Bump version to v1.5.3

utils/article_extractor.py

@@ -0,0 +1,27 @@
+# utils/article_extractor.py
+
+import requests
+from bs4 import BeautifulSoup
+
+def extract_full_article(url: str) -> str:
+    try:
+        response = requests.get(url, timeout=10)
+        response.raise_for_status()
+        soup = BeautifulSoup(response.text, "html.parser")
+
+        # Promobil & WordPress & allgemeine Fallbacks
+        candidates = [
+            {"tag": "div", "class_": "article__text"},     # Promobil
+            {"tag": "div", "class_": "entry-content"},     # WordPress Standard
+            {"tag": "article", "class_": None},            # Generisch
+        ]
+
+        for selector in candidates:
+            el = soup.find(selector["tag"], class_=selector["class_"])
+            if el and len(el.get_text(strip=True).split()) > 50:
+                return el.get_text(" ", strip=True)
+
+        # Fallback: ganzer Seiteninhalt
+        return soup.get_text(" ", strip=True)
+    except Exception:
+        return ""

utils/article_utils.py

@@ -0,0 +1,23 @@
+# utils/article_utils.py
+
+import hashlib
+
+def clean_text(text: str) -> str:
+    return text.strip()
+
+def generate_id(link: str) -> str:
+    return hashlib.md5(link.encode("utf-8")).hexdigest()
+
+def categorize_article(text: str) -> str:
+    # Dummy-Kategorie
+    return "Allgemein"
+
+def tag_article(text: str) -> list:
+    # Dummy-Tags
+    return ["tag1", "tag2"]
+
+def summarize_text(text: str) -> str:
+    return text[:200] + "..."
+
+def rewrite_text(text: str) -> str:
+    return text  # Platzhalter, z. B. für GPT-Rewrite später