free
/
searx_ynh
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

update version 0.8

This commit is contained in:
Beudbeud 2015-09-08 23:05:37 +02:00
parent f03a6c556f
commit a1618d9d20
243 changed files with 17255 additions and 2643 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

111
conf/settings.yml
View File

@ -1,16 +1,37 @@
general:
debug : False # Debug mode, only for development
search:
safe_search : 0 # Filter results. 0: None, 1: Moderate, 2: Strict
autocomplete : "duckduckgo" # Existing autocomplete backends: "dbpedia", "duckduckgo", "google", "startpage", "wikipedia" - leave blank to turn it off by default
server: server:
port : 8888 port : 8888
bind_address : "127.0.0.1" # address to listen on
secret_key : "ultrasecretkey" # change this! secret_key : "ultrasecretkey" # change this!
debug : False # Debug mode, only for development
request_timeout : 2.0 # seconds
base_url : ynhbaseurl # Set custom base_url. Possible values: False or "https://your.custom.host/location/" base_url : ynhbaseurl # Set custom base_url. Possible values: False or "https://your.custom.host/location/"
image_proxy : False # Proxying image results through searx
ui:
themes_path : "" # Custom ui themes path - leave it blank if you didn't change themes_path : "" # Custom ui themes path - leave it blank if you didn't change
default_theme : oscar # ui theme default_theme : oscar # ui theme
https_rewrite : True # Force rewrite result urls. See searx/https_rewrite.py
useragent_suffix : "" # suffix of searx_useragent, could contain informations like an email address to the administrator
image_proxy : False # Proxying image results through searx
default_locale : "" # Default interface locale - leave blank to detect from browser information or use codes from the 'locales' config section default_locale : "" # Default interface locale - leave blank to detect from browser information or use codes from the 'locales' config section
outgoing: # communication with search engines
request_timeout : 2.0 # seconds
useragent_suffix : "" # suffix of searx_useragent, could contain informations like an email address to the administrator
# uncomment below section if you want to use a proxy
# see http://docs.python-requests.org/en/latest/user/advanced/#proxies
# SOCKS proxies are not supported : see https://github.com/kennethreitz/requests/pull/478
# proxies :
# http : http://127.0.0.1:8080
# https: http://127.0.0.1:8080
# uncomment below section only if you have more than one network interface
# which can be the source of outgoing search requests
# source_ips:
# - 1.1.1.1
# - 1.1.1.2
engines: engines:
- name : wikipedia - name : wikipedia
engine : mediawiki engine : mediawiki
@ -20,17 +41,14 @@ engines:
- name : bing - name : bing
engine : bing engine : bing
locale : en-US
shortcut : bi shortcut : bi
- name : bing images - name : bing images
engine : bing_images engine : bing_images
locale : en-US
shortcut : bii shortcut : bii
- name : bing news - name : bing news
engine : bing_news engine : bing_news
locale : en-US
shortcut : bin shortcut : bin
- name : btdigg - name : btdigg
@ -73,12 +91,6 @@ engines:
# shortcut : fa # shortcut : fa
# api_key : 'apikey' # required! # api_key : 'apikey' # required!
# down - website is under criminal investigation by the UK
# - name : filecrop
# engine : filecrop
# categories : files
# shortcut : fc
- name : 500px - name : 500px
engine : www500px engine : www500px
shortcut : px shortcut : px
@ -98,10 +110,10 @@ engines:
# Or you can use the html non-stable engine, activated by default # Or you can use the html non-stable engine, activated by default
engine : flickr_noapi engine : flickr_noapi
- name : general-file - name : gigablast
engine : generalfile engine : gigablast
shortcut : gf shortcut : gb
disabled : True disabled: True
- name : github - name : github
engine : github engine : github
@ -164,6 +176,28 @@ engines:
- name : piratebay - name : piratebay
engine : piratebay engine : piratebay
shortcut : tpb shortcut : tpb
disabled : True
- name : qwant
engine : qwant
shortcut : qw
categories : general
disabled : True
- name : qwant images
engine : qwant
shortcut : qwi
categories : images
- name : qwant news
engine : qwant
shortcut : qwn
categories : news
- name : qwant social
engine : qwant
shortcut : qws
categories : social media
- name : kickass - name : kickass
engine : kickass engine : kickass
@ -186,6 +220,10 @@ engines:
shortcut : scc shortcut : scc
disabled : True disabled : True
- name : spotify
engine : spotify
shortcut : stf
- name : subtitleseeker - name : subtitleseeker
engine : subtitleseeker engine : subtitleseeker
shortcut : ss shortcut : ss
@ -196,12 +234,21 @@ engines:
- name : startpage - name : startpage
engine : startpage engine : startpage
shortcut : sp shortcut : sp
timeout : 6.0
disabled : True
# +30% page load time - name : ixquick
# - name : ixquick engine : startpage
# engine : startpage base_url : 'https://www.ixquick.com/'
# base_url : 'https://www.ixquick.com/' search_url : 'https://www.ixquick.com/do/search'
# search_url : 'https://www.ixquick.com/do/search' shortcut : iq
timeout : 6.0
disabled : True
- name : swisscows
engine : swisscows
shortcut : sw
disabled : True
- name : twitter - name : twitter
engine : twitter engine : twitter
@ -232,8 +279,13 @@ engines:
shortcut : yhn shortcut : yhn
- name : youtube - name : youtube
engine : youtube
shortcut : yt shortcut : yt
# You can use the engine using the official stable API, but you need an API key
# See : https://console.developers.google.com/project
# engine : youtube_api
# api_key: 'apikey' # required!
# Or you can use the html non-stable engine, activated by default
engine : youtube_noapi
- name : dailymotion - name : dailymotion
engine : dailymotion engine : dailymotion
@ -241,9 +293,14 @@ engines:
- name : vimeo - name : vimeo
engine : vimeo engine : vimeo
locale : en-US
shortcut : vm shortcut : vm
#The blekko technology and team have joined IBM Watson! -> https://blekko.com/
# - name : blekko images
# engine : blekko_images
# locale : en-US
# shortcut : bli
# - name : yacy # - name : yacy
# engine : yacy # engine : yacy
# shortcut : ya # shortcut : ya
@ -254,6 +311,7 @@ engines:
locales: locales:
en : English en : English
de : Deutsch de : Deutsch
he : Hebrew
hu : Magyar hu : Magyar
fr : Français fr : Français
es : Español es : Español
@ -261,4 +319,7 @@ locales:
nl : Nederlands nl : Nederlands
ja : 日本語 (Japanese) ja : 日本語 (Japanese)
tr : Türkçe tr : Türkçe
pt : Português
ru : Russian ru : Russian
ro : Romanian
zh : 中文 (Chinese)

8
sources/AUTHORS.rst
View File

@ -1,11 +1,11 @@
Searx was created and is maintained by Adam Tauber. Searx was created by Adam Tauber and is maintained by Adam Tauber and Alexandre Flament.
Major contributing authors: Major contributing authors:
- Adam Tauber <asciimoo@gmail.com> `@asciimoo <https://github.com/asciimoo>`_ - Adam Tauber <asciimoo@gmail.com> `@asciimoo <https://github.com/asciimoo>`_
- Matej Cotman - Matej Cotman
- Thomas Pointhuber - Thomas Pointhuber
- Alexandre Flament - Alexandre Flament `@dalf <https://github.com/dalf>`_
- @Cqoicebordel - @Cqoicebordel
People who have submitted patches/translates, reported bugs, consulted features or People who have submitted patches/translates, reported bugs, consulted features or
@ -34,3 +34,7 @@ generally made searx better:
- @opi - @opi
- @dimqua - @dimqua
- Giorgos Logiotatidis - Giorgos Logiotatidis
- Luc Didry
- Niklas Haas
- @underr
- Emmanuel Benazera

46
sources/CHANGELOG.rst
View File

@ -1,3 +1,49 @@
0.8.0 2015.09.08
================
- New engines
- Blekko (image)
- Gigablast (general)
- Spotify (music)
- Swisscows (general, images)
- Qwant (general, images, news, social media)
- Plugin system
- New plugins
- HTTPS rewrite
- Search on cagetory select
- User information
- Tracker url part remover
- Multiple outgoing IP and HTTP/HTTPS proxy support
- New autocompleter: startpage
- New theme: pix-art
- Settings file structure change
- Fabfile, docker deployment
- Optional safesearch result filter
- Force HTTPS in engines if possible
- Disabled HTTP referrer on outgoing links
- Display cookie information
- Prettier search URLs
- Right-to-left text handling in themes
- Translation updates (New locales: Chinese, Hebrew, Portuguese, Romanian)
New dependencies
~~~~~~~~~~~~~~~~
- pyopenssl
- ndg-httpsclient
- pyasn1
- pyasn1-modules
- certifi
News
~~~~
@dalf joined the maintainer "team"
0.7.0 2015.02.03 0.7.0 2015.02.03
================ ================

27
sources/Dockerfile
View File

@ -1,21 +1,22 @@
FROM debian:stable FROM python:2.7-slim
RUN apt-get update && \ WORKDIR /app
apt-get install -y --no-install-recommends \
python-dev python2.7-minimal python-virtualenv \
python-pybabel python-pip zlib1g-dev \
libxml2-dev libxslt1-dev build-essential \
openssl
RUN useradd searx RUN useradd searx
WORKDIR /app EXPOSE 5000
RUN pip install uwsgi CMD ["/usr/local/bin/uwsgi", "--uid", "searx", "--gid", "searx", "--http", ":5000", "-w", "searx.webapp"]
RUN apt-get update && \
apt-get install -y --no-install-recommends \
zlib1g-dev libxml2-dev libxslt1-dev libffi-dev build-essential \
libssl-dev openssl && \
rm -rf /var/lib/apt/lists/*
RUN pip install --no-cache uwsgi
COPY requirements.txt /app/requirements.txt COPY requirements.txt /app/requirements.txt
RUN pip install -r requirements.txt RUN pip install --no-cache -r requirements.txt
COPY . /app COPY . /app
RUN sed -i -e "s/ultrasecretkey/`openssl rand -hex 16`/g" searx/settings.yml RUN sed -i -e "s/ultrasecretkey/`openssl rand -hex 16`/g" searx/settings.yml
EXPOSE 5000
CMD ["/usr/local/bin/uwsgi", "--uid", "searx", "--gid", "searx", "--http", ":5000", "-w", "searx.webapp"]

