since things like fetching URLs involves lots of latency, a modest number of threads is expected to improve throughput.
31 lines
806 B
Text
31 lines
806 B
Text
|
|
#python -*- coding: utf-8 -*-
|
|
|
|
# This file is offered under the CC0 1.0 Universal (CC0 1.0) Public Domain
|
|
# Dedication http://creativecommons.org/publicdomain/zero/1.0/
|
|
|
|
# furss will be very slow if it is run with the default
|
|
# cacher, so use memcache
|
|
cacher = lambda: MemcacheCacher(['localhost:11211'])
|
|
|
|
# Fetch at most 3 items per feed
|
|
max_items = 3
|
|
|
|
# Keys are feed URLs, values are lists of XPATH expressions to extract
|
|
feeds = {
|
|
'http://emergent.unpythonic.net/_atom': ['.//*[@class="content"]'],
|
|
'http://rss.slashdot.org/Slashdot/slashdot':
|
|
['.//article/header', './/article/div[@class="body"]']
|
|
}
|
|
|
|
# Always cache URLs for at least this long
|
|
# expiry = 3600
|
|
|
|
# Output is placed here
|
|
# outdir = 'out'
|
|
|
|
# Extension of output files
|
|
# extension = '.atom'
|
|
|
|
# Number of worker threads
|
|
# nworkers = 3
|