网络数据
import urllib.request
r=urllib.request.urlopen("http://www.njcie.com")
page=r.read()
page=page.decode('UTF-8-sig')
print(page)



抓取并剥离其中的论文链接
import urllib.request
import re

r = urllib.request.urlopen("http://www.njcie.com")
page = r.read()
page=page.decode('utf-8')

results = re.findall("href=\"papers/.+\"", page)

for result in results:
    result=result.replace("href=\"papers/","http://www.njcie.com/papers/")
    result=result.rstrip("\"")
    print(result)