diff options
Diffstat (limited to 'modules/snoopy')
-rw-r--r-- | modules/snoopy/AUTHORS | 11 | ||||
-rw-r--r-- | modules/snoopy/COPYING.lib | 458 | ||||
-rw-r--r-- | modules/snoopy/ChangeLog | 105 | ||||
-rw-r--r-- | modules/snoopy/FAQ | 14 | ||||
-rw-r--r-- | modules/snoopy/NEWS | 61 | ||||
-rw-r--r-- | modules/snoopy/Snoopy.class.php | 1250 | ||||
-rw-r--r-- | modules/snoopy/TODO | 9 |
7 files changed, 1908 insertions, 0 deletions
diff --git a/modules/snoopy/AUTHORS b/modules/snoopy/AUTHORS new file mode 100644 index 00000000..dbbe3f4f --- /dev/null +++ b/modules/snoopy/AUTHORS @@ -0,0 +1,11 @@ +Monte Ohrt <monte@ispi.net> + - main Snoopy work + +Andrei Zmievski <andrei@ispi.net> + - miscellaneous fixes + - read timeout support + - file submission capability + +Gene Wood <gene_wood@users.sourceforge.net> + - bug fixes + - security fixes diff --git a/modules/snoopy/COPYING.lib b/modules/snoopy/COPYING.lib new file mode 100644 index 00000000..3b204400 --- /dev/null +++ b/modules/snoopy/COPYING.lib @@ -0,0 +1,458 @@ + GNU LESSER GENERAL PUBLIC LICENSE + Version 2.1, February 1999 + + Copyright (C) 1991, 1999 Free Software Foundation, Inc. + 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + Everyone is permitted to copy and distribute verbatim copies + of this license document, but changing it is not allowed. + +[This is the first released version of the Lesser GPL. It also counts + as the successor of the GNU Library Public License, version 2, hence + the version number 2.1.] + + Preamble + + The licenses for most software are designed to take away your +freedom to share and change it. By contrast, the GNU General Public +Licenses are intended to guarantee your freedom to share and change +free software--to make sure the software is free for all its users. + + This license, the Lesser General Public License, applies to some +specially designated software packages--typically libraries--of the +Free Software Foundation and other authors who decide to use it. You +can use it too, but we suggest you first think carefully about whether +this license or the ordinary General Public License is the better +strategy to use in any particular case, based on the explanations below. + + When we speak of free software, we are referring to freedom of use, +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 this service if you wish); that you receive source code or can get +it if you want it; that you can change the software and use pieces of +it in new free programs; and that you are informed that you can do +these things. + + To protect your rights, we need to make restrictions that forbid +distributors to deny you these rights or to ask you to surrender these +rights. These restrictions translate to certain responsibilities for +you if you distribute copies of the library or if you modify it. + + For example, if you distribute copies of the library, whether gratis +or for a fee, you must give the recipients all the rights that we gave +you. You must make sure that they, too, receive or can get the source +code. If you link other code with the library, you must provide +complete object files to the recipients, so that they can relink them +with the library after making changes to the library and recompiling +it. And you must show them these terms so they know their rights. + + We protect your rights with a two-step method: (1) we copyright the +library, and (2) we offer you this license, which gives you legal +permission to copy, distribute and/or modify the library. + + To protect each distributor, we want to make it very clear that +there is no warranty for the free library. Also, if the library is +modified by someone else and passed on, the recipients should know +that what they have is not the original version, so that the original +author's reputation will not be affected by problems that might be +introduced by others. + + Finally, software patents pose a constant threat to the existence of +any free program. We wish to make sure that a company cannot +effectively restrict the users of a free program by obtaining a +restrictive license from a patent holder. Therefore, we insist that +any patent license obtained for a version of the library must be +consistent with the full freedom of use specified in this license. + + Most GNU software, including some libraries, is covered by the +ordinary GNU General Public License. This license, the GNU Lesser +General Public License, applies to certain designated libraries, and +is quite different from the ordinary General Public License. We use +this license for certain libraries in order to permit linking those +libraries into non-free programs. + + When a program is linked with a library, whether statically or using +a shared library, the combination of the two is legally speaking a +combined work, a derivative of the original library. The ordinary +General Public License therefore permits such linking only if the +entire combination fits its criteria of freedom. The Lesser General +Public License permits more lax criteria for linking other code with +the library. + + We call this license the "Lesser" General Public License because it +does Less to protect the user's freedom than the ordinary General +Public License. It also provides other free software developers Less +of