Update extract_resume_content.py

extract_resume_content.py

@@ -1,14 +1,11 @@
-import pdfplumber
+import re
 from docx import Document
+import pdfplumber
 from bs4 import BeautifulSoup
-import os
-import re
 
 def extract_text_from_pdf(file):
     with pdfplumber.open(file) as pdf:
-        return "\n".join(
-            page.extract_text() for page in pdf.pages if page.extract_text()
-        )
+        return "\n".join(page.extract_text() for page in pdf.pages if page.extract_text())
 
 def extract_text_from_docx(file):
     doc = Document(file)
@@ -34,20 +31,13 @@ def extract_resume_text(file, file_type):
         return ""
 
 def extract_fields_from_text(text):
-    # Extract email
     email_match = re.search(r'[\w\.-]+@[\w\.-]+', text)
-    email = email_match.group() if email_match else "Not found"
-
-    # Extract phone number
     phone_match = re.search(r'(\+?\d{1,3})?[\s\-]?\(?\d{2,4}\)?[\s\-]?\d{3,4}[\s\-]?\d{3,4}', text)
-    phone = phone_match.group() if phone_match else "Not found"
-
-    # Try to find a name (optional heuristic - first line of text)
     lines = text.strip().split("\n")
     name = lines[0] if lines and len(lines[0].split()) <= 4 else "Not found"
 
     return {
         "name": name,
-        "email": email,
-        "phone": phone,
+        "email": email_match.group() if email_match else "Not found",
+        "phone": phone_match.group() if phone_match else "Not found"
     }