summaryrefslogtreecommitdiff
path: root/searx/engines
diff options
context:
space:
mode:
Diffstat (limited to 'searx/engines')
-rw-r--r--searx/engines/currency_convert.py13
-rw-r--r--searx/engines/solidtorrents.py88
-rw-r--r--searx/engines/tineye.py103
-rw-r--r--searx/engines/www1x.py17
4 files changed, 183 insertions, 38 deletions
diff --git a/searx/engines/currency_convert.py b/searx/engines/currency_convert.py
index 969688126..18ea6cb19 100644
--- a/searx/engines/currency_convert.py
+++ b/searx/engines/currency_convert.py
@@ -1,6 +1,6 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
-"""
- currency convert (DuckDuckGo)
+# lint: pylint
+"""Currency convert (DuckDuckGo)
"""
import json
@@ -13,18 +13,19 @@ about = {
"use_official_api": False,
"require_api_key": False,
"results": 'JSONP',
+ "description": "Service from DuckDuckGo.",
}
engine_type = 'online_currency'
categories = []
-url = 'https://duckduckgo.com/js/spice/currency/1/{0}/{1}'
+base_url = 'https://duckduckgo.com/js/spice/currency/1/{0}/{1}'
weight = 100
https_support = True
-def request(query, params):
- params['url'] = url.format(params['from'], params['to'])
+def request(_query, params):
+ params['url'] = base_url.format(params['from'], params['to'])
return params
@@ -34,7 +35,7 @@ def response(resp):
results = []
try:
conversion_rate = float(json.loads(json_resp)['conversion']['converted-amount'])
- except:
+ except ValueError:
return results
answer = '{0} {1} = {2} {3}, 1 {1} ({5}) = {4} {3} ({6})'.format(
resp.search_params['amount'],
diff --git a/searx/engines/solidtorrents.py b/searx/engines/solidtorrents.py
index 614b38277..9b5d543d8 100644
--- a/searx/engines/solidtorrents.py
+++ b/searx/engines/solidtorrents.py
@@ -1,51 +1,89 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
# lint: pylint
-"""Solid Torrents
-
+"""SolidTorrents
"""
-from json import loads
+from datetime import datetime
from urllib.parse import urlencode
+import random
+
+from lxml import html
+
+from searx.utils import (
+ extract_text,
+ eval_xpath,
+ eval_xpath_getindex,
+ eval_xpath_list,
+ get_torrent_size,
+)
about = {
"website": 'https://www.solidtorrents.net/',
"wikidata_id": None,
"official_api_documentation": None,
- "use_official_api": True,
+ "use_official_api": False,
"require_api_key": False,
- "results": 'JSON',
+ "results": 'HTML',
}
categories = ['files']
paging = True
-base_url = 'https://www.solidtorrents.net/'
-search_url = base_url + 'api/v1/search?{query}'
+# base_url can be overwritten by a list of URLs in the settings.yml
+base_url = 'https://solidtorrents.net'
def request(query, params):
- skip = (params['pageno'] - 1) * 20
- query = urlencode({'q': query, 'skip': skip})
+ if isinstance(base_url, list):
+ params['base_url'] = random.choice(base_url)
+ else:
+ params['base_url'] = base_url
+ search_url = params['base_url'] + '/search?{query}'
+ page = (params['pageno'] - 1) * 20
+ query = urlencode({'q': query, 'page': page})
params['url'] = search_url.format(query=query)
- logger.debug("query_url --> %s", params['url'])
return params
def response(resp):
results = []
- search_results = loads(resp.text)
-
- for result in search_results["results"]:
- results.append(
- {
- 'infohash': result["infohash"],
- 'seed': result["swarm"]["seeders"],
- 'leech': result["swarm"]["leechers"],
- 'title': result["title"],
- 'url': "https://solidtorrents.net/view/" + result["_id"],
- 'filesize': result["size"],
- 'magnetlink': result["magnet"],
- 'template': "torrent.html",
- }
- )
+ dom = html.fromstring(resp.text)
+
+ for result in eval_xpath(dom, '//div[contains(@class, "search-result")]'):
+ a = eval_xpath_getindex(result, './div/h5/a', 0, None)
+ if a is None:
+ continue
+ title = extract_text(a)
+ url = eval_xpath_getindex(a, '@href', 0, None)
+ categ = eval_xpath(result, './div//a[contains(@class, "category")]')
+ metadata = extract_text(categ)
+ stats = eval_xpath_list(result, './div//div[contains(@class, "stats")]/div', min_len=5)
+ n, u = extract_text(stats[1]).split()
+ filesize = get_torrent_size(n, u)
+ leech = extract_text(stats[2])
+ seed = extract_text(stats[3])
+ torrentfile = eval_xpath_getindex(result, './div//a[contains(@class, "dl-torrent")]/@href', 0, None)
+ magnet = eval_xpath_getindex(result, './div//a[contains(@class, "dl-magnet")]/@href', 0, None)
+
+ params = {
+ 'seed': seed,
+ 'leech': leech,
+ 'title': title,
+ 'url': resp.search_params['base_url'] + url,
+ 'filesize': filesize,
+ 'magnetlink': magnet,
+ 'torrentfile': torrentfile,
+ 'metadata': metadata,
+ 'template': "torrent.html",
+ }
+
+ date_str = extract_text(stats[4])
+
+ try:
+ params['publishedDate'] = datetime.strptime(date_str, '%b %d, %Y')
+ except ValueError:
+ pass
+
+ results.append(params)
+
return results
diff --git a/searx/engines/tineye.py b/searx/engines/tineye.py
new file mode 100644
index 000000000..fe5b60393
--- /dev/null
+++ b/searx/engines/tineye.py
@@ -0,0 +1,103 @@
+# SPDX-License-Identifier: AGPL-3.0-or-later
+# lint: pylint
+"""This engine implements *Tineye - reverse image search*
+
+Using TinEye, you can search by image or perform what we call a reverse image
+search. You can do that by uploading an image or searching by URL. You can also
+simply drag and drop your images to start your search. TinEye constantly crawls
+the web and adds images to its index. Today, the TinEye index is over 50.2
+billion images `[tineye.com] <https://tineye.com/how>`_.
+
+.. hint::
+
+ This SearXNG engine only supports *'searching by URL'* and it does not use
+ the official API `[api.tineye.com] <https://api.tineye.com/python/docs/>`_.
+
+"""
+
+from urllib.parse import urlencode
+from datetime import datetime
+
+about = {
+ "website": 'https://tineye.com',
+ "wikidata_id": 'Q2382535',
+ "official_api_documentation": 'https://api.tineye.com/python/docs/',
+ "use_official_api": False,
+ "require_api_key": False,
+ "results": 'JSON',
+}
+
+engine_type = 'online_url_search'
+categories = ['general']
+paging = True
+safesearch = False
+base_url = 'https://tineye.com'
+search_string = '/result_json/?page={page}&{query}'
+
+
+def request(query, params):
+
+ if params['search_urls']['data:image']:
+ query = params['search_urls']['data:image']
+ elif params['search_urls']['http']:
+ query = params['search_urls']['http']
+
+ query = urlencode({'url': query})
+
+ # see https://github.com/TinEye/pytineye/blob/main/pytineye/api.py
+ params['url'] = base_url + search_string.format(query=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 = resp.json()
+ 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
diff --git a/searx/engines/www1x.py b/searx/engines/www1x.py
index f6b82944d..a7ec06f18 100644
--- a/searx/engines/www1x.py
+++ b/searx/engines/www1x.py
@@ -1,10 +1,12 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
-"""
- 1x (Images)
+# lint: pylint
+"""1x (Images)
+
"""
-from lxml import html, etree
from urllib.parse import urlencode, urljoin
+from lxml import html, etree
+
from searx.utils import extract_text, eval_xpath_list, eval_xpath_getindex
# about
@@ -38,13 +40,14 @@ def request(query, params):
def response(resp):
results = []
xmldom = etree.fromstring(resp.content)
- xmlsearchresult = eval_xpath_getindex(xmldom, '//searchresult', 0)
+ xmlsearchresult = eval_xpath_getindex(xmldom, '//data', 0)
dom = html.fragment_fromstring(xmlsearchresult.text, create_parent='div')
- for link in eval_xpath_list(dom, '/div/table/tr/td/div[2]//a'):
+ for link in eval_xpath_list(dom, '//a'):
url = urljoin(base_url, link.attrib.get('href'))
title = extract_text(link)
- thumbnail_src = urljoin(gallery_url, eval_xpath_getindex(link, './/img', 0).attrib['src'])
-
+ thumbnail_src = urljoin(
+ gallery_url, (eval_xpath_getindex(link, './/img', 0).attrib['src']).replace(base_url, '')
+ )
# append result
results.append(
{
generated by cgit v1.2.3 (git 2.25.1) at 2026-04-16 23:31:16 +0000