Repository: s0md3v/Photon
Branch: master
Commit: 7781cd676a33
Files: 27
Total size: 88.6 KB
Directory structure:
gitextract_pxos8_d_/
├── .gitignore
├── .travis.yml
├── .whitesource
├── CHANGELOG.md
├── Dockerfile
├── LICENSE.md
├── MANIFEST.in
├── README.md
├── core/
│ ├── __init__.py
│ ├── colors.py
│ ├── config.py
│ ├── flash.py
│ ├── mirror.py
│ ├── prompt.py
│ ├── regex.py
│ ├── requester.py
│ ├── updater.py
│ ├── user-agents.txt
│ ├── utils.py
│ └── zap.py
├── photon.py
├── plugins/
│ ├── __init__.py
│ ├── dnsdumpster.py
│ ├── exporter.py
│ ├── find_subdomains.py
│ └── wayback.py
└── requirements.txt
================================================
FILE CONTENTS
================================================
================================================
FILE: .gitignore
================================================
*.pyc
================================================
FILE: .travis.yml
================================================
language: python
os:
- linux
python:
- 3.6
install:
- pip install -r requirements.txt
- pip install flake8
before_script:
# stop the build if there are Python syntax errors or undefined names
- flake8 . --count --select=E901,E999,F821,F822,F823 --show-source --statistics
# exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
- flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
script:
- python photon.py -u "https://somdev.me" -l 1 -d 1 -t 100 --regex "\d{10}" --dns --output="d3v"
- python photon.py -u "https://somdev.me" -l 1 -t 10 --seeds="https://somdev.me/posts" --only-urls --export=json --wayback
================================================
FILE: .whitesource
================================================
{
"generalSettings": {
"shouldScanRepo": true
},
"checkRunSettings": {
"vulnerableCheckRunConclusionLevel": "failure"
}
}
================================================
FILE: CHANGELOG.md
================================================
#### v1.3.2
- add support for socks proxies
- add rotating proxies
- `-p` now takes `IP:PORT` or `DOMAIN:PORT` with `http://`, `socks5://` or nothing (default is `http`) or a `file` with a list of proxies (`http://` or `socks5://` or nothing).
#### v1.3.1
- Added more intels (GENERIC_URL, BRACKET_URL, BACKSLASH_URL, HEXENCODED_URL, URLENCODED_URL, B64ENCODED_URL, IPV4, IPV6, EMAIL, MD5, SHA1, SHA256, SHA512, YARA_PARSE, CREDIT_CARD)
- proxy support with `-p, --proxy` option (http proxy only)
- minor fixes and pep8 format
#### v1.3.0
- Dropped Python < 3.2 support
- Removed Ninja mode
- Fixed a bug in link parsing
- Fixed Unicode output
- Fixed a bug which caused URLs to be treated as files
- Intel is now associated with the URL where it was found
#### v1.2.1
- Added cloning ability
- Refactored to be modular
#### v1.1.6
- Reuse TCP connection for better performance
- Handle redirect loops
- CSV export support
- Fixed `sitemap.xml` parsing
- Improved regex
#### v1.1.5
- fixed some minor bugs
- fixed a bug in domain name parsing
- added --headers option for interactive HTTP headers input
#### v1.1.4
- Added `-v` option
- Fixed progress animation for Python 2
- Added `developer.facebook.com` API for Ninja mode
#### v1.1.3
- Added `--stdout` option
- Fixed a bug in `zap()` function
- Fixed crashing when target is an IP address
- Minor refactor
#### v1.1.2
- Added `--wayback`
- Fixed progress bar for Python > 3.2
- Added `/core/config.py` for easy customization
- `--dns` now saves subdomains in `subdomains.txt`
#### v1.1.1
- Use of `ThreadPoolExecutor` for x2 speed (for Python > 3.2)
- Fixed mishandling of urls starting with `//`
- Removed a redundant try-except statement
- Evaluate entropy of found keys to avoid false positives
#### v1.1.0
- Added `--keys` option
- Fixed a bug related to SSL certificate verification
#### v1.0.9
- Code refactor
- Better identification of external URLs
- Fixed a major bug that made several intel URLs pass under the radar
- Fixed a major bug that caused non-html type content to be marked a crawlable URL
#### v1.0.8
- added `--exclude` option
- Better regex and code logic to favor performance
- Fixed a bug that caused dnsdumpster to fail if target was a subdomain
- Fixed a bug that caused a crash if run outside "Photon" directory
- Fixed a bug in file saving (specific to Python 3)
#### v1.0.7
- Added `--timeout` option
- Added `--output` option
- Added `--user-agent` option
- Replaced lxml with regex
- Better logic for favoring performance
- Added bigger and separate file for user-agents
#### v1.0.6
- Fixed lot of bugs
- Suppress SSL warnings in MAC
- x100 speed by code optimization
- Simplified code of `exporter` plugin
#### v1.0.5
- Added `exporter` plugin
- Added seamless update ability
- Fixed a bug in update function
#### v1.0.4
- Fixed an issue which caused regular links to be saved in robots.txt
- Simplified `flash` function
- Removed `-n` as an alias of `--ninja`
- Added `--only-urls` option
- Refactored code for readability
- Skip saving files if the content is empty
#### v1.0.3
- Introduced plugins
- Added `dnsdumpster` plugin
- Fixed non-ascii character handling, again
- 404 pages are now added to `failed` list
- Handling exceptions in `jscanner`
#### v1.0.2
- Proper handling of null response from `robots.txt` & `sitemap.xml`
- Python2 compatibility
- Proper handling of non-ascii chars
- Added ability to specify custom regex pattern
- Display total time taken and average time per request
#### v1.0.1
- Disabled colors on Windows and macOS
- Cross platform file handling
#### v1.0.0
- First stable release
================================================
FILE: Dockerfile
================================================
FROM python:3-alpine
LABEL name photon
LABEL src "https://github.com/s0md3v/Photon"
LABEL creator s0md3v
LABEL dockerfile_maintenance khast3x
LABEL desc "Incredibly fast crawler designed for reconnaissance."
RUN apk add git && git clone https://github.com/s0md3v/Photon.git Photon
WORKDIR Photon
RUN pip install -r requirements.txt
VOLUME [ "/Photon" ]
# ENTRYPOINT ["sh"]
ENTRYPOINT [ "python", "photon.py" ]
CMD ["--help"]
================================================
FILE: LICENSE.md
================================================
GNU GENERAL PUBLIC LICENSE
Version 3, 29 June 2007
Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
Preamble
The GNU General Public License is a free, copyleft license for
software and other kinds of works.
The licenses for most software and other practical works are designed
to take away your freedom to share and change the works. By contrast,
the GNU General Public License is 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. We, the Free Software Foundation, use the
GNU General Public License for most of our software; it applies also to
any other work released this way by its authors. You can apply it to
your programs, too.
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.
To protect your rights, we need to prevent others from denying you
these rights or asking you to surrender the rights. Therefore, you have
certain responsibilities if you distribute copies of the software, or if
you modify it: responsibilities to respect the freedom of others.
For example, if you distribute copies of such a program, whether
gratis or for a fee, you must pass on to the recipients the same
freedoms that you received. You must make sure that they, too, receive
or can get the source code. And you must show them these terms so they
know their rights.
Developers that use the GNU GPL protect your rights with two steps:
(1) assert copyright on the software, and (2) offer you this License
giving you legal permission to copy, distribute and/or modify it.
For the developers' and authors' protection, the GPL clearly explains
that there is no warranty for this free software. For both users' and
authors' sake, the GPL requires that modified versions be marked as
changed, so that their problems will not be attributed erroneously to
authors of previous versions.
Some devices are designed to deny users access to install or run
modified versions of the software inside them, although the manufacturer
can do so. This is fundamentally incompatible with the aim of
protecting users' freedom to change the software. The systematic
pattern of such abuse occurs in the area of products for individuals to
use, which is precisely where it is most unacceptable. Therefore, we
have designed this version of the GPL to prohibit the practice for those
products. If such problems arise substantially in other domains, we
stand ready to extend this provision to those domains in future versions
of the GPL, as needed to protect the freedom of users.
Finally, every program is threatened constantly by software patents.
States should not allow patents to restrict development and use of
software on general-purpose computers, but in those that do, we wish to
avoid the special danger that patents applied to a free program could
make it effectively proprietary. To prevent this, the GPL assures that
patents cannot be used to render the program non-free.
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 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. Use with the GNU Affero General Public License.
