re format

.gitignore

@@ -83,4 +83,9 @@ poetry.lock
 # XML generated files
 podcast_feed.xml
 feed.xml
-video_feed.xml
+video_feed.xml
+uv.lock
+*.svg
+
+old.pyproject.toml
+.github

docker/docker-compose.yml

@@ -0,0 +1,14 @@
+version: '3.8'
+
+services:
+  c2c-scraper:
+    image: death916/c2cscrape:latest  
+    volumes:
+      - /mnt/media/media/books/audio/podcasts/C2C:/downloads
+      - /mnt/media/docker/volumes/c2cscrape
+    restart: unless-stopped
+    environment:
+      - TZ=America/Los_Angeles
+
+
+

docker/dockerfile

@@ -0,0 +1,22 @@
+FROM python:3.11-slim
+
+# Set timezone
+ENV TZ=America/Los_Angeles
+RUN apt-get update && apt-get install -y tzdata
+
+# Create app directory
+WORKDIR /app
+
+# Install dependencies
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy source code
+COPY . .
+
+# Set hardcoded download path
+ENV DOWNLOAD_DIR=/downloads
+
+# Start the scraper
+CMD ["python", "-u", "c2cscrape.py"]
+

pyproject.toml

@@ -1,18 +1,17 @@
-[tool.poetry]
+[project]
 name = "c2cscrape"
 version = "0.1.0"
 description = "scrape blog site for old c2c am episdodes and serve as rss"
-authors = ["Death916 <mail@trentnelson.dev>"]
+authors = [{ name = "Death916", email = "mail@trentnelson.dev" }]
-readme = "README.md"
+source = "src"
-
+requires-python = ">=3.11"
-[tool.poetry.dependencies]
+dependencies = [
-python = "^3.11"
+    "bs4>=0.0.2",
-playwright = "^1.50.0"
+    "feedgen>=1.0.0",
-bs4 = "^0.0.2"
+    "playwright>=1.50.0",
-requests = "^2.32.3"
+    "requests>=2.32.3",
-feedgen = "^1.0.0"
+]
-
 
 [build-system]
-requires = ["poetry-core"]
+requires = ["hatchling"]
-build-backend = "poetry.core.masonry.api"
+build-backend = "hatchling.build"

src/c2cscrape.py

@@ -17,6 +17,7 @@ class C2CScrape:
             'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'
         }
         self.episodes_downloaded = 0
+        self.download_location = '/downloads'
     def sanitize_filename(self, filename):
         # Remove or replace invalid filename characters
         return re.sub(r'[<>:"/\\|?*]', '-', filename)
@@ -78,7 +79,7 @@ class C2CScrape:
                 return
 
             # Create downloads directory if it doesn't exist
-            download_dir = 'downloads'
+            download_dir = '/downloads'
             os.makedirs(download_dir, exist_ok=True)
 
             # Get current date
@@ -154,7 +155,17 @@ class C2CScrape:
 
 
     # timer to check for new episodes every 12 hours
+    def timer(self):
     
+        try:
+            # Run our core operations
+            self.process_episode()
+            self.get_older_posts()
+            print(f'Episodes downloaded: {self.episodes_downloaded}')
+        finally:
+            # Ensure timer restarts even if there's an error
+            print("waiting 12 hours")
+            threading.Timer(43200, self.timer).start()  # 43200 sec = 12 hours
     # navigate to older posts button 5 times and get last 5 episodes with no repeats/ span id is blog-pager-older-link
     def get_older_posts(self, limit=5):
         try:
@@ -194,9 +205,15 @@ class C2CScrape:
 
 if __name__ == '__main__':
     c2c = C2CScrape()
-    c2c.process_episode()
+    # Start initial timer immediately
-    c2c.get_older_posts()
-    print(f'Episodes downloaded: {c2c.episodes_downloaded}')
     c2c.timer()
+    # Keep main thread alive with minimal resource usage
+    try:
+        while True:
+            time.sleep(3600)  # Check once per hour
+    except KeyboardInterrupt:
+        print("\nStopping scheduled downloads...")
+    print(f'Episodes downloaded: {c2c.episodes_downloaded}')
+    
     #rss = createRss()
     #rss.process_episodes()

src/main.py

@@ -0,0 +1,6 @@
+def main():
+    print("Hello from c2cscrape!")
+
+
+if __name__ == "__main__":
+    main()