Mein feature 062 Abzucht Pegel

base_images/flask_monitor/requirements.txt

@@ -1,13 +1,3 @@
 flask==3.0.0
-blinker==1.9.0
-certifi==2025.8.3
-charset-normalizer==3.4.3
-click==8.2.1
-idna==3.10
-itsdangerous==2.2.0
-Jinja2==3.1.6
-MarkupSafe==3.0.2
-pillow==11.3.0
-requests==2.32.5
-urllib3==2.5.0
-Werkzeug==3.1.3
+Jinja2==3.1.2
+requests==2.32.4

compose.dev.yaml

@@ -119,6 +119,13 @@ services:
     container_name: gs_compiler_035_talsperren
     restart: unless-stopped
 
+  gs_compiler_062_abzucht_oker:
+    build: ./docker_instances/gs_compiler_062_abzucht_oker
+    volumes:
+      - ./httpdocs/crawler:/app/output
+    container_name: gs_compiler_062_abzucht_oker
+    restart: unless-stopped
+
   # === EDUCATION CRAWLER ===
   gs_compiler_050_tschuessschule_studium:
     build: ./docker_instances/050_tschuessschule_studium

compose.yaml

@@ -184,10 +184,6 @@ services:
       - ./httpdocs/crawler:/app/output
     container_name: gs_compiler_056_serviceportal
     restart: unless-stopped
-  gs_compiler_068_serviceportal:
-    image: ghcr.io/machmitgoslar/gs_crawler_068_altstadtfest:latest
-    container_name: gs_compiler_068_altstadtfest
-    restart: unless-stopped
 
 # Gemeinsames Volume für alle Output-Dateien
 volumes:

docker_instances/000_health_monitor/app.py

@@ -173,13 +173,6 @@
         'source': 'https://service.goslar.de/home',
         'schedule': 'Täglich 09:00',
         'type': 'Service Portal'
-    },
-    'gs_compiler_068_altstadtfest': {
-        'name': 'Altstadtfest Goslar',
-        'expected_files': [],
-        'source': 'https://meingoslar.de/',
-        'schedule': 'API Endpoint',
-        'type': 'API Endpoint'
     }
 }
 

docker_instances/044_wiedelah/script.py

@@ -6,38 +6,54 @@
 import os
 
 # URL der Quelle
-url = "https://dg-wiedelah.de/category/berichte-von-veranstaltungen/"
+url = "https://dg-wiedelah.de/category/arbeitseinsaetze/"
 
 # Anfrage und HTML parsen
 response = requests.get(url)
 soup = BeautifulSoup(response.text, "html.parser")
 
 # Alle Einträge finden
-container = soup.find("div", id="main-content")
-widget = container.find("div", class_="post-listing") if container else None
-li_tags = widget.find_all("article") if widget else []
+container = soup.find("div", id="categort-posts-widget-5")
+widget = container.find("div", class_="widget-container") if container else None
+ul = widget.find("ul") if widget else None
+li_tags = ul.find_all("li") if ul else []
 
 entries = []
 for index, li in enumerate(li_tags):
-    div = li.find("h2")
+    div = li.find("div")
     a_tag = div.find("a", href=True) if div else None
-    call_to_action_url = a_tag["href"] if a_tag else "https://dg-wiedelah.de/"
+    call_to_action_url = a_tag["href"] if a_tag else ""
 
     img_tag = a_tag.find("img") if a_tag else None
     image_url = img_tag["src"] if img_tag else ""
 
-    div_beschreibung = li.find("div", class_="entry") if div else None
+    h3 = li.find("h3") if div else None
 
-    p_tag = div_beschreibung.find("p") if div else None
-    description = p_tag.get_text(strip=True) if p_tag else ""
+    a_tag = h3.find("a") if div else None
+    description = a_tag.get_text(strip=True) if a_tag else ""
 
     # call_to_action_url = a_tag["href"] if a_tag else ""
 
     span_tag = li.find("span", class_="tie-date")
     date_text = span_tag.get_text(strip=True) if span_tag else ""
 
-    # Datum leer
-    published_at = ""
+    # Datum umwandeln in datetime-Objekt (mit deutschem Format)
+    try:
+        date_obj = datetime.strptime(date_text, "%d. %B %Y")
+    except ValueError:
+        # Fallback für Monatsnamen (z. B. Juni) ins Englische konvertieren
+        month_map = {
+            "Januar": "January", "Februar": "February", "März": "March",
+            "April": "April", "Mai": "May", "Juni": "June",
+            "Juli": "July", "August": "August", "September": "September",
+            "Oktober": "October", "November": "November", "Dezember": "December"
+        }
+        for de, en in month_map.items():
+            date_text = date_text.replace(de, en)
+        date_obj = datetime.strptime(date_text, "%d. %B %Y")
+
+    # Datum ins Format yyyy-mm-ddThh:00 umwandeln
+    published_at = date_obj.strftime("%Y-%m-%dT%H:00")
 
     entry = {
         "id": index,
@@ -54,8 +70,7 @@
 
 # Zufälligen Eintrag speichern
 if entries:
-    # zufall = random.choice(entries)
-    zufall = entries[0]
+    zufall = random.choice(entries)
     with open("output/044-wiedelah.json", "w", encoding="utf-8") as f:
         json.dump(zufall, f, ensure_ascii=False, indent=2)
     print(zufall)
@@ -64,4 +79,3 @@
         json.dump(entries, f, ensure_ascii=False, indent=2)
 else:
     print("❌ Keine Arbeitseinsätze gefunden.")
-

docker_instances/062_abzucht_oker/Dockerfile

@@ -0,0 +1,12 @@
+# Migriert zu Base-Image für bessere Wartbarkeit
+FROM ghcr.io/machmitgoslar/gs_crawler_python_basic_crawler:latest
+
+# Kopiere container-spezifische Dateien
+COPY script.py .
+COPY crontab /etc/cron.d/mycron
+
+
+
+# Konfiguriere Cron
+RUN chmod 0600 /etc/cron.d/mycron && \
+    crontab /etc/cron.d/mycron

docker_instances/062_abzucht_oker/crontab

@@ -0,0 +1,8 @@
+# ┌───────────── Minute (0 - 59)
+# │ ┌───────────── Hour (0 - 23)
+# │ │ ┌───────────── Day of month (1 - 31)
+# │ │ │ ┌───────────── Month (1 - 12)
+# │ │ │ │ ┌───────────── Day of week (0 - 6) (Sunday to Saturday)
+# │ │ │ │ │
+# │ │ │ │ │
+0 */6 * * * cd /app ; .venv/bin/python3 /app/script.py >> /proc/1/fd/1