an advantage over competing non-free programs. These disadvantages +are the reason we use the ordinary General Public License for many +libraries. However, the Lesser license provides advantages in certain +special circumstances. + + For example, on rare occasions, there may be a special need to +encourage the widest possible use of a certain library, so that it becomes +a de-facto standard. To achieve this, non-free programs must be +allowed to use the library. A more frequent case is that a free +library does the same job as widely used non-free libraries. In this +case, there is little to gain by limiting the free library to free +software only, so we use the Lesser General Public License. + + In other cases, permission to use a particular library in non-free +programs enables a greater number of people to use a large body of +free software. For example, permission to use the GNU C Library in +non-free programs enables many more people to use the whole GNU +operating system, as well as its variant, the GNU/Linux operating +system. + + Although the Lesser General Public License is Less protective of the +users' freedom, it does ensure that the user of a program that is +linked with the Library has the freedom and the wherewithal to run +that program using a modified version of the Library. + + The precise terms and conditions for copying, distribution and +modification follow. Pay close attention to the difference between a +"work based on the library" and a "work that uses the library". The +former contains code derived from the library, whereas the latter must +be combined with the library in order to run. + + GNU LESSER GENERAL PUBLIC LICENSE + TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION + + 0. This License Agreement applies to any software library or other +program which contains a notice placed by the copyright holder or +other authorized party saying it may be distributed under the terms of +this Lesser General Public License (also called "this License"). +Each licensee is addressed as "you". + + A "library" means a collection of software functions and/or data +prepared so as to be conveniently linked with application programs +(which use some of those functions and data) to form executables. + + The "Library", below, refers to any such software library or work +which has been distributed under these terms. A "work based on the +Library" means either the Library or any derivative work under +copyright law: that is to say, a work containing the Library or a +portion of it, either verbatim or with modifications and/or translated +straightforwardly into another language. (Hereinafter, translation is +included without limitation in the term "modification".) + + "Source code" for a work means the preferred form of the work for +making modifications to it. For a library, complete source code means +all the source code for all modules it contains, plus any associated +interface definition files, plus the scripts used to control compilation +and installation of the library. + + Activities other than copying, distribution and modification are not +covered by this License; they are outside its scope. The act of +running a program using the Library is not restricted, and output from +such a program is covered only if its contents constitute a work based +on the Library (independent of the use of the Library in a tool for +writing it). Whether that is true depends on what the Library does +and what the program that uses the Library does. + + 1. You may copy and distribute verbatim copies of the Library's +complete source code as you receive it, in any medium, provided that +you conspicuously and appropriately publish on each copy an +appropriate copyright notice and disclaimer of warranty; keep intact +all the notices that refer to this License and to the absence of any +warranty; and distribute a copy of this License along with the +Library. + + You may charge a fee for the physical act of transferring a copy, +and you may at your option offer warranty protection in exchange for a +fee. + + 2. You may modify your copy or copies of the Library or any portion +of it, thus forming a work based on the Library, and copy and +distribute such modifications or work under the terms of Section 1 +above, provided that you also meet all of these conditions: + + a) The modified work must itself be a software library. + + b) You must cause the files modified to carry prominent notices + stating that you changed the files and the date of any change. + + c) You must cause the whole of the work to be licensed at no + charge to all third parties under the terms of this License. + + d) If a facility in the modified Library refers to a function or a + table of data to be supplied by an application program that uses + the facility, other than as an argument passed when the facility + is invoked, then you must make a good faith effort to ensure that, + in the event an application does not supply such function or + table, the facility still operates, and performs whatever part of + its purpose remains meaningful. + + (For example, a function in a library to compute square roots has + a purpose that is entirely well-defined independent of the + application. Therefore, Subsection 2d requires that any + application-supplied