From 86144935e338a9f02d626dab959b375ff5c2b07b Mon Sep 17 00:00:00 2001 From: Simon Date: Sat, 16 Jun 2018 15:30:44 -0400 Subject: [PATCH] Attempt to fix Unicode errors part two --- 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 1ad4b50..c146b49 100644 --- a/crawl_server/remote_http.py +++ b/crawl_server/remote_http.py @@ -113,7 +113,7 @@ class HttpDirectory(RemoteDirectory): for link in links: result.append((link.text, link.get("href"))) except UnicodeDecodeError: - tree = etree.HTML(body.decode("utf-8", errors="ignore"), parser=self.parser) + tree = etree.HTML(body.decode("utf-8", errors="ignore").encode("utf-8"), parser=self.parser) links = [] try: links = tree.findall(".//a/[@href]")