1. import requests
    2. import csv
    3. from lxml import etree
    5. headers = {
    6.     'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/100.0.4896.60 Safari/537.36'
    7. }
    8. lis = []
    9. for i in range(1, 6):
    10.     url = f'https://cs.lianjia.com/ershoufang/pg{i}/'
    11.     response = requests.get(url=url, headers=headers).text
    12.     html_element = etree.HTML(response)
    13.     div_tags = html_element.xpath('//div[@class="info clear"]')
    14.     for div_tag in div_tags:
    15.         dic = {}
    16.         title = div_tag.xpath('./div[@class="title"]/a/text()')[0]
    17.         location = div_tag.xpath('./div[@class="flood"]/div//text()')[0] + div_tag.xpath('./div[@class="flood"]/div//text()')[1] + div_tag.xpath('./div[@class="flood"]/div//text()')[2]
    18.         address = div_tag.xpath('./div[@class="address"]/div/text()')[0]
    19.         priceInfo = div_tag.xpath('./div[@class="priceInfo"]/div//text()')[1] + div_tag.xpath('./div[@class="priceInfo"]/div//text()')[2] + ' ' + div_tag.xpath('./div[@class="priceInfo"]/div//text()')[3]
    20.         dic['title'] = title
    21.         dic['location'] = location
    22.         dic['address'] = address
    23.         dic['priceInfo'] = priceInfo
    24.         lis.append(dic)
    26. with open('房子.csv', 'w', encoding='utf-8', newline='') as f:
    27.     wt = csv.DictWriter(f, fieldnames=['title', 'location', 'address', 'priceInfo'])
    28.     wt.writeheader()
    29.     wt.writerows(lis)