working on making the script importable by about_collector

fedicrawler.py

@@ -1,20 +1,8 @@
 #!/bin/env python3
-# fedicrawler v4
+# fedicrawler v5
 
-import json, requests
-from multiprocessing.dummy import Pool as ThreadPool 
 from urllib.parse import urlparse
 
-start_url = 'https://post.lurk.org'
-activity = ''
-peers_info ='/api/v1/instance/peers'
-
-proxies = {
-'http':'socks5://localhost:12345',
-'http':'socks5://localhost:12345'}
-
-pool = ThreadPool(512)
-
 def not_gab(instance):
     #gab does some weird stuff wrt enumerating subdomains
     #example: epa1pu1qcxxyzcxher0u.gab.best
@@ -117,43 +105,58 @@ def get_instance_info(instance):
         info = {'error': str(e)}
     return info
 
-filters = [not_gab, only_netloc] #what to filter out
+def fedicrawler():
 
-instances = set([])
-r = requests.get(start_url+peers_info) # normal brain, initial peer list
-if r. status_code == 200:
-    start_peers = pool.map(get_peers, r.json())  #expanding brain, get all peers of those initial peers
-    for i in start_peers:
-        if not i:
-            start_peers.remove(i)
-        else:
-            pool.map(instances.add, i)
-    # for i in r.json():
-    #     instances.add(i)
-    instances = set(multi_filter(filters,instances)) # apply filters before we move to network
+    start_url = 'https://post.lurk.org'
+    activity = ''
+    peers_info ='/api/v1/instance/peers'
 
-    network = pool.map(get_peers, instances) #galaxy brain, get all peers of all peers of the initial peers
-    for peer_list in network:
-        if peer_list:
-            for instance in peer_list:
-                if not_gab(instance): #prevent gab.best subdomain enumeration
-                    instances.add(instance)
+    proxies = {
+    'http':'socks5://localhost:12345',
+    'http':'socks5://localhost:12345'}
 
-    instances = set(multi_filter(filters,instances))
+    pool = ThreadPool(512)
 
-instance_info = pool.map(get_nodeinfo, instances)
+    filters = [not_gab, only_netloc] #what to filter out
 
-scrape = {}
-instances_list = list(instances)
+    instances = set([])
+    r = requests.get(start_url+peers_info) # normal brain, initial peer list
+    if r. status_code == 200:
+        start_peers = pool.map(get_peers, r.json())  #expanding brain, get all peers of those initial peers
+        for i in start_peers:
+            if not i:
+                start_peers.remove(i)
+            else:
+                pool.map(instances.add, i)
+        # for i in r.json():
+        #     instances.add(i)
+        instances = set(multi_filter(filters,instances)) # apply filters before we move to network
 
-for count, value in enumerate(instances_list):
-    scrape[value] = instance_info[count]
+        network = pool.map(get_peers, instances) #galaxy brain, get all peers of all peers of the initial peers
+        for peer_list in network:
+            if peer_list:
+                for instance in peer_list:
+                    if not_gab(instance): #prevent gab.best subdomain enumeration
+                        instances.add(instance)
 
-print('found {} instances'.format(len(scrape)))
+        instances = set(multi_filter(filters,instances))
 
-pool.close()
-pool.join()
+    instance_info = pool.map(get_nodeinfo, instances)
 
-with open('instance_scrape.json','w') as f:
-    f.write(json.dumps(scrape,indent=4))
-    #f.write('\n'.join(text)
+    scrape = {}
+    instances_list = list(instances)
+
+    for count, value in enumerate(instances_list):
+        scrape[value] = instance_info[count]
+
+    print('found {} instances'.format(len(scrape)))
+
+    pool.close()
+    pool.join()
+
+    with open('instance_scrape.json','w') as f:
+        f.write(json.dumps(scrape,indent=4))
+        #f.write('\n'.join(text)
+
+if __name__ == '__main__':
+    fedicrawler()