From b97b8f67845fa2aa5430b71077f447a9ce8ba534 Mon Sep 17 00:00:00 2001 From: Simon Date: Sun, 17 Jun 2018 22:17:21 -0400 Subject: [PATCH] Temporary fix for decoding errors --- crawl_server/remote_http.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/crawl_server/remote_http.py b/crawl_server/remote_http.py index 2775703..2547da0 100644 --- a/crawl_server/remote_http.py +++ b/crawl_server/remote_http.py @@ -164,7 +164,7 @@ class HttpDirectory(RemoteDirectory): parser = HTMLAnchorParser() for chunk in body: - parser.feed(chunk.decode("utf-8")) + parser.feed(chunk.decode("utf-8", errors="ignore")) for anchor in parser.anchors: yield anchor