mirrors/searxng
1
0
Fork 0
mirror of https://github.com/searxng/searxng.git synced 2025-02-28 17:56:48 +00:00
Code Issues Projects Releases Wiki Activity

[fix] engines bing.images & brave.videos - fix parse data string

Browse source 
Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
This commit is contained in:
Markus Heiser 2025-02-20 16:52:35 +01:00 committed by Markus Heiser
parent caf0dd5372
commit 4994fbb5af
1 changed files with 29 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

33
searx/engines/brave.py
View file

@ -131,7 +131,6 @@ from lxml import html
from searx import locales
from searx.utils import (
extract_text,
extr,
eval_xpath,
eval_xpath_list,
eval_xpath_getindex,
@ -249,6 +248,33 @@ def _extract_published_date(published_date_raw):
return None
def parse_data_string(resp):
# kit.start(app, element, {
# node_ids: [0, 19],
# data: [{"type":"data","data" .... ["q","goggles_id"],"route":1,"url":1}}]
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
kit_start = resp.text.index("kit.start(app,")
start = resp.text[kit_start:].index('data: [{"type":"data"')
start = kit_start + start + len('data: ')
lev = 0
end = start
inner = False
for c in resp.text[start:]:
if inner and lev == 0:
break
end += 1
if c == "[":
lev += 1
inner = True
continue
if c == "]":
lev -= 1
json_data = js_variable_to_python(resp.text[start:end])
return json_data
def response(resp) -> EngineResults:
if brave_category in ('search', 'goggles'):
@ -257,9 +283,8 @@ def response(resp) -> EngineResults:
if brave_category in ('news'):
return _parse_news(resp)
datastr = extr(resp.text, "const data = ", ";\n").strip()
json_data = js_variable_to_python(datastr)
json_data = parse_data_string(resp)
# json_data is a list and at the second position (0,1) in this list we find the "response" data we need ..
json_resp = json_data[1]['data']['body']['response']
if brave_category == 'images':