Upload 2 files

app.py

@@ -8,6 +8,7 @@ import os
 from tabula import read_pdf
 import pandas as pd
 import gdown
+import camelot
 
 
 if os.path.exists('prediction') and os.path.isdir('prediction'):
@@ -48,7 +49,7 @@ def main():
 
 
         inputpath = "temp//temp.pdf"
-        outputpath = "temp_pdf"
+        outputpath = ""
         with st.spinner('Converting pdf to images...'):
             result = pdf2jpg.convert_pdf2jpg(inputpath,outputpath, pages="ALL")
 
@@ -65,11 +66,18 @@ def main():
         st.markdown('### Extracted data from tables')
         
         with st.spinner('Performing OCR on tables to extract images...'):
-            tables = read_pdf(inputpath, pages='all', multiple_tables=True)
+            # Extract tables from the PDF
+            tables = camelot.read_pdf(inputpath, pages='all', flavor='stream')
+
+            # Print the tables or convert them to a different format like CSV
             for i, table in enumerate(tables):
-                print(f"Table {i+1}")
-                print(table)
-                st.dataframe(table)
+                st.dataframe(table.df)
+                # table.to_csv(f'table_{i}.csv') # Save to CSV
+            # tables = read_pdf(inputpath, pages='all', multiple_tables=True)
+            # for i, table in enumerate(tables):
+            #     print(f"Table {i+1}")
+            #     print(table)
+            #     st.dataframe(table)
 
         st.success('Processing Completed!')
 

requirements.txt

@@ -2,4 +2,6 @@ streamlit==1.25.0
 ultralytics
 pdf2jpg
 tabula-py[jpype]
-gdown
+gdown
+camelot-py[cv]
+PyPDF2<3.0