From 6c3a55d70d537abaf87d5e31080ad39b37dfb5ae Mon Sep 17 00:00:00 2001
From: Jacob Babor <jacob@babor.tech>
Date: Sat, 18 Jan 2025 23:06:34 -0600
Subject: [PATCH] Add initial work on odysee scraper doohickey

---
 odyseescraper/models.py | 13 +++++++++-
 odyseescraper/odysee.py | 55 +++++++++++++++++++++++++++++++++++++++++
 2 files changed, 67 insertions(+), 1 deletion(-)
 create mode 100644 odyseescraper/odysee.py

diff --git a/odyseescraper/models.py b/odyseescraper/models.py
index 71a8362..92c2eef 100644
--- a/odyseescraper/models.py
+++ b/odyseescraper/models.py
@@ -1,3 +1,14 @@
+import uuid
 from django.db import models
+from . import odysee
 
-# Create your models here.
+class OdyseeChannel(models.Model):
+    id = models.UUIDField(primary_key=True, default=uuid.uuid4, editable=False)
+    name = models.CharField(max_length=1024)
+    handle = models.CharField(max_length=1024)
+
+class OdyseeRelease(models.Model):
+    id = models.UUIDField(primary_key=True, default=uuid.uuid4, editable=False)
+    channel = models.ForeignKey(OdyseeChannel, on_delete=models.CASCADE)
+    name = models.CharField(max_length=1024)
+    url = models.URLField(max_length=512)
diff --git a/odyseescraper/odysee.py b/odyseescraper/odysee.py
new file mode 100644
index 0000000..2021ba1
--- /dev/null
+++ b/odyseescraper/odysee.py
@@ -0,0 +1,55 @@
+#! /usr/bin/env python3
+import json
+import requests
+
+odysee_url = r'https://odysee.com'
+odysee_api_url = r'https://api.na-backend.odysee.com/api/v1/proxy'
+
+def odysee_get_channel_url(handle):
+    return f'{odysee_url}/{handle}'
+
+def odysee_get_releases(handle):
+    releases = {}
+    try:
+        for i in range(1,20):
+            print(f'Examining page {i} for handle {handle}')
+            payload = {
+                "method": "claim_search",
+                "params": {
+                    "channel": handle,
+                    "page_size": 20,
+                    "page": i
+                }
+            }
+            response = requests.post(odysee_api_url, json=payload)
+            response.raise_for_status()
+            data = response.json()
+            lastpage = data.get("result", {}).get("total_pages", 1)
+            items = data.get("result", {}).get("items", [])
+            for raw_item in items:
+                item = raw_item
+                if item["value_type"] == "repost":
+                    item = raw_item["reposted_claim"]
+                elif item["value_type"] == "stream":
+                    # This is known to be a zip file
+                    pass
+                else:
+                    print(f'Unknown value type, continuing: item["value_type"]')
+                print(f'Importing item {item["claim_id"]}')
+                releases[item["claim_id"]] = {
+                    "name": item.get("name", "Unnamed Release"),
+                    "title": item["value"].get("title", "Untitled Release"),
+                    "description": item["value"].get("description", "No description provided for this release"),
+                    "thumbnail": item["value"].get("thumbnail", {}).get("url", ""),
+                    "url": f"{odysee_url}/{handle}/{item['name']}"
+                }
+            if i == lastpage:
+                break
+    except requests.RequestException as e:
+        print(f'RequestException occurred while getting releases for {handle}: {e}')
+        return None
+    except KeyError as e:
+        print(f'KeyError occurred while getting releases for {handle}: {e}')
+        print(f'Nonzero chance Odysee updated their API out from under you')
+        return None
+    return releases