doing applied fediverse research
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

54 lines
1.9 KiB

#!/bin/env python3
# fediscraper v1
import json, requests,threading
start_url = 'https://post.lurk.org'
activity = ''
peers_info = '/api/v1/instance/peers'
instance_info = '/api/v1/instance'
def get_peers(instance):
r = requests.get('https://'+instance+'/api/v1/instance/peers', timeout=10)
if r.status_code == 200:
peers = r.json()
print(instance, 'peers with', len(peers))
return(peers)
else:
print('fail: got {} on {}'.format(r.status_code, instance))
instances = {}
r = requests.get(start_url+peers_info)
if r. status_code == 200:
print('200 for '+start_url)
peers = r.json()
print('{} has {} peers'.format(start_url, len(peers)))
for count, peer in enumerate(peers):
#instances.add(peer)
try:
peer_list = get_peers(peer)
if peer_list:
for i in peer_list:
if i not in instances:
try:
ii = requests.get('https://'+i+instance_info, timeout=10)
info = ii.json()
except Exception as e:
print('failed to query instance info')
print(e)
info = 'error'
pass
instances[i] = info
print('added {}, n={}'.format(i,len(instances)))
else:
print(i.status_code, 'on', peer)
except Exception as e:
print('failure for', peer)
# instances[peer] = {'error':e}
print(e)
#text = list(filter(None.__ne__, instances))
with open('instance_scrape.json','w') as f:
f.write(json.dumps(instances,indent=4))
#f.write('\n'.join(text)