strip_gutenberg_linebreaks.py

#!/usr/bin/env python

# You may need to set the environment variable to output utf-8.
# On Windows, the command is: set PYTHONIOENCODING=utf-8
# Or, more sensibly, you could rewrite this to write directly 
# to a file rather than stdout

import sys
for line in open(sys.argv[1], mode='r', encoding="utf-8"):
    if line.strip()=='':
        print('\n')
    else:
        if line.isupper():
            print(line, sep='', end='')
        else:
            if line[:1]=="*":
                print(line, sep='', end='')
            else:
                print((line.rstrip()), end=' ')