Cannot find substring from input file in python 3

Question

I am trying to find format from input file. But sometimes I get no match if I use 'r' and sometimes unicode error.

def extract_files(filename):
    file = open(filename, 'r')
    text = file.read()
    files_match = re.findall('<Compile Include="src\asf\preprocessor\string.h">', text)
    if not files_match:
        sys.stderr.write('no match')
        sys.exit()
    for f in files_match:
        print(f)

Answer 1

Looks like you're trying to pull all the strings after <Compile Include=" and until ">. We can do that, but be aware this will probably break on edge cases!

import re

def extract_files(filename):
    with open(filename,'r') as file:
        text = file.read
    matches = re.findall(r'(?<=<Compile Include=")[-.A-Za-z\\]+(?=")', text)
    # finds all pathnames that contain ONLY lowercase or uppercase letters,
    # a dash (-) or a dot (.), separated ONLY by a backslash (\)
    # terminates as soon as it finds a double-quote ("), NOT WHEN IT FINDS A
    # SINGLE QUOTE (')
    if not matches:
        sys.stderr.write("no match")
        sys.exit()
    for match in matches:
        print(match)