Merge pull request #99 from m-appel/41-alice-looking-glass-route-servers

Add Alice-LG crawler

config.json.example

@@ -69,9 +69,16 @@
             "iyp.crawlers.pch.daily_routing_snapshots_v6",
             "iyp.crawlers.emileaben.as_names",
             "iyp.crawlers.ripe.atlas_probes",
+            "iyp.crawlers.iana.root_zone",
+            "iyp.crawlers.alice_lg.amsix",
+            "iyp.crawlers.alice_lg.bcix",
+            "iyp.crawlers.alice_lg.decix",
+            "iyp.crawlers.alice_lg.ixbr",
+            "iyp.crawlers.alice_lg.linx",
+            "iyp.crawlers.alice_lg.megaport",
+            "iyp.crawlers.alice_lg.netnod",
             "iyp.crawlers.cloudflare.dns_top_locations",
-            "iyp.crawlers.cloudflare.dns_top_ases",
-            "iyp.crawlers.iana.root_zone"
+            "iyp.crawlers.cloudflare.dns_top_ases"
         ],
 
         "post": [

iyp/crawlers/alice_lg/README.md

@@ -0,0 +1,47 @@
+# Alice-LG -- https://github.com/alice-lg/alice-lg
+
+Alice-LG is a BGP looking glass which gets its data from external APIs.
+
+It is used by some large IXPs (e.g., DE-CIX, LINX, AMS-IX) and IYP imports membership
+information by reading the route server neighbors.
+
+The crawler *can* also import the received routes of all neighbors, however testing has
+shown that this takes an unreasonable amount of time for most IXPs due to the tiny
+pagination size (250 routes per page). Therefore this functionality is disabled by default.
+
+List of supported IXPs:
+
+- AMS-IX (`amsix.py`)
+- BCIX (`bcix.py`)
+- DE-CIX (`decix.py`)
+- IX.br (`ixbr.py`)
+- LINX (`linx.py`)
+- Megaport (`megaport.py`)
+- Netnod (`netnod.py`)
+
+## Graph representation
+
+```Cypher
+(:AS {asn: 2497})-[:MEMBER_OF {address: '80.81.193.136', routeserver_id: 'rs1_fra_ipv4'}]->(:IXP {name: 'DE-CIX Frankfurt'})
+// Routes are not crawled by default
+(:AS {asn: 3333})-[:ORIGINATE {neighbor_id: 'pb_0280_as20562', routeserver_id: 'rs01-bcix-v4'}]->(:Prefix {prefix: '193.0.0.0/21'})
+```
+
+There is the possibility of multiple relationships between the same node. However, these
+contain different information, e.g., a member is present with multiple interfaces
+(`address`) or the information is seen by different route servers (`routeserver_id`).
+Similarly, a route can be seen via multiple neighbors (`neighbor_id`) or different route
+servers (`routeserver_id`).
+
+## Dependence
+
+This crawler requires peering LAN information to map the neighbor IP to an IXP.
+Therefore, it should be run after crawlers that create
+
+```Cypher
+(:Prefix)-[:MANAGED_BY]->(:IXP)
+```
+
+relationships:
+
+- `iyp.crawlers.peeringdb.ix`

iyp/crawlers/alice_lg/amsix.py

@@ -1,25 +1,40 @@
+import argparse
 import logging
+import os
 import sys
 
 from iyp.crawlers.alice_lg import Crawler
 
+ORG = 'Alice-LG'
 URL = 'https://lg.ams-ix.net/api/v1/'
+NAME = 'alice_lg.amsix'
 
-# Main program
-if __name__ == '__main__':
 
-    scriptname = sys.argv[0].replace('/', '_')[0:-3]
-    FORMAT = '%(asctime)s %(processName)s %(message)s'
+def main() -> None:
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--unit-test', action='store_true')
+    args = parser.parse_args()
+
+    scriptname = os.path.basename(sys.argv[0]).replace('/', '_')[0:-3]
+    FORMAT = '%(asctime)s %(levelname)s %(message)s'
     logging.basicConfig(
         format=FORMAT,
         filename='log/' + scriptname + '.log',
         level=logging.INFO,
         datefmt='%Y-%m-%d %H:%M:%S'
     )
-    logging.info('Started: %s' % sys.argv)
 
-    crawler = Crawler(URL)
-    if len(sys.argv) > 1 and sys.argv[1] == 'unit_test':
+    logging.info(f'Started: {sys.argv}')
+
+    crawler = Crawler(ORG, URL, NAME)
+    if args.unit_test:
         crawler.unit_test(logging)
     else:
         crawler.run()
+        crawler.close()
+    logging.info(f'Finished: {sys.argv}')
+
+
+if __name__ == '__main__':
+    main()
+    sys.exit(0)

iyp/crawlers/alice_lg/bcix.py

@@ -0,0 +1,40 @@
+import argparse
+import logging
+import os
+import sys
+
+from iyp.crawlers.alice_lg import Crawler
+
+ORG = 'Alice-LG'
+URL = 'https://lg.bcix.de/api/v1/'
+NAME = 'alice_lg.bcix'
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--unit-test', action='store_true')
+    args = parser.parse_args()
+
+    scriptname = os.path.basename(sys.argv[0]).replace('/', '_')[0:-3]
+    FORMAT = '%(asctime)s %(levelname)s %(message)s'
+    logging.basicConfig(
+        format=FORMAT,
+        filename='log/' + scriptname + '.log',
+        level=logging.INFO,
+        datefmt='%Y-%m-%d %H:%M:%S'
+    )
+
+    logging.info(f'Started: {sys.argv}')
+
+    crawler = Crawler(ORG, URL, NAME)
+    if args.unit_test:
+        crawler.unit_test(logging)
+    else:
+        crawler.run()
+        crawler.close()
+    logging.info(f'Finished: {sys.argv}')
+
+
+if __name__ == '__main__':
+    main()
+    sys.exit(0)

iyp/crawlers/alice_lg/decix.py

@@ -1,25 +1,40 @@
+import argparse
 import logging
+import os
 import sys
 
 from iyp.crawlers.alice_lg import Crawler
 
+ORG = 'Alice-LG'
 URL = 'https://lg.de-cix.net/api/v1/'
+NAME = 'alice_lg.decix'
 
