爬虫练习-某站数据爬取代码并存入数据库（简易）

import requests
import re
import pymysql
p=0
x=re.compile(r' <span class="t2"><a target="_blank" title="(.*?)" href="')
y=re.compile(r'<a target="_blank" title="(.*?)" href=".*?"  on')
z=re.compile(r'<span class="t4">(.*?)</span>')
j=re.compile(r'a target="_blank" title=".*?" href="(.*?)"  on')
for i in range(1,21):
    url='**/list/070200,000000,0000,00,9,99,%25E6%2595%25B0%25E6%258D%25AE%25E5%2588%2586%25E6%259E%2590,2,{}.html?lang=c&postchannel=0000&workyear=99&cotype=99&degreefrom=99&jobterm=99&companysize=99&ord_field=0&dibiaoid=0&line=&welfare='.format(i)
    headers={'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.116 Safari/537.36'}
    # tail%2F%3Fquery%3D%25E6%2595%25B0%25E6%258D%25AE%25E5%2588%2586%25E6%259E%2590%26city%3D101190100%26industry%3D%26position%3D&p=IvdF9Ge3R2sBRGsxOA%7E%7E''}
    response = requests.get(url=url,headers=headers)
    response.encoding='gb2312'
    x1=re.findall(x,response.text)
    y1=re.findall(y,response.text)
    z1=re.findall(z,response.text)
    del (z1[0])
    # print(z1)
    j1=re.findall(j,response.text)
    for i in range (len(j1)):
        # p=p+1
        # print(j1[i],p)
        # print(str(p)+':'+x1[i]+'  '+y1[i]+' '+z1[i]+' '+j1[i])
        # print(z1[i],p)
        db = pymysql.connect(
            host='。。',
            port=3306,
            user='root',
            passwd='。。',
            database='test',
            charset='utf8'
        )
        cursor = db.cursor()
        sql = "INSERT INTO job51 (name,position,RMB,LINK) VALUES ('{}','{}','{}','{}');".format(x1[i],y1[i],z1[i],j1[i])
        cursor.execute(sql)
        db.commit()
        cursor.close()
        db.close()

    # print(x1)
    # print(y1)
    # print(z1)
    # print(j1)
    # # print(response.text)
发表评论 取消回复

发表评论取消回复
