Python网络爬虫案例（二）——爬取招聘信息网站

利用Python，爬取 51job 上面有关于 IT行业 的招聘信息

　　版权声明：未经博主授权，内容严禁分享转载　　

案例代码：

# __author : "J"
# date : 2018-03-07

import urllib.request
import re
import pymysql

connection = pymysql.connect(host='127.0.0.1', port=3306, user='root', password='******', db='51job',
                             charset='utf8')
cursor = connection.cursor()

num = 0
textnum = 1
while num < 18:

    num += 1
    # 51job IT行业招聘网址 需要翻页，大约800多条数据
    request = urllib.request.Request(
        "http://search.51job.com/list/120000,000000,0100,32,9,99,%2B,2," + str(
            num) + ".html?lang=c&stype=1&postchannel=0000&workyear=99&cotype=99&degreefrom=99&jobterm=99&companysize=99&lonlat=0%2C0&radius=-1&ord_field=0&confirmdate=9&fromType=1&dibiaoid=0&address=&line=&specialarea=00&from=&welfare=")

    response = urllib.request.urlopen(request)
    my_html = response.read().decode('gbk')
    # print(my_html)

    my_re = re.compile(r'href="(.*?)" onmousedown="">')
    second_html_list = re.findall(my_re, my_html)

    for i in second_html_list:
        second_request = urllib.request.Request(i)
        second_response = urllib.request.urlopen(second_request)
        second_my_html = second_response.read().decode('gbk')
        # 职位 地区 工资 公司名称 公司简介
        # 工作经验 学历 招聘人数 发布时间
        # 职位信息 联系方式 公司信息
        second_my_re = re.compile('<h1 title=.*?">(.*?)<input value=.*?' +
                                  '<span class="lname">(.*?)</span>.*?' +
                                  '<strong>(.*?)</strong>.*?' +
                                  'target="_blank" title=".*?">(.*?)<em class="icon_b i_link"></em></a>.*?' +
                                  '<p class="msg ltype">(.*?)</p>.*?</div>'
                                  , re.S | re.M | re.I)
        second_html_news = re.findall(second_my_re, second_my_html)[0]
        zhiwei = second_html_news[0].replace("\n|\t|\r|\r\n", '').replace("&nbsp;", '').replace("    ", '').replace(
            " ",
            '')
        diqu = second_html_news[1].replace("\n|\t|\r|\r\n", '').replace("&nbsp;", '').replace("    ", '').replace(
            " ",
            '')
        gongzi = second_html_news[2].replace("\n|\t|\r|\r\n", '').replace("&nbsp;", '').replace("    ", '').replace(
            " ",
            '')
        gongsimingcheng = second_html_news[3].replace("\n|\t|\r|\r\n", '').replace("&nbsp;", '').replace("    ",
                                                                                                         '').replace(
            " ",
            '')
        gongsijianjie = second_html_news[4].replace("\n|\t|\r|\r\n", '').replace("&nbsp;", '').replace("    ",
                                                                                                       '').replace(
            " ",
            '')
        # print(zhiwei,diqu,gongzi,gongsimingcheng,gongsijianjie)
        try:
            second_my_re = re.compile('<span class="sp4"><em class="i1"></em>(.*?)</span>'
                                      , re.S | re.M | re.I)
            yaoqiu = re.findall(second_my_re, second_my_html)[0]
        except Exception as e:
            pass
        try:
            second_my_re = re.compile('<span class="sp4"><em class="i2"></em>(.*?)</span>'
                                      , re.S | re.M | re.I)
            yaoqiu += ' | ' + re.findall(second_my_re, second_my_html)[0]
        except Exception as e:
            pass
        try:
            second_my_re = re.compile('<span class="sp4"><em class="i3"></em>(.*?)</span>'
                                      , re.S | re.M | re.I)
            yaoqiu += ' | ' + re.findall(second_my_re, second_my_html)[0]
        except Exception as e:
            pass
        try:
            second_my_re = re.compile('<span class="sp4"><em class="i4"></em>(.*?)</span>'
                                      , re.S | re.M | re.I)
            yaoqiu += ' | ' + re.findall(second_my_re, second_my_html)[0]
        except Exception as e:
            pass
        # print(yaoqiu)
        second_my_re = re.compile('<div class="bmsg job_msg inbox">(.*?)<div class="mt10">'
                                  , re.S | re.M | re.I)
        gangweizhize = re.findall(second_my_re, second_my_html)[0].replace("\r\n|\n|\t|\r", '').replace("    ",
                                                                                                        '').replace(
            " ", '').replace("&nbsp;", '')

        dr = re.compile(r'<[^>]+>', re.S)
        gangweizhize = dr.sub('', gangweizhize)

        second_my_re = re.compile('<span class="bname">联系方式</span>(.*?)<div class="tBorderTop_box">'
                                  , re.S | re.M | re.I)
        lianxifangshi = re.findall(second_my_re, second_my_html)[0].replace("\r\n|\n|\t|\r", '').replace("&nbsp;", '')

        dr = re.compile(r'<[^>]+>', re.S)
        lianxifangshi = dr.sub('', lianxifangshi)
        lianxifangshi = re.sub('\s', '', lianxifangshi)

        second_my_re = re.compile('<span class="bname">公司信息</span>(.*?)<div class="tCompany_sidebar">'
                                  , re.S | re.M | re.I)
        gongsixinxi = re.findall(second_my_re, second_my_html)[0].replace("&nbsp;", '')
        dr = re.compile(r'<[^>]+>', re.S)
        gongsixinxi = dr.sub('', gongsixinxi)
        gongsixinxi = re.sub('\s', '', gongsixinxi)

        print('第 '+str(textnum) + ' 条数据 **********************************************')
        print(zhiwei, diqu, gongzi, gongsimingcheng, gongsijianjie, yaoqiu, gangweizhize, lianxifangshi, gongsixinxi)
        textnum += 1
        # try:
        #     sql = "INSERT INTO `jobNews` (`position`,`region`,`Pay`,`company`,`Nature`,`Requirement`,`Job_information`,`Contact_information`,`Company_information`) VALUES ('" + zhiwei + "','" + diqu + "','" + gongzi + "','" + gongsimingcheng + "','" + gongsijianjie + "','" + yaoqiu + "','" + gangweizhize + "','" + lianxifangshi + "','" + gongsixinxi + "')"
        #     cursor.execute(sql)
        #     connection.commit()
        #     print('存储成功！')
        # except Exception as e:
        #     pass

cursor.close()
connection.close()

效果：

我正则表达式用的不好，所以写的很麻烦，接受建议～