From 9bcca427a0b59b4fe7cd7addea2b6309305285cd Mon Sep 17 00:00:00 2001
From: msramalho <19508417+msramalho@users.noreply.github.com>
Date: Thu, 2 Feb 2023 12:41:06 +0000
Subject: [PATCH] wacz in gsheets

---
 src/auto_archiver/databases/gsheet_db.py     | 15 +++++----------
 src/auto_archiver/enrichers/wacz_enricher.py |  3 +++
 2 files changed, 8 insertions(+), 10 deletions(-)

diff --git a/src/auto_archiver/databases/gsheet_db.py b/src/auto_archiver/databases/gsheet_db.py
index 8721725..8c711e8 100644
--- a/src/auto_archiver/databases/gsheet_db.py
+++ b/src/auto_archiver/databases/gsheet_db.py
@@ -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)
 
diff --git a/src/auto_archiver/enrichers/wacz_enricher.py b/src/auto_archiver/enrichers/wacz_enricher.py
index 49bc6a8..9b69d91 100644
--- a/src/auto_archiver/enrichers/wacz_enricher.py
+++ b/src/auto_archiver/enrichers/wacz_enricher.py
@@ -20,6 +20,9 @@ class WaczEnricher(Enricher):
         return {
             "profile": {"default": None, "help": "browsertrix-profile (for profile generation see https://github.com/webrecorder/browsertrix-crawler#creating-and-using-browser-profiles)."},
             "timeout": {"default": 90, "help": "timeout for WACZ generation in seconds"},
+            # #TODO: make WACZ conditional because it is not useful for some URLs and takes a long time
+            # "enrich_if_success": {"default": True, 
+            # "help": "if False will not enrich when a previous archiver has worked successfully."},
         }
 
     def enrich(self, to_enrich: Metadata) -> bool: