686f529ebf5b4ab06a; Hm_lpvt_1db88642e346389874251b5a1eded6e3=1582100987'}
                      )
headers_xueqiu.append({'Referer': 'https://xueqiu.com/u/3801921172',
                       'User-Agent': 'Mozilla/5.0',
                       'cookie': 'aliyungf_tc=AQAAAKd7yFTFjAoAtcKEdSDxLV5FCp46; acw_tc=2760821a15820984687844418edc2e869d8485911ed7c90640c4ba33632f81; s=dx11t858l7; xq_a_token=b2f87b997a1558e1023f18af36cab23af8d202ea; xq_r_token=823123c3118be244b35589176a5974c844687d5e; xq_id_token=eyJ0eXAiOiJKV1QiLCJhbGciOiJSUzI1NiJ9.eyJ1aWQiOi0xLCJpc3MiOiJ1YyIsImV4cCI6MTU4MzE0MzIwMCwiY3RtIjoxNTgyMDk4NDI5MjU0LCJjaWQiOiJkOWQwbjRBWnVwIn0.OuUax528Ug96Mv18JXYbgemPn4dZbo3coZmcmHu49DG3xX4Esf3xtJZzfyq9_S3Uame_Euq47p4XL-xuqG3nmS0zN5SOrRCf2g6WFMQAzIXAOyqQIHGvZn3EnZ-dkElXNi_5QUNG8Uvu_HL6_9KAdaQryU5Kn8Tkkzu3xd05sbxy9WT_qEZe6Fega2Sjh2GlwO-k7FsvkBJcbkFlKTmZnk6HaqrPVlIrMlV6C5X2QPZEYFXq5RiRkEpkVwh9SaG3_UwI8kbGI_ggKF7aPpc48aV-ZxCsZhbV8kLkJ96vZlm4ZP18AeYjZpEA5thAjOhjYjDOpjWIAE0iC-eEAgpO2g; u=181582098495409; cookiesu=181582098495409; Hm_lvt_1db88642e346389874251b5a1eded6e3=1582098497; device_id=f3bae24173cc39686f529ebf5b4ab06a; Hm_lpvt_1db88642e346389874251b5a1eded6e3=1582102587'}
                      )
headers_xueqiu.append({'Referer': 'https://xueqiu.com/u/1314783718',
                       'User-Agent': 'Mozilla/5.0',
                       'cookie': 'acw_tc=2760821a15820984687844418edc2e869d8485911ed7c90640c4ba33632f81; s=dx11t858l7; device_id=f3bae24173cc39686f529ebf5b4ab06a; aliyungf_tc=AQAAAFkbfHaZAQsAK8KEddBs2OH7Zmqv; xq_a_token=b2f87b997a1558e1023f18af36cab23af8d202ea; xqat=b2f87b997a1558e1023f18af36cab23af8d202ea; xq_r_token=823123c3118be244b35589176a5974c844687d5e; xq_id_token=eyJ0eXAiOiJKV1QiLCJhbGciOiJSUzI1NiJ9.eyJ1aWQiOi0xLCJpc3MiOiJ1YyIsImV4cCI6MTU4MzE0MzIwMCwiY3RtIjoxNTgyMzg1Mjg3MTgwLCJjaWQiOiJkOWQwbjRBWnVwIn0.Crta07q4xFTBXA1raWy-kFHZydPOytwS5Tz1CN14ABe5ruoojfHDVH_Y1shaGaqrpP_9b_l2Zg4Dx87WAC4-wWCNzSijCyKkwqtAQXS9QpfjH79-zmqAloo86dz5DY_H297QDuQZd0-Psi6-hQW2o70lc75DI2pTHWRHVeENRH1sIaWUylGaouXLugIM1ppXLdgyEqf85zGJQxPQUX-ryNOQINn6FBKPw4lfn--2k78U-aCZmPh-Mxx_BStyEOAZPkWwcYiBxcGpU_Wr9tlqedaj-NoTR71mJ5OZFToqYEzcvkk1BKUbPh1li4g1KZ7DhK-FVOivyi8o70c8TN3ygg; u=741582385322747; Hm_lvt_1db88642e346389874251b5a1eded6e3=1582098497,1582385350; cookiesu=381582390368314; Hm_lpvt_1db88642e346389874251b5a1eded6e3=1582390370'}
                      )

