Selenium based missing kid verify url

This commit is contained in:
Luciano Gervasoni
2025-07-07 16:02:11 +02:00
parent 15035c108d
commit a8b236bac0
3 changed files with 82 additions and 6 deletions

View File

@@ -115,12 +115,14 @@ class DB_Handler():
# Set duplicate, and insert new canonical form
self._set_duplicate_and_insert_canonical(obj_url, url_canonical)
elif (r.status_code == 200):
self._set_status(obj_url, Urls.STATUS_ENUM.VALID)
# Not enough to determine if it is valid. Need to wait to finish javascript, it might redirect to 404
# self._set_status(obj_url, Urls.STATUS_ENUM.VALID)
self._set_status(obj_url, Urls.STATUS_ENUM.UNKNOWN)
elif (r.status_code == 404):
self._set_status(obj_url, Urls.STATUS_ENUM.INVALID)
else:
logger.info("Unknown request status: {} for missing kids request: {}".format(r.status_code, obj_url.url))
logger.debug("Unknown request status: {} for missing kids request: {}".format(r.status_code, obj_url.url))
self._set_status(obj_url, Urls.STATUS_ENUM.UNKNOWN)
return
##########################################################################
@@ -275,18 +277,37 @@ class DB_Handler():
missingkids_urls = Urls.objects.order_by("-ts_fetch").filter(
(Q(url__contains="missingkids.org/poster") | Q(url__contains="missingkids.org/new-poster"))
&
(Q(status=Urls.STATUS_ENUM.VALID) | Q(status=Urls.STATUS_ENUM.INVALID) | Q(status=Urls.STATUS_ENUM.ERROR))
(Q(status=Urls.STATUS_ENUM.VALID) | Q(status=Urls.STATUS_ENUM.INVALID) | Q(status=Urls.STATUS_ENUM.UNKNOWN) | Q(status=Urls.STATUS_ENUM.ERROR))
)
# Get batch size
if (batch_size is not None):
missingkids_urls = missingkids_urls[:batch_size]
# TODO: Cache processed during last X hours, filter them...
# Per URL
for obj_url in missingkids_urls:
try:
# Process URL
self._process_single_url(obj_url, status_pattern_match=None, raise_exception_on_error=None)
# Missing kids fetching endpoint, verify URL
missingkids_fetch_endpoint = os.path.join(os.getenv("SELENIUM_ENDPOINT", "http://localhost:80"), "verify_missing_kid/")
data = {"url": obj_url.url}
# POST
r = requests.post(missingkids_fetch_endpoint, json=data)
# Jsonify
results = r.json()
if (results.get("status") == "valid"):
self._set_status(obj_url, Urls.STATUS_ENUM.VALID)
elif (results.get("status") == "invalid"):
self._set_status(obj_url, Urls.STATUS_ENUM.INVALID)
elif (results.get("status") == "duplicate"):
self._set_duplicate_and_insert_canonical(obj_url, results.get("redirection"))
elif (results.get("status") == "unknown"):
# Nothing to do, not sure about it...
logger.info("Missing kid verification returned unknown for URL: {}".format(obj_url.url))
pass
except Exception as e:
logger.warning("Unknown error processing missing kids poster for URL: {}\n{}".format(obj_url.url, str(e)))