How to Extract Text from the Pdf Document

How to extract text from pdf in Python 3.7

Using tika worked for me!

from tika import parser

rawText = parser.from_file('January2019.pdf')

rawList = rawText['content'].splitlines()

This made it really easy to extract separate each line in the bank statement into a list.

Extract text from pdf file using javascript

here is a nice example of how to use pdf.js for extracting the text:
http://git.macropus.org/2011/11/pdftotext/example/

of course you have to remove a lot of code for your purpose, but it should do it

How to extract text from multiple pdf in a location with specific line and store in Excel?

Tika is one of the Python packages that you can use to extract the data from your PDF files.

In the example below I'm using Tika and regular expressions to extract these five data elements:

• bid no
• end date
• item category
• organisation name
• total quantity

import re as regex
from tika import parser

parse_entire_pdf = parser.from_file('2022251527199.pdf', xmlContent=True)
for key, values in parse_entire_pdf.items():
    if key == 'content':
        bid_number = regex.search(r'(Bid Number:)\W(GEM\W\d{4}\W[A-Z]\W\d+)', values)
        print(bid_number.group(2))
        GEM/2022/B/1916455

        bid_end_date = regex.search(r'(Bid End Date\WTime)\W(\d{2}-\d{2}-\d{4}\W\d{2}:\d{2}:\d{2})', values)
        print(bid_end_date.group(2))
        21-02-2022 15:00:00

        org_name = regex.search(r'(Organisation Name)\W(.*)', values)
        print(org_name.group(2))
        State Election Commission (sec), Gujarat

        item_category = regex.search(r'(Item Category)\W(.*)', values)
        print(item_category.group(2))
        Desktop Computers (Q2) , Computer Printers (Q2)
 
        total_quantity = regex.search(r'(Total Quantity)\W(\d+)', values)
        print(total_quantity.group(2))
        18

Here is one way to write out the extracted data to a CSV file:

import csv
import re as regex
from tika import parser

document_elements = []

# processing 2 documents 
documents = ['202225114747453.pdf', '2022251527199.pdf']
for doc in documents:
    parse_entire_pdf = parser.from_file(doc, xmlContent=True)
    for key, values in parse_entire_pdf.items():
        if key == 'content':
            bid_number = regex.search(r'(Bid Number:)\W(GEM\W\d{4}\W[A-Z]\W\d+)', values)

            bid_end_date = regex.search(r'(Bid End Date\WTime)\W(\d{2}-\d{2}-\d{4}\W\d{2}:\d{2}:\d{2})', values)

            org_name = regex.search(r'(Organisation Name)\W(.*)', values)

            item_category = regex.search(r'(Item Category)\W(.*)', values)

            total_quantity = regex.search(r'(Total Quantity)\W(\d+)', values)
            
            document_elements.append([bid_number.group(2),
                                      bid_end_date.group(2), 
                                      org_name.group(2), 
                                      item_category.group(2),
                                      total_quantity.group(2)])


with open("out.csv", "w", newline="") as f:
    headerList = ['bid_number', 'bid_end_date', 'org_name', 'item_category', 'total_quantity']
    writer = csv.writer(f)
    writer.writerow(headerList)
    writer.writerows(document_elements)

Here is the additional code that you asked for in the comments.

import os
import re as regex
from tika import parser

document_elements = []

image_directory = "pdf_files"
image_directory_abspath = os.path.abspath(image_directory)
for dirpath, dirnames, filenames in os.walk(image_directory_abspath):
    for filename in [f for f in filenames if f.endswith(".pdf")]:
        parse_entire_pdf = parser.from_file(os.path.join(dirpath, filename), xmlContent=True)
        for key, values in parse_entire_pdf.items():
            if key == 'content':
                bid_number = regex.search(r'(Bid Number:)\W(GEM\W\d{4}\W[A-Z]\W\d+)', values)

                bid_end_date = regex.search(r'(Bid End Date\WTime)\W(\d{2}-\d{2}-\d{4}\W\d{2}:\d{2}:\d{2})', values)

                org_name = regex.search(r'(Organisation Name)\W(.*)', values)

                item_category = regex.search(r'(Item Category)\W(.*)', values)

                total_quantity = regex.search(r'(Total Quantity)\W(\d+)', values)

                document_elements.append([bid_number.group(2),
                                          bid_end_date.group(2),
                                          org_name.group(2),
                                          item_category.group(2),
                                          total_quantity.group(2)])

with open("out.csv", "w", newline="") as f:
    headerList = ['bid_number', 'bid_end_date', 'org_name', 'item_category', 'total_quantity']
    writer = csv.writer(f)
    writer.writerow(headerList)
    writer.writerows(document_elements)

SPECIAL NOTE: I noted that some PDFs don't have an org_name, so you will have to figure out how to handle these with either a N/A, None, or Null

How extract text from this compressed PDF/A?

If you want to decompress the streams in a PDF file, I can recommend using qdpf, but on this file

 qpdf --decrypt --stream-data=uncompress document.pdf out.pdf

doesn't help either.

I am not sure though why your efforts with xpdf and tesseract did not work out, using image-magick's convert
to create PNG files in a temporary directory and tesseract, you can do:

import os
from pathlib import Path
from tempfile import TemporaryDirectory
import subprocess

DPI=600

def call(*args):
    cmd = [str(x) for x in args]
    return subprocess.check_output(cmd, stderr=subprocess.STDOUT).decode('utf-8')

def ocr(docpath, lang):
    result = []
    abs_path = Path(docpath).expanduser().resolve()
    old_dir = os.getcwd()
    out = Path('out.txt')
    with TemporaryDirectory() as tmpdir:
         os.chdir(tmpdir)
         call('convert', '-density', DPI, abs_path, 'out.png')
         index = -1
         while True:
             # names have no leading zeros on the digits, would be difficult to sort glob() output
             # so just count them
             index += 1
             png = Path(f'out-{index}.png')
             if not png.exists():
                 break
             call('tesseract', '--dpi', DPI, png, out.stem, '-l', lang)
             result.append(out.read_text())
         os.chdir(old_dir)
    return result

pages = ocr('~/Downloads/document.pdf', 'por')
print('\n'.join(pages[1].splitlines()[21:24]))

which gives:

DA NÃO REALIZAÇÃO DE AUDIÊNCIA DE AUTOCOMPOSIÇÃO NO CASO EM CONCRETO

Com vista a obter maior celeridade processual, assim como da impossibilidade de conciliação entre

If you are on Windows, make sure your PDF file is not open in a different process (like a PDF viewer), as Windows doesn't seem to like that.

The final print is limited as the full output is quite large.

This converting and OCR-ing takes a while so you might want to uncomment the print in call() to get some sense of progress.

---

Related Topics