Process missing kids url based on API endpoint

This commit is contained in:
Luciano Gervasoni
2025-09-08 16:12:27 +02:00
parent 1fbc5beb6e
commit 079b2473f8
5 changed files with 86 additions and 48 deletions

View File

@@ -4,7 +4,7 @@ from django.core.cache import cache
from django.db import IntegrityError
from django.utils import timezone
from datetime import timedelta
from .fetch_utils_url_processor import process_url, get_with_protocol, url_host_slowdown
from .fetch_utils_url_processor import process_url, verify_missing_kid_url
import re
import requests
import os
@@ -16,7 +16,15 @@ class DB_Handler():
def __init__(self):
pass
def insert_raw_urls(self, urls, obj_source, obj_search):
def insert_raw_urls(self, urls, obj_source, obj_search):
def get_with_protocol(url):
# http:// -> https://
url = url.replace("http://", "https://")
# "" -> https://
if not (url.startswith("https://")):
url = "https://" + url
return url
try:
logger.debug("Inserting raw URLs")
# Empty?
@@ -104,11 +112,9 @@ class DB_Handler():
##########################################################################
# URL pattern: missingkids.org/poster OR missingkids.org/new-poster
if ("missingkids.org" in obj_url.url) and ("poster" in obj_url.url):
# Sleep required? To avoid too many requests error (original URL, not paywall bypassing endpoint)
url_host_slowdown(obj_url.url, url_host_slowdown_seconds=float(os.getenv("FETCHER_URL_HOST_SLEEP", 5)))
try:
# Request
r = requests.get(obj_url.url, allow_redirects=True)
# Verify missing kid URL
results = verify_missing_kid_url(obj_url.url)
except Exception as e:
if (raise_exception_on_error):
# Simply raise exception, handled in a different way
@@ -118,20 +124,16 @@ class DB_Handler():
# Set status to error
self._set_status(obj_url, Urls.STATUS_ENUM.ERROR)
return
if (r.url != obj_url.url):
# Canonical
url_canonical = r.url
# Set duplicate, and insert new canonical form
self._set_duplicate_and_insert_canonical(obj_url, url_canonical)
elif (r.status_code == 200):
# 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):
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)
else:
logger.debug("Unknown request status: {} for missing kids request: {}".format(r.status_code, obj_url.url))
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))
self._set_status(obj_url, Urls.STATUS_ENUM.UNKNOWN)
return
##########################################################################
@@ -314,14 +316,20 @@ class DB_Handler():
# Per URL
for obj_url in missingkids_urls:
try:
# 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, timeout=120)
# Jsonify
results = r.json()
logger.debug("Selenium results for URL {}: {}".format(obj_url.url, str(results)))
SELENIUM_BASED_MISSINGKID_VERIFICATION = False
if (SELENIUM_BASED_MISSINGKID_VERIFICATION):
# 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, timeout=120)
# Jsonify
results = r.json()
logger.debug("Missingkids Selenium results for URL {}: {}".format(obj_url.url, str(results)))
else:
# Verify
results = verify_missing_kid_url(obj_url.url)
logger.debug("Missingkids verify results for URL {}: {}".format(obj_url.url, str(results)))
if (results.get("status") == "valid"):
self._set_status(obj_url, Urls.STATUS_ENUM.VALID)