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 Affero 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 special requirements of the GNU Affero General Public License,
section 13, concerning interaction through a network will apply to the
combination as such.
14. Revised Versions of this License.
The Free Software Foundation may publish revised and/or new versions of
the GNU 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 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 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 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 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 General Public License for more details.
You should have received a copy of the GNU 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 the program does terminal interaction, make it output a short
notice like this when it starts in an interactive mode:
{{ project }} Copyright (C) {{ year }} {{ organization }}
This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
This is free software, and you are welcome to redistribute it
under certain conditions; type `show c' for details.
The hypothetical commands `show w' and `show c' should show the appropriate
parts of the General Public License. Of course, your program's commands
might be different; for a GUI interface, you would use an "about box".
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 GPL, see
<http://www.gnu.org/licenses/>.
The GNU General Public License does not permit incorporating your program
into proprietary programs. If your program is a subroutine library, you
may consider it more useful to permit linking proprietary applications with
the library. If this is what you want to do, use the GNU Lesser General
Public License instead of this License. But first, please read
<http://www.gnu.org/philosophy/why-not-lgpl.html>.
================================================
FILE: MANIFEST.in
================================================
include LICENSE.md
================================================
FILE: README.md
================================================
<h1 align="center">
<br>
<a href="https://github.com/s0md3v/Photon"><img src="https://image.ibb.co/h5OZAK/photonsmall.png" alt="Photon"></a>
<br>
Photon
<br>
</h1>
<h4 align="center">Incredibly fast crawler designed for OSINT.</h4>
<p align="center">
<a href="https://github.com/s0md3v/Photon/releases">
<img src="https://img.shields.io/github/release/s0md3v/Photon.svg">
</a>
<a href="https://pypi.org/project/photon/">
<img src="https://img.shields.io/badge/pypi-@photon-red.svg?style=style=flat-square"
alt="pypi">
</a>
<a href="https://github.com/s0md3v/Photon/issues?q=is%3Aissue+is%3Aclosed">
<img src="https://img.shields.io/github/issues-closed-raw/s0md3v/Photon.svg">
</a>
<a href="https://travis-ci.com/s0md3v/Photon">
<img src="https://img.shields.io/travis/com/s0md3v/Photon.svg">
</a>
</p>
<p align="center">
<a href="https://github.com/s0md3v/Photon/wiki">Photon Wiki</a> •
<a href="https://github.com/s0md3v/Photon/wiki/Usage">How To Use</a> •
<a href="https://github.com/s0md3v/Photon/wiki/Compatibility-&-Dependencies">Compatibility</a> •
<a href="https://github.com/s0md3v/Photon/wiki/Photon-Library">Photon Library</a> •
<a href="#contribution--license">Contribution</a> •
<a href="https://github.com/s0md3v/Photon/projects/1">Roadmap</a>
</p>
### Key Features
#### Data Extraction
Photon can extract the following data while crawling:
- URLs (in-scope & out-of-scope)
- URLs with parameters (`example.com/gallery.php?id=2`)
- Intel (emails, social media accounts, amazon buckets etc.)
- Files (pdf, png, xml etc.)
- Secret keys (auth/API keys & hashes)
- JavaScript files & Endpoints present in them
- Strings matching custom regex pattern
- Subdomains & DNS related data
The extracted information is saved in an organized manner or can be [exported as json](https://github.com/s0md3v/Photon/wiki/Usage#export-formatted-result).
#### Flexible
Control timeout, delay, add seeds, exclude URLs matching a regex pattern and other cool stuff.
The extensive range of [options](https://github.com/s0md3v/Photon/wiki/Usage) provided by Photon lets you crawl the web exactly the way you want.
#### Genius
Photon's smart thread management & refined logic gives you top notch performance.
Still, crawling can be resource intensive but Photon has some tricks up it's sleeves. You can fetch URLs archived by [archive.org](https://archive.org/) to be used as seeds by using `--wayback` option.
#### Plugins
- **[wayback](https://github.com/s0md3v/Photon/wiki/Usage#use-urls-from-archiveorg-as-seeds)**
- **[dnsdumpster](https://github.com/s0md3v/Photon/wiki/Usage#dumping-dns-data)**
- **[Exporter](https://github.com/s0md3v/Photon/wiki/Usage#export-formatted-result)**
#### Docker
Photon can be launched using a lightweight Python-Alpine (103 MB) Docker image.
```bash
$ git clone https://github.com/s0md3v/Photon.git
$ cd Photon
$ docker build -t photon .
$ docker run -it --name photon photon:latest -u google.com
```
To view results, you can either head over to the local docker volume, which you can find by running `docker inspect photon` or by mounting the target loot folder:
```bash
$ docker run -it --name photon -v "$PWD:/Photon/google.com" photon:latest -u google.com
```
#### Frequent & Seamless Updates
Photon is under heavy development and updates for fixing bugs. optimizing performance & new features are being rolled regularly.
If you would like to see features and issues that are being worked on, you can do that on [Development](https://github.com/s0md3v/Photon/projects/1) project board.
Updates can be installed & checked for with the `--update` option. Photon has seamless update capabilities which means you can update Photon without losing any of your saved data.
Use Control + Shift + m to toggle the tab key moving focus. Alternatively, use esc then tab to move to the next interactive element on the page.
Attach files by dragging & dropping, selecting or pasting them.
(https://www.thordata.com/?ls=github&lk=Photon)
<p align="center">
<a href="https://github.com/s0md3v/Photon/wiki">Photon Wiki</a> •
<a href="https://github.com/s0md3v/Photon/wiki/Usage">How To Use</a> •
<a href="https://github.com/s0md3v/Photon/wiki/Compatibility-&-Dependencies">Compatibility</a> •
<a href="https://github.com/s0md3v/Photon/wiki/Photon-Library">Photon Library</a> •
<a href="#contribution--license">Contribution</a> •
<a href="https://github.com/s0md3v/Photon/projects/1">Roadmap</a>
</p>
### Key Features
#### Data Extraction
Photon can extract the following data while crawling:
- URLs (in-scope & out-of-scope)
- URLs with parameters (`example.com/gallery.php?id=2`)
- Intel (emails, social media accounts, amazon buckets etc.)
- Files (pdf, png, xml etc.)
- Secret keys (auth/API keys & hashes)
- JavaScript files & Endpoints present in them
- Strings matching custom regex pattern
- Subdomains & DNS related data
The extracted information is saved in an organized manner or can be [exported as json](https://github.com/s0md3v/Photon/wiki/Usage#export-formatted-result).
#### Flexible
Control timeout, delay, add seeds, exclude URLs matching a regex pattern and other cool stuff.
The extensive range of [options](https://github.com/s0md3v/Photon/wiki/Usage) provided by Photon lets you crawl the web exactly the way you want.
#### Genius
Photon's smart thread management & refined logic gives you top notch performance.
Still, crawling can be resource intensive but Photon has some tricks up it's sleeves. You can fetch URLs archived by [archive.org](https://archive.org/) to be used as seeds by using `--wayback` option.
#### Plugins
- **[wayback](https://github.com/s0md3v/Photon/wiki/Usage#use-urls-from-archiveorg-as-seeds)**
- **[dnsdumpster](https://github.com/s0md3v/Photon/wiki/Usage#dumping-dns-data)**
- **[Exporter](https://github.com/s0md3v/Photon/wiki/Usage#export-formatted-result)**
#### Docker
Photon can be launched using a lightweight Python-Alpine (103 MB) Docker image.
```bash
$ git clone https://github.com/s0md3v/Photon.git
$ cd Photon
$ docker build -t photon .
$ docker run -it --name photon photon:latest -u google.com
```
To view results, you can either head over to the local docker volume, which you can find by running `docker inspect photon` or by mounting the target loot folder:
```bash
$ docker run -it --name photon -v "$PWD:/Photon/google.com" photon:latest -u google.com
```
#### Frequent & Seamless Updates
Photon is under heavy development and updates for fixing bugs. optimizing performance & new features are being rolled regularly.
If you would like to see features and issues that are being worked on, you can do that on [Development](https://github.com/s0md3v/Photon/projects/1) project board.
Updates can be installed & checked for with the `--update` option. Photon has seamless update capabilities which means you can update Photon without losing any of your saved data.
### Contribution & License
You can contribute in following ways:
- Report bugs
- Develop plugins
- Add more "APIs" for ninja mode
- Give suggestions to make it better
- Fix issues & submit a pull request
Please read the [guidelines](https://github.com/s0md3v/Photon/wiki/Guidelines) before submitting a pull request or issue.
