This commit is contained in:
pw3t 2014-01-23 22:11:36 +01:00
commit 132681b3aa
52 changed files with 889 additions and 412 deletions

20
.gitignore vendored
View File

@ -1,20 +1,24 @@
env
engines.cfg
.installed.cfg
.coverage .coverage
covearge/ .installed.cfg
engines.cfg
env
robot_log.html
robot_output.xml
robot_report.html
setup.cfg setup.cfg
*.pyc *.pyc
*/*.pyc */*.pyc
bin/ bin/
build/
covearge/
develop-eggs/
dist/
eggs/
include/ include/
lib/ lib/
build/
develop-eggs/
eggs/
local/ local/
searx.egg-info/
parts/ parts/
searx.egg-info/
var/ var/

View File

@ -21,11 +21,7 @@ $(python):
tests: .installed.cfg tests: .installed.cfg
@bin/test @bin/test
enginescfg: robot: .installed.cfg
@test -f ./engines.cfg || echo "Copying engines.cfg ..."
@cp --no-clobber engines.cfg_sample engines.cfg
robot: .installed.cfg enginescfg
@bin/robot @bin/robot
flake8: .installed.cfg flake8: .installed.cfg
@ -37,18 +33,21 @@ coverage: .installed.cfg
@bin/coverage report --show-missing @bin/coverage report --show-missing
@bin/coverage html --directory ./coverage @bin/coverage html --directory ./coverage
production: bin/buildout production.cfg setup.py enginescfg production: bin/buildout production.cfg setup.py
bin/buildout -c production.cfg $(options) bin/buildout -c production.cfg $(options)
@echo "* Please modify `readlink --canonicalize-missing ./searx/settings.py`" @echo "* Please modify `readlink --canonicalize-missing ./searx/settings.py`"
@echo "* Hint 1: on production, disable debug mode and change secret_key" @echo "* Hint 1: on production, disable debug mode and change secret_key"
@echo "* Hint 2: searx will be executed at server startup by crontab" @echo "* Hint 2: searx will be executed at server startup by crontab"
@echo "* Hint 3: to run immediatley, execute 'bin/supervisord'" @echo "* Hint 3: to run immediatley, execute 'bin/supervisord'"
minimal: bin/buildout minimal.cfg setup.py enginescfg minimal: bin/buildout minimal.cfg setup.py
bin/buildout -c minimal.cfg $(options) bin/buildout -c minimal.cfg $(options)
locales:
@pybabel compile -d searx/translations
clean: clean:
@rm -rf .installed.cfg .mr.developer.cfg bin parts develop-eggs \ @rm -rf .installed.cfg .mr.developer.cfg bin parts develop-eggs \
searx.egg-info lib include .coverage coverage searx.egg-info lib include .coverage coverage
.PHONY: all tests enginescfg robot flake8 coverage production minimal clean .PHONY: all tests robot flake8 coverage production minimal locales clean

122
README.md
View File

@ -1,122 +0,0 @@
searx
=====
A privacy-respecting, hackable [metasearch engine](https://en.wikipedia.org/wiki/Metasearch_engine).
List of [running instances](https://github.com/asciimoo/searx/wiki/Searx-instances).
[![Flattr searx](http://api.flattr.com/button/flattr-badge-large.png)](https://flattr.com/submit/auto?user_id=asciimoo&url=https://github.com/asciimoo/searx&title=searx&language=&tags=github&category=software)
### Features
* Tracking free
* Modular (see [examples](https://github.com/asciimoo/searx/blob/master/examples))
* Parallel queries
* Supports multiple output formats
* json `curl https://searx.0x2a.tk/?format=json&q=[query]`
* csv `curl https://searx.0x2a.tk/?format=csv&q=[query]`
* opensearch/rss `curl https://searx.0x2a.tk/?format=rss&q=[query]`
* Opensearch support (you can set as default search engine)
* Configurable search engines/categories
### Installation
* clone source: `git clone git@github.com:asciimoo/searx.git && cd searx`
* install dependencies: `pip install -r requirements.txt`
* edit your [settings.yml](https://github.com/asciimoo/searx/blob/master/settings.yml) (set your `secret_key`!)
* run `python searx/webapp.py` to start the application
For all the details, follow this [step by step installation](https://github.com/asciimoo/searx/wiki/Installation)
### Alternative (Recommended) Installation
* clone source: `git clone git@github.com:asciimoo/searx.git && cd searx`
* build in current folder: `make minimal`
* run `bin/searx-run` to start the application
### Development
Just run `make`. Versions of dependencies are pinned down inside `versions.cfg` to produce most stable build. Also remember, NO make command should be run as root, not even `make production`
### Deployment
* clone source: `git clone git@github.com:asciimoo/searx.git && cd searx`
* build in current folder: `make production`
* run `bin/supervisord` to start the application
### Upgrading
* inside previously cloned searx directory run: `git stash` to temporarily save any changes you have made
* pull source: `git pull origin master`
* re-build in current folder: `make production`
* run `bin/supervisorctl stop searx` to stop searx, if it does not, then run `fuser -k 8888/tcp`
* run `bin/supervisorctl reload` to re-read supervisor config and start searx
### Command make
##### `make`
Builds development environment with testing support.
##### `make tests`
Runs tests. You can write tests [here](https://github.com/asciimoo/searx/tree/master/searx/tests) and remember 'untested code is broken code'.
##### `make robot`
Runs robot (Selenium) tests, you must have `firefox` installed because this functional tests actually run the browser and perform operations on it. Also searx is executed with [settings_robot](https://github.com/asciimoo/searx/blob/master/searx/settings_robot.py).
##### `make flake8`
'pep8 is a tool to check your Python code against some of the style conventions in [PEP 8](http://www.python.org/dev/peps/pep-0008/).'
##### `make coverage`
Checks coverage of tests, after running this, execute this: `firefox ./coverage/index.html`
##### `make production`
Used to make co-called production environment - without tests (you should ran tests before deploying searx on the server). This installs supervisord, so if searx crashes, it will try to pick itself up again. And crontab entry is added to start supervisord at server boot.
##### `make minimal`
Minimal build - without test frameworks, the quickest build option.
##### `make clean`
Deletes several folders and files (see `Makefile` for more), so that next time you run any other `make` command it will rebuild everithing.
### TODO
* Moar engines
* Better ui
* Language support
* Documentation
* Pagination
* Fix `flake8` errors, `make flake8` will be merged into `make tests` when it does not fail anymore
* Tests
* When we have more tests, we can integrate Travis-CI
### Bugs
Bugs or suggestions? Visit the [issue tracker](https://github.com/asciimoo/searx/issues).
### [License](https://github.com/asciimoo/searx/blob/master/LICENSE)
### More about searx
* [ohloh](https://www.ohloh.net/p/searx/)
* [twitter](https://twitter.com/Searx_engine)
* IRC: #searx @ freenode

159
README.rst Normal file
View File

@ -0,0 +1,159 @@
searx
=====
A privacy-respecting, hackable `metasearch
engine <https://en.wikipedia.org/wiki/Metasearch_engine>`__.
List of `running
instances <https://github.com/asciimoo/searx/wiki/Searx-instances>`__.
|Flattr searx|
Features
~~~~~~~~
- Tracking free
- Modular (see
`examples <https://github.com/asciimoo/searx/blob/master/examples>`__)
- Parallel queries
- Supports multiple output formats
- json ``curl https://searx.0x2a.tk/?format=json&q=[query]``
- csv ``curl https://searx.0x2a.tk/?format=csv&q=[query]``
- opensearch/rss ``curl https://searx.0x2a.tk/?format=rss&q=[query]``
- Opensearch support (you can set as default search engine)
- Configurable search engines/categories
Installation
~~~~~~~~~~~~
- clone source:
``git clone git@github.com:asciimoo/searx.git && cd searx``
- install dependencies: ``pip install -r requirements.txt``
- edit your
`settings.yml <https://github.com/asciimoo/searx/blob/master/settings.yml>`__
(set your ``secret_key``!)
- run ``python searx/webapp.py`` to start the application
For all the details, follow this `step by step
installation <https://github.com/asciimoo/searx/wiki/Installation>`__
Alternative (Recommended) Installation
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- clone source:
``git clone git@github.com:asciimoo/searx.git && cd searx``
- build in current folder: ``make minimal``
- run ``bin/searx-run`` to start the application
Development
~~~~~~~~~~~
Just run ``make``. Versions of dependencies are pinned down inside
``versions.cfg`` to produce most stable build. Also remember, NO make
command should be run as root, not even ``make production``
Deployment
~~~~~~~~~~
- clone source:
``git clone git@github.com:asciimoo/searx.git && cd searx``
- build in current folder: ``make production``
- run ``bin/supervisord`` to start the application
Upgrading
~~~~~~~~~
- inside previously cloned searx directory run: ``git stash`` to
temporarily save any changes you have made
- pull source: ``git pull origin master``
- re-build in current folder: ``make production``
- run ``bin/supervisorctl stop searx`` to stop searx, if it does not,
then run ``fuser -k 8888/tcp``
- run ``bin/supervisorctl reload`` to re-read supervisor config and
start searx
Command make
~~~~~~~~~~~~
``make``
''''''''
Builds development environment with testing support.
``make tests``
''''''''''''''
Runs tests. You can write tests
`here <https://github.com/asciimoo/searx/tree/master/searx/tests>`__ and
remember 'untested code is broken code'.
``make robot``
''''''''''''''
Runs robot (Selenium) tests, you must have ``firefox`` installed because
this functional tests actually run the browser and perform operations on
it. Also searx is executed with
`settings\_robot <https://github.com/asciimoo/searx/blob/master/searx/settings_robot.py>`__.
``make flake8``
'''''''''''''''
'pep8 is a tool to check your Python code against some of the style
conventions in `PEP 8 <http://www.python.org/dev/peps/pep-0008/>`__.'
``make coverage``
'''''''''''''''''
Checks coverage of tests, after running this, execute this:
``firefox ./coverage/index.html``
``make production``
'''''''''''''''''''
Used to make co-called production environment - without tests (you
should ran tests before deploying searx on the server). This installs
supervisord, so if searx crashes, it will try to pick itself up again.
And crontab entry is added to start supervisord at server boot.
``make minimal``
''''''''''''''''
Minimal build - without test frameworks, the quickest build option.
``make clean``
''''''''''''''
Deletes several folders and files (see ``Makefile`` for more), so that
next time you run any other ``make`` command it will rebuild everithing.
TODO
~~~~
- Moar engines
- Better ui
- Language support
- Documentation
- Pagination
- Fix ``flake8`` errors, ``make flake8`` will be merged into
``make tests`` when it does not fail anymore
- Tests
- When we have more tests, we can integrate Travis-CI
Bugs
~~~~
Bugs or suggestions? Visit the `issue
tracker <https://github.com/asciimoo/searx/issues>`__.
