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>
48 lines
1.4 KiB
Python
48 lines
1.4 KiB
Python
"""
|
|
Migration 0026 -- Crawl Pages
|
|
"""
|
|
|
|
from btrixcloud.migrations import BaseMigration
|
|
from btrixcloud.utils import gather_tasks_with_concurrency
|
|
|
|
|
|
MIGRATION_VERSION = "0026"
|
|
|
|
|
|
class Migration(BaseMigration):
|
|
"""Migration class."""
|
|
|
|
def __init__(self, mdb, **kwargs):
|
|
super().__init__(mdb, migration_version=MIGRATION_VERSION)
|
|
self.page_ops = kwargs["page_ops"]
|
|
|
|
async def migrate_up(self):
|
|
"""Perform migration up.
|
|
|
|
Add pages to database for each crawl without them, pulling from WACZ files.
|
|
"""
|
|
# pylint: disable=duplicate-code
|
|
crawls_mdb = self.mdb["crawls"]
|
|
pages_mdb = self.mdb["pages"]
|
|
|
|
crawl_ids = await crawls_mdb.distinct(
|
|
"_id", {"type": "crawl", "finished": {"$ne": None}}
|
|
)
|
|
crawl_ids_with_pages = await pages_mdb.distinct("crawl_id")
|
|
|
|
crawl_ids_no_pages = list(set(crawl_ids) - set(crawl_ids_with_pages))
|
|
if not crawl_ids_no_pages:
|
|
return
|
|
|
|
all_coroutines = []
|
|
|
|
for crawl_id in crawl_ids_no_pages:
|
|
current_coroutine = self.page_ops.add_crawl_pages_to_db_from_wacz(crawl_id)
|
|
all_coroutines.append(current_coroutine)
|
|
|
|
try:
|
|
await gather_tasks_with_concurrency(*all_coroutines)
|
|
# pylint: disable=broad-exception-caught, raise-missing-from
|
|
except Exception as err:
|
|
print(f"Error adding pages to db: {err}", flush=True)
|