Do you want to have a conversation in private? Hit me up on my [twitter](https://twitter.com/s0md3v/), inbox is open :)
**Photon** is licensed under [GPL v3.0 license](https://www.gnu.org/licenses/gpl-3.0.en.html)
================================================
FILE: core/__init__.py
================================================
"""The Photon core."""
================================================
FILE: core/colors.py
================================================
import sys
if sys.platform.lower().startswith(('os', 'win', 'darwin', 'ios')):
# Colors shouldn't be displayed on Mac and Windows
end = red = white = green = yellow = run = bad = good = info = que = ''
else:
white = '\033[97m'
green = '\033[92m'
red = '\033[91m'
yellow = '\033[93m'
end = '\033[0m'
back = '\033[7;91m'
info = '\033[93m[!]\033[0m'
que = '\033[94m[?]\033[0m'
bad = '\033[91m[-]\033[0m'
good = '\033[92m[+]\033[0m'
run = '\033[97m[~]\033[0m'
================================================
FILE: core/config.py
================================================
"""Configuration options for Photon."""
VERBOSE = False
INTELS = [
'facebook.com',
'github.com',
'instagram.com',
'youtube.com',
]
BAD_TYPES = (
'bmp',
'css',
'csv',
'docx',
'ico',
'jpeg',
'jpg',
'js',
'json',
'pdf',
'png',
'svg',
'xls',
'xml',
)
================================================
FILE: core/flash.py
================================================
from __future__ import print_function
import concurrent.futures
from core.colors import info
def flash(function, links, thread_count):
"""Process the URLs and uses a threadpool to execute a function."""
# Convert links (set) to list
links = list(links)
threadpool = concurrent.futures.ThreadPoolExecutor(
max_workers=thread_count)
futures = (threadpool.submit(function, link) for link in links)
for i, _ in enumerate(concurrent.futures.as_completed(futures)):
if i + 1 == len(links) or (i + 1) % thread_count == 0:
print('%s Progress: %i/%i' % (info, i + 1, len(links)),
end='\r')
print('')
================================================
FILE: core/mirror.py
================================================
import os
def mirror(url, response):
if response != 'dummy':
clean_url = url.replace('http://', '').replace('https://', '').rstrip('/')
parts = clean_url.split('?')[0].split('/')
root = parts[0]
webpage = parts[-1]
parts.remove(root)
try:
parts.remove(webpage)
except ValueError:
pass
prefix = root + '_mirror'
try:
os.mkdir(prefix)
except OSError:
pass
suffix = ''
if parts:
for directory in parts:
suffix += directory + '/'
try:
os.mkdir(prefix + '/' + suffix)
except OSError:
pass
path = prefix + '/' + suffix
trail = ''
if '.' not in webpage:
trail += '.html'
if webpage == root:
name = 'index.html'
else:
name = webpage
if len(url.split('?')) > 1:
trail += '?' + url.split('?')[1]
with open(path + name + trail, 'w+') as out_file:
out_file.write(response.encode('utf-8'))
================================================
FILE: core/prompt.py
================================================
"""Support for an input prompt."""
import os
import tempfile
def prompt(default=None):
"""Present the user a prompt."""
editor = 'nano'
with tempfile.NamedTemporaryFile(mode='r+') as tmpfile:
if default:
tmpfile.write(default)
tmpfile.flush()
child_pid = os.fork()
is_child = child_pid == 0
if is_child:
os.execvp(editor, [editor, tmpfile.name])
else:
os.waitpid(child_pid, 0)
tmpfile.seek(0)
return tmpfile.read().strip()
================================================
FILE: core/regex.py
================================================
import re
# regex taken from https://github.com/InQuest/python-iocextract
# Reusable end punctuation regex.
END_PUNCTUATION = r"[\.\?>\"'\)!,}:;\u201d\u2019\uff1e\uff1c\]]*"
# Reusable regex for symbols commonly used to defang.
SEPARATOR_DEFANGS = r"[\(\)\[\]{}<>\\]"
# Split URLs on some characters that may be valid, but may also be garbage.
URL_SPLIT_STR = r"[>\"'\),};]"
# Get basic url format, including a few obfuscation techniques, main anchor is the uri scheme.
GENERIC_URL = re.compile(r"""
(
# Scheme.
[fhstu]\S\S?[px]s?
# One of these delimiters/defangs.
(?:
:\/\/|
:\\\\|
:?__
)
# Any number of defang characters.
(?:
\x20|
""" + SEPARATOR_DEFANGS + r"""
)*
# Domain/path characters.
\w
\S+?
# CISCO ESA style defangs followed by domain/path characters.
(?:\x20[\/\.][^\.\/\s]\S*?)*
)
""" + END_PUNCTUATION + r"""
(?=\s|$)
""", re.IGNORECASE | re.VERBOSE | re.UNICODE)
# Get some obfuscated urls, main anchor is brackets around the period.
BRACKET_URL = re.compile(r"""
\b
(
[\.\:\/\\\w\[\]\(\)-]+
(?:
\x20?
[\(\[]
\x20?
\.
\x20?
[\]\)]
\x20?
\S*?
)+
)
""" + END_PUNCTUATION + r"""
(?=\s|$)
""", re.VERBOSE | re.UNICODE)
# Get some obfuscated urls, main anchor is backslash before a period.
BACKSLASH_URL = re.compile(r"""
\b
(
[\:\/\\\w\[\]\(\)-]+
(?:
\x20?
\\?\.
\x20?
\S*?
)*?
(?:
\x20?
\\\.
\x20?
\S*?
)
(?:
\x20?
\\?\.
\x20?
\S*?
)*
)
""" + END_PUNCTUATION + r"""
(?=\s|$)
""", re.VERBOSE | re.UNICODE)
# Get hex-encoded urls.
HEXENCODED_URL = re.compile(r"""
(
[46][86]
(?:[57]4)?
[57]4[57]0
(?:[57]3)?
3a2f2f
(?:2[356def]|3[0-9adf]|[46][0-9a-f]|[57][0-9af])+
)
(?:[046]0|2[0-2489a-c]|3[bce]|[57][b-e]|[8-f][0-9a-f]|0a|0d|09|[
\x5b-\x5d\x7b\x7d\x0a\x0d\x20
]|$)
""", re.IGNORECASE | re.VERBOSE)
# Get urlencoded urls.
URLENCODED_URL = re.compile(r"""
(s?[hf]t?tps?%3A%2F%2F\w[\w%-]*?)(?:[^\w%-]|$)
""", re.IGNORECASE | re.VERBOSE)
# Get base64-encoded urls.
B64ENCODED_URL = re.compile(r"""
(
# b64re '([hH][tT][tT][pP][sS]|[hH][tT][tT][pP]|[fF][tT][pP])://'
# Modified to ignore whitespace.
(?:
[\x2b\x2f-\x39A-Za-z]\s*[\x2b\x2f-\x39A-Za-z]\s*[\x31\x35\x39BFJNRVZdhlptx]\s*[Gm]\s*[Vd]\s*[FH]\s*[A]\s*\x36\s*L\s*y\s*[\x2b\x2f\x38-\x39]\s*|
[\x2b\x2f-\x39A-Za-z]\s*[\x2b\x2f-\x39A-Za-z]\s*[\x31\x35\x39BFJNRVZdhlptx]\s*[Io]\s*[Vd]\s*[FH]\s*[R]\s*[Qw]\s*[O]\s*i\s*\x38\s*v\s*[\x2b\x2f-\x39A-Za-z]\s*|
[\x2b\x2f-\x39A-Za-z]\s*[\x2b\x2f-\x39A-Za-z]\s*[\x31\x35\x39BFJNRVZdhlptx]\s*[Io]\s*[Vd]\s*[FH]\s*[R]\s*[Qw]\s*[Uc]\s*[z]\s*o\s*v\s*L\s*[\x2b\x2f-\x39w-z]\s*|
[\x2b\x2f-\x39A-Za-z]\s*[\x30\x32EGUWkm]\s*[Z]\s*[\x30U]\s*[Uc]\s*[D]\s*o\s*v\s*L\s*[\x2b\x2f-\x39w-z]\s*|
[\x2b\x2f-\x39A-Za-z]\s*[\x30\x32EGUWkm]\s*[h]\s*[\x30U]\s*[Vd]\s*[FH]\s*[A]\s*\x36\s*L\s*y\s*[\x2b\x2f\x38-\x39]\s*|
[\x2b\x2f-\x39A-Za-z]\s*[\x30\x32EGUWkm]\s*[h]\s*[\x30U]\s*[Vd]\s*[FH]\s*[B]\s*[Tz]\s*[O]\s*i\s*\x38\s*v\s*[\x2b\x2f-\x39A-Za-z]\s*|
[RZ]\s*[ln]\s*[R]\s*[Qw]\s*[O]\s*i\s*\x38\s*v\s*[\x2b\x2f-\x39A-Za-z]\s*|
[Sa]\s*[FH]\s*[R]\s*[\x30U]\s*[Uc]\s*[D]\s*o\s*v\s*L\s*[\x2b\x2f-\x39w-z]\s*|
[Sa]\s*[FH]\s*[R]\s*[\x30U]\s*[Uc]\s*[FH]\s*[M]\s*\x36\s*L\s*y\s*[\x2b\x2f\x38-\x39]\s*
)
# Up to 260 characters (pre-encoding, reasonable URL length).
[A-Za-z0-9+/=\s]{1,357}
)
(?=[^A-Za-z0-9+/=\s]|$)
""", re.VERBOSE)
# Get some valid obfuscated ip addresses.
IPV4 = re.compile(r"""
(?:^|
(?![^\d\.])
