moved to asyncd

.gitignore

@@ -6,3 +6,5 @@ __pycache__/
 
 package-lock.json
 package.json
+
+cheatsheet_inventory.json

Dockerfile

@@ -1,10 +1,12 @@
-FROM python:3.12-slim
+FROM python:3.12-alpine
 
 WORKDIR /app
 
+RUN apk add --no-cache curl git libsass
+
 COPY requirements.txt .
 RUN pip install --no-cache-dir -r requirements.txt
 
 COPY . .
 
-CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000"]
+CMD ["python", "src/main.py"]

docker-compose.yml

@@ -1,6 +0,0 @@
-
-services:
-  server_html:
-    build: .
-    ports:
-      - "8000:8000"

requirements.txt

@@ -1,22 +1,32 @@
 annotated-types==0.7.0
+anyio==4.12.1
 blinker==1.9.0
 certifi==2026.1.4
 charset-normalizer==3.4.4
 click==8.3.1
+fastapi==0.115.0
 Flask==3.1.2
+h11==0.16.0
+httpcore==1.0.9
+httptools==0.7.1
+httpx==0.28.1
 idna==3.11
 itsdangerous==2.2.0
 Jinja2==3.1.6
-libsass==0.23.0
 livereload==2.7.1
 MarkupSafe==3.0.3
 pydantic==2.12.5
 pydantic_core==2.41.5
+python-dotenv==1.2.1
+PyYAML==6.0.3
 requests==2.32.5
+starlette==0.38.6
 tornado==6.5.4
 typing-inspection==0.4.2
 typing_extensions==4.15.0
 urllib3==2.6.3
+uvicorn==0.30.1
+uvloop==0.22.1
+watchfiles==1.1.1
+websockets==16.0
 Werkzeug==3.1.5
-fastapi==0.115.0
-uvicorn[standard]==0.30.1

src/build.py

@@ -51,6 +51,7 @@ async def build(trigger_list: list[str] | None = None):
     # Copy to prod
     print("Copying to prod directory...")
     shutil.copytree(OUTPUT_DIR, PROD_DIR, dirs_exist_ok=True)
+    print("Done.")
 
 
 if __name__ == "__main__":

src/inventory.py

@@ -38,6 +38,7 @@ async def prepare_cheatsheets(config: CSInventoryConfig, outdir: str) -> list[CS
                     print("Unknow Source Type:", item.source.type)
         except:
             traceback.print_exc()
+            print("Error processing item:", item)
             new_item = None
 
         if new_items:

src/main.py

@@ -55,5 +55,6 @@ async def trigger_all():
 
 if __name__ == "__main__":
     import uvicorn
-    uvicorn.run("main:app", host="0.0.0.0", port=8000)
+    uvicorn.run(app, host="0.0.0.0", port=8000, log_level="debug")
+
  

src/sources/gitea.py

@@ -1,23 +1,27 @@
 
 from sources import CSSourceGitea, CSItem, CSInventoryItem
 from sources.util import cache_cheatsheet, get_datestring
-import requests
+import httpx
 from pathlib import Path
 
 
 async def process_gitea(item: CSInventoryItem, outdir: str) -> list[CSItem] | None:
     source: CSSourceGitea = item.source
-    commit_hash = get_release_commit_sha(source.base_url, source.owner, source.repo, source.tag)
-    asserts = list_release_assets(source.base_url, source.owner, source.repo, source.tag)
+    commit_hash = await get_release_commit_sha(source.base_url, source.owner, source.repo, source.tag)
+    asserts = await list_release_assets(source.base_url, source.owner, source.repo, source.tag)
     
-    asserts = filter(lambda a: a[1].endswith(".pdf"), asserts)
+    asserts = list(filter(lambda a: a[1].endswith(".pdf"), asserts))
+    asserts = list(map(lambda a: (a[0], f"{source.base_url}/repos/{source.owner}/{source.repo}/releases/download/{source.tag}/{a[0]}"), asserts))
+
+    print(f"Found {len(asserts)} PDF assets in Gitea release {source.owner}/{source.repo}@{source.tag}")
 
     res = []
 
     for a in asserts:
         res_url = a[0]
+
         if item.cache:
-            cache_url = cache_cheatsheet(a[0], outdir)
+            cache_url = await cache_cheatsheet(a[0], outdir)
             if cache_url:
                 res_url = cache_url
             else:
@@ -38,7 +42,7 @@ async def process_gitea(item: CSInventoryItem, outdir: str) -> list[CSItem] | No
 
     return res
 
-def get_release_commit_sha(base_url, owner, repo, tag_name, token=None):
+async def get_release_commit_sha(base_url, owner, repo, tag_name, token=None):
     """
     Resolve the commit SHA for a Gitea release tag.
 
