feat(tames) ongoing case scraper

.github/workflows/lint.yml

@@ -85,4 +85,5 @@ jobs:
           cl/corpus_importer/management/commands/import_texas_dockets.py \
           cl/corpus_importer/management/utils.py \
           cl/lib/decorators.py \
-          cl/corpus_importer/management/commands/import_scotus_dockets.py
+          cl/corpus_importer/management/commands/import_scotus_dockets.py \
+          cl/scrapers/management/commands/tames_poller.py

cl/corpus_importer/tasks.py

@@ -4041,6 +4041,9 @@ def download_texas_document_unthrottled(
     return _download_texas_document(self, texas_document_pk)
 
 
+TAMES_PENDING_SUBSCRIPTIONS_KEY = "tames:pending_subscriptions"
+
+
 class MergeResult[T = int](NamedTuple):
     """Stores data about the result of an attempted merge operation."""
 
@@ -4990,6 +4993,7 @@ def texas_ingest_docket_task(
     task: Task,
     i: tuple[bytes, TexasDocketMeta],
     download_attachments: bool = True,
+    subscription_data: str | None = None,
 ) -> MergeResult:
     """
     Task to parse and merge a Texas docket.
@@ -5000,6 +5004,8 @@ def texas_ingest_docket_task(
     - Bytes string to parse.
     - Docket metadata.
     :param download_attachments: Whether to download docket entry attachments.
+    :param subscription_data: Optional JSON string to add to the pending
+        subscriptions Redis SET when a new docket is created.
 
     :return: The result of the merge operation.
     """
@@ -5032,9 +5038,13 @@ def texas_ingest_docket_task(
         )
         task.request.chain = None
         return MergeResult.failed()
-    return merge_texas_docket(
+    result = merge_texas_docket(
         docket_data, download_attachments=download_attachments
     )
+    if subscription_data and result.create and result.pk is not None:
+        redis = get_redis_interface("CACHE")
+        redis.sadd(TAMES_PENDING_SUBSCRIPTIONS_KEY, subscription_data)
+    return result
 
 
 @app.task(

cl/lib/exceptions.py

@@ -4,6 +4,18 @@ class ScrapeFailed(Exception):
     pass
 
 
+class ConfigurationException(Exception):
+    """Raised when required configuration is not set."""
+
+    pass
+
+
+class SubscriptionFailure(Exception):
+    """Raised when subscribing to case updates fails."""
+
+    pass
+
+
 class NoSuchKey(Exception):
     """Raised when an S3 key does not exist."""
 

cl/scrapers/management/commands/back_scrape_dockets.py

@@ -250,7 +250,7 @@ def save_docket_response(
     case_meta: dict,
     court_id: str = "unknown_court",
     skip_meta: bool = False,
-) -> None:
+) -> tuple[str, str]:
     """Store docket scraper response content and headers in S3.
 
     Args:
@@ -259,6 +259,10 @@ def save_docket_response(
         court_id: Court identifier extracted from response data
         case_meta: Optional metadata dict from the scraper (e.g., case_number,
             date_filed, etc.) to save alongside the response
+
+    Returns:
+        Tuple of (bucket_name, base_key) for locating stored files. HTML
+        is at ``{base_key}.html``, meta at ``{base_key}_meta.json``.
     """
     storage = S3GlacierInstantRetrievalStorage(
         naming_strategy=clobbering_get_name
@@ -288,6 +292,8 @@ def save_docket_response(
     content_name = f"{base_name}.{extension}"
     storage.save(content_name, ContentFile(content))
 
+    return storage.bucket_name, base_name
+
 
 def parse_date_filed(date_str: str | None) -> date | None:
     """Parse a date_filed string in '%m/%d/%Y' format to a date object."""