`License <https://github.com/asciimoo/searx/blob/master/LICENSE>`__
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
More about searx
~~~~~~~~~~~~~~~~
- `ohloh <https://www.ohloh.net/p/searx/>`__
- `twitter <https://twitter.com/Searx_engine>`__
- IRC: #searx @ freenode
.. |Flattr searx| image:: http://api.flattr.com/button/flattr-badge-large.png
:target: https://flattr.com/submit/auto?user_id=asciimoo&url=https://github.com/asciimoo/searx&title=searx&language=&tags=github&category=software

3
babel.cfg Normal file
View File

@ -0,0 +1,3 @@
[python: **.py]
[jinja2: **/templates/**.html]
extensions=jinja2.ext.autoescape,jinja2.ext.with_

View File

@ -16,8 +16,6 @@ recipe = zc.recipe.egg:script
eggs = ${buildout:eggs} eggs = ${buildout:eggs}
interpreter = py interpreter = py
dependent-scripts = true dependent-scripts = true
entry-points =
searx-run=searx.webapp:run
[robot] [robot]

View File

@ -13,5 +13,3 @@ parts +=
recipe = zc.recipe.egg:script recipe = zc.recipe.egg:script
eggs = ${buildout:eggs} eggs = ${buildout:eggs}
interpreter = py interpreter = py
entry-points =
searx-run=searx.webapp:run

View File

@ -15,8 +15,6 @@ parts +=
recipe = zc.recipe.egg:script recipe = zc.recipe.egg:script
eggs = ${buildout:eggs} eggs = ${buildout:eggs}
interpreter = py interpreter = py
entry-points =
searx-run=searx.webapp:run
[supervisor] [supervisor]

View File

@ -1,4 +1,5 @@
flask flask
flask-babel
grequests grequests
lxml lxml
pyyaml pyyaml

View File

@ -1,5 +1,5 @@
from os import environ from os import environ
from os.path import realpath, dirname, join from os.path import realpath, dirname, join, abspath
try: try:
from yaml import load from yaml import load
except: except:
@ -7,8 +7,7 @@ except:
stderr.write('[E] install pyyaml\n') stderr.write('[E] install pyyaml\n')
exit(2) exit(2)
searx_dir = abspath(dirname(__file__))
searx_dir = realpath(dirname(realpath(__file__))+'/../')
engine_dir = dirname(realpath(__file__)) engine_dir = dirname(realpath(__file__))
if 'SEARX_SETTINGS_PATH' in environ: if 'SEARX_SETTINGS_PATH' in environ:
@ -19,4 +18,3 @@ else:
with open(settings_path) as settings_yaml: with open(settings_path) as settings_yaml:
settings = load(settings_yaml) settings = load(settings_yaml)

View File

@ -26,6 +26,7 @@ from searx import settings
from searx.utils import gen_useragent from searx.utils import gen_useragent
import sys import sys
from datetime import datetime from datetime import datetime
from flask.ext.babel import gettext
engine_dir = dirname(realpath(__file__)) engine_dir = dirname(realpath(__file__))
@ -35,6 +36,7 @@ engines = {}
categories = {'general': []} categories = {'general': []}
def load_module(filename): def load_module(filename):
modname = splitext(filename)[0] modname = splitext(filename)[0]
if modname in sys.modules: if modname in sys.modules:
@ -50,7 +52,7 @@ if not 'engines' in settings or not settings['engines']:
for engine_data in settings['engines']: for engine_data in settings['engines']:
engine_name = engine_data['engine'] engine_name = engine_data['engine']
engine = load_module(engine_name+'.py') engine = load_module(engine_name + '.py')
for param_name in engine_data: for param_name in engine_data:
if param_name == 'engine': if param_name == 'engine':
continue continue
@ -58,38 +60,50 @@ for engine_data in settings['engines']:
if engine_data['categories'] == 'none': if engine_data['categories'] == 'none':
engine.categories = [] engine.categories = []
else: else:
engine.categories = map(str.strip, engine_data['categories'].split(',')) engine.categories = map(
str.strip, engine_data['categories'].split(','))
continue continue
setattr(engine, param_name, engine_data[param_name]) setattr(engine, param_name, engine_data[param_name])
for engine_attr in dir(engine): for engine_attr in dir(engine):
if engine_attr.startswith('_'): if engine_attr.startswith('_'):
continue continue
if getattr(engine, engine_attr) == None: if getattr(engine, engine_attr) is None:
print '[E] Engine config error: Missing attribute "{0}.{1}"'.format(engine.name, engine_attr) print '[E] Engine config error: Missing attribute "{0}.{1}"'.format(engine.name, engine_attr) # noqa
sys.exit(1) sys.exit(1)
engines[engine.name] = engine engines[engine.name] = engine
engine.stats = {'result_count': 0, 'search_count': 0, 'page_load_time': 0, 'score_count': 0, 'errors': 0} engine.stats = {
'result_count': 0,
'search_count': 0,
'page_load_time': 0,
'score_count': 0,
'errors': 0
}
if hasattr(engine, 'categories'): if hasattr(engine, 'categories'):
for category_name in engine.categories: for category_name in engine.categories:
categories.setdefault(category_name, []).append(engine) categories.setdefault(category_name, []).append(engine)
else: else:
categories['general'].append(engine) categories['general'].append(engine)
def default_request_params(): def default_request_params():
return {'method': 'GET', 'headers': {}, 'data': {}, 'url': '', 'cookies': {}} return {
'method': 'GET', 'headers': {}, 'data': {}, 'url': '', 'cookies': {}}
def make_callback(engine_name, results, suggestions, callback, params): def make_callback(engine_name, results, suggestions, callback, params):
# creating a callback wrapper for the search engine results # creating a callback wrapper for the search engine results
def process_callback(response, **kwargs): def process_callback(response, **kwargs):
cb_res = [] cb_res = []
response.search_params = params response.search_params = params
engines[engine_name].stats['page_load_time'] += (datetime.now() - params['started']).total_seconds() engines[engine_name].stats['page_load_time'] += \
(datetime.now() - params['started']).total_seconds()
try: try:
search_results = callback(response) search_results = callback(response)
except Exception, e: except Exception, e:
engines[engine_name].stats['errors'] += 1 engines[engine_name].stats['errors'] += 1
results[engine_name] = cb_res results[engine_name] = cb_res
print '[E] Error with engine "{0}":\n\t{1}'.format(engine_name, str(e)) print '[E] Error with engine "{0}":\n\t{1}'.format(
engine_name, str(e))
return return
for result in search_results: for result in search_results:
result['engine'] = engine_name result['engine'] = engine_name
@ -101,23 +115,25 @@ def make_callback(engine_name, results, suggestions, callback, params):
results[engine_name] = cb_res results[engine_name] = cb_res
return process_callback return process_callback
def score_results(results): def score_results(results):
flat_res = filter(None, chain.from_iterable(izip_longest(*results.values()))) flat_res = filter(
None, chain.from_iterable(izip_longest(*results.values())))
flat_len = len(flat_res) flat_len = len(flat_res)
engines_len = len(results) engines_len = len(results)
results = [] results = []
# deduplication + scoring # deduplication + scoring
for i,res in enumerate(flat_res): for i, res in enumerate(flat_res):
res['parsed_url'] = urlparse(res['url']) res['parsed_url'] = urlparse(res['url'])
res['engines'] = [res['engine']] res['engines'] = [res['engine']]
weight = 1.0 weight = 1.0
if hasattr(engines[res['engine']], 'weight'): if hasattr(engines[res['engine']], 'weight'):
weight = float(engines[res['engine']].weight) weight = float(engines[res['engine']].weight)
score = int((flat_len - i)/engines_len)*weight+1 score = int((flat_len - i) / engines_len) * weight + 1
duplicated = False duplicated = False
for new_res in results: for new_res in results:
p1 = res['parsed_url'].path[:-1] if res['parsed_url'].path.endswith('/') else res['parsed_url'].path p1 = res['parsed_url'].path[:-1] if res['parsed_url'].path.endswith('/') else res['parsed_url'].path # noqa
p2 = new_res['parsed_url'].path[:-1] if new_res['parsed_url'].path.endswith('/') else new_res['parsed_url'].path p2 = new_res['parsed_url'].path[:-1] if new_res['parsed_url'].path.endswith('/') else new_res['parsed_url'].path # noqa
if res['parsed_url'].netloc == new_res['parsed_url'].netloc and\ if res['parsed_url'].netloc == new_res['parsed_url'].netloc and\
p1 == p2 and\ p1 == p2 and\
res['parsed_url'].query == new_res['parsed_url'].query and\ res['parsed_url'].query == new_res['parsed_url'].query and\
@ -125,7 +141,7 @@ def score_results(results):
duplicated = new_res duplicated = new_res
break break
if duplicated: if duplicated:
if len(res.get('content', '')) > len(duplicated.get('content', '')): if len(res.get('content', '')) > len(duplicated.get('content', '')): # noqa
duplicated['content'] = res['content'] duplicated['content'] = res['content']
duplicated['score'] += score duplicated['score'] += score
duplicated['engines'].append(res['engine']) duplicated['engines'].append(res['engine'])
@ -139,6 +155,7 @@ def score_results(results):
results.append(res) results.append(res)
return sorted(results, key=itemgetter('score'), reverse=True) return sorted(results, key=itemgetter('score'), reverse=True)
def search(query, request, selected_engines): def search(query, request, selected_engines):
global engines, categories, number_of_searches global engines, categories, number_of_searches
requests = [] requests = []
@ -160,13 +177,20 @@ def search(query, request, selected_engines):
request_params['started'] = datetime.now() request_params['started'] = datetime.now()
request_params = engine.request(query, request_params) request_params = engine.request(query, request_params)
callback = make_callback(selected_engine['name'], results, suggestions, engine.response, request_params) callback = make_callback(
selected_engine['name'],
results,
suggestions,
engine.response,
request_params
)
request_args = dict(headers = request_params['headers'] request_args = dict(
,hooks = dict(response=callback) headers=request_params['headers'],
,cookies = request_params['cookies'] hooks=dict(response=callback),
,timeout = settings['server']['request_timeout'] cookies=request_params['cookies'],
) timeout=settings['server']['request_timeout']
)
if request_params['method'] == 'GET': if request_params['method'] == 'GET':
req = grequests.get req = grequests.get
@ -180,7 +204,7 @@ def search(query, request, selected_engines):
requests.append(req(request_params['url'], **request_args)) requests.append(req(request_params['url'], **request_args))
grequests.map(requests) grequests.map(requests)
for engine_name,engine_results in results.items(): for engine_name, engine_results in results.items():
engines[engine_name].stats['search_count'] += 1 engines[engine_name].stats['search_count'] += 1
engines[engine_name].stats['result_count'] += len(engine_results) engines[engine_name].stats['result_count'] += len(engine_results)
@ -192,6 +216,7 @@ def search(query, request, selected_engines):
return results, suggestions return results, suggestions
def get_engines_stats(): def get_engines_stats():
# TODO refactor # TODO refactor
pageloads = [] pageloads = []
@ -200,14 +225,15 @@ def get_engines_stats():
errors = [] errors = []
scores_per_result = [] scores_per_result = []
max_pageload = max_results = max_score = max_errors = max_score_per_result = 0 max_pageload = max_results = max_score = max_errors = max_score_per_result = 0 # noqa
for engine in engines.values(): for engine in engines.values():
if engine.stats['search_count'] == 0: if engine.stats['search_count'] == 0:
continue continue
results_num = engine.stats['result_count']/float(engine.stats['search_count']) results_num = \
load_times = engine.stats['page_load_time']/float(engine.stats['search_count']) engine.stats['result_count'] / float(engine.stats['search_count'])
load_times = engine.stats['page_load_time'] / float(engine.stats['search_count']) # noqa
