wangzixaun2

import requests from bs4 import BeautifulSoup4 # 数据采集基础知识豆瓣读书T250的数据的获取 for i in range(0, 1): 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/137.0.0.0 Safari/537.36} r requests.get(url, headersheader, params{start: i * 25}) print(r.text) htmlr.text # 用beautifulsoup4库解析网页用lxml解析器解析器也要安装 soup BeautifulSoup(html, featureslxml) books soup.select(tr) # print(books) for book in books: tds book.select(td) name tds[1].div.a.text.strip().split(\n)[0] info tds[1].p.text