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>
73 lines
2.5 KiB
Python
73 lines
2.5 KiB
Python
"""
|
|
Migration 0005 - Updating scheduled cron jobs after Operator changes
|
|
"""
|
|
|
|
from btrixcloud.models import CrawlConfig, UpdateCrawlConfig
|
|
from btrixcloud.crawlmanager import CrawlManager
|
|
from btrixcloud.migrations import BaseMigration
|
|
|
|
|
|
MIGRATION_VERSION = "0005"
|
|
|
|
|
|
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.
|
|
|
|
Find existing workflows with schedule and create new crawl_cron_jobs
|
|
from template for each, then delete existing scheduled jobs from
|
|
crawler namespace.
|
|
|
|
Additionally update the configmap for crawl configs with scale > 1
|
|
or crawlTimeout > 0.
|
|
"""
|
|
# pylint: disable=too-many-locals, duplicate-code
|
|
crawl_configs = self.mdb["crawl_configs"]
|
|
crawl_manager = CrawlManager()
|
|
|
|
# Update configmap for crawl configs that have non-zero timeout or scale > 1
|
|
match_query = {
|
|
"$or": [
|
|
{"crawlTimeout": {"$gt": 0}},
|
|
{"scale": {"$gt": 1}},
|
|
{"schedule": {"$nin": ["", None]}},
|
|
]
|
|
}
|
|
async for config_dict in crawl_configs.find(match_query):
|
|
config = CrawlConfig.from_dict(config_dict)
|
|
print(
|
|
f"Updating Crawl Config {config.id}: schedule: {config.schedule}, "
|
|
+ f"timeout: {config.crawlTimeout}, scale: {config.scale}"
|
|
)
|
|
try:
|
|
await crawl_manager.update_crawl_config(
|
|
config,
|
|
UpdateCrawlConfig(
|
|
scale=config.scale,
|
|
crawlTimeout=config.crawlTimeout,
|
|
schedule=config.schedule,
|
|
),
|
|
)
|
|
# pylint: disable=broad-except
|
|
except Exception as exc:
|
|
print(
|
|
"Skip crawl config migration due to error, likely missing config",
|
|
exc,
|
|
)
|
|
|
|
# Delete existing scheduled jobs from crawler namespace
|
|
print("Deleting cronjobs from crawler namespace")
|
|
await crawl_manager.batch_api.delete_collection_namespaced_cron_job(
|
|
namespace=crawl_manager.namespace
|
|
)
|
|
result = await crawl_manager.batch_api.list_namespaced_cron_job(
|
|
namespace=crawl_manager.namespace
|
|
)
|
|
assert len(result.items) == 0
|