if results_num: if results_num:
score = engine.stats['score_count'] / float(engine.stats['search_count']) score = engine.stats['score_count'] / float(engine.stats['search_count']) # noqa
score_per_result = score / results_num score_per_result = score / results_num
else: else:
score = score_per_result = 0.0 score = score_per_result = 0.0
@ -220,30 +246,48 @@ def get_engines_stats():
results.append({'avg': results_num, 'name': engine.name}) results.append({'avg': results_num, 'name': engine.name})
scores.append({'avg': score, 'name': engine.name}) scores.append({'avg': score, 'name': engine.name})
errors.append({'avg': engine.stats['errors'], 'name': engine.name}) errors.append({'avg': engine.stats['errors'], 'name': engine.name})
scores_per_result.append({'avg': score_per_result, 'name': engine.name}) scores_per_result.append({
'avg': score_per_result,
'name': engine.name
})
for engine in pageloads: for engine in pageloads:
engine['percentage'] = int(engine['avg']/max_pageload*100) engine['percentage'] = int(engine['avg'] / max_pageload * 100)
for engine in results: for engine in results:
engine['percentage'] = int(engine['avg']/max_results*100) engine['percentage'] = int(engine['avg'] / max_results * 100)
for engine in scores: for engine in scores:
engine['percentage'] = int(engine['avg']/max_score*100) engine['percentage'] = int(engine['avg'] / max_score * 100)
for engine in scores_per_result: for engine in scores_per_result:
engine['percentage'] = int(engine['avg']/max_score_per_result*100) engine['percentage'] = int(engine['avg'] / max_score_per_result * 100)
for engine in errors: for engine in errors:
if max_errors: if max_errors:
engine['percentage'] = int(float(engine['avg'])/max_errors*100) engine['percentage'] = int(float(engine['avg']) / max_errors * 100)
else: else:
engine['percentage'] = 0 engine['percentage'] = 0
return [
return [('Page loads (sec)', sorted(pageloads, key=itemgetter('avg'))) (
,('Number of results', sorted(results, key=itemgetter('avg'), reverse=True)) gettext('Page loads (sec)'),
,('Scores', sorted(scores, key=itemgetter('avg'), reverse=True)) sorted(pageloads, key=itemgetter('avg'))
,('Scores per result', sorted(scores_per_result, key=itemgetter('avg'), reverse=True)) ),
,('Errors', sorted(errors, key=itemgetter('avg'), reverse=True)) (
] gettext('Number of results'),
sorted(results, key=itemgetter('avg'), reverse=True)
),
(
gettext('Scores'),
sorted(scores, key=itemgetter('avg'), reverse=True)
),
(
gettext('Scores per result'),
sorted(scores_per_result, key=itemgetter('avg'), reverse=True)
),
(
gettext('Errors'),
sorted(errors, key=itemgetter('avg'), reverse=True)
),
]

View File

@ -4,11 +4,12 @@ from cgi import escape
base_url = 'http://www.bing.com/' base_url = 'http://www.bing.com/'
search_string = 'search?{query}' search_string = 'search?{query}'
locale = 'en-US' # see http://msdn.microsoft.com/en-us/library/dd251064.aspx locale = 'en-US' # see http://msdn.microsoft.com/en-us/library/dd251064.aspx
def request(query, params): def request(query, params):
search_path = search_string.format(query=urlencode({'q': query, 'setmkt': locale})) search_path = search_string.format(
query=urlencode({'q': query, 'setmkt': locale}))
#if params['category'] == 'images': #if params['category'] == 'images':
# params['url'] = base_url + 'images/' + search_path # params['url'] = base_url + 'images/' + search_path
params['url'] = base_url + search_path params['url'] = base_url + search_path

View File

@ -5,7 +5,8 @@ categories = []
url = 'http://finance.yahoo.com/d/quotes.csv?e=.csv&f=sl1d1t1&s={query}=X' url = 'http://finance.yahoo.com/d/quotes.csv?e=.csv&f=sl1d1t1&s={query}=X'
weight = 100 weight = 100
parser_re = re.compile(r'^\W*(\d+(?:\.\d+)?)\W*([a-z]{3})\W*(?:in)?\W*([a-z]{3})\W*$', re.I) parser_re = re.compile(r'^\W*(\d+(?:\.\d+)?)\W*([a-z]{3})\W*(?:in)?\W*([a-z]{3})\W*$', re.I) # noqa
def request(query, params): def request(query, params):
m = parser_re.match(query) m = parser_re.match(query)
@ -19,7 +20,7 @@ def request(query, params):
# wrong params # wrong params
return params return params
q = (from_currency+to_currency).upper() q = (from_currency + to_currency).upper()
params['url'] = url.format(query=q) params['url'] = url.format(query=q)
params['ammount'] = ammount params['ammount'] = ammount
@ -33,25 +34,29 @@ def response(resp):
global base_url global base_url
results = [] results = []
try: try:
_,conversion_rate,_ = resp.text.split(',', 2) _, conversion_rate, _ = resp.text.split(',', 2)
conversion_rate = float(conversion_rate) conversion_rate = float(conversion_rate)
except: except:
return results return results
title = '{0} {1} in {2} is {3}'.format(resp.search_params['ammount'] title = '{0} {1} in {2} is {3}'.format(
,resp.search_params['from'] resp.search_params['ammount'],
,resp.search_params['to'] resp.search_params['from'],
,resp.search_params['ammount']*conversion_rate resp.search_params['to'],
) resp.search_params['ammount'] * conversion_rate
)
content = '1 {0} is {1} {2}'.format(resp.search_params['from'], conversion_rate, resp.search_params['to']) content = '1 {0} is {1} {2}'.format(resp.search_params['from'],
conversion_rate,
resp.search_params['to'])
now_date = datetime.now().strftime('%Y%m%d') now_date = datetime.now().strftime('%Y%m%d')
url = 'http://finance.yahoo.com/currency/converter-results/{0}/{1}-{2}-to-{3}.html' url = 'http://finance.yahoo.com/currency/converter-results/{0}/{1}-{2}-to-{3}.html' # noqa
url = url.format(now_date url = url.format(
,resp.search_params['ammount'] now_date,
,resp.search_params['from'].lower() resp.search_params['ammount'],
,resp.search_params['to'].lower() resp.search_params['from'].lower(),
) resp.search_params['to'].lower()
)
results.append({'title': title, 'content': content, 'url': url}) results.append({'title': title, 'content': content, 'url': url})
return results return results

View File

@ -1,17 +1,21 @@
from urllib import urlencode from urllib import urlencode
from lxml import html from lxml import html
from json import loads from json import loads
from cgi import escape
categories = ['videos'] categories = ['videos']
locale = 'en_US' locale = 'en_US'
# see http://www.dailymotion.com/doc/api/obj-video.html # see http://www.dailymotion.com/doc/api/obj-video.html
search_url = 'https://api.dailymotion.com/videos?fields=title,description,duration,url,thumbnail_360_url&sort=relevance&limit=25&page=1&{query}' search_url = 'https://api.dailymotion.com/videos?fields=title,description,duration,url,thumbnail_360_url&sort=relevance&limit=25&page=1&{query}' # noqa
# TODO use video result template
content_tpl = '<a href="{0}" title="{0}" ><img src="{1}" /></a><br />'
def request(query, params): def request(query, params):
global search_url global search_url
params['url'] = search_url.format(query=urlencode({'search': query, 'localization': locale })) params['url'] = search_url.format(
query=urlencode({'search': query, 'localization': locale}))
return params return params
@ -24,7 +28,7 @@ def response(resp):
title = res['title'] title = res['title']
url = res['url'] url = res['url']
if res['thumbnail_360_url']: if res['thumbnail_360_url']:
content = '<a href="{0}" title="{0}" ><img src="{1}" /></a><br />'.format(url, res['thumbnail_360_url']) content = content_tpl.format(url, res['thumbnail_360_url'])
else: else:
content = '' content = ''
if res['description']: if res['description']:
@ -33,6 +37,7 @@ def response(resp):
results.append({'url': url, 'title': title, 'content': content}) results.append({'url': url, 'title': title, 'content': content})
return results return results
def text_content_from_html(html_string): def text_content_from_html(html_string):
desc_html = html.fragment_fromstring(html_string, create_parent=True) desc_html = html.fragment_fromstring(html_string, create_parent=True)
return desc_html.text_content() return desc_html.text_content()

View File

@ -7,6 +7,7 @@ categories = ['images']
base_url = 'https://www.deviantart.com/' base_url = 'https://www.deviantart.com/'
search_url = base_url+'search?' search_url = base_url+'search?'
def request(query, params): def request(query, params):
global search_url global search_url
params['url'] = search_url + urlencode({'q': query}) params['url'] = search_url + urlencode({'q': query})
@ -22,8 +23,11 @@ def response(resp):
for result in dom.xpath('//div[contains(@class, "tt-a tt-fh")]'): for result in dom.xpath('//div[contains(@class, "tt-a tt-fh")]'):
link = result.xpath('.//a[contains(@class, "thumb")]')[0] link = result.xpath('.//a[contains(@class, "thumb")]')[0]
url = urljoin(base_url, link.attrib.get('href')) url = urljoin(base_url, link.attrib.get('href'))
title_links = result.xpath('.//span[@class="details"]//a[contains(@class, "t")]') title_links = result.xpath('.//span[@class="details"]//a[contains(@class, "t")]') # noqa
title = ''.join(title_links[0].xpath('.//text()')) title = ''.join(title_links[0].xpath('.//text()'))
img_src = link.xpath('.//img')[0].attrib['src'] img_src = link.xpath('.//img')[0].attrib['src']
results.append({'url': url, 'title': title, 'img_src': img_src, 'template': 'images.html'}) results.append({'url': url,
'title': title,
'img_src': img_src,
'template': 'images.html'})
return results return results

View File

@ -6,8 +6,11 @@ url = 'https://duckduckgo.com/'
search_url = url + 'd.js?{query}&p=1&s=0' search_url = url + 'd.js?{query}&p=1&s=0'
locale = 'us-en' locale = 'us-en'
def request(query, params): def request(query, params):
params['url'] = search_url.format(query=urlencode({'q': query, 'l': locale})) q = urlencode({'q': query,
'l': locale})
params['url'] = search_url.format(query=q)
return params return params
@ -17,8 +20,7 @@ def response(resp):
for r in search_res: for r in search_res:
if not r.get('t'): if not r.get('t'):
continue continue
results.append({'title': r['t'] results.append({'title': r['t'],
,'content': html_to_text(r['a']) 'content': html_to_text(r['a']),
,'url': r['u'] 'url': r['u']})
})
return results return results

View File

@ -3,8 +3,9 @@ from urllib import urlencode
url = 'http://api.duckduckgo.com/?{query}&format=json&pretty=0&no_redirect=1' url = 'http://api.duckduckgo.com/?{query}&format=json&pretty=0&no_redirect=1'
def request(query, params): def request(query, params):
params['url'] = url.format(query=urlencode({'q': query})) params['url'] = url.format(query=urlencode({'q': query}))
return params return params
@ -13,11 +14,10 @@ def response(resp):
results = [] results = []
if 'Definition' in search_res: if 'Definition' in search_res:
if search_res.get('AbstractURL'): if search_res.get('AbstractURL'):
res = {'title' : search_res.get('Heading', '') res = {'title': search_res.get('Heading', ''),
,'content' : search_res.get('Definition', '') 'content': search_res.get('Definition', ''),
,'url' : search_res.get('AbstractURL', '') 'url': search_res.get('AbstractURL', ''),
,'class' : 'definition_result' 'class': 'definition_result'}
}
results.append(res) results.append(res)
return results return results

View File

@ -2,7 +2,8 @@ from urllib import urlencode
from HTMLParser import HTMLParser from HTMLParser import HTMLParser
url = 'http://www.filecrop.com/' url = 'http://www.filecrop.com/'
search_url = url + '/search.php?{query}&size_i=0&size_f=100000000&engine_r=1&engine_d=1&engine_e=1&engine_4=1&engine_m=1' search_url = url + '/search.php?{query}&size_i=0&size_f=100000000&engine_r=1&engine_d=1&engine_e=1&engine_4=1&engine_m=1' # noqa
class FilecropResultParser(HTMLParser): class FilecropResultParser(HTMLParser):
