diff options
| author | Bnyro <bnyro@tutanota.com> | 2025-12-01 15:19:06 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-12-01 15:19:06 +0100 |
| commit | ab8224c9394236d2cbcf6ec7d9bf0d7c602ca6ac (patch) | |
| tree | 84245e49b761b87806abeda80068a27265a111e6 /searx | |
| parent | c954e71f87d41ef5b70c0d20eb8c1ee5284573e2 (diff) | |
[fix] brave: content description also contains website URL (#5502)
there are other classes like 'site-name-content' we don't want to match,
however only using contains(@class, 'content') would e.g. also match `site-name-content`
thus, we explicitly also require the spaces as class separator
Diffstat (limited to 'searx')
| -rw-r--r-- | searx/engines/brave.py | 5 |
1 files changed, 4 insertions, 1 deletions
diff --git a/searx/engines/brave.py b/searx/engines/brave.py index 2c5854705..a19046b77 100644 --- a/searx/engines/brave.py +++ b/searx/engines/brave.py @@ -301,7 +301,10 @@ def _parse_search(resp: SXNG_Response) -> EngineResults: content: str = "" pub_date = None - _content = eval_xpath_getindex(result, ".//div[contains(@class, 'content')]", 0, default="") + # there are other classes like 'site-name-content' we don't want to match, + # however only using contains(@class, 'content') would e.g. also match `site-name-content` + # thus, we explicitly also require the spaces as class separator + _content = eval_xpath_getindex(result, ".//div[contains(concat(' ', @class, ' '), ' content ')]", 0, default="") if len(_content): content = extract_text(_content) # type: ignore _pub_date = extract_text( |