File size: 1,770 Bytes
17dc25e | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 | import streamlit as st # data app development
import subprocess # process in the os
from subprocess import STDOUT, check_call #os process manipulation
import os #os proces manipulation
import base64 # byte object into a pdf file
import camelot as cam # extracting tables from PDFs
# to run this only once it's cached
@st.cache
def gh():
""" install ghostscript on the linux machine"""
proc = subprocess.Popen('apt-get install -y ghostscript', shell=True, stdin=None, stdout=open(os.devnull, "wb",), stderr=STDOUT, executable="/bin/bash")
proc.wait()
gh()
st.title("PDF Table Extractor")
st.subheader("with `Camelot` python library")
st.image("https://raw.githubusercontent.com/camelot-dev/camelot/master/docs/_static/camelot.png", width=200)
# file uploader on streamlit
input_pdf = st.file_uploader(label = "upload your pdf here", type = 'pdf')
st.markdown("### Page Number")
page_number = st.text_input("Enter the page # from where you want to extract the PDF eg: 3", value = 1)
# run this only when the pdf is uploaded
if input_pdf is not None:
#byte object into a PDF file
with open("input.pdf", "wb") as f:
base64_pdf = base64.b64encode(input_pdf.read()).decode('utf-8')
f.write(base64.b64encode(base64_pdf))
f.close()
# read the pdf and parse it using stream
table = cam.read_pdf("input.pdf", pages=page_number, flavor='stream')
st.markdown("### Number of Tables")
# display the output of the table
st.write(table)
# display the table
if len(table) > 0:
# extract the index value of the table
option = st.selectbox(label="Select the table to be displayed", options = range(len(table) + 1))
st.markdown('### Output Table')
# display the dataframe
st.dataframe(table[int(option)-1].df) |