def __init__(self): def __init__(self):
@ -18,22 +19,28 @@ class FilecropResultParser(HTMLParser):
def handle_starttag(self, tag, attrs): def handle_starttag(self, tag, attrs):
if tag == 'tr': if tag == 'tr':
if ('bgcolor', '#edeff5') in attrs or ('bgcolor', '#ffffff') in attrs: if ('bgcolor', '#edeff5') in attrs or\
('bgcolor', '#ffffff') in attrs:
self.__start_processing = True self.__start_processing = True
if not self.__start_processing: if not self.__start_processing:
return return
if tag == 'label': if tag == 'label':
self.result['title'] = [attr[1] for attr in attrs if attr[0] == 'title'][0] self.result['title'] = [attr[1] for attr in attrs
elif tag == 'a' and ('rel', 'nofollow') in attrs and ('class', 'sourcelink') in attrs: if attr[0] == 'title'][0]
elif tag == 'a' and ('rel', 'nofollow') in attrs\
and ('class', 'sourcelink') in attrs:
if 'content' in self.result: if 'content' in self.result:
self.result['content'] += [attr[1] for attr in attrs if attr[0] == 'title'][0] self.result['content'] += [attr[1] for attr in attrs
if attr[0] == 'title'][0]
else: else:
self.result['content'] = [attr[1] for attr in attrs if attr[0] == 'title'][0] self.result['content'] = [attr[1] for attr in attrs
if attr[0] == 'title'][0]
self.result['content'] += ' ' self.result['content'] += ' '
elif tag == 'a': elif tag == 'a':
self.result['url'] = url + [attr[1] for attr in attrs if attr[0] == 'href'][0] self.result['url'] = url + [attr[1] for attr in attrs
if attr[0] == 'href'][0]
def handle_endtag(self, tag): def handle_endtag(self, tag):
if self.__start_processing is False: if self.__start_processing is False:
@ -60,10 +67,12 @@ class FilecropResultParser(HTMLParser):
self.data_counter += 1 self.data_counter += 1
def request(query, params): def request(query, params):
params['url'] = search_url.format(query=urlencode({'w' :query})) params['url'] = search_url.format(query=urlencode({'w': query}))
return params return params
def response(resp): def response(resp):
parser = FilecropResultParser() parser = FilecropResultParser()
parser.feed(resp.text) parser.feed(resp.text)

View File

@ -8,21 +8,27 @@ categories = ['images']
url = 'https://secure.flickr.com/' url = 'https://secure.flickr.com/'
search_url = url+'search/?{query}' search_url = url+'search/?{query}'
results_xpath = '//div[@id="thumbnails"]//a[@class="rapidnofollow photo-click" and @data-track="photo-click"]' # noqa
def request(query, params): def request(query, params):
params['url'] = search_url.format(query=urlencode({'q': query})) params['url'] = search_url.format(query=urlencode({'q': query}))
return params return params
def response(resp): def response(resp):
global base_url global base_url
results = [] results = []
dom = html.fromstring(resp.text) dom = html.fromstring(resp.text)
for result in dom.xpath('//div[@id="thumbnails"]//a[@class="rapidnofollow photo-click" and @data-track="photo-click"]'): for result in dom.xpath(results_xpath):
href = urljoin(url, result.attrib.get('href')) href = urljoin(url, result.attrib.get('href'))
img = result.xpath('.//img')[0] img = result.xpath('.//img')[0]
title = img.attrib.get('alt', '') title = img.attrib.get('alt', '')
img_src = img.attrib.get('data-defer-src') img_src = img.attrib.get('data-defer-src')
if not img_src: if not img_src:
continue continue
results.append({'url': href, 'title': title, 'img_src': img_src, 'template': 'images.html'}) results.append({'url': href,
'title': title,
'img_src': img_src,
'template': 'images.html'})
return results return results

View File

@ -4,12 +4,15 @@ from cgi import escape
categories = ['it'] categories = ['it']
search_url = 'https://api.github.com/search/repositories?sort=stars&order=desc&{query}' search_url = 'https://api.github.com/search/repositories?sort=stars&order=desc&{query}' # noqa
accept_header = 'application/vnd.github.preview.text-match+json'
def request(query, params): def request(query, params):
global search_url global search_url
params['url'] = search_url.format(query=urlencode({'q': query})) params['url'] = search_url.format(query=urlencode({'q': query}))
params['headers']['Accept'] = 'application/vnd.github.preview.text-match+json' params['headers']['Accept'] = accept_header
return params return params

View File

@ -6,12 +6,14 @@ from json import loads
categories = ['images'] categories = ['images']
url = 'https://ajax.googleapis.com/' url = 'https://ajax.googleapis.com/'
search_url = url + 'ajax/services/search/images?v=1.0&start=0&rsz=large&safe=off&filter=off&{query}' search_url = url + 'ajax/services/search/images?v=1.0&start=0&rsz=large&safe=off&filter=off&{query}' # noqa
def request(query, params): def request(query, params):
params['url'] = search_url.format(query=urlencode({'q': query})) params['url'] = search_url.format(query=urlencode({'q': query}))
return params return params
def response(resp): def response(resp):
results = [] results = []
search_res = loads(resp.text) search_res = loads(resp.text)
@ -24,5 +26,9 @@ def response(resp):
title = result['title'] title = result['title']
if not result['url']: if not result['url']:
continue continue
results.append({'url': href, 'title': title, 'content': '', 'img_src': result['url'], 'template': 'images.html'}) results.append({'url': href,
'title': title,
'content': '',
'img_src': result['url'],
'template': 'images.html'})
return results return results

View File

@ -2,12 +2,13 @@ from urllib import urlencode
from json import loads from json import loads
from collections import Iterable from collections import Iterable
search_url = None search_url = None
url_query = None url_query = None
content_query = None content_query = None
title_query = None title_query = None
#suggestion_xpath = '' #suggestion_xpath = ''
def iterate(iterable): def iterate(iterable):
if type(iterable) == dict: if type(iterable) == dict:
it = iterable.iteritems() it = iterable.iteritems()
@ -17,11 +18,15 @@ def iterate(iterable):
for index, value in it: for index, value in it:
yield str(index), value yield str(index), value
def is_iterable(obj): def is_iterable(obj):
if type(obj) == str: return False if type(obj) == str:
if type(obj) == unicode: return False return False
if type(obj) == unicode:
return False
return isinstance(obj, Iterable) return isinstance(obj, Iterable)
def parse(query): def parse(query):
q = [] q = []
for part in query.split('/'): for part in query.split('/'):
@ -31,6 +36,7 @@ def parse(query):
q.append(part) q.append(part)
return q return q
def do_query(data, q): def do_query(data, q):
ret = [] ret = []
if not len(q): if not len(q):
@ -38,7 +44,7 @@ def do_query(data, q):
qkey = q[0] qkey = q[0]
for key,value in iterate(data): for key, value in iterate(data):
if len(q) == 1: if len(q) == 1:
if key == qkey: if key == qkey:
@ -54,11 +60,13 @@ def do_query(data, q):
ret.extend(do_query(value, q)) ret.extend(do_query(value, q))
return ret return ret
def query(data, query_string): def query(data, query_string):
q = parse(query_string) q = parse(query_string)
return do_query(data, q) return do_query(data, q)
def request(query, params): def request(query, params):
query = urlencode({'q': query})[2:] query = urlencode({'q': query})[2:]
params['url'] = search_url.format(query=query) params['url'] = search_url.format(query=query)

View File

@ -3,10 +3,12 @@ from urllib import urlencode, quote
url = 'https://en.wikipedia.org/' url = 'https://en.wikipedia.org/'
search_url = url + 'w/api.php?action=query&list=search&{query}&srprop=timestamp&format=json' # noqa
number_of_results = 10 number_of_results = 10
def request(query, params): def request(query, params):
search_url = url + 'w/api.php?action=query&list=search&{query}&srprop=timestamp&format=json'
params['url'] = search_url.format(query=urlencode({'srsearch': query})) params['url'] = search_url.format(query=urlencode({'srsearch': query}))
return params return params
@ -14,7 +16,5 @@ def request(query, params):
def response(resp): def response(resp):
search_results = loads(resp.text) search_results = loads(resp.text)
res = search_results.get('query', {}).get('search', []) res = search_results.get('query', {}).get('search', [])
return [{'url': url + 'wiki/' + quote(result['title'].replace(' ', '_').encode('utf-8')), # noqa
return [{'url': url + 'wiki/' + quote(result['title'].replace(' ', '_').encode('utf-8')),
'title': result['title']} for result in res[:int(number_of_results)]] 'title': result['title']} for result in res[:int(number_of_results)]]

View File

@ -7,13 +7,18 @@ categories = ['videos', 'music']
url = 'https://thepiratebay.se/' url = 'https://thepiratebay.se/'
search_url = url + 'search/{search_term}/0/99/{search_type}' search_url = url + 'search/{search_term}/0/99/{search_type}'
search_types = {'videos': '200' search_types = {'videos': '200',
,'music' : '100' 'music': '100',
,'files' : '0' 'files': '0'}
}
magnet_xpath = './/a[@title="Download this torrent using magnet"]'
content_xpath = './/font[@class="detDesc"]//text()'
def request(query, params): def request(query, params):
params['url'] = search_url.format(search_term=quote(query), search_type=search_types.get(params['category'])) search_type = search_types.get(params['category'])
params['url'] = search_url.format(search_term=quote(query),
search_type=search_type)
return params return params
@ -27,10 +32,14 @@ def response(resp):
link = result.xpath('.//div[@class="detName"]//a')[0] link = result.xpath('.//div[@class="detName"]//a')[0]
href = urljoin(url, link.attrib.get('href')) href = urljoin(url, link.attrib.get('href'))
title = ' '.join(link.xpath('.//text()')) title = ' '.join(link.xpath('.//text()'))
content = escape(' '.join(result.xpath('.//font[@class="detDesc"]//text()'))) content = escape(' '.join(result.xpath(content_xpath)))
seed, leech = result.xpath('.//td[@align="right"]/text()')[:2] seed, leech = result.xpath('.//td[@align="right"]/text()')[:2]
magnetlink = result.xpath('.//a[@title="Download this torrent using magnet"]')[0] magnetlink = result.xpath(magnet_xpath)[0]
results.append({'url': href, 'title': title, 'content': content, results.append({'url': href,
'seed': seed, 'leech': leech, 'magnetlink': magnetlink.attrib['href'], 'title': title,
'content': content,
'seed': seed,
'leech': leech,
'magnetlink': magnetlink.attrib['href'],
'template': 'torrent.html'}) 'template': 'torrent.html'})
return results return results

View File

@ -5,7 +5,8 @@ categories = ['music']
guest_client_id = 'b45b1aa10f1ac2941910a7f0d10f8e28' guest_client_id = 'b45b1aa10f1ac2941910a7f0d10f8e28'
url = 'https://api.soundcloud.com/' url = 'https://api.soundcloud.com/'
search_url = url + 'search?{query}&facet=model&limit=20&offset=0&linked_partitioning=1&client_id='+guest_client_id search_url = url + 'search?{query}&facet=model&limit=20&offset=0&linked_partitioning=1&client_id='+guest_client_id # noqa
def request(query, params): def request(query, params):
global search_url global search_url
@ -21,5 +22,7 @@ def response(resp):
if result['kind'] in ('track', 'playlist'): if result['kind'] in ('track', 'playlist'):
title = result['title'] title = result['title']
content = result['description'] content = result['description']
results.append({'url': result['permalink_url'], 'title': title, 'content': content}) results.append({'url': result['permalink_url'],
'title': title,
'content': content})
return results return results

View File

@ -7,6 +7,8 @@ categories = ['it']
url = 'http://stackoverflow.com/' url = 'http://stackoverflow.com/'
search_url = url+'search?' search_url = url+'search?'