)
(?:
(?:[1-9]?\d|1\d\d|2[0-4]\d|25[0-5])
[\[\(\\]*?\.[\]\)]*?
){3}
(?:[1-9]?\d|1\d\d|2[0-4]\d|25[0-5])
(?:(?=[^\d\.])|$)
""", re.VERBOSE)
# Experimental IPv6 regex, will not catch everything but should be sufficent for now.
IPV6 = re.compile(r"""
\b(?:[a-f0-9]{1,4}:|:){2,7}(?:[a-f0-9]{1,4}|:)\b
""", re.IGNORECASE | re.VERBOSE)
# Capture email addresses including common defangs.
EMAIL = re.compile(r"""
(
[a-z0-9_.+-]+
[\(\[{\x20]*
(?:@|\Wat\W)
[\)\]}\x20]*
[a-z0-9-]+
(?:
(?:
(?:
\x20*
""" + SEPARATOR_DEFANGS + r"""
\x20*
)*
\.
(?:
\x20*
""" + SEPARATOR_DEFANGS + r"""
\x20*
)*
|
\W+dot\W+
)
[a-z0-9-]+?
)+
)
""" + END_PUNCTUATION + r"""
(?=\s|$)
""", re.IGNORECASE | re.VERBOSE | re.UNICODE)
MD5 = re.compile(r"(?:[^a-fA-F\d]|\b)([a-fA-F\d]{32})(?:[^a-fA-F\d]|\b)")
SHA1 = re.compile(r"(?:[^a-fA-F\d]|\b)([a-fA-F\d]{40})(?:[^a-fA-F\d]|\b)")
SHA256 = re.compile(r"(?:[^a-fA-F\d]|\b)([a-fA-F\d]{64})(?:[^a-fA-F\d]|\b)")
SHA512 = re.compile(
r"(?:[^a-fA-F\d]|\b)([a-fA-F\d]{128})(?:[^a-fA-F\d]|\b)")
# YARA regex.
YARA_PARSE = re.compile(r"""
(?:^|\s)
(
(?:
\s*?import\s+?"[^\r\n]*?[\r\n]+|
\s*?include\s+?"[^\r\n]*?[\r\n]+|
\s*?//[^\r\n]*[\r\n]+|
\s*?/\*.*?\*/\s*?
)*
(?:
\s*?private\s+|
\s*?global\s+
)*
rule\s*?
\w+\s*?
(?:
:[\s\w]+
)?
\s+\{
.*?
condition\s*?:
.*?
\s*\}
)
(?:$|\s)
""", re.MULTILINE | re.DOTALL | re.VERBOSE)
CREDIT_CARD = re.compile(r"[0-9]{4}[ ]?[-]?[0-9]{4}[ ]?[-]?[0-9]{4}[ ]?[-]?[0-9]{4}")
rintels = [(GENERIC_URL, "GENERIC_URL"),
(BRACKET_URL, "BRACKET_URL"),
(BACKSLASH_URL, "BACKSLASH_URL"),
(HEXENCODED_URL, "HEXENCODED_URL"),
(URLENCODED_URL, "URLENCODED_URL"),
(B64ENCODED_URL, "B64ENCODED_URL"),
(IPV4, "IPV4"),
(IPV6, "IPV6"),
(EMAIL, "EMAIL"),
(MD5, "MD5"),
(SHA1, "SHA1"),
(SHA256, "SHA256"),
(SHA512, "SHA512"),
(YARA_PARSE, "YARA_PARSE"),
(CREDIT_CARD, "CREDIT_CARD")]
rscript = re.compile(r'<(script|SCRIPT).*(src|SRC)=([^\s>]+)')
rhref = re.compile(r'<[aA].*(href|HREF)=([^\s>]+)')
rendpoint = re.compile(r'[\'"](/.*?)[\'"]|[\'"](http.*?)[\'"]')
rentropy = re.compile(r'[\w-]{16,45}')
================================================
FILE: core/requester.py
================================================
import random
import time
import requests
from requests.exceptions import TooManyRedirects
SESSION = requests.Session()
SESSION.max_redirects = 3
def requester(
url,
main_url=None,
delay=0,
cook=None,
headers=None,
timeout=10,
host=None,
proxies=[None],
user_agents=[None],
failed=None,
processed=None
):
"""Handle the requests and return the response body."""
cook = cook or set()
headers = headers or set()
user_agents = user_agents or ['Photon']
failed = failed or set()
processed = processed or set()
# Mark the URL as crawled
processed.add(url)
# Pause/sleep the program for specified time
time.sleep(delay)
def make_request(url):
"""Default request"""
final_headers = headers or {
'Host': host,
# Selecting a random user-agent
'User-Agent': random.choice(user_agents),
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
'Accept-Language': 'en-US,en;q=0.5',
'Accept-Encoding': 'gzip',
'DNT': '1',
'Connection': 'close',
}
try:
response = SESSION.get(
url,
cookies=cook,
headers=final_headers,
verify=False,
timeout=timeout,
stream=True,
proxies=random.choice(proxies)
)
except TooManyRedirects:
return 'dummy'
if 'text/html' in response.headers['content-type'] or \
'text/plain' in response.headers['content-type']:
if response.status_code != '404':
return response.text
else:
response.close()
failed.add(url)
return 'dummy'
else:
response.close()
return 'dummy'
return make_request(url)
================================================
FILE: core/updater.py
================================================
import os
import re
from core.colors import run, que, good, green, end, info
from core.requester import requester
def updater():
"""Update the current installation.
git clones the latest version and merges it with the current directory.
"""
print('%s Checking for updates' % run)
# Changes must be separated by ;
changes = '''major bug fixes;removed ninja mode;dropped python < 3.2 support;fixed unicode output;proxy support;more intels'''
latest_commit = requester('https://raw.githubusercontent.com/s0md3v/Photon/master/core/updater.py', host='raw.githubusercontent.com')
# Just a hack to see if a new version is available
if changes not in latest_commit:
changelog = re.search(r"changes = '''(.*?)'''", latest_commit)
# Splitting the changes to form a list
changelog = changelog.group(1).split(';')
print('%s A new version of Photon is available.' % good)
print('%s Changes:' % info)
for change in changelog: # print changes
print('%s>%s %s' % (green, end, change))
current_path = os.getcwd().split('/') # if you know it, you know it
folder = current_path[-1] # current directory name
path = '/'.join(current_path) # current directory path
choice = input('%s Would you like to update? [Y/n] ' % que).lower()
if choice != 'n':
print('%s Updating Photon' % run)
os.system('git clone --quiet https://github.com/s0md3v/Photon %s'
% (folder))
os.system('cp -r %s/%s/* %s && rm -r %s/%s/ 2>/dev/null'
% (path, folder, path, path, folder))
print('%s Update successful!' % good)
else:
print('%s Photon is up to date!' % good)
================================================
FILE: core/user-agents.txt
================================================
Mozilla/4.0 (compatible; MSIE 6.0; MSIE 5.5; Windows NT 5.0) Opera 7.02 Bork-edition [en]
Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.0; .NET CLR 1.0.3705)
Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; .NET CLR 2.0.50727; .NET CLR 3.0.4506.2152; .NET CLR 3.5.30729)
Mozilla/5.0 (compatible; Baiduspider/2.0; +http://www.baidu.com/search/spider.html)
Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0)
Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_2) AppleWebKit/601.3.9 (KHTML, like Gecko) Version/9.0.2 Safari/601.3.9
Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.135 Safari/537.36 Edge/12.246
Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; FSL 7.0.7.01001)
Mozilla/5.0 (Windows NT 5.1; rv:13.0) Gecko/20100101 Firefox/13.0.1
Mozilla/5.0 (Windows NT 6.0) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/13.0.782.112 Safari/535.1
Mozilla/5.0 (Windows NT 6.1; rv:5.0) Gecko/20100101 Firefox/5.02
Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/47.0.2526.111 Safari/537.36
Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; SV1; .NET CLR 2.0.50727)
Mozilla/5.0 (Windows NT 6.1; WOW64; rv:12.0) Gecko/20100101 Firefox/12.0
Mozilla/5.0 (X11; CrOS x86_64 8172.45.0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.64 Safari/537.36
Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:15.0) Gecko/20100101 Firefox/15.0.1
Mozilla/5.0 (X11; U; Linux x86_64; de; rv:1.9.2.8) Gecko/20100723 Ubuntu/10.04 (lucid) Firefox/3.6.8
Opera/9.80 (Windows NT 5.1; U; en) Presto/2.10.289 Version/12.01
================================================
FILE: core/utils.py
================================================
import requests
import math
import os.path
import re
import argparse
import tld
from core.colors import info
from core.config import VERBOSE, BAD_TYPES
from urllib.parse import urlparse
def regxy(pattern, response, supress_regex, custom):
"""Extract a string based on regex pattern supplied by user."""
