某老师的作业。 说做完直接给优。。。真是愉快 。。
#!/usr/bin/python env
import bs4,urllib2,urllib,sys
import time
import traceback
from bs4 import BeautifulSoup
reload(sys)
sys.setdefaultencoding("utf-8")
def getImage(addr):
u = urllib.urlopen(addr)
data = u.read()
splitPath = addr.split('/')
fName = splitPath.pop()
print fName
f = open(fName, 'wb')
f.write(data)
f.close()
getImage("http://f11.topit.me/l/201010/24/12879143531545.jpg")
for number in range(0,1111111):
url = "http://www.topit.me/item/"+str(number)
print url
try:
data = urllib2.urlopen(url)
doc = data.read()
soup = BeautifulSoup(doc)
f = soup.find('div',{"id":"canvasbox"})
if f != None:
f = f.find('a',{"id":"item-tip"})
if f!= None:
now_url = f.get('href')
print now_url
getImage(now_url)
except Exception as err:
print (err)
traceback.print_exc()
time.sleep(10)
continue
请先安装python 环境跟 BeautifulSoup模块