[enh] engine - add Tineye reverse image search

Other optional parameter ..

`&sort=crawl_date`
    can be appended to search_string to sort results by date.

`&domain=example.org`
    can be implemented to search_string to get results from just one domain.

Public instances could get relatively fast timed-out for 3600s.

--

Merged from @allendema's commit [1] and slightly modfied / see [2].

Related-to: [1] 455b2b4460
Related-to: [2] https://github.com/searx/searx/pull/3040
Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
This commit is contained in:
Allen 2021-10-27 03:04:52 +02:00 committed by Markus Heiser
parent 8f100d7046
commit 880555e263
2 changed files with 89 additions and 0 deletions

83
searx/engines/tineye.py Normal file
View file

@ -0,0 +1,83 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
# lint: pylint
"""Tineye - Reverse search images
"""
from json import loads
from urllib.parse import urlencode
from datetime import datetime
about = {
"website": 'https://tineye.com',
"wikidata_id": 'Q2382535',
"use_official_api": False,
"require_api_key": False,
"results": 'JSON',
}
categories = ['images']
paging = True
safesearch = False
base_url = 'https://tineye.com'
search_string = '/result_json/?page={page}&{query}'
def request(query, params):
# see https://github.com/TinEye/pytineye/blob/main/pytineye/api.py
params['url'] = base_url + search_string.format(query=urlencode({'url': query}), page=params['pageno'])
params['headers'].update(
{
'Connection': 'keep-alive',
'Accept-Encoding': 'gzip, defalte, br',
'Host': 'tineye.com',
'DNT': '1',
'TE': 'trailers',
}
)
return params
def response(resp):
results = []
# Define wanted results
json_data = loads(resp.text)
number_of_results = json_data['num_matches']
for i in json_data['matches']:
image_format = i['format']
width = i['width']
height = i['height']
thumbnail_src = i['image_url']
backlink = i['domains'][0]['backlinks'][0]
url = backlink['backlink']
source = backlink['url']
title = backlink['image_name']
img_src = backlink['url']
# Get and convert published date
api_date = backlink['crawl_date'][:-3]
publishedDate = datetime.fromisoformat(api_date)
# Append results
results.append(
{
'template': 'images.html',
'url': url,
'thumbnail_src': thumbnail_src,
'source': source,
'title': title,
'img_src': img_src,
'format': image_format,
'widht': width,
'height': height,
'publishedDate': publishedDate,
}
)
# Append number of results
results.append({'number_of_results': number_of_results})
return results

View file

@ -483,6 +483,12 @@ engines:
timeout: 3.0
disabled: true
- name: tineye
engine: tineye
shortcut: tin
timeout: 9.0
disabled: true
- name: etymonline
engine: xpath
paging: true