PdfToText / app.py
PirateXX's picture
Update app.py
2fae4f3
raw
history blame contribute delete
935 Bytes
from flask import Flask, request
from torch import cuda
import torch
import gradio as gr
import pdfplumber
app = Flask(__name__)
# function to break text into an array of sentences
def upload_file(file):
if file:
pdf_file = file.name
text = ""
with pdfplumber.open(pdf_file) as pdf:
cnt = 0
for page in pdf.pages:
cnt+=1
text+=(page.extract_text(x_tolerance = 1))
if cnt>5:
break
text = text.replace('\n', ' ')
return {"text": text}
else:
return {"error":'No PDF file found in request'}
demo = gr.Interface(
fn=upload_file,
inputs=gr.File(),
article = "Implemented in <a href = \"https://ai-content-detector.online/\">AI Content Detector</a>",
outputs=gr.outputs.JSON(),
interpretation="default",)
demo.launch(show_api=False)