Merge branch 'master' into flask_perimeter

This commit is contained in:
Adam Tauber 2017-01-04 19:09:12 +01:00 committed by GitHub
commit 627962ce40
13 changed files with 179 additions and 147 deletions

View file

@ -14,6 +14,36 @@ update_dev_packages() {
pip install --upgrade -r "$BASE_DIR/requirements-dev.txt" pip install --upgrade -r "$BASE_DIR/requirements-dev.txt"
} }
check_geckodriver() {
echo '[!] Checking geckodriver'
set -e
geckodriver -V 2>1 > /dev/null || NOTFOUND=1
set +e
if [ -z $NOTFOUND ]; then
return
fi
GECKODRIVER_VERSION="v0.11.1"
PLATFORM=`python -c "import platform; print platform.system().lower(), platform.architecture()[0]"`
case $PLATFORM in
"linux 32bit" | "linux2 32bit") ARCH="linux32";;
"linux 64bit" | "linux2 64bit") ARCH="linux64";;
"windows 32 bit") ARCH="win32";;
"windows 64 bit") ARCH="win64";;
"mac 64bit") ARCH="macos";;
esac
GECKODRIVER_URL="https://github.com/mozilla/geckodriver/releases/download/$GECKODRIVER_VERSION/geckodriver-$GECKODRIVER_VERSION-$ARCH.tar.gz";
if [ -z "$VIRTUAL_ENV" ]; then
echo "geckodriver can't be installed because VIRTUAL_ENV is not set, you should download it from\n $GECKODRIVER_URL"
exit
else
echo "Installing $VIRTUAL_ENV from\n $GECKODRIVER_URL"
FILE=`mktemp`
wget "$GECKODRIVER_URL" -qO $FILE && tar xz -C $VIRTUAL_ENV/bin/ -f $FILE geckodriver
rm $FILE
chmod 777 $VIRTUAL_ENV/bin/geckodriver
fi
}
pep8_check() { pep8_check() {
echo '[!] Running pep8 check' echo '[!] Running pep8 check'
# ignored rules: # ignored rules:
@ -43,6 +73,7 @@ tests() {
set -e set -e
pep8_check pep8_check
unit_tests unit_tests
check_geckodriver
robot_tests robot_tests
set +e set +e
} }
@ -88,6 +119,7 @@ Commands
unit_tests - Run unit tests unit_tests - Run unit tests
update_dev_packages - Check & update development and production dependency changes update_dev_packages - Check & update development and production dependency changes
update_packages - Check & update dependency changes update_packages - Check & update dependency changes
check_geckodriver - Check & download geckodriver (required for robot_tests)
" "
} }

View file

@ -1,12 +1,12 @@
certifi==2016.9.26 certifi==2016.9.26
flask==0.11.1 flask==0.12
flask-babel==0.11.1 flask-babel==0.11.1
lxml==3.6.0 lxml==3.7.1
ndg-httpsclient==0.4.1 ndg-httpsclient==0.4.2
pyasn1==0.1.9 pyasn1==0.1.9
pyasn1-modules==0.0.8 pyasn1-modules==0.0.8
pygments==2.1.3 pygments==2.1.3
pyopenssl==0.15.1 pyopenssl==16.2.0
python-dateutil==2.5.3 python-dateutil==2.5.3
pyyaml==3.11 pyyaml==3.11
requests[socks]==2.10.0 requests[socks]==2.12.4

View file

@ -81,22 +81,22 @@ def searx_bang(full_query):
engine_query = full_query.getSearchQuery()[1:] engine_query = full_query.getSearchQuery()[1:]
for lc in language_codes: for lc in language_codes:
lang_id, lang_name, country, english_name = map(str.lower, lc) lang_id, lang_name, country, english_name = map(unicode.lower, lc)
# check if query starts with language-id # check if query starts with language-id
if lang_id.startswith(engine_query): if lang_id.startswith(engine_query):
if len(engine_query) <= 2: if len(engine_query) <= 2:
results.append(':{lang_id}'.format(lang_id=lang_id.split('-')[0])) results.append(u':{lang_id}'.format(lang_id=lang_id.split('-')[0]))
else: else:
results.append(':{lang_id}'.format(lang_id=lang_id)) results.append(u':{lang_id}'.format(lang_id=lang_id))
# check if query starts with language name # check if query starts with language name
if lang_name.startswith(engine_query) or english_name.startswith(engine_query): if lang_name.startswith(engine_query) or english_name.startswith(engine_query):
results.append(':{lang_name}'.format(lang_name=lang_name)) results.append(u':{lang_name}'.format(lang_name=lang_name))
# check if query starts with country # check if query starts with country
if country.startswith(engine_query.replace('_', ' ')): if country.startswith(engine_query.replace('_', ' ')):
results.append(':{country}'.format(country=country.replace(' ', '_'))) results.append(u':{country}'.format(country=country.replace(' ', '_')))
# remove duplicates # remove duplicates
result_set = set(results) result_set = set(results)

