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
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
|
#!/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) 2013- by Adam Tauber, <asciimoo@gmail.com>
'''
import json
import cStringIO
import os
from flask import Flask, request, render_template
from flask import url_for, Response, make_response, redirect
from flask import send_from_directory
from searx import settings, searx_dir
from searx.engines import search, categories, engines, get_engines_stats
from searx.utils import UnicodeWriter
from searx.utils import highlight_content, html_to_text
from searx.languages import language_codes
from flask.ext.babel import Babel
app = Flask(
__name__,
static_folder=os.path.join(searx_dir, 'static'),
template_folder=os.path.join(searx_dir, 'templates')
)
app.secret_key = settings['server']['secret_key']
babel = Babel(app)
#TODO configurable via settings.yml
favicons = ['wikipedia', 'youtube', 'vimeo', 'soundcloud',
'twitter', 'stackoverflow', 'github']
@babel.localeselector
def get_locale():
locale = request.accept_languages.best_match(settings['locales'].keys())
if request.cookies.get('locale', '') in settings['locales']:
locale = request.cookies.get('locale', '')
if 'locale' in request.args\
and request.args['locale'] in settings['locales']:
locale = request.args['locale']
if 'locale' in request.form\
and request.form['locale'] in settings['locales']:
locale = request.form['locale']
return locale
def get_base_url():
if settings['server']['base_url']:
hostname = settings['server']['base_url']
else:
scheme = 'http'
if request.is_secure:
scheme = 'https'
hostname = url_for('index', _external=True, _scheme=scheme)
return hostname
def render(template_name, **kwargs):
global categories
kwargs['categories'] = ['general']
kwargs['categories'].extend(x for x in
sorted(categories.keys()) if x != 'general')
if not 'selected_categories' in kwargs:
kwargs['selected_categories'] = []
cookie_categories = request.cookies.get('categories', '').split(',')
for ccateg in cookie_categories:
if ccateg in categories:
kwargs['selected_categories'].append(ccateg)
if not len(kwargs['selected_categories']):
kwargs['selected_categories'] = ['general']
return render_template(template_name, **kwargs)
def parse_query(query):
query_engines = []
query_parts = query.split()
if query_parts[0].startswith('-'):
engine_name = query_parts[0][1:].replace('_', ' ')
if engine_name in engines:
query_engines.append({'category': 'none',
'name': query_parts[0][1:]})
elif query_parts[0].startswith('!'):
category_name = query_parts[0][1:].replace('_', ' ')
if category_name in categories:
query_engines.extend({'category': category_name,
'name': engine.name}
for engine in categories[category_name])
if len(query_engines):
query = query.replace(query_parts[0], '', 1).strip()
return query, query_engines
@app.route('/', methods=['GET', 'POST'])
def index():
paging = False
lang = 'all'
if request.cookies.get('language')\
and request.cookies['language'] in (x[0] for x in language_codes):
lang = request.cookies['language']
if request.method == 'POST':
request_data = request.form
else:
request_data = request.args
if not request_data.get('q'):
return render('index.html')
pageno_param = request_data.get('pageno', '1')
if not pageno_param.isdigit() or int(pageno_param) < 1:
return render('index.html')
pageno = int(pageno_param)
selected_categories = []
query, selected_engines = parse_query(request_data['q'].encode('utf-8'))
if len(selected_engines):
selected_categories = list(set(engine['category']
for engine in selected_engines))
else:
for pd_name, pd in request_data.items():
if pd_name.startswith('category_'):
category = pd_name[9:]
if not category in categories:
continue
selected_categories.append(category)
if not len(selected_categories):
cookie_categories = request.cookies.get('categories', '')
cookie_categories = cookie_categories.split(',')
for ccateg in cookie_categories:
if ccateg in categories:
selected_categories.append(ccateg)
if not len(selected_categories):
selected_categories = ['general']
for categ in selected_categories:
selected_engines.extend({'category': categ,
'name': x.name}
for x in categories[categ])
results, suggestions = search(query,
request,
