get_file_list.py

def get_file_list(dir=options.source_dir):
    """ Returns list of all html files in specified directory (recursive) """
    fileList = []

    print dir
    try:
        for root, subFolders, files in os.walk(dir):
            for file in files:
                filepath = os.path.join(root,file)
                if ".html" in filepath:
                    fileList.append(filepath)
        print fileList
        return fileList
    except OSError as e:
        print e.errno
        print e.filename
        print e.strerror