parse_gutenberg.py

import re
import sys

GUTENBERG_START = re.compile(r'\*\*\*.*START.*PROJECT GUTENBERG')
GUTENBERG_END = re.compile('End of.*Project Gutenberg')

def parse_gutenberg(fp):
    for line in fp:
        if GUTENBERG_START.match(line):
            break
    for line in fp:
        line = line.strip()
        if GUTENBERG_END.match(line):
            break
        elif line:
            yield line

if __name__ == '__main__':
    for line in parse_gutenberg(sys.stdin):
        print line