爬取51job准备练习数据可视化

版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。

本文链接： https://blog.csdn.net/lipachong/article/details/101155790

import requests
from bs4 import BeautifulSoup
from fake_useragent import UserAgent
import random
import time
from lxml import etree
from pymysql import *

def get_list_url(url):
    ua = UserAgent()
    useragent=ua.chrome
    headers={
            'User-Agent':useragent
    }
    rq=requests.get(url,headers=headers)
    print(url)
    time.sleep(random.choice(range(1,4)))
    rq.encoding='gbk'
    soup=BeautifulSoup(rq.text,'lxml')
    company_div=soup.find('div',id='resultList').findAll('div',class_='el')
    urls=[]
    for x in company_div:
        try:
            url1=x.find('a')['href']
            urls.append(url1)
        except:
            pass

    return urls
def get_massage(urls):
    for url in urls:
        ua = UserAgent()
        useragent = ua.chrome
        headers = {
            'User-Agent': useragent
        }
        rq = requests.get(url, headers=headers)
        print(url)
        time.sleep(random.choice(range(1, 4)))
        rq.encoding = 'gbk'
        data = rq.text
        h = etree.HTML(data)
        soup=BeautifulSoup(data,'lxml')
        try:
            zhiwei=h.xpath('/html/body/div[3]/div[2]/div[2]/div/div[1]/h1/text()')[0]
            print(zhiwei)
            company = h.xpath('/html/body/div[3]/div[2]/div[2]/div/div[1]/p[1]/a[1]/text()')[0]
            print(company)
            address = h.xpath('/html/body/div[3]/div[2]/div[2]/div/div[1]/p[2]/text()[1]')[0]
            print(address)
            xingzhi = h.xpath('/html/body/div[3]/div[2]/div[4]/div[1]/div[2]/p[1]/text()')[0]
            print(xingzhi)
            xinzi = h.xpath('/html/body/div[3]/div[2]/div[2]/div/div[1]/strong/text()')[0]
            print(xinzi)
            xuewei = h.xpath('/html/body/div[3]/div[2]/div[2]/div/div[1]/p[2]/text()[3]')[0].replace(' ','').replace('\\r','')
            print(xuewei)
            jingyan = h.xpath('/html/body/div[3]/div[2]/div[2]/div/div[1]/p[2]/text()[2]')[0].replace(' ','').replace('\\r','')
            print(jingyan)
            guimo = h.xpath('/html/body/div[3]/div[2]/div[4]/div[1]/div[2]/p[2]/text()')[0]
            print(guimo)
            leixing = h.xpath('/html/body/div[3]/div[2]/div[4]/div[1]/div[2]/p[3]/a/text()')[0]
            print(leixing)
            fuli = soup.find('div',class_='t1').find('span').get_text()
            print(fuli)
            time1 = h.xpath('/html/body/div[3]/div[2]/div[2]/div/div[1]/p[2]/text()[5]')[0].replace(' ','').replace('\\r','').replace('\\n','')
            print(time1)
            yaoqiu = soup.find('div',class_='bmsg job_msg inbox').get_text().replace(' ','').replace('\\r','').replace('\\n','')
            print(yaoqiu)
            insert_data(zhiwei=zhiwei, company=company, address=address, xingzhi=xingzhi, xinzi=xinzi, xuewei=xuewei
                        , jingyan=jingyan, guimo=guimo, leixing=leixing, fuli=fuli, time1=time1
                        , yaoqiu=yaoqiu)
        except:
            pass

# #插入数据
def insert_data(**args):
    cursor = conn.cursor()
    query = cursor.execute("insert into 51job(zhiwei, company, address, "
                           "xingzhi, xinzi, xuewei, jingyan, guimo,"
                           " leixing, fuli, time1, yaoqiu)values(%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)",
                           (args['zhiwei'],args['company'],args['address'],args['xingzhi'],args['xinzi'],args['xuewei']
                            , args['jingyan'],args['guimo'],args['leixing'],args['fuli'],args['time1'],args['yaoqiu']))
    conn.commit()

if __name__=='__main__':
    conn = connect(host='127.0.0.1', port=3306, user='root', passwd='', db='qianchengwuyou', charset='utf8')
    for page in range(33,753):
        url='https://search.51job.com/list/000000,000000,0000,00,9,99,python,2,{}.html?lang=c&postchannel=0000&workyear=99&cotype=99&degreefrom=99&jobterm=99&companysize=99&ord_field=0&dibiaoid=0&line=&welfare='.format(str(page))
        urls=get_list_url(url)
        get_massage(urls)