不重复第访问网站，采用递归的方法from bs4 import BeautifulSoupimport urllib.requestdef spider(url): global urls if url not in urls: ____________________ try: data=urllib.request.urlopen(url) data=data.read() data=data.decode() soup=BeautifulSoup(data,"lxml") print(soup.find("h3").text) links=soup.select("a") for link in links: href=link["href"] _________________________ spider(url) except Exception as err: print(err)start_url="http://127.0.0.1:5000"urls=[]spider(start_url)print("The End")