python 20来行的代码,请大家帮忙加下注释。多谢
python 20来行的代码,请大家帮忙加下注释。谢谢
import urllib2
from sgmllib import SGMLParser
class URLLister(SGMLParser):
def reset(self):
SGMLParser.reset(self)
self.urls = []
def start_a(self, attrs):
href = [v for k, v in attrs if k=='href']
if href:
self.urls.extend(href)
f = urllib2.urlopen("http://www.ewebeditor.net/demo7")
if f.code == 200:
parser = URLLister()
parser.feed(f.read())
f.close()
for url in parser.urls: print url
------解决方案--------------------
import urllib2
from sgmllib import SGMLParser
class URLLister(SGMLParser):
def reset(self):
SGMLParser.reset(self)
self.urls = []
def start_a(self, attrs):
href = [v for k, v in attrs if k=='href']
if href:
self.urls.extend(href)
f = urllib2.urlopen("http://www.ewebeditor.net/demo7")
if f.code == 200:
parser = URLLister()
parser.feed(f.read())
f.close()
for url in parser.urls: print url
------解决方案--------------------