Extracting IP addresses from a file

Question

I'm trying to extract IP addresses from an asp file in Python, the file looks something like this:

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") ||

How I'm attempting to extract them is with a regex:

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

However I'm getting an error:

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'

I don't understand why I'm getting that error, what can I do to this code to make it extract the information like I want it to?

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)

EDIT

Realized I hadn't opened the file:

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)

Still getting the same error:

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 was expecting an appropriate flags parameter (an integer) of which line (a string) is not.

You should be doing re.match not re.compile :

re.compile

Compile a regular expression pattern into a regular expression object, which can be used for matching using its match() and search() methods...

Answer 2

Your initial error

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

is caused by exactly what @Moses said in his answer. flags are supposed to be int values, not strings.

---

You should compile your regex once. Also, you need to use an open file handle when you iterate over the lines.

import re

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)

This will find all matches, if you only want the first, then use IP_MATCHER.search and match.groups() . This is of course assuming you actually want to extract the IP addresses.

For instance:

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

Please check the below code:

Did couple of changes

1. re.compile - Regex should be complied first and then can be used with 'match/search/findall'.
2. Regex was not proper. While writing regex we need to consider from the start of line. Regex didn't match words in between line directly.

 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)

Output:

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