Source code for irc.rfc
from __future__ import absolute_import
import re
[docs]def get_pages(filename):
with open(filename) as f:
data = f.read()
return data.split('\x0c')
header_pattern = re.compile(r'^RFC \d+\s+.*\s+(\w+ \d{4})$', re.M)
footer_pattern = re.compile(r'^\w+\s+\w+\s+\[Page \d+\]$', re.M)
[docs]def clean_pages():
return map(remove_header, map(remove_footer, get_pages('rfc2812.txt')))
[docs]def save_clean():
with open('rfc2812-clean.txt', 'w') as f:
map(f.write, clean_pages())
if __name__ == '__main__':
save_clean()