From b2342c48685f40b48493b066f465b6908260adf5 Mon Sep 17 00:00:00 2001
From: Jan Eggers <janeggers@untergeekPro.local>
Date: Wed, 18 Dec 2024 22:55:04 +0100
Subject: [PATCH] Init Commit

---
 README.md | 20 +++++++++++++++
 main.py   | 76 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 96 insertions(+)
 create mode 100644 main.py

diff --git a/README.md b/README.md
index c27a790..2f9c5bd 100644
--- a/README.md
+++ b/README.md
@@ -1,2 +1,22 @@
 # aichecker
 Checks Bluesky accounts (and, later, similar media) for AI suspicion. 
+
+## Der Plan
+
+### Phase 1: Bluesky
+
+- Bluesky-API anschauen 
+- Beliebiges Account vier Wochen scannen
+- AIorNot-API einbauen https://docs.aiornot.com/
+    - Bilder checken
+    - Videos checken:
+        - Audiospur extrahieren
+        - Audiospur checken
+- hive-API einbauen 
+- Detectora-API einbauen
+- Ausgabe: Vermuteter KI-Anteil 
+
+### Phase 2: 4CAT
+- 4CAT-Server aufsetzen
+- "processor" für KI-Check einbauen
+- 
diff --git a/main.py b/main.py
new file mode 100644
index 0000000..dfec1ec
--- /dev/null
+++ b/main.py
@@ -0,0 +1,76 @@
+import json
+
+# Define the global posts list
+posts = []
+
+# Nicking the code to read from the bsky firehose here: 
+# https://gist.github.com/stuartlangridge/20ffe860fee0ecc315d3878c1ea77c35
+def append_post(json_data):
+    # Parse JSON data and append to
+
+
+#
+# Basic idea: 
+# - Get a feed.
+# - Collect basic data on the author
+# - Collect four weeks' posts
+# - Analyse each post: 
+#   - Check text with Hive and Detectora
+#   - Check images with Hive and AIorNot
+#   - Check video by isolating audio to AIorNot
+
+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))
+
+
+# Also look at this: 
+# https://social-media-ethics-automation.github.io/book/bsky/ch04_data/05_data_python_platform/03_demo_data_from_platform.html
+
+def main():
+    client.start(on_message_handler)
+    return
+
+
+
+if __name__ == "__main__":
+    main()
\ No newline at end of file
-- 
GitLab