Python file to read the Bluesky ("atproto") firehose and show the json of each message. (Doesn't contain the author, because who knows how the hell to do that.)

firehose.py

from atproto.firehose import FirehoseSubscribeReposClient, parse_subscribe_repos_message
import sys
from atproto import CAR, models
from atproto.cbor import decode_dag, decode_dag_multi
from atproto.xrpc_client.models.utils import get_or_create
import json

class JSONExtra(json.JSONEncoder):
    """raw objects sometimes contain CID() objects, which
    seem to be references to something elsewhere in bluesky.
    So, we 'serialise' these as a string representation,
    which is a hack but whatevAAAAR"""
    def default(self, obj):
        try:
            result = json.JSONEncoder.default(self, obj)
            return result
        except:
            return repr(obj)

client = FirehoseSubscribeReposClient()

# all of this undocumented horseshit is based on cargo-culting the bollocks out of
# https://github.com/MarshalX/atproto/blob/main/examples/firehose/sub_repos.py
# and
# https://github.com/MarshalX/bluesky-feed-generator/blob/main/server/data_stream.py

def on_message_handler(message):
    commit = parse_subscribe_repos_message(message)
    if not isinstance(commit, models.ComAtprotoSyncSubscribeRepos.Commit):
        return
    car = CAR.from_bytes(commit.blocks)
    for op in commit.ops:
        if op.action in ["create"] and op.cid:
            raw = car.blocks.get(op.cid)
            cooked = get_or_create(raw, strict=False)
            if cooked._type == "app.bsky.feed.post":
                # other types include "app.bsky.feed.like" etc which we ignore
                # note that this data does not include who posted this skeet
                # or possibly it does as a "CID" which you have to look up somehow
                # who the hell knows? not me
                print(json.dumps(raw, cls=JSONExtra, indent=2))

client.start(on_message_handler)

glorious, i think

Here is a (mostly unchanged) version for 0.0.56 with the updated dependency locations and methods.

import json
from atproto_client.models import get_or_create
from atproto import CAR, models
from atproto_firehose import FirehoseSubscribeReposClient, parse_subscribe_repos_message

class JSONExtra(json.JSONEncoder):
    """raw objects sometimes contain CID() objects, which
    seem to be references to something elsewhere in bluesky.
    So, we 'serialise' these as a string representation,
    which is a hack but whatevAAAAR"""
    def default(self, obj):
        try:
            result = json.JSONEncoder.default(self, obj)
            return result
        except:
            return repr(obj)

client = FirehoseSubscribeReposClient()

# all of this undocumented horseshit is based on cargo-culting the bollocks out of
# https://github.com/MarshalX/atproto/blob/main/examples/firehose/sub_repos.py
# and
# https://github.com/MarshalX/bluesky-feed-generator/blob/main/server/data_stream.py

def on_message_handler(message):
    commit = parse_subscribe_repos_message(message)
    if not isinstance(commit, models.ComAtprotoSyncSubscribeRepos.Commit):
        return
    car = CAR.from_bytes(commit.blocks)
    for op in commit.ops:
        if op.action in ["create"] and op.cid:
            raw = car.blocks.get(op.cid)
            cooked = get_or_create(raw, strict=False)
            if cooked.py_type == "app.bsky.feed.post":
                # other types include "app.bsky.feed.like" etc which we ignore
                # note that this data does not include who posted this skeet
                # or possibly it does as a "CID" which you have to look up somehow
                # who the hell knows? not me
                print(json.dumps(raw, cls=JSONExtra, indent=2))

client.start(on_message_handler)