[Python知识库]租房数据3000行

import requests
from bs4 import BeautifulSoup
from re import *
import csv


def looking(pages1):
    # 1. 获取网页数据
    response = requests.get(f'https://cd.zu.ke.com/zufang/pg{pages1}#contentList')
    '''
        https://cd.zu.ke.com/zufang/pg1#contentList
        https://cd.zu.ke.com/zufang/pg2/#contentList
        https://cd.zu.ke.com/zufang/pg3/#contentList
        '''
    # print(response.text)

    # 2. 解析网页数据
    soup = BeautifulSoup(response.text, 'lxml')
    all_house = soup.select('.content__list>.content__list--item')
    data = []
    for house in all_house:
        # 名字
        name = house.select_one('.twoline').text.strip()
        name1 = name.split()
        name2 = name1[0]
        # 价格
        price = house.select_one('.content__list--item-price').text

        # 地址-面积-户型
        p = house.select_one('.content__list--item--des')
        message = sub(r'\s+', '', p.text)
        list = message.split('/')
        location = list[-5]
        # print(location)
        area = list[-4]
        # print(area)
        model = list[-2]
        # print(model)
        data.append([name2, price, location, area, model])

    writer = csv.writer(open('files/租房.csv', "a", newline=''))
    if pages1 == 0:
        writer.writerow(['名字', '价格', '位置', '面积', '户型'])
    writer.writerows(data)

    # print(data)


for pages1 in range(100):
    looking(pages1)

import time

time.sleep(1)