Add docker-compose file

Dockerfile

@@ -8,11 +8,11 @@ RUN apt-get update && apt-get install --yes \
 
 RUN adduser --uid 1000 --gecos '' --disabled-password linky
 
-ENV POSTGRES_HOST=localhost
+ENV POSTGRES_HOST=host.docker.internal
 ENV POSTGRES_PORT=5432
 ENV POSTGRES_DB=postgres
 ENV POSTGRES_USER=postgres
-ENV POSTGRES_PASSWORD=******
+ENV POSTGRES_PASSWORD=w4qu+0sj
 
 WORKDIR /home/link-liveliness-assessment
 
@@ -34,6 +34,4 @@ WORKDIR /home/link-liveliness-assessment/src
 
 EXPOSE 8000
 
-USER linky
-
-ENTRYPOINT [ "python3", "-m", "uvicorn", "api:app", "--reload", "--host", "0.0.0.0", "--port", "8000" ]
+USER linky

docker-compose.yml

@@ -0,0 +1,16 @@
+services:
+  linkchecker:
+    build:
+      context: .
+      dockerfile: Dockerfile
+    container_name: linkchecker
+    command: python linkchecker.py
+  api:
+    build:
+      context: .
+      dockerfile: Dockerfile
+    command: python api.py
+    ports:
+      - "8000:8000"
+    depends_on:
+      - linkchecker

requirements.txt

@@ -5,4 +5,5 @@ pydantic
 uvicorn
 pandas
 asyncpg
+linkchecker
 databases

src/linkchecker.py

@@ -104,8 +104,11 @@ def run_linkchecker(urls):
     for url in urls:
         # Run LinkChecker Docker command with specified user and group IDs for each URL
         process = subprocess.Popen([
-            "docker", "run", "--rm", "-i", "-u", "1000:1000", "ghcr.io/linkchecker/linkchecker:latest", 
-            "--verbose", "--check-extern", "--recursion-level=1",  "--output=csv",
+           "linkchecker",
+            "--verbose",
+            "--check-extern",
+            "--recursion-level=1",
+            "--output=csv",
             url + "?f=html"
         ], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
 
@@ -123,7 +126,6 @@ def main():
 
     print("Time started processing links.")
     print("Loading EJP SOIL Catalogue links...")
-    filename = "soil_catalogue_link.csv"
     total_pages, numbers_returned = get_pagination_info(ejp_catalogue_json_url)
 
     # Base URL
@@ -147,10 +149,6 @@ def main():
 
     # Filter out links with the specified formats
     filtered_links = {link for link in all_links if not any(format_to_remove in link for format_to_remove in formats_to_remove)}
-
-    # Remove the existing file if it exists
-    if os.path.exists(filename):
-        os.remove(filename)
 
     # Specify the fields to include in the CSV file
     fields_to_include = ['urlname', 'parentname', 'baseref', 'valid', 'result', 'warning', 'info', 'url', 'name']