office-gobmx/bin/get-bugzilla-attachments-by-mimetype

#!/usr/bin/env python
# -*- coding: utf-8 -*-
# Version: MPL 1.1 / GPLv3+ / LGPLv3+
#
# The contents of this file are subject to the Mozilla Public License Version
# 1.1 (the "License"); you may not use this file except in compliance with
# the License or as specified alternatively below. You may obtain a copy of
# the License at http://www.mozilla.org/MPL/
#
# Software distributed under the License is distributed on an "AS IS" basis,
# WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
# for the specific language governing rights and limitations under the
# License.
#
# Major Contributor(s):
# Copyright (C) 2011 Red Hat, Inc., Caolán McNamara <caolanm@redhat.com>
#  (initial developer)
#
# All Rights Reserved.
#
# For minor contributions see the git repository.
#
# Alternatively, the contents of this file may be used under the terms of
# either the GNU General Public License Version 3 or later (the "GPLv3+"), or
# the GNU Lesser General Public License Version 3 or later (the "LGPLv3+"),
# in which case the provisions of the GPLv3+ or the LGPLv3+ are applicable
# instead of those above.

#This digs through a pile of bugzilla's and populates the cwd with a big
#collection of bug-docs in per-filetype dirs with bug-ids as names with
#prefixes to indicate which bug-tracker, e.g.
#
#fdo-bugid-X.suffix
#rhbz-bugid-X.suffix
#moz-bugid-X.suffix
#
#where X is the n'th attachment of that type in the bug

import urllib
import feedparser
import base64
import os, os.path
import xmlrpclib
from xml.dom import minidom
from xml.sax.saxutils import escape

def get_from_bug_url_via_xml(url, mimetype, prefix, suffix):
    id = url.rsplit('=', 2)[1]
    print "id is", prefix, id, suffix
    if os.path.isfile(suffix + '/' + prefix + id + '-1.' + suffix):
        print "assuming", id, "is up to date"
    else:
        print "parsing", id
        sock = urllib.urlopen(url+"&ctype=xml")
        dom = minidom.parse(sock)
        sock.close()
        attachmentid=1
        for attachment in dom.getElementsByTagName('attachment'):
            print " mimetype is", 
            for node in attachment.childNodes:
                if node.nodeName == 'type':
                    print node.firstChild.nodeValue,
                    if node.firstChild.nodeValue.lower() != mimetype.lower():
                        print 'skipping'
                        break
                elif node.nodeName == 'data':
                    download = suffix + '/' +prefix + id + '-' + str(attachmentid) + '.' + suffix
                    print 'downloading as', download
                    f = open(download, 'w')
                    f.write(base64.b64decode(node.firstChild.nodeValue))
                    f.close()
                    attachmentid += 1
                    break

def get_through_rpc_query(rpcurl, showurl, mimetype, prefix, suffix):
    try:
        proxy = xmlrpclib.ServerProxy(rpcurl)
        query = dict()
        query['column_list']='bug_id'
        query['query_format']='advanced'
        query['field0-0-0']='attachments.mimetype'
        query['type0-0-0']='equals'
        query['value0-0-0']=mimetype
        result = proxy.Bug.search(query)
        bugs = result['bugs']
        print len(bugs), 'bugs to process'
        for bug in bugs:
            url = showurl + str(bug['bug_id'])
            get_from_bug_url_via_xml(url, mimetype, prefix, suffix)
    except xmlrpclib.Fault, err:
        print "A fault occurred"
        print "Fault code: %s" % err.faultCode
        print err.faultString

def get_through_rss_query_url(url, mimetype, prefix, suffix):
    try:
        os.mkdir(suffix)
    except:
        pass
    d = feedparser.parse(url)
    for entry in d['entries']:
        get_from_bug_url_via_xml(entry['id'], mimetype, prefix, suffix)

def get_through_rss_query(queryurl, mimetype, prefix, suffix):
    url = queryurl + '?query_format=advanced&field0-0-0=attachments.mimetype&type0-0-0=equals&value0-0-0=' + escape(mimetype) + '&ctype=rss'
    print 'url is', url
    get_through_rss_query_url(url, mimetype, prefix, suffix)


freedesktop = 'http://bugs.freedesktop.org/buglist.cgi'
openoffice = 'http://openoffice.org/bugzilla/buglist.cgi'
redhatrpc = 'https://bugzilla.redhat.com/xmlrpc.cgi'
redhatbug = 'https://bugzilla.redhat.com/show_bug.cgi?id='
novell = 'https://bugzilla.novell.com/buglist.cgi'
mozilla = 'https://bugzilla.mozilla.org/buglist.cgi'

mimetypes = [
    ('application/msword', 'doc'),
    ('application/rtf', 'rtf'),
    ('text/rtf', 'rtf'),
    ('text/spreadsheet', 'slk'),
    ('application/vnd.ms-powerpoint', 'ppt'),
]

for (mimetype,extension) in mimetypes:
    get_through_rss_query(freedesktop, mimetype, "fdo", extension)

for (mimetype,extension) in mimetypes:
    get_through_rpc_query(redhatrpc, redhatbug, mimetype, "rhbz", extension)

#to-do, get attachments some other way, not inline in xml
#get_through_rss_query(novell, 'application/msword', "n", "doc")

for (mimetype,extension) in mimetypes:
    get_through_rss_query(openoffice, mimetype, "ooo", extension)

# vim:set shiftwidth=4 softtabstop=4 expandtab: