A Python script that searches recursively through a given directory and pulls technical metadata about the video codec and wrapper

video_analyzer.py

import os
import sys
import subprocess
import lxml.etree as ET
import pprint

rootdir = sys.argv[1]
accepted_file_types = ['mov', 'mp4', 'm4v', 'wmv']
files_list = []
formats_list = []


def dirwalker(rootdir, accepted_file_types, files_list):
	for root, dirs, files in os.walk(rootdir):
		for file_ in files:
				file_extension = file_.rpartition('.')[2]
				if file_extension in accepted_file_types: 
					path = ( os.path.join(root, file_) )
					files_list.append(path)
	generate_mediainfo(files_list)


def generate_mediainfo(files_list):
	for filepath in files_list:
		print(filepath)
		try:
			mediainfo_output = subprocess.check_output(['mediainfo', '--Output=XML', filepath])
		except FileNotFoundError as e:
			print(e)
		except Exception as e:
			print(e)
		else:
			asset_dict = {}
			root = ET.fromstring(mediainfo_output)
			for text in root.xpath('.//track[@type="General"]/Complete_name/text()'):
				asset_dict['Complete_name'] = text
			for text in root.xpath('.//track[@type="General"]/Format/text()'):
				asset_dict['Format'] = text
			for text in root.xpath('.//track[@type="General"]/Commercial_name/text()'):
				asset_dict['Commerical_name'] = text
			for text in root.xpath('.//track[@type="General"]/Format_profile/text()'):
				asset_dict['Format_profile'] = text
			for text in root.xpath('.//track[@type="General"]/Codec_ID/text()'):
				asset_dict['Codec_ID'] = text
			for text in root.xpath('.//track[@type="General"]/Overall_bit_rate_mode/text()'):
				asset_dict['Overall_bit_rate_mode'] = text
			for text in root.xpath('.//track[@type="General"]/Writing_library/text()'):
				asset_dict['Writing_library'] = text
			# pp = pprint.PrettyPrinter(indent=4)
			# pp.pprint(asset_dict)
			formats_list.append(asset_dict)		
		# finally:
			
			
			# print(formats_list)


dirwalker(rootdir, accepted_file_types, files_list)
pp = pprint.PrettyPrinter(indent=4)
pp.pprint(formats_list)