python爬取链家租房数据

以下是使用Python爬取链家租房数据的示例代码：

import requests
from bs4 import BeautifulSoup

# 设置请求头，模拟浏览器访问
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3'
}

# 设置要爬取的城市和页码范围
city = 'bj'  # 北京
start_page = 1
end_page = 5

# 循环遍历每一页的房源列表页
for page in range(start_page, end_page + 1):
    url = f'https://{city}.lianjia.com/zufang/pg{page}/#contentList'
    response = requests.get(url, headers=headers)
    soup = BeautifulSoup(response.text, 'html.parser')

    # 解析房源信息
    house_list = soup.find_all('div', class_='content__list--item--main')
    for house in house_list:
        district = house.find('a', class_='content__list--item--des').text.strip()
        street = house.find('a', class_='content__list--item--des').find_next('a').text.strip()
        community = house.find('a', class_='content__list--item--des').find_next('a').find_next('a').text.strip()
        floor = house.find('span', class_='content__list--item--des').text.strip()
        lift = house.find('span', class_='content__list--item--des').find_next('span').text.strip()
        area = house.find('span', class_='content__list--item--des').find_next('span').find_next('span').text.strip()
        toward = house.find('span', class_='content__list--item--des').find_next('span').find_next('span').find_next('span').text.strip()
        model = house.find('span', class_='content__list--item--des').find_next('span').find_next('span').find_next('span').find_next('span').text.strip()
        rent = house.find('span', class_='content__list--item-price').text.strip()

        # 打印房源信息
        print(f"城区名：{district}")
        print(f"街道名：{street}")
        print(f"小区名：{community}")
        print(f"楼层信息：{floor}")
        print(f"有无电梯：{lift}")
        print(f"面积：{area}")
        print(f"房屋朝向：{toward}")
        print(f"户型：{model}")
        print(f"租金：{rent}")
        print("")