669
sources/LICENSE
View File

@ -1,14 +1,661 @@
searx is free software: you can redistribute it and/or modify GNU AFFERO GENERAL PUBLIC LICENSE
it under the terms of the GNU Affero General Public License as published by Version 3, 19 November 2007
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, Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>
but WITHOUT ANY WARRANTY; without even the implied warranty of Everyone is permitted to copy and distribute verbatim copies
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the of this license document, but changing it is not allowed.
GNU Affero General Public License for more details.
You should have received a copy of the GNU Affero General Public License Preamble
along with searx. If not, see < http://www.gnu.org/licenses/ >.
(C) 2013- by Adam Tauber, <asciimoo@gmail.com> The GNU Affero General Public License is a free, copyleft license for
software and other kinds of works, specifically designed to ensure
cooperation with the community in the case of network server software.
The licenses for most software and other practical works are designed
to take away your freedom to share and change the works. By contrast,
our General Public Licenses are intended to guarantee your freedom to
share and change all versions of a program--to make sure it remains free
software for all its users.
When we speak of free software, we are referring to freedom, not
price. Our General Public Licenses are designed to make sure that you
have the freedom to distribute copies of free software (and charge for
them if you wish), that you receive source code or can get it if you
want it, that you can change the software or use pieces of it in new
free programs, and that you know you can do these things.
Developers that use our General Public Licenses protect your rights
with two steps: (1) assert copyright on the software, and (2) offer
you this License which gives you legal permission to copy, distribute
and/or modify the software.
A secondary benefit of defending all users' freedom is that
improvements made in alternate versions of the program, if they
receive widespread use, become available for other developers to
incorporate. Many developers of free software are heartened and
encouraged by the resulting cooperation. However, in the case of
software used on network servers, this result may fail to come about.
The GNU General Public License permits making a modified version and
letting the public access it on a server without ever releasing its
source code to the public.
The GNU Affero General Public License is designed specifically to
ensure that, in such cases, the modified source code becomes available
to the community. It requires the operator of a network server to
provide the source code of the modified version running there to the
users of that server. Therefore, public use of a modified version, on
a publicly accessible server, gives the public access to the source
code of the modified version.
An older license, called the Affero General Public License and
published by Affero, was designed to accomplish similar goals. This is
a different license, not a version of the Affero GPL, but Affero has
released a new version of the Affero GPL which permits relicensing under
this license.
The precise terms and conditions for copying, distribution and
modification follow.
TERMS AND CONDITIONS
0. Definitions.
"This License" refers to version 3 of the GNU Affero General Public License.
"Copyright" also means copyright-like laws that apply to other kinds of
works, such as semiconductor masks.
"The Program" refers to any copyrightable work licensed under this
License. Each licensee is addressed as "you". "Licensees" and
"recipients" may be individuals or organizations.
To "modify" a work means to copy from or adapt all or part of the work
in a fashion requiring copyright permission, other than the making of an
exact copy. The resulting work is called a "modified version" of the
earlier work or a work "based on" the earlier work.
A "covered work" means either the unmodified Program or a work based
on the Program.
To "propagate" a work means to do anything with it that, without
permission, would make you directly or secondarily liable for
infringement under applicable copyright law, except executing it on a
computer or modifying a private copy. Propagation includes copying,
distribution (with or without modification), making available to the
public, and in some countries other activities as well.
To "convey" a work means any kind of propagation that enables other
parties to make or receive copies. Mere interaction with a user through
a computer network, with no transfer of a copy, is not conveying.
An interactive user interface displays "Appropriate Legal Notices"
to the extent that it includes a convenient and prominently visible
feature that (1) displays an appropriate copyright notice, and (2)
tells the user that there is no warranty for the work (except to the
extent that warranties are provided), that licensees may convey the
work under this License, and how to view a copy of this License. If
the interface presents a list of user commands or options, such as a
menu, a prominent item in the list meets this criterion.
1. Source Code.
The "source code" for a work means the preferred form of the work
for making modifications to it. "Object code" means any non-source
form of a work.
A "Standard Interface" means an interface that either is an official
standard defined by a recognized standards body, or, in the case of
interfaces specified for a particular programming language, one that
is widely used among developers working in that language.
The "System Libraries" of an executable work include anything, other
than the work as a whole, that (a) is included in the normal form of
packaging a Major Component, but which is not part of that Major
Component, and (b) serves only to enable use of the work with that
Major Component, or to implement a Standard Interface for which an
implementation is available to the public in source code form. A
"Major Component", in this context, means a major essential component
(kernel, window system, and so on) of the specific operating system
(if any) on which the executable work runs, or a compiler used to
produce the work, or an object code interpreter used to run it.
The "Corresponding Source" for a work in object code form means all
the source code needed to generate, install, and (for an executable
work) run the object code and to modify the work, including scripts to
control those activities. However, it does not include the work's
System Libraries, or general-purpose tools or generally available free
programs which are used unmodified in performing those activities but
which are not part of the work. For example, Corresponding Source
includes interface definition files associated with source files for
the work, and the source code for shared libraries and dynamically
linked subprograms that the work is specifically designed to require,
such as by intimate data communication or control flow between those
subprograms and other parts of the work.
The Corresponding Source need not include anything that users
can regenerate automatically from other parts of the Corresponding
Source.
The Corresponding Source for a work in source code form is that
same work.
2. Basic Permissions.
All rights granted under this License are granted for the term of
copyright on the Program, and are irrevocable provided the stated
conditions are met. This License explicitly affirms your unlimited
permission to run the unmodified Program. The output from running a
covered work is covered by this License only if the output, given its
content, constitutes a covered work. This License acknowledges your
rights of fair use or other equivalent, as provided by copyright law.
You may make, run and propagate covered works that you do not
convey, without conditions so long as your license otherwise remains
in force. You may convey covered works to others for the sole purpose
of having them make modifications exclusively for you, or provide you
with facilities for running those works, provided that you comply with
the terms of this License in conveying all material for which you do
not control copyright. Those thus making or running the covered works
for you must do so exclusively on your behalf, under your direction
and control, on terms that prohibit them from making any copies of
your copyrighted material outside their relationship with you.
Conveying under any other circumstances is permitted solely under
the conditions stated below. Sublicensing is not allowed; section 10
makes it unnecessary.
3. Protecting Users' Legal Rights From Anti-Circumvention Law.
No covered work shall be deemed part of an effective technological
measure under any applicable law fulfilling obligations under article
11 of the WIPO copyright treaty adopted on 20 December 1996, or
similar laws prohibiting or restricting circumvention of such
measures.
When you convey a covered work, you waive any legal power to forbid
circumvention of technological measures to the extent such circumvention
is effected by exercising rights under this License with respect to
the covered work, and you disclaim any intention to limit operation or
modification of the work as a means of enforcing, against the work's
users, your or third parties' legal rights to forbid circumvention of
technological measures.
4. Conveying Verbatim Copies.
You may convey verbatim copies of the Program's source code as you
receive it, in any medium, provided that you conspicuously and
appropriately publish on each copy an appropriate copyright notice;
keep intact all notices stating that this License and any
non-permissive terms added in accord with section 7 apply to the code;
keep intact all notices of the absence of any warranty; and give all
recipients a copy of this License along with the Program.
You may charge any price or no price for each copy that you convey,
and you may offer support or warranty protection for a fee.
5. Conveying Modified Source Versions.
You may convey a work based on the Program, or the modifications to
produce it from the Program, in the form of source code under the
terms of section 4, provided that you also meet all of these conditions:
a) The work must carry prominent notices stating that you modified
it, and giving a relevant date.
b) The work must carry prominent notices stating that it is
released under this License and any conditions added under section
7. This requirement modifies the requirement in section 4 to
"keep intact all notices".
c) You must license the entire work, as a whole, under this
License to anyone who comes into possession of a copy. This
License will therefore apply, along with any applicable section 7
additional terms, to the whole of the work, and all its parts,
regardless of how they are packaged. This License gives no
permission to license the work in any other way, but it does not
invalidate such permission if you have separately received it.
d) If the work has interactive user interfaces, each must display
Appropriate Legal Notices; however, if the Program has interactive
interfaces that do not display Appropriate Legal Notices, your
work need not make them do so.
A compilation of a covered work with other separate and independent
works, which are not by their nature extensions of the covered work,
and which are not combined with it such as to form a larger program,
in or on a volume of a storage or distribution medium, is called an
"aggregate" if the compilation and its resulting copyright are not
used to limit the access or legal rights of the compilation's users
beyond what the individual works permit. Inclusion of a covered work
in an aggregate does not cause this License to apply to the other
parts of the aggregate.
6. Conveying Non-Source Forms.
You may convey a covered work in object code form under the terms
of sections 4 and 5, provided that you also convey the
machine-readable Corresponding Source under the terms of this License,
in one of these ways:
a) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by the
Corresponding Source fixed on a durable physical medium
customarily used for software interchange.
b) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by a
written offer, valid for at least three years and valid for as
long as you offer spare parts or customer support for that product
model, to give anyone who possesses the object code either (1) a
copy of the Corresponding Source for all the software in the
product that is covered by this License, on a durable physical
medium customarily used for software interchange, for a price no
more than your reasonable cost of physically performing this
conveying of source, or (2) access to copy the
Corresponding Source from a network server at no charge.
c) Convey individual copies of the object code with a copy of the
written offer to provide the Corresponding Source. This
alternative is allowed only occasionally and noncommercially, and
only if you received the object code with such an offer, in accord
with subsection 6b.
d) Convey the object code by offering access from a designated
place (gratis or for a charge), and offer equivalent access to the
Corresponding Source in the same way through the same place at no
further charge. You need not require recipients to copy the
Corresponding Source along with the object code. If the place to
copy the object code is a network server, the Corresponding Source
may be on a different server (operated by you or a third party)
that supports equivalent copying facilities, provided you maintain
clear directions next to the object code saying where to find the
Corresponding Source. Regardless of what server hosts the
Corresponding Source, you remain obligated to ensure that it is
available for as long as needed to satisfy these requirements.
e) Convey the object code using peer-to-peer transmission, provided
you inform other peers where the object code and Corresponding
Source of the work are being offered to the general public at no
charge under subsection 6d.
A separable portion of the object code, whose source code is excluded
from the Corresponding Source as a System Library, need not be
included in conveying the object code work.
A "User Product" is either (1) a "consumer product", which means any
tangible personal property which is normally used for personal, family,
or household purposes, or (2) anything designed or sold for incorporation
into a dwelling. In determining whether a product is a consumer product,
doubtful cases shall be resolved in favor of coverage. For a particular
product received by a particular user, "normally used" refers to a
typical or common use of that class of product, regardless of the status
of the particular user or of the way in which the particular user
actually uses, or expects or is expected to use, the product. A product
is a consumer product regardless of whether the product has substantial
commercial, industrial or non-consumer uses, unless such uses represent
the only significant mode of use of the product.
"Installation Information" for a User Product means any methods,
procedures, authorization keys, or other information required to install
and execute modified versions of a covered work in that User Product from
a modified version of its Corresponding Source. The information must
suffice to ensure that the continued functioning of the modified object
code is in no case prevented or interfered with solely because
modification has been made.
If you convey an object code work under this section in, or with, or
specifically for use in, a User Product, and the conveying occurs as
part of a transaction in which the right of possession and use of the
User Product is transferred to the recipient in perpetuity or for a
fixed term (regardless of how the transaction is characterized), the
Corresponding Source conveyed under this section must be accompanied
by the Installation Information. But this requirement does not apply
if neither you nor any third party retains the ability to install
modified object code on the User Product (for example, the work has
been installed in ROM).
The requirement to provide Installation Information does not include a
requirement to continue to provide support service, warranty, or updates
for a work that has been modified or installed by the recipient, or for
the User Product in which it has been modified or installed. Access to a
network may be denied when the modification itself materially and
adversely affects the operation of the network or violates the rules and
protocols for communication across the network.
Corresponding Source conveyed, and Installation Information provided,
in accord with this section must be in a format that is publicly
documented (and with an implementation available to the public in
source code form), and must require no special password or key for
unpacking, reading or copying.
7. Additional Terms.
"Additional permissions" are terms that supplement the terms of this
License by making exceptions from one or more of its conditions.
Additional permissions that are applicable to the entire Program shall
be treated as though they were included in this License, to the extent
that they are valid under applicable law. If additional permissions
apply only to part of the Program, that part may be used separately
under those permissions, but the entire Program remains governed by
this License without regard to the additional permissions.
When you convey a copy of a covered work, you may at your option
remove any additional permissions from that copy, or from any part of
it. (Additional permissions may be written to require their own
removal in certain cases when you modify the work.) You may place
additional permissions on material, added by you to a covered work,
for which you have or can give appropriate copyright permission.
Notwithstanding any other provision of this License, for material you
add to a covered work, you may (if authorized by the copyright holders of
that material) supplement the terms of this License with terms:
a) Disclaiming warranty or limiting liability differently from the
terms of sections 15 and 16 of this License; or
b) Requiring preservation of specified reasonable legal notices or
author attributions in that material or in the Appropriate Legal
Notices displayed by works containing it; or
c) Prohibiting misrepresentation of the origin of that material, or
requiring that modified versions of such material be marked in
reasonable ways as different from the original version; or
d) Limiting the use for publicity purposes of names of licensors or
authors of the material; or
e) Declining to grant rights under trademark law for use of some
trade names, trademarks, or service marks; or
f) Requiring indemnification of licensors and authors of that
material by anyone who conveys the material (or modified versions of
it) with contractual assumptions of liability to the recipient, for
any liability that these contractual assumptions directly impose on
those licensors and authors.
All other non-permissive additional terms are considered "further
restrictions" within the meaning of section 10. If the Program as you
received it, or any part of it, contains a notice stating that it is
governed by this License along with a term that is a further
restriction, you may remove that term. If a license document contains
a further restriction but permits relicensing or conveying under this
License, you may add to a covered work material governed by the terms
of that license document, provided that the further restriction does
not survive such relicensing or conveying.
If you add terms to a covered work in accord with this section, you
must place, in the relevant source files, a statement of the
additional terms that apply to those files, or a notice indicating
where to find the applicable terms.
Additional terms, permissive or non-permissive, may be stated in the
form of a separately written license, or stated as exceptions;
the above requirements apply either way.
8. Termination.
You may not propagate or modify a covered work except as expressly
provided under this License. Any attempt otherwise to propagate or
modify it is void, and will automatically terminate your rights under
this License (including any patent licenses granted under the third
paragraph of section 11).
However, if you cease all violation of this License, then your
license from a particular copyright holder is reinstated (a)
provisionally, unless and until the copyright holder explicitly and
finally terminates your license, and (b) permanently, if the copyright
holder fails to notify you of the violation by some reasonable means
prior to 60 days after the cessation.
Moreover, your license from a particular copyright holder is
reinstated permanently if the copyright holder notifies you of the
violation by some reasonable means, this is the first time you have
received notice of violation of this License (for any work) from that
copyright holder, and you cure the violation prior to 30 days after
your receipt of the notice.
Termination of your rights under this section does not terminate the
licenses of parties who have received copies or rights from you under
this License. If your rights have been terminated and not permanently
reinstated, you do not qualify to receive new licenses for the same
material under section 10.
9. Acceptance Not Required for Having Copies.
You are not required to accept this License in order to receive or
run a copy of the Program. Ancillary propagation of a covered work
occurring solely as a consequence of using peer-to-peer transmission
to receive a copy likewise does not require acceptance. However,
nothing other than this License grants you permission to propagate or
modify any covered work. These actions infringe copyright if you do
not accept this License. Therefore, by modifying or propagating a
covered work, you indicate your acceptance of this License to do so.
10. Automatic Licensing of Downstream Recipients.
Each time you convey a covered work, the recipient automatically
receives a license from the original licensors, to run, modify and
propagate that work, subject to this License. You are not responsible
for enforcing compliance by third parties with this License.
An "entity transaction" is a transaction transferring control of an
organization, or substantially all assets of one, or subdividing an
organization, or merging organizations. If propagation of a covered
work results from an entity transaction, each party to that
transaction who receives a copy of the work also receives whatever
licenses to the work the party's predecessor in interest had or could
give under the previous paragraph, plus a right to possession of the
Corresponding Source of the work from the predecessor in interest, if
the predecessor has it or can get it with reasonable efforts.
You may not impose any further restrictions on the exercise of the
rights granted or affirmed under this License. For example, you may
not impose a license fee, royalty, or other charge for exercise of
rights granted under this License, and you may not initiate litigation
(including a cross-claim or counterclaim in a lawsuit) alleging that
any patent claim is infringed by making, using, selling, offering for
sale, or importing the Program or any portion of it.
11. Patents.
A "contributor" is a copyright holder who authorizes use under this
License of the Program or a work on which the Program is based. The
work thus licensed is called the contributor's "contributor version".
A contributor's "essential patent claims" are all patent claims
owned or controlled by the contributor, whether already acquired or
hereafter acquired, that would be infringed by some manner, permitted
by this License, of making, using, or selling its contributor version,
but do not include claims that would be infringed only as a
consequence of further modification of the contributor version. For
purposes of this definition, "control" includes the right to grant
patent sublicenses in a manner consistent with the requirements of
this License.
Each contributor grants you a non-exclusive, worldwide, royalty-free
patent license under the contributor's essential patent claims, to
make, use, sell, offer for sale, import and otherwise run, modify and
propagate the contents of its contributor version.
In the following three paragraphs, a "patent license" is any express
agreement or commitment, however denominated, not to enforce a patent
(such as an express permission to practice a patent or covenant not to
sue for patent infringement). To "grant" such a patent license to a
party means to make such an agreement or commitment not to enforce a
patent against the party.
If you convey a covered work, knowingly relying on a patent license,
and the Corresponding Source of the work is not available for anyone
to copy, free of charge and under the terms of this License, through a
publicly available network server or other readily accessible means,
then you must either (1) cause the Corresponding Source to be so
available, or (2) arrange to deprive yourself of the benefit of the
patent license for this particular work, or (3) arrange, in a manner
consistent with the requirements of this License, to extend the patent
license to downstream recipients. "Knowingly relying" means you have
actual knowledge that, but for the patent license, your conveying the
covered work in a country, or your recipient's use of the covered work
in a country, would infringe one or more identifiable patents in that
country that you have reason to believe are valid.
If, pursuant to or in connection with a single transaction or
arrangement, you convey, or propagate by procuring conveyance of, a
covered work, and grant a patent license to some of the parties
receiving the covered work authorizing them to use, propagate, modify
or convey a specific copy of the covered work, then the patent license
you grant is automatically extended to all recipients of the covered
work and works based on it.
A patent license is "discriminatory" if it does not include within
the scope of its coverage, prohibits the exercise of, or is
conditioned on the non-exercise of one or more of the rights that are
specifically granted under this License. You may not convey a covered
work if you are a party to an arrangement with a third party that is
in the business of distributing software, under which you make payment
to the third party based on the extent of your activity of conveying
the work, and under which the third party grants, to any of the
parties who would receive the covered work from you, a discriminatory
patent license (a) in connection with copies of the covered work
conveyed by you (or copies made from those copies), or (b) primarily
for and in connection with specific products or compilations that
contain the covered work, unless you entered into that arrangement,
or that patent license was granted, prior to 28 March 2007.
Nothing in this License shall be construed as excluding or limiting
any implied license or other defenses to infringement that may
otherwise be available to you under applicable patent law.
12. No Surrender of Others' Freedom.
If conditions are imposed on you (whether by court order, agreement or
otherwise) that contradict the conditions of this License, they do not
excuse you from the conditions of this License. If you cannot convey a
covered work so as to satisfy simultaneously your obligations under this
License and any other pertinent obligations, then as a consequence you may
not convey it at all. For example, if you agree to terms that obligate you
to collect a royalty for further conveying from those to whom you convey
the Program, the only way you could satisfy both those terms and this
License would be to refrain entirely from conveying the Program.
13. Remote Network Interaction; Use with the GNU General Public License.
Notwithstanding any other provision of this License, if you modify the
Program, your modified version must prominently offer all users
interacting with it remotely through a computer network (if your version
supports such interaction) an opportunity to receive the Corresponding
Source of your version by providing access to the Corresponding Source
from a network server at no charge, through some standard or customary
means of facilitating copying of software. This Corresponding Source
shall include the Corresponding Source for any work covered by version 3
of the GNU General Public License that is incorporated pursuant to the
following paragraph.
Notwithstanding any other provision of this License, you have
permission to link or combine any covered work with a work licensed
under version 3 of the GNU General Public License into a single
combined work, and to convey the resulting work. The terms of this
License will continue to apply to the part which is the covered work,
but the work with which it is combined will remain governed by version
3 of the GNU General Public License.
14. Revised Versions of this License.
The Free Software Foundation may publish revised and/or new versions of
the GNU Affero General Public License from time to time. Such new versions
will be similar in spirit to the present version, but may differ in detail to
address new problems or concerns.
Each version is given a distinguishing version number. If the
Program specifies that a certain numbered version of the GNU Affero General
Public License "or any later version" applies to it, you have the
option of following the terms and conditions either of that numbered
version or of any later version published by the Free Software
Foundation. If the Program does not specify a version number of the
GNU Affero General Public License, you may choose any version ever published
by the Free Software Foundation.
If the Program specifies that a proxy can decide which future
versions of the GNU Affero General Public License can be used, that proxy's
public statement of acceptance of a version permanently authorizes you
to choose that version for the Program.
Later license versions may give you additional or different
permissions. However, no additional obligations are imposed on any
author or copyright holder as a result of your choosing to follow a
later version.
15. Disclaimer of Warranty.
THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
16. Limitation of Liability.
IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
SUCH DAMAGES.
17. Interpretation of Sections 15 and 16.
If the disclaimer of warranty and limitation of liability provided
above cannot be given local legal effect according to their terms,
reviewing courts shall apply local law that most closely approximates
an absolute waiver of all civil liability in connection with the
Program, unless a warranty or assumption of liability accompanies a
copy of the Program in return for a fee.
END OF TERMS AND CONDITIONS
How to Apply These Terms to Your New Programs
If you develop a new program, and you want it to be of the greatest
possible use to the public, the best way to achieve this is to make it
free software which everyone can redistribute and change under these terms.
To do so, attach the following notices to the program. It is safest
to attach them to the start of each source file to most effectively
state the exclusion of warranty; and each file should have at least
the "copyright" line and a pointer to where the full notice is found.
<one line to give the program's name and a brief idea of what it does.>
Copyright (C) <year> <name of author>
This program 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.
This program 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 this program. If not, see <http://www.gnu.org/licenses/>.
Also add information on how to contact you by electronic and paper mail.
If your software can interact with users remotely through a computer
network, you should also make sure that it provides a way for users to
get its source. For example, if your program is a web application, its
interface could display a "Source" link that leads users to an archive
of the code. There are many ways you could offer source, and different
solutions will be better for different programs; see section 13 for the
specific requirements.
You should also get your employer (if you work as a programmer) or school,
if any, to sign a "copyright disclaimer" for the program, if necessary.
For more information on this, and how to apply and follow the GNU AGPL, see
<http://www.gnu.org/licenses/>.

