Script to sort files from a moodle backup into a new directory.

extract_moodle_files.py

#!/usr/bin/env python3
"""
Moodle provides a backup system for courses offering an mbz file. This is a zip file with
all the resources and files included and the needed metadata about the files encoded in XML.

This script gets an unzipped mbz directory and copies all the files from the course into 
a directory tree with the same layout than the original moodle course.

unzip my_moodle_backup.zip
extract_moodle_files.py --source my_moodle_backup_FILES --destination sorted_course 

"""
# ChangeLog:
#
#  [2015-10-16] Sergio Oller
#  - Ported to python-3.4
#  - Added command line arguments
#
#  [2012-11-29] Jon Reades
#  - Script hosted at: http://www.reades.com/2012/11/29/mb-archives/
#

import xml.etree.ElementTree as etree
import fnmatch
import shutil
import os
import re

import argparse

def parse_arguments():
    parser = argparse.ArgumentParser(description='Sort files from moodle backup.',
                                     usage='extract_moodle_files.py --source my_moodle_backup_FILES --destination sorted_course')
    parser.add_argument('--source', dest='source', type=str,
                        help='path to extracted backup files')
    parser.add_argument('--destination', dest='destination', type=str,
                        help='path to destination directory')
    args = parser.parse_args()
    if args.source is None:
        raise ValueError("Path to extracted backup files not given. Use --source /path/to/extracted_mbz_FILES/")
    if args.destination is None:
        raise ValueError("Path to destination files not given. Use --destination /path/to/a/directory")
    return args

def locate(pattern, root=os.curdir):
    '''Locate all files matching supplied filename pattern in and below
    supplied root directory.'''
    for path, dirs, files in os.walk(os.path.abspath(root)):
        for filename in fnmatch.filter(files, pattern):
            yield os.path.join(path, filename)


def main(destination, source, pattern):
    tree = etree.parse(source + 'files.xml')
    root = tree.getroot()
    os.makedirs(destination, exist_ok=True)
    print("Root: ", root)

    print(destination)

    for rsrc in root:
        # print "Child id: ", rsrc.attrib
        fhash = rsrc.find('contenthash').text
        filepath = rsrc.find('filepath').text
        if filepath.startswith("/"):
             filepath = filepath[1:]
        fname = rsrc.find('filename').text
        os.makedirs(os.path.join(destination, filepath), exist_ok=True)
        # If file name is just a directory, skip it:
        if fname == ".":
            continue
        if pattern is not None:
            hit = pattern.search(fname)
        else:
            hit = True

        if hit:
            # print "\tMatch: ", hit.group(1)
            files = locate(fhash, source)
            # print "\tFiles: ", files
            for x in files:
                print("Copying: ", x)
                shutil.copyfile(x, os.path.join(destination, filepath, fname))
        else:
            print("File excluded by pattern: '", fname, "'", sep="")

if __name__ == "__main__":
    args = parse_arguments()
    #pattern = re.compile('^\s*(.+\.(?:pdf|png|zip|rtf|sav|mp3|mht|por|xlsx?|docx?|pptx?))\s*$', flags=re.IGNORECASE)
    pattern = None
    main(args.destination, args.source, pattern)