try:
matches = re.findall(r'%s' % pattern, response)
for match in matches:
verb('Custom regex', match)
custom.add(match)
except:
supress_regex = True
def is_link(url, processed, files):
"""
Determine whether or not a link should be crawled
A url should not be crawled if it
- Is a file
- Has already been crawled
Args:
url: str Url to be processed
processed: list[str] List of urls that have already been crawled
Returns:
bool If `url` should be crawled
"""
if url not in processed:
if url.startswith('#') or url.startswith('javascript:'):
return False
is_file = url.endswith(BAD_TYPES)
if is_file:
files.add(url)
return False
return True
return False
def remove_regex(urls, regex):
"""
Parse a list for non-matches to a regex.
Args:
urls: iterable of urls
regex: string regex to be parsed for
Returns:
list of strings not matching regex
"""
if not regex:
return urls
# To avoid iterating over the characters of a string
if not isinstance(urls, (list, set, tuple)):
urls = [urls]
try:
non_matching_urls = [url for url in urls if not re.search(regex, url)]
except TypeError:
return []
return non_matching_urls
def writer(datasets, dataset_names, output_dir):
"""Write the results."""
for dataset, dataset_name in zip(datasets, dataset_names):
if dataset:
filepath = output_dir + '/' + dataset_name + '.txt'
with open(filepath, 'w+') as out_file:
joined = '\n'.join(dataset)
out_file.write(str(joined.encode('utf-8').decode('utf-8')))
out_file.write('\n')
def timer(diff, processed):
"""Return the passed time."""
# Changes seconds into minutes and seconds
minutes, seconds = divmod(diff, 60)
try:
# Finds average time taken by requests
time_per_request = diff / float(len(processed))
except ZeroDivisionError:
time_per_request = 0
return minutes, seconds, time_per_request
def entropy(string):
"""Calculate the entropy of a string."""
entropy = 0
for number in range(256):
result = float(string.encode('utf-8').count(
chr(number))) / len(string.encode('utf-8'))
if result != 0:
entropy = entropy - result * math.log(result, 2)
return entropy
def xml_parser(response):
"""Extract links from .xml files."""
# Regex for extracting URLs
return re.findall(r'<loc>(.*?)</loc>', response)
def verb(kind, string):
"""Enable verbose output."""
if VERBOSE:
print('%s %s: %s' % (info, kind, string))
def extract_headers(headers):
"""This function extracts valid headers from interactive input."""
sorted_headers = {}
matches = re.findall(r'(.*):\s(.*)', headers)
for match in matches:
header = match[0]
value = match[1]
try:
if value[-1] == ',':
value = value[:-1]
sorted_headers[header] = value
except IndexError:
pass
return sorted_headers
def top_level(url, fix_protocol=True):
"""Extract the top level domain from an URL."""
ext = tld.get_tld(url, fix_protocol=fix_protocol)
toplevel = '.'.join(urlparse(url).netloc.split('.')[-2:]).split(
ext)[0] + ext
return toplevel
def is_proxy_list(v, proxies):
if os.path.isfile(v):
with open(v, 'r') as _file:
for line in _file:
line = line.strip()
if re.match(r"((http|socks5):\/\/.)?(\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}):(\d{1,5})", line) or \
re.match(r"((http|socks5):\/\/.)?[-a-zA-Z0-9@:%._\+~#=]{2,256}\.[a-z]{2,6}:(\d{1,5})", line):
proxies.append({"http": line,
"https": line})
else:
print("%s ignored" % line)
if proxies:
return True
return False
def proxy_type(v):
""" Match IP:PORT or DOMAIN:PORT in a losse manner """
proxies = []
if re.match(r"((http|socks5):\/\/.)?(\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}):(\d{1,5})", v):
proxies.append({"http": v,
"https": v})
return proxies
elif re.match(r"((http|socks5):\/\/.)?[-a-zA-Z0-9@:%._\+~#=]{2,256}\.[a-z]{2,6}:(\d{1,5})", v):
proxies.append({"http": v,
"https": v})
return proxies
elif is_proxy_list(v, proxies):
return proxies
else:
raise argparse.ArgumentTypeError(
"Proxy should follow IP:PORT or DOMAIN:PORT format")
def luhn(purported):
# sum_of_digits (index * 2)
LUHN_ODD_LOOKUP = (0, 2, 4, 6, 8, 1, 3, 5, 7, 9)
if not isinstance(purported, str):
purported = str(purported)
try:
evens = sum(int(p) for p in purported[-1::-2])
odds = sum(LUHN_ODD_LOOKUP[int(p)] for p in purported[-2::-2])
return (evens + odds) % 10 == 0
except ValueError: # Raised if an int conversion fails
return False
def is_good_proxy(pip):
try:
requests.get('http://example.com', proxies=pip, timeout=3)
except requests.exceptions.ConnectTimeout as e:
return False
except Exception as detail:
return False
return True
================================================
FILE: core/zap.py
================================================
import re
import requests
import random
from core.utils import verb, xml_parser
from core.colors import run, good
from plugins.wayback import time_machine
def zap(input_url, archive, domain, host, internal, robots, proxies):
"""Extract links from robots.txt and sitemap.xml."""
if archive:
print('%s Fetching URLs from archive.org' % run)
if False:
archived_urls = time_machine(domain, 'domain')
else:
archived_urls = time_machine(host, 'host')
print('%s Retrieved %i URLs from archive.org' % (
good, len(archived_urls) - 1))
for url in archived_urls:
verb('Internal page', url)
internal.add(url)
# Makes request to robots.txt
response = requests.get(input_url + '/robots.txt',
proxies=random.choice(proxies)).text
# Making sure robots.txt isn't some fancy 404 page
if '<body' not in response:
# If you know it, you know it
matches = re.findall(r'Allow: (.*)|Disallow: (.*)', response)
if matches:
# Iterating over the matches, match is a tuple here
for match in matches:
# One item in match will always be empty so will combine both
# items
match = ''.join(match)
# If the URL doesn't use a wildcard
if '*' not in match:
url = input_url + match
# Add the URL to internal list for crawling
internal.add(url)
# Add the URL to robots list
robots.add(url)
print('%s URLs retrieved from robots.txt: %s' % (good, len(robots)))
# Makes request to sitemap.xml
response = requests.get(input_url + '/sitemap.xml',
proxies=random.choice(proxies)).text
# Making sure robots.txt isn't some fancy 404 page
if '<body' not in response:
matches = xml_parser(response)
if matches: # if there are any matches
print('%s URLs retrieved from sitemap.xml: %s' % (
good, len(matches)))
for match in matches:
verb('Internal page', match)
# Cleaning up the URL and adding it to the internal list for
# crawling
internal.add(match)
================================================
FILE: photon.py
================================================
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""The Photon main part."""
