2.数据采集基础知识

import requests from bs4 import BeautifulSoup #数据采集基础知识:豆瓣读书T250的数据获取 for i in range(0,10): url https://book.douban.com/top250 header {user-agent:Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36} r requests.get(url,headersheader,params{start:i*25}) print(r) #用beautifulsoup4库解析网页用lxml解析器,解析器也要安装 soupBeautifulSoup(r.text,lxml) bookssoup.select(tr) # print(books) for book in books: tdsbook.select(td) nametds[1].div.a.text.strip().split(\n)[0] infotds[1].p.text print(name)