[Python] 把房产网页里面的二手房数据全部扒了下来！

import requestsimport parsel
import csv
import re
from threading import Thread


headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari/537.36'
}


def respon(first_url): # 请求函数
    resp = requests.get(url=first_url, headers=headers).text
    return resp


def get_url(first_url): # 获取二级链接
    resp = respon(first_url)
    select = parsel.Selector(resp)
    href = select.css('.house_item h1 a::attr(href)').getall()
    href_list = []
    for item in href:
        if 'broker' in item:
            pass
        elif 'community' in item:
            pass
        else:
            href_list.append(item)
    return href_list


def get_data(second_url): # 获取数据
    resp = respon(second_url)
    select = parsel.Selector(resp)
    title = select.css('.house_info h1::attr(title)').get()
    info = select.css('.other span::text').getall()
    price = select.css('.price_left::text').get()
    phone = select.css('.other1 div:nth-child(4) span::text').get()
    infor = [title, info[0], info[1], info[2], info[3], info[4], price, phone]
    return infor


def save(first_url): # 保存函数
    list_url = get_url(first_url)
    title = ['名称', '房型', '属性', '平方', '楼层', '装修', '价格', '电话']
    with open('二手房.csv', mode='a', newline='', encoding='utf-8') as f:
        writer = csv.writer(f)
        writer.writerow(title)
        for link in list_url:
            list_data = get_data(link)
            writer.writerow(list_data)


def main(): # 主函数
    for i in range(1, 11):
        # print(i)
        url = f'http://www.*****.com/house/second/f_-page_{i}.html'
        save(url)


if __name__ == '__main__': # 调试函数
    t = Thread(target=main)
    t1 = Thread(target=main)
    t2 = Thread(target=main)
    t3 = Thread(target=main)
    t.start()
    t1.start()
    t2.start()
    t3.start()
    main()