result_xpath = './/div[@class="excerpt"]//text()'
def request(query, params): def request(query, params):
params['url'] = search_url + urlencode({'q': query}) params['url'] = search_url + urlencode({'q': query})
@ -20,6 +22,6 @@ def response(resp):
link = result.xpath('.//div[@class="result-link"]//a')[0] link = result.xpath('.//div[@class="result-link"]//a')[0]
href = urljoin(url, link.attrib.get('href')) href = urljoin(url, link.attrib.get('href'))
title = escape(' '.join(link.xpath('.//text()'))) title = escape(' '.join(link.xpath('.//text()')))
content = escape(' '.join(result.xpath('.//div[@class="excerpt"]//text()'))) content = escape(' '.join(result.xpath(result_xpath)))
results.append({'url': href, 'title': title, 'content': content}) results.append({'url': href, 'title': title, 'content': content})
return results return results

View File

@ -1,11 +1,10 @@
from urllib import urlencode from urllib import urlencode
from lxml import html from lxml import html
from urlparse import urlparse
from cgi import escape
base_url = 'https://startpage.com/' base_url = 'https://startpage.com/'
search_url = base_url+'do/search' search_url = base_url+'do/search'
def request(query, params): def request(query, params):
global search_url global search_url
query = urlencode({'q': query})[2:] query = urlencode({'q': query})[2:]
@ -20,11 +19,10 @@ def response(resp):
results = [] results = []
dom = html.fromstring(resp.content) dom = html.fromstring(resp.content)
# ads xpath //div[@id="results"]/div[@id="sponsored"]//div[@class="result"] # ads xpath //div[@id="results"]/div[@id="sponsored"]//div[@class="result"]
# not ads : div[@class="result"] are the direct childs of div[@id="results"] # not ads: div[@class="result"] are the direct childs of div[@id="results"]
for result in dom.xpath('//div[@id="results"]/div[@class="result"]'): for result in dom.xpath('//div[@id="results"]/div[@class="result"]'):
link = result.xpath('.//h3/a')[0] link = result.xpath('.//h3/a')[0]
url = link.attrib.get('href') url = link.attrib.get('href')
parsed_url = urlparse(url)
title = link.text_content() title = link.text_content()
content = result.xpath('./p[@class="desc"]')[0].text_content() content = result.xpath('./p[@class="desc"]')[0].text_content()
results.append({'url': url, 'title': title, 'content': content}) results.append({'url': url, 'title': title, 'content': content})

View File

@ -7,6 +7,9 @@ categories = ['social media']
base_url = 'https://twitter.com/' base_url = 'https://twitter.com/'
search_url = base_url+'search?' search_url = base_url+'search?'
title_xpath = './/span[@class="username js-action-profile-name"]//text()'
content_xpath = './/p[@class="js-tweet-text tweet-text"]//text()'
def request(query, params): def request(query, params):
global search_url global search_url
@ -21,7 +24,9 @@ def response(resp):
for tweet in dom.xpath('//li[@data-item-type="tweet"]'): for tweet in dom.xpath('//li[@data-item-type="tweet"]'):
link = tweet.xpath('.//small[@class="time"]//a')[0] link = tweet.xpath('.//small[@class="time"]//a')[0]
url = urljoin(base_url, link.attrib.get('href')) url = urljoin(base_url, link.attrib.get('href'))
title = ''.join(tweet.xpath('.//span[@class="username js-action-profile-name"]//text()')) title = ''.join(tweet.xpath(title_xpath))
content = escape(''.join(tweet.xpath('.//p[@class="js-tweet-text tweet-text"]//text()'))) content = escape(''.join(tweet.xpath(content_xpath)))
results.append({'url': url, 'title': title, 'content': content}) results.append({'url': url,
'title': title,
'content': content})
return results return results

View File

@ -5,27 +5,31 @@ from lxml import html
base_url = 'http://vimeo.com' base_url = 'http://vimeo.com'
search_url = base_url + '/search?{query}' search_url = base_url + '/search?{query}'
url_xpath = None url_xpath = None
content_xpath = None content_xpath = None
title_xpath = None title_xpath = None
results_xpath = '' results_xpath = ''
content_tpl = '<a href="{0}"> <img src="{2}"/> </a>'
# the cookie set by vimeo contains all the following values, but only __utma seems to be requiered # the cookie set by vimeo contains all the following values,
# but only __utma seems to be requiered
cookie = { cookie = {
#'vuid':'918282893.1027205400' #'vuid':'918282893.1027205400'
# 'ab_bs':'%7B%223%22%3A279%7D' # 'ab_bs':'%7B%223%22%3A279%7D'
'__utma':'00000000.000#0000000.0000000000.0000000000.0000000000.0' '__utma': '00000000.000#0000000.0000000000.0000000000.0000000000.0'
# '__utmb':'18302654.1.10.1388942090' # '__utmb':'18302654.1.10.1388942090'
#, '__utmc':'18302654' #, '__utmc':'18302654'
#, '__utmz':'18#302654.1388942090.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none)' #, '__utmz':'18#302654.1388942090.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none)' # noqa
#, '__utml':'search' #, '__utml':'search'
} }
def request(query, params): def request(query, params):
params['url'] = search_url.format(query=urlencode({'q' :query})) params['url'] = search_url.format(query=urlencode({'q': query}))
params['cookies'] = cookie params['cookies'] = cookie
return params return params
def response(resp): def response(resp):
results = [] results = []
dom = html.fromstring(resp.text) dom = html.fromstring(resp.text)
@ -36,10 +40,9 @@ def response(resp):
url = base_url + result.xpath(url_xpath)[0] url = base_url + result.xpath(url_xpath)[0]
title = p.unescape(extract_text(result.xpath(title_xpath))) title = p.unescape(extract_text(result.xpath(title_xpath)))
thumbnail = extract_text(result.xpath(content_xpath)[0]) thumbnail = extract_text(result.xpath(content_xpath)[0])
content = '<a href="{0}"> <img src="{2}"/> </a>'.format(url, title, thumbnail) results.append({'url': url,
results.append({'url': url 'title': title,
, 'title': title 'content': content_tpl.format(url, title, thumbnail),
, 'content': content 'template': 'videos.html',
, 'template':'videos.html' 'thumbnail': thumbnail})
, 'thumbnail': thumbnail})
return results return results

View File

@ -1,21 +1,25 @@
from lxml import html from lxml import html
from urllib import urlencode, unquote from urllib import urlencode, unquote
from urlparse import urlparse, urljoin from urlparse import urlparse, urljoin
from cgi import escape
from lxml.etree import _ElementStringResult from lxml.etree import _ElementStringResult
from searx.utils import html_to_text
search_url = None search_url = None
url_xpath = None url_xpath = None
content_xpath = None content_xpath = None
title_xpath = None title_xpath = None
suggestion_xpath = '' suggestion_xpath = ''
results_xpath = '' results_xpath = ''
''' '''
if xpath_results is list, extract the text from each result and concat the list if xpath_results is list, extract the text from each result and concat the list
if xpath_results is a xml element, extract all the text node from it ( text_content() method from lxml ) if xpath_results is a xml element, extract all the text node from it
( text_content() method from lxml )
if xpath_results is a string element, then it's already done if xpath_results is a string element, then it's already done
''' '''
def extract_text(xpath_results): def extract_text(xpath_results):
if type(xpath_results) == list: if type(xpath_results) == list:
# it's list of result : concat everything using recursive call # it's list of result : concat everything using recursive call
@ -30,7 +34,7 @@ def extract_text(xpath_results):
return ''.join(xpath_results) return ''.join(xpath_results)
else: else:
# it's a element # it's a element
return xpath_results.text_content() return html_to_text(xpath_results.text_content())
def extract_url(xpath_results): def extract_url(xpath_results):
@ -60,7 +64,8 @@ def normalize_url(url):
url += '/' url += '/'
# FIXME : hack for yahoo # FIXME : hack for yahoo
if parsed_url.hostname == 'search.yahoo.com' and parsed_url.path.startswith('/r'): if parsed_url.hostname == 'search.yahoo.com'\
and parsed_url.path.startswith('/r'):
p = parsed_url.path p = parsed_url.path
mark = p.find('/**') mark = p.find('/**')
if mark != -1: if mark != -1:
@ -82,15 +87,15 @@ def response(resp):
if results_xpath: if results_xpath:
for result in dom.xpath(results_xpath): for result in dom.xpath(results_xpath):
url = extract_url(result.xpath(url_xpath)) url = extract_url(result.xpath(url_xpath))
title = extract_text(result.xpath(title_xpath)[0 ]) title = extract_text(result.xpath(title_xpath)[0])
content = extract_text(result.xpath(content_xpath)[0]) content = extract_text(result.xpath(content_xpath)[0])
results.append({'url': url, 'title': title, 'content': content}) results.append({'url': url, 'title': title, 'content': content})
else: else:
for url, title, content in zip( for url, title, content in zip(
map(extract_url, dom.xpath(url_xpath)), \ map(extract_url, dom.xpath(url_xpath)),
map(extract_text, dom.xpath(title_xpath)), \ map(extract_text, dom.xpath(title_xpath)),
map(extract_text, dom.xpath(content_xpath)), \ map(extract_text, dom.xpath(content_xpath))
): ):
results.append({'url': url, 'title': title, 'content': content}) results.append({'url': url, 'title': title, 'content': content})
if not suggestion_xpath: if not suggestion_xpath:

View File

@ -4,10 +4,12 @@ from urllib import urlencode
url = 'http://localhost:8090' url = 'http://localhost:8090'
search_url = '/yacysearch.json?{query}&maximumRecords=10' search_url = '/yacysearch.json?{query}&maximumRecords=10'
def request(query, params): def request(query, params):
params['url'] = url + search_url.format(query=urlencode({'query':query})) params['url'] = url + search_url.format(query=urlencode({'query': query}))
return params return params
def response(resp): def response(resp):
raw_search_results = loads(resp.text) raw_search_results = loads(resp.text)
@ -25,7 +27,7 @@ def response(resp):
tmp_result['content'] = '' tmp_result['content'] = ''
if len(result['description']): if len(result['description']):
tmp_result['content'] += result['description'] +"<br/>" tmp_result['content'] += result['description'] + "<br/>"
if len(result['pubDate']): if len(result['pubDate']):
tmp_result['content'] += result['pubDate'] + "<br/>" tmp_result['content'] += result['pubDate'] + "<br/>"

View File

@ -5,6 +5,7 @@ categories = ['videos']
search_url = 'https://gdata.youtube.com/feeds/api/videos?alt=json&{query}' search_url = 'https://gdata.youtube.com/feeds/api/videos?alt=json&{query}'
def request(query, params): def request(query, params):
params['url'] = search_url.format(query=urlencode({'q': query})) params['url'] = search_url.format(query=urlencode({'q': query}))
return params return params
@ -30,17 +31,16 @@ def response(resp):
thumbnail = '' thumbnail = ''
if len(result['media$group']['media$thumbnail']): if len(result['media$group']['media$thumbnail']):
thumbnail = result['media$group']['media$thumbnail'][0]['url'] thumbnail = result['media$group']['media$thumbnail'][0]['url']
content += '<a href="{0}" title="{0}" ><img src="{1}" /></a>'.format(url, thumbnail) content += '<a href="{0}" title="{0}" ><img src="{1}" /></a>'.format(url, thumbnail) # noqa
if len(content): if len(content):
content += '<br />' + result['content']['$t'] content += '<br />' + result['content']['$t']
else: else:
content = result['content']['$t'] content = result['content']['$t']
results.append({'url': url results.append({'url': url,
, 'title': title 'title': title,
, 'content': content 'content': content,
, 'template':'videos.html' 'template': 'videos.html',
, 'thumbnail':thumbnail}) 'thumbnail': thumbnail})
return results return results

View File

@ -105,3 +105,7 @@ engines:
url_xpath : ./a/@href url_xpath : ./a/@href
title_xpath : ./a/div[@class="data"]/p[@class="title"]/text() title_xpath : ./a/div[@class="data"]/p[@class="title"]/text()
content_xpath : ./a/img/@src content_xpath : ./a/img/@src
locales:
en : English
hu : Magyar

View File

@ -1,16 +0,0 @@
port = 11111
secret_key = "ultrasecretkey" # change this!
