\n \n \n \n
\n \n [\"title\"=>$title,\"image\"=>$image,\"episodes\"=>$episodes,\"last\"=>$last,\"max\"=>$max,\"keep\"=>$keep,\"feed\"=>$feed]): ?>\n \n \n
\n \n
\n \n \n
\n \n \n \n
\n \n \n\n'''\n\n"
},
{
"path": "spodcast/podcast.py",
"content": "import json\nimport logging\nimport os\nimport time\nfrom datetime import datetime\nfrom html import escape\nimport urllib.parse\n\nimport base62\nfrom base62 import CHARSET_INVERTED\nimport ffmpeg\n\nfrom librespot import util\nfrom librespot.metadata import ShowId, EpisodeId\nfrom librespot.core import ApiClient\n\nfrom spodcast.const import FILE_EXISTS, IMAGE_CDN\nfrom spodcast.feedgenerator import RSS_FEED_CODE, RSS_FEED_FILE_NAME, RSS_FEED_SHOW_INDEX, RSS_FEED_INFO_EXTENSION, RSS_FEED_SHOW_IMAGE, RSS_FEED_VERSION, get_index_version\nfrom spodcast.utils import clean_filename, uri_to_url\nfrom spodcast.spodcast import Spodcast\n\nlog = logging.getLogger(__name__)\n\n\ndef hex_to_spotify_id(hex_id):\n return base62.encodebytes(util.hex_to_bytes(hex_id), CHARSET_INVERTED)\n\n\ndef get_show_info(show_id_hex):\n log.info(\"Fetching show information...\")\n show_id = ShowId.from_hex(show_id_hex)\n uri = f'spotify:show:{hex_to_spotify_id(show_id_hex)}'\n info = Spodcast.SESSION.api().get_metadata_4_show(show_id)\n link = uri_to_url(uri)\n description = info.description\n image = IMAGE_CDN(util.bytes_to_hex(info.cover_image.image[1].file_id))\n\n return link, description, image\n\n\ndef get_episode_info(episode_id_hex):\n log.info(\"Fetching episode information...\")\n episode_id = EpisodeId.from_hex(episode_id_hex)\n uri = f'spotify:episode:{hex_to_spotify_id(episode_id_hex)}'\n info = Spodcast.SESSION.api().get_metadata_4_episode(episode_id)\n podcast_name = info.show.name\n podcast_id = util.bytes_to_hex(info.show.gid)\n episode_name = info.name\n duration_ms = info.duration\n description = info.description\n external_url = info.external_url if info.external_url else None\n pt = info.publish_time\n release_date = f'{pt.year}-{pt.month}-{pt.day}T{pt.hour}:{pt.minute}:00Z'\n date_temp = datetime.strptime(release_date, '%Y-%m-%dT%H:%M:%SZ')\n release_date_clean = f'{date_temp.strftime(\"%Y\")}-{date_temp.strftime(\"%m\")}-{date_temp.strftime(\"%d\")}'\n\n return podcast_name, podcast_id, duration_ms, episode_name, description, release_date, uri, external_url, release_date_clean\n\n\ndef get_episodes(show_id):\n info = Spodcast.SESSION.api().get_metadata_4_show(show_id)\n episodes = info.episode\n episodes.sort(key = lambda x: datetime.strptime(f'{x.publish_time.year}-{x.publish_time.month}-{x.publish_time.day}T{x.publish_time.hour}:{x.publish_time.minute}:00Z', \"%Y-%m-%dT%H:%M:%SZ\"), reverse=True)\n\n return [util.bytes_to_hex(episode.gid) for episode in episodes]\n\n\ndef download_file(url, filepath):\n import functools\n import pathlib\n import shutil\n import requests\n\n mimetype = \"audio/mpeg\"\n\n r = requests.get(url, stream=True, allow_redirects=True)\n if r.status_code != 200:\n r.raise_for_status() # Will only raise for 4xx codes, so...\n log.error(f\"Request to {url} returned status code {r.status_code}\")\n return\n\n file_size = int(r.headers.get('Content-Length', 0))\n\n if (\n os.path.isfile(filepath)\n and abs(file_size - os.path.getsize(filepath)) < 1000\n and Spodcast.CONFIG.get_skip_existing_files()\n ):\n return filepath, FILE_EXISTS, mimetype\n\n log.info(\"Downloading file\")\n r.raw.read = functools.partial(r.raw.read, decode_content=True)\n with open(filepath, \"wb\") as file:\n shutil.copyfileobj(r.raw, file)\n\n\n return filepath, os.path.getsize(filepath), mimetype\n\n\ndef download_stream(stream, filepath):\n