# Extract the title from the next line
title = next(infile)[7:]
# Skip three metadata lines and the blank line separator
next(infile); next(infile); next(infile); next(infile)
elif (line[0] == "#"): # Handle linkposts
title = line.split("](")[0][2:]
else: # Handle original articles
title = line
next(infile)
# Write opening HTML tags and title to output file
outfile.write(f"{template[0]}\n<article>\n<h2>{title}</h2>\n")
continue
# Parse Markdown line into HTML
html_line = md.html(line)
# Strip out all HTML tags from line, to leave only content.
text_line = unescape(sub(r"(\<[^\>]+\>)", "", html_line))
# Increase the paragraph count
if (len(line) != 0):
if (line[0] != "#"):
paragraph_count += 1
# Tokenize paragraph by splitting into individual words.
tokens = resplit(r"\W",text_line)
# Extract unique words in sentence.
tokens_set = frozenset(tokens)
