python 利用爬虫将最新数据更新至微信

def job():
    from urllib import request
    import pandas as pd
    from datetime import datetime

    head={}
    head['User-Agent']='Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36'

    jts_url="https://ts.21cn.com/front/api/ranking/merchantPostList.do?pageNo=1&merchantId=7037&listType=1&offset=b911ff99c1c81c99"
    jts_req=request.Request(url=jts_url,headers=head)
    jts_respon=request.urlopen(jts_req)
    jts_html=jts_respon.read().decode('utf-8','ignore')
    jts_dict=eval(jts_html)
    jts_ctime_list=[]
    jts_id_list=[]
    jts_picture_list=[]
    jts_title_list=[]
    jts_shortTopic_list=[]
    jts_shuqiu_list=[]
    jts_tail_url_list=[]
    output2=pd.DataFrame()
    for jts_url_num in range(10):
        jts_ctime_list.append(jts_dict.get('postList')[jts_url_num].get('ctime'))
        jts_id_list.append(jts_dict.get('postList')[jts_url_num].get('id'))
        jts_picture_list.append(jts_dict.get('postList')[jts_url_num].get('picture'))
        jts_title_list.append(jts_dict.get('postList')[jts_url_num].get('title'))
        jts_shortTopic_list.append(jts_dict.get('postList')[jts_url_num].get('shortTopic'))
        jts_shuqiu_list.append(jts_dict.get('postList')[jts_url_num].get('shuqiu'))
        jts_tail_url_list.append("https://ts.21cn.com/tousu/show/id/"+str(jts_dict.get('postList')[jts_url_num].get('id')))
        output2 = pd.DataFrame({'ctime':jts_ctime_list,
                               'id':jts_id_list,
                               'picture':jts_picture_list,
                               'title':jts_title_list,
                               'shortTopic':jts_shortTopic_list,
                               'shuqiu':jts_shuqiu_list,
                               'tail_url':jts_tail_url_list})

    def stamp_to_datetime(stamp):
        """
        将时间戳(1539100800)转换为 datetime2018-10-09 16:00:00格式并返回
        :param stamp:
        :return:
        """
        time_stamp_array = datetime.utcfromtimestamp(stamp)
        date_time = time_stamp_array.strftime("%Y-%m-%d %H:%M:%S")
        # 如果直接返回 date_time则为字符串格式2018-10-09 16:00:00
        date = datetime.strptime(date_time,"%Y-%m-%d %H:%M:%S")
        return date

    output2['ctime']=output2.ctime.apply(lambda txt:stamp_to_datetime(txt))

    def output_wx(title,shortTopic,tail_url,picture):
        import json  
        import requests
        import base64
        import hashlib
        header = {  "Content-Type":"application/json",  "Charset":"utf-8"  } 
        url = "微信机器人地址"
        markdown = {
            "msgtype": "news",
            "news": {
               "articles" : [
                   {
                       "title" :title,
                       "description" : shortTopic,
                       "url" : tail_url,
                       "picurl" :picture
                   }
                ]
            }
        }
        request = requests.post(url,data = json.dumps(markdown),headers=header) 

    remain_jts=pd.read_excel('聚投诉爬虫结果.xlsx',encoding='GB18030')

    input_jts=output2[~output2.id.isin(remain_jts.id)].reset_index(drop=True)

    for i in range(len(input_jts)):
        output_wx(input_jts.loc[i].title,
                input_jts.loc[i].shortTopic,
                input_jts.loc[i].tail_url,
                input_jts.loc[i].picture)

    remain_jts=pd.concat([remain_jts,input_jts],ignore_index=True)
    remain_jts=remain_jts.sort_values('ctime')

    remain_jts.to_excel('聚投诉爬虫结果.xlsx',index=False)