function or table used by this function must + be optional: if the application does not supply it, the square + root function must still compute square roots.) + +These requirements apply to the modified work as a whole. If +identifiable sections of that work are not derived from the Library, +and can be reasonably considered independent and separate works in +themselves, then this License, and its terms, do not apply to those +sections when you distribute them as separate works. But when you +distribute the same sections as part of a whole which is a work based +on the Library, the distribution of the whole must be on the terms of +this License, whose permissions for other licensees extend to the +entire whole, and thus to each and every part regardless of who wrote +it. + +Thus, it is not the intent of this section to claim rights or contest +your rights to work written entirely by you; rather, the intent is to +exercise the right to control the distribution of derivative or +collective works based on the Library. + +In addition, mere aggregation of another work not based on the Library +with the Library (or with a work based on the Library) on a volume of +a storage or distribution medium does not bring the other work under +the scope of this License. + + 3. You may opt to apply the terms of the ordinary GNU General Public +License instead of this License to a given copy of the Library. To do +this, you must alter all the notices that refer to this License, so +that they refer to the ordinary GNU General Public License, version 2, +instead of to this License. (If a newer version than version 2 of the +ordinary GNU General Public License has appeared, then you can specify +that version instead if you wish.) Do not make any other change in +these notices. + + Once this change is made in a given copy, it is irreversible for +that copy, so the ordinary GNU General Public License applies to all +subsequent copies and derivative works made from that copy. + + This option is useful when you wish to copy part of the code of +the Library into a program that is not a library. + + 4. You may copy and distribute the Library (or a portion or +derivative of it, under Section 2) in object code or executable form +under the terms of Sections 1 and 2 above provided that you accompany +it with the complete corresponding machine-readable source code, which +must be distributed under the terms of Sections 1 and 2 above on a +medium customarily used for software interchange. + + If distribution of object code is made by offering access to copy +from a designated place, then offering equivalent access to copy the +source code from the same place satisfies the requirement to +distribute the source code, even though third parties are not +compelled to copy the source along with the object code. + + 5. A program that contains no derivative of any portion of the +Library, but is designed to work with the Library by being compiled or +linked with it, is called a "work that uses the Library". Such a +work, in isolation, is not a derivative work of the Library, and +therefore falls outside the scope of this License. + + However, linking a "work that uses the Library" with the Library +creates an executable that is a derivative of the Library (because it +contains portions of the Library), rather than a "work that uses the +library". The executable is therefore covered by this License. +Section 6 states terms for distribution of such executables. + + When a "work that uses the Library" uses material from a header file +that is part of the Library, the object code for the work may be a +derivative work of the Library even though the source code is not. +Whether this is true is especially significant if the work can be +linked without the Library, or if the work is itself a library. The +threshold for this to be true is not precisely defined by law. + + If such an object file uses only numerical parameters, data +structure layouts and accessors, and small macros and small inline +functions (ten lines or less in length), then the use of the object +file is unrestricted, regardless of whether it is legally a derivative +work. (Executables containing this object code plus portions of the +Library will still fall under Section 6.) + + Otherwise, if the work is a derivative of the Library, you may +distribute the object code for the work under the terms of Section 6. +Any executables containing that work also fall under Section 6, +whether or not they are linked directly with the Library itself. + + 6. As an exception to the Sections above, you may also combine or +link a "work that uses the Library" with the Library to produce a +work containing portions of the Library, and distribute that work +under terms of your choice, provided that the terms permit +modification of the work for the customer's own use and reverse +engineering for debugging such modifications. + + You must give prominent notice with each copy of the work that the +Library is used in it and that the Library and its use are covered by +this License. You must supply a copy of this License. If the work +during execution displays copyright notices, you must include the +copyright notice for the Library among them, as well as a reference +directing the user to the copy of this