From 5a6b814c7935ccc1571abd8d5b2487186cac96c7 Mon Sep 17 00:00:00 2001 From: jdcaballerov Date: Tue, 24 Nov 2020 09:35:06 -0500 Subject: [PATCH] Add exception handling for indexable content reader --- archivebox/search/__init__.py | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/archivebox/search/__init__.py b/archivebox/search/__init__.py index a262d926..ebeebcd0 100644 --- a/archivebox/search/__init__.py +++ b/archivebox/search/__init__.py @@ -97,6 +97,14 @@ def index_links(links: Union[List[Link],None], out_dir: Path=OUTPUT_DIR): for link in links: if snap := Snapshot.objects.filter(url=link.url).first(): results = ArchiveResult.objects.indexable().filter(snapshot=snap) - texts = get_indexable_content(results) log_index_started(link.url) - write_search_index(link, texts, out_dir=out_dir) + try: + texts = get_indexable_content(results) + except Exception as err: + stderr() + stderr( + f'[X] An Exception ocurred reading the indexable content={err}:', + color='red', + ) + else: + write_search_index(link, texts, out_dir=out_dir) \ No newline at end of file