爬取企查查公司信息

import requests
import time
from lxml import etree
import pandas as pd
import csv

base_url = 'https://www.qcc.com/web/search?key='
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:86.0) Gecko/20100101 Firefox/86.0'
}
data = pd.read_csv('E:\movieinfo3.csv',header=None)
data.columns=['id','url']
a = []
f = open('E:\qichacha.csv','w',newline='')
writer  = csv.writer(f)

title = ['统一社会信用代码','企业名称','法定代表人','成立日期','注册资本','工商注册号','企业类型','营业期限','登记机关','注册地址','经营范围']
writer.writerow(title)
def getCompanyData(url,num):
    try:
        response = requests.get(url, headers=headers)
        response.encoding="utf-8"
        # print(response.text)
        html = etree.HTML(response.text)
        try:     #信用代码               #//*[@id="cominfo"]/div[2]/table/tr[1]/td[2]
            shehui_xinyong=html.xpath('//*[@id="cominfo"]/div[2]/table/tr[1]/td[2]/text()')[0]
        except:
            shehui_xinyong = None

        try:     #公司名称              #//*[@id="cominfo"]/div[2]/table/tr[1]/td[4]
            gongsi_name = html.xpath('//*[@id="cominfo"]/div[2]/table/tr[1]/td[4]/text()')[0]
        except:
            gongsi_name = None

        try:      #法定代表人                #//*[@id="cominfo"]/div[2]/table/tr[2]/td[2]/div/span[2]/span/a
            fadingdaibiaoren = html.xpath('//*[@id="cominfo"]/div[2]/table/tr[2]/td[2]/div/span[2]/span/a/text()')[0]
        except:
            fadingdaibiaoren = None

        try:     #注册资本              #//*[@id="cominfo"]/div[2]/table/tr[3]/td[2]
            zhuceziben =  html.xpath('//*[@id="cominfo"]/div[2]/table/tr[3]/td[2]/text()')[0]
        except:
            zhuceziben = None

        try:    #注册号               #//*[@id="cominfo"]/div[2]/table/tr[4]/td[4]
            gszucehao = html.xpath('//*[@id="cominfo"]/div[2]/table/tr[4]/td[4]/text()')[0]
        except:
            gszucehao = None

        try:   #企业类型            #//*[@id="cominfo"]/div[2]/table/tr[5]/td[2]
            qiyeleix = html.xpath('//*[@id="cominfo"]/div[2]/table/tr[5]/td[2]/text()')[0]
        except:
            qiyeleix = None

        try:   #营业期限              #//*[@id="cominfo"]/div[2]/table/tr[5]/td[4]
            yingyeqixian = html.xpath('//*[@id="cominfo"]/div[2]/table/tr[5]/td[4]/text()')[0]
        except:
            yingyeqixian = None

        try:   #注册地址             #//*[@id="cominfo"]/div[2]/table/tr[9]/td[2]/a[1]
            zucedizhi = html.xpath('//*[@id="cominfo"]/div[2]/table/tr[9]/td[2]/a[1]/text()')[0]
        except:
            zucedizhi = None

        try:    #营业范围              #//*[@id="cominfo"]/div[2]/table/tr[10]/td[2]
            jingyingfanwei = html.xpath('//*[@id="cominfo"]/div[2]/table/tr[10]/td[2]/text()')[0]
        except:
            jingyingfanwei = None

        try:    #成立日期           #//*[@id="cominfo"]/div[2]/table/tr[2]/td[6]
            chengliriqi = html.xpath('//*[@id="cominfo"]/div[2]/table/tr[2]/td[6]/text()')[0]
        except:
            chengliriqi = None

        try:     #登记机关           #//*[@id="cominfo"]/div[2]/table/tr[6]/td[6]
            dengjijiguan = html.xpath('//*[@id="cominfo"]/div[2]/table/tr[6]/td[6]/text()')[0]
        except:
            dengjijiguan = None
        writer.writerow([shehui_xinyong,gongsi_name,fadingdaibiaoren,chengliriqi,zhuceziben,gszucehao,qiyeleix,yingyeqixian,dengjijiguan,zucedizhi,jingyingfanwei])

        print('第{}条------->>>'.format(num), gongsi_name)
        num += 1

        time.sleep(30)
    except:
        time.sleep(10)
        print('错误')
        pass
# a.append(title)
for j,i in enumerate(data.url):
    getCompanyData(i,j+1)
f.close()

print('successlly')

数据：https://download.youkuaiyun.com/download/yangzheng_520/21979543

关注一下，谢谢