def process_recap_attachment(self, pk, tag_names=None):
"""Process an uploaded attachment page from the RECAP API endpoint.
:param pk: The primary key of the processing queue item you want to work on
:param tag_names: A list of tag names to add to all items created or
modified in this function.
:return: Tuple indicating the status of the processing and a related
message
"""
pq = ProcessingQueue.objects.get(pk=pk)
mark_pq_status(pq, "", PROCESSING_STATUS.IN_PROGRESS)
logger.info("Processing RECAP item (debug is: %s): %s" % (pq.debug, pq))
with open(pq.filepath_local.path) as f:
text = f.read().decode("utf-8")
att_data = get_data_from_att_report(text, pq.court_id)
logger.info("Parsing completed for item %s" % pq)
if att_data == {}:
# Bad attachment page.
msg = "Not a valid attachment page upload."
self.request.chain = None
return mark_pq_status(pq, msg, PROCESSING_STATUS.INVALID_CONTENT)
if pq.pacer_case_id in ["undefined", "null"]:
# Bad data from the client. Fix it with parsed data.
pq.pacer_case_id = att_data.get("pacer_case_id")
pq.save()
try:
rds_affected, de = merge_attachment_page_data(
pq.court,
pq.pacer_case_id,
att_data["pacer_doc_id"],
att_data["document_number"],
text,
att_data["attachments"],
pq.debug,
)
except RECAPDocument.MultipleObjectsReturned:
msg = ("Too many documents found when attempting to associate "
"attachment data")
return mark_pq_status(pq, msg, PROCESSING_STATUS.FAILED)
except RECAPDocument.DoesNotExist as exc:
msg = "Could not find docket to associate with attachment metadata"
if (self.request.retries == self.max_retries) or pq.debug:
return mark_pq_status(pq, msg, PROCESSING_STATUS.FAILED)
else:
mark_pq_status(pq, msg, PROCESSING_STATUS.QUEUED_FOR_RETRY)
raise self.retry(exc=exc)
add_tags_to_objs(tag_names, rds_affected)
return mark_pq_successful(pq, d_id=de.docket_id, de_id=de.pk)
def fetch_attachment_page(self, fq_pk):
"""Fetch a PACER attachment page by rd_pk
This is very similar to process_recap_attachment, except that it manages
status as it proceeds and it gets the cookie info from redis.
:param fq_pk: The PK of the RECAP Fetch Queue to update.
:return: None
"""
fq = PacerFetchQueue.objects.get(pk=fq_pk)
mark_fq_status(fq, "", PROCESSING_STATUS.IN_PROGRESS)
rd = fq.recap_document
if not rd.pacer_doc_id:
msg = (
"Unable to get attachment page: Unknown pacer_doc_id for "
"RECAP Document object %s" % rd.pk
)
mark_fq_status(fq, msg, PROCESSING_STATUS.NEEDS_INFO)
return
cookies = get_pacer_cookie_from_cache(fq.user_id)
if not cookies:
msg = "Unable to find cached cookies. Aborting request."
mark_fq_status(fq, msg, PROCESSING_STATUS.FAILED)
return
try:
r = get_attachment_page_by_rd(rd.pk, cookies)
except (requests.RequestException, HTTPError):
msg = "Failed to get attachment page from network."
mark_fq_status(fq, msg, PROCESSING_STATUS.FAILED)
return
text = r.response.text
att_data = get_data_from_att_report(text, rd.docket_entry.docket.court_id,)
if att_data == {}:
msg = "Not a valid attachment page upload"
mark_fq_status(fq, msg, PROCESSING_STATUS.INVALID_CONTENT)
return
try:
merge_attachment_page_data(
rd.docket_entry.docket.court,
rd.docket_entry.docket.pacer_case_id,
att_data["pacer_doc_id"],
att_data["document_number"],
text,
att_data["attachments"],
)
except RECAPDocument.MultipleObjectsReturned:
msg = (
"Too many documents found when attempting to associate "
"attachment data"
)
mark_fq_status(fq, msg, PROCESSING_STATUS.FAILED)
return
except RECAPDocument.DoesNotExist as exc:
msg = "Could not find docket to associate with attachment metadata"
if self.request.retries == self.max_retries:
mark_fq_status(fq, msg, PROCESSING_STATUS.FAILED)
return
mark_fq_status(fq, msg, PROCESSING_STATUS.QUEUED_FOR_RETRY)
raise self.retry(exc=exc)
msg = "Successfully completed fetch and save."
mark_fq_status(fq, msg, PROCESSING_STATUS.SUCCESSFUL)