1
sources/Makefile
View File

@ -51,6 +51,7 @@ styles:
@lessc -x searx/static/themes/courgette/less/style-rtl.less > searx/static/themes/courgette/css/style-rtl.css @lessc -x searx/static/themes/courgette/less/style-rtl.less > searx/static/themes/courgette/css/style-rtl.css
@lessc -x searx/static/less/bootstrap/bootstrap.less > searx/static/css/bootstrap.min.css @lessc -x searx/static/less/bootstrap/bootstrap.less > searx/static/css/bootstrap.min.css
@lessc -x searx/static/themes/oscar/less/oscar/oscar.less > searx/static/themes/oscar/css/oscar.min.css @lessc -x searx/static/themes/oscar/less/oscar/oscar.less > searx/static/themes/oscar/css/oscar.min.css
@lessc -x searx/static/themes/pix-art/less/style.less > searx/static/themes/pix-art/css/style.css
grunt: grunt:
@grunt --gruntfile searx/static/themes/oscar/gruntfile.js @grunt --gruntfile searx/static/themes/oscar/gruntfile.js

5
sources/requirements.txt
View File

@ -5,3 +5,8 @@ lxml
pyyaml pyyaml
pygments pygments
python-dateutil python-dateutil
ndg-httpsclient
pyopenssl
pyasn1
pyasn1-modules
certifi

13
sources/searx/__init__.py
View File

@ -36,26 +36,15 @@ if 'SEARX_SETTINGS_PATH' in environ:
else: else:
settings_path = join(searx_dir, 'settings.yml') settings_path = join(searx_dir, 'settings.yml')
if 'SEARX_HTTPS_REWRITE_PATH' in environ:
https_rewrite_path = environ['SEARX_HTTPS_REWRITE_PATH']
else:
https_rewrite_path = join(searx_dir, 'https_rules')
# load settings # load settings
with open(settings_path) as settings_yaml: with open(settings_path) as settings_yaml:
settings = load(settings_yaml) settings = load(settings_yaml)
if settings.get('server', {}).get('debug'): if settings.get('general', {}).get('debug'):
logging.basicConfig(level=logging.DEBUG) logging.basicConfig(level=logging.DEBUG)
else: else:
logging.basicConfig(level=logging.WARNING) logging.basicConfig(level=logging.WARNING)
logger = logging.getLogger('searx') logger = logging.getLogger('searx')
# load https rules only if https rewrite is enabled
if settings.get('server', {}).get('https_rewrite'):
# loade https rules
from searx.https_rewrite import load_https_rules
load_https_rules(https_rewrite_path)
logger.info('Initialisation done') logger.info('Initialisation done')

35
sources/searx/autocomplete.py
View File

@ -19,11 +19,19 @@ along with searx. If not, see < http://www.gnu.org/licenses/ >.
from lxml import etree from lxml import etree
from json import loads from json import loads
from urllib import urlencode from urllib import urlencode
from searx import settings
from searx.languages import language_codes from searx.languages import language_codes
from searx.engines import ( from searx.engines import (
categories, engines, engine_shortcuts categories, engines, engine_shortcuts
) )
from searx.poolrequests import get from searx.poolrequests import get as http_get
def get(*args, **kwargs):
if 'timeout' not in kwargs:
kwargs['timeout'] = settings['outgoing']['request_timeout']
return http_get(*args, **kwargs)
def searx_bang(full_query): def searx_bang(full_query):
@ -49,17 +57,17 @@ def searx_bang(full_query):
# check if query starts with categorie name # check if query starts with categorie name
for categorie in categories: for categorie in categories:
if categorie.startswith(engine_query): if categorie.startswith(engine_query):
results.append(first_char+'{categorie}'.format(categorie=categorie)) results.append(first_char + '{categorie}'.format(categorie=categorie))
# check if query starts with engine name # check if query starts with engine name
for engine in engines: for engine in engines:
if engine.startswith(engine_query.replace('_', ' ')): if engine.startswith(engine_query.replace('_', ' ')):
results.append(first_char+'{engine}'.format(engine=engine.replace(' ', '_'))) results.append(first_char + '{engine}'.format(engine=engine.replace(' ', '_')))
# check if query starts with engine shortcut # check if query starts with engine shortcut
for engine_shortcut in engine_shortcuts: for engine_shortcut in engine_shortcuts:
if engine_shortcut.startswith(engine_query): if engine_shortcut.startswith(engine_query):
results.append(first_char+'{engine_shortcut}'.format(engine_shortcut=engine_shortcut)) results.append(first_char + '{engine_shortcut}'.format(engine_shortcut=engine_shortcut))
# check if current query stats with :bang # check if current query stats with :bang
elif first_char == ':': elif first_char == ':':
@ -103,8 +111,8 @@ def searx_bang(full_query):
def dbpedia(query): def dbpedia(query):
# dbpedia autocompleter # dbpedia autocompleter, no HTTPS
autocomplete_url = 'http://lookup.dbpedia.org/api/search.asmx/KeywordSearch?' # noqa autocomplete_url = 'http://lookup.dbpedia.org/api/search.asmx/KeywordSearch?'
response = get(autocomplete_url response = get(autocomplete_url
+ urlencode(dict(QueryString=query))) + urlencode(dict(QueryString=query)))
@ -131,7 +139,7 @@ def duckduckgo(query):
def google(query): def google(query):
# google autocompleter # google autocompleter
autocomplete_url = 'http://suggestqueries.google.com/complete/search?client=toolbar&' # noqa autocomplete_url = 'https://suggestqueries.google.com/complete/search?client=toolbar&'
response = get(autocomplete_url response = get(autocomplete_url
+ urlencode(dict(q=query))) + urlencode(dict(q=query)))
@ -145,9 +153,19 @@ def google(query):
return results return results
def startpage(query):
# wikipedia autocompleter
url = 'https://startpage.com/do/suggest?{query}'
resp = get(url.format(query=urlencode({'query': query}))).text.split('\n')
if len(resp) > 1:
return resp
return []
def wikipedia(query): def wikipedia(query):
# wikipedia autocompleter # wikipedia autocompleter
url = 'https://en.wikipedia.org/w/api.php?action=opensearch&{0}&limit=10&namespace=0&format=json' # noqa url = 'https://en.wikipedia.org/w/api.php?action=opensearch&{0}&limit=10&namespace=0&format=json'
resp = loads(get(url.format(urlencode(dict(search=query)))).text) resp = loads(get(url.format(urlencode(dict(search=query)))).text)
if len(resp) > 1: if len(resp) > 1:
@ -158,5 +176,6 @@ def wikipedia(query):
backends = {'dbpedia': dbpedia, backends = {'dbpedia': dbpedia,
'duckduckgo': duckduckgo, 'duckduckgo': duckduckgo,
'google': google, 'google': google,
'startpage': startpage,
'wikipedia': wikipedia 'wikipedia': wikipedia
} }

7655
sources/searx/data/currencies.json Normal file
View File

File diff suppressed because it is too large Load Diff

9
sources/searx/engines/__init__.py
View File

@ -71,8 +71,11 @@ def load_engine(engine_data):
if not hasattr(engine, 'language_support'): if not hasattr(engine, 'language_support'):
engine.language_support = True engine.language_support = True
if not hasattr(engine, 'safesearch'):
engine.safesearch = False
if not hasattr(engine, 'timeout'): if not hasattr(engine, 'timeout'):
engine.timeout = settings['server']['request_timeout'] engine.timeout = settings['outgoing']['request_timeout']
if not hasattr(engine, 'shortcut'): if not hasattr(engine, 'shortcut'):
engine.shortcut = '' engine.shortcut = ''
@ -86,7 +89,7 @@ def load_engine(engine_data):
continue continue
if getattr(engine, engine_attr) is None: if getattr(engine, engine_attr) is None:
logger.error('Missing engine config attribute: "{0}.{1}"' logger.error('Missing engine config attribute: "{0}.{1}"'
.format(engine.name, engine_attr)) .format(engine.name, engine_attr))
sys.exit(1) sys.exit(1)
engine.stats = { engine.stats = {
@ -106,7 +109,7 @@ def load_engine(engine_data):
if engine.shortcut: if engine.shortcut:
if engine.shortcut in engine_shortcuts: if engine.shortcut in engine_shortcuts:
logger.error('Engine config error: ambigious shortcut: {0}' logger.error('Engine config error: ambigious shortcut: {0}'
.format(engine.shortcut)) .format(engine.shortcut))
sys.exit(1) sys.exit(1)
engine_shortcuts[engine.shortcut] = engine.name engine_shortcuts[engine.shortcut] = engine.name
return engine return engine

28
sources/searx/engines/bing.py
View File

@ -1,15 +1,17 @@
## Bing (Web) """
# Bing (Web)
# @website https://www.bing.com
# @provide-api yes (http://datamarket.azure.com/dataset/bing/search), @website https://www.bing.com
# max. 5000 query/month @provide-api yes (http://datamarket.azure.com/dataset/bing/search),
# max. 5000 query/month
# @using-api no (because of query limit)
# @results HTML (using search portal) @using-api no (because of query limit)
# @stable no (HTML can change) @results HTML (using search portal)
# @parse url, title, content @stable no (HTML can change)
# @parse url, title, content
# @todo publishedDate
@todo publishedDate
"""
from urllib import urlencode from urllib import urlencode
from cgi import escape from cgi import escape
@ -50,7 +52,7 @@ def request(query, params):
def response(resp): def response(resp):
results = [] results = []
dom = html.fromstring(resp.content) dom = html.fromstring(resp.text)
# parse results # parse results
for result in dom.xpath('//div[@class="sa_cc"]'): for result in dom.xpath('//div[@class="sa_cc"]'):

36
sources/searx/engines/bing_images.py
View File

@ -1,17 +1,19 @@
## Bing (Images) """
# Bing (Images)
# @website https://www.bing.com/images
# @provide-api yes (http://datamarket.azure.com/dataset/bing/search), @website https://www.bing.com/images
# max. 5000 query/month @provide-api yes (http://datamarket.azure.com/dataset/bing/search),
# max. 5000 query/month
# @using-api no (because of query limit)
# @results HTML (using search portal) @using-api no (because of query limit)
# @stable no (HTML can change) @results HTML (using search portal)
# @parse url, title, img_src @stable no (HTML can change)
# @parse url, title, img_src
# @todo currently there are up to 35 images receive per page,
# because bing does not parse count=10. @todo currently there are up to 35 images receive per page,
# limited response to 10 images because bing does not parse count=10.
limited response to 10 images
"""
from urllib import urlencode from urllib import urlencode
from lxml import html from lxml import html
@ -26,7 +28,7 @@ safesearch = True
# search-url # search-url
base_url = 'https://www.bing.com/' base_url = 'https://www.bing.com/'
search_string = 'images/search?{query}&count=10&first={offset}' search_string = 'images/search?{query}&count=10&first={offset}'
thumb_url = "http://ts1.mm.bing.net/th?id={ihk}" thumb_url = "https://www.bing.com/th?id={ihk}"
# safesearch definitions # safesearch definitions
safesearch_types = {2: 'STRICT', safesearch_types = {2: 'STRICT',
@ -61,7 +63,7 @@ def request(query, params):
def response(resp): def response(resp):
results = [] results = []
dom = html.fromstring(resp.content) dom = html.fromstring(resp.text)
# init regex for yaml-parsing # init regex for yaml-parsing
p = re.compile('({|,)([a-z]+):(")') p = re.compile('({|,)([a-z]+):(")')
@ -76,7 +78,7 @@ def response(resp):
title = link.attrib.get('t1') title = link.attrib.get('t1')
ihk = link.attrib.get('ihk') ihk = link.attrib.get('ihk')
#url = 'http://' + link.attrib.get('t3') # url = 'http://' + link.attrib.get('t3')
url = yaml_data.get('surl') url = yaml_data.get('surl')
img_src = yaml_data.get('imgurl') img_src = yaml_data.get('imgurl')

121
sources/searx/engines/bing_news.py
View File

@ -1,21 +1,22 @@
## Bing (News) """
# Bing (News)
# @website https://www.bing.com/news
# @provide-api yes (http://datamarket.azure.com/dataset/bing/search), @website https://www.bing.com/news
# max. 5000 query/month @provide-api yes (http://datamarket.azure.com/dataset/bing/search),
# max. 5000 query/month
# @using-api no (because of query limit)
# @results HTML (using search portal) @using-api no (because of query limit)
# @stable no (HTML can change) @results RSS (using search portal)
# @parse url, title, content, publishedDate @stable yes (except perhaps for the images)
@parse url, title, content, publishedDate, thumbnail
"""
from urllib import urlencode from urllib import urlencode
from cgi import escape from urlparse import urlparse, parse_qsl
from lxml import html from datetime import datetime
from datetime import datetime, timedelta
from dateutil import parser from dateutil import parser
import re from lxml import etree
from searx.engines.xpath import extract_text from searx.utils import list_get
# engine dependent config # engine dependent config
categories = ['news'] categories = ['news']
@ -24,7 +25,25 @@ language_support = True
# search-url # search-url
base_url = 'https://www.bing.com/' base_url = 'https://www.bing.com/'
search_string = 'news/search?{query}&first={offset}' search_string = 'news/search?{query}&first={offset}&format=RSS'
# remove click
def url_cleanup(url_string):
parsed_url = urlparse(url_string)
if parsed_url.netloc == 'www.bing.com' and parsed_url.path == '/news/apiclick.aspx':
query = dict(parse_qsl(parsed_url.query))
return query.get('url', None)
return url_string
# replace the http://*bing4.com/th?id=... by https://www.bing.com/th?id=...
def image_url_cleanup(url_string):
parsed_url = urlparse(url_string)
if parsed_url.netloc.endswith('bing4.com') and parsed_url.path == '/th':
query = dict(parse_qsl(parsed_url.query))
return "https://www.bing.com/th?id=" + query.get('id')
return url_string
# do search-request # do search-request
@ -40,8 +59,6 @@ def request(query, params):
query=urlencode({'q': query, 'setmkt': language}), query=urlencode({'q': query, 'setmkt': language}),
offset=offset) offset=offset)
params['cookies']['_FP'] = "ui=en-US"
params['url'] = base_url + search_path params['url'] = base_url + search_path
return params return params
@ -51,48 +68,44 @@ def request(query, params):
def response(resp): def response(resp):
results = [] results = []
dom = html.fromstring(resp.content) rss = etree.fromstring(resp.text)
ns = rss.nsmap
# parse results # parse results
for result in dom.xpath('//div[@class="sn_r"]'): for item in rss.xpath('./channel/item'):
link = result.xpath('.//div[@class="newstitle"]/a')[0] # url / title / content
url = link.attrib.get('href') url = url_cleanup(item.xpath('./link/text()')[0])
title = extract_text(link) title = list_get(item.xpath('./title/text()'), 0, url)
contentXPath = result.xpath('.//div[@class="sn_txt"]/div//span[@class="sn_snip"]') content = list_get(item.xpath('./description/text()'), 0, '')
content = escape(extract_text(contentXPath))
# parse publishedDate # publishedDate
publishedDateXPath = result.xpath('.//div[@class="sn_txt"]/div' publishedDate = list_get(item.xpath('./pubDate/text()'), 0)
'//span[contains(@class,"sn_ST")]' try:
'//span[contains(@class,"sn_tm")]') publishedDate = parser.parse(publishedDate, dayfirst=False)
except TypeError:
publishedDate = datetime.now()
except ValueError:
publishedDate = datetime.now()
publishedDate = escape(extract_text(publishedDateXPath)) # thumbnail
thumbnail = list_get(item.xpath('./News:Image/text()', namespaces=ns), 0)
if re.match("^[0-9]+ minute(s|) ago$", publishedDate): if thumbnail is not None:
timeNumbers = re.findall(r'\d+', publishedDate) thumbnail = image_url_cleanup(thumbnail)
publishedDate = datetime.now() - timedelta(minutes=int(timeNumbers[0]))
elif re.match("^[0-9]+ hour(s|) ago$", publishedDate):
timeNumbers = re.findall(r'\d+', publishedDate)
publishedDate = datetime.now() - timedelta(hours=int(timeNumbers[0]))
elif re.match("^[0-9]+ hour(s|), [0-9]+ minute(s|) ago$", publishedDate):
timeNumbers = re.findall(r'\d+', publishedDate)
publishedDate = datetime.now()\
- timedelta(hours=int(timeNumbers[0]))\
- timedelta(minutes=int(timeNumbers[1]))
elif re.match("^[0-9]+ day(s|) ago$", publishedDate):
timeNumbers = re.findall(r'\d+', publishedDate)
publishedDate = datetime.now() - timedelta(days=int(timeNumbers[0]))
else:
try:
publishedDate = parser.parse(publishedDate, dayfirst=False)
except TypeError:
publishedDate = datetime.now()
# append result # append result
results.append({'url': url, if thumbnail is not None:
'title': title, results.append({'template': 'videos.html',
'publishedDate': publishedDate, 'url': url,
'content': content}) 'title': title,
'publishedDate': publishedDate,
'content': content,
'thumbnail': thumbnail})
else:
results.append({'url': url,
'title': title,
'publishedDate': publishedDate,
'content': content})
# return results # return results
return results return results

