Merge branch 'develop' of github.com:tikazyq/crawlab into develop

2026-01-26 17:49:15 +01:00 · 2019-06-06 20:16:47 +08:00
parent 560428bf6a fee7d4dfac
commit b736102fb9
1 changed files with 4 additions and 1 deletions
--- a/crawlab/routes/spiders.py
+++ b/crawlab/routes/spiders.py
@@ -509,7 +509,10 @@ class SpiderApi(BaseApi):
                   }, r.status_code

        # get html parse tree
-        sel = etree.HTML(r.content)
+        try:
+            sel = etree.HTML(r.content.decode('utf-8'))
+        except Exception as err:
+            sel = etree.HTML(r.content)

        # remove unnecessary tags
        unnecessary_tags = [