Add Episode Metadata: Author and Original URL

Enhance episode tracking by adding support for author and original
article URL. This allows users to see more context about each podcast
episode, improving the overall user experience and providing additional
information about the source material.

3 files changed, 63 insertions, 5 deletions

diff --git a/Biz/PodcastItLater/Core.py b/Biz/PodcastItLater/Core.py
index 86676b5..542bb8b 100644
--- a/Biz/PodcastItLater/Core.py
+++ b/Biz/PodcastItLater/Core.py
@@ -122,6 +122,9 @@ class Database:  # noqa: PLR0904
         # Run migration to add metadata fields
         Database.migrate_add_metadata_fields(db_path)
 
+        # Run migration to add episode metadata fields
+        Database.migrate_add_episode_metadata(db_path)
+
     @staticmethod
     def add_to_queue(  # noqa: PLR0913, PLR0917
         url: str,
@@ -218,6 +221,8 @@ class Database:  # noqa: PLR0904
         duration: int,
         content_length: int,
         user_id: int | None = None,
+        author: str | None = None,
+        original_url: str | None = None,
         db_path: str | None = None,
     ) -> int:
         """Insert episode record, return episode ID.
@@ -231,9 +236,17 @@ class Database:  # noqa: PLR0904
             cursor = conn.cursor()
             cursor.execute(
                 "INSERT INTO episodes "
-                "(title, audio_url, duration, content_length, user_id) "
-                "VALUES (?, ?, ?, ?, ?)",
-                (title, audio_url, duration, content_length, user_id),
+                "(title, audio_url, duration, content_length, user_id, author, "
+                "original_url) VALUES (?, ?, ?, ?, ?, ?, ?)",
+                (
+                    title,
+                    audio_url,
+                    duration,
+                    content_length,
+                    user_id,
+                    author,
+                    original_url,
+                ),
             )
             conn.commit()
             episode_id = cursor.lastrowid
@@ -316,7 +329,7 @@ class Database:  # noqa: PLR0904
                 cursor.execute(
                     """
                     SELECT id, title, audio_url, duration, created_at,
-                           content_length
+                           content_length, author, original_url
                     FROM episodes
                     WHERE user_id = ?
                     ORDER BY created_at DESC
@@ -326,7 +339,7 @@ class Database:  # noqa: PLR0904
             else:
                 cursor.execute("""
                     SELECT id, title, audio_url, duration, created_at,
-                           content_length
+                           content_length, author, original_url
                     FROM episodes
                     ORDER BY created_at DESC
                 """)
@@ -521,6 +534,30 @@ class Database:  # noqa: PLR0904
             logger.info("Database migrated to support metadata fields")
 
     @staticmethod
+    def migrate_add_episode_metadata(db_path: str | None = None) -> None:
+        """Add author and original_url fields to episodes table."""
+        if db_path is None:
+            db_path = Database.get_default_db_path()
+        with Database.get_connection(db_path) as conn:
+            cursor = conn.cursor()
+
+            # Check if columns already exist
+            cursor.execute("PRAGMA table_info(episodes)")
+            episodes_info = cursor.fetchall()
+            episodes_columns = [col[1] for col in episodes_info]
+
+            if "author" not in episodes_columns:
+                cursor.execute("ALTER TABLE episodes ADD COLUMN author TEXT")
+
+            if "original_url" not in episodes_columns:
+                cursor.execute(
+                    "ALTER TABLE episodes ADD COLUMN original_url TEXT",
+                )
+
+            conn.commit()
+            logger.info("Database migrated to support episode metadata fields")
+
+    @staticmethod
     def create_user(email: str, db_path: str | None = None) -> tuple[int, str]:
         """Create a new user and return (user_id, token).
 
diff --git a/Biz/PodcastItLater/Web.py b/Biz/PodcastItLater/Web.py
index 8586aaf..3493b7b 100644
--- a/Biz/PodcastItLater/Web.py
+++ b/Biz/PodcastItLater/Web.py
@@ -432,6 +432,13 @@ class EpisodeList(Component[AnyChildren, EpisodeListAttrs]):
             episode_items.append(
                 html.div(
                     html.h4(episode["title"]),
+                    # Show author if available
+                    html.p(
+                        f"by {episode['author']}",
+                        style={"margin": "5px 0", "font-style": "italic"},
+                    )
+                    if episode.get("author")
+                    else html.span(),
                     html.audio(
                         html.source(
                             src=episode["audio_url"],
@@ -445,6 +452,18 @@ class EpisodeList(Component[AnyChildren, EpisodeListAttrs]):
                         f"Duration: {duration_str} | "
                         f"Created: {episode['created_at']}",
                     ),
+                    # Show link to original article if available
+                    html.div(
+                        html.a(
+                            "View original article",
+                            href=episode["original_url"],
+                            target="_blank",
+                            style={"color": "#007cba"},
+                        ),
+                        style={"margin-top": "10px"},
+                    )
+                    if episode.get("original_url")
+                    else html.span(),
                     style={
                         "border": "1px solid #ddd",
                         "padding": "15px",
diff --git a/Biz/PodcastItLater/Worker.py b/Biz/PodcastItLater/Worker.py
index ce3d432..56a91bc 100644
--- a/Biz/PodcastItLater/Worker.py
+++ b/Biz/PodcastItLater/Worker.py
@@ -280,6 +280,8 @@ class ArticleProcessor:
                 duration=duration,
                 content_length=len(content),
                 user_id=job.get("user_id"),
+                author=job.get("author"),  # Pass author from job
+                original_url=url,  # Pass the original article URL
                 db_path=DATABASE_PATH,
             )