Upload 2 files

app.py

@@ -0,0 +1,22 @@
+import tabula
+import pandas as pd
+import streamlit as st
+
+st.title("TableOCR")
+
+with st.form(key='my_form'):
+    file = st.file_uploader("Upload a file", type="pdf", accept_multiple_files=False)
+    page_no = st.number_input("Enter page number", min_value=1, value=1)
+    submit_button = st.form_submit_button(label='Submit')
+
+    if submit_button and file is not None and page_no is not None:
+        with st.spinner("Converting PDF page to image..."):
+            tables = tabula.read_pdf(file, pages=page_no, multiple_tables=True)
+            table_df = tables[0] if tables else pd.DataFrame()
+            st.write("Scroll down to download the output file.")
+            st.table(table_df)
+            table_df.to_excel("output.xlsx", index=False)
+            st.markdown(
+                f'<a href="output.xlsx" download="output.xlsx">Click here to download the output file</a>',
+                unsafe_allow_html=True
+            )

requirements.txt

@@ -0,0 +1,49 @@
+altair==5.2.0
+attrs==23.2.0
+blinker==1.7.0
+cachetools==5.3.3
+certifi==2024.2.2
+charset-normalizer==3.3.2
+click==8.1.7
+distro==1.9.0
+et-xmlfile==1.1.0
+gitdb==4.0.11
+GitPython==3.1.42
+idna==3.6
+importlib-metadata==7.0.1
+Jinja2==3.1.3
+jsonschema==4.21.1
+jsonschema-specifications==2023.12.1
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+mdurl==0.1.2
+numpy==1.26.4
+openpyxl==3.1.2
+packaging==23.2
+pandas==2.2.1
+pillow==10.2.0
+protobuf==4.25.3
+pyarrow==15.0.0
+pydeck==0.8.1b0
+Pygments==2.17.2
+python-dateutil==2.9.0.post0
+pytz==2024.1
+referencing==0.33.0
+requests==2.31.0
+rich==13.7.1
+rpds-py==0.18.0
+six==1.16.0
+smmap==5.0.1
+streamlit==1.31.1
+tabula-py==2.9.0
+tenacity==8.2.3
+toml==0.10.2
+toolz==0.12.1
+tornado==6.4
+typing_extensions==4.10.0
+tzdata==2024.1
+tzlocal==5.2
+urllib3==2.2.1
+validators==0.22.0
+watchdog==4.0.0
+zipp==3.17.0