extract_wdr_m3u8.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-

import sys
import json
import requests
from lxml import html
from urlparse import urlparse
from fake_useragent import UserAgent

ua = UserAgent()


def make_title(title):
    return title.replace('//', '').replace(' ', '_').replace(u'–', '').replace('?', '').replace('!', '').replace('-', '').replace('__', '_').replace(':', '').replace(',', '').lower()


def find_js_url(text):
    document = html.document_fromstring(text)
    target_url = document.xpath('//a/@data-extension')
    json_obj = json.loads(target_url[0])
    return json_obj['mediaObj']['url']


def request_content(url, origin, ua_string):
    headers = {'User-Agent': ua_string, 'Origin': origin}
    response = requests.get(url, headers=headers)

    if response.status_code == 200:
        return response.text


def main():
    if len(sys.argv) > 1:
        wdr_url = sys.argv[1]
    else:
        print 'Enter the wdr.de url you want to download the m3u8 source!'
        sys.exit(1)

    useragent = ua.chrome
    html_document = request_content(wdr_url, 'https://www1.wdr.de', useragent)
    js_url = find_js_url(html_document)
    media_url = request_content(js_url, sys.argv[1], useragent)
    json_obj = json.loads(media_url.replace('$mediaObject.jsonpHelper.storeAndPlay(', '').replace(');', ''))
    url = json_obj['mediaResource']['dflt']['videoURL'].replace('//', '')
    title = u'{}.m3u8'.format(json_obj['trackerData']['trackerClipTitle'])

    print make_title(title).replace('_.', '.')
    print url



if __name__ == '__main__':
    main()