把爬取的数据放进mysql时提示“string index out of range ”

Question

把爬取的数据放进mysql时提示“string index out of range，而且数据库里的公司名不全的状况
以下是代码

import requests
import re
import time
import numpy
import pymysql
import pandas
headers= {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.54 Safari/537.36'}
company = ["腾讯","百度"]
page_num= 1
for i in range(len(company)):
    for j in range(page_num):
        url = 'https://a.jiemian.com/index.php?m=search&a=index&msg='+company[i]+'type=news&page='+str(j+1)
        res = requests.get(url,headers=headers).text
        comntent = res
        
        p_allnews = '<div class="news-view left">(.*?)</div></div></div>'
        result_all = re.findall(p_allnews,comntent,re.S)
        
        new_single=[]
        for l in range(len(result_all)):
            p_title = '<div class="news-header"><h3><a href=.*?target="_blank" title="(.*?)">'
            title = re.findall(p_title,result_all[l])
            if title ==[]:
                title.append("没有标题")

            p_s = '<span class="author"><a href=.*? target="_blank">(.*?)</a> '
            s = re.findall(p_s,result_all[l].strip(),re.S)
            if s ==[]:
                s.append("没有来源")

            p_dt = '<span class="date">(.*?)</span>'
            dt = re.findall(p_dt,result_all[l].strip(),re.S)
            if dt ==[]:
                dt.append("没有时间")


            p_c = '<div class="news-main"><p>(.*?)</p></div>'
            c = re.findall(p_c,result_all[l].strip(),re.S)
            if c ==[]:
                c.append("没有内容")

            print(str(l+1)+'.'+title[0])
            print("来源："+s[0]+"\n发布日期："+dt[0])
            print("新闻摘要："+c[0])
            
            company = company[i]
            title = title[0]
            s = s[0]
            dt = dt[0]
            c = c[0]
            
            db = pymysql.connect(host='localhost',port=3306,user='root',password='',database='jpnew',charset='utf8')
            cur = db.cursor()
            sql = "INSERT INTO `news` (`company`, `title`, `source`, `datatime`, `content`) VALUES (%s,%s,%s,%s,%s)"
            cur.execute(sql,(company,title,s,dt,c))
            db.commit()
            cur.close()
            db.close()
            

提示错误：string index out of range，而且数据库里的公司名不全的状况，为什么会出现这种情况，要怎么解决呢？

以下是数据库图片

Answer 1

你的写法有些奇怪,再说用+串联效率是非常低的。

company = ["腾讯","百度"]
page=3
for i in company:
    for j in range(1,page+1):
        url = f'https://a.jiemian.com/index.php?m=search&a=index&msg={i}type=news&page={j}'