download experiences audio about jw-scripts HOT 3 CLOSED

#!/usr/bin/env python3
# Run the program with an jw.org URL as an argument to
# download all recordings that are referenced to in that page
import sys, re, urllib.request, json

lang = 'E'
api_url = 'https://apps.jw.org/GETPUBMEDIALINKS?output=json&alllangs=0&fileformat=MP3&langwritten=' + lang + '&txtCMSLang=' + lang + '&docid='
data = urllib.request.urlopen(sys.argv[1]).read().decode('utf-8')
matches = re.finditer('data-page-id="mid([^"]*)"', data)
ids = set(x.group(1) for x in matches)  # set() removes all doubles

for i in ids:
    try:
        print('requesting data about', i)
        response = urllib.request.urlopen(api_url + i)
    except:
        continue

    tree = json.loads(response.read().decode('utf-8'))
    file_url = tree['files'][lang]['MP3'][0]['file']['url']  # Assuming there's only one MP3
    file_title = tree['files'][lang]['MP3'][0]['title']
    file_name = re.sub('[<>:"|?*/\0]', '', file_title) + '.mp3'  # NTFS safe
    print('downloading', file_title)
    urllib.request.urlretrieve(file_url, filename=file_name)