调用函数获取所需的博文内容，在’statuses’结构中：

def get_xueqiu(r):
    r_text = r.text
    r_json = json.loads(r_text)
    need = r_json['statuses']
    return need

微博也同理：

url_weibo = []
headers_weibo = []
url_weibo.append("https://m.weibo.cn/api/container/getIndex?type=uid&value=3191919325&containerid=1076033191919325")
headers_weibo.append({'Referer': 'https://m.weibo.cn/u/3191919325',
                      'User-Agent': 'Mozilla/5.0'})
url_weibo.append("https://m.weibo.cn/api/container/getIndex?type=uid&value=2301894077&containerid=1076032301894077")
headers_weibo.append({'Referer': 'https://m.weibo.cn/u/2301894077',
                      'User-Agent': 'Mozilla/5.0'})

但是微博的文字所在内容在’data’里面的’cardss’中

def get_weibo(r):
    r_text = r.text
    r_json = json.loads(r_text)
    need = r_json['data']['cards']
    return need

雪球7*27小时新闻：
在这里插入图片描述

url_7 = 'https://xueqiu.com/?category=livenews&tdsourcetag=s_pctim_aiomsg'
headers_7 = {'Referer': 'https://xueqiu.com/u/1314783718',
             'User-Agent': 'Mozilla/5.0',
             'cookie': 'acw_tc=2760821a15820984687844418edc2e869d8485911ed7c90640c4ba33632f81; s=dx11t858l7; device_id=f3bae24173cc39686f529ebf5b4ab06a; aliyungf_tc=AQAAAFkbfHaZAQsAK8KEddBs2OH7Zmqv; xq_a_token=b2f87b997a1558e1023f18af36cab23af8d202ea; xqat=b2f87b997a1558e1023f18af36cab23af8d202ea; xq_r_token=823123c3118be244b35589176a5974c844687d5e; xq_id_token=eyJ0eXAiOiJKV1QiLCJhbGciOiJSUzI1NiJ9.eyJ1aWQiOi0xLCJpc3MiOiJ1YyIsImV4cCI6MTU4MzE0MzIwMCwiY3RtIjoxNTgyMzg1Mjg3MTgwLCJjaWQiOiJkOWQwbjRBWnVwIn0.Crta07q4xFTBXA1raWy-kFHZydPOytwS5Tz1CN14ABe5ruoojfHDVH_Y1shaGaqrpP_9b_l2Zg4Dx87WAC4-wWCNzSijCyKkwqtAQXS9QpfjH79-zmqAloo86dz5DY_H297QDuQZd0-Psi6-hQW2o70lc75DI2pTHWRHVeENRH1sIaWUylGaouXLugIM1ppXLdgyEqf85zGJQxPQUX-ryNOQINn6FBKPw4lfn--2k78U-aCZmPh-Mxx_BStyEOAZPkWwcYiBxcGpU_Wr9tlqedaj-NoTR71mJ5OZFToqYEzcvkk1BKUbPh1li4g1KZ7DhK-FVOivyi8o70c8TN3ygg; u=741582385322747; Hm_lvt_1db88642e346389874251b5a1eded6e3=1582098497,1582385350; cookiesu=901582391948014; Hm_lpvt_1db88642e346389874251b5a1eded6e3=1582391948'}

