I was recently asked how to count the total pages on a 4.2 Confluence server so I provided this python script that shows how to use the XML-RPC API to do it. The technique can be used for more than counting pages. The API provides all sorts of useful operations, like adding users. For more information on the available methods see this page: https://developer.atlassian.com/display/CONFDEV/Remote+Confluence+Methods.
|
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 |
#!/usr/bin/env python r''' This script shows how to use the XML-RPC API to access information from a Confluence server. Here is how you might use it: $ confluence_pages.py URL: http://confluence Username: myself Password: <secret> Server Info baseUrl : http://confluence:8090 buildId : 3284 developmentBuild : false majorVersion : 4 minorVersion : 2 patchLevel : 5 Misc Info Active Users : 580 Spaces : 120 Pages : 7260 ''' import datetime import getpass import sys import xmlrpclib def get_credentials(): ''' Get the access credentials. They are accessed positionally from the command line or from a prompt. @returns a tuple of url, username and password ''' url = None username = None password = None if len(sys.argv) > 1: url = sys.argv[1] if len(sys.argv) > 2: username = sys.argv[2] if len(sys.argv) > 3: password = sys.argv[3] if url is None: url = raw_input('URL: ') # ex. https://docs.tabula.com if username is None: username = raw_input('Username: ') # ex. jlinoff if password is None: password = getpass.getpass('Password: ') return url, username, password def access_confluence(url, username, password): ''' Access confluence and report some information. @param url The URL of the server. @param username Login username. @param password Login password. ''' server = xmlrpclib.ServerProxy(url + '/rpc/xmlrpc') token = server.confluence2.login(username, password) # Server info = server.confluence2.getServerInfo(token) now = datetime.datetime.now() print print 'Confluence Pages Report '+now.strftime('%Y-%m-%d %H:%M:%S') print print ' Server Info' maxlen = 0 for item in sorted(info): maxlen = max(len(item), maxlen) for item in sorted(info): val = info[item] print ' %-*s : %s' % (maxlen, item, val) # Misc spaces = server.confluence2.getSpaces(token) users = server.confluence2.getActiveUsers(token, True) print print ' Misc Info' print ' %-12s : %5d' % ('Active Users', len(users)) print ' %-12s : %5d' % ('Spaces', len(spaces)) num_pages = 0 for space in spaces: space_key = space['key'] num_pages += len(server.confluence2.getPages(token, space_key)) print ' %-12s : %5d' % ('Pages', num_pages) server.confluence2.logout(token) print def main(): ''' Run program. ''' url, username, password = get_credentials() access_confluence(url, username, password) if __name__ == '__main__': main() |
Note that this script has very weak option handling and, as such, is not suitable for production.