Download new episodes based on keywords from SVT play

svtplay_subscribe.py

import os
import svtplay_dl
import re
import feedparser

__author__ = 'oakninja'


def lines(file_name):
    home = os.path.expanduser("~")
    path = home + '/' + file_name
    if not os.path.isfile(path):
        open(path, 'w').close()
    with open(path) as f:
        content = f.readlines()
        f.close()
    return content


def search(keywords, text):
    for keyword in keywords:
        if keyword.strip(' \t\n\r') in text:
            # print 'keyword =' + keyword.strip(' \t\n\r') + ' text =' + text
            return True
    return False


def is_new(downloaded, link):
    pattern = re.compile('http://www.svtplay.se/video/([0-9]+)/.+')
    id = pattern.search(link)
    if id and search(downloaded, id.group(1)):
        return False
    else:
        return True


def find_new_downloads(feed, keywords, downloaded):
    new_downloads = []
    for entry in feed.entries:
        if search(keywords, entry.title) and is_new(downloaded, entry.link):
            new_downloads.append(entry)
    return new_downloads


def download_new_streams(new_downloads):
    pattern = re.compile('http://www.svtplay.se/video/([0-9]+)/.+')
    downloaded = []
    home = os.path.expanduser("~")
    options = svtplay_dl.Options()
    options.subtitle = True
    options.get_url = False
    for item in new_downloads:
        options.output = home + '/Movies/svtplay_subscribe/' + item.title + '.mp4'
        print(item)
        svtplay_dl.get_media(item.link, options)
        video_number = pattern.search(item.link)
        if video_number:
            downloaded.append(video_number.group(1))
    f = open(home + '/' + 'svt_new_downloaded', 'a+')
    for item in downloaded:
        print>>f, item
        print('Downloaded ' + item)
    f.close()


def svtplay_subscribe():
    downloaded = lines('svt_new_downloaded')
    # new_downloads = lines('new_downloads')
    keywords = lines('svt_keywords')
    print('Looking for ...')
    print(keywords)
    feed = feedparser.parse('http://www.svtplay.se/daniel-tigers-kvarter/rss.xml')

    new_downloads = find_new_downloads(feed, keywords, downloaded)
    print(new_downloads)

    download_new_streams(new_downloads)


svtplay_subscribe()

Download episodes from SVT play based on keywords defined in /usr/keywords. Only downloads new videos. Dependent on svtplay_dl