接下来开始第一次读取网页内容：

id_weibo = []#这几个id用来记录内容的标识，使其具有唯一性。
id_xueqiu = []
id_http = []
for i in zip(url_xueqiu, headers_xueqiu):
    temp_r = get_url(i[0], i[1])
    temp_need = get_xueqiu(temp_r)
    for j in temp_need:
        id_xueqiu.append([j['id'], j['user_id']])#记录当前页面的所有标识
for i in zip(url_weibo, headers_weibo):
    temp_r = get_url(i[0], i[1])
    temp_need = get_weibo(temp_r)
    for j in temp_need:
        id_weibo.append(j['mblog']['id'])
#处理与前面不大一样
r_7 = requests.get(url_7, headers=headers_7)
r_7.encoding = "utf-8"#该网页是utf-8编码
soup = BeautifulSoup(r_7.text, 'html.parser')#用静态网页工具把str转换成网页
new_list = soup.find('div', {'id': 'app'})
new_2 = new_list.find_all_next('table')#找到其内容所在的地方。
for i in new_2:
    pre_a = i.find('a')
    id_http.append(pre_a.__getitem__('href'))#记录其标识

接下来开始发送微信消息：

# 构建机器人
bot = wxpy.Bot(cache_path=True, console_qr=False)#登陆微信号
xiaohao = bot.friends().search("张张张")[0]#找到一个联系人，可以发消息的

设置循环开是监听消息：

print("开始监听")
while True:
    time.sleep(5)
    # 监视雪球
    for i in zip(url_xueqiu, headers_xueqiu):
        temp_r = get_url(i[0], i[1])
        try:
            temp_need = get_xueqiu(temp_r)
        except:
            print("无网络连接")
            break
        for j in temp_need:
            if [j['id'], j['user_id']] not in id_xueqiu:
                text_temp = j['text']
                text_temp = text_temp.replace('<p>', '')
                text_temp = text_temp.replace('</p>', '\n')
                text_send = j['user']['screen_name'] + "有新消息：\n\n" + text_temp
                print(text_send)
                xiaohao.send(text_send)
                id_xueqiu.append([j['id'], j['user_id']])
    # 监视微博
    for i in zip(url_weibo, headers_weibo):
        temp_r = get_url(i[0], i[1])
        try:
            temp_need = get_weibo(temp_r)
        except:
            print("无网络连接")
            break
        for j in temp_need:
            if j['mblog']['id'] not in id_weibo:
                text_send = j['mblog']['user']['screen_name'] + "有新消息：\n\n" + j['mblog']['text']
                print(text_send)
                xiaohao.send(text_send)
                id_weibo.append(j['mblog']['id'])
    # 7X24小时新闻
    try:
        r_7 = requests.get(url_7, headers=headers_7)
        r_7.encoding = "utf-8"
        soup = BeautifulSoup(r_7.text, 'html.parser')
        new_list = soup.find('div', {'id': 'app'})
        new_2 = new_list.find_all_next('table')
        for i in new_2:
            pre_a = i.find('a')
            if pre_a.__getitem__('href') not in id_http:
                text_send = "7*24小时新闻有新消息：\n\n" + pre_a.get_text() + '\n' + pre_a.__getitem__('href')
                xiaohao.send(text_send)
                print(text_send)
                id_http.append(pre_a.__getitem__('href'))
    except:
        print("无网络连接")

代码：

import wxpy
import requests
import json
import time
from bs4 import BeautifulSoup


def get_url(url, kv):
    try:
        r = requests.get(url, headers=kv)
        r.raise_for_status()
        return r
    except:
        return 0


def get_xueqiu(r):
    r_text = r.text
    r_json = json.loads(r_text)
    need = r_json['statuses']
    return need


def get_weibo(r):
    r_text = r.text
    r_json = json.loads(r_text)
    need = r_json['data']['cards']
    return need


