summaryrefslogtreecommitdiff
path: root/searx/plugins/hostnames.py
blob: 770b00e15d68dcdcf4f47b761480af3085ae5b4f (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
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
# SPDX-License-Identifier: AGPL-3.0-or-later
# pylint: disable=too-many-branches
"""In addition to rewriting/replace reslut URLs, the *hoostnames* plugin offers
other features.

- ``hostnames.replace``: A **mapping** of regular expressions to hostnames to be
  replaced by other hostnames.

  .. code:: yaml

     hostnames:
       replace:
         '(.*\\.)?youtube\\.com$': 'invidious.example.com'
         '(.*\\.)?youtu\\.be$': 'invidious.example.com'
         ...

- ``hostnames.remove``: A **list** of regular expressions of the hostnames whose
  results should be taken from the results list.

  .. code:: yaml

     hostnames:
       remove:
         - '(.*\\.)?facebook.com$'
         - ...

- ``hostnames.high_priority``: A **list** of regular expressions for hostnames
  whose result should be given higher priority. The results from these hosts are
  arranged higher in the results list.

  .. code:: yaml

     hostnames:
       high_priority:
         - '(.*\\.)?wikipedia.org$'
         - ...

- ``hostnames.lower_priority``: A **list** of regular expressions for hostnames
  whose result should be given lower priority. The results from these hosts are
  arranged lower in the results list.

  .. code:: yaml

     hostnames:
       low_priority:
         - '(.*\\.)?google(\\..*)?$'
         - ...

If the URL matches the pattern of ``high_priority`` AND ``low_priority``, the
higher priority wins over the lower priority.

Alternatively, you can also specify a file name for the **mappings** or
**lists** to load these from an external file:

.. code:: yaml

   hostnames:
     replace: 'rewrite-hosts.yml'
     remove:
       - '(.*\\.)?facebook.com$'
       - ...
     low_priority:
       - '(.*\\.)?google(\\..*)?$'
       - ...
     high_priority:
       - '(.*\\.)?wikipedia.org$'
       - ...

The ``rewrite-hosts.yml`` from the example above must be in the folder in which
the ``settings.yml`` file is already located (``/etc/searxng``). The file then
only contains the lists or the mapping tables without further information on the
namespaces.  In the example above, this would be a mapping table that looks
something like this:

.. code:: yaml

   '(.*\\.)?youtube\\.com$': 'invidious.example.com'
   '(.*\\.)?youtu\\.be$': 'invidious.example.com'

"""

import re
from urllib.parse import urlunparse, urlparse

from flask_babel import gettext

from searx import settings
from searx.plugins import logger
from searx.settings_loader import get_yaml_cfg

name = gettext('Hostnames plugin')
description = gettext('Rewrite hostnames, remove results or prioritize them based on the hostname')
default_on = False
preference_section = 'general'

plugin_id = 'hostnames'

logger = logger.getChild(plugin_id)
parsed = 'parsed_url'
_url_fields = ['iframe_src', 'audio_src']


def _load_regular_expressions(settings_key):
    setting_value = settings.get(plugin_id, {}).get(settings_key)

    if not setting_value:
        return {}

    # load external file with configuration
    if isinstance(setting_value, str):
        setting_value = get_yaml_cfg(setting_value)

    if isinstance(setting_value, list):
        return {re.compile(r) for r in setting_value}

    if isinstance(setting_value, dict):
        return {re.compile(p): r for (p, r) in setting_value.items()}

    return {}


replacements = _load_regular_expressions('replace')
removables = _load_regular_expressions('remove')
high_priority = _load_regular_expressions('high_priority')
low_priority = _load_regular_expressions('low_priority')


def _matches_parsed_url(result, pattern):
    return parsed in result and pattern.search(result[parsed].netloc)


def on_result(_request, _search, result):
    for pattern, replacement in replacements.items():
        if _matches_parsed_url(result, pattern):
            # logger.debug(result['url'])
            result[parsed] = result[parsed]._replace(netloc=pattern.sub(replacement, result[parsed].netloc))
            result['url'] = urlunparse(result[parsed])
            # logger.debug(result['url'])

        for url_field in _url_fields:
            if not result.get(url_field):
                continue

            url_src = urlparse(result[url_field])
            if pattern.search(url_src.netloc):
                url_src = url_src._replace(netloc=pattern.sub(replacement, url_src.netloc))
                result[url_field] = urlunparse(url_src)

    for pattern in removables:
        if _matches_parsed_url(result, pattern):
            return False

        for url_field in _url_fields:
            if not result.get(url_field):
                continue

            url_src = urlparse(result[url_field])
            if pattern.search(url_src.netloc):
                del result[url_field]

    for pattern in low_priority:
        if _matches_parsed_url(result, pattern):
            result['priority'] = 'low'

    for pattern in high_priority:
        if _matches_parsed_url(result, pattern):
            result['priority'] = 'high'

    return True