-# Main program
-if __name__ == '__main__':
 
-    scriptname = sys.argv[0].replace('/', '_')[0:-3]
-    FORMAT = '%(asctime)s %(processName)s %(message)s'
+def main() -> None:
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--unit-test', action='store_true')
+    args = parser.parse_args()
+
+    scriptname = os.path.basename(sys.argv[0]).replace('/', '_')[0:-3]
+    FORMAT = '%(asctime)s %(levelname)s %(message)s'
     logging.basicConfig(
         format=FORMAT,
         filename='log/' + scriptname + '.log',
         level=logging.INFO,
         datefmt='%Y-%m-%d %H:%M:%S'
     )
-    logging.info('Started: %s' % sys.argv)
 
-    crawler = Crawler(URL)
-    if len(sys.argv) > 1 and sys.argv[1] == 'unit_test':
+    logging.info(f'Started: {sys.argv}')
+
+    crawler = Crawler(ORG, URL, NAME)
+    if args.unit_test:
         crawler.unit_test(logging)
     else:
         crawler.run()
+        crawler.close()
+    logging.info(f'Finished: {sys.argv}')
+
+
+if __name__ == '__main__':
+    main()
+    sys.exit(0)

iyp/crawlers/alice_lg/ixbr.py

@@ -0,0 +1,40 @@
+import argparse
+import logging
+import os
+import sys
+
+from iyp.crawlers.alice_lg import Crawler
+
+ORG = 'Alice-LG'
+URL = 'https://lg.ix.br/api/v1/'
+NAME = 'alice_lg.ixbr'
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--unit-test', action='store_true')
+    args = parser.parse_args()
+
+    scriptname = os.path.basename(sys.argv[0]).replace('/', '_')[0:-3]
+    FORMAT = '%(asctime)s %(levelname)s %(message)s'
+    logging.basicConfig(
+        format=FORMAT,
+        filename='log/' + scriptname + '.log',
+        level=logging.INFO,
+        datefmt='%Y-%m-%d %H:%M:%S'
+    )
+
+    logging.info(f'Started: {sys.argv}')
+
+    crawler = Crawler(ORG, URL, NAME)
+    if args.unit_test:
+        crawler.unit_test(logging)
+    else:
+        crawler.run()
+        crawler.close()
+    logging.info(f'Finished: {sys.argv}')
+
+
+if __name__ == '__main__':
+    main()
+    sys.exit(0)

iyp/crawlers/alice_lg/linx.py

@@ -1,25 +1,40 @@
+import argparse
 import logging
+import os
 import sys
 
 from iyp.crawlers.alice_lg import Crawler
 
+ORG = 'Alice-LG'
 URL = 'https://alice-rs.linx.net/api/v1/'
+NAME = 'alice_lg.linx'
 
-# Main program
-if __name__ == '__main__':
 
-    scriptname = sys.argv[0].replace('/', '_')[0:-3]
-    FORMAT = '%(asctime)s %(processName)s %(message)s'
+def main() -> None:
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--unit-test', action='store_true')
+    args = parser.parse_args()
+
+    scriptname = os.path.basename(sys.argv[0]).replace('/', '_')[0:-3]
+    FORMAT = '%(asctime)s %(levelname)s %(message)s'
     logging.basicConfig(
         format=FORMAT,
         filename='log/' + scriptname + '.log',
         level=logging.INFO,
         datefmt='%Y-%m-%d %H:%M:%S'
     )
-    logging.info('Started: %s' % sys.argv)
 
-    crawler = Crawler(URL)
-    if len(sys.argv) > 1 and sys.argv[1] == 'unit_test':
+    logging.info(f'Started: {sys.argv}')
+
+    crawler = Crawler(ORG, URL, NAME)
+    if args.unit_test:
         crawler.unit_test(logging)
     else:
         crawler.run()
+        crawler.close()
+    logging.info(f'Finished: {sys.argv}')
+
+
+if __name__ == '__main__':
+    main()
+    sys.exit(0)

iyp/crawlers/alice_lg/megaport.py

@@ -0,0 +1,40 @@
+import argparse
+import logging
+import os
+import sys
+
+from iyp.crawlers.alice_lg import Crawler
+
+ORG = 'Alice-LG'
+URL = 'https://lg.megaport.com/api/v1/'
+NAME = 'alice_lg.megaport'
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--unit-test', action='store_true')
+    args = parser.parse_args()
+
+    scriptname = os.path.basename(sys.argv[0]).replace('/', '_')[0:-3]
+    FORMAT = '%(asctime)s %(levelname)s %(message)s'
+    logging.basicConfig(
+        format=FORMAT,
+        filename='log/' + scriptname + '.log',
+        level=logging.INFO,
+        datefmt='%Y-%m-%d %H:%M:%S'
+    )
+
+    logging.info(f'Started: {sys.argv}')
+
+    crawler = Crawler(ORG, URL, NAME)
+    if args.unit_test:
+        crawler.unit_test(logging)
+    else:
+        crawler.run()
+        crawler.close()
+    logging.info(f'Finished: {sys.argv}')
+
+
+if __name__ == '__main__':
+    main()
+    sys.exit(0)