extract_3sat_mp4.py

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

import sys
import requests
from lxml import etree
from fake_useragent import UserAgent

ua = UserAgent()


def request_content(url, ua_string):
    headers = {'User-Agent': ua_string, 'Origin': 'http://www.3sat.de'}
    response = requests.get(url, headers=headers)

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


def load_document(filename):
    with open(filename, 'r') as f:
        return f.read()


def extract_video(node):
    try:
        return node.xpath('//formitaet/quality[text()="veryhigh"]/following-sibling::url[1]/text()')[3]
    except IndexError as e:
        return


def extract_title(node):
    try:
        return node.xpath('//information/title/text()')[0]
    except IndexError as e:
        return


def extract_channel(node):
    try:
        return node.xpath('//originChannelTitle/text()')[0]
    except IndexError as e:
        return


def main():
    if len(sys.argv) > 1:
        drei_sat_url = sys.argv[1]
    else:
        print 'Enter the 3SAT url you want to download the mp4!'
        sys.exit(1)

    content = request_content(drei_sat_url, ua.chrome)

    try:
        node = etree.fromstring(content.encode('utf-8'), parser=etree.XMLParser(encoding='utf-8'))
    except UnicodeEncodeError as e:
        sys.exit(1)

    channel = extract_channel(node)
    title = extract_title(node)
    video = extract_video(node)

    if video and channel and title:
        print u'{}_{}.mp4'.format(channel.lower(), title.replace(' ', '_').replace('.', '').replace(':', '').replace('-', '').replace('?', '').replace('!', '').replace(',', '').replace('__', '_').replace('"', '').replace('/', '_').lower())
        print u'{}\n'.format(video)


if __name__ == '__main__':
    main()