37,719
社区成员
发帖
与我相关
我的任务
分享
#!/usr/bin/python
import urllib2
import re
def downURL(url,filename):
print url
print filename
try:
fp = urllib2.urlopen(url)
except:
print 'download exception'
return 0
op = open(filename,"wb")
while 1:
s = fp.read()
if not s:
break
op.write(s)
fp.close()
op.close()
return 1
#downURL('http://www.sohu.com','http.log')
def getURL(url):
try:
fp = urllib2.urlopen(url)
except:
print 'get url exception'
return 0
pattern = re.compile("http://sports.sina.com.cn/[^\>]+.shtml")
while 1:
s = fp.read()
if not s:
break
urls = pattern.findall(s)
fp.close()
return urls
def spider(startURL,times):
urls = []
urls.append(startURL)
i = 0
while 1:
if i > times:
break;
if len(urls)>0:
url = urls.pop(0)
print url,len(urls)
downURL(url,str(i)+'.htm')
i = i + 1
if len(urls)<times:
urllist = getURL(url)
for url in urllist:
if urls.count(url) == 0:
urls.append(url)
else:
break
return 1
spider('http://www.baidu.com',10)
http://www.baidu.com 0
http://www.baidu.com
0.htm
download exception
get url exception
Traceback (most recent call last):
File "D:/test/papa.py", line 62, in <module>
spider('http://www.baidu.com',10)
File "D:/test/papa.py", line 56, in spider
for url in urllist:
TypeError: 'int' object is not iterable
print 'get url exception'
return 0
print 'get url exception'
return []
downURL(url,str(i)+'.htm')