单项选择题
不重复访问网站，使用栈的程序 from bs4 import BeautifulSoup import urllib.request class Stack: def __init__(self): self.st=[] def pop(self): return self.st.pop() def push(self,obj): self.st.append(obj) def empty(self): return len(self.st)==0 def spider(url): global urls stack=Stack() stack.push(url) while not stack.empty(): url=stack.pop() 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 i in _______________________: href=links[i]["href"] url=start_url+"/"+href stack.push(url) except Exception as err: print(err) start_url="http://127.0.0.1:5000" urls=[] spider(start_url) print("The End")
A、urls.append(url); range(len(links),-1,-1)
B、urls.append(url); range(len(links)-1,0,-1)
C、urls.insert(url,0); range(len(links)-1,-1,-1)
D、urls.append(url); range(len(links)-1,-1,-1)
A.request
B.st=[]
C.st.pop()
D.st.append(obj)
E.st)==0
F.push(url)
G.empty():
H.pop()
I.request.urlopen(url)
J.read()
K.decode()
L.find("h3").text)
M.select("a")
N.push(url)
O.0.0.1:5000"
P.append(url);
Q.append(url);
R.insert(url,0);
S.append(url);