License. Also, you must do one +of these things: + + a) Accompany the work with the complete corresponding + machine-readable source code for the Library including whatever + changes were used in the work (which must be distributed under + Sections 1 and 2 above); and, if the work is an executable linked + with the Library, with the complete machine-readable "work that + uses the Library", as object code and/or source code, so that the + user can modify the Library and then relink to produce a modified + executable containing the modified Library. (It is understood + that the user who changes the contents of definitions files in the + Library will not necessarily be able to recompile the application + to use the modified definitions.) + + b) Use a suitable shared library mechanism for linking with the + Library. A suitable mechanism is one that (1) uses at run time a + copy of the library already present on the user's computer system, + rather than copying library functions into the executable, and (2) + will operate properly with a modified version of the library, if + the user installs one, as long as the modified version is + interface-compatible with the version that the work was made with. + + c) Accompany the work with a written offer, valid for at + least three years, to give the same user the materials + specified in Subsection 6a, above, for a charge no more + than the cost of performing this distribution. + + d) If distribution of the work is made by offering access to copy + from a designated place, offer equivalent access to copy the above + specified materials from the same place. + + e) Verify that the user has already received a copy of these + materials or that you have already sent this user a copy. + + For an executable, the required form of the "work that uses the +Library" must include any data and utility programs needed for +reproducing the executable from it. However, as a special exception, +the materials to be distributed need not include anything that is +normally distributed (in either source or binary form) with the major +components (compiler, kernel, and so on) of the operating system on +which the executable runs, unless that component itself accompanies +the executable. + + It may happen that this requirement contradicts the license +restrictions of other proprietary libraries that do not normally +accompany the operating system. Such a contradiction means you cannot +use both them and the Library together in an executable that you +distribute. + + 7. You may place library facilities that are a work based on the +Library side-by-side in a single library together with other library +facilities not covered by this License, and distribute such a combined +library, provided that the separate distribution of the work based on +the Library and of the other library facilities is otherwise +permitted, and provided that you do these two things: + + a) Accompany the combined library with a copy of the same work + based on the Library, uncombined with any other library + facilities. This must be distributed under the terms of the + Sections above. + + b) Give prominent notice with the combined library of the fact + that part of it is a work based on the Library, and explaining + where to find the accompanying uncombined form of the same work. + + 8. You may not copy, modify, sublicense, link with, or distribute +the Library except as expressly provided under this License. Any +attempt otherwise to copy, modify, sublicense, link with, or +distribute the Library is void, and will automatically terminate your +rights under this License. However, parties who have received copies, +or rights, from you under this License will not have their licenses +terminated so long as such parties remain in full compliance. + + 9. You are not required to accept this License, since you have not +signed it. However, nothing else grants you permission to modify or +distribute the Library or its derivative works. These actions are +prohibited by law if you do not accept this License. Therefore, by +modifying or distributing the Library (or any work based on the +Library), you indicate your acceptance of this License to do so, and +all its terms and conditions for copying, distributing or modifying +the Library or works based on it. + + 10. Each time you redistribute the Library (or any work based on the +Library), the recipient automatically receives a license from the +original licensor to copy, distribute, link with or modify the Library +subject to these terms and conditions. You may not impose any further +restrictions on the recipients' exercise of the rights granted herein. +You are not responsible for enforcing compliance by third parties with +this License. + + 11. If, as a consequence of a court judgment or allegation of patent +infringement or for any other reason (not limited to patent issues), +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 +distribute so as to satisfy simultaneously your obligations under this +License and any other pertinent obligations, then as a consequence you +may not distribute the Library at all. For example, if a patent +license would not permit royalty-free redistribution of the Library by +all those who receive copies directly or indirectly through you, then +the