python小爬虫

tool.py

from urllib import urlencode
import cookielib, urllib2, urllib, re, os

_loginweb = "http://0.0.0.0:8080/"
_userinfo = {	'os_username': "wangkangan",
		'os_password': "***",
		'os_cookie':'true'}
		
def issue(opener, issue):
	op = opener.open(_loginweb + "browse/" + issue + "?page=com.atlassian.jira.plugin.ext.subversion:subversion-commits-tabpanel")
	text = op.read()
	reg = re.compile('<td bgcolor="#ffffff" width="10%" valign="top" rowspan="3">[a-z]+[0-9]*</td>')
	result = {}
	authors = reg.findall(text)
	for v in authors:
		v = v.replace('<td bgcolor="#ffffff" width="10%" valign="top" rowspan="3">', "")
		v = v.replace('</td>', "")
		if not result.has_key(v):
			result[v] = v
	return result
	
cj = cookielib.CookieJar()
opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cj))
opener.addheaders=[('User-agent','Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)')]
data = urllib.urlencode(_userinfo)
opener.open(_loginweb + "login.jsp", data)

if os.path.exists('result.txt'):
	os.remove("result.txt")
wfile = open("result.txt", 'w')
rfile = open("input.txt", 'r')
line = rfile.readline()
while line:
	line = line.replace(" ", "")
	line = line.replace("\t", "")
	line = line.replace("\r", "")
	line = line.replace("\n", "")
	result = issue(opener, line)
	authors = ""
	for v in result:
		authors = authors + v + ","
	wfile.write(line + ":" + authors + "\r\n")
	line = rfile.readline()
rfile.close()
wfile.close()
print("****** Everything is OK! ******")