豆瓣读书top250（半结构化数据）

import requests
from bs4 import BeautifulSoup
import json
import os

url = "https://book.douban.com/top250"
header = {
   
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/112.0.0.0 Safari/537.36"
}
def getHtml(num):
    r = requests.get(url,headers=header,params={
   "start": num})
    return r.text

html = getHtml(0)
# print(html)

# 打印一页数据
def getPrintData(html):
    soup = BeautifulSoup(html,"lxml")
    books = soup.select("tr")
    for book in books:
        tds=book.select("td")
        print("书名：",tds[1].div.a.text.strip().split("\n")