Converts Pluralsight transcript HTML to Markdown.

html2md.py

"""Converts Pluralsight transcript HTML to Markdown.
"""

from bs4 import BeautifulSoup
import sys

soup = BeautifulSoup(open(sys.argv[1]))

name = soup.find('meta', itemprop='name')['content']
description = soup.find('meta', property='og:description')['content']

print(name)
print('=' * len(name))
print('\n' + description)

lis = soup.find_all('li', class_='transcript-module')

for li in lis:
    title = li.strings.next().strip()
    print('\n' + title)
    print('-' * len(title))

    clips = li.find('ul').find_all('li', class_='transcript-clip')
    for clip in clips:
        it = clip.strings
        sub_title = next(it).strip()
        print('\n**' + sub_title + '**\n')
        print('\n'.join((s for s in it if s.rstrip())))