debug = False
request_timeout = 5.0 # seconds
weights = {} # 'search_engine_name': float(weight) | default is 1.0
blacklist = [] # search engine blacklist
categories = {} # custom search engine categories
base_url = None # "https://your.domain.tld/" or None (to use request parameters)

107
searx/settings_robot.yml Normal file
View File

@ -0,0 +1,107 @@
server:
port : 11111
secret_key : "ultrasecretkey" # change this!
debug : False
request_timeout : 3.0 # seconds
base_url: False
engines:
- name : wikipedia
engine : mediawiki
url : https://en.wikipedia.org/
number_of_results : 1
- name : bing
engine : bing
locale : en-US
- name : currency
engine : currency_convert
categories : general
- name : deviantart
engine : deviantart
categories : images
- name : ddg definitions
engine : duckduckgo_definitions
- name : duckduckgo
engine : duckduckgo
locale : en-us
- name : filecrop
engine : filecrop
categories : files
- name : flickr
engine : flickr
categories : images
- name : github
engine : github
categories : it
- name : google
engine : json_engine
search_url : https://ajax.googleapis.com/ajax/services/search/web?v=2.0&start=0&rsz=large&safe=off&filter=off&q={query}
categories : general
url_query : /responseData/results/unescapedUrl
content_query : /responseData/results/content
title_query : /responseData/results/titleNoFormatting
- name : google images
engine : google_images
categories : images
- name : piratebay
engine : piratebay
categories : videos, music, files
- name : soundcloud
engine : soundcloud
categories : music
- name : stackoverflow
engine : stackoverflow
categories : it
- name : startpage
engine : startpage
- name : twitter
engine : twitter
categories : social media
- name : urbandictionary
engine : xpath
search_url : http://www.urbandictionary.com/define.php?term={query}
url_xpath : //div[@class="word"]//a/@href
title_xpath : //div[@class="word"]//a
content_xpath : //div[@class="definition"]
- name : yahoo
engine : xpath
search_url : http://search.yahoo.com/search?p={query}
results_xpath : //div[@class="res"]
url_xpath : .//h3/a/@href
title_xpath : .//h3/a
content_xpath : .//div[@class="abstr"]
suggestion_xpath : //div[@id="satat"]//a
- name : youtube
engine : youtube
categories : videos
- name : dailymotion
engine : dailymotion
locale : en_US
categories : videos
- name : vimeo
engine : vimeo
categories : videos
results_xpath : //div[@id="browse_content"]/ol/li
url_xpath : ./a/@href
title_xpath : ./a/div[@class="data"]/p[@class="title"]/text()
content_xpath : ./a/img/@src

View File

@ -49,6 +49,8 @@ input[type="submit"] { border: 1px solid #666666; color: #444444; padding: 4px;
input[type="checkbox"] { visibility: hidden; } input[type="checkbox"] { visibility: hidden; }
fieldset { margin: 8px; }
#categories { margin: 0 10px; } #categories { margin: 0 10px; }
.checkbox_container { display: inline-block; position: relative; margin: 0 3px; padding: 0px; } .checkbox_container { display: inline-block; position: relative; margin: 0 3px; padding: 0px; }
@ -79,7 +81,6 @@ a { text-decoration: none; color: #1a11be; }
a:visited { color: #7b11be; } a:visited { color: #7b11be; }
.result { margin: 19px 0 18px 0; padding: 0; max-width: 55em; clear: both; } .result { margin: 19px 0 18px 0; padding: 0; max-width: 55em; clear: both; }
.result:hover { background: #e8e7e6; }
.result_title { margin-bottom: 0; } .result_title { margin-bottom: 0; }
.result h3 { font-size: 1em; word-wrap:break-word; margin: 5px 0 1px 0; padding: 0 } .result h3 { font-size: 1em; word-wrap:break-word; margin: 5px 0 1px 0; padding: 0 }
.result .content { font-size: 0.8em; margin: 0; padding: 0; max-width: 54em; word-wrap:break-word; line-height: 1.24; } .result .content { font-size: 0.8em; margin: 0; padding: 0; max-width: 54em; word-wrap:break-word; line-height: 1.24; }
@ -201,3 +202,5 @@ tr:hover td { background: #DDDDDD; }
.result img { max-width: 90%; width: auto; height: auto } .result img { max-width: 90%; width: auto; height: auto }
} }
.favicon { float: left; margin-right: 4px; }

View File

@ -8,25 +8,25 @@
</p> </p>
<h2>Why use Searx?</h2> <h2>Why use Searx?</h2>
<ul> <ul>
<li>Maybe Searx wont offer you as personalised results as Google, but it doesn't make a profile about you</li> <li>Searx may not offer you as personalised results as Google, but it doesn't generate a profile about you</li>
<li>Searx doesn't care about what you search, never shares anything with a third party, and it can't be used to compromise you</li> <li>Searx doesn't care about what you search for, never shares anything with a third party, and it can't be used to compromise you</li>
<li>Searx is a free software, the code is 100% open and you can help to make it better. See more on <a href="https://gmail.com/asciimoo/searx">github</a></li> <li>Searx is free software, the code is 100% open and you can help to make it better. See more on <a href="https://github.com/asciimoo/searx">github</a></li>
</ul> </ul>
<p>If you do care about privacy, want to be a conscious user, moreover believe <p>If you do care about privacy, want to be a conscious user, or otherwise believe
in digital freedom, make Searx your default search engine or run it on your own server</p> in digital freedom, make Searx your default search engine or run it on your own server</p>
<h2>Technical details - How does it work?</h2> <h2>Technical details - How does it work?</h2>
<p>Searx is a <a href="https://en.wikipedia.org/wiki/Metasearch_engine">metasearch engine</a>, <p>Searx is a <a href="https://en.wikipedia.org/wiki/Metasearch_engine">metasearch engine</a>,
inspired by the <a href="http://seeks-project.info/">seeks project</a>.<br /> inspired by the <a href="http://seeks-project.info/">seeks project</a>.<br />
It provides basic privacy by mixing your queries with searches on other platforms without storing search data. Queries are made using a POST request on every browser (except chrome*). Therefore they don't show up in our logs, neither in your url history. In case of Chrome* users there is an exception, Searx uses the search bar to perform GET requests.<br /> It provides basic privacy by mixing your queries with searches on other platforms without storing search data. Queries are made using a POST request on every browser (except chrome*). Therefore they show up in neither our logs, nor your url history. In case of Chrome* users there is an exception, Searx uses the search bar to perform GET requests.<br />
Searx can be added to your browser's search bar, moreover it can be set as the default search engine. Searx can be added to your browser's search bar; moreover, it can be set as the default search engine.
</p> </p>
<h2>How can I have my own?</h2> <h2>How can I make it my own?</h2>
<p>Searx appreciates your suspicion regarding logs, so take the <a href="https://github.com/asciimoo/searx">code</a> and run it yourself! <br />Add your Searx to this <a href="https://github.com/asciimoo/searx/wiki/Searx-instances">list</a> to help other people to have privacy and make the Internet freer! <p>Searx appreciates your concern regarding logs, so take the <a href="https://github.com/asciimoo/searx">code</a> and run it yourself! <br />Add your Searx to this <a href="https://github.com/asciimoo/searx/wiki/Searx-instances">list</a> to help other people reclaim their privacy and make the Internet freer!
<br />The more decentralized the Internet is the more freedom we have!</p> <br />The more decentralized the Internet, is the more freedom we have!</p>
<hr /> <hr />
@ -39,7 +39,7 @@ Searx can be added to your browser's search bar, moreover it can be set as the d
<h3>New engines?</h3> <h3>New engines?</h3>
<ul> <ul>
<li>Edit your engines.cfg, see <a href="https://raw.github.com/asciimoo/searx/master/engines.cfg_sample">sample config</a></li> <li>Edit your <a href="https://raw.github.com/asciimoo/searx/master/searx/settings.yml">settings.yml</a></li>
<li>Create your custom engine module, check the <a href="https://github.com/asciimoo/searx/blob/master/examples/basic_engine.py">example engine</a></li> <li>Create your custom engine module, check the <a href="https://github.com/asciimoo/searx/blob/master/examples/basic_engine.py">example engine</a></li>
</ul> </ul>
<p>Don't forget to restart searx after config edit!</p> <p>Don't forget to restart searx after config edit!</p>
@ -48,7 +48,7 @@ Searx can be added to your browser's search bar, moreover it can be set as the d
<p>See the <a href="https://github.com/asciimoo/searx/wiki/Installation">installation and setup</a> wiki page</p> <p>See the <a href="https://github.com/asciimoo/searx/wiki/Installation">installation and setup</a> wiki page</p>
<h3>How to debug engines?</h3> <h3>How to debug engines?</h3>
<p><a href="/stats">Stats page</a> contains some useful data about the used engines.</p> <p><a href="/stats">Stats page</a> contains some useful data about the engines used.</p>
</div> </div>
{% endblock %} {% endblock %}

View File

@ -1,7 +1,7 @@
<div id="categories"> <div id="categories">
{% for category in categories %} {% for category in categories %}
<div class="checkbox_container"> <div class="checkbox_container">
<input type="checkbox" id="checkbox_{{ category|replace(' ', '_') }}" name="category_{{ category }}" {% if category in selected_categories %}checked="checked"{% endif %} /><label for="checkbox_{{ category|replace(' ', '_') }}">{{ category }}</label> <input type="checkbox" id="checkbox_{{ category|replace(' ', '_') }}" name="category_{{ category }}" {% if category in selected_categories %}checked="checked"{% endif %} /><label for="checkbox_{{ category|replace(' ', '_') }}">{{ _(category) }}</label>
</div> </div>
{% endfor %} {% endfor %}
</div> </div>

View File

@ -1,12 +1,12 @@
{% extends 'base.html' %} {% extends 'base.html' %}
{% block content %} {% block content %}
<div class="row"> <div class="row">
<h2>Currently used search engines</h2> <h2>{{ _('Currently used search engines') }}</h2>
<table style="width: 80%;"> <table style="width: 80%;">
<tr> <tr>
<th>Engine name</th> <th>{{ _('Engine name') }}</th>
<th>Category</th> <th>{{ _('Category') }}</th>
</tr> </tr>
{% for (categ,search_engines) in categs %} {% for (categ,search_engines) in categs %}
{% for search_engine in search_engines %} {% for search_engine in search_engines %}
@ -20,7 +20,6 @@
{% endfor %} {% endfor %}
{% endfor %} {% endfor %}
</table> </table>
<p>Please add more engines to this list, pull requests are welcome!</p> <p class="right"><a href="/">{{ _('back') }}</a></p>
<p class="right"><a href="/">back</a></p>
</div> </div>
{% endblock %} {% endblock %}

View File

@ -4,8 +4,8 @@
<div class="title"><h1>searx</h1></div> <div class="title"><h1>searx</h1></div>
{% include 'search.html' %} {% include 'search.html' %}
<p class="top_margin"> <p class="top_margin">
<a href="/about" class="hmarg">about</a> <a href="/about" class="hmarg">{{ _('about') }}</a>
<a href="/preferences" class="hmarg">preferences</a> <a href="/preferences" class="hmarg">{{ _('preferences') }}</a>
</p> </p>
</div> </div>
{% endblock %} {% endblock %}

View File

@ -2,18 +2,28 @@
{% block head %} {% endblock %} {% block head %} {% endblock %}
{% block content %} {% block content %}
<div class="row"> <div class="row">
