[podcasts] Add parsing of RSS feed urls
This commit is contained in:
22
PROJECT.org
22
PROJECT.org
@ -92,7 +92,7 @@ fetching and simple saving.
|
||||
:LOGBOOK:
|
||||
CLOCK: [2025-07-09 Wed 09:55]--[2025-07-09 Wed 10:15] => 0:20
|
||||
:END:
|
||||
* Backlog [0/24]
|
||||
* Backlog [1/28]
|
||||
** TODO [#C] Create small utility to clean up tracks scrobbled with wonky playback times :vrobbler:personal:bug:music:scrobbles:
|
||||
** TODO [#C] Move to using more robust mopidy-webhooks pacakge form pypi :utility:improvement:
|
||||
:PROPERTIES:
|
||||
@ -491,6 +491,26 @@ https://life.lab.unbl.ink/scrobble/e39779c8-62a5-46a6-bdef-fb7662810dc6/start/
|
||||
- Note taken on [2025-09-30 Tue 09:33]
|
||||
|
||||
This may have already been resolved ... need to just confirm it.
|
||||
** TODO
|
||||
|
||||
** DONE [#A] Add RSS feed lookups to podcasts :vrobbler:personal:feature:podcasts:
|
||||
:PROPERTIES:
|
||||
:ID: d60645b0-7578-97c1-0278-05bd9de4269c
|
||||
:END:
|
||||
|
||||
- Note taken on [2025-10-14 Tue 10:08]
|
||||
|
||||
Turns out the Podcast plugin for mopidy does a pretty good job of showing the
|
||||
latest file without having to scroll the bottom using only Muse to not parse
|
||||
the podcast title name. BUT, now we're getting urls like this:
|
||||
|
||||
https://nsf.libsyn.com/rss#77e01251-cb20-4609-b577-d48e985d2e7b
|
||||
|
||||
This is great, because there's more context there, but it has to read out of
|
||||
the RSS feed. We should add a check in the podcast util to sniff out the file
|
||||
referenced in the # in that url and populate the info from there. This should
|
||||
actually be much more reliable than the current state of the podcast lookup
|
||||
which depends on the file to be name properly.
|
||||
|
||||
* Version 26.0 [3/3]
|
||||
** DONE Clean up templates for scrobble details :vrobbler:personal:bug:templates:
|
||||
|
||||
28
poetry.lock
generated
28
poetry.lock
generated
@ -1602,6 +1602,21 @@ files = [
|
||||
[package.extras]
|
||||
devel = ["colorama", "json-spec", "jsonschema", "pylint", "pytest", "pytest-benchmark", "pytest-cache", "validictory"]
|
||||
|
||||
[[package]]
|
||||
name = "feedparser"
|
||||
version = "6.0.12"
|
||||
description = "Universal feed parser, handles RSS 0.9x, RSS 1.0, RSS 2.0, CDF, Atom 0.3, and Atom 1.0 feeds"
|
||||
optional = false
|
||||
python-versions = ">=3.6"
|
||||
groups = ["main"]
|
||||
files = [
|
||||
{file = "feedparser-6.0.12-py3-none-any.whl", hash = "sha256:6bbff10f5a52662c00a2e3f86a38928c37c48f77b3c511aedcd51de933549324"},
|
||||
{file = "feedparser-6.0.12.tar.gz", hash = "sha256:64f76ce90ae3e8ef5d1ede0f8d3b50ce26bcce71dd8ae5e82b1cd2d4a5f94228"},
|
||||
]
|
||||
|
||||
[package.dependencies]
|
||||
sgmllib3k = "*"
|
||||
|
||||
[[package]]
|
||||
name = "filelock"
|
||||
version = "3.18.0"
|
||||
@ -4403,6 +4418,17 @@ enabler = ["pytest-enabler (>=2.2)"]
|
||||
test = ["build[virtualenv] (>=1.0.3)", "filelock (>=3.4.0)", "ini2toml[lite] (>=0.14)", "jaraco.develop (>=7.21) ; python_version >= \"3.9\" and sys_platform != \"cygwin\"", "jaraco.envs (>=2.2)", "jaraco.path (>=3.7.2)", "jaraco.test (>=5.5)", "packaging (>=24.2)", "pip (>=19.1)", "pyproject-hooks (!=1.1)", "pytest (>=6,!=8.1.*)", "pytest-home (>=0.5)", "pytest-perf ; sys_platform != \"cygwin\"", "pytest-subprocess", "pytest-timeout", "pytest-xdist (>=3)", "tomli-w (>=1.0.0)", "virtualenv (>=13.0.0)", "wheel (>=0.44.0)"]
|
||||
type = ["importlib_metadata (>=7.0.2) ; python_version < \"3.10\"", "jaraco.develop (>=7.21) ; sys_platform != \"cygwin\"", "mypy (==1.14.*)", "pytest-mypy"]
|
||||
|
||||
[[package]]
|
||||
name = "sgmllib3k"
|
||||
version = "1.0.0"
|
||||
description = "Py3k port of sgmllib."
