improve parsing json with error message

Dockerfile

@@ -1,6 +1,6 @@
 # syntax=docker/dockerfile:1.5
 ARG BUILDPLATFORM=linux/amd64
-FROM --platform=$BUILDPLATFORM python:3.12-bookworm as builder
+FROM --platform=$BUILDPLATFORM python:3.12-bookworm AS builder
 
 # Dockerfile that builds the Rogue Scholar API Docker image. Based on the following:
 # - https://medium.com/@albertazzir/blazing-fast-python-docker-builds-with-poetry-a78a66f5aed0
@@ -11,7 +11,7 @@ FROM --platform=$BUILDPLATFORM python:3.12-bookworm as builder
 # Install OS package dependency: pandoc
 # install poetry to manage Python dependencies
 ENV PANDOC_VERSION=3.1.12.3 \
-    POETRY_VERSION=1.8.2
+    POETRY_VERSION=1.8.3
 
 ADD https://github.com/jgm/pandoc/releases/download/${PANDOC_VERSION}/pandoc-${PANDOC_VERSION}-1-amd64.deb /tmp/pandoc-${PANDOC_VERSION}-1-amd64.deb
 
@@ -35,7 +35,7 @@ RUN touch README.md
 RUN --mount=type=cache,target=$POETRY_CACHE_DIR poetry install --without dev --no-root --no-interaction --no-ansi
 
 
-FROM --platform=$BUILDPLATFORM python:3.12-slim-bookworm as runtime
+FROM --platform=$BUILDPLATFORM python:3.12-slim-bookworm AS runtime
 
 # Install OS package dependency (for weasyprint): pango
 RUN --mount=type=cache,target=/var/cache/apt apt-get update -y && \

api/posts.py

@@ -4,6 +4,7 @@
 from typing import Optional
 from furl import furl
 import httpx
+import json as JSON
 import asyncio
 import re
 import pydash as py_
@@ -195,7 +196,7 @@ async def extract_all_posts_by_blog(
 
         feed_url = url.set(params).url
         blog_with_posts = {}
-        # print(feed_url)
+        print(f"Extracting posts from {blog['slug']} at {feed_url}.")
 
         # use pagination of results only for non-API blogs
         if params:
@@ -214,7 +215,10 @@ async def extract_all_posts_by_blog(
         elif generator == "WordPress" and blog["use_api"]:
             async with httpx.AsyncClient() as client:
                 response = await client.get(feed_url, timeout=30, follow_redirects=True)
-                posts = response.json()
+                # filter out error messages that are not valid json
+                json_start = response.text.find('[{')
+                response = response.text[json_start:]
+                posts = JSON.loads(response)
                 if not update_all:
                     posts = filter_updated_posts(posts, blog, key="modified_gmt")
                 extract_posts = [extract_wordpress_post(x, blog) for x in posts]

api/works.py

@@ -2,6 +2,11 @@
 from os import environ
 import httpx
 
+# from api.supabase import (
+#     supabase_client as supabase,
+#     supabase_admin_client as supabase_admin,
+# )
+
 # supported accept headers for content negotiation
 SUPPORTED_ACCEPT_HEADERS = [
     "application/vnd.commonmeta+json",