20
sources/searx/engines/blekko_images.py
View File

@ -1,12 +1,14 @@
## Blekko (Images) """
# Blekko (Images)
# @website https://blekko.com
# @provide-api yes (inofficial) @website https://blekko.com
# @provide-api yes (inofficial)
# @using-api yes
# @results JSON @using-api yes
# @stable yes @results JSON
# @parse url, title, img_src @stable yes
@parse url, title, img_src
"""
from json import loads from json import loads
from urllib import urlencode from urllib import urlencode

20
sources/searx/engines/btdigg.py
View File

@ -1,12 +1,14 @@
## BTDigg (Videos, Music, Files) """
# BTDigg (Videos, Music, Files)
# @website https://btdigg.org
# @provide-api yes (on demand) @website https://btdigg.org
# @provide-api yes (on demand)
# @using-api no
# @results HTML (using search portal) @using-api no
# @stable no (HTML can change) @results HTML (using search portal)
# @parse url, title, content, seed, leech, magnetlink @stable no (HTML can change)
@parse url, title, content, seed, leech, magnetlink
"""
from urlparse import urljoin from urlparse import urljoin
from cgi import escape from cgi import escape

56
sources/searx/engines/currency_convert.py
View File

@ -1,21 +1,49 @@
from datetime import datetime from datetime import datetime
import re import re
import os
import json
import unicodedata
categories = [] categories = []
url = 'http://finance.yahoo.com/d/quotes.csv?e=.csv&f=sl1d1t1&s={query}=X' url = 'https://download.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*$', re.I) # noqa parser_re = re.compile(u'^\W*(\d+(?:\.\d+)?)\W*([^.0-9].+)\W+in?\W+([^\.]+)\W*$', re.I) # noqa
db = 1
def normalize_name(name):
name = name.lower().replace('-', ' ')
name = re.sub(' +', ' ', name)
return unicodedata.normalize('NFKD', name).lower()
def name_to_iso4217(name):
global db
name = normalize_name(name)
currencies = db['names'].get(name, [name])
return currencies[0]
def iso4217_to_name(iso4217, language):
global db
return db['iso4217'].get(iso4217, {}).get(language, iso4217)
def request(query, params): def request(query, params):
m = parser_re.match(query) m = parser_re.match(unicode(query, 'utf8'))
if not m: if not m:
# wrong query # wrong query
return params return params
ammount, from_currency, to_currency = m.groups() ammount, from_currency, to_currency = m.groups()
ammount = float(ammount) ammount = float(ammount)
from_currency = name_to_iso4217(from_currency.strip())
to_currency = name_to_iso4217(to_currency.strip())
q = (from_currency + to_currency).upper() q = (from_currency + to_currency).upper()
@ -23,6 +51,8 @@ def request(query, params):
params['ammount'] = ammount params['ammount'] = ammount
params['from'] = from_currency params['from'] = from_currency
params['to'] = to_currency params['to'] = to_currency
params['from_name'] = iso4217_to_name(from_currency, 'en')
params['to_name'] = iso4217_to_name(to_currency, 'en')
return params return params
@ -35,16 +65,18 @@ def response(resp):
except: except:
return results return results
answer = '{0} {1} = {2} {3} (1 {1} = {4} {3})'.format( answer = '{0} {1} = {2} {3}, 1 {1} ({5}) = {4} {3} ({6})'.format(
resp.search_params['ammount'], resp.search_params['ammount'],
resp.search_params['from'], resp.search_params['from'],
resp.search_params['ammount'] * conversion_rate, resp.search_params['ammount'] * conversion_rate,
resp.search_params['to'], resp.search_params['to'],
conversion_rate conversion_rate,
resp.search_params['from_name'],
resp.search_params['to_name'],
) )
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' # noqa url = 'https://finance.yahoo.com/currency/converter-results/{0}/{1}-{2}-to-{3}.html' # noqa
url = url.format( url = url.format(
now_date, now_date,
resp.search_params['ammount'], resp.search_params['ammount'],
@ -55,3 +87,15 @@ def response(resp):
results.append({'answer': answer, 'url': url}) results.append({'answer': answer, 'url': url})
return results return results
def load():
global db
current_dir = os.path.dirname(os.path.realpath(__file__))
json_data = open(current_dir + "/../data/currencies.json").read()
db = json.loads(json_data)
load()

29
sources/searx/engines/dailymotion.py
View File

@ -1,14 +1,16 @@
## Dailymotion (Videos) """
# Dailymotion (Videos)
# @website https://www.dailymotion.com
# @provide-api yes (http://www.dailymotion.com/developer) @website https://www.dailymotion.com
# @provide-api yes (http://www.dailymotion.com/developer)
# @using-api yes
# @results JSON @using-api yes
# @stable yes @results JSON
# @parse url, title, thumbnail, publishedDate, embedded @stable yes
# @parse url, title, thumbnail, publishedDate, embedded
# @todo set content-parameter with correct data
@todo set content-parameter with correct data
"""
from urllib import urlencode from urllib import urlencode
from json import loads from json import loads
@ -48,7 +50,7 @@ def response(resp):
search_res = loads(resp.text) search_res = loads(resp.text)
# return empty array if there are no results # return empty array if there are no results
if not 'list' in search_res: if 'list' not in search_res:
return [] return []
# parse results # parse results
@ -60,6 +62,9 @@ def response(resp):
publishedDate = datetime.fromtimestamp(res['created_time'], None) publishedDate = datetime.fromtimestamp(res['created_time'], None)
embedded = embedded_url.format(videoid=res['id']) embedded = embedded_url.format(videoid=res['id'])
# http to https
thumbnail = thumbnail.replace("http://", "https://")
results.append({'template': 'videos.html', results.append({'template': 'videos.html',
'url': url, 'url': url,
'title': title, 'title': title,

28
sources/searx/engines/deezer.py
View File

@ -1,12 +1,14 @@
## Deezer (Music) """
# Deezer (Music)
# @website https://deezer.com
# @provide-api yes (http://developers.deezer.com/api/) @website https://deezer.com
# @provide-api yes (http://developers.deezer.com/api/)
# @using-api yes
# @results JSON @using-api yes
# @stable yes @results JSON
# @parse url, title, content, embedded @stable yes
@parse url, title, content, embedded
"""
from json import loads from json import loads
from urllib import urlencode from urllib import urlencode
@ -16,11 +18,11 @@ categories = ['music']
paging = True paging = True
# search-url # search-url
url = 'http://api.deezer.com/' url = 'https://api.deezer.com/'
search_url = url + 'search?{query}&index={offset}' search_url = url + 'search?{query}&index={offset}'
embedded_url = '<iframe scrolling="no" frameborder="0" allowTransparency="true" ' +\ embedded_url = '<iframe scrolling="no" frameborder="0" allowTransparency="true" ' +\
'data-src="http://www.deezer.com/plugins/player?type=tracks&id={audioid}" ' +\ 'data-src="https://www.deezer.com/plugins/player?type=tracks&id={audioid}" ' +\
'width="540" height="80"></iframe>' 'width="540" height="80"></iframe>'
@ -45,6 +47,10 @@ def response(resp):
if result['type'] == 'track': if result['type'] == 'track':
title = result['title'] title = result['title']
url = result['link'] url = result['link']
if url.startswith('http://'):
url = 'https' + url[4:]
content = result['artist']['name'] +\ content = result['artist']['name'] +\
" &bull; " +\ " &bull; " +\
result['album']['title'] +\ result['album']['title'] +\

32
sources/searx/engines/deviantart.py
View File

@ -1,14 +1,16 @@
## Deviantart (Images) """
# Deviantart (Images)
# @website https://www.deviantart.com/
# @provide-api yes (https://www.deviantart.com/developers/) (RSS) @website https://www.deviantart.com/
# @provide-api yes (https://www.deviantart.com/developers/) (RSS)
# @using-api no (TODO, rewrite to api)
# @results HTML @using-api no (TODO, rewrite to api)
# @stable no (HTML can change) @results HTML
# @parse url, title, thumbnail_src, img_src @stable no (HTML can change)
# @parse url, title, thumbnail_src, img_src
# @todo rewrite to api
@todo rewrite to api
"""
from urllib import urlencode from urllib import urlencode
from urlparse import urljoin from urlparse import urljoin
@ -22,7 +24,7 @@ paging = True
# search-url # search-url
base_url = 'https://www.deviantart.com/' base_url = 'https://www.deviantart.com/'
search_url = base_url+'search?offset={offset}&{query}' search_url = base_url+'browse/all/?offset={offset}&{query}'
# do search-request # do search-request
@ -56,6 +58,12 @@ def response(resp):
thumbnail_src = link.xpath('.//img')[0].attrib.get('src') thumbnail_src = link.xpath('.//img')[0].attrib.get('src')
img_src = regex.sub('/', thumbnail_src) img_src = regex.sub('/', thumbnail_src)
# http to https, remove domain sharding
thumbnail_src = re.sub(r"https?://(th|fc)\d+.", "https://th01.", thumbnail_src)
thumbnail_src = re.sub(r"http://", "https://", thumbnail_src)
url = re.sub(r"http://(.*)\.deviantart\.com/", "https://\\1.deviantart.com/", url)
# append result # append result
results.append({'url': url, results.append({'url': url,
'title': title, 'title': title,

23
sources/searx/engines/digg.py
View File

@ -1,12 +1,14 @@
## Digg (News, Social media) """
# Digg (News, Social media)
# @website https://digg.com/
# @provide-api no @website https://digg.com/
# @provide-api no
# @using-api no
# @results HTML (using search portal) @using-api no
# @stable no (HTML can change) @results HTML (using search portal)
# @parse url, title, content, publishedDate, thumbnail @stable no (HTML can change)
@parse url, title, content, publishedDate, thumbnail
"""
from urllib import quote_plus from urllib import quote_plus
from json import loads from json import loads
@ -58,6 +60,9 @@ def response(resp):
pubdate = result.xpath(pubdate_xpath)[0].attrib.get('datetime') pubdate = result.xpath(pubdate_xpath)[0].attrib.get('datetime')
publishedDate = parser.parse(pubdate) publishedDate = parser.parse(pubdate)
# http to https
thumbnail = thumbnail.replace("http://static.digg.com", "https://static.digg.com")
# append result # append result
results.append({'url': url, results.append({'url': url,
'title': title, 'title': title,

30
sources/searx/engines/duckduckgo.py
View File

@ -1,17 +1,19 @@
## DuckDuckGo (Web) """
# DuckDuckGo (Web)
# @website https://duckduckgo.com/
# @provide-api yes (https://duckduckgo.com/api), @website https://duckduckgo.com/
# but not all results from search-site @provide-api yes (https://duckduckgo.com/api),
# but not all results from search-site
# @using-api no
# @results HTML (using search portal) @using-api no
# @stable no (HTML can change) @results HTML (using search portal)
# @parse url, title, content @stable no (HTML can change)
# @parse url, title, content
# @todo rewrite to api
# @todo language support @todo rewrite to api
# (the current used site does not support language-change) @todo language support
(the current used site does not support language-change)
"""
from urllib import urlencode from urllib import urlencode
from lxml.html import fromstring from lxml.html import fromstring

10
sources/searx/engines/dummy.py
View File

@ -1,7 +1,9 @@
## Dummy """
# Dummy
# @results empty array
# @stable yes @results empty array
@stable yes
"""
# do search-request # do search-request

20
sources/searx/engines/faroo.py
View File

@ -1,12 +1,14 @@
## Faroo (Web, News) """
# Faroo (Web, News)
# @website http://www.faroo.com
# @provide-api yes (http://www.faroo.com/hp/api/api.html), require API-key @website http://www.faroo.com
# @provide-api yes (http://www.faroo.com/hp/api/api.html), require API-key
# @using-api yes
# @results JSON @using-api yes
# @stable yes @results JSON
# @parse url, title, content, publishedDate, img_src @stable yes
@parse url, title, content, publishedDate, img_src
"""
from urllib import urlencode from urllib import urlencode
from json import loads from json import loads

26
sources/searx/engines/flickr.py
View File

@ -1,15 +1,17 @@
#!/usr/bin/env python #!/usr/bin/env python
## Flickr (Images) """
# Flickr (Images)
# @website https://www.flickr.com
# @provide-api yes (https://secure.flickr.com/services/api/flickr.photos.search.html) @website https://www.flickr.com
# @provide-api yes (https://secure.flickr.com/services/api/flickr.photos.search.html)
# @using-api yes
# @results JSON @using-api yes
# @stable yes @results JSON
# @parse url, title, thumbnail, img_src @stable yes
#More info on api-key : https://www.flickr.com/services/apps/create/ @parse url, title, thumbnail, img_src
More info on api-key : https://www.flickr.com/services/apps/create/
"""
from urllib import urlencode from urllib import urlencode
from json import loads from json import loads
@ -48,10 +50,10 @@ def response(resp):
search_results = loads(resp.text) search_results = loads(resp.text)
# return empty array if there are no results # return empty array if there are no results
if not 'photos' in search_results: if 'photos' not in search_results:
return [] return []
if not 'photo' in search_results['photos']: if 'photo' not in search_results['photos']:
return [] return []
photos = search_results['photos']['photo'] photos = search_results['photos']['photo']

41
sources/searx/engines/flickr_noapi.py
View File

@ -1,14 +1,16 @@
#!/usr/bin/env python #!/usr/bin/env python
# Flickr (Images) """
# Flickr (Images)
# @website https://www.flickr.com
# @provide-api yes (https://secure.flickr.com/services/api/flickr.photos.search.html) @website https://www.flickr.com
# @provide-api yes (https://secure.flickr.com/services/api/flickr.photos.search.html)
# @using-api no
# @results HTML @using-api no
# @stable no @results HTML
# @parse url, title, thumbnail, img_src @stable no
@parse url, title, thumbnail, img_src
"""
from urllib import urlencode from urllib import urlencode
from json import loads from json import loads
@ -20,10 +22,10 @@ logger = logger.getChild('flickr-noapi')
categories = ['images'] categories = ['images']
url = 'https://secure.flickr.com/' url = 'https://www.flickr.com/'
search_url = url + 'search/?{query}&page={page}' search_url = url + 'search?{query}&page={page}'
photo_url = 'https://www.flickr.com/photos/{userid}/{photoid}' photo_url = 'https://www.flickr.com/photos/{userid}/{photoid}'
regex = re.compile(r"\"search-photos-models\",\"photos\":(.*}),\"totalItems\":", re.DOTALL) regex = re.compile(r"\"search-photos-lite-models\",\"photos\":(.*}),\"totalItems\":", re.DOTALL)
image_sizes = ('o', 'k', 'h', 'b', 'c', 'z', 'n', 'm', 't', 'q', 's') image_sizes = ('o', 'k', 'h', 'b', 'c', 'z', 'n', 'm', 't', 'q', 's')
paging = True paging = True
@ -36,6 +38,7 @@ def build_flickr_url(user_id, photo_id):
def request(query, params): def request(query, params):
params['url'] = search_url.format(query=urlencode({'text': query}), params['url'] = search_url.format(query=urlencode({'text': query}),
page=params['pageno']) page=params['pageno'])
return params return params
@ -73,10 +76,10 @@ def response(resp):
logger.debug('cannot find valid image size: {0}'.format(repr(photo))) logger.debug('cannot find valid image size: {0}'.format(repr(photo)))
continue continue
if 'id' not in photo['owner']: if 'ownerNsid' not in photo:
continue continue
# For a bigger thumbnail, keep only the url_z, not the url_n # For a bigger thumbnail, keep only the url_z, not the url_n
if 'n' in photo['sizes']: if 'n' in photo['sizes']:
thumbnail_src = photo['sizes']['n']['url'] thumbnail_src = photo['sizes']['n']['url']
elif 'z' in photo['sizes']: elif 'z' in photo['sizes']:
@ -84,20 +87,14 @@ def response(resp):
else: else:
thumbnail_src = img_src thumbnail_src = img_src
url = build_flickr_url(photo['owner']['id'], photo['id']) url = build_flickr_url(photo['ownerNsid'], photo['id'])
title = photo.get('title', '') title = photo.get('title', '')
content = '<span class="photo-author">' +\ content = '<span class="photo-author">' +\
photo['owner']['username'] +\ photo['username'] +\
'</span><br />' '</span><br />'
if 'description' in photo:
content = content +\
'<span class="description">' +\
photo['description'] +\
'</span>'
# append result # append result
results.append({'url': url, results.append({'url': url,
'title': title, 'title': title,

