爬虫爬一个隐式提交的网站

import csv
import re
import requests

f = open("shuhua.csv", mode="w", encoding="utf-8")
csvwrite = csv.writer(f)

form = {"status": "5", "page": 1, "orderby": "6", "evaluation_price": "", "advancedSeach": "", "startdate": "",
        "enddate": "", "rmbPriceStart": "", "rmbPriceEnd": "", "classCode": "020100000000", "organCode": "",
        "organName": "", "item": "", "city": "", "is_total": "1", "keyword": ""}

obj = re.compile(
    r'"detail".*?"workName":"(?P<title>.*?)".*?"name":"(?P<name>.*?)".*?"label":"材质","text":"(?P<caizhi>.*?)".*?'
    r'"label":"尺寸","text":"(?P<size>.*?)".*?"label":"估价","text":"(?P<gujia>.*?)".*?"label":"成交价","text":'
    r'"(?P<price>.*?)".*?label":"形制","text":"(?P<xingzhi>.*?)".*?"label":"拍品分类","text":"(?P<fenlei>.*?)"'
    r'.*?"label":"拍品描述","text":"(?P<miaoshu>.*?)"', re.S)

url = f"https://api.artron.net/v1/auctions/index"

count = 0
headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/102.0.5005.63 Safari/537.36 Edg/102.0.1245.33"
}

for pa in range(1, 10):
    form["page"] = pa

    resp = requests.post(url, headers=headers, data=form)  # 拿到网页源代码

    content = resp.text

    result = obj.finditer(content)

    for i in result:
        # print(i.group("title"))
        # print(i.group("name"))
        # print(i.group("caizhi"))
        # print(i.group("size"))
        # print(i.group("gujia"))
        # print(i.group("price"))
        # print(i.group("xingzhi"))
        # print(i.group("fenlei"))
        # print(i.group("miaoshu"))
        count += 1
        print(count)
        dic = i.groupdict()

        csvwrite.writerow(dic.values())

f.close()
resp.close()
print("over!")

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值