本文实例讲述了python提取页面内url列表的方法。分享给大家供大家参考。具体实现方法如下:
from bs4 import BeautifulSoup
import time,re,urllib2
t=time.time()
websiteurls={}
def scanpage(url):
websiteurl=url
t=time.time()
n=0
html=urllib2.urlopen(websiteurl).read()
soup=BeautifulSoup(html)
pageurls=[]
Upageurls={}
pageurls=soup.find_all("a",href=True)
for links in pageurls:
if websiteurl in links.get("href") and links.get("href") not in Upageurls and links.get("href") not in websiteurls:
Upageurls[links.get("href")]=0
for links in Upageurls.keys():
try:
urllib2.urlopen(links).getcode()
except:
print "connect failed"
else:
t2=time.time()
Upageurls[links]=urllib2.urlopen(links).getcode()
print n,
print links,
print Upageurls[links]
t1=time.time()
print t1-t2
n+=1
print ("total is "+repr(n)+" links")
print time.time()-t
scanpage("http://news.163.com/")
希望本文所述对大家的Python程序设计有所帮助。
Copyright© 2013-2020
All Rights Reserved 京ICP备2023019179号-8