summaryrefslogtreecommitdiff
path: root/searx/engines/google_videos.py
blob: 5ab29f9fff3748991511cc545ea99b924ded64db (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
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
# SPDX-License-Identifier: AGPL-3.0-or-later
# lint: pylint
"""This is the implementation of the google videos engine.

.. admonition:: Content-Security-Policy (CSP)

   This engine needs to allow images from the `data URLs`_ (prefixed with the
   ``data:`` scheme)::

     Header set Content-Security-Policy "img-src 'self' data: ;"

.. _data URLs:
   https://developer.mozilla.org/en-US/docs/Web/HTTP/Basics_of_HTTP/Data_URIs

"""

# pylint: disable=invalid-name

import re
from urllib.parse import urlencode
from lxml import html

from searx.utils import (
    eval_xpath,
    eval_xpath_list,
    eval_xpath_getindex,
    extract_text,
)

from searx.engines.google import (
    get_lang_info,
    time_range_dict,
    filter_mapping,
    g_section_with_header,
    title_xpath,
    suggestion_xpath,
    detect_google_sorry,
)

# pylint: disable=unused-import
from searx.engines.google import supported_languages_url, _fetch_supported_languages, fetch_traits

# pylint: enable=unused-import

# about
about = {
    "website": 'https://www.google.com',
    "wikidata_id": 'Q219885',
    "official_api_documentation": 'https://developers.google.com/custom-search',
    "use_official_api": False,
    "require_api_key": False,
    "results": 'HTML',
}

# engine dependent config

categories = ['videos', 'web']
paging = False
language_support = True
use_locale_domain = True
time_range_support = True
safesearch = True
send_accept_language_header = True

RE_CACHE = {}


def _re(regexpr):
    """returns compiled regular expression"""
    RE_CACHE[regexpr] = RE_CACHE.get(regexpr, re.compile(regexpr))
    return RE_CACHE[regexpr]


def scrap_out_thumbs_src(dom):
    ret_val = {}
    thumb_name = 'dimg_'
    for script in eval_xpath_list(dom, '//script[contains(., "google.ldi={")]'):
        _script = script.text
        # "dimg_35":"https://i.ytimg.c....",
        _dimurl = _re("s='([^']*)").findall(_script)
        for k, v in _re('(' + thumb_name + '[0-9]*)":"(http[^"]*)').findall(_script):
            v = v.replace(r'\u003d', '=')
            v = v.replace(r'\u0026', '&')
            ret_val[k] = v
    logger.debug("found %s imgdata for: %s", thumb_name, ret_val.keys())
    return ret_val


def scrap_out_thumbs(dom):
    """Scrap out thumbnail data from <script> tags."""
    ret_val = {}
    thumb_name = 'dimg_'

    for script in eval_xpath_list(dom, '//script[contains(., "_setImagesSrc")]'):
        _script = script.text

        # var s='data:image/jpeg;base64, ...'
        _imgdata = _re("s='([^']*)").findall(_script)
        if not _imgdata:
            continue

        # var ii=['dimg_17']
        for _vidthumb in _re(r"(%s\d+)" % thumb_name).findall(_script):
            # At least the equal sign in the URL needs to be decoded
            ret_val[_vidthumb] = _imgdata[0].replace(r"\x3d", "=")

    logger.debug("found %s imgdata for: %s", thumb_name, ret_val.keys())
    return ret_val


def request(query, params):
    """Google-Video search request"""

    lang_info = get_lang_info(params, supported_languages, language_aliases, False)

    query_url = (
        'https://'
        + lang_info['subdomain']
        + '/search'
        + "?"
        + urlencode({'q': query, 'tbm': "vid", **lang_info['params'], 'ie': "utf8", 'oe': "utf8"})
    )

    if params['time_range'] in time_range_dict:
        query_url += '&' + urlencode({'tbs': 'qdr:' + time_range_dict[params['time_range']]})
    if params['safesearch']:
        query_url += '&' + urlencode({'safe': filter_mapping[params['safesearch']]})
    params['url'] = query_url

    params['cookies']['CONSENT'] = "YES+"
    params['headers'].update(lang_info['headers'])
    params['headers']['Accept'] = 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'
    return params


def response(resp):
    """Get response from google's search request"""
    results = []

    detect_google_sorry(resp)

    # convert the text to dom
    dom = html.fromstring(resp.text)
    vidthumb_imgdata = scrap_out_thumbs(dom)
    thumbs_src = scrap_out_thumbs_src(dom)
    logger.debug(str(thumbs_src))

    # parse results
    for result in eval_xpath_list(dom, '//div[contains(@class, "g ")]'):

        # ignore google *sections*
        if extract_text(eval_xpath(result, g_section_with_header)):
            logger.debug("ignoring <g-section-with-header>")
            continue

        # ingnore articles without an image id / e.g. news articles
        img_id = eval_xpath_getindex(result, './/g-img/img/@id', 0, default=None)
        if img_id is None:
            logger.error("no img_id found in item %s (news article?)", len(results) + 1)
            continue

        img_src = vidthumb_imgdata.get(img_id, None)
        if not img_src:
            img_src = thumbs_src.get(img_id, "")

        title = extract_text(eval_xpath_getindex(result, title_xpath, 0))
        url = eval_xpath_getindex(result, './/div[@class="dXiKIc"]//a/@href', 0)
        length = extract_text(eval_xpath(result, './/div[contains(@class, "P7xzyf")]/span/span'))
        c_node = eval_xpath_getindex(result, './/div[@class="Uroaid"]', 0)
        content = extract_text(c_node)
        pub_info = extract_text(eval_xpath(result, './/div[@class="Zg1NU"]'))

        results.append(
            {
                'url': url,
                'title': title,
                'content': content,
                'length': length,
                'author': pub_info,
                'thumbnail': img_src,
                'template': 'videos.html',
            }
        )

    # parse suggestion
    for suggestion in eval_xpath_list(dom, suggestion_xpath):
        # append suggestion
        results.append({'suggestion': extract_text(suggestion)})

    return results