from __future__ import print_function
import argparse
import os
import re
import requests
import sys
import time
import warnings
import random
from core.colors import good, info, run, green, red, white, end, bad
# Just a fancy ass banner
print('''%s ____ __ __
/ %s__%s \/ /_ ____ / /_____ ____
/ %s/_/%s / __ \/ %s__%s \/ __/ %s__%s \/ __ \\
/ ____/ / / / %s/_/%s / /_/ %s/_/%s / / / /
/_/ /_/ /_/\____/\__/\____/_/ /_/ %sv1.3.2%s\n''' %
(red, white, red, white, red, white, red, white, red, white, red, white,
red, white, end))
try:
from urllib.parse import urlparse # For Python 3
except ImportError:
print('%s Photon runs only on Python 3.2 and above.' % info)
quit()
import core.config
from core.config import INTELS
from core.flash import flash
from core.mirror import mirror
from core.prompt import prompt
from core.requester import requester
from core.updater import updater
from core.utils import (luhn,
proxy_type,
is_good_proxy,
top_level,
extract_headers,
verb, is_link,
entropy, regxy,
remove_regex,
timer,
writer)
from core.regex import rintels, rendpoint, rhref, rscript, rentropy
from core.zap import zap
# Disable SSL related warnings
warnings.filterwarnings('ignore')
# Processing command line arguments
parser = argparse.ArgumentParser()
# Options
parser.add_argument('-u', '--url', help='root url', dest='root')
parser.add_argument('-c', '--cookie', help='cookie', dest='cook')
parser.add_argument('-r', '--regex', help='regex pattern', dest='regex')
parser.add_argument('-e', '--export', help='export format', dest='export', choices=['csv', 'json'])
parser.add_argument('-o', '--output', help='output directory', dest='output')
parser.add_argument('-l', '--level', help='levels to crawl', dest='level',
type=int)
parser.add_argument('-t', '--threads', help='number of threads', dest='threads',
type=int)
parser.add_argument('-d', '--delay', help='delay between requests',
dest='delay', type=float)
parser.add_argument('-v', '--verbose', help='verbose output', dest='verbose',
action='store_true')
parser.add_argument('-s', '--seeds', help='additional seed URLs', dest='seeds',
nargs="+", default=[])
parser.add_argument('--stdout', help='send variables to stdout', dest='std')
parser.add_argument('--user-agent', help='custom user agent(s)',
dest='user_agent')
parser.add_argument('--exclude', help='exclude URLs matching this regex',
dest='exclude')
parser.add_argument('--timeout', help='http request timeout', dest='timeout',
type=float)
parser.add_argument('-p', '--proxy', help='Proxy server IP:PORT or DOMAIN:PORT', dest='proxies',
type=proxy_type)
# Switches
parser.add_argument('--clone', help='clone the website locally', dest='clone',
action='store_true')
parser.add_argument('--headers', help='add headers', dest='headers',
action='store_true')
parser.add_argument('--dns', help='enumerate subdomains and DNS data',
dest='dns', action='store_true')
parser.add_argument('--keys', help='find secret keys', dest='api',
action='store_true')
parser.add_argument('--update', help='update photon', dest='update',
action='store_true')
parser.add_argument('--only-urls', help='only extract URLs', dest='only_urls',
action='store_true')
parser.add_argument('--wayback', help='fetch URLs from archive.org as seeds',
dest='archive', action='store_true')
args = parser.parse_args()
# If the user has supplied --update argument
if args.update:
updater()
quit()
# If the user has supplied a URL
if args.root:
main_inp = args.root
if main_inp.endswith('/'):
# We will remove it as it can cause problems later in the code
main_inp = main_inp[:-1]
# If the user hasn't supplied an URL
else:
print('\n' + parser.format_help().lower())
quit()
clone = args.clone
headers = args.headers # prompt for headers
verbose = args.verbose # verbose output
delay = args.delay or 0 # Delay between requests
timeout = args.timeout or 6 # HTTP request timeout
cook = args.cook or None # Cookie
api = bool(args.api) # Extract high entropy strings i.e. API keys and stuff
proxies = []
if args.proxies:
print("%s Testing proxies, can take a while..." % info)
for proxy in args.proxies:
if is_good_proxy(proxy):
proxies.append(proxy)
else:
print("%s Proxy %s doesn't seem to work or timedout" %
(bad, proxy['http']))
print("%s Done" % info)
if not proxies:
print("%s no working proxies, quitting!" % bad)
exit()
else:
proxies.append(None)
crawl_level = args.level or 2 # Crawling level
thread_count = args.threads or 2 # Number of threads
only_urls = bool(args.only_urls) # Only URLs mode is off by default
# Variables we are gonna use later to store stuff
keys = set() # High entropy strings, prolly secret keys
files = set() # The pdf, css, png, etc files.
intel = set() # The email addresses, website accounts, AWS buckets etc.
robots = set() # The entries of robots.txt
custom = set() # Strings extracted by custom regex pattern
failed = set() # URLs that photon failed to crawl
scripts = set() # THe Javascript files
external = set() # URLs that don't belong to the target i.e. out-of-scope
# URLs that have get params in them e.g. example.com/page.php?id=2
fuzzable = set()
endpoints = set() # URLs found from javascript files
processed = set(['dummy']) # URLs that have been crawled
# URLs that belong to the target i.e. in-scope
internal = set(args.seeds)
everything = []
bad_scripts = set() # Unclean javascript file urls
bad_intel = set() # needed for intel filtering
core.config.verbose = verbose
if headers:
try:
prompt = prompt()
except FileNotFoundError as e:
print('Could not load headers prompt: {}'.format(e))
quit()
headers = extract_headers(prompt)
# If the user hasn't supplied the root URL with http(s), we will handle it
if main_inp.startswith('http'):
main_url = main_inp
else:
try:
requests.get('https://' + main_inp, proxies=random.choice(proxies))
main_url = 'https://' + main_inp
except:
main_url = 'http://' + main_inp
schema = main_url.split('//')[0] # https: or http:?
# Adding the root URL to internal for crawling
internal.add(main_url)
# Extracts host out of the URL
host = urlparse(main_url).netloc
output_dir = args.output or host
try:
domain = top_level(main_url)
except:
domain = host
if args.user_agent:
user_agents = args.user_agent.split(',')
else:
with open(sys.path[0] + '/core/user-agents.txt', 'r') as uas:
user_agents = [agent.strip('\n') for agent in uas]
supress_regex = False
def intel_extractor(url, response):
"""Extract intel from the response body."""
for rintel in rintels:
res = re.sub(r'<(script).*?</\1>(?s)', '', response)
res = re.sub(r'<[^<]+?>', '', res)
matches = rintel[0].findall(res)
if matches:
for match in matches:
verb('Intel', match)
bad_intel.add((match, rintel[1], url))
def js_extractor(response):
"""Extract js files from the response body"""
# Extract .js files
matches = rscript.findall(response)
for match in matches:
match = match[2].replace('\'', '').replace('"', '')
verb('JS file', match)
bad_scripts.add(match)
def remove_file(url):
if url.count('/') > 2:
replacable = re.search(r'/[^/]*?$', url).group()
if replacable != '/':
return url.replace(replacable, '')
else:
return url
else:
return url
def extractor(url):
"""Extract details from the response body."""
response = requester(url, main_url, delay, cook, headers, timeout, host, proxies, user_agents, failed, processed)
if clone:
mirror(url, response)
matches = rhref.findall(response)
for link in matches:
# Remove everything after a "#" to deal with in-page anchors
link = link[1].replace('\'', '').replace('"', '').split('#')[0]
# Checks if the URLs should be crawled
if is_link(link, processed, files):
if link[:4] == 'http':
if link.startswith(main_url):
verb('Internal page', link)
internal.add(link)
else:
verb('External page', link)
external.add(link)
elif link[:2] == '//':
if link.split('/')[2].startswith(host):
verb('Internal page', link)
internal.add(schema + '://' + link)
else:
verb('External page', link)
external.add(link)
elif link[:1] == '/':
verb('Internal page', link)
internal.add(remove_file(url) + link)
else:
verb('Internal page', link)
usable_url = remove_file(url)
if usable_url.endswith('/'):
internal.add(usable_url + link)
elif link.startswith('/'):
internal.add(usable_url + link)
else:
internal.add(usable_url + '/' + link)
if not only_urls:
intel_extractor(url, response)
js_extractor(response)
if args.regex and not supress_regex:
regxy(args.regex, response, supress_regex, custom)
if api:
matches = rentropy.findall(response)
for match in matches:
if entropy(match) >= 4:
verb('Key', match)
keys.add(url + ': ' + match)
def jscanner(url):
"""Extract endpoints from JavaScript code."""
