add-api-extract-pdf-content

app.py

@@ -2,6 +2,8 @@ from flask import Flask, request, jsonify
 import requests
 from bs4 import BeautifulSoup
 from DuckDuckGo import search_duckduckgo
+from PdfExtract import process_pdf, process_uploaded_pdf
+
 app = Flask(__name__)
 
 
@@ -14,6 +16,41 @@ def search():
     results = search_duckduckgo(query)
     return jsonify(results)
 
+# ================= API 1: Extract from URL =================
+@app.route("/extract", methods=["POST"])
+def extract():
+    try:
+        data = request.get_json()
+        if not data or "url" not in data:
+            return jsonify({"error": "Missing URL"}), 400
+
+        result = process_pdf(data["url"])
+        return jsonify(result)
+
+    except Exception as e:
+        return jsonify({"error": str(e)}), 400
+
+
+# ================= API 2: Upload file =================
+@app.route("/upload", methods=["POST"])
+def upload():
+    try:
+        if "file" not in request.files:
+            return jsonify({"error": "No file field"}), 400
+
+        file = request.files["file"]
+
+        if file.filename == "":
+            return jsonify({"error": "No selected file"}), 400
+
+        file_bytes = file.read()
+
+        result = process_uploaded_pdf(file_bytes)
+        return jsonify(result)
+
+    except Exception as e:
+        return jsonify({"error": str(e)}), 400
+
 
 if __name__ == "__main__":
-    app.run(debug=True)
+    app.run(host="0.0.0.0", port=8000)