Update app.py

app.py

@@ -15,6 +15,7 @@ tokenizer = RobertaTokenizer.from_pretrained(model_name, map_location=torch.devi
 
 # function to break text into an array of sentences
 def text_to_sentences(text):
+    re.sub(r'(?<=[.!?])(?=[^\s])', r' ', text)
     return re.split(r'[.!?]', text)
 
 # function to concatenate sentences into chunks of size 600 or less
@@ -59,6 +60,25 @@ def findRealProb(text):
     realProb = ans/len(text)
     return {"Real": realProb, "Fake": 1-realProb}, results
 
+@app.route('/upload', methods=['POST'])
+def upload_file():
+    if 'pdfFile' in request.files:
+        pdf_file = request.files['pdfFile']
+        text = ""
+        with pdfplumber.open(pdf_file) as pdf:
+            cnt = 0
+            for page in pdf.pages:
+                cnt+=1
+                text+=(page.extract_text(x_tolerance = 1))
+                print(text)
+                if cnt>5: 
+                    break
+            return findRealProb(text)
+            # return jsonify({'text': text})
+    else:
+        return {"error":'No PDF file found in request'}
+
+
 demo = gr.Interface(
         fn=findRealProb, 
         inputs=gr.Textbox(placeholder="Copy and paste here..."),