diff options
| author | Markus Heiser <markus.heiser@darmarit.de> | 2025-01-20 11:45:00 +0100 |
|---|---|---|
| committer | Markus Heiser <markus.heiser@darmarIT.de> | 2025-01-20 16:40:36 +0100 |
| commit | e581921c9229f11a9ab23de2963b020546f2be0d (patch) | |
| tree | f2ad01d6481618b22f5c9424dd31863760a22a3b | |
| parent | 073d9549a00362cb6fe0398396e139bc93ed4918 (diff) | |
[fix] engine brave: remove date from the content string
Related: https://github.com/searxng/searxng/issues/4211#issuecomment-2601941440
Closes: https://github.com/searxng/searxng/issues/4006
Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
| -rw-r--r-- | searx/engines/brave.py | 12 |
1 files changed, 9 insertions, 3 deletions
diff --git a/searx/engines/brave.py b/searx/engines/brave.py index 648aee562..db1fc7976 100644 --- a/searx/engines/brave.py +++ b/searx/engines/brave.py @@ -291,15 +291,21 @@ def _parse_search(resp): if url is None or title_tag is None or not urlparse(url).netloc: # partial url likely means it's an ad continue - content_tag = eval_xpath_getindex(result, './/div[contains(@class, "snippet-description")]', 0, default='') + content: str = extract_text( + eval_xpath_getindex(result, './/div[contains(@class, "snippet-description")]', 0, default='') + ) # type: ignore pub_date_raw = eval_xpath(result, 'substring-before(.//div[contains(@class, "snippet-description")], "-")') + pub_date = _extract_published_date(pub_date_raw) + if pub_date and content.startswith(pub_date_raw): + content = content.lstrip(pub_date_raw).strip("- \n\t") + thumbnail = eval_xpath_getindex(result, './/img[contains(@class, "thumb")]/@src', 0, default='') item = { 'url': url, 'title': extract_text(title_tag), - 'content': extract_text(content_tag), - 'publishedDate': _extract_published_date(pub_date_raw), + 'content': content, + 'publishedDate': pub_date, 'thumbnail': thumbnail, } |