24
sources/searx/engines/generalfile.py
View File

@ -1,14 +1,16 @@
## General Files (Files) """
# General Files (Files)
# @website http://www.general-files.org
# @provide-api no (nothing found) @website http://www.general-files.org
# @provide-api no (nothing found)
# @using-api no (because nothing found)
# @results HTML (using search portal) @using-api no (because nothing found)
# @stable no (HTML can change) @results HTML (using search portal)
# @parse url, title, content @stable no (HTML can change)
# @parse url, title, content
# @todo detect torrents?
@todo detect torrents?
"""
from lxml import html from lxml import html

22
sources/searx/engines/gigablast.py
View File

@ -1,12 +1,14 @@
## Gigablast (Web) """
# Gigablast (Web)
# @website http://gigablast.com
# @provide-api yes (http://gigablast.com/api.html) @website http://gigablast.com
# @provide-api yes (http://gigablast.com/api.html)
# @using-api yes
# @results XML @using-api yes
# @stable yes @results XML
# @parse url, title, content @stable yes
@parse url, title, content
"""
from urllib import urlencode from urllib import urlencode
from cgi import escape from cgi import escape
@ -17,7 +19,7 @@ categories = ['general']
paging = True paging = True
number_of_results = 5 number_of_results = 5
# search-url # search-url, invalid HTTPS certificate
base_url = 'http://gigablast.com/' base_url = 'http://gigablast.com/'
search_string = 'search?{query}&n={number_of_results}&s={offset}&xml=1&qh=0' search_string = 'search?{query}&n={number_of_results}&s={offset}&xml=1&qh=0'

22
sources/searx/engines/github.py
View File

@ -1,12 +1,14 @@
## Github (It) """
# Github (It)
# @website https://github.com/
# @provide-api yes (https://developer.github.com/v3/) @website https://github.com/
# @provide-api yes (https://developer.github.com/v3/)
# @using-api yes
# @results JSON @using-api yes
# @stable yes (using api) @results JSON
# @parse url, title, content @stable yes (using api)
@parse url, title, content
"""
from urllib import urlencode from urllib import urlencode
from json import loads from json import loads
@ -37,7 +39,7 @@ def response(resp):
search_res = loads(resp.text) search_res = loads(resp.text)
# check if items are recieved # check if items are recieved
if not 'items' in search_res: if 'items' not in search_res:
return [] return []
# parse results # parse results

272
sources/searx/engines/google.py
View File

@ -8,39 +8,126 @@
# @stable no (HTML can change) # @stable no (HTML can change)
# @parse url, title, content, suggestion # @parse url, title, content, suggestion
import re
from urllib import urlencode from urllib import urlencode
from urlparse import urlparse, parse_qsl from urlparse import urlparse, parse_qsl
from lxml import html from lxml import html
from searx.poolrequests import get from searx.poolrequests import get
from searx.engines.xpath import extract_text, extract_url from searx.engines.xpath import extract_text, extract_url
# engine dependent config # engine dependent config
categories = ['general'] categories = ['general']
paging = True paging = True
language_support = True language_support = True
use_locale_domain = True
# based on https://en.wikipedia.org/wiki/List_of_Google_domains and tests
default_hostname = 'www.google.com'
country_to_hostname = {
'BG': 'www.google.bg', # Bulgaria
'CZ': 'www.google.cz', # Czech Republic
'DE': 'www.google.de', # Germany
'DK': 'www.google.dk', # Denmark
'AT': 'www.google.at', # Austria
'CH': 'www.google.ch', # Switzerland
'GR': 'www.google.gr', # Greece
'AU': 'www.google.com.au', # Australia
'CA': 'www.google.ca', # Canada
'GB': 'www.google.co.uk', # United Kingdom
'ID': 'www.google.co.id', # Indonesia
'IE': 'www.google.ie', # Ireland
'IN': 'www.google.co.in', # India
'MY': 'www.google.com.my', # Malaysia
'NZ': 'www.google.co.nz', # New Zealand
'PH': 'www.google.com.ph', # Philippines
'SG': 'www.google.com.sg', # Singapore
# 'US': 'www.google.us', # United State, redirect to .com
'ZA': 'www.google.co.za', # South Africa
'AR': 'www.google.com.ar', # Argentina
'CL': 'www.google.cl', # Chile
'ES': 'www.google.es', # Span
'MX': 'www.google.com.mx', # Mexico
'EE': 'www.google.ee', # Estonia
'FI': 'www.google.fi', # Finland
'BE': 'www.google.be', # Belgium
'FR': 'www.google.fr', # France
'IL': 'www.google.co.il', # Israel
'HR': 'www.google.hr', # Croatia
'HU': 'www.google.hu', # Hungary
'IT': 'www.google.it', # Italy
'JP': 'www.google.co.jp', # Japan
'KR': 'www.google.co.kr', # South Korean
'LT': 'www.google.lt', # Lithuania
'LV': 'www.google.lv', # Latvia
'NO': 'www.google.no', # Norway
'NL': 'www.google.nl', # Netherlands
'PL': 'www.google.pl', # Poland
'BR': 'www.google.com.br', # Brazil
'PT': 'www.google.pt', # Portugal
'RO': 'www.google.ro', # Romania
'RU': 'www.google.ru', # Russia
'SK': 'www.google.sk', # Slovakia
'SL': 'www.google.si', # Slovenia (SL -> si)
'SE': 'www.google.se', # Sweden
'TH': 'www.google.co.th', # Thailand
'TR': 'www.google.com.tr', # Turkey
'UA': 'www.google.com.ua', # Ikraine
# 'CN': 'www.google.cn', # China, only from china ?
'HK': 'www.google.com.hk', # Hong kong
'TW': 'www.google.com.tw' # Taiwan
}
# osm
url_map = 'https://www.openstreetmap.org/'\
+ '?lat={latitude}&lon={longitude}&zoom={zoom}&layers=M'
# search-url # search-url
google_hostname = 'www.google.com'
search_path = '/search' search_path = '/search'
redirect_path = '/url' search_url = ('https://{hostname}' +
images_path = '/images'
search_url = ('https://' +
google_hostname +
search_path + search_path +
'?{query}&start={offset}&gbv=1') '?{query}&start={offset}&gbv=1')
# other URLs
map_hostname_start = 'maps.google.'
maps_path = '/maps'
redirect_path = '/url'
images_path = '/images'
# specific xpath variables # specific xpath variables
results_xpath = '//li[@class="g"]' results_xpath = '//li[@class="g"]'
url_xpath = './/h3/a/@href' url_xpath = './/h3/a/@href'
title_xpath = './/h3' title_xpath = './/h3'
content_xpath = './/span[@class="st"]' content_xpath = './/span[@class="st"]'
content_misc_xpath = './/div[@class="f slp"]'
suggestion_xpath = '//p[@class="_Bmc"]' suggestion_xpath = '//p[@class="_Bmc"]'
# map : detail location
map_address_xpath = './/div[@class="s"]//table//td[2]/span/text()'
map_phone_xpath = './/div[@class="s"]//table//td[2]/span/span'
map_website_url_xpath = 'h3[2]/a/@href'
map_website_title_xpath = 'h3[2]'
# map : near the location
map_near = 'table[@class="ts"]//tr'
map_near_title = './/h4'
map_near_url = './/h4/a/@href'
map_near_phone = './/span[@class="nobr"]'
# images
images_xpath = './/div/a' images_xpath = './/div/a'
image_url_xpath = './@href' image_url_xpath = './@href'
image_img_src_xpath = './img/@src' image_img_src_xpath = './img/@src'
# property names
# FIXME : no translation
property_address = "Address"
property_phone = "Phone number"
# cookies
pref_cookie = '' pref_cookie = ''
nid_cookie = {}
# see https://support.google.com/websearch/answer/873?hl=en # see https://support.google.com/websearch/answer/873?hl=en
@ -52,8 +139,21 @@ def get_google_pref_cookie():
return pref_cookie return pref_cookie
def get_google_nid_cookie(google_hostname):
global nid_cookie
if google_hostname not in nid_cookie:
resp = get('https://' + google_hostname)
nid_cookie[google_hostname] = resp.cookies.get("NID", None)
return nid_cookie[google_hostname]
# remove google-specific tracking-url # remove google-specific tracking-url
def parse_url(url_string): def parse_url(url_string, google_hostname):
# sanity check
if url_string is None:
return url_string
# normal case
parsed_url = urlparse(url_string) parsed_url = urlparse(url_string)
if (parsed_url.netloc in [google_hostname, ''] if (parsed_url.netloc in [google_hostname, '']
and parsed_url.path == redirect_path): and parsed_url.path == redirect_path):
@ -63,20 +163,45 @@ def parse_url(url_string):
return url_string return url_string
# returns extract_text on the first result selected by the xpath or None
def extract_text_from_dom(result, xpath):
r = result.xpath(xpath)
if len(r) > 0:
return extract_text(r[0])
return None
# do search-request # do search-request
def request(query, params): def request(query, params):
offset = (params['pageno'] - 1) * 10 offset = (params['pageno'] - 1) * 10
if params['language'] == 'all': if params['language'] == 'all':
language = 'en' language = 'en'
country = 'US'
else: else:
language = params['language'].replace('_', '-').lower() language_array = params['language'].lower().split('_')
if len(language_array) == 2:
country = language_array[1]
else:
country = 'US'
language = language_array[0] + ',' + language_array[0] + '-' + country
if use_locale_domain:
google_hostname = country_to_hostname.get(country.upper(), default_hostname)
else:
google_hostname = default_hostname
params['url'] = search_url.format(offset=offset, params['url'] = search_url.format(offset=offset,
query=urlencode({'q': query})) query=urlencode({'q': query}),
hostname=google_hostname)
params['headers']['Accept-Language'] = language params['headers']['Accept-Language'] = language
params['cookies']['PREF'] = get_google_pref_cookie() params['headers']['Accept'] = 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8'
if google_hostname == default_hostname:
params['cookies']['PREF'] = get_google_pref_cookie()
params['cookies']['NID'] = get_google_nid_cookie(google_hostname)
params['google_hostname'] = google_hostname
return params return params
@ -85,33 +210,63 @@ def request(query, params):
def response(resp): def response(resp):
results = [] results = []
# detect google sorry
resp_url = urlparse(resp.url)
if resp_url.netloc == 'sorry.google.com' or resp_url.path == '/sorry/IndexRedirect':
raise RuntimeWarning('sorry.google.com')
# which hostname ?
google_hostname = resp.search_params.get('google_hostname')
google_url = "https://" + google_hostname
# convert the text to dom
dom = html.fromstring(resp.text) dom = html.fromstring(resp.text)
# parse results # parse results
for result in dom.xpath(results_xpath): for result in dom.xpath(results_xpath):
title = extract_text(result.xpath(title_xpath)[0]) title = extract_text(result.xpath(title_xpath)[0])
try: try:
url = parse_url(extract_url(result.xpath(url_xpath), search_url)) url = parse_url(extract_url(result.xpath(url_xpath), google_url), google_hostname)
parsed_url = urlparse(url) parsed_url = urlparse(url, google_hostname)
if (parsed_url.netloc == google_hostname
and parsed_url.path == search_path): # map result
# remove the link to google news if ((parsed_url.netloc == google_hostname and parsed_url.path.startswith(maps_path))
continue or (parsed_url.netloc.startswith(map_hostname_start))):
x = result.xpath(map_near)
if len(x) > 0:
# map : near the location
results = results + parse_map_near(parsed_url, x, google_hostname)
else:
# map : detail about a location
results = results + parse_map_detail(parsed_url, result, google_hostname)
# google news
elif (parsed_url.netloc == google_hostname
and parsed_url.path == search_path):
# skipping news results
pass
# images result # images result
if (parsed_url.netloc == google_hostname elif (parsed_url.netloc == google_hostname
and parsed_url.path == images_path): and parsed_url.path == images_path):
# only thumbnail image provided, # only thumbnail image provided,
# so skipping image results # so skipping image results
# results = results + parse_images(result) # results = results + parse_images(result, google_hostname)
pass pass
else: else:
# normal result # normal result
content = extract_text(result.xpath(content_xpath)[0]) content = extract_text_from_dom(result, content_xpath)
if content is None:
continue
content_misc = extract_text_from_dom(result, content_misc_xpath)
if content_misc is not None:
content = content_misc + "<br />" + content
# append result # append result
results.append({'url': url, results.append({'url': url,
'title': title, 'title': title,
'content': content}) 'content': content
})
except: except:
continue continue
@ -124,10 +279,10 @@ def response(resp):
return results return results
def parse_images(result): def parse_images(result, google_hostname):
results = [] results = []
for image in result.xpath(images_xpath): for image in result.xpath(images_xpath):
url = parse_url(extract_text(image.xpath(image_url_xpath)[0])) url = parse_url(extract_text(image.xpath(image_url_xpath)[0]), google_hostname)
img_src = extract_text(image.xpath(image_img_src_xpath)[0]) img_src = extract_text(image.xpath(image_img_src_xpath)[0])
# append result # append result
@ -135,6 +290,77 @@ def parse_images(result):
'title': '', 'title': '',
'content': '', 'content': '',
'img_src': img_src, 'img_src': img_src,
'template': 'images.html'}) 'template': 'images.html'
})
return results return results
def parse_map_near(parsed_url, x, google_hostname):
results = []
for result in x:
title = extract_text_from_dom(result, map_near_title)
url = parse_url(extract_text_from_dom(result, map_near_url), google_hostname)
attributes = []
phone = extract_text_from_dom(result, map_near_phone)
add_attributes(attributes, property_phone, phone, 'tel:' + phone)
results.append({'title': title,
'url': url,
'content': attributes_to_html(attributes)
})
return results
def parse_map_detail(parsed_url, result, google_hostname):
results = []
# try to parse the geoloc
m = re.search('@([0-9\.]+),([0-9\.]+),([0-9]+)', parsed_url.path)
if m is None:
m = re.search('ll\=([0-9\.]+),([0-9\.]+)\&z\=([0-9]+)', parsed_url.query)
if m is not None:
# geoloc found (ignored)
lon = float(m.group(2)) # noqa
lat = float(m.group(1)) # noqa
zoom = int(m.group(3)) # noqa
# attributes
attributes = []
address = extract_text_from_dom(result, map_address_xpath)
phone = extract_text_from_dom(result, map_phone_xpath)
add_attributes(attributes, property_address, address, 'geo:' + str(lat) + ',' + str(lon))
add_attributes(attributes, property_phone, phone, 'tel:' + phone)
# title / content / url
website_title = extract_text_from_dom(result, map_website_title_xpath)
content = extract_text_from_dom(result, content_xpath)
website_url = parse_url(extract_text_from_dom(result, map_website_url_xpath), google_hostname)
# add a result if there is a website
if website_url is not None:
results.append({'title': website_title,
'content': (content + '<br />' if content is not None else '')
+ attributes_to_html(attributes),
'url': website_url
})
return results
def add_attributes(attributes, name, value, url):
if value is not None and len(value) > 0:
attributes.append({'label': name, 'value': value, 'url': url})
def attributes_to_html(attributes):
retval = '<table class="table table-striped">'
for a in attributes:
value = a.get('value')
if 'url' in a:
value = '<a href="' + a.get('url') + '">' + value + '</a>'
retval = retval + '<tr><th>' + a.get('label') + '</th><td>' + value + '</td></tr>'
retval = retval + '</table>'
return retval

25
sources/searx/engines/google_images.py
View File

@ -1,13 +1,15 @@
## Google (Images) """
# Google (Images)
# @website https://www.google.com
# @provide-api yes (https://developers.google.com/web-search/docs/), @website https://www.google.com
# deprecated! @provide-api yes (https://developers.google.com/web-search/docs/),
# deprecated!
# @using-api yes
# @results JSON @using-api yes
# @stable yes (but deprecated) @results JSON
# @parse url, title, img_src @stable yes (but deprecated)
@parse url, title, img_src
"""
from urllib import urlencode, unquote from urllib import urlencode, unquote
from json import loads from json import loads
@ -56,6 +58,9 @@ def response(resp):
continue continue
thumbnail_src = result['tbUrl'] thumbnail_src = result['tbUrl']
# http to https
thumbnail_src = thumbnail_src.replace("http://", "https://")
# append result # append result
results.append({'url': href, results.append({'url': href,
'title': title, 'title': title,

22
sources/searx/engines/google_news.py
View File

@ -1,13 +1,15 @@
## Google (News) """
# Google (News)
# @website https://www.google.com
# @provide-api yes (https://developers.google.com/web-search/docs/), @website https://www.google.com
# deprecated! @provide-api yes (https://developers.google.com/web-search/docs/),
# deprecated!
# @using-api yes
# @results JSON @using-api yes
# @stable yes (but deprecated) @results JSON
# @parse url, title, content, publishedDate @stable yes (but deprecated)
@parse url, title, content, publishedDate
"""
from urllib import urlencode from urllib import urlencode
from json import loads from json import loads

