Cache Goodreads data and slow down bulk requests

tools/content/goodreads.py

@@ -22,6 +22,10 @@ REQUEST_HEADERS = {
 }
 
 
+class BlockedError(ValueError):
+    pass
+
+
 class PageResult:
     def __init__(self, status: int, final_url: str, text: str):
         self.status = status
@@ -168,10 +172,14 @@ def scrape_book(url: str) -> dict:
     if not identifier:
         raise ValueError(f"not a Goodreads book url: {url}")
     page = download_page(url)
+    raise_if_blocked(page)
+    return parse_book(page.text, identifier)
+
+
+def raise_if_blocked(page: PageResult):
     reason = blocked_reason(page.text)
     if reason:
-        raise ValueError(reason)
-    return parse_book(page.text, identifier)
+        raise BlockedError(f"Goodreads is rate limiting requests ({reason}), wait a few minutes and try again")
 
 
 def print_diagnostics(url: str, save_path: Path | None):