if __name__ == '__main__':
    # 构建机器人
    bot = wxpy.Bot(cache_path=True, console_qr=False)
    xiaohao = bot.friends().search("张张张")[0]
    # 雪球
    url_xueqiu = []
    headers_xueqiu = []
    url_xueqiu.append("https://xueqiu.com/v4/statuses/user_timeline.json?page=1&user_id=3072042836")
    url_xueqiu.append("https://xueqiu.com/v4/statuses/user_timeline.json?page=1&user_id=3801921172")
    url_xueqiu.append("https://xueqiu.com/v4/statuses/user_timeline.json?page=1&user_id=1314783718")
    headers_xueqiu.append({'Referer': 'https://xueqiu.com/u/3072042836',
                           'User-Agent': 'Mozilla/5.0',
                           'cookie': 'aliyungf_tc=AQAAAKd7yFTFjAoAtcKEdSDxLV5FCp46; acw_tc=2760821a15820984687844418edc2e869d8485911ed7c90640c4ba33632f81; s=dx11t858l7; xq_a_token=b2f87b997a1558e1023f18af36cab23af8d202ea; xq_r_token=823123c3118be244b35589176a5974c844687d5e; xq_id_token=eyJ0eXAiOiJKV1QiLCJhbGciOiJSUzI1NiJ9.eyJ1aWQiOi0xLCJpc3MiOiJ1YyIsImV4cCI6MTU4MzE0MzIwMCwiY3RtIjoxNTgyMDk4NDI5MjU0LCJjaWQiOiJkOWQwbjRBWnVwIn0.OuUax528Ug96Mv18JXYbgemPn4dZbo3coZmcmHu49DG3xX4Esf3xtJZzfyq9_S3Uame_Euq47p4XL-xuqG3nmS0zN5SOrRCf2g6WFMQAzIXAOyqQIHGvZn3EnZ-dkElXNi_5QUNG8Uvu_HL6_9KAdaQryU5Kn8Tkkzu3xd05sbxy9WT_qEZe6Fega2Sjh2GlwO-k7FsvkBJcbkFlKTmZnk6HaqrPVlIrMlV6C5X2QPZEYFXq5RiRkEpkVwh9SaG3_UwI8kbGI_ggKF7aPpc48aV-ZxCsZhbV8kLkJ96vZlm4ZP18AeYjZpEA5thAjOhjYjDOpjWIAE0iC-eEAgpO2g; u=181582098495409; cookiesu=181582098495409; Hm_lvt_1db88642e346389874251b5a1eded6e3=1582098497; device_id=f3bae24173cc39686f529ebf5b4ab06a; Hm_lpvt_1db88642e346389874251b5a1eded6e3=1582100987'}
                          )
    headers_xueqiu.append({'Referer': 'https://xueqiu.com/u/3801921172',
                           'User-Agent': 'Mozilla/5.0',
                           'cookie': 'aliyungf_tc=AQAAAKd7yFTFjAoAtcKEdSDxLV5FCp46; acw_tc=2760821a15820984687844418edc2e869d8485911ed7c90640c4ba33632f81; s=dx11t858l7; xq_a_token=b2f87b997a1558e1023f18af36cab23af8d202ea; xq_r_token=823123c3118be244b35589176a5974c844687d5e; xq_id_token=eyJ0eXAiOiJKV1QiLCJhbGciOiJSUzI1NiJ9.eyJ1aWQiOi0xLCJpc3MiOiJ1YyIsImV4cCI6MTU4MzE0MzIwMCwiY3RtIjoxNTgyMDk4NDI5MjU0LCJjaWQiOiJkOWQwbjRBWnVwIn0.OuUax528Ug96Mv18JXYbgemPn4dZbo3coZmcmHu49DG3xX4Esf3xtJZzfyq9_S3Uame_Euq47p4XL-xuqG3nmS0zN5SOrRCf2g6WFMQAzIXAOyqQIHGvZn3EnZ-dkElXNi_5QUNG8Uvu_HL6_9KAdaQryU5Kn8Tkkzu3xd05sbxy9WT_qEZe6Fega2Sjh2GlwO-k7FsvkBJcbkFlKTmZnk6HaqrPVlIrMlV6C5X2QPZEYFXq5RiRkEpkVwh9SaG3_UwI8kbGI_ggKF7aPpc48aV-ZxCsZhbV8kLkJ96vZlm4ZP18AeYjZpEA5thAjOhjYjDOpjWIAE0iC-eEAgpO2g; u=181582098495409; cookiesu=181582098495409; Hm_lvt_1db88642e346389874251b5a1eded6e3=1582098497; device_id=f3bae24173cc39686f529ebf5b4ab06a; Hm_lpvt_1db88642e346389874251b5a1eded6e3=1582102587'}
                          )
    headers_xueqiu.append({'Referer': 'https://xueqiu.com/u/1314783718',
                           'User-Agent': 'Mozilla/5.0',
                           'cookie': 'acw_tc=2760821a15820984687844418edc2e869d8485911ed7c90640c4ba33632f81; s=dx11t858l7; device_id=f3bae24173cc39686f529ebf5b4ab06a; aliyungf_tc=AQAAAFkbfHaZAQsAK8KEddBs2OH7Zmqv; xq_a_token=b2f87b997a1558e1023f18af36cab23af8d202ea; xqat=b2f87b997a1558e1023f18af36cab23af8d202ea; xq_r_token=823123c3118be244b35589176a5974c844687d5e; xq_id_token=eyJ0eXAiOiJKV1QiLCJhbGciOiJSUzI1NiJ9.eyJ1aWQiOi0xLCJpc3MiOiJ1YyIsImV4cCI6MTU4MzE0MzIwMCwiY3RtIjoxNTgyMzg1Mjg3MTgwLCJjaWQiOiJkOWQwbjRBWnVwIn0.Crta07q4xFTBXA1raWy-kFHZydPOytwS5Tz1CN14ABe5ruoojfHDVH_Y1shaGaqrpP_9b_l2Zg4Dx87WAC4-wWCNzSijCyKkwqtAQXS9QpfjH79-zmqAloo86dz5DY_H297QDuQZd0-Psi6-hQW2o70lc75DI2pTHWRHVeENRH1sIaWUylGaouXLugIM1ppXLdgyEqf85zGJQxPQUX-ryNOQINn6FBKPw4lfn--2k78U-aCZmPh-Mxx_BStyEOAZPkWwcYiBxcGpU_Wr9tlqedaj-NoTR71mJ5OZFToqYEzcvkk1BKUbPh1li4g1KZ7DhK-FVOivyi8o70c8TN3ygg; u=741582385322747; Hm_lvt_1db88642e346389874251b5a1eded6e3=1582098497,1582385350; cookiesu=381582390368314; Hm_lpvt_1db88642e346389874251b5a1eded6e3=1582390370'}
                          )
    # 微博：
    url_weibo = []
    headers_weibo = []
    url_weibo.append("https://m.weibo.cn/api/container/getIndex?type=uid&value=3191919325&containerid=1076033191919325")
    headers_weibo.append({'Referer': 'https://m.weibo.cn/u/3191919325',
                          'User-Agent': 'Mozilla/5.0'})
    url_weibo.append("https://m.weibo.cn/api/container/getIndex?type=uid&value=2301894077&containerid=1076032301894077")
    headers_weibo.append({'Referer': 'https://m.weibo.cn/u/2301894077',
                          'User-Agent': 'Mozilla/5.0'})

