Biegral Blog

前言

本文的文字及图片来源于网络,仅供学习、交流使用,不具有任何商业用途,如有问题请及时联系我们以作处理。

PS：如有需要Python学习资料的小伙伴可以加点击下方链接自行获取

python免费学习资料以及群交流解答点击即可加入

---

开发工具

• Python 3.6.5
• Pycharm
• requests
• re
• json

相关模块可用pip命令安装

网页分析

https://search.51job.com/list/010000%252c020000%252c030200%252c040000,000000,0000,00,9,99,python,2,1.html

请求网页

import requests
url = 'https://search.51job.com/list/010000%252c020000%252c030200%252c040000,000000,0000,00,9,99,python,2,1.html'
params = {
    'lang': 'c',
    'postchannel': '0000',
    'workyear': '99',
    'cotype': '99',
    'degreefrom': '99',
    'jobterm': '99',
    'companysize': '99',
    'ord_field': '0',
    'dibiaoid': '0',
    'line': '',
    'welfare': '',
}
cookies = {
	'''
	你的cookie
	'''
}
headers = {
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
    'Host': 'search.51job.com',
    'Referer': 'https://search.51job.com/list/190200,000000,0000,00,9,99,python,2,1.html?lang=c&postchannel=0000&workyear=99&cotype=99&degreefrom=99&jobterm=99&companysize=99&ord_field=0&dibiaoid=0&line=&welfare=',
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.105 Safari/537.36',
}

response = requests.get(url=url, params=params, headers=headers, cookies=cookies)
response.encoding = response.apparent_encoding
print(response.text)

咱们需要的数据的在<script> 里面

<script type="text/javascript">
window.__SEARCH_RESULT__ = 
'''
你想要获取的内容
'''
<div class="clear"></div>

用正则表达式匹配出来就可以了

把匹配出来的数据转化程json数据，然后根据字典的取值方式取自己想要数据即可

r = re.findall('window.__SEARCH_RESULT__ = (.*?)</script>', response.text, re.S)
string = ''.join(r)
info_dict = json.loads(string)
pprint.pprint(info_dict)

完整代码

import requests
import re
import json
for page in range(1, 11):
    url = 'https://search.51job.com/list/010000%252c020000%252c030200%252c040000,000000,0000,00,9,99,python,2,{}.html'.format(page)
    params = {
        'lang': 'c',
        'postchannel': '0000',
        'workyear': '99',
        'cotype': '99',
        'degreefrom': '99',
        'jobterm': '99',
        'companysize': '99',
        'ord_field': '0',
        'dibiaoid': '0',
        'line': '',
        'welfare': '',
    }
    cookies = {

    }
    headers = {
        'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
        'Host': 'search.51job.com',
        'Referer': 'https://search.51job.com/list/190200,000000,0000,00,9,99,python,2,1.html?lang=c&postchannel=0000&workyear=99&cotype=99&degreefrom=99&jobterm=99&companysize=99&ord_field=0&dibiaoid=0&line=&welfare=',
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.105 Safari/537.36',
    }

    response = requests.get(url=url, params=params, headers=headers, cookies=cookies)
    response.encoding = response.apparent_encoding
    r = re.findall('window.__SEARCH_RESULT__ = (.*?)</script>', response.text, re.S)
    string = ''.join(r)
    info_dict = json.loads(string)
    dit_py = info_dict['engine_search_result']
    dit = {}
    for i in dit_py:
        attribute_text = ' '.join(i['attribute_text'][1:])
        print(attribute_text)
        # dit['job_href'] = i['job_href']
        dit['job_name'] = i['job_name']
        dit['company_name'] = i['company_name']
        dit['money'] = i['providesalary_text']
        dit['workarea'] = i['workarea_text']
        dit['updatedate'] = i['updatedate']
        dit['companytype'] = i['companytype_text']
        dit['jobwelf'] = i['jobwelf']
        dit['attribute'] = attribute_text
        dit['companysize'] = i['companysize_text']
        print(dit)
        with open('python招聘信息.csv', mode='a', encoding='utf-8') as f:
            f.write('{},{},{},{},{},{},{},{}\n'.format(dit['job_name'], dit['company_name'], dit['money'], dit['workarea'], dit['companytype'], dit['jobwelf'], dit['attribute'], dit['companysize']))

实现效果