2
sources/searx/engines/json_engine.py
View File

@ -6,7 +6,7 @@ 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):

24
sources/searx/engines/kickass.py
View File

@ -1,12 +1,14 @@
## Kickass Torrent (Videos, Music, Files) """
# Kickass Torrent (Videos, Music, Files)
# @website https://kickass.so
# @provide-api no (nothing found) @website https://kickass.so
# @provide-api no (nothing found)
# @using-api no
# @results HTML (using search portal) @using-api no
# @stable yes (HTML can change) @results HTML (using search portal)
# @parse url, title, content, seed, leech, magnetlink @stable yes (HTML can change)
@parse url, title, content, seed, leech, magnetlink
"""
from urlparse import urljoin from urlparse import urljoin
from cgi import escape from cgi import escape
@ -34,10 +36,6 @@ def request(query, params):
params['url'] = search_url.format(search_term=quote(query), params['url'] = search_url.format(search_term=quote(query),
pageno=params['pageno']) pageno=params['pageno'])
# FIX: SSLError: hostname 'kickass.so'
# doesn't match either of '*.kickass.to', 'kickass.to'
params['verify'] = False
return params return params

24
sources/searx/engines/mediawiki.py
View File

@ -1,14 +1,16 @@
## general mediawiki-engine (Web) """
# general mediawiki-engine (Web)
# @website websites built on mediawiki (https://www.mediawiki.org)
# @provide-api yes (http://www.mediawiki.org/wiki/API:Search) @website websites built on mediawiki (https://www.mediawiki.org)
# @provide-api yes (http://www.mediawiki.org/wiki/API:Search)
# @using-api yes
# @results JSON @using-api yes
# @stable yes @results JSON
# @parse url, title @stable yes
# @parse url, title
# @todo content
@todo content
"""
from json import loads from json import loads
from string import Formatter from string import Formatter

22
sources/searx/engines/mixcloud.py
View File

@ -1,12 +1,14 @@
## Mixcloud (Music) """
# Mixcloud (Music)
# @website https://http://www.mixcloud.com/
# @provide-api yes (http://www.mixcloud.com/developers/ @website https://http://www.mixcloud.com/
# @provide-api yes (http://www.mixcloud.com/developers/
# @using-api yes
# @results JSON @using-api yes
# @stable yes @results JSON
# @parse url, title, content, embedded, publishedDate @stable yes
@parse url, title, content, embedded, publishedDate
"""
from json import loads from json import loads
from urllib import urlencode from urllib import urlencode
@ -17,7 +19,7 @@ categories = ['music']
paging = True paging = True
# search-url # search-url
url = 'http://api.mixcloud.com/' url = 'https://api.mixcloud.com/'
search_url = url + 'search/?{query}&type=cloudcast&limit=10&offset={offset}' search_url = url + 'search/?{query}&type=cloudcast&limit=10&offset={offset}'
embedded_url = '<iframe scrolling="no" frameborder="0" allowTransparency="true" ' +\ embedded_url = '<iframe scrolling="no" frameborder="0" allowTransparency="true" ' +\

20
sources/searx/engines/openstreetmap.py
View File

@ -1,12 +1,14 @@
## OpenStreetMap (Map) """
# OpenStreetMap (Map)
# @website https://openstreetmap.org/
# @provide-api yes (http://wiki.openstreetmap.org/wiki/Nominatim) @website https://openstreetmap.org/
# @provide-api yes (http://wiki.openstreetmap.org/wiki/Nominatim)
# @using-api yes
# @results JSON @using-api yes
# @stable yes @results JSON
# @parse url, title @stable yes
@parse url, title
"""
from json import loads from json import loads
from searx.utils import searx_useragent from searx.utils import searx_useragent

23
sources/searx/engines/photon.py
View File

@ -1,12 +1,14 @@
## Photon (Map) """
# Photon (Map)
# @website https://photon.komoot.de
# @provide-api yes (https://photon.komoot.de/) @website https://photon.komoot.de
# @provide-api yes (https://photon.komoot.de/)
# @using-api yes
# @results JSON @using-api yes
# @stable yes @results JSON
# @parse url, title @stable yes
@parse url, title
"""
from urllib import urlencode from urllib import urlencode
from json import loads from json import loads
@ -41,9 +43,6 @@ def request(query, params):
# using searx User-Agent # using searx User-Agent
params['headers']['User-Agent'] = searx_useragent() params['headers']['User-Agent'] = searx_useragent()
# FIX: SSLError: SSL3_GET_SERVER_CERTIFICATE:certificate verify failed
params['verify'] = False
return params return params

10
sources/searx/engines/piratebay.py
View File

@ -1,4 +1,4 @@
## Piratebay (Videos, Music, Files) # Piratebay (Videos, Music, Files)
# #
# @website https://thepiratebay.se # @website https://thepiratebay.se
# @provide-api no (nothing found) # @provide-api no (nothing found)
@ -78,7 +78,11 @@ def response(resp):
leech = 0 leech = 0
magnetlink = result.xpath(magnet_xpath)[0] magnetlink = result.xpath(magnet_xpath)[0]
torrentfile = result.xpath(torrent_xpath)[0] torrentfile_links = result.xpath(torrent_xpath)
if torrentfile_links:
torrentfile_link = torrentfile_links[0].attrib.get('href')
else:
torrentfile_link = None
# append result # append result
results.append({'url': href, results.append({'url': href,
@ -87,7 +91,7 @@ def response(resp):
'seed': seed, 'seed': seed,
'leech': leech, 'leech': leech,
'magnetlink': magnetlink.attrib.get('href'), 'magnetlink': magnetlink.attrib.get('href'),
'torrentfile': torrentfile.attrib.get('href'), 'torrentfile': torrentfile_link,
'template': 'torrent.html'}) 'template': 'torrent.html'})
# return results sorted by seeder # return results sorted by seeder

98
sources/searx/engines/qwant.py Normal file
View File

@ -0,0 +1,98 @@
"""
Qwant (Web, Images, News, Social)
@website https://qwant.com/
@provide-api not officially (https://api.qwant.com/api/search/)
@using-api yes
@results JSON
@stable yes
@parse url, title, content
"""
from urllib import urlencode
from json import loads
from datetime import datetime
# engine dependent config
categories = None
paging = True
language_support = True
category_to_keyword = {'general': 'web',
'images': 'images',
'news': 'news',
'social media': 'social'}
# search-url
url = 'https://api.qwant.com/api/search/{keyword}?count=10&offset={offset}&f=&{query}'
# do search-request
def request(query, params):
offset = (params['pageno'] - 1) * 10
if categories[0] and categories[0] in category_to_keyword:
params['url'] = url.format(keyword=category_to_keyword[categories[0]],
query=urlencode({'q': query}),
offset=offset)
else:
params['url'] = url.format(keyword='web',
query=urlencode({'q': query}),
offset=offset)
# add language tag if specified
if params['language'] != 'all':
params['url'] += '&locale=' + params['language'].lower()
return params
# get response from search-request
def response(resp):
results = []
search_results = loads(resp.text)
# return empty array if there are no results
if 'data' not in search_results:
return []
data = search_results.get('data', {})
res = data.get('result', {})
# parse results
for result in res.get('items', {}):
title = result['title']
res_url = result['url']
content = result['desc']
if category_to_keyword.get(categories[0], '') == 'web':
results.append({'title': title,
'content': content,
'url': res_url})
elif category_to_keyword.get(categories[0], '') == 'images':
thumbnail_src = result['thumbnail']
img_src = result['media']
results.append({'template': 'images.html',
'url': res_url,
'title': title,
'content': '',
'thumbnail_src': thumbnail_src,
'img_src': img_src})
elif (category_to_keyword.get(categories[0], '') == 'news' or
category_to_keyword.get(categories[0], '') == 'social'):
published_date = datetime.fromtimestamp(result['date'], None)
results.append({'url': res_url,
'title': title,
'publishedDate': published_date,
'content': content})
# return results
return results

25
sources/searx/engines/searchcode_code.py
View File

@ -1,12 +1,14 @@
## Searchcode (It) """
# Searchcode (It)
# @website https://searchcode.com/
# @provide-api yes (https://searchcode.com/api/) @website https://searchcode.com/
# @provide-api yes (https://searchcode.com/api/)
# @using-api yes
# @results JSON @using-api yes
# @stable yes @results JSON
# @parse url, title, content @stable yes
@parse url, title, content
"""
from urllib import urlencode from urllib import urlencode
from json import loads from json import loads
@ -32,6 +34,11 @@ def request(query, params):
params['url'] = search_url.format(query=urlencode({'q': query}), params['url'] = search_url.format(query=urlencode({'q': query}),
pageno=params['pageno']-1) pageno=params['pageno']-1)
# Disable SSL verification
# error: (60) SSL certificate problem: unable to get local issuer
# certificate
params['verify'] = False
return params return params

25
sources/searx/engines/searchcode_doc.py
View File

@ -1,12 +1,14 @@
## Searchcode (It) """
# Searchcode (It)
# @website https://searchcode.com/
# @provide-api yes (https://searchcode.com/api/) @website https://searchcode.com/
# @provide-api yes (https://searchcode.com/api/)
# @using-api yes
# @results JSON @using-api yes
# @stable yes @results JSON
# @parse url, title, content @stable yes
@parse url, title, content
"""
from urllib import urlencode from urllib import urlencode
from json import loads from json import loads
@ -25,6 +27,11 @@ def request(query, params):
params['url'] = search_url.format(query=urlencode({'q': query}), params['url'] = search_url.format(query=urlencode({'q': query}),
pageno=params['pageno']-1) pageno=params['pageno']-1)
# Disable SSL verification
# error: (60) SSL certificate problem: unable to get local issuer
# certificate
params['verify'] = False
return params return params

20
sources/searx/engines/soundcloud.py
View File

@ -1,12 +1,14 @@
## Soundcloud (Music) """
# Soundcloud (Music)
# @website https://soundcloud.com
# @provide-api yes (https://developers.soundcloud.com/) @website https://soundcloud.com
# @provide-api yes (https://developers.soundcloud.com/)
# @using-api yes
# @results JSON @using-api yes
# @stable yes @results JSON
# @parse url, title, content, publishedDate, embedded @stable yes
@parse url, title, content, publishedDate, embedded
"""
from json import loads from json import loads
from urllib import urlencode, quote_plus from urllib import urlencode, quote_plus

62
sources/searx/engines/spotify.py Normal file
View File

@ -0,0 +1,62 @@
"""
Spotify (Music)
@website https://spotify.com
@provide-api yes (https://developer.spotify.com/web-api/search-item/)
@using-api yes
@results JSON
@stable yes
@parse url, title, content, embedded
"""
from json import loads
from urllib import urlencode
# engine dependent config
categories = ['music']
paging = True
# search-url
url = 'https://api.spotify.com/'
search_url = url + 'v1/search?{query}&type=track&offset={offset}'
embedded_url = '<iframe data-src="https://embed.spotify.com/?uri=spotify:track:{audioid}"\
width="300" height="80" frameborder="0" allowtransparency="true"></iframe>'
# do search-request
def request(query, params):
offset = (params['pageno'] - 1) * 20
params['url'] = search_url.format(query=urlencode({'q': query}),
offset=offset)
return params
# get response from search-request
def response(resp):
results = []
search_res = loads(resp.text)
# parse results
for result in search_res.get('tracks', {}).get('items', {}):
if result['type'] == 'track':
title = result['name']
url = result['external_urls']['spotify']
content = result['artists'][0]['name'] +\
" &bull; " +\
result['album']['name'] +\
" &bull; " + result['name']
embedded = embedded_url.format(audioid=result['id'])
# append result
results.append({'url': url,
'title': title,
'embedded': embedded,
'content': content})
# return results
return results

22
sources/searx/engines/stackoverflow.py
View File

@ -1,12 +1,14 @@
## Stackoverflow (It) """
# Stackoverflow (It)
# @website https://stackoverflow.com/
# @provide-api not clear (https://api.stackexchange.com/docs/advanced-search) @website https://stackoverflow.com/
# @provide-api not clear (https://api.stackexchange.com/docs/advanced-search)
# @using-api no
# @results HTML @using-api no
# @stable no (HTML can change) @results HTML
# @parse url, title, content @stable no (HTML can change)
@parse url, title, content
"""
from urlparse import urljoin from urlparse import urljoin
from cgi import escape from cgi import escape
@ -19,7 +21,7 @@ categories = ['it']
paging = True paging = True
# search-url # search-url
url = 'http://stackoverflow.com/' url = 'https://stackoverflow.com/'
search_url = url+'search?{query}&page={pageno}' search_url = url+'search?{query}&page={pageno}'
# specific xpath variables # specific xpath variables

10
sources/searx/engines/startpage.py
View File

@ -66,7 +66,15 @@ def response(resp):
url = link.attrib.get('href') url = link.attrib.get('href')
# block google-ad url's # block google-ad url's
if re.match("^http(s|)://www.google.[a-z]+/aclk.*$", url): if re.match("^http(s|)://(www\.)?google\.[a-z]+/aclk.*$", url):
continue
# block startpage search url's
if re.match("^http(s|)://(www\.)?startpage\.com/do/search\?.*$", url):
continue
# block ixquick search url's
if re.match("^http(s|)://(www\.)?ixquick\.com/do/search\?.*$", url):
continue continue
title = escape(extract_text(link)) title = escape(extract_text(link))

20
sources/searx/engines/subtitleseeker.py
View File

@ -1,12 +1,14 @@
## Subtitleseeker (Video) """
# Subtitleseeker (Video)
# @website http://www.subtitleseeker.com
# @provide-api no @website http://www.subtitleseeker.com
# @provide-api no
# @using-api no
# @results HTML @using-api no
# @stable no (HTML can change) @results HTML
# @parse url, title, content @stable no (HTML can change)
@parse url, title, content
"""
from cgi import escape from cgi import escape
from urllib import quote_plus from urllib import quote_plus

108
sources/searx/engines/swisscows.py Normal file
View File

@ -0,0 +1,108 @@
"""
Swisscows (Web, Images)
@website https://swisscows.ch
@provide-api no
@using-api no
@results HTML (using search portal)
@stable no (HTML can change)
@parse url, title, content
"""
from json import loads
from urllib import urlencode, unquote
import re
# engine dependent config
categories = ['general', 'images']
paging = True
language_support = True
# search-url
base_url = 'https://swisscows.ch/'
search_string = '?{query}&page={page}'
# regex
regex_json = re.compile('initialData: {"Request":(.|\n)*},\s*environment')
regex_json_remove_start = re.compile('^initialData:\s*')
regex_json_remove_end = re.compile(',\s*environment$')
regex_img_url_remove_start = re.compile('^https?://i\.swisscows\.ch/\?link=')
# do search-request
def request(query, params):
if params['language'] == 'all':
ui_language = 'browser'
region = 'browser'
else:
region = params['language'].replace('_', '-')
ui_language = params['language'].split('_')[0]
search_path = search_string.format(
query=urlencode({'query': query,
'uiLanguage': ui_language,
'region': region}),
page=params['pageno'])
# image search query is something like 'image?{query}&page={page}'
if params['category'] == 'images':
search_path = 'image' + search_path
params['url'] = base_url + search_path
return params
# get response from search-request
def response(resp):
results = []
json_regex = regex_json.search(resp.content)
# check if results are returned
if not json_regex:
return []
json_raw = regex_json_remove_end.sub('', regex_json_remove_start.sub('', json_regex.group()))
json = loads(json_raw)
# parse results
for result in json['Results'].get('items', []):
result_title = result['Title'].replace(u'\uE000', '').replace(u'\uE001', '')
# parse image results
if result.get('ContentType', '').startswith('image'):
img_url = unquote(regex_img_url_remove_start.sub('', result['Url']))
# append result
results.append({'url': result['SourceUrl'],
'title': result['Title'],
'content': '',
'img_src': img_url,
'template': 'images.html'})
# parse general results
else:
result_url = result['Url'].replace(u'\uE000', '').replace(u'\uE001', '')
result_content = result['Description'].replace(u'\uE000', '').replace(u'\uE001', '')
# append result
results.append({'url': result_url,
'title': result_title,
'content': result_content})
# parse images
for result in json.get('Images', []):
# decode image url
img_url = unquote(regex_img_url_remove_start.sub('', result['Url']))
# append result
results.append({'url': result['SourceUrl'],
'title': result['Title'],
'content': '',
'img_src': img_url,
'template': 'images.html'})
# return results
return results

