searxng/searx/engines/duckduckgo.py

252 lines
7.2 KiB
Python
Raw Normal View History

# SPDX-License-Identifier: AGPL-3.0-or-later
# lint: pylint
"""DuckDuckGo Lite
"""
import json
from lxml import html
from searx.utils import (
dict_subset,
eval_xpath,
eval_xpath_getindex,
extract_text,
match_language,
)
from searx import network
from searx.enginelib.traits import EngineTraits
traits: EngineTraits
2013-10-14 21:09:13 +00:00
# about
about = {
"website": 'https://lite.duckduckgo.com/lite/',
"wikidata_id": 'Q12805',
"official_api_documentation": 'https://duckduckgo.com/api',
"use_official_api": False,
"require_api_key": False,
"results": 'HTML',
}
# engine dependent config
2021-12-22 15:58:52 +00:00
categories = ['general', 'web']
paging = True
supported_languages_url = 'https://duckduckgo.com/util/u588.js'
2016-07-18 14:15:37 +00:00
time_range_support = True
send_accept_language_header = True
2013-10-14 21:09:13 +00:00
language_aliases = {
'ar-SA': 'ar-XA',
'es-419': 'es-XL',
'ja': 'jp-JP',
'ko': 'kr-KR',
'sl-SI': 'sl-SL',
'zh-TW': 'tzh-TW',
'zh-HK': 'tzh-HK',
}
time_range_dict = {'day': 'd', 'week': 'w', 'month': 'm', 'year': 'y'}
2014-03-29 15:38:45 +00:00
# search-url
url = 'https://lite.duckduckgo.com/lite/'
url_ping = 'https://duckduckgo.com/t/sl_l'
2017-05-21 03:33:08 +00:00
# match query's language to a region code that duckduckgo will accept
def get_region_code(lang, lang_list=None):
if lang == 'all':
return None
lang_code = match_language(lang, lang_list or [], language_aliases, 'wt-WT')
lang_parts = lang_code.split('-')
# country code goes first
return lang_parts[1].lower() + '-' + lang_parts[0].lower()
2017-05-21 03:33:08 +00:00
def request(query, params):
params['url'] = url
params['method'] = 'POST'
params['data']['q'] = query
# The API is not documented, so we do some reverse engineering and emulate
# what https://lite.duckduckgo.com/lite/ does when you press "next Page"
# link again and again ..
params['headers']['Content-Type'] = 'application/x-www-form-urlencoded'
params['headers']['Referer'] = 'https://google.com/'
# initial page does not have an offset
if params['pageno'] == 2:
# second page does have an offset of 30
offset = (params['pageno'] - 1) * 30
params['data']['s'] = offset
params['data']['dc'] = offset + 1
elif params['pageno'] > 2:
# third and following pages do have an offset of 30 + n*50
offset = 30 + (params['pageno'] - 2) * 50
params['data']['s'] = offset
params['data']['dc'] = offset + 1
# initial page does not have additional data in the input form
if params['pageno'] > 1:
# request the second page (and more pages) needs 'o' and 'api' arguments
params['data']['o'] = 'json'
params['data']['api'] = 'd.js'
# initial page does not have additional data in the input form
if params['pageno'] > 2:
# request the third page (and more pages) some more arguments
params['data']['nextParams'] = ''
params['data']['v'] = ''
params['data']['vqd'] = ''
region_code = get_region_code(params['language'], supported_languages)
if region_code:
params['data']['kl'] = region_code
params['cookies']['kl'] = region_code
2016-07-18 14:15:37 +00:00
params['data']['df'] = ''
if params['time_range'] in time_range_dict:
params['data']['df'] = time_range_dict[params['time_range']]
params['cookies']['df'] = time_range_dict[params['time_range']]
logger.debug("param data: %s", params['data'])
