Python使用urllib2模块抓取HTML页面资源的实例分享
先把要抓取的网络地址列在单独的list文件中
https://www.nhooo.com/article/83440.html https://www.nhooo.com/article/83437.html https://www.nhooo.com/article/83430.html https://www.nhooo.com/article/83449.html
然后我们来看程序操作，代码如下：
#!/usr/bin/python
importos
importsys
importurllib2
importre
defCdown_data(fileurl,fpath,dpath):
ifnotos.path.exists(dpath):
os.makedirs(dpath)
try:
getfile=urllib2.urlopen(fileurl)
data=getfile.read()
f=open(fpath,'w')
f.write(data)
f.close()
except:
print
withopen('u1.list')aslines:
forlineinlines:
URI=line.strip()
if'?'and'%'inURI:
continue
elifURI.count('/')==2:
continue
elifURI.count('/')>2:
#printURI,URI.count('/')
try:
dirpath=URI.rpartition('/')[0].split('//')[1]
#filepath=URI.split('//')[1].split('/')[1]
filepath=URI.split('//')[1]
iffilepath:
printURI,filepath,dirpath
Cdown_data(URI,filepath,dirpath)
except:
printURI,'error'