    # 雪球每7X24小时新闻
    url_7 = 'https://xueqiu.com/?category=livenews&tdsourcetag=s_pctim_aiomsg'
    headers_7 = {'Referer': 'https://xueqiu.com/u/1314783718',
                 'User-Agent': 'Mozilla/5.0',
                 'cookie': 'acw_tc=2760821a15820984687844418edc2e869d8485911ed7c90640c4ba33632f81; s=dx11t858l7; device_id=f3bae24173cc39686f529ebf5b4ab06a; aliyungf_tc=AQAAAFkbfHaZAQsAK8KEddBs2OH7Zmqv; xq_a_token=b2f87b997a1558e1023f18af36cab23af8d202ea; xqat=b2f87b997a1558e1023f18af36cab23af8d202ea; xq_r_token=823123c3118be244b35589176a5974c844687d5e; xq_id_token=eyJ0eXAiOiJKV1QiLCJhbGciOiJSUzI1NiJ9.eyJ1aWQiOi0xLCJpc3MiOiJ1YyIsImV4cCI6MTU4MzE0MzIwMCwiY3RtIjoxNTgyMzg1Mjg3MTgwLCJjaWQiOiJkOWQwbjRBWnVwIn0.Crta07q4xFTBXA1raWy-kFHZydPOytwS5Tz1CN14ABe5ruoojfHDVH_Y1shaGaqrpP_9b_l2Zg4Dx87WAC4-wWCNzSijCyKkwqtAQXS9QpfjH79-zmqAloo86dz5DY_H297QDuQZd0-Psi6-hQW2o70lc75DI2pTHWRHVeENRH1sIaWUylGaouXLugIM1ppXLdgyEqf85zGJQxPQUX-ryNOQINn6FBKPw4lfn--2k78U-aCZmPh-Mxx_BStyEOAZPkWwcYiBxcGpU_Wr9tlqedaj-NoTR71mJ5OZFToqYEzcvkk1BKUbPh1li4g1KZ7DhK-FVOivyi8o70c8TN3ygg; u=741582385322747; Hm_lvt_1db88642e346389874251b5a1eded6e3=1582098497,1582385350; cookiesu=901582391948014; Hm_lpvt_1db88642e346389874251b5a1eded6e3=1582391948'}
    # 存储id
    id_weibo = []
    id_xueqiu = []
    id_http = []

