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>
36 lines
1.1 KiB
Python
36 lines
1.1 KiB
Python
"""
|
|
Migration 0006 - Precomputing workflow crawl stats
|
|
"""
|
|
|
|
from btrixcloud.crawlconfigs import stats_recompute_all
|
|
from btrixcloud.migrations import BaseMigration
|
|
|
|
|
|
MIGRATION_VERSION = "0006"
|
|
|
|
|
|
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.
|
|
|
|
Add data on workflow crawl statistics that was previously dynamically
|
|
computed when needed to the database.
|
|
"""
|
|
# pylint: disable=duplicate-code
|
|
crawl_configs = self.mdb["crawl_configs"]
|
|
crawls = self.mdb["crawls"]
|
|
|
|
async for config in crawl_configs.find({"inactive": {"$ne": True}}):
|
|
config_id = config["_id"]
|
|
try:
|
|
await stats_recompute_all(crawl_configs, crawls, config_id)
|
|
# pylint: disable=broad-exception-caught
|
|
except Exception as err:
|
|
print(f"Unable to update workflow {config_id}: {err}", flush=True)
|