Instantly share code, notes, and snippets.
Last activeMay 22, 2016 17:27
Save emileaben/0d832b78e00d2355bac520afb9603b82 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.Learn more about bidirectional Unicode characters
| #!/usr/bin/env python | |
| ''' | |
| Prototype tool for bulk IP->AS lookups for a specific date | |
| Downloads RIS data locally (using CAIDA BGPSTREAM) | |
| expects IP addresses/prefixes on STDIN (IPv4 and IPv6) | |
| takes a single command-line argument which is the DATE for which to download the table (any format convertable by arrow will do) | |
| example use: | |
| cat file_with_maaaaany_ips | ./bulk-ris-lookup.py 2009-03-22 | |
| ''' | |
| importarrow | |
| importtime | |
| importsys | |
| fromradiximportRadix | |
| from_pybgpstreamimportBGPStream,BGPRecord,BGPElem | |
| stream=BGPStream() | |
| rec=BGPRecord() | |
| input_time=sys.argv[1] | |
| ### | |
| timestamp=arrow.get(input_time ).timestamp | |
| # fudge by 12 minutes to allow for creating of ribs | |
| now=time.time() | |
| fudge_secs=12*60 | |
| ifnow-timestamp<fudge_secs: | |
| old_timestamp=timestamp | |
| timestamp=now-fudge_secs | |
| print>>sys.stderr,"timestamp to close to realtime, adjusted by %s"% (timestamp-old_timestamp ) | |
| # processing RIS only because of 8hrs dumps (rv is different) | |
| stream.add_filter('project','ris') | |
| stream.add_filter('record-type','ribs') | |
| # test | |
| #stream.add_filter('collector','rrc11') | |
| stream.add_interval_filter(timestamp-8*3600,timestamp) | |
| # start the stream | |
| stream.start() | |
| print>>sys.stderr,"start loading BGP data" | |
| t1=time.time() | |
| rtree=Radix() | |
| while(stream.get_next_record(rec)): | |
| elem=rec.get_next_elem() | |
| while(elem): | |
| # as path | |
| path=elem.fields['as-path'] | |
| pfx=elem.fields['prefix'] | |
| # as list | |
| ases=path.split(" ") | |
| ases.reverse() | |
| origin=ases[0] | |
| rnode=rtree.search_exact(pfx ) | |
| ifrnode: | |
| rnode.data['origin'].add(origin ) | |
| else: | |
| rnode=rtree.add(pfx ) | |
| rnode.data['origin']=set([origin ]) | |
| elem=rec.get_next_elem() | |
| t2=time.time() | |
| print>>sys.stderr,"finished loading BGP data (in %s s)"% (t2-t1 ) | |
| forlineinsys.stdin: | |
| line=line.rstrip('\n') | |
| origin='-' | |
| try: | |
| rnode=rtree.search_best(line ) | |
| ifrnode: | |
| # account for multi-origin: | |
| origin='|'.join(rnode.data['origin'] ) | |
| except: | |
| pass | |
| print"{line}\t{origin}".format(line=line,origin=origin ) |
Sign up for freeto join this conversation on GitHub. Already have an account?Sign in to comment