Clean up wiki module

sgu/main.py

@@ -5,7 +5,10 @@
 
 from sgu.config import CUSTOM_HEADERS
 from sgu.custom_logger import logger
+from sgu.data_gathering import gather_data
+from sgu.parsers.episode_data import convert_episode_data_to_episode_segments
 from sgu.parsers.rss_feed import get_podcast_episodes
+from sgu.transcription_splitting import add_transcript_to_segments
 from sgu.wiki import create_podcast_wiki_page, episode_has_wiki_page
 
 load_dotenv()
@@ -14,7 +17,8 @@
 async def main() -> None:
     """Main function that starts the program and processes podcast episodes.
 
-    This function retrieves podcast episodes from an RSS feed, checks if each episode has a wiki page,
+    This function retrieves podcast episodes from an RSS feed,
+    checks if each episode has a wiki page,
     and creates a wiki page for episodes that don't have one.
     """
     logger.success("Starting...")
@@ -35,7 +39,16 @@ async def main() -> None:
                 logger.info("Episode has a wiki page. Stopping.")
                 break
 
-            await create_podcast_wiki_page(client, podcast_episode)
+            logger.debug("Gathering all data...")
+            episode_data = await gather_data(client, podcast_episode)
+
+            logger.debug("Converting data to segments...")
+            episode_segments = convert_episode_data_to_episode_segments(episode_data)
+
+            logger.debug("Merging transcript into episode segments...")
+            episode_segments = add_transcript_to_segments(episode_data.transcript, episode_segments)
+
+            await create_podcast_wiki_page(client, episode_data, episode_segments)
 
             break  # TODO: Maybe remove this at some point. It's just making sure that we don't process multiple episodes
 

sgu/wiki.py

@@ -6,47 +6,23 @@
 
 from sgu.config import WIKI_API_BASE, WIKI_EPISODE_URL_BASE
 from sgu.custom_logger import logger
-from sgu.data_gathering import gather_data
-from sgu.episode_segments import BaseSegment, QuoteSegment
-from sgu.parsers.episode_data import convert_episode_data_to_episode_segments
+from sgu.episode_segments import BaseSegment, QuoteSegment, Segments
 from sgu.parsers.show_notes import get_episode_image_url
 from sgu.template_environment import template_env
-from sgu.transcription_splitting import add_transcript_to_segments
 
 if TYPE_CHECKING:
     from requests import Session
 
     from sgu.data_gathering import EpisodeData
-    from sgu.parsers.rss_feed import PodcastEpisode
 
 
 # region public functions
-
-
-async def create_podcast_wiki_page(client: "Session", podcast: "PodcastEpisode"):
+async def create_podcast_wiki_page(client: "Session", episode_data: "EpisodeData", episode_segments: Segments) -> None:
     """Creates a wiki page for a podcast episode.
 
     This function gathers all the necessary data for the episode, merges the data into segments,
     and converts the segments into wiki page content.
-
-    Args:
-        client (requests.Session): The HTTP client session.
-        podcast (PodcastEpisode): The podcast episode.
-
-    Returns:
-        str: The wiki page content.
     """
-    logger.debug("Gathering all data...")
-    episode_data = await gather_data(client, podcast)
-
-    logger.debug("Converting data to segments...")
-    episode_segments = convert_episode_data_to_episode_segments(episode_data)
-
-    logger.debug("Merging transcript into episode segments...")
-    episode_segments = add_transcript_to_segments(episode_data.transcript, episode_segments)
-
-    # Above: Generic actions
-    # Below: Wiki-specific actions
     # we must grab speaker data before we convert transcript to wiki
     speakers = {s["speaker"].lower() for s in episode_data.transcript}
     wiki_segments = "\n".join(s.to_wiki() for s in episode_segments)
@@ -94,8 +70,6 @@ def log_into_wiki(client: "Session") -> str:
 
 # endregion
 # region private functions
-
-
 def _find_image_upload(client: "Session", episode_number: str) -> str:
     params = {"action": "query", "list": "allimages", "aiprefix": episode_number, "format": "json"}
     response = client.get(WIKI_API_BASE, params=params)