bellingcat/auto-archiver
1
0
Fork 0
mirror of https://github.com/bellingcat/auto-archiver.git synced 2026-06-11 20:58:29 +03:00
Code Issues Packages Projects Releases Wiki Activity

wacz in gsheets

Browse Source
This commit is contained in:
msramalho
2023-02-02 12:41:06 +00:00
parent 77a8c290f7
commit 9bcca427a0
2 changed files with 8 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
src/auto_archiver/databases/gsheet_db.py
View File

@@ -1,5 +1,6 @@
from typing import Union, Tuple
import datetime
from urllib.parse import quote
# from metadata import Metadata
from loguru import logger
@@ -45,7 +46,7 @@ class GsheetsDb(Database):
def done(self, item: Metadata) -> None:
"""archival result ready - should be saved to DB"""
logger.success(f"DONE {item}")
logger.success(f"DONE {item.get_url()}")
gw, row = self._retrieve_gsheet(item)
# self._safe_status_update(item, 'done')
@@ -68,16 +69,10 @@ class GsheetsDb(Database):
batch_if_valid('timestamp', item.get_timestamp())
if (screenshot := item.get_media_by_id("screenshot")):
batch_if_valid('screenshot', "\n".join(screenshot.urls))
# batch_if_valid('status', item.status)
# TODO: AFTER ENRICHMENTS
# batch_if_valid('hash', media.hash)
# batch_if_valid('thumbnail', result.thumbnail, f'=IMAGE("{result.thumbnail}")')
# batch_if_valid('thumbnail_index', result.thumbnail_index)
# batch_if_valid('duration', result.duration, str(result.duration))
# if result.wacz is not None:
# batch_if_valid('wacz', result.wacz)
# batch_if_valid('replaywebpage', f'https://replayweb.page/?source={quote(result.wacz)}#view=pages&url={quote(url)}')
if (browsertrix := item.get_media_by_id("browsertrix")):
batch_if_valid('wacz', "\n".join(browsertrix.urls))
batch_if_valid('replaywebpage', "\n".join([f'https://replayweb.page/?source={quote(wacz)}#view=pages&url={quote(item.get_url())}' for wacz in browsertrix.urls]))
gw.batch_set_cell(cell_updates)