[enh] Add Tineye reverse image search (#3040)

* [enh] Add Tineye reverse image search 

Other optional parametesr:

"&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.

* [enh] Add TIneye to settings.yml 

Check if that's the right shortcut.

* [mod] Fix checks

* [mod] Try to fix checks

* [mod] Use Four spaces for indentation

And set paging back to True

Co-authored-by: Noémi Ványi <kvch@users.noreply.github.com>
This commit is contained in:
Allen 2022-01-22 12:15:19 +01:00 committed by GitHub
parent fd9d6b58d5
commit 0c351ea364
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 93 additions and 0 deletions

86
searx/engines/tineye.py Normal file
View File

@ -0,0 +1,86 @@
"""
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):
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']:
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

@ -410,6 +410,13 @@ engines:
timeout: 3.0
disabled : True
- name : tineye
engine : tineye
shortcut : tin
paging : True
timeout : 9.0
disabled : True
- name : etools
engine : etools
shortcut : eto