Extracting Datatable in a PDF

Help Activities
, ,
7

I have done this by using python in the past.

from tabula import read_pdf
import pandas as pd
import os

# Path to your PDF file
pdf_path = 'INPUT'

# Define your static output folder
output_folder = 'OUTPUTFOLDER'

# Check if the output folder exists, create it if it doesn't
if not os.path.exists(output_folder):
    os.makedirs(output_folder)

# Use read_pdf function with pages="all" to extract tables from all pages
tables = read_pdf(pdf_path, pages="all", multiple_tables=True)

# Iterate over each table (DataFrame) and process or save it
for i, table in enumerate(tables):
    # Define the path for each output CSV file within the output folder
    output_path = os.path.join(output_folder, f"FILENAME_{i+1}.csv")
    # Save each table to a CSV file in the specified output folder
    table.to_csv(output_path, index=False)from tabula import read_pdf
import pandas as pd
import os

# Path to your PDF file
pdf_path = 'INPUT'

# Define your static output folder
output_folder = 'OUTPUTFOLDER'

# Check if the output folder exists, create it if it doesn't
if not os.path.exists(output_folder):
    os.makedirs(output_folder)

# Use read_pdf function with pages="all" to extract tables from all pages
tables = read_pdf(pdf_path, pages="all", multiple_tables=True)

# Iterate over each table (DataFrame) and process or save it
for i, table in enumerate(tables):
    # Define the path for each output CSV file within the output folder
    output_path = os.path.join(output_folder, f"FILENAME_{i+1}.csv")
    # Save each table to a CSV file in the specified output folder
    table.to_csv(output_path, index=False)