response = requester(url, main_url, delay, cook, headers, timeout, host, proxies, user_agents, failed, processed)
# Extract URLs/endpoints
matches = rendpoint.findall(response)
# Iterate over the matches, match is a tuple
for match in matches:
# Combining the items because one of them is always empty
match = match[0] + match[1]
# Making sure it's not some JavaScript code
if not re.search(r'[}{><"\']', match) and not match == '/':
verb('JS endpoint', match)
endpoints.add(match)
# Records the time at which crawling started
then = time.time()
# Step 1. Extract urls from robots.txt & sitemap.xml
zap(main_url, args.archive, domain, host, internal, robots, proxies)
# This is so the level 1 emails are parsed as well
internal = set(remove_regex(internal, args.exclude))
# Step 2. Crawl recursively to the limit specified in "crawl_level"
for level in range(crawl_level):
# Links to crawl = (all links - already crawled links) - links not to crawl
links = remove_regex(internal - processed, args.exclude)
# If links to crawl are 0 i.e. all links have been crawled
if not links:
break
# if crawled links are somehow more than all links. Possible? ;/
elif len(internal) <= len(processed):
if len(internal) > 2 + len(args.seeds):
break
print('%s Level %i: %i URLs' % (run, level + 1, len(links)))
try:
flash(extractor, links, thread_count)
except KeyboardInterrupt:
print('')
break
if not only_urls:
for match in bad_scripts:
if match.startswith(main_url):
scripts.add(match)
elif match.startswith('/') and not match.startswith('//'):
scripts.add(main_url + match)
elif not match.startswith('http') and not match.startswith('//'):
scripts.add(main_url + '/' + match)
# Step 3. Scan the JavaScript files for endpoints
print('%s Crawling %i JavaScript files' % (run, len(scripts)))
flash(jscanner, scripts, thread_count)
for url in internal:
if '=' in url:
fuzzable.add(url)
for match, intel_name, url in bad_intel:
if isinstance(match, tuple):
for x in match: # Because "match" is a tuple
if x != '': # If the value isn't empty
if intel_name == "CREDIT_CARD":
if not luhn(match):
# garbage number
continue
intel.add("%s:%s" % (intel_name, x))
else:
if intel_name == "CREDIT_CARD":
if not luhn(match):
# garbage number
continue
intel.add("%s:%s:%s" % (url, intel_name, match))
for url in external:
try:
if top_level(url, fix_protocol=True) in INTELS:
intel.add(url)
except:
pass
# Records the time at which crawling stopped
now = time.time()
# Finds total time taken
diff = (now - then)
minutes, seconds, time_per_request = timer(diff, processed)
# Step 4. Save the results
if not os.path.exists(output_dir): # if the directory doesn't exist
os.mkdir(output_dir) # create a new directory
datasets = [files, intel, robots, custom, failed, internal, scripts,
external, fuzzable, endpoints, keys]
dataset_names = ['files', 'intel', 'robots', 'custom', 'failed', 'internal',
'scripts', 'external', 'fuzzable', 'endpoints', 'keys']
writer(datasets, dataset_names, output_dir)
# Printing out results
print(('%s-%s' % (red, end)) * 50)
for dataset, dataset_name in zip(datasets, dataset_names):
if dataset:
print('%s %s: %s' % (good, dataset_name.capitalize(), len(dataset)))
print(('%s-%s' % (red, end)) * 50)
print('%s Total requests made: %i' % (info, len(processed)))
print('%s Total time taken: %i minutes %i seconds' % (info, minutes, seconds))
print('%s Requests per second: %i' % (info, int(len(processed) / diff)))
datasets = {
'files': list(files), 'intel': list(intel), 'robots': list(robots),
'custom': list(custom), 'failed': list(failed), 'internal': list(internal),
'scripts': list(scripts), 'external': list(external),
'fuzzable': list(fuzzable), 'endpoints': list(endpoints),
'keys': list(keys)
}
if args.dns:
print('%s Enumerating subdomains' % run)
from plugins.find_subdomains import find_subdomains
subdomains = find_subdomains(domain)
print('%s %i subdomains found' % (info, len(subdomains)))
writer([subdomains], ['subdomains'], output_dir)
datasets['subdomains'] = subdomains
from plugins.dnsdumpster import dnsdumpster
print('%s Generating DNS map' % run)
dnsdumpster(domain, output_dir)
if args.export:
from plugins.exporter import exporter
# exporter(directory, format, datasets)
exporter(output_dir, args.export, datasets)
print('%s Results saved in %s%s%s directory' % (good, green, output_dir, end))
if args.std:
for string in datasets[args.std]:
sys.stdout.write(string + '\n')
================================================
FILE: plugins/__init__.py
================================================
"""Plugins for Photon."""
================================================
FILE: plugins/dnsdumpster.py
================================================
"""Support for dnsdumpster.com."""
import re
import requests
def dnsdumpster(domain, output_dir):
"""Query dnsdumpster.com."""
response = requests.Session().get('https://dnsdumpster.com/').text
csrf_token = re.search(
r'name=\"csrfmiddlewaretoken\" value=\"(.*?)\"', response).group(1)
cookies = {'csrftoken': csrf_token}
headers = {'Referer': 'https://dnsdumpster.com/'}
data = {'csrfmiddlewaretoken': csrf_token, 'targetip': domain}
response = requests.Session().post(
'https://dnsdumpster.com/', cookies=cookies, data=data, headers=headers)
image = requests.get('https://dnsdumpster.com/static/map/%s.png' % domain)
if image.status_code == 200:
with open('%s/%s.png' % (output_dir, domain), 'wb') as f:
f.write(image.content)
================================================
FILE: plugins/exporter.py
================================================
"""Support for exporting the results."""
import csv
import json
def exporter(directory, method, datasets):
"""Export the results."""
if method.lower() == 'json':
# Convert json_dict to a JSON styled string
json_string = json.dumps(datasets, indent=4)
savefile = open('{}/exported.json'.format(directory), 'w+')
savefile.write(json_string)
savefile.close()
if method.lower() == 'csv':
with open('{}/exported.csv'.format(directory), 'w+') as csvfile:
csv_writer = csv.writer(
csvfile, delimiter=',', quoting=csv.QUOTE_MINIMAL)
for key, values in datasets.items():
if values is None:
csv_writer.writerow([key])
else:
csv_writer.writerow([key] + values)
csvfile.close()
================================================
FILE: plugins/find_subdomains.py
================================================
"""Support for findsubdomains.com."""
from re import findall
from requests import get
def find_subdomains(domain):
"""Find subdomains according to the TLD."""
result = set()
response = get('https://findsubdomains.com/subdomains-of/' + domain).text
matches = findall(r'(?s)<div class="domains js-domain-name">(.*?)</div>', response)
for match in matches:
result.add(match.replace(' ', '').replace('\n', ''))
return list(result)
================================================
FILE: plugins/wayback.py
================================================
"""Support for archive.org."""
import datetime
import json
from requests import get
def time_machine(host, mode):
"""Query archive.org."""
