Merge pull request #9 from voko/feature/add-related-links

Feature/add related links

Dockerfile

@@ -26,7 +26,7 @@ RUN mkdir -p /var/mbz-rss-feeder/cache /var/mbz-rss-feeder/log /var/mbz-rss-feed
 
 # Test stage
 FROM builder AS test
-COPY mzb_rss_service/tests/requirements.txt .
+COPY mbz_rss_service/tests/requirements.txt .
 RUN pip install --no-cache-dir -r requirements.txt
 COPY . .
 CMD ["python -m pytest"]
@@ -35,8 +35,8 @@ CMD ["python -m pytest"]
 FROM base AS final
 COPY --from=builder /usr/local/lib/python3.10/site-packages /usr/local/lib/python3.10/site-packages
 COPY --from=builder /usr/local/bin /usr/local/bin
-COPY mzb_rss_service mzb_rss_service
+COPY mbz_rss_service mbz_rss_service
 COPY VERSION .
 
 EXPOSE 8080
-CMD ["gunicorn", "--bind", "0.0.0.0:8080", "mzb_rss_service.main:app"]
+CMD ["gunicorn", "--bind", "0.0.0.0:8080", "mbz_rss_service.main:app"]

README.md

@@ -45,7 +45,7 @@ This is a local container running with data stored in ./local/testdata
   -p 8080:8080 -e LOG_LEVEL=debug --rm --name mbz-rss\
   -v ./local/testdata/:/var/mbz-rss-feeder \
   --env-file ./local/testdata/.env \
-  docker.io/library/mzb-rss-feeder:latest`
+  docker.io/library/mbz-rss-feeder:latest`
 
 After startup the server can be accessed through http://docker-host:8080.
 

VERSION

@@ -1 +1 @@
-1.0.6
+1.2.0

mbz_rss_service/__init__.py

@@ -0,0 +1 @@
+# mbz_rss_service package

mbz_rss_service/config.py

@@ -11,9 +11,10 @@ logger = logging.getLogger(__name__)
 FEEDS_FILE_PATH = os.path.expandvars(os.environ.get('FEEDS_FILE_PATH', '/var/mbz-rss-feeder/feeds.yml'))
 CONFIG_FILE_PATH = os.path.expandvars(os.environ.get('CONFIG_FILE_PATH', '/var/mbz-rss-feeder/etc/mbz-rss-feeder.yml'))
 CACHE_DIR = os.path.expandvars(os.environ.get('CACHE_DIR', '/var/mbz-rss-feeder/cache'))
-MB_APP_NAME = os.path.expandvars(os.environ.get('MB_APP_NAME', 'mzb-rss-service'))
+MB_APP_NAME = os.path.expandvars(os.environ.get('MB_APP_NAME', 'mbz-rss-service'))
-MB_VERSION = os.path.expandvars(os.environ.get('MB_VERSION', '0.1.0'))
+MB_VERSION = os.path.expandvars(os.environ.get('MB_VERSION', '1'))
 MB_CONTACT = os.path.expandvars(os.environ.get('MB_CONTACT', 'someone@somewhere.com'))
+MBZ_SERVICE_BASE_URL = os.path.expandvars(os.environ.get('MBZ_SERVICE_BASE_URL', 'http://mbz-rss-feeder:8080'))
 
 # file system dir check
 if not os.path.exists(CACHE_DIR):
@@ -41,6 +42,8 @@ class Config:
         self.MB_APP_NAME = MB_APP_NAME
         self.MB_VERSION = MB_VERSION
         self.MB_CONTACT = MB_CONTACT
+        self.MBZ_SERVICE_BASE_URL = MBZ_SERVICE_BASE_URL
+
         try:
             with open(os.path.join(os.path.dirname(__file__), '..', 'VERSION')) as f:
                 self.VERSION = f.read().strip()
@@ -68,10 +71,13 @@ class Config:
             backup_path = f"{file_path}.{datetime.now().strftime('%Y%m%d%H%M%S')}.bak"
             shutil.copy(file_path, backup_path)
 
+        logger.debug(f"Saving yaml to {file_path}")
         os.makedirs(os.path.dirname(file_path), exist_ok=True)
         with open(file_path, 'w') as f:
             yaml.dump(data, f, default_flow_style=False, sort_keys=False)
 
+        logger.debug(f"Saved yaml to {file_path}")
+
     @property
     def feeds(self):
         return self._feeds_data.get('feeds', [])
@@ -105,13 +111,16 @@ class Config:
             self._feeds_data['feeds'] = [feed for feed in self.feeds if feed['id'] != feed_id]
             self.save_feeds()
 
