diff --git a/validator/requirements.txt b/validator/requirements.txt
index f565733..fe30b93 100644
--- a/validator/requirements.txt
+++ b/validator/requirements.txt
@@ -9,6 +9,8 @@ Jinja2==2.11.2
 joblib==1.0.0
 MarkupSafe==1.1.1
 nltk==3.5
+pdftotext==2.1.5
+PyPDF2==1.26.0
 regex==2020.11.13
 requests==2.25.1
 retrying==1.3.3
diff --git a/validator/server.py b/validator/server.py
index 46e4940..bad18ef 100644
--- a/validator/server.py
+++ b/validator/server.py
@@ -1,4 +1,4 @@
-from flask import Flask, render_template, request
+from flask import Flask, render_template, request, jsonify
 import json
 import validator
 
diff --git a/validator/validator.py b/validator/validator.py
index f3dffe2..c4620c8 100644
--- a/validator/validator.py
+++ b/validator/validator.py
@@ -1,14 +1,29 @@
+import os
+import pdftotext
+
 def process_jpg(f):
     pass
 
 def process_pdf(f):
-    pass
+    pdf = pdftotext.PDF(f)
+    aggregate = "\n\n".join(pdf)
+    return aggregate
 
 def process_docx(f):
     pass
 
 def process_file(f):
-    pass
+    # TODO proper file format distinguishing, not only by suffix?
+    _, ext = os.path.splitext(f.filename)
+    print(ext)
+    if ext == '.jpg':
+        return process_jpg(f)
+    elif ext == '.pdf':
+        return process_pdf(f)
+    elif ext == '.docx':
+        return process_docx(f)
+
+    
 
 def validate_court(lawsuit):
     pass