WP-Footnotes to Markdown footnotes.

WPFootnotesToMarkdown.py

from sys import argv
import re

name, file_path = argv

p = re.compile(r"[\s]\(\((.*?[)]{0,1})\)\)[\s]{0,1}")
# The tricky part here is to match all text between (()), including as many as
# one set of (), which may even terminate ))). The {0,1} captures as many as
# one ). The trailing space is there because I often surrounded the (()) with
# a space to make it clear in the Wordpress editor.

# file_path = str(raw_input('File Name >'))
text = open(file_path).read()

footnoteMatches = p.finditer(text)

coordinates = []
footnotes = []

# Print span of matches
for match in footnoteMatches:
    coordinates.append(match.span())
# Capture only group(1) so you get the content of the footnote, not the whole
# pattern which includes the parenthesis delimiter.
    footnotes.append(match.group(1))

newText = []
for i in range(0, len(coordinates)):
    if i == 0:
        newText.append(''.join(text[:coordinates[i][0]] + 
                               ' [^{}]').format(i + 1))
    elif i < len(coordinates) - 1 :
        newText.append(''.join(text[coordinates[i-1][1]:coordinates[i][0]] + 
                          ' [^{}]').format(i + 1))
    else:
        newText.append(''.join(text[coordinates[i-1][1]:coordinates[i][0]] + 
                          ' [^{}]').format(i + 1))
        # Accounts for text after the last footnote which only runs once.
        newText.append(text[coordinates[i][1]:]+'\n')

endNotes = []
for j in range(0, len(footnotes)):
    insertList = ''.join(['\n','[^{}]: ', footnotes[j], '\n']).format(j + 1)
    endNotes.append(insertList)


newText = ''.join(newText) + '\n' + ''.join(endNotes)

newFile = open(file_path, 'w')
newFile.truncate()
newFile.write(newText)
newFile.close()