Table extract PDF2CSV
Jump to navigation
Jump to search
Astuce pour convertir correctement des tableaux PDF à CSV
import camelot # Use the 'file_path' variable to specify the path to your PDF file_path = '/home/noname/Downloads/liste_nationale_internet_310719.pdf' # Extract tables from the PDF tables = camelot.read_pdf(file_path, pages='all', flavor='stream') for i, table in enumerate(tables): # Convert table to DataFrame df = table.df # Define CSV file path, unique for each table csv_file_path = f'table_{i}.csv' # Export the DataFrame to a CSV file df.to_csv(csv_file_path, index=False)