Changes

app.py

@@ -5,6 +5,7 @@ import json
 from typing_extensions import Annotated
 
 #SkillExtraction Packages
+import PyPDF2
 from PyPDF2 import PdfReader
 import psycopg2
 from psycopg2 import sql
@@ -25,6 +26,8 @@ register_adapter(np.int64, AsIs)
 import warnings
 warnings.filterwarnings('ignore')
 
+from io import BytesIO
+import requests
 #Custom Classes for endpoints
 from DbConnection import DbConnection
 from UploadFile import UploadOpenFile
@@ -113,15 +116,26 @@ def upload_PDF(file: UploadFile = File(...)):
     return {"message": f"Successfully uploaded {contents}"}
 
 @app.post("/uploadJobDescriptionPDF2/")
-def upload_PDF2(file: UploadFile = File(...)):
-    text =''
+def process_pdf_file(file: UploadFile = File(...)):
+    # Save file locally for processing
+    contents = file.read()
+    with open(file.filename, 'wb') as f:
+        f.write(contents)
     
-    if file.filename.endswith("pdf"):
-        pdf_reader = PdfReader(file)
-            
-        for page in pdf_reader.pages:
-            text += page.extract_text()
-        
-   
+    # Process saved file
+    return process_pdf(file.filename, is_local_file=True)
+
+def process_pdf(pdf_source, is_local_file=False):
+    # Process the PDF from URL or local file
+    file = BytesIO(requests.get(pdf_source).content) if not is_local_file else open(pdf_source, 'rb')
+
+    # Extract text from PDF
+    pdf_reader = PyPDF2.PdfFileReader(file)
+    text = ""
+    for page in range(pdf_reader.numPages):
+        text += pdf_reader.getPage(page).extractText()
+    
+    if is_local_file:
+        file.close()
 
-    return {"message": f"Successfully uploaded {text}"}
+    return {"content": text}