mirror of https://github.com/WikiTeam/wikiteam
You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
88 lines
3.3 KiB
Python
88 lines
3.3 KiB
Python
#!/usr/bin/env python2
|
|
# -*- coding: utf-8 -*-
|
|
|
|
# wikia.py List of not archived Wikia wikis
|
|
# Downloads Wikia's dumps and lists wikis which have none.
|
|
# TODO: check date, http://www.cyberciti.biz/faq/linux-unix-curl-if-modified-since-command-linux-example/
|
|
#
|
|
# Copyright (C) 2014 WikiTeam developers
|
|
# This program is free software: you can redistribute it and/or modify
|
|
# it under the terms of the GNU General Public License as published by
|
|
# the Free Software Foundation, either version 3 of the License, or
|
|
# (at your option) any later version.
|
|
#
|
|
# This program is distributed in the hope that it will be useful,
|
|
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
# GNU General Public License for more details.
|
|
#
|
|
# You should have received a copy of the GNU General Public License
|
|
# along with this program. If not, see <http://www.gnu.org/licenses/>.
|
|
|
|
import subprocess
|
|
import re
|
|
from wikitools import wiki, api
|
|
|
|
def getlist(wikia, wkfrom = 1, wkto = 1000):
|
|
params = {'action': 'query', 'list': 'wkdomains', 'wkactive': '1', 'wkfrom': wkfrom, 'wkto': wkto,}
|
|
request = api.APIRequest(wikia, params)
|
|
return request.query()['query']['wkdomains']
|
|
|
|
def getall():
|
|
wikia = wiki.Wiki('http://community.wikia.com/api.php')
|
|
offset = 0
|
|
limit = 1000
|
|
domains = {}
|
|
# This API module has no query continuation facility
|
|
print 'Getting list of active domains...'
|
|
while True:
|
|
list = getlist(wikia, offset, offset + limit)
|
|
if list:
|
|
print offset
|
|
domains = dict(domains.items() + list.items() )
|
|
offset += 1000
|
|
else:
|
|
break
|
|
return domains
|
|
|
|
def main():
|
|
domains = getall()
|
|
undumped = []
|
|
# Or we could iterate over each sublist while we get it?
|
|
for i in domains:
|
|
dbname = re.sub('[-_.]', '', domains[i]['domain'].replace('.wikia.com', '') )
|
|
dbname = re.escape(dbname)
|
|
print dbname
|
|
first = dbname[0]
|
|
# There are one-letter dbnames; the second letter is replaced by an underscore
|
|
# http://s3.amazonaws.com/wikia_xml_dumps/n/n_/n_pages_full.xml.gz
|
|
try:
|
|
second = dbname[1]
|
|
except:
|
|
second = '_'
|
|
base = 'http://s3.amazonaws.com/wikia_xml_dumps/' + first + '/' \
|
|
+ first + second + '/' + dbname
|
|
full = base + '_pages_full.xml.gz'
|
|
print full
|
|
current = base + '_pages_current.xml.gz'
|
|
images = base + '_images.tar'
|
|
try:
|
|
#subprocess.check_call(['wget', '-e', 'robots=off', '--fail', '-nc', '-a', 'wikia.log', full])
|
|
# Use this instead, and comment out the next try, to only list.
|
|
subprocess.check_call(['curl', '-I', '--fail', full])
|
|
except subprocess.CalledProcessError as e:
|
|
# We added --fail for this https://superuser.com/a/854102/283120
|
|
if e.returncode == 22:
|
|
print 'Missing: ' + domains[i]['domain']
|
|
undumped.append( domains[i]['domain'] )
|
|
|
|
#try:
|
|
# subprocess.check_call(['wget', '-e', 'robots=off', '-nc', '-a', 'wikia.log', current])
|
|
# subprocess.check_call(['wget', '-e', 'robots=off', '-nc', '-a', 'wikia.log', images])
|
|
#except:
|
|
# pass
|
|
print '\n'.join(str(dump) for dump in undumped)
|
|
|
|
if __name__ == '__main__':
|
|
main()
|