import Kindle "My Clippings.txt" into separate markdown files per author

load_from_clippings.py

import re
import sys
"""

This is a helpful little script for importing your kindle underlines from books.
Because I read multiple books at once, my underlines get mixed up and out of order.
This script untangles my underlines and puts each book into a nice neat markdown file.

Things to be wary of:
- Author names should be adjusted to be 3 words or less (including hyphenations)
- Use Calibre to access your clippings file easily

"""

# pass in the "My Clippings.txt" filepath
clippings_path = sys.argv[1]

with open(clippings_path) as clipping_file:
    lines = clipping_file.readlines()
    for i, line in enumerate(lines):
        # This regex finds the book's author name (Author Name)
        results = re.findall(r"\(((?:.\w*){,3})\)", line)
        # if there is a parenthetical candidate in this line
        if len(results) == 1:
            name = results[0]
            parts = name.split(' ')
            # if the author name is 3 words or less
            if len(parts) <= 3:
                # if the author name has at least 2 capital letters
                if sum(1 for c in name if c.isupper()) >= 2:
                    # if the author name has at least 4 characters
                    if len(name) > 4:
                        # make the filename-- underscores and lowercase
                        name = name.replace(' ', '_').lower()
                        # this regex gets rid of any non-alphanumeric characters except underscores
                        filename = re.sub(r'([^_\w])+', '', name)
                        # this is Kindle clipping markup for the end of a quote
                        if "=====" in lines[i + 4]:
                            # grab the actual underline (they exist as a single line)
                            quote = lines[i + 3]
                            # append the author's file with the new quote
                            with open("output/" + filename + ".md",
                                      'a') as output_file:
                                output_file.write('==========\n')
                                output_file.write(quote)
                                title = re.sub(r"(\((?:.\w*){,3}\))", '', line)
                                output_file.write(title)
                                output_file.write(lines[i + 1])
                                output_file.write('\n\n')