now = datetime.datetime.now()
to = str(now.year) + str(now.day) + str(now.month)
if now.month > 6:
fro = str(now.year) + str(now.day) + str(now.month - 6)
else:
fro = str(now.year - 1) + str(now.day) + str(now.month + 6)
url = "http://web.archive.org/cdx/search?url=%s&matchType=%s&collapse=urlkey&fl=original&filter=mimetype:text/html&filter=statuscode:200&output=json&from=%s&to=%s" % (host, mode, fro, to)
response = get(url).text
parsed = json.loads(response)[1:]
urls = []
for item in parsed:
urls.append(item[0])
return urls
================================================
FILE: requirements.txt
================================================
requests
requests[socks]
urllib3
tld
gitextract_pxos8_d_/ ├── .gitignore ├── .travis.yml ├── .whitesource ├── CHANGELOG.md ├── Dockerfile ├── LICENSE.md ├── MANIFEST.in ├── README.md ├── core/ │ ├── __init__.py │ ├── colors.py │ ├── config.py │ ├── flash.py │ ├── mirror.py │ ├── prompt.py │ ├── regex.py │ ├── requester.py │ ├── updater.py │ ├── user-agents.txt │ ├── utils.py │ └── zap.py ├── photon.py ├── plugins/ │ ├── __init__.py │ ├── dnsdumpster.py │ ├── exporter.py │ ├── find_subdomains.py │ └── wayback.py └── requirements.txt
SYMBOL INDEX (29 symbols across 12 files) FILE: core/flash.py function flash (line 6) | def flash(function, links, thread_count): FILE: core/mirror.py function mirror (line 4) | def mirror(url, response): FILE: core/prompt.py function prompt (line 6) | def prompt(default=None): FILE: core/requester.py function requester (line 11) | def requester( FILE: core/updater.py function updater (line 8) | def updater(): FILE: core/utils.py function regxy (line 15) | def regxy(pattern, response, supress_regex, custom): function is_link (line 26) | def is_link(url, processed, files): function remove_regex (line 51) | def remove_regex(urls, regex): function writer (line 78) | def writer(datasets, dataset_names, output_dir): function timer (line 89) | def timer(diff, processed): function entropy (line 101) | def entropy(string): function xml_parser (line 112) | def xml_parser(response): function verb (line 118) | def verb(kind, string): function extract_headers (line 124) | def extract_headers(headers): function top_level (line 140) | def top_level(url, fix_protocol=True): function is_proxy_list (line 148) | def is_proxy_list(v, proxies): function proxy_type (line 164) | def proxy_type(v): function luhn (line 182) | def luhn(purported): function is_good_proxy (line 197) | def is_good_proxy(pip): FILE: core/zap.py function zap (line 10) | def zap(input_url, archive, domain, host, internal, robots, proxies): FILE: photon.py function intel_extractor (line 208) | def intel_extractor(url, response): function js_extractor (line 220) | def js_extractor(response): function remove_file (line 229) | def remove_file(url): function extractor (line 239) | def extractor(url): function jscanner (line 290) | def jscanner(url): FILE: plugins/dnsdumpster.py function dnsdumpster (line 7) | def dnsdumpster(domain, output_dir): FILE: plugins/exporter.py function exporter (line 6) | def exporter(directory, method, datasets): FILE: plugins/find_subdomains.py function find_subdomains (line 7) | def find_subdomains(domain): FILE: plugins/wayback.py function time_machine (line 8) | def time_machine(host, mode):
Condensed preview — 27 files, each showing path, character count, and a content snippet. Download the .json file or copy for the full structured content (96K chars).
[
{
"path": ".gitignore",
"chars": 7,
"preview": "\n*.pyc\n"
},
{
"path": ".travis.yml",
"chars": 686,
"preview": "language: python\nos:\n - linux\npython:\n - 3.6\ninstall:\n - pip install -r requirements.txt\n - pip install flake8\nbefor"
},
{
"path": ".whitesource",
"chars": 137,
"preview": "{\n \"generalSettings\": {\n \"shouldScanRepo\": true\n },\n \"checkRunSettings\": {\n \"vulnerableCheckRunConclusionLevel\""
},
{
"path": "CHANGELOG.md",
"chars": 3628,
"preview": "#### v1.3.2\n- add support for socks proxies\n- add rotating proxies\n- `-p` now takes `IP:PORT` or `DOMAIN:PORT` with `htt"
},
{
"path": "Dockerfile",
"chars": 428,
"preview": "FROM python:3-alpine\n\nLABEL name photon\nLABEL src \"https://github.com/s0md3v/Photon\"\nLABEL creator s0md3v\nLABEL dockerfi"
},
{
"path": "LICENSE.md",
"chars": 35156,
"preview": " GNU GENERAL PUBLIC LICENSE\n Version 3, 29 June 2007\n\n Copyright (C) 2007 Free "
},
{
"path": "MANIFEST.in",
"chars": 19,
"preview": "include LICENSE.md\n"
},
{
"path": "README.md",
"chars": 7663,
"preview": "<h1 align=\"center\">\n <br>\n <a href=\"https://github.com/s0md3v/Photon\"><img src=\"https://image.ibb.co/h5OZAK/photonsmal"
},
{
"path": "core/__init__.py",
"chars": 23,
"preview": "\"\"\"The Photon core.\"\"\"\n"
},
{
"path": "core/colors.py",
"chars": 510,
"preview": "import sys\n\n\nif sys.platform.lower().startswith(('os', 'win', 'darwin', 'ios')):\n # Colors shouldn't be displayed on "
},
{
"path": "core/config.py",
"chars": 322,
"preview": "\"\"\"Configuration options for Photon.\"\"\"\n\nVERBOSE = False\n\nINTELS = [\n 'facebook.com',\n 'github.com',\n 'instagra"
},
{
"path": "core/flash.py",
"chars": 673,
"preview": "from __future__ import print_function\nimport concurrent.futures\n\nfrom core.colors import info\n\ndef flash(function, links"
},
{
"path": "core/mirror.py",
"chars": 1143,
"preview": "import os\n\n\ndef mirror(url, response):\n if response != 'dummy':\n clean_url = url.replace('http://', '').replac"
},
{
"path": "core/prompt.py",
"chars": 551,
"preview": "\"\"\"Support for an input prompt.\"\"\"\nimport os\nimport tempfile\n\n\ndef prompt(default=None):\n \"\"\"Present the user a promp"
},
{
"path": "core/regex.py",
"chars": 7508,
"preview": "import re\n\n# regex taken from https://github.com/InQuest/python-iocextract\n# Reusable end punctuation regex.\nEND_PUNCTUA"
},
{
"path": "core/requester.py",
"chars": 1989,
"preview": "import random\nimport time\n\nimport requests\nfrom requests.exceptions import TooManyRedirects\n\n\nSESSION = requests.Session"
},
{
"path": "core/updater.py",
"chars": 1767,
"preview": "import os\nimport re\n\nfrom core.colors import run, que, good, green, end, info\nfrom core.requester import requester\n\n\ndef"
},
{
"path": "core/user-agents.txt",
"chars": 1607,
"preview": "Mozilla/4.0 (compatible; MSIE 6.0; MSIE 5.5; Windows NT 5.0) Opera 7.02 Bork-edition [en]\nMozilla/4.0 (compatible; MSIE "
},
{
"path": "core/utils.py",
"chars": 5805,
"preview": "import requests\nimport math\nimport os.path\nimport re\nimport argparse\n\nimport tld\n\nfrom core.colors import info\nfrom core"
},
{
"path": "core/zap.py",
"chars": 2365,
"preview": "import re\nimport requests\nimport random\n\nfrom core.utils import verb, xml_parser\nfrom core.colors import run, good\nfrom "
},
{
"path": "photon.py",
"chars": 15862,
"preview": "#!/usr/bin/env python3\r\n# -*- coding: utf-8 -*-\r\n\"\"\"The Photon main part.\"\"\"\r\nfrom __future__ import print_function\r\n\r\ni"
},
{
"path": "plugins/__init__.py",
"chars": 26,
"preview": "\"\"\"Plugins for Photon.\"\"\"\n"
},
{
"path": "plugins/dnsdumpster.py",
"chars": 806,
"preview": "\"\"\"Support for dnsdumpster.com.\"\"\"\nimport re\n\nimport requests\n\n\ndef dnsdumpster(domain, output_dir):\n \"\"\"Query dnsdum"
},
{
"path": "plugins/exporter.py",
"chars": 849,
"preview": "\"\"\"Support for exporting the results.\"\"\"\nimport csv\nimport json\n\n\ndef exporter(directory, method, datasets):\n \"\"\"Expo"
},
{
"path": "plugins/find_subdomains.py",
"chars": 462,
"preview": "\"\"\"Support for findsubdomains.com.\"\"\"\nfrom re import findall\n\nfrom requests import get\n\n\ndef find_subdomains(domain):\n "
},
{
"path": "plugins/wayback.py",
"chars": 735,
"preview": "\"\"\"Support for archive.org.\"\"\"\nimport datetime\nimport json\n\nfrom requests import get\n\n\ndef time_machine(host, mode):\n "
},
{
"path": "requirements.txt",
"chars": 36,
"preview": "requests\nrequests[socks]\nurllib3\ntld"
}
]
About this extraction
This page contains the full source code of the s0md3v/Photon GitHub repository, extracted and formatted as plain text for AI agents and large language models (LLMs). The extraction includes 27 files (88.6 KB), approximately 23.0k tokens, and a symbol index with 29 extracted functions, classes, methods, constants, and types. Use this with OpenClaw, Claude, ChatGPT, Cursor, Windsurf, or any other AI tool that accepts text input. You can copy the full output to your clipboard or download it as a .txt file.
Extracted by GitExtract — free GitHub repo to text converter for AI. Built by Nikandr Surkov.