diff options
| author | Grant Lanham <contact@grantlanham.com> | 2024-07-08 15:16:53 -0400 |
|---|---|---|
| committer | Markus Heiser <markus.heiser@darmarIT.de> | 2024-07-15 06:58:39 +0200 |
| commit | 9a4fa7cc4f0339a1ea696f6fb7068fd6156f03e2 (patch) | |
| tree | dcce202c714c4b8b66ed704cd8e0b14843760e17 | |
| parent | 2039060b640189e250020e6e17db10b0a0730e7e (diff) | |
| download | searxng-9a4fa7cc4f0339a1ea696f6fb7068fd6156f03e2.tar.gz searxng-9a4fa7cc4f0339a1ea696f6fb7068fd6156f03e2.zip | |
Update mullvad_leta.py to account for img_elem
A recent update from Mullvad Leta introduced the img_elem. This update
broke the existing logic. Now, by checking the length of the dom_result
to see if it was included in the return results, we can handle the logic
accordingly.
| -rw-r--r-- | searx/engines/mullvad_leta.py | 15 |
1 files changed, 11 insertions, 4 deletions
diff --git a/searx/engines/mullvad_leta.py b/searx/engines/mullvad_leta.py index a1e59d93b..7e2b590e8 100644 --- a/searx/engines/mullvad_leta.py +++ b/searx/engines/mullvad_leta.py @@ -128,7 +128,14 @@ def request(query: str, params: dict): def extract_result(dom_result: list[html.HtmlElement]): - [a_elem, h3_elem, p_elem] = dom_result + # Infoboxes sometimes appear in the beginning and will have a length of 0 + if len(dom_result) == 3: + [a_elem, h3_elem, p_elem] = dom_result + elif len(dom_result) == 4: + [_, a_elem, h3_elem, p_elem] = dom_result + else: + return None + return { 'url': extract_text(a_elem.text), 'title': extract_text(h3_elem), @@ -139,9 +146,9 @@ def extract_result(dom_result: list[html.HtmlElement]): def extract_results(search_results: html.HtmlElement): for search_result in search_results: dom_result = eval_xpath_list(search_result, 'div/div/*') - # sometimes an info box pops up, will need to filter that out - if len(dom_result) == 3: - yield extract_result(dom_result) + result = extract_result(dom_result) + if result is not None: + yield result def response(resp: Response): |