当前位置：首页 > news >正文

自己写的爬虫小案例

news 2025/8/4 5:02:20

网址：aHR0cDovL2pzc2NqZ3B0Lmp4d3JkLmdvdi5jbi8/dXJsPS92aWV3L3dvcmtpbmdVbml0L3dvcmtpbmdVbml0Lmh0bWw=

这串代码能够爬取勘察单位企业的详细信息。

import requests
import time
import csv
f = open('勘察单位公司信息.csv','w',encoding='utf-8',newline='')
csv_writer = csv.DictWriter(f,fieldnames=['公司名称','涉及领域','所属省市','注册资本（万元）','成立日期','发证机关','统一社会信用码','经营范围','单位网址','法人','主营业务','注册地址','证书网址',])
csv_writer.writeheader()
cookies = {'JSESSIONID': 'BD8F06872E4D854606108A0F4AF55D79',
}
def get_response(id):info_url = f'http://jsscjgpt.jxwrd.gov.cn/api/employer/findByEmployer?unitId={id}'result = requests.get(url=info_url,headers=headers).json()return result
headers = {'Accept': 'application/json, text/javascript, */*; q=0.01','Accept-Language': 'zh-CN,zh;q=0.9','Cache-Control': 'no-cache','Connection': 'keep-alive','Content-Type': 'application/json',# 'Cookie': 'JSESSIONID=BD8F06872E4D854606108A0F4AF55D79','Origin': 'http://jsscjgpt.jxwrd.gov.cn','Pragma': 'no-cache','User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36','X-Requested-With': 'XMLHttpRequest',
}
for page in range(1,299):time.sleep(1)json_data = {'pageNum': page,'pageSize': 10,'query': '1','unitName': '','unitCode': '','userName': '',}response = requests.post('http://jsscjgpt.jxwrd.gov.cn/api/employer/findAll',cookies=cookies,headers=headers,json=json_data,verify=False,)json_response = response.json()for index in json_response['data']['list']:id = index['companyId']data = get_response(id)['data']dit = {'公司名称': data['name'],'涉及领域': data['categoryType'],'所属省市': data['address'],'注册资本（万元）': data['registeredMoney'],'成立日期': data['setUpYear'],'发证机关': data['certificateCompany'],'统一社会信用码': data['code'],'经营范围': data['businessRange'],'单位网址': data['companyUrl'],'法人': data['legalPerson'],'主营业务': data['mainBusiness'],'注册地址': data['registeredAddress'],'证书网址': data['companyCommitment'],}print(dit)csv_writer.writerow(dit)