only way you could satisfy both it and this License would be to +refrain entirely from distribution of the Library. + +If any portion of this section is held invalid or unenforceable under any +particular circumstance, the balance of the section is intended to apply, +and the section as a whole is intended to apply in other circumstances. + +It is not the purpose of this section to induce you to infringe any +patents or other property right claims or to contest validity of any +such claims; this section has the sole purpose of protecting the +integrity of the free software distribution system which is +implemented by public license practices. Many people have made +generous contributions to the wide range of software distributed +through that system in reliance on consistent application of that +system; it is up to the author/donor to decide if he or she is willing +to distribute software through any other system and a licensee cannot +impose that choice. + +This section is intended to make thoroughly clear what is believed to +be a consequence of the rest of this License. + + 12. If the distribution and/or use of the Library is restricted in +certain countries either by patents or by copyrighted interfaces, the +original copyright holder who places the Library under this License may add +an explicit geographical distribution limitation excluding those countries, +so that distribution is permitted only in or among countries not thus +excluded. In such case, this License incorporates the limitation as if +written in the body of this License. + + 13. The Free Software Foundation may publish revised and/or new +versions of the Lesser 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 Library +specifies a version number of this License which applies to it and +"any later version", you have the option of following the terms and +conditions either of that version or of any later version published by +the Free Software Foundation. If the Library does not specify a +license version number, you may choose any version ever published by +the Free Software Foundation. + + 14. If you wish to incorporate parts of the Library into other free +programs whose distribution conditions are incompatible with these, +write to the author to ask for permission. For software which is +copyrighted by the Free Software Foundation, write to the Free +Software Foundation; we sometimes make exceptions for this. Our +decision will be guided by the two goals of preserving the free status +of all derivatives of our free software and of promoting the sharing +and reuse of software generally. + + NO WARRANTY + + 15. BECAUSE THE LIBRARY IS LICENSED FREE OF CHARGE, THERE IS NO +WARRANTY FOR THE LIBRARY, TO THE EXTENT PERMITTED BY APPLICABLE LAW. +EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR +OTHER PARTIES PROVIDE THE LIBRARY "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 +LIBRARY IS WITH YOU. SHOULD THE LIBRARY PROVE DEFECTIVE, YOU ASSUME +THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION. + + 16. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN +WRITING WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY +AND/OR REDISTRIBUTE THE LIBRARY 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 +LIBRARY (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 LIBRARY TO OPERATE WITH ANY OTHER SOFTWARE), EVEN IF +SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH +DAMAGES. + + END OF TERMS AND CONDITIONS diff --git a/modules/snoopy/ChangeLog b/modules/snoopy/ChangeLog new file mode 100644 index 00000000..f4557613 --- /dev/null +++ b/modules/snoopy/ChangeLog @@ -0,0 +1,105 @@ +Version 1.2.4 +------------- + + - fix command line escapement vulnerability with execution of curl binary on https fetches (mohrt) + +Version 1.2.3 +----------- + - updated the version variable in the code to reflect the new version number + - fixed a typo that I introduced in 1.2.2 (the first character of the file is a "z" (gene_wood, Marc Desrousseaux, Jan Pedersen) + - fixed BUG # 1328793 : fetch is case sensetive when it comes to the scheme (http / https) (gene_wood) + +Version 1.2.2 +----------- + - incorporated PATCH # 985470 : pass port information in http 1.1 Host header ( http://www.w3.org/Protocols/rfc2616/rfc2616-sec14.html#sec14.23 ) (gene_wood) + - fixed BUG # 1110049 : redirect is case sensitive + - fixed bug in security bugfix from 1.2.1 (gene_wood, kellan, zaruba) + +Version 1.2.1 +----------- + - fixed potential security issue with unchecked variables being passed to exec (for https with curl) (gene_wood) + - fixed BUG # 1086830 : submitlinks,fetchlinks and submittext expandlinks with the URI of the original page not the refreshed page (gene_wood) + - fixed BUG # 1077870 : Snoopy can't deal with multiple spaces in a refresh tag (gene_wood) + - fixed BUG # 864047 : Root relative links are treated as relative (gene_wood) + - fixed BUG # 1097134 : Undefined URI_PARTS["path"] generates Notice (gene_wood) + +Version 1.2 +----------- + - fixed BUG # 1014823 : Meta redirect regex inaccurate (gene_wood) + - fixed BUG # 999079 : Trailing slashes not removed in uri passed to fetchlinks (gene_wood) + - fixed BUG # 642958 and 912060 : $URI_PARTS["query"] causing undefined variable notices (gene_wood) + - fixed BUG # 626849 : cURL