@@ -50,16 +54,15 @@ def get_release_commit_sha(base_url, owner, repo, tag_name, token=None):
     :return: commit SHA (str)
     """
 
+
+    async with httpx.AsyncClient() as client:
         headers = {}
         if token:
             headers["Authorization"] = f"token {token}"
 
-    session = requests.Session()
-    session.headers.update(headers)
-
         # 1) List tags and find the matching tag
         tags_url = f"{base_url}/api/v1/repos/{owner}/{repo}/tags"
-    resp = session.get(tags_url)
+        resp = await client.get(tags_url, headers=headers)
         resp.raise_for_status()
         tags = resp.json()
 
@@ -80,7 +83,7 @@ def get_release_commit_sha(base_url, owner, repo, tag_name, token=None):
             raise RuntimeError("Tag object SHA missing; cannot dereference annotated tag")
 
         git_tag_url = f"{base_url}/api/v1/repos/{owner}/{repo}/git/tags/{tag_obj_sha}"
-    resp = session.get(git_tag_url)
+        resp = await client.get(git_tag_url, headers=headers)
         resp.raise_for_status()
         annotated = resp.json()
 
@@ -92,7 +95,7 @@ def get_release_commit_sha(base_url, owner, repo, tag_name, token=None):
     return target.get("sha")
 
 
-def list_release_assets(base_url, owner, repo, tag, token=None):
+async def list_release_assets(base_url, owner, repo, tag, token=None):
     """
     Return a list of (download_url, filename) for all assets of a Gitea release.
 
@@ -103,15 +106,17 @@ def list_release_assets(base_url, owner, repo, tag, token=None):
     :param token: optional API token
     :returns: list of (download_url, filename) tuples
     """
+
+    async with httpx.AsyncClient() as client:
         headers = {}
         if token:
             headers["Authorization"] = f"token {token}"
 
         # 1) Get release by tag
         rel_url = f"{base_url}/api/v1/repos/{owner}/{repo}/releases/tags/{tag}"
-    rel_resp = requests.get(rel_url, headers=headers)
+        rel_resp = await client.get(rel_url, headers=headers)
         rel_resp.raise_for_status()
-    release = rel_resp.json()
+        release: dict = rel_resp.json()
 
         assets = release.get("assets", [])
         result = []

src/sources/plain.py

@@ -6,7 +6,7 @@ async def process_plain_url(item: CSInventoryItem, outdir: str) -> CSItem | None
     res_url = source.url
 
     if item.cache:
-        cache_url = cache_cheatsheet(source.url, outdir)
+        cache_url = await cache_cheatsheet(source.url, outdir)
         if cache_url:
             res_url = cache_url
         else:

src/sources/util.py

@@ -1,22 +1,32 @@
 import hashlib
-import requests 
+import httpx
 import datetime
 import os
+from pathlib import Path
+from urllib.parse import urlparse
 
 def get_datestring() -> str:
     return datetime.datetime.now().strftime("%d.%m.%y")
 
 
-def cache_cheatsheet(url, outdir: str) -> str | None:
-    r = requests.get(url)
-    if not r.ok and r.headers.get("Content-Type") != "application/pdf":
+async def cache_cheatsheet(url, outdir: str) -> str | None:
+
+    print("Caching cheatsheet from", url)
+
+    try:
+        async with httpx.AsyncClient() as client:
+            r = await client.get(url, timeout=5.0)
+            if not r.is_success and r.headers.get("Content-Type") != "application/pdf":
+                return None 
+    except httpx.TimeoutException:
+        print("Timeout fetching URL:", url)
         return None
 
     data = r.content
 
-    hashdata = hashlib.sha256(data)
+    url_base_name = Path(urlparse(url).path).stem
 
-    filesname = os.path.join("cache", f"{hashdata.hexdigest()}.pdf")
+    filesname = os.path.join("cache", f"{url_base_name}.pdf")
     
     if not os.path.exists(os.path.join(outdir, "cache")):
         os.mkdir(os.path.join(outdir, "cache"))

static/robots.txt

@@ -0,0 +1,4 @@
+User-agent: *
+Disallow: /
+Disallow: /impressum
+Disallow: /cgi-bin/