Scrapy, a fast high-level web crawling & scraping framework for Python.
Add try/except to safe_url_string()
Samuel Bartlett90ce6589eee5
diff --git a/scrapy/linkextractors/lxmlhtml.py b/scrapy/linkextractors/lxmlhtml.pyindex dd8dcdf7c..1ee81427c 100644--- a/scrapy/linkextractors/lxmlhtml.py+++ b/scrapy/linkextractors/lxmlhtml.py@@ -88,7 +88,11 @@ class LxmlParserLinkExtractor:url = self.process_attr(attr_val)if url is None:continue- url = safe_url_string(url, encoding=response_encoding)+ try:+ url = safe_url_string(url, encoding=response_encoding)+ except ValueError:+ continue # Disregard badly formatted urls+# to fix relative links after process_valueurl = urljoin(response_url, url)link = Link(