parse-theinternetarchive-ocr-pages.py | takes a text and a page info json files and prints tag-separated pages

parse-theinternetarchive-ocr-pages.py

# Example: https://archive.org/details/style-lessons-in-clarity-and-grace-12th-edition-pdf-ebook
import json, sys

page_ranges, text = json.load(open(sys.argv[2])), open(sys.argv[1]).read()

chapters = []
current_chapter_name = None
current_chapter_pages = []
chapter_number = 0

for page_number, page_range in enumerate(page_ranges):
    page_text = text[page_range[0] : page_range[1]]
    page_lines = page_text.split("\n")
    chapter_name = page_lines[0]
    
    if chapter_name != current_chapter_name:
        # New chapter detected - save previous chapter if it exists
        if current_chapter_name is not None:
            chapter_content = "\n\n".join(current_chapter_pages)
            chapters.append(f"<Chapter {chapter_number}: {current_chapter_name!r}>\n{chapter_content}\n</Chapter {chapter_number}: {current_chapter_name!r}>")
        
        # Start new chapter
        chapter_number += 1
        current_chapter_name = chapter_name
        current_chapter_pages = []
    
    # Add current page to the current chapter (excluding chapter name from content)
    page_content_without_chapter = "\n".join(page_lines[1:])
    page_content = f"<Page {page_number + 1}>\n{page_content_without_chapter}</Page {page_number + 1}>"
    current_chapter_pages.append(page_content)

# Last chapter
if current_chapter_name is not None:
    chapter_content = "\n\n".join(current_chapter_pages)
    chapters.append(f"<Chapter {chapter_number}: {current_chapter_name!r}>\n{chapter_content}\n</Chapter {chapter_number}: {current_chapter_name!r}>")

print("\n\n".join(chapters))