# Run this command on command prompt in your python folder 'pip install tabula-py', it will install Tabula Library
# Run this code to convert PDF to CSV
import tabula
tabula.convert_into("yourpdf.pdf", "output.csv", output_format="csv", pages='all')
import tabula
# Read pdf into list of DataFrame
df = tabula.read_pdf("test.pdf", pages='all')
# Read remote pdf into list of DataFrame
df2 = tabula.read_pdf("https://github.com/tabulapdf/tabula-java/raw/master/src/test/resources/technology/tabula/arabic.pdf")
# convert PDF into CSV file
tabula.convert_into("test.pdf", "output.csv", output_format="csv", pages='all')
# convert all PDFs in a directory
tabula.convert_into_by_batch("input_directory", output_format='csv', pages='all')
pytesseract.pytesseract.tesseract_cmd = r"C:\Program Files (x86)\Tesseract-OCR\tesseract.exe"
import pandas as pd
from PIL import Image
import pytesseract
import io
from wand.image import Image as wand
pd.set_option('max_colwidth', 2000)
pd.options.display.max_rows = 500