<h2>Preferences</h2> <h2>{{ _('Preferences') }}</h2>
<form method="post" action="/preferences" id="search_form">
<fieldset> <fieldset>
<legend>Default categories</legend> <legend>{{ _('Default categories') }}</legend>
<form method="post" action="/preferences" id="search_form">
<p> <p>
{% include 'categories.html' %} {% include 'categories.html' %}
</p> </p>
<input type="submit" value="save" />
</form>
</fieldset> </fieldset>
<div class="right"><a href="/">back</a></div> <fieldset>
<legend>{{ _('Interface language') }}</legend>
<p>
<select name='locale'>
{% for locale_id,locale_name in locales.items() %}
<option value={{ locale_id }} {% if locale_id == current_locale %}selected="selected"{% endif %}>{{ locale_name}}</option>
{% endfor %}
</select>
</p>
</fieldset>
<input type="submit" value="{{ _('save') }}" />
</form>
<div class="right"><a href="/">{{ _('back') }}</a></div>
</div> </div>
{% endblock %} {% endblock %}

View File

@ -1,13 +1,11 @@
<div class="result {{ result.class }}"> <div class="result {{ result.class }}">
{% if result['favicon'] %} {% if result['favicon'] %}
<div style="float:left; margin:2px;"> <img width="14" height="14" class="favicon" src="static/img/icon_{{result['favicon']}}.ico" />
<img width="18" height="18" src="static/img/icon_{{result['favicon']}}.ico" alt="{{result['favicon']}}.ico" title="{{result['favicon']}}.ico" />
</div>
{% endif %} {% endif %}
<div> <div>
<h3 class="result_title"><a href="{{ result.url }}">{{ result.title|safe }}</a></h3></br> <h3 class="result_title"><a href="{{ result.url }}">{{ result.title|safe }}</a></h3>
<p class="content">{% if result.content %}{{ result.content|safe }}<br />{% endif %}</p> <p class="content">{% if result.content %}{{ result.content|safe }}<br />{% endif %}</p>
<p class="url">{{ result.pretty_url }}</p> <p class="url">{{ result.pretty_url }}</p>
</div> </div>

View File

@ -1,13 +1,11 @@
<div class="result"> <div class="result">
{% if result['favicon'] %} {% if result['favicon'] %}
<div style="float:left; margin:2px;"> <img width="14" height="14" class="favicon" src="static/img/icon_{{result['favicon']}}.ico" />
<img width="18" height="18" src="static/img/icon_{{result['favicon']}}.ico" alt="{{result['favicon']}}.ico" title="{{result['favicon']}}.ico" />
</div>
{% endif %} {% endif %}
<p> <p>
<h3 class="result_title"><a href="{{ result.url }}">{{ result.title|safe }}</a></h3> <h3 class="result_title"><a href="{{ result.url }}">{{ result.title|safe }}</a></h3>
<a href="{{ result.url }}"><img width="300" height="170" src="{{ result.thumbnail }}" title={{ result.title }} alt=" {{ result.title }}"/></a> <a href="{{ result.url }}"><img width="400px" src="{{ result.thumbnail }}" title={{ result.title }} alt=" {{ result.title }}"/></a>
<p class="url">{{ result.url }}</p> <p class="url">{{ result.url }}</p>
</p> </p>
</div> </div>

View File

@ -7,12 +7,12 @@
</div> </div>
<div id="results"> <div id="results">
{% if suggestions %} {% if suggestions %}
<div id="suggestions"><span>Suggestions: </span>{% for suggestion in suggestions %}<form method="post" action="/"><input type="hidden" name="q" value="{{suggestion}}"><input type="submit" value="{{ suggestion }}" /></form>{% endfor %}</div> <div id="suggestions"><span>{{ _('Suggestions') }}:</span>{% for suggestion in suggestions %}<form method="post" action="/"><input type="hidden" name="q" value="{{suggestion}}"><input type="submit" value="{{ suggestion }}" /></form>{% endfor %}</div>
{% endif %} {% endif %}
<div id ="result_count"> <div id ="result_count">
Number of results: {{ number_of_results }} {{ _('Number of results') }}: {{ number_of_results }}
</div> </div>
{% for result in results %} {% for result in results %}
@ -23,7 +23,7 @@
{% endif %} {% endif %}
{% endfor %} {% endfor %}
<div id="apis"> <div id="apis">
Download results {{ _('Download results') }}
<form method="post" action="/"> <form method="post" action="/">
<div class="left"> <div class="left">
<input type="hidden" name="q" value="{{ q }}" /> <input type="hidden" name="q" value="{{ q }}" />

View File

@ -1,7 +1,7 @@
{% extends "base.html" %} {% extends "base.html" %}
{% block head %} {% endblock %} {% block head %} {% endblock %}
{% block content %} {% block content %}
<h2>Engine stats</h2> <h2>{{ _('Engine stats') }}</h2>
{% for stat_name,stat_category in stats %} {% for stat_name,stat_category in stats %}
<div class="left"> <div class="left">

View File

@ -7,10 +7,10 @@ from unittest2 import TestCase
import os import os
import subprocess import subprocess
import sys
class SearxTestLayer: class SearxTestLayer:
"""Base layer for non-robot tests."""
__name__ = u'SearxTestLayer' __name__ = u'SearxTestLayer'
@ -36,24 +36,37 @@ class SearxRobotLayer(Layer):
def setUp(self): def setUp(self):
os.setpgrp() # create new process group, become its leader os.setpgrp() # create new process group, become its leader
# get program paths
webapp = os.path.join( webapp = os.path.join(
os.path.abspath(os.path.dirname(os.path.realpath(__file__))), os.path.abspath(os.path.dirname(os.path.realpath(__file__))),
'webapp.py' 'webapp.py'
) )
exe = os.path.abspath(os.path.dirname(__file__) + '/../bin/py') exe = os.path.abspath(os.path.dirname(__file__) + '/../bin/py')
# set robot settings path
os.environ['SEARX_SETTINGS_PATH'] = os.path.abspath(
os.path.dirname(__file__) + '/settings_robot.yml')
# run the server
self.server = subprocess.Popen( self.server = subprocess.Popen(
[exe, webapp, 'settings_robot'], [exe, webapp],
stdout=subprocess.PIPE, stdout=subprocess.PIPE,
stderr=subprocess.STDOUT stderr=subprocess.STDOUT
) )
def tearDown(self): def tearDown(self):
# TERM all processes in my group # send TERM signal to all processes in my group, to stop subprocesses
os.killpg(os.getpgid(self.server.pid), 15) os.killpg(os.getpgid(self.server.pid), 15)
# remove previously set environment variable
del os.environ['SEARX_SETTINGS_PATH']
SEARXROBOTLAYER = SearxRobotLayer() SEARXROBOTLAYER = SearxRobotLayer()
class SearxTestCase(TestCase): class SearxTestCase(TestCase):
"""Base test case for non-robot tests."""
layer = SearxTestLayer layer = SearxTestLayer

Binary file not shown.

View File

@ -0,0 +1,115 @@
# Hungarian translations for PROJECT.
# Copyright (C) 2014 ORGANIZATION
# This file is distributed under the same license as the PROJECT project.
# FIRST AUTHOR <EMAIL@ADDRESS>, 2014.
#
msgid ""
msgstr ""
"Project-Id-Version: PROJECT VERSION\n"
"Report-Msgid-Bugs-To: EMAIL@ADDRESS\n"
"POT-Creation-Date: 2014-01-22 00:55+0100\n"
"PO-Revision-Date: 2014-01-21 23:33+0100\n"
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
"Language-Team: hu <LL@li.org>\n"
"Plural-Forms: nplurals=1; plural=0\n"
"MIME-Version: 1.0\n"
"Content-Type: text/plain; charset=utf-8\n"
"Content-Transfer-Encoding: 8bit\n"
"Generated-By: Babel 1.3\n"
#: searx/engines/__init__.py:274
msgid "Page loads (sec)"
msgstr "Válaszidők (sec)"
#: searx/engines/__init__.py:278 searx/templates/results.html:15
msgid "Number of results"
msgstr "Találatok száma"
#: searx/engines/__init__.py:282
msgid "Scores"
msgstr "Pontszámok"
#: searx/engines/__init__.py:286
msgid "Scores per result"
msgstr "Pontszámok találatonként"
#: searx/engines/__init__.py:290
msgid "Errors"
msgstr "Hibák"
#: searx/templates/engines.html:4
msgid "Currently used search engines"
msgstr "Jelenleg használt keresők"
#: searx/templates/engines.html:8
msgid "Engine name"
msgstr "Kereső neve"
#: searx/templates/engines.html:9
msgid "Category"
msgstr "Kategória"
#: searx/templates/engines.html:23 searx/templates/preferences.html:27
msgid "back"
msgstr "vissza"
#: searx/templates/index.html:7
msgid "about"
msgstr "rólunk"
#: searx/templates/index.html:8
msgid "preferences"
msgstr "beállítások"
#: searx/templates/preferences.html:5
msgid "Preferences"
msgstr "Beállítások"
#: searx/templates/preferences.html:10
msgid "Default categories"
msgstr "Alapértelmezett kategóriák"
#: searx/templates/preferences.html:16
msgid "Interface language"
msgstr "Nyelv"
#: searx/templates/preferences.html:25
msgid "save"
msgstr "mentés"
#: searx/templates/results.html:10
msgid "Suggestions"
msgstr "Javaslatok"
#: searx/templates/results.html:26
msgid "Download results"
msgstr "Találatok letöltése"
#: searx/templates/stats.html:4
msgid "Engine stats"
msgstr "Kereső statisztikák"
# categories - manually added
# TODO - automatically add
msgid "files"
msgstr "fájlok"
msgid "general"
msgstr "általános"
msgid "music"
msgstr "zene"
msgid "social media"
msgstr "közösségi média"
msgid "images"
msgstr "képek"
msgid "videos"
msgstr "videók"
msgid "it"
msgstr "it"

View File

@ -1,13 +1,16 @@
from HTMLParser import HTMLParser from HTMLParser import HTMLParser
#import htmlentitydefs #import htmlentitydefs
import csv import csv
import codecs from codecs import getincrementalencoder
import cStringIO import cStringIO
import re import re
def gen_useragent(): def gen_useragent():
# TODO # TODO
return "Mozilla/5.0 (X11; Linux x86_64; rv:26.0) Gecko/20100101 Firefox/26.0" ua = "Mozilla/5.0 (X11; Linux x86_64; rv:26.0) Gecko/20100101 Firefox/26.0"
return ua
def highlight_content(content, query): def highlight_content(content, query):
@ -34,16 +37,20 @@ def highlight_content(content, query):
return content return content
class HTMLTextExtractor(HTMLParser): class HTMLTextExtractor(HTMLParser):
def __init__(self): def __init__(self):
HTMLParser.__init__(self) HTMLParser.__init__(self)
self.result = [ ] self.result = []
def handle_data(self, d): def handle_data(self, d):
self.result.append(d) self.result.append(d)
def handle_charref(self, number): def handle_charref(self, number):
codepoint = int(number[1:], 16) if number[0] in (u'x', u'X') else int(number) if number[0] in (u'x', u'X'):
codepoint = int(number[1:], 16)
else:
codepoint = int(number)
self.result.append(unichr(codepoint)) self.result.append(unichr(codepoint))
def handle_entityref(self, name): def handle_entityref(self, name):
@ -54,6 +61,7 @@ class HTMLTextExtractor(HTMLParser):
def get_text(self): def get_text(self):
return u''.join(self.result) return u''.join(self.result)
def html_to_text(html): def html_to_text(html):
s = HTMLTextExtractor() s = HTMLTextExtractor()
s.feed(html) s.feed(html)
@ -71,10 +79,16 @@ class UnicodeWriter:
self.queue = cStringIO.StringIO() self.queue = cStringIO.StringIO()
self.writer = csv.writer(self.queue, dialect=dialect, **kwds) self.writer = csv.writer(self.queue, dialect=dialect, **kwds)
self.stream = f self.stream = f
self.encoder = codecs.getincrementalencoder(encoding)() self.encoder = getincrementalencoder(encoding)()
def writerow(self, row): def writerow(self, row):
self.writer.writerow([(s.encode("utf-8").strip() if type(s) == str or type(s) == unicode else str(s)) for s in row]) unicode_row = []
for col in row:
if type(col) == str or type(col) == unicode:
unicode_row.append(col.encode('utf-8').strip())
else:
unicode_row.append(col)
self.writer.writerow(unicode_row)
# Fetch UTF-8 output from the queue ... # Fetch UTF-8 output from the queue ...
data = self.queue.getvalue() data = self.queue.getvalue()
data = data.decode("utf-8") data = data.decode("utf-8")

View File

@ -17,26 +17,36 @@ along with searx. If not, see < http://www.gnu.org/licenses/ >.
