From 390bca11881b7fc4309200b8dc60c38328bbd58e Mon Sep 17 00:00:00 2001 From: Magnus Hagander Date: Wed, 25 May 2016 15:37:32 +0200 Subject: [PATCH] Update for https Uncommented "add length 7" to array deindex seems to have come from it being the length of http://. Now changed to https://, so change the length as well, and properly comment it. --- tools/search/crawler/lib/sitemapsite.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tools/search/crawler/lib/sitemapsite.py b/tools/search/crawler/lib/sitemapsite.py index a6f5ae83..4534a456 100644 --- a/tools/search/crawler/lib/sitemapsite.py +++ b/tools/search/crawler/lib/sitemapsite.py @@ -69,7 +69,8 @@ class SitemapSiteCrawler(BaseSiteCrawler): u.close() for url, prio, lastmod in p.urls: - url = url[len(self.hostname)+7:] + # Advance 8 characters - length of https://. + url = url[len(self.hostname)+8:] if lastmod: if self.scantimes.has_key(url): if lastmod < self.scantimes[url]: -- 2.39.5