py提取文本内容的问题

[blackhat591]

test.txt内容如下：
uid=freeway,ou=People,dc=com
bsn-number=60257685
contentfilterconfigurable=N
brcfilequotatotkb=0
s-webconf=N
fsa-admin-status=N
rm-plan=S
s-contentfilter=N
s-priorityrouting=N
s-br=N
s-hsdpa=N
priorityroutingconfigurable=N
gidNumber=6009
gecos=FREEWAY SHIPPING LIMITED
sn=FREEWAY SHIPPING LIMITED
givenName=FREEWAY SHIPPING LIMITED
cn=FREEWAY SHIPPING LIMITED
netpasshs=e40797da998d1723
userPassword={crypt}9K35ik9Jdj2555
status=A
suspend-reason=T
suspendsince=20091229024501Z
lastpasswdmodifytimestamp=20090502072406Z
lastpasswdmodifymechanism=C
membershipid=1603029
uid=freeway
objectClass=top
objectClass=person
objectClass=organizationalPerson
objectClass=inetOrgPerson
objectClass=ShadowAccount
uidNumber=124850
s-bu=B
s-emailallm=N

uid=freeway2,ou=People,dc=com
bsn-number=60257685
fsanumber=13603824
contentfilterconfigurable=N
brcfilequotatotkb=0
s-webconf=N
fsa-admin-status=N
rm-plan=S
s-contentfilter=N
s-priorityrouting=N
s-br=N
s-hsdpa=N
priorityroutingconfigurable=N
gidNumber=6009
gecos=FREEWAY SHIPPING LIMITED
sn=FREEWAY SHIPPING LIMITED
givenName=FREEWAY SHIPPING LIMITED
cn=FREEWAY SHIPPING LIMITED
netpasshs=e40797da998d1723
userPassword={crypt}9Klw666w5ik9Jdj2
activesince=20100226110216Z
status=A
suspend-reason=T
suspendsince=20091229024501Z
lastpasswdmodifytimestamp=20090502072406Z
lastpasswdmodifymechanism=Cs
uid=freeway2
objectClass=top
objectClass=person
objectClass=organizationalPerson
objectClass=inetOrgPerson
objectClass=pccwinternetuser
s-bu=B
s-emailallm=N

//这样的段很多，空行为不同的段
提取uid和userPassword的内容，输出到txt，格式 uid:userpassword
如 freeway:9K35ik9Jdj2555

这里要注意每个uid对应一个password，空行的没一段中有2个重复的uid，判断一下。

[JoeBlackzqq]

# coding=UTF8

import re

def readFile(fname, result):
	f = open(fname, "r")
	if not f:
		return False
	lines = f.readlines()
	f.close()
	
	i = 0
	cnt = len(lines)
	pat = ['uid=(\w+),', 'userPassword=\{crypt\}(\w+)']
	while  i < cnt:
		line = lines[i].strip(" \t\n")
		i += 1
		uid = None
		m = re.findall(pat[0], line)
		if len(m) > 0:
			uid = m[0]
		while uid:
			line = lines[i].strip(" \t\n")
			i += 1
			m = re.findall(pat[1], line)
			if len(m) > 0:
				pwd = m[0]
				result.append((uid, pwd))
				uid = None
				break
	return True

def printArray(arr, fout):
	f = open(fout, "w")
	if not f:
		return False

	for item in arr:
		#print "%s:%s" %(item[0], item[1])
		f.write("%s:%s\n" %(item[0], item[1]))
	f.close()
	return True
	
if __name__ == '__main__':
	fname = "test.txt"
	fout = "result.log"
	result = []
	if readFile(fname, result):
		printArray(result, fout)

[panghuhu250]

你的代码？问题？

[blackhat591]

不错啊！ 这样会不会更简单：

import re
for line in open('D:/t00ls/PyScripter/1.txt'):
    match_uid=re.search(r'(?<=^uid=)\w+(?=,)',line)
    if match_uid:
        uid=match_uid.group(0)
    match_password=re.search(r'(?<=^userPassword={crypt}).*',line)
    if match_password:
        cmd='%s:%s\n'%(uid,match_password.group(0))
        #f=open('D:/t00ls/PyScripter/f.txt','a')
        #f.write(cmd)
        #f.close()
        print cmd

引用 1 楼 JoeBlackzqq 的回复:

# coding=UTF8

import re

def readFile(fname, result):
	f = open(fname, "r")
	if not f:
		return False
	lines = f.readlines()
	f.close()
	
	i = 0
	cnt = len(lines)
	pat = ['uid=(\w+),', 'userPassword=\{crypt\}(\w+)']
	while  i < cnt:
		line = lines[i].strip(" \t\n")
		i += 1
		uid = None
		m = re.findall(pat[0], line)
		if len(m) > 0:
			uid = m[0]
		while uid:
			line = lines[i].strip(" \t\n")
			i += 1
			m = re.findall(pat[1], line)
			if len(m) > 0:
				pwd = m[0]
				result.append((uid, pwd))
				uid = None
				break
	return True

def printArray(arr, fout):
	f = open(fout, "w")
	if not f:
		return False

	for item in arr:
		#print "%s:%s" %(item[0], item[1])
		f.write("%s:%s\n" %(item[0], item[1]))
	f.close()
	return True
	
if __name__ == '__main__':
	fname = "test.txt"
	fout = "result.log"
	result = []
	if readFile(fname, result):
		printArray(result, fout)

[JoeBlackzqq]

引用 3 楼 blackhat591 的回复:

不错啊！ 这样会不会更简单：

import re
for line in open('D:/t00ls/PyScripter/1.txt'):
    match_uid=re.search(r'(?<=^uid=)\w+(?=,)',line)
    if match_uid:
        uid=match_uid.group(0)
    match_password=re.search(r'(?<=^userPassword={crypt}).*',line)
    if match_password:
        cmd='%s:%s\n'%(uid,match_password.group(0))
        #f=open('D:/t00ls/PyScripter/f.txt','a')
        #f.write(cmd)
        #f.close()
        print cmd

[quote=引用 1 楼 JoeBlackzqq 的回复:]

# coding=UTF8

import re

def readFile(fname, result):
	f = open(fname, "r")
	if not f:
		return False
	lines = f.readlines()
	f.close()
	
	i = 0
	cnt = len(lines)
	pat = ['uid=(\w+),', 'userPassword=\{crypt\}(\w+)']
	while  i < cnt:
		line = lines[i].strip(" \t\n")
		i += 1
		uid = None
		m = re.findall(pat[0], line)
		if len(m) > 0:
			uid = m[0]
		while uid:
			line = lines[i].strip(" \t\n")
			i += 1
			m = re.findall(pat[1], line)
			if len(m) > 0:
				pwd = m[0]
				result.append((uid, pwd))
				uid = None
				break
	return True

def printArray(arr, fout):
	f = open(fout, "w")
	if not f:
		return False

	for item in arr:
		#print "%s:%s" %(item[0], item[1])
		f.write("%s:%s\n" %(item[0], item[1]))
	f.close()
	return True
	
if __name__ == '__main__':
	fname = "test.txt"
	fout = "result.log"
	result = []
	if readFile(fname, result):
		printArray(result, fout)

[/quote] 只要正确就行，你的代码挺短的，不错！