Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit cc6f7012 authored by Romain Hunault's avatar Romain Hunault
Browse files

Merge branch 'asciimoo/master' into merge

parents fe929d43 d51732c0

requirements.txt

+5 −5
Original line number Diff line number Diff line 
redis

certifi==2017.11.5

flask==0.12.2

flask==1.0.2

flask-babel==0.11.2

lxml==4.1.1

idna==2.5

lxml==4.2.1

idna==2.6

pygments==2.1.3

pyopenssl==17.4.0

python-dateutil==2.6.1

pyopenssl==18.0.0

python-dateutil==2.7.3

pyyaml==3.12

requests[socks]==2.18.4

searx/engines/base.py

+1 −1
Original line number Diff line number Diff line
@@ -55,7 +55,7 @@ shorcut_dict = { 
def request(query, params):

    # replace shortcuts with API advanced search keywords

    for key in shorcut_dict.keys():

        query = re.sub(str(key), str(shorcut_dict[key]), query)

        query = re.sub(key, shorcut_dict[key], str(query))



    # basic search

    offset = (params['pageno'] - 1) * number_of_results

searx/engines/bing.py

+4 −1
Original line number Diff line number Diff line
@@ -16,7 +16,7 @@ 
from lxml import html

from searx.engines.xpath import extract_text

from searx.url_utils import urlencode

from searx.utils import match_language

from searx.utils import match_language, gen_useragent



# engine dependent config

categories = ['general']
@@ -43,6 +43,9 @@ def request(query, params): 
        offset=offset)



    params['url'] = base_url + search_path



    params['headers']['User-Agent'] = gen_useragent('Windows NT 6.3; WOW64')



    return params

searx/engines/gigablast.py

+2 −0
Original line number Diff line number Diff line
@@ -34,6 +34,7 @@ search_string = 'search?{query}'\ 
    '&qlang={lang}'\

    '&ff={safesearch}'\

    '&rxiec={rxieu}'\

    '&ulse={ulse}'\

    '&rand={rxikd}'  # current unix timestamp



# specific xpath variables
@@ -64,6 +65,7 @@ def request(query, params): 
                                       number_of_results=number_of_results,

                                       rxikd=int(time() * 1000),

                                       rxieu=random.randint(1000000000, 9999999999),

                                       ulse=random.randint(100000000, 999999999),

                                       lang=language,

                                       safesearch=safesearch)

searx/engines/google_images.py

+16 −25
Original line number Diff line number Diff line
@@ -13,7 +13,7 @@ 
from datetime import date, timedelta

from json import loads

from lxml import html

from searx.url_utils import urlencode

from searx.url_utils import urlencode, urlparse, parse_qs





# engine dependent config
@@ -25,10 +25,9 @@ number_of_results = 100 


search_url = 'https://www.google.com/search'\

    '?{query}'\

    '&asearch=ichunk'\

    '&async=_id:rg_s,_pms:s'\

    '&tbm=isch'\

    '&yv=2'\

    '&gbv=1'\

    '&sa=G'\

    '&{search_options}'

time_range_attr = "qdr:{range}"

time_range_custom_attr = "cdr:1,cd_min:{start},cd_max{end}"
@@ -66,30 +65,22 @@ def request(query, params): 
def response(resp):

    results = []



    g_result = loads(resp.text)



    dom = html.fromstring(g_result[1][1])

    dom = html.fromstring(resp.text)



    # parse results

    for result in dom.xpath('//div[@data-ved]'):



        try:

            metadata = loads(''.join(result.xpath('./div[contains(@class, "rg_meta")]/text()')))

        except:

            continue



        thumbnail_src = metadata['tu']



        # http to https

        thumbnail_src = thumbnail_src.replace("http://", "https://")



    for img in dom.xpath('//a'):

        r = {

            'title': u' '.join(img.xpath('.//div[class="rg_ilmbg"]//text()')),

            'content': '',

            'template': 'images.html',

        }

        url = urlparse(img.xpath('.//@href')[0])

        query = parse_qs(url.query)

        r['url'] = query['imgrefurl'][0]

        r['img_src'] = query['imgurl'][0]

        r['thumbnail_src'] = r['img_src']

        # append result

        results.append({'url': metadata['ru'],

                        'title': metadata['pt'],

                        'content': metadata['s'],

                        'thumbnail_src': thumbnail_src,

                        'img_src': metadata['ou'],

                        'template': 'images.html'})

        results.append(r)



    # return results

    return results