size = stream.input_stream.size\n\n mp3_filepath = os.path.splitext(filepath)[0] + \".mp3\"\n mimetype = \"audio/ogg\"\n\n if (\n # \"FILE SIZE CHECK TEMPORARILY OUT OF ORDER\"\n # Need to find a way to get decrypted content size\n # from Spotify to enable file size checks, for now\n # this only checks for the presence of a file with\n # the same name. To recover from failed downloads\n # simply remove incomplete files\n #\n #((os.path.isfile(filepath)\n #and abs(size - os.path.getsize(filepath)) < 1000)\n (os.path.isfile(filepath)\n or (Spodcast.CONFIG.get_transcode()\n and os.path.isfile(mp3_filepath)))\n and Spodcast.CONFIG.get_skip_existing_files()\n ):\n return filepath, FILE_EXISTS, mimetype\n \n log.info(\"Downloading stream\")\n time_start = time.time()\n downloaded = 0\n with open(filepath, 'wb') as file:\n data = b\"\"\n while data := stream.input_stream.stream().read(Spodcast.CONFIG.get_chunk_size()):\n if data == b\"\":\n break\n file.write(data)\n downloaded += len(data)\n if Spodcast.CONFIG.get_download_real_time():\n delta_real = time.time() - time_start\n delta_want = (downloaded / size) * (duration_ms/1000)\n log.debug(f\"realtime enabled, waiting for {delta_real} seconds...\")\n if delta_want > delta_real:\n time.sleep(delta_want - delta_real)\n\n if Spodcast.CONFIG.get_transcode():\n log.info(\"transcoding ogg->mp3\")\n transcoder = ffmpeg.input(filepath)\n transcoder = ffmpeg.output(transcoder, mp3_filepath)\n ffmpeg.run(transcoder, quiet=True)\n file.close()\n os.unlink(filepath)\n filepath = mp3_filepath\n downloaded = os.path.getsize(filepath)\n mimetype = \"audio/mpeg\"\n\n return filepath, downloaded, mimetype\n\n\ndef download_episode(episode_id) -> None:\n try:\n podcast_name, podcast_id, duration_ms, episode_name, description, release_date, uri, download_url, release_date_clean = get_episode_info(episode_id)\n\n if podcast_name is None:\n log.warning('Skipping episode (podcast NOT FOUND)')\n elif episode_name is None:\n log.warning('Skipping episode (episode NOT FOUND)')\n else:\n filename = clean_filename(release_date_clean + ' - ' + podcast_name + ' - ' + episode_name)\n show_directory = os.path.realpath(os.path.join(Spodcast.CONFIG.get_root_path(), clean_filename(podcast_name) + '/'))\n os.makedirs(show_directory, exist_ok=True)\n\n if download_url is None:\n episode_stream_id = EpisodeId.from_hex(episode_id)\n stream = Spodcast.get_content_stream(episode_stream_id, Spodcast.DOWNLOAD_QUALITY)\n basename = f\"{filename}.ogg\"\n filepath = os.path.join(show_directory, basename)\n path, size, mimetype = download_stream(stream, filepath)\n basename = os.path.basename(path) # may have changed due to transcoding\n else:\n basename=f\"{filename}.mp3\"\n filepath = os.path.join(show_directory, basename)\n path, size, mimetype = download_file(download_url, filepath)\n\n if size == FILE_EXISTS:\n log.info(f\"Skipped {podcast_name}: {episode_name}\")\n else:\n log.warning(f\"Downloaded {podcast_name}: {episode_name}\")\n\n if Spodcast.CONFIG.get_rss_feed():\n episode_info = {\n \"mimetype\": mimetype,\n \"medium\": \"audio\",\n \"duration\": int(duration_ms/1000),\n \"date\": time.strftime(\"%a, %d %b %Y %H:%M:%S +0000\", time.strptime(release_date, \"%Y-%m-%dT%H:%M:%SZ\")),\n \"title\": escape(episode_name), \"guid\": uri, \"description\": escape(description),\n \"filename\": urllib.parse.quote(basename),\n \"size\": int(size) }\n info_file = open(os.path.join(show_directory, f\"{basename}.{RSS_FEED_INFO_EXTENSION}\"), \"w\")\n info_file.write(json.dumps(episode_info))\n info_file.close()\n\n if Spodcast.CONFIG.get_rss_feed():\n show_index_file_name = os.path.join(show_directory, f\"{RSS_FEED_SHOW_INDEX}.