View file

@ -42,7 +42,9 @@ def extract_text(xpath_results):
return ''.join(xpath_results) return ''.join(xpath_results)
else: else:
# it's a element # it's a element
return html_to_text(xpath_results.text_content()).strip() text = html.tostring(xpath_results, encoding='unicode', method='text', with_tail=False)
text = text.strip().replace('\n', ' ')
return ' '.join(text.split())
def extract_url(xpath_results, search_url): def extract_url(xpath_results, search_url):

View file

@ -4,13 +4,9 @@ $(document).ready(function() {
if ($(document).height() - win.height() == win.scrollTop()) { if ($(document).height() - win.height() == win.scrollTop()) {
var formData = $('#pagination form:last').serialize(); var formData = $('#pagination form:last').serialize();
if (formData) { if (formData) {
var pageno = $('#pagination input[name=pageno]:last').attr('value');
$('#pagination').html('<div class="loading-spinner"></div>'); $('#pagination').html('<div class="loading-spinner"></div>');
$.post('./', formData, function (data) { $.post('./', formData, function (data) {
var lastImageHref = $('.result-images:last a').attr('href');
var body = $(data); var body = $(data);
$('a[href^="#open-modal"]:last').attr('href', '#open-modal-1-' + pageno);
body.find('.modal-image a:first').attr('href', lastImageHref);
$('#pagination').remove(); $('#pagination').remove();
$('#main_results').append('<hr/>'); $('#main_results').append('<hr/>');
$('#main_results').append(body.find('.result')); $('#main_results').append(body.find('.result'));

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

View file

@ -1,77 +0,0 @@
.modal-image {
position: fixed;
top: 0;
right: 0;
bottom: 0;
left: 0;
background: rgba(0,0,0,0.8);
z-index: 1000000001;
opacity:0 !important;
pointer-events: none;
button {
display: none;
}
&:target {
opacity: 1 !important;
pointer-events: auto;
}
& > div {
margin: 2% auto;
width: 97%;
background: @dim-gray;
border: @gray 0.1rem solid;
}
@media (min-width: 769px) {
& > div {
max-width: 60.0rem;
}
}
.image-paging-left {
margin-right: 1.0rem;
margin-top: 0.5rem;
width:15px;
height:15px;
background: url(data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAA8AAAAPCAYAAAA71pVKAAAABmJLR0QA/wD/AP+gvaeTAAAACXBI
WXMAAAsTAAALEwEAmpwYAAAAB3RJTUUH4AweDQoOuikqUQAAAB1pVFh0Q29tbWVudAAAAAAAQ3Jl
YXRlZCB3aXRoIEdJTVBkLmUHAAAAiElEQVQoz6XTrQ0CQRCG4SesQHI5g6EAqIEewNLSVUACzfAT
BApDDSgSBAaJORKyauf2czOZdybzl5SpxR5j3H/OUQHYoMMMNwE1fcUT5hFwUgPuenAxBDxHwRZb
HKMgbPDCuiQ4ZfYDU6xwxTNafXDP1dOu3nP1heUJDnmCVAB/cMES7/+v+gIq0Bs3k6NL9AAAAABJ
RU5ErkJggg==) 96% no-repeat;
}
.image-paging-right {
margin-left: 1.2rem;
margin-top: 0.5rem;
width:15px;
height:15px;
background: url(data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAA8AAAAPCAYAAAA71pVKAAAABmJLR0QA/wD/AP+gvaeTAAAACXBI
WXMAAAsTAAALEwEAmpwYAAAAB3RJTUUH4AweDQon+JuyPQAAAB1pVFh0Q29tbWVudAAAAAAAQ3Jl
YXRlZCB3aXRoIEdJTVBkLmUHAAAAaklEQVQoz73TsQ2DUAxF0SMWAFEzwGcaWhgpEyAlbQYJMACj
sAINTaiIf8Tt3FzL9jPfDHijdoHiVK9o8EAlQMKM1z8EZUTQHoJnjmDJFUwYr17hTIcN/W2dwzOH
tx2+czhhCZ9oNH/6qh1F2RaYgWxrQwAAAABJRU5ErkJggg==);
}
.image-container::before {
display: block;
min-width: 1.0rem;
max-width: 60.0rem;
min-height: 10.0rem;
height: 30.0rem;
content: "";
}
}
.modal-close {
position:fixed;
top: 0;
left: 0;
height: 100% !important;
width: 100% !important;
z-index: -1;
}