36
sources/searx/engines/twitter.py
View File

@ -1,14 +1,16 @@
## Twitter (Social media) """
# Twitter (Social media)
# @website https://twitter.com/
# @provide-api yes (https://dev.twitter.com/docs/using-search) @website https://twitter.com/
# @provide-api yes (https://dev.twitter.com/docs/using-search)
# @using-api no
# @results HTML (using search portal) @using-api no
# @stable no (HTML can change) @results HTML (using search portal)
# @parse url, title, content @stable no (HTML can change)
# @parse url, title, content
# @todo publishedDate
@todo publishedDate
"""
from urlparse import urljoin from urlparse import urljoin
from urllib import urlencode from urllib import urlencode
@ -27,8 +29,8 @@ search_url = base_url + 'search?'
# specific xpath variables # specific xpath variables
results_xpath = '//li[@data-item-type="tweet"]' results_xpath = '//li[@data-item-type="tweet"]'
link_xpath = './/small[@class="time"]//a' link_xpath = './/small[@class="time"]//a'
title_xpath = './/span[@class="username js-action-profile-name"]' title_xpath = './/span[contains(@class, "username")]'
content_xpath = './/p[@class="js-tweet-text tweet-text"]' content_xpath = './/p[contains(@class, "tweet-text")]'
timestamp_xpath = './/span[contains(@class,"_timestamp")]' timestamp_xpath = './/span[contains(@class,"_timestamp")]'
@ -53,10 +55,14 @@ def response(resp):
# parse results # parse results
for tweet in dom.xpath(results_xpath): for tweet in dom.xpath(results_xpath):
link = tweet.xpath(link_xpath)[0] try:
link = tweet.xpath(link_xpath)[0]
content = extract_text(tweet.xpath(content_xpath)[0])
except Exception:
continue
url = urljoin(base_url, link.attrib.get('href')) url = urljoin(base_url, link.attrib.get('href'))
title = extract_text(tweet.xpath(title_xpath)) title = extract_text(tweet.xpath(title_xpath))
content = extract_text(tweet.xpath(content_xpath)[0])
pubdate = tweet.xpath(timestamp_xpath) pubdate = tweet.xpath(timestamp_xpath)
if len(pubdate) > 0: if len(pubdate) > 0:

14
sources/searx/engines/vimeo.py
View File

@ -23,15 +23,15 @@ categories = ['videos']
paging = True paging = True
# search-url # search-url
base_url = 'http://vimeo.com' base_url = 'https://vimeo.com'
search_url = base_url + '/search/page:{pageno}?{query}' search_url = base_url + '/search/page:{pageno}?{query}'
# specific xpath variables # specific xpath variables
results_xpath = '//div[@id="browse_content"]/ol/li' results_xpath = '//div[contains(@class,"results_grid")]/ul/li'
url_xpath = './a/@href' url_xpath = './/a/@href'
title_xpath = './a/div[@class="data"]/p[@class="title"]' title_xpath = './/span[@class="title"]'
content_xpath = './a/img/@src' thumbnail_xpath = './/img[@class="js-clip_thumbnail_image"]/@src'
publishedDate_xpath = './/p[@class="meta"]//attribute::datetime' publishedDate_xpath = './/time/attribute::datetime'
embedded_url = '<iframe data-src="//player.vimeo.com/video{videoid}" ' +\ embedded_url = '<iframe data-src="//player.vimeo.com/video{videoid}" ' +\
'width="540" height="304" frameborder="0" ' +\ 'width="540" height="304" frameborder="0" ' +\
@ -58,7 +58,7 @@ def response(resp):
videoid = result.xpath(url_xpath)[0] videoid = result.xpath(url_xpath)[0]
url = base_url + videoid url = base_url + videoid
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(thumbnail_xpath)[0])
publishedDate = parser.parse(extract_text(result.xpath(publishedDate_xpath)[0])) publishedDate = parser.parse(extract_text(result.xpath(publishedDate_xpath)[0]))
embedded = embedded_url.format(videoid=videoid) embedded = embedded_url.format(videoid=videoid)

34
sources/searx/engines/wikidata.py
View File

@ -1,8 +1,15 @@
import json import json
from urllib import urlencode
from searx import logger
from searx.poolrequests import get from searx.poolrequests import get
from searx.utils import format_date_by_locale from searx.utils import format_date_by_locale
from datetime import datetime
from dateutil.parser import parse as dateutil_parse
from urllib import urlencode
logger = logger.getChild('wikidata')
result_count = 1 result_count = 1
wikidata_host = 'https://www.wikidata.org' wikidata_host = 'https://www.wikidata.org'
wikidata_api = wikidata_host + '/w/api.php' wikidata_api = wikidata_host + '/w/api.php'
@ -164,14 +171,12 @@ def getDetail(jsonresponse, wikidata_id, language, locale):
if postal_code is not None: if postal_code is not None:
attributes.append({'label': 'Postal code(s)', 'value': postal_code}) attributes.append({'label': 'Postal code(s)', 'value': postal_code})
date_of_birth = get_time(claims, 'P569', None) date_of_birth = get_time(claims, 'P569', locale, None)
if date_of_birth is not None: if date_of_birth is not None:
date_of_birth = format_date_by_locale(date_of_birth[8:], locale)
attributes.append({'label': 'Date of birth', 'value': date_of_birth}) attributes.append({'label': 'Date of birth', 'value': date_of_birth})
date_of_death = get_time(claims, 'P570', None) date_of_death = get_time(claims, 'P570', locale, None)
if date_of_death is not None: if date_of_death is not None:
date_of_death = format_date_by_locale(date_of_death[8:], locale)
attributes.append({'label': 'Date of death', 'value': date_of_death}) attributes.append({'label': 'Date of death', 'value': date_of_death})
if len(attributes) == 0 and len(urls) == 2 and len(description) == 0: if len(attributes) == 0 and len(urls) == 2 and len(description) == 0:
@ -229,7 +234,7 @@ def get_string(claims, propertyName, defaultValue=None):
return result[0] return result[0]
def get_time(claims, propertyName, defaultValue=None): def get_time(claims, propertyName, locale, defaultValue=None):
propValue = claims.get(propertyName, {}) propValue = claims.get(propertyName, {})
if len(propValue) == 0: if len(propValue) == 0:
return defaultValue return defaultValue
@ -244,9 +249,22 @@ def get_time(claims, propertyName, defaultValue=None):
result.append(value.get('time', '')) result.append(value.get('time', ''))
if len(result) == 0: if len(result) == 0:
return defaultValue date_string = defaultValue
else: else:
return ', '.join(result) date_string = ', '.join(result)
try:
parsed_date = datetime.strptime(date_string, "+%Y-%m-%dT%H:%M:%SZ")
except:
if date_string.startswith('-'):
return date_string.split('T')[0]
try:
parsed_date = dateutil_parse(date_string, fuzzy=False, default=False)
except:
logger.debug('could not parse date %s', date_string)
return date_string.split('T')[0]
return format_date_by_locale(parsed_date, locale)
def get_geolink(claims, propertyName, defaultValue=''): def get_geolink(claims, propertyName, defaultValue=''):

21
sources/searx/engines/www1x.py
View File

@ -1,13 +1,14 @@
## 1x (Images) """
# 1x (Images)
# @website http://1x.com/
# @provide-api no
#
# @using-api no
# @results HTML
# @stable no (HTML can change)
# @parse url, title, thumbnail, img_src, content
@website http://1x.com/
@provide-api no
@using-api no
@results HTML
@stable no (HTML can change)
@parse url, title, thumbnail, img_src, content
"""
from urllib import urlencode from urllib import urlencode
from urlparse import urljoin from urlparse import urljoin
@ -20,7 +21,7 @@ categories = ['images']
paging = False paging = False
# search-url # search-url
base_url = 'http://1x.com' base_url = 'https://1x.com'
search_url = base_url+'/backend/search.php?{query}' search_url = base_url+'/backend/search.php?{query}'

24
sources/searx/engines/www500px.py
View File

@ -1,14 +1,16 @@
## 500px (Images) """
# 500px (Images)
# @website https://500px.com
# @provide-api yes (https://developers.500px.com/) @website https://500px.com
# @provide-api yes (https://developers.500px.com/)
# @using-api no
# @results HTML @using-api no
# @stable no (HTML can change) @results HTML
# @parse url, title, thumbnail, img_src, content @stable no (HTML can change)
# @parse url, title, thumbnail, img_src, content
# @todo rewrite to api
@todo rewrite to api
"""
from urllib import urlencode from urllib import urlencode

2
sources/searx/engines/yacy.py
View File

@ -1,4 +1,4 @@
## Yacy (Web, Images, Videos, Music, Files) # Yacy (Web, Images, Videos, Music, Files)
# #
# @website http://yacy.net # @website http://yacy.net
# @provide-api yes # @provide-api yes

33
sources/searx/engines/yahoo.py
View File

@ -1,13 +1,15 @@
## Yahoo (Web) """
# Yahoo (Web)
# @website https://search.yahoo.com/web
# @provide-api yes (https://developer.yahoo.com/boss/search/), @website https://search.yahoo.com/web
# $0.80/1000 queries @provide-api yes (https://developer.yahoo.com/boss/search/),
# $0.80/1000 queries
# @using-api no (because pricing)
# @results HTML (using search portal) @using-api no (because pricing)
# @stable no (HTML can change) @results HTML (using search portal)
# @parse url, title, content, suggestion @stable no (HTML can change)
@parse url, title, content, suggestion
"""
from urllib import urlencode from urllib import urlencode
from urlparse import unquote from urlparse import unquote
@ -24,11 +26,11 @@ base_url = 'https://search.yahoo.com/'
search_url = 'search?{query}&b={offset}&fl=1&vl=lang_{lang}' search_url = 'search?{query}&b={offset}&fl=1&vl=lang_{lang}'
# specific xpath variables # specific xpath variables
results_xpath = '//div[@class="res"]' results_xpath = "//div[contains(concat(' ', normalize-space(@class), ' '), ' Sr ')]"
url_xpath = './/h3/a/@href' url_xpath = './/h3/a/@href'
title_xpath = './/h3/a' title_xpath = './/h3/a'
content_xpath = './/div[@class="abstr"]' content_xpath = './/div[@class="compText aAbs"]'
suggestion_xpath = '//div[@id="satat"]//a' suggestion_xpath = "//div[contains(concat(' ', normalize-space(@class), ' '), ' AlsoTry ')]//a"
# remove yahoo-specific tracking-url # remove yahoo-specific tracking-url
@ -91,11 +93,12 @@ def response(resp):
'content': content}) 'content': content})
# if no suggestion found, return results # if no suggestion found, return results
if not dom.xpath(suggestion_xpath): suggestions = dom.xpath(suggestion_xpath)
if not suggestions:
return results return results
# parse suggestion # parse suggestion
for suggestion in dom.xpath(suggestion_xpath): for suggestion in suggestions:
# append suggestion # append suggestion
results.append({'suggestion': extract_text(suggestion)}) results.append({'suggestion': extract_text(suggestion)})

25
sources/searx/engines/yahoo_news.py
View File

@ -23,15 +23,15 @@ paging = True
language_support = True language_support = True
# search-url # search-url
search_url = 'https://news.search.yahoo.com/search?{query}&b={offset}&fl=1&vl=lang_{lang}' # noqa search_url = 'https://news.search.yahoo.com/search?{query}&b={offset}&{lang}=uh3_news_web_gs_1&pz=10&xargs=0&vl=lang_{lang}' # noqa
# specific xpath variables # specific xpath variables
results_xpath = '//div[@class="res"]' results_xpath = '//ol[contains(@class,"searchCenterMiddle")]//li'
url_xpath = './/h3/a/@href' url_xpath = './/h3/a/@href'
title_xpath = './/h3/a' title_xpath = './/h3/a'
content_xpath = './/div[@class="abstr"]' content_xpath = './/div[@class="compText"]'
publishedDate_xpath = './/span[@class="timestamp"]' publishedDate_xpath = './/span[contains(@class,"tri")]'
suggestion_xpath = '//div[@id="satat"]//a' suggestion_xpath = '//div[contains(@class,"VerALSOTRY")]//a'
# do search-request # do search-request
@ -48,11 +48,18 @@ def request(query, params):
lang=language) lang=language)
# TODO required? # TODO required?
params['cookies']['sB'] = 'fl=1&vl=lang_{lang}&sh=1&rw=new&v=1'\ params['cookies']['sB'] = '"v=1&vm=p&fl=1&vl=lang_{lang}&sh=1&pn=10&rw=new'\
.format(lang=language) .format(lang=language)
return params return params
def sanitize_url(url):
if ".yahoo.com/" in url:
return re.sub(u"\;\_ylt\=.+$", "", url)
else:
return url
# get response from search-request # get response from search-request
def response(resp): def response(resp):
results = [] results = []
@ -61,13 +68,17 @@ def response(resp):
# parse results # parse results
for result in dom.xpath(results_xpath): for result in dom.xpath(results_xpath):
url = parse_url(extract_url(result.xpath(url_xpath), search_url)) urls = result.xpath(url_xpath)
if len(urls) != 1:
continue
url = sanitize_url(parse_url(extract_url(urls, search_url)))
title = extract_text(result.xpath(title_xpath)[0]) title = extract_text(result.xpath(title_xpath)[0])
content = extract_text(result.xpath(content_xpath)[0]) content = extract_text(result.xpath(content_xpath)[0])
# parse publishedDate # parse publishedDate
publishedDate = extract_text(result.xpath(publishedDate_xpath)[0]) publishedDate = extract_text(result.xpath(publishedDate_xpath)[0])
# still useful ?
if re.match("^[0-9]+ minute(s|) ago$", publishedDate): if re.match("^[0-9]+ minute(s|) ago$", publishedDate):
publishedDate = datetime.now() - timedelta(minutes=int(re.match(r'\d+', publishedDate).group())) # noqa publishedDate = datetime.now() - timedelta(minutes=int(re.match(r'\d+', publishedDate).group())) # noqa
else: else:

48
sources/searx/engines/youtube.py → sources/searx/engines/youtube_api.py
View File

@ -1,7 +1,7 @@
## Youtube (Videos) # Youtube (Videos)
# #
# @website https://www.youtube.com/ # @website https://www.youtube.com/
# @provide-api yes (http://gdata-samples-youtube-search-py.appspot.com/) # @provide-api yes (https://developers.google.com/apis-explorer/#p/youtube/v3/youtube.search.list)
# #
# @using-api yes # @using-api yes
# @results JSON # @results JSON
@ -14,28 +14,29 @@ from dateutil import parser
# engine dependent config # engine dependent config
categories = ['videos', 'music'] categories = ['videos', 'music']
paging = True paging = False
language_support = True language_support = True
api_key = None
# search-url # search-url
base_url = 'https://gdata.youtube.com/feeds/api/videos' base_url = 'https://www.googleapis.com/youtube/v3/search'
search_url = base_url + '?alt=json&{query}&start-index={index}&max-results=5' search_url = base_url + '?part=snippet&{query}&maxResults=20&key={api_key}'
embedded_url = '<iframe width="540" height="304" ' +\ embedded_url = '<iframe width="540" height="304" ' +\
'data-src="//www.youtube-nocookie.com/embed/{videoid}" ' +\ 'data-src="//www.youtube-nocookie.com/embed/{videoid}" ' +\
'frameborder="0" allowfullscreen></iframe>' 'frameborder="0" allowfullscreen></iframe>'
base_youtube_url = 'https://www.youtube.com/watch?v='
# do search-request # do search-request
def request(query, params): def request(query, params):
index = (params['pageno'] - 1) * 5 + 1
params['url'] = search_url.format(query=urlencode({'q': query}), params['url'] = search_url.format(query=urlencode({'q': query}),
index=index) api_key=api_key)
# add language tag if specified # add language tag if specified
if params['language'] != 'all': if params['language'] != 'all':
params['url'] += '&lr=' + params['language'].split('_')[0] params['url'] += '&relevanceLanguage=' + params['language'].split('_')[0]
return params return params
@ -47,36 +48,25 @@ def response(resp):
search_results = loads(resp.text) search_results = loads(resp.text)
# return empty array if there are no results # return empty array if there are no results
if not 'feed' in search_results: if 'items' not in search_results:
return [] return []
feed = search_results['feed']
# parse results # parse results
for result in feed['entry']: for result in search_results['items']:
url = [x['href'] for x in result['link'] if x['type'] == 'text/html'] videoid = result['id']['videoId']
if not url: title = result['snippet']['title']
continue
# remove tracking
url = url[0].replace('feature=youtube_gdata', '')
if url.endswith('&'):
url = url[:-1]
videoid = url[32:]
title = result['title']['$t']
content = '' content = ''
thumbnail = '' thumbnail = ''
pubdate = result['published']['$t'] pubdate = result['snippet']['publishedAt']
publishedDate = parser.parse(pubdate) publishedDate = parser.parse(pubdate)
if 'media$thumbnail' in result['media$group']: thumbnail = result['snippet']['thumbnails']['high']['url']
thumbnail = result['media$group']['media$thumbnail'][0]['url']
content = result['content']['$t'] content = result['snippet']['description']
url = base_youtube_url + videoid
embedded = embedded_url.format(videoid=videoid) embedded = embedded_url.format(videoid=videoid)

