想买房？我教你用python爬取链家房子信息

源码如下（解释请看注释）：

import re
import requests
from my_fake_useragent import UserAgent


class LianJia():
    def __init__(self, html):
        self.html = html
        # print(self.html)
        pass

    def __call__(self, *args, **kwargs):
        self.main()
        pass

    def main(self):
        #  去除获取页面中所有的空格和换行
        str = re.sub('\s+', '', self.html).strip()
        # print(str)
        # 匹配所有房子的li标签
        res = re.findall('<liclass="res.*?"data.*?>(.*?)</li>', str)
        # 去除匹配结果中的无用值
        res.pop()
        for j, i in enumerate(res, 1):
            print(f'第{j}个')
            # 获取房子名字
            rule1 = '.*?class="resblock-img-wrapper"title="(.*?)"'
            res1 = re.findall(rule1, i)
            print('名称：', res1[0] if res1 else '暂无', )
            # 获取房子效果图
            rule2 = '.*?class="lj-lazy"data-original="(.*?)"'
            res2 = re.findall(rule2, i)
            print('效果图：', res2[0] if res2 else '暂无')
            # 获取楼盘状态
            rule3 = 'style=.*?>(.*?)</span><spanclass="sale-status"style=.*?>(.*?)</span>'
            res3 = re.findall(rule3, i)
            print('状态：', ''.join([i + ' ' for i in res3[0]]) if res3 else '暂无')
            # 单价
            rule4 = '<spanclass="number">(.*?)</span>'
            res4 = re.findall(rule4, i)
            print('均价：', res4[0], '元/㎡' if res4 else '暂无')
            # 总价
            rule5 = '<divclass="second">总价(.*?)</div>'
            res5 = re.findall(rule5, i)
            print('总价：', res5[0] if res5 else '暂无')
            # 建筑面积
            rule6 = '<divclass="resblock-area"><span>建面(.*?)</span>'
            res6 = re.findall(rule6, i)
            print('建筑面积：', res6[0] if res6 else '暂无')
            # 地址
            rule7 = '<span>(.*?)</span><iclass="split">/</i><span>(.*?)</span><iclass="split">/</i><ahref=.*?}">(.*?)</a>'
            res7 = re.findall(rule7, i)
            print('地址：', ''.join([i + '，' for i in res7[0]]) if res7 else '暂无')
            # 特点
            rule8 = '<divclass="resblock-tag"><span>(.*?)</span><span>(.*?)</span><span>(.*?)</span><span>(.*?)</span>'
            res8 = re.findall(rule8, i)
            print(print('优点：', ''.join([i + '，' for i in res8[0]]) if res8 else '暂无'))
            print()
        pass


if __name__ == '__main__':
	# 这里是看到这个网页一共有100页，所以直接循环100次，这里也可以直接在网页去获取页数
    for page in range(1,101):
        print(f'第{page}页')
        # 拼接网址
        url = f'https://xa.fang.lianjia.com/loupan/pg{page}/'
        # 请求头
        headers = {
            'Cookie': 'ab_jid_BFESS=b4db74462a11ae46581569a222fcfacbd11f;'
                      ' ab_jid=b4db74462a11ae46581569a222fcfacbd11f;'
                      ' ab_jid=b4db74462a11ae46581569a222fcfacbd11f; '
                      'BIDUPSID=B14AA316D2CDE2A262495641CB162AC7;'
                      ' PSTM=1578509640;'
                      ' BDUSS_BFESS=hSU0k2eWF-Y0VtOEt1TlRVfk1JMlpxMGpyNHNmQ'
                      'ldqalpCTU4yTUo4dkI0SDlnRVFBQUFBJCQAAAAAAAAAAAEAAADv7'
                      'Mp2n2~0dWNrAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA'
                      'AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAMFTWGDBU1hgN2; '
                      'BAIDUID_BFESS=4E5DC05E66B65A2F0A1BAA1D6504F37D:FG=1;'
                      ' ab_sr=1.0.0_MDRhNWI1MzMxMmVjNjMxZjI5NWFmYjJiOWI5MjdmY'
                      '2I4OWE3ZjUxMTNjZjRjODI4NWIxZmY2ODQyZDFlOTEwZjQyZjAxMDY'
                      'yMWE5NjhlN2RmOGEyYmI4YzYwMmE5MWJh',
            'Host': 'xa.fang.lianjia.com',
            "user-agent": UserAgent().random(),
            'Referer': 'https: // xa.fang.lianjia.com /'
        }
        # 获取页面
        response = requests.get(url=url, headers=headers)
        html = response.content.decode('utf-8')
        #  实例化对象和调用
        LianJia(html)()