|
||||
optional = false
|
||||
python-versions = "*"
|
||||
groups = ["main"]
|
||||
files = [
|
||||
{file = "sgmllib3k-1.0.0.tar.gz", hash = "sha256:7868fb1c8bfa764c1ac563d3cf369c381d1325d36124933a726f29fcdaa812e9"},
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "shellingham"
|
||||
version = "1.5.4"
|
||||
@ -5499,4 +5525,4 @@ cffi = ["cffi (>=1.11)"]
|
||||
[metadata]
|
||||
lock-version = "2.1"
|
||||
python-versions = ">=3.9,<3.12"
|
||||
content-hash = "3a483aefea0a3afebf187b17b7df72a158788024ca8121b512b39567fb5ec8ca"
|
||||
content-hash = "cd3b566597e09aa444f9af30f95f94f922bf3dca71fbd05c887fb10cbc11d7bf"
|
||||
|
||||
@ -56,6 +56,7 @@ poetry-bumpversion = "^0.3.3"
|
||||
orgparse = "^0.4.20250520"
|
||||
tmdbv3api = "^1.9.0"
|
||||
themoviedb = "^1.0.2"
|
||||
feedparser = "^6.0.12"
|
||||
|
||||
[tool.poetry.group.test]
|
||||
optional = true
|
||||
|
||||
@ -1,7 +1,9 @@
|
||||
import logging
|
||||
import os
|
||||
from typing import Any
|
||||
from urllib.parse import unquote
|
||||
|
||||
import feedparser
|
||||
from dateutil.parser import ParserError, parse
|
||||
from podcasts.models import PodcastEpisode
|
||||
|
||||
@ -10,26 +12,80 @@ logger = logging.getLogger(__name__)
|
||||
# TODO This should be configurable in settings or per deploy
|
||||
PODCAST_DATE_FORMAT = "YYYY-MM-DD"
|
||||
|
||||
def parse_duration(d):
|
||||
if not d:
|
||||
return None
|
||||
if d.isdigit():
|
||||
return int(d)
|
||||
parts = [int(p) for p in d.split(":")]
|
||||
while len(parts) < 3:
|
||||
parts.insert(0, 0)
|
||||
h, m, s = parts
|
||||
return h * 3600 + m * 60 + s
|
||||
|
||||
def fetch_metadata_from_rss(uri: str) -> dict[str, Any]:
|
||||
log_context = {"mopidy_uri": uri, "media_type": "Podcast"}
|
||||
podcast_data: dict[str, Any] = {}
|
||||
|
||||
try:
|
||||
feed = feedparser.parse(uri.split("#")[0])
|
||||
target_guid = uri.split("#")[1]
|
||||
except IndexError:
|
||||
logger.warning("Tried to parse uri as RSS feed, but no target found", extra=log_context)
|
||||
return podcast_data
|
||||
|
||||
podcast_data = {
|
||||
"podcast_name": feed.feed.get("title", "Unknown Podcast"),
|
||||
"podcast_description": feed.feed.get("description", ""),
|
||||
"podcast_link": feed.feed.get("link", ""),
|
||||
}
|
||||
|
||||
for entry in feed.entries:
|
||||
if target_guid in target_guid:
|
||||
logger.info("🎧 Episode found in RSS feed", extra=log_context)
|
||||
podcast_data["episode_name"] = entry.title
|
||||
podcast_data["episode_num"] = entry.guid
|
||||
podcast_data["episode_pub_date"] = entry.get("published", None)
|
||||
podcast_data["episode_description"] = entry.get("description", None)
|
||||
podcast_data["episode_url"] = entry.enclosures[0].href if entry.get("enclosures") else None
|
||||
podcast_data["episode_runtime_seconds"] = parse_duration(entry.get("itunes_duration", None))
|
||||
return podcast_data
|
||||
else:
|
||||
logger.info("Episode not found in RSS feed.")