(C) 2013- by Adam Tauber, <asciimoo@gmail.com> (C) 2013- by Adam Tauber, <asciimoo@gmail.com>
''' '''
import os
import sys
if __name__ == "__main__":
sys.path.append(os.path.realpath(os.path.dirname(os.path.realpath(__file__))+'/../'))
from searx import settings
from flask import Flask, request, render_template, url_for, Response, make_response, redirect
from searx.engines import search, categories, engines, get_engines_stats
import json import json
import cStringIO import cStringIO
from searx.utils import UnicodeWriter 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 flask import send_from_directory
from searx import settings
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.utils import highlight_content, html_to_text
from flask.ext.babel import Babel
app = Flask(__name__) app = Flask(
__name__,
static_folder=os.path.join(os.path.dirname(__file__), 'static'),
template_folder=os.path.join(os.path.dirname(__file__), 'templates')
)
app.secret_key = settings['server']['secret_key'] app.secret_key = settings['server']['secret_key']
babel = Babel(app)
#TODO configurable via settings.yml
favicons = ['wikipedia', 'youtube', 'vimeo', 'soundcloud',
'twitter', 'stackoverflow', 'github']
opensearch_xml = '''<?xml version="1.0" encoding="utf-8"?> opensearch_xml = '''<?xml version="1.0" encoding="utf-8"?>
<OpenSearchDescription xmlns="http://a9.com/-/spec/opensearch/1.1/"> <OpenSearchDescription xmlns="http://a9.com/-/spec/opensearch/1.1/">
@ -51,6 +61,24 @@ opensearch_xml = '''<?xml version="1.0" encoding="utf-8"?>
''' '''
@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(): def get_base_url():
if settings['server']['base_url']: if settings['server']['base_url']:
hostname = settings['server']['base_url'] hostname = settings['server']['base_url']
@ -65,7 +93,8 @@ def get_base_url():
def render(template_name, **kwargs): def render(template_name, **kwargs):
global categories global categories
kwargs['categories'] = ['general'] kwargs['categories'] = ['general']
kwargs['categories'].extend(x for x in sorted(categories.keys()) if x != 'general') kwargs['categories'].extend(x for x in
sorted(categories.keys()) if x != 'general')
if not 'selected_categories' in kwargs: if not 'selected_categories' in kwargs:
kwargs['selected_categories'] = [] kwargs['selected_categories'] = []
cookie_categories = request.cookies.get('categories', '').split(',') cookie_categories = request.cookies.get('categories', '').split(',')
@ -76,6 +105,7 @@ def render(template_name, **kwargs):
kwargs['selected_categories'] = ['general'] kwargs['selected_categories'] = ['general']
return render_template(template_name, **kwargs) return render_template(template_name, **kwargs)
def parse_query(query): def parse_query(query):
query_engines = [] query_engines = []
query_parts = query.split() query_parts = query.split()
@ -89,7 +119,7 @@ def parse_query(query):
def index(): def index():
global categories global categories
if request.method=='POST': if request.method == 'POST':
request_data = request.form request_data = request.form
else: else:
request_data = request.args request_data = request.args
@ -101,14 +131,15 @@ def index():
query, selected_engines = parse_query(request_data['q'].encode('utf-8')) query, selected_engines = parse_query(request_data['q'].encode('utf-8'))
if not len(selected_engines): if not len(selected_engines):
for pd_name,pd in request_data.items(): for pd_name, pd in request_data.items():
if pd_name.startswith('category_'): if pd_name.startswith('category_'):
category = pd_name[9:] category = pd_name[9:]
if not category in categories: if not category in categories:
continue continue
selected_categories.append(category) selected_categories.append(category)
if not len(selected_categories): if not len(selected_categories):
cookie_categories = request.cookies.get('categories', '').split(',') cookie_categories = request.cookies.get('categories', '')
cookie_categories = cookie_categories.split(',')
for ccateg in cookie_categories: for ccateg in cookie_categories:
if ccateg in categories: if ccateg in categories:
selected_categories.append(ccateg) selected_categories.append(ccateg)
@ -116,7 +147,9 @@ def index():
selected_categories = ['general'] selected_categories = ['general']
for categ in selected_categories: for categ in selected_categories:
selected_engines.extend({'category': categ, 'name': x.name} for x in categories[categ]) selected_engines.extend({'category': categ,
'name': x.name}
for x in categories[categ])
results, suggestions = search(query, request, selected_engines) results, suggestions = search(query, request, selected_engines)
@ -131,16 +164,18 @@ def index():
result['content'] = html_to_text(result['content']).strip() result['content'] = html_to_text(result['content']).strip()
result['title'] = html_to_text(result['title']).strip() result['title'] = html_to_text(result['title']).strip()
if len(result['url']) > 74: if len(result['url']) > 74:
result['pretty_url'] = result['url'][:35] + '[..]' + result['url'][-35:] url_parts = result['url'][:35], result['url'][-35:]
result['pretty_url'] = '{0}[...]{1}'.format(*url_parts)
else: else:
result['pretty_url'] = result['url'] result['pretty_url'] = result['url']
for engine in result['engines']: for engine in result['engines']:
if engine in ['wikipedia', 'youtube', 'vimeo', 'soundcloud', 'twitter', 'stackoverflow', 'github']: if engine in favicons:
result['favicon'] = engine result['favicon'] = engine
if request_data.get('format') == 'json': if request_data.get('format') == 'json':
return Response(json.dumps({'query': query, 'results': results}), mimetype='application/json') return Response(json.dumps({'query': query, 'results': results}),
mimetype='application/json')
elif request_data.get('format') == 'csv': elif request_data.get('format') == 'csv':
csv = UnicodeWriter(cStringIO.StringIO()) csv = UnicodeWriter(cStringIO.StringIO())
keys = ('title', 'url', 'content', 'host', 'engine', 'score') keys = ('title', 'url', 'content', 'host', 'engine', 'score')
@ -151,26 +186,28 @@ def index():
csv.writerow([row.get(key, '') for key in keys]) csv.writerow([row.get(key, '') for key in keys])
csv.stream.seek(0) csv.stream.seek(0)
response = Response(csv.stream.read(), mimetype='application/csv') response = Response(csv.stream.read(), mimetype='application/csv')
response.headers.add('Content-Disposition', 'attachment;Filename=searx_-_{0}.csv'.format('_'.join(query.split()))) content_disp = 'attachment;Filename=searx_-_{0}.csv'.format(query)
response.headers.add('Content-Disposition', content_disp)
return response return response
elif request_data.get('format') == 'rss': elif request_data.get('format') == 'rss':
response_rss = render('opensearch_response_rss.xml' response_rss = render(
,results=results 'opensearch_response_rss.xml',
,q=request_data['q'] results=results,
,number_of_results=len(results) q=request_data['q'],
,base_url=get_base_url() number_of_results=len(results),
) base_url=get_base_url()
)
return Response(response_rss, mimetype='text/xml') return Response(response_rss, mimetype='text/xml')
return render(
return render('results.html' 'results.html',
,results=results results=results,
,q=request_data['q'] q=request_data['q'],
,selected_categories=selected_categories selected_categories=selected_categories,
,number_of_results=len(results)+len(featured_results) number_of_results=len(results) + len(featured_results),
,featured_results=featured_results featured_results=featured_results,
,suggestions=suggestions suggestions=suggestions
) )
@app.route('/about', methods=['GET']) @app.route('/about', methods=['GET'])
@ -187,20 +224,37 @@ def list_engines():
@app.route('/preferences', methods=['GET', 'POST']) @app.route('/preferences', methods=['GET', 'POST'])
def preferences(): def preferences():
if request.method=='POST': if request.method == 'POST':
selected_categories = [] selected_categories = []
for pd_name,pd in request.form.items(): locale = None
for pd_name, pd in request.form.items():
if pd_name.startswith('category_'): if pd_name.startswith('category_'):
category = pd_name[9:] category = pd_name[9:]
if not category in categories: if not category in categories:
continue continue
selected_categories.append(category) selected_categories.append(category)
if selected_categories: elif pd_name == 'locale' and pd in settings['locales']:
resp = make_response(redirect('/')) locale = pd
resp = make_response(redirect('/'))
if locale:
# cookie max age: 4 weeks # cookie max age: 4 weeks
resp.set_cookie('categories', ','.join(selected_categories), max_age=60*60*24*7*4) resp.set_cookie(
return resp 'locale', locale,
return render('preferences.html') 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())
@app.route('/stats', methods=['GET']) @app.route('/stats', methods=['GET'])
@ -216,6 +270,7 @@ def robots():
Allow: / Allow: /
Allow: /about Allow: /about
Disallow: /stats Disallow: /stats
Disallow: /engines
""", mimetype='text/plain') """, mimetype='text/plain')
@ -229,24 +284,27 @@ def opensearch():
base_url = get_base_url() base_url = get_base_url()
ret = opensearch_xml.format(method=method, host=base_url) ret = opensearch_xml.format(method=method, host=base_url)
resp = Response(response=ret, resp = Response(response=ret,
status=200, status=200,
mimetype="application/xml") mimetype="application/xml")
return resp return resp
@app.route('/favicon.ico') @app.route('/favicon.ico')
def favicon(): def favicon():
return send_from_directory(os.path.join(app.root_path, 'static/img'), return send_from_directory(os.path.join(app.root_path, 'static/img'),
'favicon.png', mimetype='image/vnd.microsoft.icon') 'favicon.png',
mimetype='image/vnd.microsoft.icon')
def run(): def run():
from gevent import monkey from gevent import monkey
monkey.patch_all() monkey.patch_all()
app.run(debug = settings['server']['debug'] app.run(
,use_debugger = settings['server']['debug'] debug=settings['server']['debug'],
,port = settings['server']['port'] use_debugger=settings['server']['debug'],
) port=settings['server']['port']
)
if __name__ == "__main__": if __name__ == "__main__":

View File

@ -11,12 +11,12 @@ def read(*rnames):
return open(os.path.join(os.path.dirname(__file__), *rnames)).read() return open(os.path.join(os.path.dirname(__file__), *rnames)).read()
long_description = read('README.md') long_description = read('README.rst')
setup( setup(
name='searx', name='searx',
version="0.1", version="0.1.2",
description="", description="A privacy-respecting, hackable metasearch engine",
long_description=long_description, long_description=long_description,
classifiers=[ classifiers=[
"Programming Language :: Python", "Programming Language :: Python",
@ -30,6 +30,7 @@ setup(
zip_safe=False, zip_safe=False,
install_requires=[ install_requires=[
'flask', 'flask',
'flask-babel',
'grequests', 'grequests',
'lxml', 'lxml',
'pyyaml', 'pyyaml',
@ -49,4 +50,20 @@ setup(
'zope.testrunner', 'zope.testrunner',
] ]
}, },
entry_points={
'console_scripts': [
'searx-run = searx.webapp:run'
]
},
package_data={
'searx': [
'settings.yml',
'../README.rst',
'static/*/*',
'translations/*/*',
'templates/*.html',
'templates/result_templates/*.html',
],
},
) )

View File

@ -1,5 +1,6 @@
[versions] [versions]
Flask = 0.10.1 Flask = 0.10.1
Flask-Babel = 0.9
Jinja2 = 2.7.2 Jinja2 = 2.7.2
MarkupSafe = 0.18 MarkupSafe = 0.18
WebOb = 1.3.1 WebOb = 1.3.1