{RSS_FEED_INFO_EXTENSION}\")\n if not os.path.isfile(show_index_file_name) or int(get_index_version(show_index_file_name)) < Spodcast.CONFIG.get_version_int():\n podcast_link, podcast_description, podcast_image = get_show_info(podcast_id)\n show_info = {}\n if os.path.isfile(show_index_file_name):\n with open(show_index_file_name, encoding='utf-8') as file:\n show_info = json.load(file)\n file.close()\n show_info[\"version\"] = str(RSS_FEED_VERSION + Spodcast.CONFIG.get_version_str())\n show_info[\"title\"] = escape(podcast_name)\n show_info[\"link\"] = podcast_link\n show_info[\"description\"] = escape(podcast_description)\n show_info[\"image\"] = RSS_FEED_SHOW_IMAGE \n show_index_file = open(show_index_file_name, \"w\")\n show_index_file.write(json.dumps(show_info))\n show_index_file.close()\n\n show_image_name = os.path.join(show_directory, f\"{RSS_FEED_SHOW_IMAGE}\")\n if not os.path.isfile(show_image_name):\n download_file(podcast_image, show_image_name)\n\n rss_file_name = os.path.join(show_directory, RSS_FEED_FILE_NAME)\n if not os.path.isfile(rss_file_name) or int(get_index_version(rss_file_name)) < Spodcast.CONFIG.get_version_int():\n rss_file = open(rss_file_name, \"w\")\n rss_file.write(RSS_FEED_CODE(Spodcast.CONFIG.get_version_str()))\n rss_file.close()\n\n except ApiClient.StatusCodeException as status:\n log.warning(\"episode %s, StatusCodeException: %s\", episode_id, status)\n"
},
{
"path": "spodcast/spodcast.py",
"content": "from getpass import getpass\nimport glob\nimport hashlib\nfrom logging import Logger\nimport logging\nimport os\nimport os.path\nimport random\nimport requests\nimport sys\nimport time\n\nfrom librespot.audio.decoders import VorbisOnlyAudioQuality\nfrom librespot.core import Session\n\nfrom spodcast.config import Config\nfrom spodcast.const import CREDENTIALS_PREFIX, TYPE, USER_READ_EMAIL, OFFSET, LIMIT\nfrom spodcast.feedgenerator import RSS_FEED_FILE_NAME, RSS_INDEX_CODE, get_index_version\n\nclass Spodcast: \n SESSION: Session = None\n DOWNLOAD_QUALITY = None\n CONFIG: Config = Config()\n LOG: Logger = None\n\n def __init__(self, args):\n Spodcast.CONFIG.load(args)\n logging.basicConfig(level=Spodcast.CONFIG.get_log_level())\n log = logging.getLogger(__name__)\n Spodcast.LOG = log\n log.debug(\"args: %s\", args)\n if args.prepare_feed is True:\n root_path=Spodcast.CONFIG.get_root_path()\n os.makedirs(root_path, exist_ok=True)\n if os.path.exists(root_path):\n index_file_name = os.path.join(root_path, RSS_FEED_FILE_NAME)\n if not os.path.isfile(index_file_name) or int(get_index_version(index_file_name)) < Spodcast.CONFIG.get_version_int():\n rss_file = open(index_file_name, \"w\")\n rss_file.write(RSS_INDEX_CODE(Spodcast.CONFIG.get_bin_path(), os.path.basename(Spodcast.CONFIG.get_config_path()), Spodcast.CONFIG.get_version_str()))\n rss_file.close()\n else:\n sys.exit(f\"Can not create root path {root_path}\")\n\n if args.login:\n filename = args.login\n if os.path.exists(filename):\n with open(filename, 'r', encoding='utf-8') as file:\n for line in file.readlines():\n Spodcast.account(line.strip())\n sys.exit(0)\n else:\n sys.exit(f\"Can not read username/password file {filename}\")\n\n Spodcast.login()\n\n @classmethod\n def account(cls, line):\n cred_directory = Config.get_config_dir()\n if os.path.isdir(cred_directory):\n (username,password) = line.split()\n cred_filename = CREDENTIALS_PREFIX + \"-\" + hashlib.md5(username.encode('utf-8'),usedforsecurity=False).hexdigest() + \".json\"\n cred_location = os.path.join(cred_directory, cred_filename)\n conf = Session.Configuration.Builder().set_stored_credential_file(cred_location).build()\n session = Session.Builder(conf).user_pass(username, password).create()\n if not session.is_valid():\n Spodcast.LOG.error(\"Invalid username/password for username \" + username);\n \n @classmethod\n def login(cls):\n cred_directory = Config.get_config_dir()\n credfiles = glob.glob(os.path.join(cred_directory, CREDENTIALS_PREFIX) + \"-*.json\")\n if credfiles:\n random.shuffle(credfiles)\n for credfile in credfiles:\n try:\n cred_location = os.path.join(cred_directory, credfile)\n conf = Session.Configuration.Builder().set_stored_credential_file(cred_location).set_store_credentials(False).build()\n session = Session.Builder(conf).stored_file().create()\n if session.is_valid():\n cls.SESSION = session\n return\n else:\n Spodcast.LOG.warning(f\"Invalid credentials in {cred_location}\")\n except RuntimeError:\n Spodcast.LOG.error(\"RuntimeError\")\n pass\n \n cred_location = Config.get_credentials_location()\n\n if os.path.isfile(cred_location):\n try:\n conf = Session.Configuration.Builder().set_stored_credential_file(cred_location).set_store_credentials(False).build()\n cls.SESSION = Session.Builder(conf).stored_file().create()\n return\n except RuntimeError:\n pass\n while True:\n user_name = ''\n while len(user_name) == 0:\n user_name = input('Username: ')\n password = getpass()\n try:\n conf = Session.Configuration.Builder().set_stored_credential_file(cred_location).build()\n cls.SESSION = Session.Builder(conf).user_pass(user_name, password).create()\n return\n except RuntimeError:\n pass\n\n @classmethod\n def get_content_stream(cls, content_id, quality):\n return cls.SESSION.content_feeder().load(content_id, VorbisOnlyAudioQuality(quality), False, None)\n\n @classmethod\n def __get_auth_token(cls):\n return cls.SESSION.tokens().get_token(USER_READ_EMAIL).access_token\n\n @classmethod\n def get_auth_header(cls):\n return {\n 'Authorization': f'Bearer {cls.__get_auth_token()}',\n 'Accept-Language': f'{cls.CONFIG.get_language()}'\n }\n\n @classmethod\n def get_auth_header_and_params(cls, limit, offset):\n return {\n 'Authorization': f'Bearer {cls.__get_auth_token()}',\n 'Accept-Language': f'{cls.CONFIG.get_language()}'\n }, {LIMIT: limit, OFFSET: offset}\n\n @classmethod\n def invoke_url_with_params(cls, url, limit, offset, **kwargs):\n headers, params = cls.get_auth_header_and_params(limit=limit, offset=offset)\n params.update(kwargs)\n return requests.get(url, headers=headers, params=params).json()\n\n @classmethod\n def invoke_url(cls, url, tryCount=0):\n headers = cls.get_auth_header()\n Spodcast.LOG.debug(headers)\n response = requests.get(url, headers=headers)\n responsetext = response.text\n responsejson = response.json()\n\n if 'error' in responsejson:\n if tryCount < (cls.CONFIG.get_retry() - 1):\n Spodcast.LOG.warning(f\"Spotify API Error (try {tryCount + 1}) ({responsejson['error']['status']}): {responsejson['error']['message']}\")\n time.sleep(5)\n return cls.invoke_url(url, tryCount + 1)\n\n Spodcast.LOG.error(f\"Spotify API Error ({responsejson['error']['status']}): {responsejson['error']['message']}\")\n\n return responsetext, responsejson\n"
},
{
"path": "spodcast/utils.py",
"content": "import re\nimport string\nimport unicodedata\nfrom enum import Enum\nfrom typing import List, Tuple\n\nfrom spodcast.spodcast import Spodcast\nfrom spodcast.const import OPEN_SPOTIFY_URL\n\nvalid_filename_chars = \"-_.() %s%s\" % (string.ascii_letters, string.digits)\n\ndef regex_input_for_urls(search_input) -> Tuple[str, str, str, str, str, str]:\n episode_uri_search = re.search(\n r'^spotify:episode:(?P