    for i in zip(url_xueqiu, headers_xueqiu):
        temp_r = get_url(i[0], i[1])
        temp_need = get_xueqiu(temp_r)
        for j in temp_need:
            id_xueqiu.append([j['id'], j['user_id']])

    for i in zip(url_weibo, headers_weibo):
        temp_r = get_url(i[0], i[1])
        temp_need = get_weibo(temp_r)
        for j in temp_need:
            id_weibo.append(j['mblog']['id'])

    r_7 = requests.get(url_7, headers=headers_7)
    r_7.encoding = "utf-8"
    soup = BeautifulSoup(r_7.text, 'html.parser')
    new_list = soup.find('div', {'id': 'app'})
    new_2 = new_list.find_all_next('table')
    for i in new_2:
        pre_a = i.find('a')
        id_http.append(pre_a.__getitem__('href'))

    print("开始监听")
    while True:
        time.sleep(5)

        # 监视雪球
        for i in zip(url_xueqiu, headers_xueqiu):
            temp_r = get_url(i[0], i[1])
            try:
                temp_need = get_xueqiu(temp_r)
            except:
                print("无网络连接")
                break
            for j in temp_need:
                if [j['id'], j['user_id']] not in id_xueqiu:
                    text_temp = j['text']
                    text_temp = text_temp.replace('<p>', '')
                    text_temp = text_temp.replace('</p>', '\n')
                    text_send = j['user']['screen_name'] + "有新消息：\n\n" + text_temp
                    print(text_send)
                    xiaohao.send(text_send)
                    id_xueqiu.append([j['id'], j['user_id']])

        # 监视微博
        for i in zip(url_weibo, headers_weibo):
            temp_r = get_url(i[0], i[1])
            try:
                temp_need = get_weibo(temp_r)
            except:
                print("无网络连接")
                break
            for j in temp_need:
                if j['mblog']['id'] not in id_weibo:
                    text_send = j['mblog']['user']['screen_name'] + "有新消息：\n\n" + j['mblog']['text']
                    print(text_send)
                    xiaohao.send(text_send)
                    id_weibo.append(j['mblog']['id'])

        # 7X24小时新闻
        try:
            r_7 = requests.get(url_7, headers=headers_7)
            r_7.encoding = "utf-8"
            soup = BeautifulSoup(r_7.text, 'html.parser')
            new_list = soup.find('div', {'id': 'app'})
            new_2 = new_list.find_all_next('table')
            for i in new_2:
                pre_a = i.find('a')
                if pre_a.__getitem__('href') not in id_http:
                    text_send = "7*24小时新闻有新消息：\n\n" + pre_a.get_text() + '\n' + pre_a.__getitem__('href')
                    xiaohao.send(text_send)
                    print(text_send)
                    id_http.append(pre_a.__getitem__('href'))
        except:
            print("无网络连接")