Update app.py

app.py

@@ -55,27 +55,35 @@ def extract_metadata(pdf_path):
         metadata = pdf.metadata or {}
         first_page_text = pdf.pages[0].extract_text() if pdf.pages else ""
 
-        # Extract title
-        title = metadata.get("Title", "").strip()
-        if not title and first_page_text:
-            title_match = re.search(r"(?i)title[:\-]?\s*(.*)", first_page_text)
-            title = title_match.group(1) if title_match else first_page_text.split("\n")[0]
+        # Normalize and split first-page text into lines
+        lines = first_page_text.split("\n") if first_page_text else []
 
-        title = title.strip() if title else "Untitled Document"
+        # Extract title (Try multiple strategies)
+        title = metadata.get("Title", "").strip()
+        if not title:
+            for line in lines[:5]:  # Check the first few lines
+                if len(line.strip()) > 5 and not line.isdigit():  # Avoid numbers (page numbers)
+                    title = line.strip()
+                    break
+        title = title if title else "Untitled Document"
 
         # Extract author
         author = metadata.get("Author", "").strip()
-        if not author and first_page_text:
-            author_match = re.search(r"(?i)(?:by|authors?)[:\-]?\s*([\w\s,]+)", first_page_text)
-            author = author_match.group(1) if author_match else "Unknown Author"
+        if not author:
+            for line in lines:
+                author_match = re.search(r"(?i)(?:by|authors?)[:\-]?\s*([\w\s,]+)", line)
+                if author_match:
+                    author = author_match.group(1).strip()
+                    break
+        author = author if author else "Unknown Author"
 
         # Extract emails
-        emails = re.findall(r"[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}", first_page_text)
-        email_str = ", ".join(set(emails)) if emails else "No emails found"
+        emails = set(re.findall(r"[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}", first_page_text))
+        email_str = ", ".join(emails) if emails else "No emails found"
 
         # Extract affiliations
-        affiliations = re.findall(r"(?:Department|Faculty|Institute|University|College|School)\s+[\w\s]+", first_page_text)
-        affiliation_str = ", ".join(set(affiliations)) if affiliations else "No affiliations found"
+        affiliations = set(re.findall(r"(?:Department|Faculty|Institute|University|College|School)\s+[\w\s]+", first_page_text))
+        affiliation_str = ", ".join(affiliations) if affiliations else "No affiliations found"
 
     return title, author, email_str, affiliation_str