#! @PYTHON@
# For a given listname, this script generates sitemap.xml.gz files
# under archives/private/<listname>/
#
# Copyright (C) 1998-2018 by the Free Software Foundation, Inc.
#
# graciously hacked from bin/sync_members
#
"""Build Sitemap files for an archive
Usage: %(program)s [options] listname
Where `options' are:
--help
-h
Print this message.
listname
Required. This specifies the list to generate sitemaps for.
"""
import os
import sys
import paths
# Import this /after/ paths so that the sys.path is properly hacked
import email.Utils
from Mailman import MailList
from Mailman import Errors
from Mailman import Utils
from Mailman.UserDesc import UserDesc
from Mailman import mm_cfg
from Mailman.i18n import _
import getopt
import re
import time
from stat import *
from datetime import datetime, timedelta
import gzip
# sitemap priorities in age-in-weeks/priority/changefreq tuples
priorities = ([1, 1.0, "daily"],
[4, 1.0, "weekly"],
[30, 1.0, "monthly"],
[52, 0.9, "never"],
[100, 0.8, "never"],
[200, 0.7, "never"],
[300, 0.6, "never"],
[400, 0.5, "never"])
program = sys.argv[0]
def usage(code, msg=''):
if code:
fd = sys.stderr
else:
fd = sys.stdout
print >> fd, _(__doc__)
if msg:
print >> fd, msg
sys.exit(code)
def main():
listname = None
# TBD: can't use getopt with this command line syntax, which is broken and
# should be changed to be getopt compatible.
i = 1
while i < len(sys.argv):
opt = sys.argv[i]
if opt in ('-h', '--help'):
usage(0)
else:
try:
listname = sys.argv[i].lower()
i += 1
except IndexError:
usage(1, _('No listname given'))
break
if listname is None:
usage(1, _('Must have a listname'))
# get the locked list object
try:
mlist = MailList.MailList(listname, lock=0)
except Errors.MMListError, e:
print _('No such list: %(listname)s')
sys.exit(1)
rootdir = mlist.archive_dir()
rooturl = mlist.GetBaseArchiveURL()
reArcPath = re.compile(r'^\d+')
reArcFile = re.compile(r'\d+\.html')
sitemaps = []
now = datetime.now()
for folder in os.listdir(rootdir):
path = os.path.join(rootdir,folder)
if not os.path.isdir(path) or not reArcPath.search(folder):
continue
dirtime = os.path.getmtime(path)
os.umask(0022)
sitemap = os.path.join(rootdir,folder,"sitemap.xml.gz")
f = gzip.open(sitemap, 'wb')
f.write('<?xml version="1.0" encoding="UTF-8"?>\n')
f.write('<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">\n')
for file in os.listdir(path):
if not reArcFile.search(file):
continue
# get timestamp of file
st = os.stat(os.path.join(rootdir,folder,file))
mtime = st[ST_MTIME] #modification time
ts = datetime.fromtimestamp(mtime)
for weeks, priority, changefreq in priorities:
if ts > now - timedelta(weeks = weeks):
break
f.write(' <url>\n <loc>' + os.path.join(rooturl,folder,file) + '</loc>\n')
f.write(' <lastmod>' + time.strftime("%Y-%m-%d",time.gmtime(mtime)) + '</lastmod>\n')
f.write(' <changefreq>' + changefreq + '</changefreq>\n')
f.write(' <priority>' + str(priority) + '</priority>\n')
f.write(' </url>\n')
f.write('</urlset>\n')
f.close()
sitemaps.append((os.path.join(rooturl,folder,"sitemap.xml.gz")))
# write out the sitemapindex file
sitemapindex = os.path.join(rootdir,"sitemap.xml.gz")
f = gzip.open(sitemapindex, 'wb')
f.write('<?xml version="1.0" encoding="UTF-8"?>\n')
f.write('<sitemapindex xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">\n')
for sitemap in sitemaps:
f.write(' <sitemap>\n <loc>' + sitemap + '</loc>\n')
f.write(' <lastmod>' + time.strftime("%Y-%m-%d", now.timetuple()) + '</lastmod>\n')
f.write(' </sitemap>\n')
f.write('</sitemapindex>\n')
f.close()
if __name__ == '__main__':
main()