-    def add_artist_to_feed(self, feed_id, artist_id, artist_name):
+    def add_artist_to_feed(self, feed_id, artist_id, artist_name, links = None):
         for feed in self.feeds:
             if feed['id'] == feed_id:
                 if 'artists' not in feed:
                     feed['artists'] = []
                 if not any(a['id'] == artist_id for a in feed['artists']):
-                    feed['artists'].append({'id': artist_id, 'name': artist_name})
+                    artist_data = {'id': artist_id, 'name': artist_name}
+                    if links:
+                        artist_data['links'] = links
+                    feed['artists'].append(artist_data)
                     feed['updated_at'] = datetime.now(timezone.utc).isoformat()
                     self.save_feeds()
                 break

mbz_rss_service/main.py

@@ -9,6 +9,8 @@ import os
 import sys
 from . import musicbrainz
 
+XML_CONTENT_TYPE = "application/xml"
+
 log_level_str = os.environ.get('LOG_LEVEL', 'INFO').upper()
 log_level = getattr(logging, log_level_str, logging.INFO)
 log_file = os.path.expandvars(os.environ.get('LOG_FILE', '/var/mbz-rss-feeder/log/mbz-rss-feeder.log'))
@@ -55,7 +57,7 @@ for handler in werkzeug_logger.handlers:
 logger = logging.getLogger(__name__)
 
 
-logger.info("Starting mzb-rss-service with the following configuration:")
+logger.info(f"Starting mbz-rss-service v{config.VERSION} with the following configuration:")
 logger.info(f"  - Log Level: {log_level_str}")
 logger.info(f"  - Log File: {log_file}")
 logger.info(f"  - Feeds File: {config.FEEDS_FILE_PATH}")
@@ -69,6 +71,30 @@ logger.info(f"  - MusicBrainz Log Level: {mbz_log_level_str}")
 # init
 musicbrainz.init_musicbrainz()
 app = Flask(__name__)
+
+@app.context_processor
+def inject_service_name():
+    return {'service_base_url': config.MBZ_SERVICE_BASE_URL}
+
+class ReverseProxied(object):
+    def __init__(self, app):
+        self.app = app
+
+    def __call__(self, environ, start_response):
+        script_name = environ.get('HTTP_X_FORWARDED_PREFIX', '')
+        if script_name:
+            logger.debug(f"Redirect prefix: {script_name}")
+            environ['SCRIPT_NAME'] = script_name
+            path_info = environ['PATH_INFO']
+            if path_info.startswith(script_name):
+                environ['PATH_INFO'] = path_info[len(script_name):]
+        else:
+            logger.debug("No redirect prefix detected")
+
+        return self.app(environ, start_response)
+
+app.wsgi_app = ReverseProxied(app.wsgi_app)
+
 app.template_folder = 'templates'
 
 
@@ -134,7 +160,7 @@ def _check_cache(feed_id):
         try:
             with open(cache_file, 'r') as f:
                 logger.debug(f"Serving cached feed for {feed_id}")
-                return f.read(), {"Content-Type": "application/xml"}
+                return f.read(), {"Content-Type": XML_CONTENT_TYPE}
         except IOError as e:
             logger.warning(f"Could not read cache file {cache_file}: {e}")
 
@@ -175,7 +201,8 @@ def add_artist(feed_id):
     artist_name = request.form.get('artist_name')
     logger.debug(f"Request to add artist '{artist_name}' ({artist_id}) to feed {feed_id}")
     if artist_id and artist_name:
-        config.add_artist_to_feed(feed_id, artist_id, artist_name)
+        meta = musicbrainz.get_artist_meta_by_id(artist_id)
+        config.add_artist_to_feed(feed_id, artist_id, artist_name, meta['links'])
     return redirect(url_for('edit_feed', feed_id=feed_id))
 
 @app.route("/feed/<feed_id>/artist/<artist_id>/remove", methods=["POST"])
@@ -208,7 +235,7 @@ def opml():
     logger.debug("Request for OPML file")
     feeds = config.feeds
     opml_content = render_template('opml.xml', feeds=feeds)
-    return opml_content, {"Content-Type": "application/xml"}
+    return opml_content, {"Content-Type": XML_CONTENT_TYPE}
 
 @app.route('/feed/<feed_id>')
 def get_feed_rss(feed_id):
@@ -257,7 +284,7 @@ def get_feed_rss(feed_id):
     except IOError as e:
         logger.warning(f"Could not write feed '{feed_data['name']}' to cache file {cache_file}: {e}")
 
-    return rss_content, {"Content-Type": "application/xml"}
+    return rss_content, {"Content-Type": XML_CONTENT_TYPE}
 
 @app.route("/health")
 def health_check():

mbz_rss_service/musicbrainz.py

@@ -1,6 +1,6 @@
+import re
 import musicbrainzngs
 import logging
-import os
 from .config import config
 from datetime import datetime
 from email.utils import formatdate
@@ -62,6 +62,10 @@ def _process_release(release, artist_id):
     release_date = release.get('date', 'Unknown')
     _, pub_date = _parse_release_date(release_date, release['title'])
 
