Python 百度爱采购ajax-获取到公司名称,电话

# @file :百度爱采购ajax.py
# @Softwara : PyCharm
import condition as condition
import requests
import re
import csv
from time import sleep
import os
#kw = input("请输入一个查询关键词：")
kw="江西"
file_name = '百度爱采购-%s.csv'%kw
f = open(file_name,mode='a',encoding='gbk')
cscwrite = csv.writer(f)
num = 0
for i in range(1,100):
    params = {
        'ajax': '1',
        'q': kw,
        'p': i,
        'sa':'',
        'mk': '全部结果',
        's': '30',
        'adn': '0',
        'resType': 'product',
        'from': 'search'
    }

    headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.114 Safari/537.36'}
    response = requests.get('https://b2b.baidu.com/s/a',params=params,headers=headers).json()
    name_list = response['data']['productList']
    list_num = len(name_list)
    print(len(name_list))
    for name in name_list:
        corporate_name = name.get('fullProviderName')       #获取到公司名称

        #构造公司联系页链接
        #url = f'https://b2b.baidu.com/shop?name={corporate_name}&xzhid=31231576&fid=0%2C1727148872616&pi=b2b.land....9846083244329408&tpath=contact'
        #xzhid=name.get('xzhid')
        jUrl=name.get('jUrl')
        jump_url=name.get('jumpUrl')
        #print(jump_url)
        match = re.search(r'xzhid=(\d+)', jump_url)
        if match:
            xzhid = match.group(1)
            #print(xzhid)
        else:
            xzhid=name.get('xzhid')
        url = f'https://b2b.baidu.com/shop?name={corporate_name}&xzhid={xzhid}&tpath=contact&fid=&pi='
        #print(url)
        resp = requests.get(url=url,headers=headers).text
        contact_name = re.findall('"contactName":"(.*?)"', resp, re.S)       #联系人
        external_Address=re.findall('"externalAddress":"(.*?)"', resp, re.S)       #公司地址
        if contact_name:
            # contact_name[0] 是字符串形式的Unicode编码
            contactName = contact_name[0].encode('utf-8').decode('unicode_escape')
        else:
            contactName="无"

        if external_Address:
            # contact_name[0] 是字符串形式的Unicode编码
            externalAddress = external_Address[0].encode('utf-8').decode('unicode_escape')
        else:
            externalAddress="无"

        phoneNumber = re.findall('"phoneNumber":"(.*?)"', resp, re.S)       #手机
        telNumber = re.findall('"telNumber":"(.*?)"', resp, re.S)           #电话
        faxNumber = re.findall('"faxNumber":"(.*?)"', resp, re.S)           #传真
        qqNumber = re.findall('"qqNumber":"(.*?)"', resp, re.S)             #qq号码
        wechatNumber = re.findall('"wechatNumber":"(.*?)"', resp, re.S)     #微信
        email = re.findall('"email":"(.*?)"', resp, re.S)                   #电子邮箱
        print(corporate_name,contactName,externalAddress, phoneNumber, telNumber, telNumber, faxNumber, qqNumber, wechatNumber, email)
        cscwrite.writerow([corporate_name,contactName,externalAddress, phoneNumber, telNumber, telNumber, faxNumber, qqNumber, wechatNumber, email])
        sleep(0.05)
        num +=1
    print('---第%s页采集完成---'%i )
    if (list_num == 0):
        f.close()
        print('---爬取完毕,共获取到%d条数据---' % num)
        os._exit(0)