1. import requests
    2. import csv
    3. from lxml import etree
    5. def read_page(url, headers):
    6.     res = requests.get(url, headers=headers)
    7.     html = res.text
    8.     html_ement = etree.HTML(html)
    9.     infos = html_ement.xpath('//div[@class="info clear"]')
    10.     info = []
    11.     for shuju in infos:
    12.         fangziDict = {}
    13.         name = shuju.xpath('.//a/text()')[0]
    14.         dizhi1 = shuju.xpath('.//a/text()')[1]
    15.         dizhi2 = shuju.xpath('.//a/text()')[2]
    16.         dizhi = dizhi1 + '-' + dizhi2
    17.         sheji1 = shuju.xpath('.//div/text()')[2]
    18.         sheji2 = shuju.xpath('.//div/text()')[3]
    19.         sheji = sheji1 + sheji2
    20.         jiage1 = shuju.xpath('.//span/text()')[-2]
    21.         jiage2 = shuju.xpath('.//span/text()')[-1]
    22.         jiage = jiage1 + '万' + '    ' + jiage2
    23.         fangziDict['房名'] = name
    24.         fangziDict['地址'] = dizhi
    25.         fangziDict['设计样式'] = sheji
    26.         fangziDict['价格'] = jiage
    27.         info.append(fangziDict)
    28.     # print(info)
    29.     return info
    31. def bao_cun(info):
    32.     with open('ershoufang.csv', 'w', encoding='utf-8-sig', newline='') as f:
    33.         writer = csv.DictWriter(f, fieldnames=['房名', '地址', '设计样式', '价格'])
    34.         writer.writeheader()
    35.         writer.writerows(info)
    38. url = 'https://cs.lianjia.com/ershoufang/'
    39. headers = {
    40.     'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/100.0.4896.75 Safari/537.36'
    41. }
    42. info = read_page(url, headers)
    43. bao_cun(info)