.gitignore


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
7apu2bq3rhoylwmucxizk54afw5jyda7pho4j5zdcqpwkufke7zdzwad.onion
 

"o">.format(query=urlencode({'q': query}), offset=offset)

    if offset > 1:
        referer = base_url + inital_query.format(query=urlencode({'q': query}))
        params['headers']['Referer'] = referer
        logger.debug("headers.Referer --> %s", referer)

    params['url'] = base_url + search_path
    params['headers']['Accept-Language'] = "en-US,en;q=0.5"
    params['headers']['Accept'] = 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'
    return params


def response(resp):

    results = []
    result_len = 0

    dom = html.fromstring(resp.text)

    for result in eval_xpath(dom, '//div[@class="sa_cc"]'):

        # IMO //div[@class="sa_cc"] does no longer match
        logger.debug('found //div[@class="sa_cc"] --> %s', result)

        link = eval_xpath(result, './/h3/a')[0]
        url = link.attrib.get('href')
        title = extract_text(link)
        content = extract_text(eval_xpath(result, './/p'))

        # append result
        results.append({'url': url, 'title': title, 'content': content})

    # parse results again if nothing is found yet
    for result in eval_xpath(dom, '//li[@class="b_algo"]'):

        link = eval_xpath(result, './/h2/a')[0]
        url = link.attrib.get('href')
        title = extract_text(link)
        content = extract_text(eval_xpath(result, './/p'))

        # append result
        results.append({'url': url, 'title': title, 'content': content})

    try:
        result_len_container = "".join(eval_xpath(dom, '//span[@class="sb_count"]//text()'))
        if "-" in result_len_container:

            # Remove the part "from-to" for paginated request ...
            result_len_container = result_len_container[result_len_container.find("-") * 2 + 2 :]

        result_len_container = re.sub('[^0-9]', '', result_len_container)

        if len(result_len_container) > 0:
            result_len = int(result_len_container)

    except Exception as e:  # pylint: disable=broad-except
        logger.debug('result error :\n%s', e)

    if result_len and _get_offset_from_pageno(resp.search_params.get("pageno", 0)) > result_len:
        return []

    results.append({'number_of_results': result_len})
    return results


# get supported languages from their site
def _fetch_supported_languages(resp):

    lang_tags = set()

    dom = html.fromstring(resp.text)
    lang_links = eval_xpath(dom, '//div[@id="language-section"]//li')

    for _li in lang_links:

        href = eval_xpath(_li, './/@href')[0]
        (_scheme, _netloc, _path, _params, query, _fragment) = urlparse(href)
        query = parse_qs(query, keep_blank_values=True)

        # fmt: off
        setlang = query.get('setlang', [None, ])[0]
        # example: 'mn-Cyrl-MN' --> '['mn', 'Cyrl-MN']
        lang, nation = (setlang.split('-', maxsplit=1) + [None,])[:2]  # fmt: skip
        # fmt: on

        if not nation:
            nation = lang.upper()
        tag = lang + '-' + nation
        lang_tags.add(tag)

    return list(lang_tags)