View file

@ -19,5 +19,3 @@
@import "cursor.less"; @import "cursor.less";
@import "code.less"; @import "code.less";
@import "modal-pic.less";

View file

@ -17,7 +17,3 @@
@import "code.less"; @import "code.less";
@import "navbar.less"; @import "navbar.less";
@import "../logicodev/variables.less";
@import "../logicodev/modal-pic.less";

View file

@ -1,54 +1,39 @@
<a href="#open-modal-{{ index }}-{{ pageno }}"> {% from 'oscar/macros.html' import draw_favicon %}
<img src="{% if result.thumbnail_src %}{{ image_proxify(result.thumbnail_src) }}{% else %}{{ image_proxify(result.img_src) }}{% endif %}" alt="{{ result.title|striptags }}" title="{{ result.title|striptags }}" class="img-thumbnail" id="img-result-thumb-{{ index }}" />
<a href="{{ result.img_src }}" {% if results_on_new_tab %}target="_blank" rel="noopener noreferrer"{% else %}rel="noreferrer"{% endif %} data-toggle="modal" data-target="#modal-{{ index }}-{{pageno}}">
<img src="{% if result.thumbnail_src %}{{ image_proxify(result.thumbnail_src) }}{% else %}{{ image_proxify(result.img_src) }}{% endif %}" alt="{{ result.title|striptags }}" title="{{ result.title|striptags }}" class="img-thumbnail">
</a> </a>
<style type="text/css" media="screen"> <div class="modal fade" id="modal-{{ index }}-{{ pageno }}" tabindex="-1" role="dialog" aria-hidden="true">
#open-modal-{{ index }}-{{ pageno }}:target .image-container::before { <div class="modal-dialog">
background: url({{ image_proxify(result.img_src)|safe }}) no-repeat center/contain; <div class="modal-wrapper">
} <div class="modal-header">
</style> <button type="button" class="close" data-dismiss="modal"><span aria-hidden="true">&times;</span><span class="sr-only">Close</span></button>
<h4 class="modal-title">{% if result.engine~".png" in favicons %}{{ draw_favicon(result.engine) }} {% endif %}{{ result.title|striptags }}</h4>
<div id="open-modal-{{ index }}-{{ pageno }}" class="modal-image">
<div class="container modal-dialog">
<div class="row">
<div class="col-md-12 col-sm-12 col-xs-12 modal-header">
<a {% if index != 1 %}href="#open-modal-{{ index-1 }}-{{ pageno }}"{% endif %}>
<span class="pull-left image-paging-left"></span>
</a>
<a href="#open-modal-{{ index+1 }}-{{ pageno }}">
<span class="pull-right image-paging-right"></span>
</a>
<h4 class="modal-title image-title">{{ result.title|striptags }}</h4>
</div> </div>
</div> <div class="modal-body">
<div class="row"> <img class="img-responsive center-block" src="{% if result.thumbnail_src %}{{ image_proxify(result.thumbnail_src) }}{% else %}{{ image_proxify(result.img_src) }}{% endif %}" alt="{{ result.title|striptags }}">
<div class="col-md-12 col-sm-12 col-xs-12 modal-body">
<a href="{{ result.img_src }}" {% if results_on_new_tab %}target="_blank" rel="noopener noreferrer"{% else %}rel="noreferrer"{% endif %}><div class="image-container"></div></a>
</div>
</div>
{% if result.content %}
<div class="row">
<div class="col-md-12 hidden-sm hidden-xs modal-body">
<p class="result-content">{{ result.content|safe }}</p>
{% if result.author %}<span class="photo-author">{{ result.author }}</span><br />{% endif %} {% if result.author %}<span class="photo-author">{{ result.author }}</span><br />{% endif %}
</div> {% if result.content %}
</div> <p class="result-content">
{{ result.content }}
</p>
{% endif %} {% endif %}
</div>
<div class="modal-footer"> <div class="modal-footer">
<div class="row"> <div class="clearfix"></div>
<div class="col-md-10 col-xs-12">
<p class="text-muted pull-left">{{ result.pretty_url }}</p>
</div>
<div class="col-md-2 hidden-sm hidden-xs">
<span class="label label-default pull-right">{{ result.engine }}</span> <span class="label label-default pull-right">{{ result.engine }}</span>
</div> <p class="text-muted pull-left">{{ result.pretty_url }}</p>
</div> <div class="clearfix"></div>
<div class="row"> <div class="row">
<a href="{{ result.url }}" class="btn btn-default"> <div class="col-md-6">
{{ _('View source') }} <a href="{{ result.img_src }}" {% if results_on_new_tab %}target="_blank" rel="noopener noreferrer"{% else %}rel="noreferrer"{% endif %} class="btn btn-default">{{ _('Get image') }}</a>
</a> </div>
<div class="col-md-6">
<a href="{{ result.url }}" {% if results_on_new_tab %}target="_blank" rel="noopener noreferrer"{% else %}rel="noreferrer"{% endif %} class="btn btn-default">{{ _('View source') }}</a>
</div>
</div>
</div> </div>
</div> </div>
</div> </div>
<a href="#img-result-thumb-{{ index }}-{{ pageno }}" class="modal-close"></a>
</div> </div>