|
||||
|
||||
|
||||
def parse_mopidy_uri(uri: str) -> dict[str, Any]:
|
||||
podcast_data: dict[str, Any] = {}
|
||||
|
||||
def parse_mopidy_uri(uri: str) -> dict:
|
||||
logger.debug(f"Parsing URI: {uri}")
|
||||
if "https://" in uri:
|
||||
return fetch_metadata_from_rss(uri)
|
||||
|
||||
|
||||
parsed_uri = os.path.splitext(unquote(uri))[0].split("/")
|
||||
|
||||
podcast_data = {
|
||||
"episode_filename": parsed_uri[-1],
|
||||
"episode_num": None,
|
||||
"podcast_name": parsed_uri[-2].strip(),
|
||||
"pub_date": None,
|
||||
}
|
||||
|
||||
|
||||
episode_str = parsed_uri[-1]
|
||||
podcast_name = parsed_uri[-2].strip()
|
||||
episode_num = None
|
||||
episode_num_pad = 0
|
||||
|
||||
try:
|
||||
# Without episode numbers the date will lead
|
||||
pub_date = parse(episode_str[0:10])
|
||||
podcast_data["pub_date"] = parse(episode_str[0:10])
|
||||
except ParserError:
|
||||
episode_num = int(episode_str.split("-")[0])
|
||||
episode_num_pad = len(str(episode_num)) + 1
|
||||
podcast_data["episode_num"] = int(episode_str.split("-")[0])
|
||||
episode_num_pad = len(str(podcast_data["episode_num"])) + 1
|
||||
|
||||
try:
|
||||
# Beacuse we have epsiode numbers on
|
||||
pub_date = parse(
|
||||
podcast_data["pub_date"] = parse(
|
||||
episode_str[
|
||||
episode_num_pad : len(PODCAST_DATE_FORMAT)
|
||||
+ episode_num_pad
|
||||
@ -39,22 +95,19 @@ def parse_mopidy_uri(uri: str) -> dict:
|
||||
pub_date = ""
|
||||
|
||||
gap_to_strip = 0
|
||||
if pub_date:
|
||||
if podcast_data["pub_date"]:
|
||||
gap_to_strip += len(PODCAST_DATE_FORMAT)
|
||||
if episode_num:
|
||||
if podcast_data["episode_num"]:
|
||||
gap_to_strip += episode_num_pad
|
||||
|
||||
episode_name = episode_str[gap_to_strip:].replace("-", " ").strip()
|
||||
podcast_data["episode_name"] = episode_str[gap_to_strip:].replace("-", " ").strip()
|
||||
|
||||
return {
|
||||
"episode_filename": episode_name,
|
||||
"episode_num": episode_num,
|
||||
"podcast_name": podcast_name,
|
||||
"pub_date": pub_date,
|
||||
}
|
||||
return podcast_data
|
||||
|
||||
|
||||
def get_or_create_podcast(post_data: dict) -> PodcastEpisode:
|
||||
logger.info("Looking up podcast", extra={"post_data": post_data, "media_type": "Podcast"})
|
||||
|
||||
mopidy_uri = post_data.get("mopidy_uri", "")
|
||||
parsed_data = parse_mopidy_uri(mopidy_uri)
|
||||
|
||||
@ -66,9 +119,10 @@ def get_or_create_podcast(post_data: dict) -> PodcastEpisode:
|
||||
podcast_dict = {"name": podcast_name}
|
||||
|
||||
episode_name = parsed_data.get("episode_filename")
|
||||
run_time_seconds = parsed_data.get("episode_runtime_seconds", post_data.get("run_time", 2700))
|
||||
episode_dict = {
|
||||
"title": episode_name,
|
||||
"run_time_seconds": post_data.get("run_time"),
|
||||
"run_time_seconds": run_time_seconds,
|
||||
"number": parsed_data.get("episode_num"),
|
||||
"pub_date": parsed_data.get("pub_date"),
|
||||
"mopidy_uri": mopidy_uri,
|
||||
|
||||
Reference in New Issue
Block a user