combining_hocr.py

# -*- coding: utf-8 -*-
"""combining_hocr.ipynb

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/drive/18aFAo3c27m7yDneiaCTDPuZLDol0H6Z2
"""

from bs4 import BeautifulSoup

def combine_hocr_files(hocr_files):
    combined_hocr = BeautifulSoup(features="xml")

    for hocr_file in hocr_files:
        with open(hocr_file, "r", encoding="utf-8") as file:
            hocr_content = file.read()
            soup = BeautifulSoup(hocr_content, "html.parser")

            # Append the contents of the current hOCR document to the combined document
            for tag in soup.find_all(recursive=False):
                combined_hocr.append(tag)

    return combined_hocr

# List of hOCR files to combine
hocr_files = ["/content/OCR-D-HOCR_142440_page_1.xml", "/content/OCR-D-HOCR_142440_page_2.xml", "/content/OCR-D-HOCR_142440_page_3.xml","/content/OCR-D-HOCR_142440_page_4.xml"]

# Combine the hOCR files
combined_hocr = combine_hocr_files(hocr_files)

# Write the combined hOCR document to a file
with open("combined_hocr.hocr", "w", encoding="utf-8") as combined_file:
    combined_file.write(str(combined_hocr))