From c6e0e7c5078ea20e0edaf063deb25fde57859d5b Mon Sep 17 00:00:00 2001 From: Noah Levitt Date: Wed, 11 May 2016 00:45:47 +0000 Subject: [PATCH] correctly handle site with no pages (which means the seed was blocked by robots.txt) in frontier.seed_page --- brozzler/frontier.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/brozzler/frontier.py b/brozzler/frontier.py index 72934a8..704c0e5 100644 --- a/brozzler/frontier.py +++ b/brozzler/frontier.py @@ -313,6 +313,8 @@ class RethinkDbFrontier: if len(pages) > 1: self.logger.warn( "more than one seed page for site_id %s ?", site_id) + if len(pages) < 1: + return None return brozzler.Page(**pages[0]) def site_pages(self, site_id, unbrozzled_only=False):