logger.debug("param cookies: %s", params['cookies'])
2013-10-14 21:09:13 +00:00
return params
# get response from search-request
2013-10-14 21:09:13 +00:00
def response(resp):
headers_ping = dict_subset(resp.request.headers, ['User-Agent', 'Accept-Encoding', 'Accept', 'Cookie'])
network.get(url_ping, headers=headers_ping)
2014-03-21 15:33:17 +00:00
if resp.status_code == 303:
return []
results = []
doc = html.fromstring(resp.text)
result_table = eval_xpath(doc, '//html/body/form/div[@class="filters"]/table')
if not len(result_table) >= 3:
# no more results
return []
result_table = result_table[2]
tr_rows = eval_xpath(result_table, './/tr')
# In the last <tr> is the form of the 'previous/next page' links
tr_rows = tr_rows[:-1]
len_tr_rows = len(tr_rows)
offset = 0
while len_tr_rows >= offset + 4:
# assemble table rows we need to scrap
tr_title = tr_rows[offset]
tr_content = tr_rows[offset + 1]
offset += 4
# ignore sponsored Adds <tr class="result-sponsored">
if tr_content.get('class') == 'result-sponsored':
2013-10-15 17:11:43 +00:00
continue
a_tag = eval_xpath_getindex(tr_title, './/td//a[@class="result-link"]', 0, None)
if a_tag is None:
continue
td_content = eval_xpath_getindex(tr_content, './/td[@class="result-snippet"]', 0, None)
if td_content is None:
continue
2014-03-21 15:33:17 +00:00
results.append(
{
'title': a_tag.text_content(),
'content': extract_text(td_content),
'url': a_tag.get('href'),
}
)
2020-06-13 21:42:16 +00:00
2013-10-15 17:11:43 +00:00
return results
# get supported languages from their site
def _fetch_supported_languages(resp):
# response is a js file with regions as an embedded object
response_page = resp.text
response_page = response_page[response_page.find('regions:{') + 8 :]
response_page = response_page[: response_page.find('}') + 1]
regions_json = json.loads(response_page)
supported_languages = map((lambda x: x[3:] + '-' + x[:2].upper()), regions_json.keys())
return list(supported_languages)
def fetch_traits(engine_traits: EngineTraits):
"""Fetch regions from DuckDuckGo."""
# pylint: disable=import-outside-toplevel
engine_traits.data_type = 'supported_languages' # deprecated
import babel
from searx.locales import region_tag
engine_traits.all_locale = 'wt-wt'
resp = network.get('https://duckduckgo.com/util/u588.js')
if not resp.ok:
print("ERROR: response from DuckDuckGo is not OK.")
pos = resp.text.find('regions:{') + 8
js_code = resp.text[pos:]
pos = js_code.find('}') + 1
regions = json.loads(js_code[:pos])
reg_map = {
'tw-tzh': 'zh_TW',
'hk-tzh': 'zh_HK',
'ct-ca': 'skip', # ct-ca and es-ca both map to ca_ES
'es-ca': 'ca_ES',
'id-en': 'id_ID',
'no-no': 'nb_NO',
'jp-jp': 'ja_JP',
'kr-kr': 'ko_KR',
'xa-ar': 'ar_SA',
'sl-sl': 'sl_SI',
'th-en': 'th_TH',
'vn-en': 'vi_VN',
}
for eng_tag, name in regions.items():
if eng_tag == 'wt-wt':
engine_traits.all_locale = 'wt-wt'
continue
region = reg_map.get(eng_tag)
if region == 'skip':
continue
if not region:
eng_territory, eng_lang = eng_tag.split('-')
region = eng_lang + '_' + eng_territory.upper()
try:
sxng_tag = region_tag(babel.Locale.parse(region))
except babel.UnknownLocaleError:
print("ERROR: %s (%s) -> %s is unknown by babel" % (name, eng_tag, region))
continue
conflict = engine_traits.regions.get(sxng_tag)
if conflict:
if conflict != eng_tag:
print("CONFLICT: babel %s --> %s, %s" % (sxng_tag, conflict, eng_tag))
continue
engine_traits.regions[sxng_tag] = eng_tag