import re, urllib
htmlSource = urllib.urlopen("http://www.sharejs.com").read(200000)
linksList = re.findall('<a href=(.*?)>.*?</a>',htmlSource)
for link in linksList:
print link
原创文章,作者:ItWorker,如若转载,请注明出处:https://blog.ytso.com/tech/pnotes/8027.html