81
sources/searx/engines/youtube_noapi.py Normal file
View File

@ -0,0 +1,81 @@
# Youtube (Videos)
#
# @website https://www.youtube.com/
# @provide-api yes (https://developers.google.com/apis-explorer/#p/youtube/v3/youtube.search.list)
#
# @using-api no
# @results HTML
# @stable no
# @parse url, title, content, publishedDate, thumbnail, embedded
from urllib import quote_plus
from lxml import html
from searx.engines.xpath import extract_text
from searx.utils import list_get
# engine dependent config
categories = ['videos', 'music']
paging = True
language_support = False
# search-url
base_url = 'https://www.youtube.com/results'
search_url = base_url + '?search_query={query}&page={page}'
embedded_url = '<iframe width="540" height="304" ' +\
'data-src="//www.youtube-nocookie.com/embed/{videoid}" ' +\
'frameborder="0" allowfullscreen></iframe>'
base_youtube_url = 'https://www.youtube.com/watch?v='
# specific xpath variables
results_xpath = "//ol/li/div[contains(@class, 'yt-lockup yt-lockup-tile yt-lockup-video vve-check')]"
url_xpath = './/h3/a/@href'
title_xpath = './/div[@class="yt-lockup-content"]/h3/a'
content_xpath = './/div[@class="yt-lockup-content"]/div[@class="yt-lockup-description yt-ui-ellipsis yt-ui-ellipsis-2"]'
# returns extract_text on the first result selected by the xpath or None
def extract_text_from_dom(result, xpath):
r = result.xpath(xpath)
if len(r) > 0:
return extract_text(r[0])
return None
# do search-request
def request(query, params):
params['url'] = search_url.format(query=quote_plus(query),
page=params['pageno'])
return params
# get response from search-request
def response(resp):
results = []
dom = html.fromstring(resp.text)
# parse results
for result in dom.xpath(results_xpath):
videoid = list_get(result.xpath('@data-context-item-id'), 0)
if videoid is not None:
url = base_youtube_url + videoid
thumbnail = 'https://i.ytimg.com/vi/' + videoid + '/hqdefault.jpg'
title = extract_text_from_dom(result, title_xpath) or videoid
content = extract_text_from_dom(result, content_xpath)
embedded = embedded_url.format(videoid=videoid)
# append result
results.append({'url': url,
'title': title,
'content': content,
'template': 'videos.html',
'embedded': embedded,
'thumbnail': thumbnail})
# return results
return results

77
sources/searx/plugins/__init__.py Normal file
View File

@ -0,0 +1,77 @@
'''
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) 2015 by Adam Tauber, <asciimoo@gmail.com>
'''
from sys import exit
from searx import logger
logger = logger.getChild('plugins')
from searx.plugins import (https_rewrite,
self_info,
search_on_category_select,
tracker_url_remover)
required_attrs = (('name', str),
('description', str),
('default_on', bool))
optional_attrs = (('js_dependencies', tuple),
('css_dependencies', tuple))
class Plugin():
default_on = False
name = 'Default plugin'
description = 'Default plugin description'
class PluginStore():
def __init__(self):
self.plugins = []
def __iter__(self):
for plugin in self.plugins:
yield plugin
def register(self, *plugins):
for plugin in plugins:
for plugin_attr, plugin_attr_type in required_attrs:
if not hasattr(plugin, plugin_attr) or not isinstance(getattr(plugin, plugin_attr), plugin_attr_type):
logger.critical('missing attribute "{0}", cannot load plugin: {1}'.format(plugin_attr, plugin))
exit(3)
for plugin_attr, plugin_attr_type in optional_attrs:
if not hasattr(plugin, plugin_attr) or not isinstance(getattr(plugin, plugin_attr), plugin_attr_type):
setattr(plugin, plugin_attr, plugin_attr_type())
plugin.id = plugin.name.replace(' ', '_')
self.plugins.append(plugin)
def call(self, plugin_type, request, *args, **kwargs):
ret = True
for plugin in request.user_plugins:
if hasattr(plugin, plugin_type):
ret = getattr(plugin, plugin_type)(request, *args, **kwargs)
if not ret:
break
return ret
plugins = PluginStore()
plugins.register(https_rewrite)
plugins.register(self_info)
plugins.register(search_on_category_select)
plugins.register(tracker_url_remover)

29
sources/searx/https_rewrite.py → sources/searx/plugins/https_rewrite.py
View File

@ -18,11 +18,22 @@ along with searx. If not, see < http://www.gnu.org/licenses/ >.
import re import re
from urlparse import urlparse from urlparse import urlparse
from lxml import etree from lxml import etree
from os import listdir from os import listdir, environ
from os.path import isfile, isdir, join from os.path import isfile, isdir, join
from searx import logger from searx.plugins import logger
from flask.ext.babel import gettext
from searx import searx_dir
name = "HTTPS rewrite"
description = gettext('Rewrite HTTP links to HTTPS if possible')
default_on = True
if 'SEARX_HTTPS_REWRITE_PATH' in environ:
rules_path = environ['SEARX_rules_path']
else:
rules_path = join(searx_dir, 'plugins/https_rules')
logger = logger.getChild("https_rewrite") logger = logger.getChild("https_rewrite")
# https://gitweb.torproject.org/\ # https://gitweb.torproject.org/\
@ -33,7 +44,7 @@ https_rules = []
# load single ruleset from a xml file # load single ruleset from a xml file
def load_single_https_ruleset(filepath): def load_single_https_ruleset(rules_path):
ruleset = () ruleset = ()
# init parser # init parser
@ -41,7 +52,7 @@ def load_single_https_ruleset(filepath):
# load and parse xml-file # load and parse xml-file
try: try:
tree = etree.parse(filepath, parser) tree = etree.parse(rules_path, parser)
except: except:
# TODO, error message # TODO, error message
return () return ()
@ -207,3 +218,13 @@ def https_url_rewrite(result):
# target has matched, do not search over the other rules # target has matched, do not search over the other rules
break break
return result return result
def on_result(request, ctx):
result = ctx['result']
if result['parsed_url'].scheme == 'http':
https_url_rewrite(result)
return True
load_https_rules(rules_path)

0
sources/searx/https_rules/00README → sources/searx/plugins/https_rules/00README
View File

0
sources/searx/https_rules/Bing.xml → sources/searx/plugins/https_rules/Bing.xml
View File

0
sources/searx/https_rules/Dailymotion.xml → sources/searx/plugins/https_rules/Dailymotion.xml
View File

0
sources/searx/https_rules/Deviantart.xml → sources/searx/plugins/https_rules/Deviantart.xml
View File

0
sources/searx/https_rules/DuckDuckGo.xml → sources/searx/plugins/https_rules/DuckDuckGo.xml
View File

0
sources/searx/https_rules/Flickr.xml → sources/searx/plugins/https_rules/Flickr.xml
View File

0
sources/searx/https_rules/Github-Pages.xml → sources/searx/plugins/https_rules/Github-Pages.xml
View File

0
sources/searx/https_rules/Github.xml → sources/searx/plugins/https_rules/Github.xml
View File

0
sources/searx/https_rules/Google-mismatches.xml → sources/searx/plugins/https_rules/Google-mismatches.xml
View File

0
sources/searx/https_rules/Google.org.xml → sources/searx/plugins/https_rules/Google.org.xml
View File

0
sources/searx/https_rules/GoogleAPIs.xml → sources/searx/plugins/https_rules/GoogleAPIs.xml
View File

0
sources/searx/https_rules/GoogleCanada.xml → sources/searx/plugins/https_rules/GoogleCanada.xml
View File

0
sources/searx/https_rules/GoogleImages.xml → sources/searx/plugins/https_rules/GoogleImages.xml
View File

0
sources/searx/https_rules/GoogleMainSearch.xml → sources/searx/plugins/https_rules/GoogleMainSearch.xml
View File

0
sources/searx/https_rules/GoogleMaps.xml → sources/searx/plugins/https_rules/GoogleMaps.xml
View File

0
sources/searx/https_rules/GoogleMelange.xml → sources/searx/plugins/https_rules/GoogleMelange.xml
View File

0
sources/searx/https_rules/GoogleSearch.xml → sources/searx/plugins/https_rules/GoogleSearch.xml
View File

0
sources/searx/https_rules/GoogleServices.xml → sources/searx/plugins/https_rules/GoogleServices.xml
View File

0
sources/searx/https_rules/GoogleShopping.xml → sources/searx/plugins/https_rules/GoogleShopping.xml
View File

0
sources/searx/https_rules/GoogleSorry.xml → sources/searx/plugins/https_rules/GoogleSorry.xml
View File

0
sources/searx/https_rules/GoogleTranslate.xml → sources/searx/plugins/https_rules/GoogleTranslate.xml
View File

0
sources/searx/https_rules/GoogleVideos.xml → sources/searx/plugins/https_rules/GoogleVideos.xml
View File

0
sources/searx/https_rules/GoogleWatchBlog.xml → sources/searx/plugins/https_rules/GoogleWatchBlog.xml
View File

0
sources/searx/https_rules/Google_App_Engine.xml → sources/searx/plugins/https_rules/Google_App_Engine.xml
View File

0
sources/searx/https_rules/Googleplex.com.xml → sources/searx/plugins/https_rules/Googleplex.com.xml
View File

0
sources/searx/https_rules/OpenStreetMap.xml → sources/searx/plugins/https_rules/OpenStreetMap.xml
View File

0
sources/searx/https_rules/Rawgithub.com.xml → sources/searx/plugins/https_rules/Rawgithub.com.xml
View File

0
sources/searx/https_rules/Soundcloud.xml → sources/searx/plugins/https_rules/Soundcloud.xml
View File

0
sources/searx/https_rules/ThePirateBay.xml → sources/searx/plugins/https_rules/ThePirateBay.xml
View File

0
sources/searx/https_rules/Torproject.xml → sources/searx/plugins/https_rules/Torproject.xml
View File

0
sources/searx/https_rules/Twitter.xml → sources/searx/plugins/https_rules/Twitter.xml
View File

0
sources/searx/https_rules/Vimeo.xml → sources/searx/plugins/https_rules/Vimeo.xml
View File

0
sources/searx/https_rules/WikiLeaks.xml → sources/searx/plugins/https_rules/WikiLeaks.xml
View File

0
sources/searx/https_rules/Wikimedia.xml → sources/searx/plugins/https_rules/Wikimedia.xml
View File

0
sources/searx/https_rules/Yahoo.xml → sources/searx/plugins/https_rules/Yahoo.xml
View File

0
sources/searx/https_rules/YouTube.xml → sources/searx/plugins/https_rules/YouTube.xml
View File

23
sources/searx/plugins/search_on_category_select.py Normal file
View File

@ -0,0 +1,23 @@
'''
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) 2015 by Adam Tauber, <asciimoo@gmail.com>
'''
from flask.ext.babel import gettext
name = gettext('Search on category select')
description = gettext('Perform search immediately if a category selected. '
'Disable to select multiple categories. (JavaScript required)')
default_on = True
js_dependencies = ('js/search_on_category_select.js',)

44
sources/searx/plugins/self_info.py Normal file
View File

@ -0,0 +1,44 @@
'''
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) 2015 by Adam Tauber, <asciimoo@gmail.com>
'''
from flask.ext.babel import gettext
import re
name = "Self Informations"
description = gettext('Displays your IP if the query is "ip" and your user agent if the query contains "user agent".')
default_on = True
# Self User Agent regex
p = re.compile('.*user[ -]agent.*', re.IGNORECASE)
# attach callback to the post search hook
# request: flask request object
# ctx: the whole local context of the pre search hook
def post_search(request, ctx):
if ctx['search'].query == 'ip':
x_forwarded_for = request.headers.getlist("X-Forwarded-For")
if x_forwarded_for:
ip = x_forwarded_for[0]
else:
ip = request.remote_addr
ctx['search'].answers.clear()
ctx['search'].answers.add(ip)
elif p.match(ctx['search'].query):
ua = request.user_agent
ctx['search'].answers.clear()
ctx['search'].answers.add(ua)
return True

44
sources/searx/plugins/tracker_url_remover.py Normal file
View File

@ -0,0 +1,44 @@
'''
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) 2015 by Adam Tauber, <asciimoo@gmail.com>
'''
from flask.ext.babel import gettext
import re
from urlparse import urlunparse
regexes = {re.compile(r'utm_[^&]+&?'),
re.compile(r'(wkey|wemail)[^&]+&?'),
re.compile(r'&$')}
name = gettext('Tracker URL remover')
description = gettext('Remove trackers arguments from the returned URL')
default_on = True
def on_result(request, ctx):
query = ctx['result']['parsed_url'].query
if query == "":
return True
for reg in regexes:
query = reg.sub('', query)
if query != ctx['result']['parsed_url'].query:
ctx['result']['parsed_url'] = ctx['result']['parsed_url']._replace(query=query)
ctx['result']['url'] = urlunparse(ctx['result']['parsed_url'])
return True

57
sources/searx/poolrequests.py
View File

@ -1,20 +1,63 @@
import requests import requests
from itertools import cycle
from searx import settings
the_http_adapter = requests.adapters.HTTPAdapter(pool_connections=100) class HTTPAdapterWithConnParams(requests.adapters.HTTPAdapter):
the_https_adapter = requests.adapters.HTTPAdapter(pool_connections=100)
def __init__(self, pool_connections=requests.adapters.DEFAULT_POOLSIZE,
pool_maxsize=requests.adapters.DEFAULT_POOLSIZE,
max_retries=requests.adapters.DEFAULT_RETRIES,
pool_block=requests.adapters.DEFAULT_POOLBLOCK,
**conn_params):
if max_retries == requests.adapters.DEFAULT_RETRIES:
self.max_retries = requests.adapters.Retry(0, read=False)
else:
self.max_retries = requests.adapters.Retry.from_int(max_retries)
self.config = {}
self.proxy_manager = {}
super(requests.adapters.HTTPAdapter, self).__init__()
self._pool_connections = pool_connections
self._pool_maxsize = pool_maxsize
self._pool_block = pool_block
self._conn_params = conn_params
self.init_poolmanager(pool_connections, pool_maxsize, block=pool_block, **conn_params)
def __setstate__(self, state):
# Can't handle by adding 'proxy_manager' to self.__attrs__ because
# because self.poolmanager uses a lambda function, which isn't pickleable.
self.proxy_manager = {}
self.config = {}
for attr, value in state.items():
setattr(self, attr, value)
self.init_poolmanager(self._pool_connections, self._pool_maxsize,
block=self._pool_block, **self._conn_params)
if settings['outgoing'].get('source_ips'):
http_adapters = cycle(HTTPAdapterWithConnParams(pool_connections=100, source_address=(source_ip, 0))
for source_ip in settings['outgoing']['source_ips'])
https_adapters = cycle(HTTPAdapterWithConnParams(pool_connections=100, source_address=(source_ip, 0))
for source_ip in settings['outgoing']['source_ips'])
else:
http_adapters = cycle((HTTPAdapterWithConnParams(pool_connections=100), ))
https_adapters = cycle((HTTPAdapterWithConnParams(pool_connections=100), ))
class SessionSinglePool(requests.Session): class SessionSinglePool(requests.Session):
def __init__(self): def __init__(self):
global the_https_adapter, the_http_adapter
super(SessionSinglePool, self).__init__() super(SessionSinglePool, self).__init__()
# reuse the same adapters # reuse the same adapters
self.adapters.clear() self.adapters.clear()
self.mount('https://', the_https_adapter) self.mount('https://', next(https_adapters))
self.mount('http://', the_http_adapter) self.mount('http://', next(http_adapters))
def close(self): def close(self):
"""Call super, but clear adapters since there are managed globaly""" """Call super, but clear adapters since there are managed globaly"""
@ -23,8 +66,10 @@ class SessionSinglePool(requests.Session):
def request(method, url, **kwargs): def request(method, url, **kwargs):
"""same as requests/requests/api.py request(...) except it use SessionSinglePool""" """same as requests/requests/api.py request(...) except it use SessionSinglePool and force proxies"""
global settings
session = SessionSinglePool() session = SessionSinglePool()
kwargs['proxies'] = settings['outgoing'].get('proxies', None)
response = session.request(method=method, url=url, **kwargs) response = session.request(method=method, url=url, **kwargs)
session.close() session.close()
return response return response

Some files were not shown because too many files have changed in this diff Show More