mirror of https://github.com/searxng/searxng.git
Compare commits
4 Commits
d8aae1a91a
...
dc728ed705
Author | SHA1 | Date |
---|---|---|
Grant Lanham Jr | dc728ed705 | |
Markus Heiser | 10d3af84b8 | |
Grant Lanham | 23bf9f9d95 | |
Grant Lanham | 2b48584bb4 |
|
@ -95,17 +95,24 @@ def request(query, params):
|
||||||
# don't ask why it is only sometimes / its M$ and they have never been
|
# don't ask why it is only sometimes / its M$ and they have never been
|
||||||
# deterministic ;)
|
# deterministic ;)
|
||||||
'pq': query,
|
'pq': query,
|
||||||
|
# TODO: Figure out how below parameters are populated
|
||||||
|
'sc': '0-0',
|
||||||
|
"sp": "-1",
|
||||||
|
"lq": "0",
|
||||||
|
"qs": "n",
|
||||||
|
"ghsh": "0",
|
||||||
|
"ghacc": "0",
|
||||||
|
"ghpl": "",
|
||||||
}
|
}
|
||||||
|
|
||||||
# To get correct page, arg first and this arg FORM is needed, the value PERE
|
# To get correct page, arg first and this arg FORM is needed, the value PERE
|
||||||
# is on page 2, on page 3 its PERE1 and on page 4 its PERE2 .. and so forth.
|
# is on page 2, on page 3 its PERE1 and on page 4 its PERE2 .. and so forth.
|
||||||
# The 'first' arg should never send on page 1.
|
# The 'first' arg should never send on page 1.
|
||||||
|
|
||||||
if page > 1:
|
if page > 1:
|
||||||
query_params['first'] = _page_offset(page) # see also arg FORM
|
query_params['first'] = _page_offset(page) # see also arg FORM
|
||||||
if page == 2:
|
if page == 2:
|
||||||
query_params['FORM'] = 'PERE'
|
query_params['FORM'] = 'PERE'
|
||||||
elif page > 2:
|
else: # page > 2:
|
||||||
query_params['FORM'] = 'PERE%s' % (page - 2)
|
query_params['FORM'] = 'PERE%s' % (page - 2)
|
||||||
|
|
||||||
params['url'] = f'{base_url}?{urlencode(query_params)}'
|
params['url'] = f'{base_url}?{urlencode(query_params)}'
|
||||||
|
|
|
@ -6,7 +6,7 @@ DuckDuckGo Lite
|
||||||
|
|
||||||
from typing import TYPE_CHECKING
|
from typing import TYPE_CHECKING
|
||||||
import re
|
import re
|
||||||
from urllib.parse import urlencode, quote_plus
|
from urllib.parse import urlencode
|
||||||
import json
|
import json
|
||||||
import babel
|
import babel
|
||||||
import lxml.html
|
import lxml.html
|
||||||
|
@ -263,7 +263,7 @@ def request(query, params):
|
||||||
|
|
||||||
params['url'] = url
|
params['url'] = url
|
||||||
params['method'] = 'POST'
|
params['method'] = 'POST'
|
||||||
params['data']['q'] = quote_plus(query)
|
params['data']['q'] = query
|
||||||
|
|
||||||
# The API is not documented, so we do some reverse engineering and emulate
|
# The API is not documented, so we do some reverse engineering and emulate
|
||||||
# what https://html.duckduckgo.com/html does when you press "next Page" link
|
# what https://html.duckduckgo.com/html does when you press "next Page" link
|
||||||
|
@ -381,7 +381,11 @@ def response(resp):
|
||||||
zero_click_info_xpath = '//div[@id="zero_click_abstract"]'
|
zero_click_info_xpath = '//div[@id="zero_click_abstract"]'
|
||||||
zero_click = extract_text(eval_xpath(doc, zero_click_info_xpath)).strip()
|
zero_click = extract_text(eval_xpath(doc, zero_click_info_xpath)).strip()
|
||||||
|
|
||||||
if zero_click and "Your IP address is" not in zero_click and "Your user agent:" not in zero_click:
|
if zero_click and (
|
||||||
|
"Your IP address is" not in zero_click
|
||||||
|
and "Your user agent:" not in zero_click
|
||||||
|
and "URL Decoded:" not in zero_click
|
||||||
|
):
|
||||||
current_query = resp.search_params["data"].get("q")
|
current_query = resp.search_params["data"].get("q")
|
||||||
|
|
||||||
results.append(
|
results.append(
|
||||||
|
|
Loading…
Reference in New Issue