## This script runs against an OR version of OCLC's WorldCat Identities service
## Given a targetKey and startKey it will attempt to find the shortest path from
## the start to target, ignoring all but personal names

## Send enquiries to Thom Hickey (hickey at oclc dot org)

import sys, urllib, time
from xml.etree import cElementTree as ET

def normalizeKey(k):
    return k.replace(' ', '%20')
def getName(nameEl):
    if not nameEl: return None
    name = []
    for a in 'abcdq':
        sub = nameEl.findtext('sub'+a)
        if sub:
            name.append(sub)
    return ' '.join(name)
#startKey = raw_input('Starting key: ')
#targetKey = raw_input('Ending key: ')
##targetKey  = 'lccn-n82-54463' # lorcan
##startKey = 'lccn-n78-51773' # sally
targetKey = 'lccn-n79-21164' # twain
startKey = 'lccn-n79-32879' # austen
##targetKey = 'lccn-n88-34930' # kevin bacon
toSearch = [startKey]
visited = {startKey:''}
path = []
nvisited = 0
while toSearch:
    pnkey = toSearch.pop(0)
    path = visited.get(pnkey,'')
    time.sleep(0.1)  # try not to be too hard on the server
    pageObj = urllib.urlopen('http://orlabs.oclc.org/Identities/'+pnkey)
    xmltext = pageObj.read()
    try:
        el = ET.fromstring(xmltext)
    except:
        print 'problem parsing', pnkey
        continue
    typeEl = el.find('.//Identity')
    try:
        if typeEl.attrib.get('type')!='personal':
            continue
    except:
        print 'Failed on', pnkey
        print path.encode('utf-8')
        continue
    nvisited += 1
    if nvisited%10==0: print '\r', 1+path.count('|'), nvisited,
    name = getName(el.find('.//nameInfo/latinName'))
    if not name:
        name = getName(el.find('.//nameInfo/rawName'))
        if not name:
            print 'unable to find name for ', pnkey
            print 'path', path
            continue
    path += '|'+name
    if nvisited%1000==0: print '\n', path.encode('utf-8')
    associatedKeys = el.findall('.//associatedNames/name/normName')
    if associatedKeys:
        for k in associatedKeys:
            nk = normalizeKey(k.text)
            if nk==targetKey:
                print '\nFound target:', path
                print 'Visited %d pages'%nvisited
                toSearch = []
                break
            if not nk in visited:
                toSearch.append(nk)
                visited[nk] = path
##Copyright [2008] [OCLC]
##Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with the License. You may obtain a copy of the License at

##http://www.apache.org/licenses/LICENSE-2.0

##Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions and limitations under the License.