Created
May 19, 2016 11:58
-
-
Save NoxMortem/8525e8413c70d08565a41bfd79e12323 to your computer and use it in GitHub Desktop.
A tiny python script which parses an input file in the same folder for strings between "" or '' and searches for a prefix. Example usage: python parse.py "html.html" "attr_"
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import sys | |
import re | |
import os | |
inputfile = sys.argv[1] | |
prefix = sys.argv[2] | |
print("Extract:"+prefix); | |
def lreplace(pattern, sub, string): | |
""" | |
Replaces 'pattern' in 'string' with 'sub' if 'pattern' starts 'string'. | |
""" | |
return re.sub('^%s' % pattern, sub, string) | |
def parseLine(line): | |
output = "" | |
parts = line.split('\"')+line.split("\'") | |
return [part for part in parts if part.startswith(prefix)] | |
files = [f for f in os.listdir('.') if os.path.isfile(f)] | |
for f in files: | |
if f.startswith(inputfile): | |
infile = f | |
outfile = "output.txt" | |
try: | |
with open(infile, encoding='utf8') as input, open(outfile,"w", encoding='utf8') as outf: | |
lines = [parseLine(line) for line in list(input) if prefix in line] | |
d = {} | |
for line in lines: | |
for attr in line: | |
d[value] = attr+"\n" | |
for key, value in sorted(d.items()): # Note the () after items! | |
outf.write(key); | |
except UnicodeDecodeError: | |
with open(infile) as input, open(outfile,"w", encoding='utf8') as outf: | |
lines = [parseLine(line) for line in list(input) if prefix in line] | |
d = {} | |
for line in lines: | |
for attr in line: | |
d[attr] = attr+"\n" | |
for key, value in sorted(d.items()): # Note the () after items! | |
outf.write(value); | |
print("Done.") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment