summaryrefslogtreecommitdiff
path: root/searx/engines/bing_images.py
blob: 0587e710fc6a239d5646da5c1b6cac5fbcc391ff (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
# SPDX-License-Identifier: AGPL-3.0-or-later
"""Bing-Images: description see :py:obj:`searx.engines.bing`.
"""
# pylint: disable=invalid-name


from typing import TYPE_CHECKING
import json
from urllib.parse import urlencode

from lxml import html

from searx.enginelib.traits import EngineTraits
from searx.engines.bing import set_bing_cookies
from searx.engines.bing import fetch_traits  # pylint: disable=unused-import


if TYPE_CHECKING:
    import logging

    logger = logging.getLogger()

traits: EngineTraits

# about
about = {
    "website": 'https://www.bing.com/images',
    "wikidata_id": 'Q182496',
    "official_api_documentation": 'https://www.microsoft.com/en-us/bing/apis/bing-image-search-api',
    "use_official_api": False,
    "require_api_key": False,
    "results": 'HTML',
}

# engine dependent config
categories = ['images', 'web']
paging = True
safesearch = True
time_range_support = True

base_url = 'https://www.bing.com/images/async'
"""Bing (Images) search URL"""

time_map = {
    'day': 60 * 24,
    'week': 60 * 24 * 7,
    'month': 60 * 24 * 31,
    'year': 60 * 24 * 365,
}


def request(query, params):
    """Assemble a Bing-Image request."""

    engine_region = traits.get_region(params['searxng_locale'], traits.all_locale)  # type: ignore
    engine_language = traits.get_language(params['searxng_locale'], 'en')  # type: ignore
    set_bing_cookies(params, engine_language, engine_region)

    # build URL query
    # - example: https://www.bing.com/images/async?q=foo&async=content&first=1&count=35
    query_params = {
        'q': query,
        'async': '1',
        # to simplify the page count lets use the default of 35 images per page
        'first': (int(params.get('pageno', 1)) - 1) * 35 + 1,
        'count': 35,
    }

    # time range
    # - example: one year (525600 minutes) 'qft=+filterui:age-lt525600'

    if params['time_range']:
        query_params['qft'] = 'filterui:age-lt%s' % time_map[params['time_range']]

    params['url'] = base_url + '?' + urlencode(query_params)

    return params


def response(resp):
    """Get response from Bing-Images"""

    results = []
    dom = html.fromstring(resp.text)

    for result in dom.xpath('//ul[contains(@class, "dgControl_list")]/li'):

        metadata = result.xpath('.//a[@class="iusc"]/@m')
        if not metadata:
            continue

        metadata = json.loads(result.xpath('.//a[@class="iusc"]/@m')[0])
        title = ' '.join(result.xpath('.//div[@class="infnmpt"]//a/text()')).strip()
        img_format = ' '.join(result.xpath('.//div[@class="imgpt"]/div/span/text()')).strip().split(" · ")
        source = ' '.join(result.xpath('.//div[@class="imgpt"]//div[@class="lnkw"]//a/text()')).strip()
        results.append(
            {
                'template': 'images.html',
                'url': metadata['purl'],
                'thumbnail_src': metadata['turl'],
                'img_src': metadata['murl'],
                'content': metadata.get('desc'),
                'title': title,
                'source': source,
                'resolution': img_format[0],
                'img_format': img_format[1] if len(img_format) >= 2 else None,
            }
        )
    return results