5分钟教你百姓网爬取喜欢的狗子信息-python

源码如下：

import requests
import re
from my_fake_useragent import  UserAgent


class Gou:
    def __init__(self, html):
        #  获取页面
        self.html = html

        pass

    def __call__(self, *args, **kwargs):
        #  内置函数调用main函数
        self.main()

    # 程序主函数
    def main(self):
        #  匹配出所有的狗子
        res = re.findall('<li\sdata-aid.*?>(.*?)</li>', self.html)
        for i in res:
            # print(i)
             # 匹配出比标题
            rule1 = r"'.*?alt='(.*?)'.*?"
            res1 = re.findall(rule1, i)
            # print(res1)
            # 狗子图片
            rule2 = ".*?data-originSource='(.*?)'"
            res2 = re.findall(rule2, i)
            # print(res2)
            #  价格
            rule3 = ".*?<span class='highlight'>(.*?)</span>"
            res3 = re.findall(rule3, i)
            # print(res3)
            # 地址
            rule4 = ".*?<div class='ad-item-detail'>(.*?)</div>.*?"
            res4 = re.findall(rule4, i)
            # print(res4[0])
            # 输处
            f = f"狗子标题：{res1},\n狗子图片链接：{res2},\n狗子价格：{res3},\n狗子地址：{res4[0]}"
            print(f)
            print()
        pass


if __name__ == '__main__':
    #  定义页数
    page = 1
    while True:
        #  拼接页数
        print(f"第{page}页")
        url = f'https://beijing.baixing.com/chongwujiaoyi/m177986/?entities=%E6%80%A7%E5%88%AB_%E5%85%AC&page={page}&%E4%BB%B7%E6%A0%BC%5B0%5D=1000&%E4%BB%B7%E6%A0%BC%5B1%5D=1100&%E5%B9%B4%E9%BE%84%5B0%5D=0&%E5%B9%B4%E9%BE%84%5B1%5D='
        headers = {
            "cookie": "__trackId=161770863848743; __city=beijing; __s=c5hnjhfuv952mpvdhl21ehgn82; Hm_lvt_5a727f1b4acc5725516637e03b07d3d2=1617708683; _ga=GA1.2.8320274.1617708683; _gid=GA1.2.703774208.1617708683; _auth_redirect=https%3A%2F%2Fbeijing.baixing.com%2Fchongwujiaoyi%2Fm177986%2F%3Fentities%3D%25E6%2580%25A7%25E5%2588%25AB_%25E5%2585%25AC%26%25E4%25BB%25B7%25E6%25A0%25BC%255B0%255D%3D1000%26%25E4%25BB%25B7%25E6%25A0%25BC%255B1%255D%3D1100%26%25E5%25B9%25B4%25E9%25BE%2584%255B0%255D%3D0%26%25E5%25B9%25B4%25E9%25BE%2584%255B1%255D%3D; __sense_session_pv=6; Hm_lpvt_5a727f1b4acc5725516637e03b07d3d2=1617708737",
            "if-modified-since": "Tue, 06 Apr 2021 11:32:16 GMT",
            "referer": "https://beijing.baixing.com/oz/s9verify_html?identity=spider_1&redirect=https%3A%2F%2Fbeijing.baixing.com%2Fchongwujiaoyi%2Fm177986%2F%3Fentities%3D%25E6%2580%25A7%25E5%2588%25AB_%25E5%2585%25AC%26%25E4%25BB%25B7%25E6%25A0%25BC%255B0%255D%3D1000%26%25E4%25BB%25B7%25E6%25A0%25BC%255B1%255D%3D1100%26%25E5%25B9%25B4%25E9%25BE%2584%255B0%255D%3D0%26%25E5%25B9%25B4%25E9%25BE%2584%255B1%255D%3D&scene=spider_1",
            "upgrade-insecure-requests": "1",
            "user-agent": UserAgent().random()
        }
        # 获取页面
        response = requests.get(url, headers=headers)
        html = response.text
        #  实例化对象和调用
        Gou(html)()
        # 判断是否为最后一页
        if "下一页" not in html:
            break
        page += 1

这里爬取的值阿拉斯加，有意者可以参考源码怕别的狗子