Skip to content


Subversion checkout URL

You can clone with
Download ZIP
Branch: master
Fetching contributors…

Cannot retrieve contributors at this time

45 lines (38 sloc) 1.441 kB
import sys, re
# parse options
options = dict(zip(sys.argv[1::2],sys.argv[2::2]))
# read entry
doc = data =
# Apply a sequence of patterns which turn a normalized Atom entry into
# a stream of text, after removal of non-human metadata.
for pattern,replacement in [
(re.compile('<id>.*?</id>'),' '),
(re.compile('<url>.*?</url>'),' '),
(re.compile('<source>.*?</source>'),' '),
(re.compile('<updated.*?</updated>'),' '),
(re.compile('<published.*?</published>'),' '),
(re.compile('<link .*?>'),' '),
(re.compile('''<[^>]* alt=['"]([^'"]*)['"].*?>'''),r' \1 '),
(re.compile('''<[^>]* title=['"]([^'"]*)['"].*?>'''),r' \1 '),
(re.compile('''<[^>]* label=['"]([^'"]*)['"].*?>'''),r' \1 '),
(re.compile('''<[^>]* term=['"]([^'"]*)['"].*?>'''),r' \1 '),
(re.compile('<.*?>'),' '),
(re.compile('\s+'),' '),
(re.compile('\s+'),' ')
# process requirements
if options.has_key('--require'):
for regexp in options['--require'].split('\n'):
if regexp and not,data): sys.exit(1)
# process exclusions
if options.has_key('--exclude'):
for regexp in options['--exclude'].split('\n'):
if regexp and,data): sys.exit(1)
# if we get this far, the feed is to be included
print doc
Jump to Line
Something went wrong with that request. Please try again.