A small command-line script to remove version strings from filenames and filename references in directories. Useful for parsing wget scrapes.

versionStringRemover.py

import os, re, sys
print ("Asset Renamer v1 ::::::::::::::")
def replaceVersionsInFile(file):
	#This regex matches all href and src attributes and finds version strings that either use question marks of the unicode string %3
	pattern = "(?:href=[\"\']?([^\"\'>]+)[\"\']?|src=[\"\']?([^\"\'>]+)[\"\']?)([\']?(?=.*%3?)[^\"\']*)|(.*(?=.*\?)[^\"\']*)"
	fo = open(file, 'r+');
	text = fo.readlines()
	fo.seek(0)
	fo.truncate()
	for line in text:
		search = re.search(pattern, line)
		if search:
			versionString = search.group(3)
			if versionString:
				print("Old line: " + line)
				line = line.replace(str(versionString), '')
				print("New Line: " + line)
		fo.write(line)
	fo.close()


if len(sys.argv) > 1:
	scrptPath = os.path.join(os.path.dirname(os.path.realpath(__file__ + '/../')), sys.argv[1])
	print (scrptPath)
else:
	scrptPath = os.path.dirname(os.path.realpath(__file__))

# Loops through all directories and files in the script path, modifying html files and renaming any files that match the regex.
for root, dirs, files in os.walk(scrptPath):
	for filename in files:
		if filename.endswith('.html'):
			replaceVersionsInFile(os.path.join(root,filename))
		if "?" in filename:
			m = re.search("(.*(?=.*%3))|(.*(?=.*\?))", filename)
			
			os.rename(os.path.join(root,filename), os.path.join(root,m.group(0)))

print ("Asset Renamer v1 DONE ::::::::::::")

Usage

Download and place in the root directory of your scrape. Open a terminal at that location and run python versionStringRemover.py. Any replaced lines found in HTML files will be listed as "Old Line:", "New Line:".