first commit

.gitignore

@@ -0,0 +1,2 @@
+.vscode
+mediathek.code-workspace

Dockerfile

@@ -0,0 +1,16 @@
+FROM python:3-alpine
+
+WORKDIR /app
+
+COPY requirements.txt ./
+RUN apk update && apk add mkvtoolnix && apk add --no-cache tzdata
+RUN pip install --no-cache-dir -r requirements.txt
+ENV TZ Europe/Berlin
+
+COPY main.py ./
+
+RUN crontab -l | { cat; echo "15      03      *       *       *       cd /app && python -u /app/main.py"; } | crontab -
+
+VOLUME ["/download"]
+
+CMD ["/usr/sbin/crond", "-f", "-l", "0"]

config.ini

@@ -0,0 +1,19 @@
+[DEFAULT]
+save_path = /download
+default_language = ger
+
+[Hubert und Staller]
+rss = https://mediathekviewweb.de/feed?query=%23Hubert%2Bund%2BStaller%20!ARD
+languages = ger
+ger =  ^(?P<titel>.*)\s+\(S(?P<season>\d+)/E(?P<episod>\d+)\)$
+
+[Hubert ohne Staller]
+rss = https://mediathekviewweb.de/feed?query=%23Hubert%2Bohne%2BStaller%20!ARD
+languages = ger
+ger = ^(?P<titel>.*)\s+\(S(?P<season>\d+)/E(?P<episod>\d+)\)$
+
+[Doctor Who]
+rss = https://mediathekviewweb.de/feed?query=%23Doctor%20!ARD
+languages = ger,eng
+ger = ^(?P<titel>.*)\s+\(S(?P<season>\d+)/E?(?P<episod>\d+|Weihnachtsspecial)\)$
+eng = ^(?P<titel>.*)\s+\(S(?P<season>\d+)/E?(?P<episod>\d+|Weihnachtsspecial)\).*Originalversion.*$

docker-compose.yaml

@@ -0,0 +1,10 @@
+version: '3'
+services:
+  app:
+    build: .
+    image: mediathekdownload:latest
+    volumes:
+      - "/home/smokephil/Videos:/download"
+      - "./config.ini:/app/config.ini"
+    environment:
+      - "TZ=Europe/Berlin"

main.py

@@ -0,0 +1,143 @@
+#! /usr/bin/env python
+# -*- coding: utf-8 -*-
+
+import logging
+import os
+import re
+import shutil
+import tempfile
+import urllib.request
+from configparser import ConfigParser
+from pprint import pp
+
+import feedparser
+import requests
+from pymkv import MKVFile, MKVTrack
+
+logging.basicConfig(format='%(levelname)s: %(message)s', level=logging.DEBUG)
+
+config = ConfigParser(interpolation=None)
+config.read('config.ini')
+
+
+def build_filename(name, titel_dict):
+    if titel_dict == []:
+        return None
+    if titel_dict[0]['episod'].isdigit():
+        filename = '{name} S{season:>02}E{episod:>02} {titel}'.format(
+            name=name, **titel_dict[0])
+    else:
+        filename = '{name} S{season:>02}.{episod} {titel}'.format(
+            name=name, **titel_dict[0])
+
+    return filename.strip().replace(' ', '.')
+
+
+def make_mkv(data):
+    series_name = data['series']
+    default_lang = config[series_name]['default_language']
+    lang_sort = config[series_name]['languages'].split(',')
+
+    def add_video(lang, path):
+        logging.debug('[MKV] add video (%s, %s)', lang, path)
+        video = MKVTrack(path, track_id=0, language=lang, default_track=True)
+        mkv.add_track(video)
+
+    def add_audio(lang, path):
+        logging.debug('[MKV] add audio (%s, %s)', lang, path)
+        audio = MKVTrack(path,
+                         track_id=1,
+                         language=lang,
+                         default_track=lang == default_lang)
+        mkv.add_track(audio)
+
+    mkv = MKVFile()
+    add_video(default_lang, data['lang'][default_lang])
+
+    for lang in lang_sort:
+        mp4_file = data['lang'].pop(lang, None)
+        if mp4_file is not None:
+            add_audio(lang, mp4_file)
+
+    mkv.mux(data['mkvpath'])
+
+
+def parse_feed(series_name):
+    d = feedparser.parse(config[series_name]['rss'])
+
+    episodes = dict()
+    for item in d['entries']:
+        title = item['title']
+        link = item['link']
+        for lang in config[series_name]['languages'].split(','):
+            pattern = config[series_name][lang]
+            groups = [x.groupdict() for x in re.finditer(pattern, title, re.M)]
+            if len(groups) == 1:
+                break
+
+        filename = build_filename(series_name, groups)
+        if filename is None:
+            logging.warning('skip %s', title)
+            continue
+        if filename not in episodes:
+            episodes[filename] = dict()
+            episodes[filename]['lang'] = dict()
+        episodes[filename]['lang'][lang] = link
+        season = '{season:>02}'.format(**groups[0])
+        episod = '{episod:>02}'.format(**groups[0])
+        basepath = os.path.join(config[series_name]['save_path'], series_name,
+                                f'Season {season:>02}')
+        mkvpath = os.path.join(basepath, filename + '.mkv')
+
+        episodes[filename]['season'] = season
+        episodes[filename]['episod'] = episod
+        episodes[filename]['series'] = series_name
+        episodes[filename]['basepath'] = basepath
+        episodes[filename]['mkvpath'] = mkvpath
+
+    return episodes
+
+
+def download_files(episodes):
+    for episod in sorted(episodes.keys()):
+        item = episodes[episod]
+        if os.path.exists(item['mkvpath']):
+            continue
+
+        basepath = item['basepath']
+        os.makedirs(basepath, exist_ok=True)
+        temp = tempfile.TemporaryDirectory(dir=basepath)
+
+        for lang in item['lang']:
+            link = item['lang'][lang]
+            filepath = os.path.join(temp.name, os.path.basename(link))
+
+            logging.info('start downloading...')
+            logging.debug('source: %s', link)
+            logging.debug('destination: %s', filepath)
+            try:
+                response = urllib.request.urlopen(link)
+                with requests.get(link, stream=True) as r:
+                    with open(filepath, 'wb') as f:
+                        shutil.copyfileobj(r.raw, f)
+
+                item['lang'][lang] = filepath
+            except:
+                logging.error("download")
+                pass
+
+        make_mkv(item)
+        temp.cleanup()
+
+
+def run():
+    logging.info('====== START ======')
+    for series_name in config.sections():
+        episodes = parse_feed(series_name)
+        download_files(episodes)
+
+    logging.info('====== END ======')
+
+
+if __name__ == "__main__":
+    run()

requirements.txt

@@ -0,0 +1,3 @@
+feedparser==5.2.1
+requests==2.24.0
+pymkv==1.0.5