From 99128537a8b6d011f545b4c3598290c83d9f1e2f Mon Sep 17 00:00:00 2001 From: Markus Heiser Date: Tue, 18 Jan 2022 13:23:35 +0100 Subject: [PATCH] [fix] googel engine - "some results are invalids: invalid content" Fix google issues listet in the `/stats?engine=google` and message:: some results are invalids: invalid content The log is:: DEBUG searx : result: invalid content: {'url': 'https://de.wikipedia.org/wiki/Foo', 'title': 'Foo - Wikipedia', 'content': None, 'engine': 'google'} WARNING searx.engines.google : ErrorContext('searx/search/processors/abstract.py', 111, 'result_container.extend(self.engine_name, search_results)', None, 'some results are invalids: invalid content', ()) True Signed-off-by: Markus Heiser --- searx/engines/google.py | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/searx/engines/google.py b/searx/engines/google.py index 95fa7e2b..36adc3e4 100644 --- a/searx/engines/google.py +++ b/searx/engines/google.py @@ -291,24 +291,27 @@ def response(resp): title_tag = eval_xpath_getindex(result, title_xpath, 0, default=None) if title_tag is None: # this not one of the common google results *section* - logger.debug('ingoring
section: missing title') + logger.debug('ingoring item from the result_xpath list: missing title') continue title = extract_text(title_tag) url = eval_xpath_getindex(result, href_xpath, 0, None) if url is None: continue content = extract_text(eval_xpath_getindex(result, content_xpath, 0, default=None), allow_none=True) + if content is None: + logger.debug('ingoring item from the result_xpath list: missing content of title "%s"', title) + continue + + logger.debug('add link to results: %s', title) + results.append({ 'url': url, 'title': title, 'content': content }) + except Exception as e: # pylint: disable=broad-except logger.error(e, exc_info=True) - # from lxml import etree - # logger.debug(etree.tostring(result, pretty_print=True)) - # import pdb - # pdb.set_trace() continue # parse suggestion