selected_engines,
pageno,
lang)
for result in results:
if not paging and engines[result['engine']].paging:
paging = True
if request_data.get('format', 'html') == 'html':
if 'content' in result:
result['content'] = highlight_content(result['content'], query)
result['title'] = highlight_content(result['title'], query)
else:
if 'content' in result:
result['content'] = html_to_text(result['content']).strip()
result['title'] = html_to_text(result['title']).strip()
if len(result['url']) > 74:
url_parts = result['url'][:35], result['url'][-35:]
result['pretty_url'] = '{0}[...]{1}'.format(*url_parts)
else:
result['pretty_url'] = result['url']
for engine in result['engines']:
if engine in favicons:
result['favicon'] = engine
if request_data.get('format') == 'json':
return Response(json.dumps({'query': query, 'results': results}),
mimetype='application/json')
elif request_data.get('format') == 'csv':
csv = UnicodeWriter(cStringIO.StringIO())
keys = ('title', 'url', 'content', 'host', 'engine', 'score')
if len(results):
csv.writerow(keys)
for row in results:
row['host'] = row['parsed_url'].netloc
csv.writerow([row.get(key, '') for key in keys])
csv.stream.seek(0)
response = Response(csv.stream.read(), mimetype='application/csv')
content_disp = 'attachment;Filename=searx_-_{0}.csv'.format(query)
response.headers.add('Content-Disposition', content_disp)
return response
elif request_data.get('format') == 'rss':
response_rss = render(
'opensearch_response_rss.xml',
results=results,
q=request_data['q'],
number_of_results=len(results),
base_url=get_base_url()
)
return Response(response_rss, mimetype='text/xml')
return render(
'results.html',
results=results,
q=request_data['q'],
selected_categories=selected_categories,
paging=paging,
pageno=pageno,
suggestions=suggestions
)
@app.route('/about', methods=['GET'])
def about():
return render('about.html')
@app.route('/engines', methods=['GET'])
def list_engines():
global categories
return render('engines.html', categs=categories.items())
@app.route('/preferences', methods=['GET', 'POST'])
def preferences():
lang = None
if request.cookies.get('language')\
and request.cookies['language'] in (x[0] for x in language_codes):
lang = request.cookies['language']
if request.method == 'POST':
selected_categories = []
locale = None
for pd_name, pd in request.form.items():
if pd_name.startswith('category_'):
category = pd_name[9:]
if not category in categories:
continue
selected_categories.append(category)
elif pd_name == 'locale' and pd in settings['locales']:
locale = pd
elif pd_name == 'language' and (pd == 'all' or
pd in (x[0] for
x in language_codes)):
lang = pd
resp = make_response(redirect('/'))
if locale:
# cookie max age: 4 weeks
resp.set_cookie(
'locale', locale,
max_age=60 * 60 * 24 * 7 * 4
)
if lang:
# cookie max age: 4 weeks
resp.set_cookie(
'language', lang,
max_age=60 * 60 * 24 * 7 * 4
)
if selected_categories:
# cookie max age: 4 weeks
resp.set_cookie(
'categories', ','.join(selected_categories),
max_age=60 * 60 * 24 * 7 * 4
)
return resp
return render('preferences.html',
locales=settings['locales'],
current_locale=get_locale(),
current_language=lang or 'all',
language_codes=language_codes)
@app.route('/stats', methods=['GET'])
def stats():
global categories
stats = get_engines_stats()
return render('stats.html', stats=stats)
@app.route('/robots.txt', methods=['GET'])
def robots():
return Response("""User-agent: *
Allow: /
Allow: /about
Disallow: /stats
Disallow: /engines
""", mimetype='text/plain')
@app.route('/opensearch.xml', methods=['GET'])
def opensearch():
method = 'post'
# chrome/chromium only supports HTTP GET....
if request.headers.get('User-Agent', '').lower().find('webkit') >= 0:
method = 'get'
ret = render('opensearch.xml', method=method, host=get_base_url())
resp = Response(response=ret,
status=200,
mimetype="application/xml")
return resp
@app.route('/favicon.ico')
def favicon():
return send_from_directory(os.path.join(app.root_path, 'static/img'),
'favicon.png',
mimetype='image/vnd.microsoft.icon')
def run():
from gevent import monkey
monkey.patch_all()
app.run(
debug=settings['server']['debug'],
use_debugger=settings['server']['debug'],
port=settings['server']['port']
)
if __name__ == "__main__":
run()
|