traverse ncbi taxonomy?

gistfile1.py

'''
> head nodes.dmp
1	|	1	|	no rank	|		|	8	|	0	|	1	|	0	|	0	|	0	|	0	|	0	|		|
2	|	131567	|	superkingdom	|		|	0	|	0	|	11	|	0	|	0	|	0	|	0	|	0	|		|
6	|	335928	|	genus	|		|	0	|	1	|	11	|	1	|	0	|	1	|	0	|	0	|		|
7	|	6	|	species	|	AC	|	0	|	1	|	11	|	1	|	0	|	1	|	1	|	0	|		|
9	|	32199	|	species	|	BA	|	0	|	1	|	11	|	1	|	0	|	1	|	1	|	0	|		|
10	|	135621	|	genus	|		|	0	|	1	|	11	|	1	|	0	|	1	|	0	|	0	|		|
11	|	1707	|	species	|	CG	|	0	|	1	|	11	|	1	|	0	|	1	|	1	|	0	|		|
13	|	203488	|	genus	|		|	0	|	1	|	11	|	1	|	0	|	1	|	0	|	0	|		|
14	|	13	|	species	|	DT	|	0	|	1	|	11	|	1	|	0	|	1	|	1	|	0	|		|
16	|	32011	|	genus	|		|	0	|	1	|	11	|	1	|	0	|	1	|	0	|	0	|		|


> head names.dmp
1	|	all	|		|	synonym	|
1	|	root	|		|	scientific name	|
2	|	Bacteria	|	Bacteria <prokaryote>	|	scientific name	|
2	|	Monera	|	Monera <Bacteria>	|	in-part	|
2	|	Procaryotae	|	Procaryotae <Bacteria>	|	in-part	|
2	|	Prokaryota	|	Prokaryota <Bacteria>	|	in-part	|
2	|	Prokaryotae	|	Prokaryotae <Bacteria>	|	in-part	|
2	|	bacteria	|	bacteria <blast2>	|	blast name	|
2	|	eubacteria	|		|	genbank common name	|
2	|	not Bacteria Haeckel 1894	|		|	synonym	|

'''
from time import time as now

try:
    rawnodes, rawnames
    print('files already loaded')
except:
    t0 = now()
    rawnodes = open('nodes.dmp').read()
    rawnames = open('names.dmp').read()
    print('loaded files in %s sec' % (now() - t0))

try:
    namemap
    print('name map already loaded')
except:
    t0 = now()
    namemap = {int(id):name for (id, name) in [[part.strip() for part in line.split('|', 2)[:2]] for line in rawnames.splitlines()]}
    print('loaded name map in %s sec' % (now() - t0))

try:
    genusmap, parentmap
    print('genus+parent map already loaded')
except:
    t0 = now()
    genusmap = {}
    parentmap = {}
    for line in rawnodes.splitlines():
        child, parent, category = [part.strip() for part in line.split('|', 3)][:3]
        child = int(child)
        parent = int(parent)
        genusmap[child] = category
        parentmap[child] = parent
    print('loaded genus+parent map in %s sec' % (now() - t0))


VERBOSE = False

def query(node_id, iter=0):
    if iter > 10:
        if VERBOSE: print(' * * * warning! big tree! * * *')
    prefix = '>>'*(iter+1)
    category = genusmap.get(node_id)
    if VERBOSE: print('%s ID %s\tis type: %s' % (prefix, node_id, category))
    if category == 'genus':
        print('|__ found genus at %s\n' % (namemap[node_id]))
    else:
        if node_id not in parentmap:
            if VERBOSE: print(' * * * warning: no parent! * * *')
        elif node_id == parentmap[node_id]:
            if VERBOSE: print(' ! ! ! end of tree ! ! !')
        else:
            query(parentmap[node_id], iter+1)

import random
allid = namemap.keys()
for i in range(10):
    rand_id = random.choice(allid)
    print('='*50)
    print('querying: %s\t%s' % (rand_id, namemap[rand_id]))
    query(rand_id)