+    links = {}
+    if 'url-relation-list' in release:
+        links = get_artist_relation_links(release['url-relation-list'])
+
     return {
         'artist': {
             'name': config.get_artist_name(artist_id),
@@ -72,8 +76,54 @@ def _process_release(release, artist_id):
         'title': release['title'],
         'date': release_date,
         'pub_date': pub_date,
-        'release-group': release.get('release-group', {})
+        'release-group': release.get('release-group', {}),
+        'links': links,
     }
+def get_artist_meta_by_id(artist_id):
+    """get additional meta data about an artist"""
+    meta = {
+        'links': {}
+    }
+    try:
+        logger.debug(f"Fetching artist {artist_id} meta data")
+        # Fetch artist data including URL relations
+        result = musicbrainzngs.get_artist_by_id(artist_id, includes=["url-rels"])
+        artist_data = result.get('artist', {})
+
+        if 'url-relation-list' in artist_data:
+            meta['links'] = get_artist_relation_links(artist_data['url-relation-list'])
+        else:
+            meta['links'] = None
+
+        return meta
+
+    except musicbrainzngs.WebServiceError as exc:
+        logger.error(f"Error fetching artist {artist_id} meta data from MusicBrainz: {exc}")
+
+    return meta
+
+def get_artist_relation_links(relationlist):
+    """Parse and extract named links from a MusicBrainz URL relation list."""
+    links = {}
+    for rel in relationlist:
+        target = rel.get('target')
+        if not target:
+            continue
+        if re.match(r'^https://([^/]+\.)?imdb\.com', target):
+            links['IMDb'] = target
+        elif re.match(r'^https://music\.apple\.com', target):
+            links['apple'] = target
+        elif re.match(r'^https://music\.amazon\.com', target):
+            links['amazon'] = target
+        elif re.match(r'^https://open\.spotify\.com', target):
+            links['spotify'] = target
+        elif re.match(r'^https://([^/]+\.)?qobuz\.com', target):
+            links['qobuz'] = target
+        elif re.match(r'^https://([^/]+\.)?deezer\.com', target):
+            links['deezer'] = target
+        elif re.match(r'^https://([^/]+\.)?beatport\.com', target):
+            links['beatport'] = target
+    return links
 
 def get_artist_releases(artist_id):
     """Fetch releases for a given artist ID from MusicBrainz."""
@@ -83,7 +133,7 @@ def get_artist_releases(artist_id):
         result = musicbrainzngs.browse_releases(
             artist=artist_id,
             release_type=['album'],
-            includes=['release-groups']
+            includes=['release-groups', 'url-rels']
         )
         
         releases = []

mbz_rss_service/templates/feed.html

@@ -9,6 +9,11 @@
         {% for artist in feed.artists %}
             <li>
                 {{ artist.name }}
+                {% if artist.links %}
+                    {% for type, link in artist.links.items() %}
+                        <a href="{{ link }}" target="_blank">{{ type }}</a>{% if not loop.last %} | {% endif %}
+                    {% endfor %}
+                {% endif %}
                 <div class="item-actions">
                     <form class="form-inline" action="{{ url_for('remove_artist', feed_id=feed.id, artist_id=artist.id) }}" method="post">
                         <button type="submit">Remove</button>

mbz_rss_service/templates/feed.xml

@@ -14,10 +14,17 @@
             <link>https://musicbrainz.org/release/{{ release.id }}</link>
             <guid isPermaLink="false">{{ release.id }}</guid>
             <description><![CDATA[
+                {% if release.hasCoverArt %}
+                    <img src="https://coverartarchive.org/release/{{ release.id }}/front" alt="Cover Art {{ release.title }}">
+                {% endif %}
                 <p><b>{{ release.artist.name }}</b> <i>{{ release.title }}</i><br>
                 Release Date: {{ release.date }}</p>
-                {% if release.hasCoverArt %}
+                {% if release.links %}
-                    <img src="http://coverartarchive.org/release/{{ release.id }}/front-500" alt="Cover Art {{ release.title }}">
+                <p><b>Links: </b>
+                {% for type, url in release.links.items() %}
+                    <a href="{{ url }}" target="_blank">{{ type | capitalize }}</a>{% if not loop.last %} | {% endif %}
+                {% endfor %}
+                </p>
                 {% endif %}
             ]]></description>
             {% if release.pub_date %}

mbz_rss_service/templates/index.html

@@ -11,7 +11,7 @@
                     ({{ feed.artists|length }})
                 </div>
                 <div class="item-actions">
-                    <a href="{{ url_for('get_feed_rss', feed_id=feed.id) }}">RSS</a>
+                    <a href="{{ url_for('get_feed_rss', feed_id=feed.id) }}">RSS</a> | <a href="{{ service_base_url }}/feed/{{ feed.id }}">service rss</a>
                     <form class="form-inline" action="{{ url_for('delete_feed', feed_id=feed.id) }}" method="post">
                         <button type="submit">Delete</button>
                     </form>

mzb_rss_service/__init__.py

@@ -1 +0,0 @@
-# mzb_rss_service package