View file

@ -13,10 +13,9 @@ request_params = default_request_params()
# Possible params # Possible params
# request_params['headers']['User-Agent'] = '' # request_params['headers']['User-Agent'] = ''
# request_params['category'] = '' # request_params['category'] = ''
# request_params['started'] = ''
request_params['pageno'] = 1 request_params['pageno'] = 1
request_params['language'] = 'en_us' request_params['language'] = 'en_us'
request_params['time_range'] = ''
params = google.request(argv[1], request_params) params = google.request(argv[1], request_params)
@ -32,5 +31,5 @@ else:
request_args['data'] = request_params['data'] request_args['data'] = request_params['data']
resp = req(request_params['url'], **request_args) resp = req(request_params['url'], **request_args)
resp.search_params = request_params
print(dumps(google.response(resp))) print(dumps(google.response(resp)))

101
utils/standalone_searx.py Executable file
View file

@ -0,0 +1,101 @@
#!/usr/bin/env python
'''
searx is free software: you can redistribute it and/or modify
it under the terms of the GNU Affero General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
searx is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU Affero General Public License for more details.
You should have received a copy of the GNU Affero General Public License
along with searx. If not, see < http://www.gnu.org/licenses/ >.
(C) 2016- by Alexandre Flament, <alex@al-f.net>
'''
# set path
from sys import path
from os.path import realpath, dirname
path.append(realpath(dirname(realpath(__file__)) + '/../'))
# initialization
from json import dumps
from searx import settings
import searx.query
import searx.search
import searx.engines
import searx.preferences
import argparse
searx.engines.initialize_engines(settings['engines'])
# command line parsing
parser = argparse.ArgumentParser(description='Standalone searx.')
parser.add_argument('query', type=str,
help='Text query')
parser.add_argument('--category', type=str, nargs='?',
choices=searx.engines.categories.keys(),
default='general',
help='Search category')
parser.add_argument('--lang', type=str, nargs='?',default='all',
help='Search language')
parser.add_argument('--pageno', type=int, nargs='?', default=1,
help='Page number starting from 1')
parser.add_argument('--safesearch', type=str, nargs='?', choices=['0', '1', '2'], default='0',
help='Safe content filter from none to strict')
parser.add_argument('--timerange', type=str, nargs='?', choices=['day', 'week', 'month', 'year'],
help='Filter by time range')
args = parser.parse_args()
# search results for the query
form = {
"q":args.query,
"categories":args.category.decode('utf-8'),
"pageno":str(args.pageno),
"language":args.lang,
"time_range":args.timerange
}
preferences = searx.preferences.Preferences(['oscar'], searx.engines.categories.keys(), searx.engines.engines, [])
preferences.key_value_settings['safesearch'].parse(args.safesearch)
search_query = searx.search.get_search_query_from_webapp(preferences, form)
search = searx.search.Search(search_query)
result_container = search.search()
# output
from datetime import datetime
def no_parsed_url(results):
for result in results:
del result['parsed_url']
return results
def json_serial(obj):
"""JSON serializer for objects not serializable by default json code"""
if isinstance(obj, datetime):
serial = obj.isoformat()
return serial
raise TypeError ("Type not serializable")
result_container_json = {
"search": {
"q": search_query.query,
"pageno": search_query.pageno,
"lang": search_query.lang,
"safesearch": search_query.safesearch,
"timerange": search_query.time_range,
"engines": search_query.engines
},
"results": no_parsed_url(result_container.get_ordered_results()),
"infoboxes": result_container.infoboxes,
"suggestions": list(result_container.suggestions),
"answers": list(result_container.answers),
"paging": result_container.paging,
"results_number": result_container.results_number()
}
print(dumps(result_container_json, sort_keys=True, indent=4, ensure_ascii=False, encoding="utf-8", default=json_serial))