从文件中提取IP地址

Question

我正在尝试从Python中的asp文件提取IP地址，该文件看起来像这样：

onInternalNet = (
        isInNet(hostDNS, "147.163.1.0", "255.255.0.0") ||
        isInNet(hostDNS, "123.264.0.0", "255.255.0.0") ||
        isInNet(hostDNS, "137.5.0.0", "255.0.0.0") ||
        isInNet(hostDNS, "100.01.02.0", "255.0.0.0") ||
        isInNet(hostDNS, "172.146.30.0", "255.240.0.0") ||
        isInNet(hostDNS, "112.268.0.0", "255.255.0.0") ||

我试图提取它们的方法是使用正则表达式：

if re.compile(r"^\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}$", line):

但是我遇到一个错误：

Traceback (most recent call last):
  File "pull_proxy.py", line 27, in <module>
    write_to_file(extract_proxies(in_file), out_file)
  File "pull_proxy.py", line 8, in extract_proxies
    if re.compile(r"^\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}$", line):
  File "C:\Python27\lib\re.py", line 194, in compile
    return _compile(pattern, flags)
  File "C:\Python27\lib\re.py", line 233, in _compile
    bypass_cache = flags & DEBUG
TypeError: unsupported operand type(s) for &: 'str' and 'int'

我不明白为什么会收到该错误，该如何处理该代码以使其像我希望的那样提取信息？

import re

def extract_proxies(in_file):
    buffer = []

    for line in in_file:
        if re.compile(r"^\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}$", line):
            print "{} appened to buffer.".format(line)
            buffer.append(line)
        else:
            pass

    return buffer

def write_to_file(buffer, out_file):
    for proxy in buffer:
        with open(out_file, "a+") as res:
            res.write(proxy)

if __name__ == '__main__':
    print "Running...."
    in_file = "C:/Users/thomas_j_perkins/Downloads/test.asp"
    out_file = "c:/users/thomas_j_perkins/Downloads/results.txt"
    write_to_file(extract_proxies(in_file), out_file)

编辑

意识到我没有打开文件：

import re

def extract_proxies(in_file):
    buffer = []

    for line in in_file:
        if re.compile(r"^\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}$", line):
            print "{} appened to buffer.".format(line)
            buffer.append(line)
        else:
            pass

    in_file.close()
    return buffer

def write_to_file(buffer, out_file):
    for proxy in buffer:
        with open(out_file, "a+") as res:
            res.write(proxy)

if __name__ == '__main__':
    print "Running...."
    in_file = "C:/Users/thomas_j_perkins/Downloads/PAC-Global-Vista.asp"
    out_file = "c:/users/thomas_j_perkins/Downloads/results.txt"
    write_to_file(extract_proxies(open(in_file, "r+")), out_file)

仍然出现相同的错误：

Running....
Traceback (most recent call last):
  File "pull_proxy.py", line 28, in <module>
    write_to_file(extract_proxies(open(in_file)), out_file)
  File "pull_proxy.py", line 8, in extract_proxies
    if re.compile(r"^\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}$", line):
  File "C:\Python27\lib\re.py", line 194, in compile
    return _compile(pattern, flags)
  File "C:\Python27\lib\re.py", line 233, in _compile
    bypass_cache = flags & DEBUG
TypeError: unsupported operand type(s) for &: 'str' and 'int'

Answer 1

re.compile期望没有line （字符串）的适当的flags参数（整数）。

你应该做re.match而不是re.compile ：

re.compile

将正则表达式模式编译为正则表达式对象，可使用其match()和search()方法进行匹配...

Answer 2

您的最初错误

TypeError: unsupported operand type(s) for &: 'str' and 'int'

正是@Moses在他的回答中所说的。 标志应该是int值，而不是字符串。

---

您应该编译一次正则表达式。 同样，遍历行时需要使用打开的文件句柄。

汇入

IP_MATCHER = re.compile(r"(\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3})")

def extract_proxies(fh):
    for line in fh:
        line = line.strip()
        match = IP_MATCHER.findall(line)
        if match:
            print "{} appened to buffer.".format(line)
            print match
        else:
            pass



def write_to_file(buffer, out_file):
    for proxy in buffer:
        with open(out_file, "a+") as res:
            res.write(proxy)


if __name__ == '__main__':
    print "Running...."
    in_file = "in.txt"
    with open(in_file) as fh:
        extract_proxies(fh)

如果只想要第一个，它将找到所有匹配项，然后使用IP_MATCHER.search和match.groups() 。 当然，这是假设您实际上要提取IP地址。

例如：

def extract_proxies(fh):
    for line in fh:
        line = line.strip()
        match = IP_MATCHER.findall(line)
        if len(match) == 2:
            print "{} appened to buffer.".format(line)
            ip, mask = match
            print "IP: %s => Mask: %s" % (ip, mask)
        else:
            pass

Answer 3

请检查以下代码：

做过几次改动

1. re.compile-首先应编译正则表达式，然后才能与“ match / search / findall”一起使用。
2. 正则表达式不正确。 在编写正则表达式时，我们需要从一开始就考虑。 正则表达式没有直接匹配行之间的单词。

 import re


    def extract_proxies(in_file):
        buffer1 = []
        #Regex compiled here
        m = re.compile(r'\s*\w+\(\w+,\s+\"(\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3})\"')

        for line in in_file:
            #Used here to match
            r = m.match(line)
            if r is not None:
                print "{} appened to buffer.".format(line)
                buffer1.append(r.group(1))
            else:
                pass

        in_file.close()
        return buffer1


    def write_to_file(buffer1, out_file):
        for proxy in buffer1:
            with open(out_file, "a+") as res:
                res.write(proxy+'\n')


    if __name__ == '__main__':
        print "Running...."
        in_file = "sample.txt"
        out_file = "results.txt"
        write_to_file(extract_proxies(open(in_file)), out_file)

输出：

C:\Users\dinesh_pundkar\Desktop>python c.py
Running....
        isInNet(hostDNS, "147.163.1.0", "255.255.0.0") ||
 appened to buffer.
        isInNet(hostDNS, "123.264.0.0", "255.255.0.0") ||
 appened to buffer.
        isInNet(hostDNS, "137.5.0.0", "255.0.0.0") ||
 appened to buffer.
        isInNet(hostDNS, "100.01.02.0", "255.0.0.0") ||
 appened to buffer.
        isInNet(hostDNS, "172.146.30.0", "255.240.0.0") ||
 appened to buffer.
        isInNet(hostDNS, "112.268.0.0", "255.255.0.0") || appened to buffer.

C:\Users\dinesh_pundkar\Desktop>python c.py