14189b7cfb
Fixes #1502 - Adds pages to database as they get added to Redis during crawl - Adds migration to add pages to database for older crawls from pages.jsonl and extraPages.jsonl files in WACZ - Adds GET, list GET, and PATCH update endpoints for pages - Adds POST (add), PATCH, and POST (delete) endpoints for page notes, each with their own id, timestamp, and user info in addition to text - Adds page_ops methods for 1. adding resources/urls to page, and 2. adding automated heuristics and supplemental info (mime, type, etc.) to page (for use in crawl QA job) - Modifies `Migration` class to accept kwargs so that we can pass in ops classes as needed for migrations - Deletes WACZ files and pages from database for failed crawls during crawl_finished process - Deletes crawl pages when a crawl is deleted Note: Requires a crawler version 1.0.0 beta3 or later, with support for `--writePagesToRedis` to populate pages at crawl completion. Beta 4 is configured in the test chart, which should be upgraded to stable 1.0.0 when it's released. Connected to https://github.com/webrecorder/browsertrix-crawler/pull/464 --------- Co-authored-by: Ilya Kreymer <ikreymer@gmail.com>
49 lines
1.4 KiB
Python
49 lines
1.4 KiB
Python
"""
|
|
Migration 0011 - Remove None CRAWL_TIMEOUT values from configmaps
|
|
"""
|
|
|
|
import os
|
|
|
|
from btrixcloud.k8sapi import K8sAPI
|
|
|
|
from btrixcloud.migrations import BaseMigration
|
|
|
|
|
|
MIGRATION_VERSION = "0011"
|
|
|
|
|
|
class Migration(BaseMigration):
|
|
"""Migration class."""
|
|
|
|
# pylint: disable=unused-argument
|
|
def __init__(self, mdb, **kwargs):
|
|
super().__init__(mdb, migration_version=MIGRATION_VERSION)
|
|
|
|
async def migrate_up(self):
|
|
"""Perform migration up.
|
|
|
|
Replace any None values in configmaps for CRAWL_TIMEOUT with 0.
|
|
"""
|
|
k8s_api_instance = K8sAPI()
|
|
crawler_namespace = os.environ.get("CRAWLER_NAMESPACE") or "crawlers"
|
|
config_maps = await k8s_api_instance.core_api.list_namespaced_config_map(
|
|
namespace=crawler_namespace
|
|
)
|
|
for item in config_maps.items:
|
|
try:
|
|
crawl_timeout = item.data["CRAWL_TIMEOUT"]
|
|
if crawl_timeout not in (None, "None"):
|
|
continue
|
|
|
|
item.data["CRAWL_TIMEOUT"] = "0"
|
|
|
|
await k8s_api_instance.core_api.patch_namespaced_config_map(
|
|
name=item.metadata.name, namespace=crawler_namespace, body=item
|
|
)
|
|
|
|
# pylint: disable=broad-exception-caught
|
|
except Exception as err:
|
|
print(
|
|
f"Error modifying configmap CRAWL_TIMEOUT value: {err}", flush=True
|
|
)
|