add pdf to text
Browse files- app.py +15 -5
- requirements.txt +2 -1
app.py
CHANGED
@@ -1,10 +1,20 @@
|
|
1 |
import gradio as gr
|
2 |
from pdf2image import convert_from_path
|
|
|
3 |
|
4 |
-
def
|
5 |
-
|
6 |
-
|
7 |
|
8 |
-
|
9 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
demo.launch(debug=True)
|
|
|
1 |
import gradio as gr
|
2 |
from pdf2image import convert_from_path
|
3 |
+
import pdfplumber
|
4 |
|
5 |
+
def convert_pdf_to_image(file):
|
6 |
+
images = convert_from_path(file)
|
7 |
+
return images
|
8 |
|
9 |
+
def extract_text_from_pdf(file):
|
10 |
+
text = ""
|
11 |
+
with pdfplumber.open(file) as pdf:
|
12 |
+
for page in pdf.pages:
|
13 |
+
text += page.extract_text()
|
14 |
+
return text
|
15 |
+
|
16 |
+
pdf_to_img = gr.Interface(convert_pdf_to_image, gr.File(), gr.Gallery(), api_name="pdf_to_img")
|
17 |
+
pdf_to_text = gr.Interface(extract_text_from_pdf, gr.File(), gr.Textbox(placeholder="Extracted text will appear here"), api_name="pdf_to_text")
|
18 |
+
|
19 |
+
demo = gr.TabbedInterface([pdf_to_img, pdf_to_text], ["PDF to Image", "Extract Text"])
|
20 |
demo.launch(debug=True)
|
requirements.txt
CHANGED
@@ -1,2 +1,3 @@
|
|
1 |
pdf2image
|
2 |
-
gradio
|
|
|
|
1 |
pdf2image
|
2 |
+
gradio
|
3 |
+
pdfplumber
|