security risk (Tajh Leitso, gene_wood) + - fixed BUG # 626849 : Corrects the redirect function under the submit functions (Tajh Leitso, gene_wood) + - fixed BUG # 912060 : Undefined variable: postdata (gene_wood) + - fixed BUG # 858526 : win32 tmp/$headerfile create error (gene_wood) + - fixed BUG # 929682 : Called undefined function is_executable() on line 194. (gene_wood) + - fixed BUG # 859711 : typo: http://snoopy.sourceforge.com (gene_wood) + - fixed BUG # 852993 : double urlencoding breaks redirect (gene_wood) + - added proxy user/pass support (Robert Zwink, Monte) + - fixed post data array problem (stefan, Monte) + +Version 1.01 +----------- + - fixed problem with PHP 4.3.2 and fread() (Monte) + +Version 1.0 +----------- + - added textarea to stripform functionality (Monte) + - fixed multiple cookie setting problem (Monte) + - fixed problem where extra text inside <frame src (Monte) + - fixed problem where extra text inside <a href (Monte) + - removed http request header from curl fetched + documents, not needed (Monte) + - added carriage return to newlines on headers (Monte) + - fixed bug with curl, removed single quotes + - fixed bug with curl and "&" in the URL + - added ability to post files. (Andrei) + +Version 0.94 +------------ + - Added fetchform() function + - Fixed misc issues with frames + - Added SSL support via cURL + - fixed bug with posting arrays of data + - added status variable for http status + +Version 0.93 +------------ + - fixed bug with hostname match in a redirect location header + - added $lastredirectaddr variable + +Version 0.92 +------------ + - fixed redirect bug with MS web server + - added ability to pass set cookies through redirects + - added ability to traverse html frames + +Version 0.91 +------------ + - fixed bug with return headers being overwritten. + Please read the NEWS file for important notes. (Monte) + +Version 0.9 +----------- + - added support for read timeouts (Andrei) + - standardized distribution (Andrei) + +Version 0.1e +------------ + - fixed bug in fetchlinks logic (Monte) + +Version 0.1d +------------ + - fixed redirect bug without fully qualified url (Monte) + +Version 0.1c +------------ + - fixed bug on submitting formvars after a redirect (Monte) + +Version 0.1b +------------ + - fixed bug to allow empty post vars on a submit (Monte) + +Version 0.1 +------------ + - initial release (Monte) diff --git a/modules/snoopy/FAQ b/modules/snoopy/FAQ new file mode 100644 index 00000000..89c251ae --- /dev/null +++ b/modules/snoopy/FAQ @@ -0,0 +1,14 @@ +Q: Why can't I fetch https pages? +A: Using Snoopy to fetch an https page requires curl. Check if curl is installed on your host. If curl is installed, it may be located in a different place than the default. By default Snoopy looks for curl in /usr/local/bin/curl. Run 'which curl' and find out your location. If it differs from the default, then you'll need to set the $snoopy->curl_path variable to the location of your curl installation. Here's an example of the code : + include "Snoopy.class.php"; + $snoopy = new Snoopy; + $snoopy->curl_path="/usr/bin/curl"; + +Q: where does the function preg_match_all come from? +A: PCRE functions in PHP 3.0.9 and later + +Q: I get the error: Warning: Wrong parameter count for fsockopen() +A: Upgrade your verion of PHP to 3.0.9 or later + +Q: Snoopy cuts of my results every time. What's wrong? +A: Upgrade your verion of PHP to 3.0.9 or later diff --git a/modules/snoopy/NEWS b/modules/snoopy/NEWS new file mode 100644 index 00000000..a2ae3d9b --- /dev/null +++ b/modules/snoopy/NEWS @@ -0,0 +1,61 @@ +RELEASE NOTE: v1.2.4 +October 22, 2008 + +https fetches were not properly escaping shell args for curl binary execution. This is fixed. + +RELEASE NOTE: v1.2.3 +November 7, 2005 + +A typo was introduced in 1.2.2 which broke the whole release. This has been fixed. +A couple small fixes have been implemented also. + +RELEASE NOTE: v1.2.2 +October 30, 2005 + +Fixed a bug with the bugfix for the security hole. + +RELEASE NOTE: v1.2.1 +October 24, 2005 + +Fixed a few outstanding bugs and a potential security hole. + +RELEASE NOTE: v1.2 +November 17, 2004 + +Fixed a number of outstanding bugs. + +RELEASE NOTE: v1.01 + +PHP fixed a bug with fread() which consequently broke the way Snoopy called it. This has been fixed. +Renamed Snoopy.class.inc to Snoopy.class.php for proper file extention. + +RELEASE NOTE: v1.0 + +Added fetchform() function for fetching form elements from an html page. +For SSL support, you must have cURL installed. see http://curl.haxx.se +for details. Snoopy does not use the cURL library fuctions within PHP, +as these are not stable as of this Snoopy release. +Fixed bug with posting arrays of data. +Added status variable to track http status. +Several other bug fixes, see Changelog. +RELEASE NOTE: v0.93 + +A bug was fixed with redirection headers not containing the hostname, doubling up the redirection location URL. + +There is also a new variable, $lastredirectaddr that contains the last redirection URL. + +RELEASE NOTE: v0.92 +March 9, 2000 + +A bug was fixed with redirection on MS web servers. Also, cookies are now passed through redirects. + +This release also adds the ability to traverse html framed pages. Just set $maxframes to the recursion depth you want to allow, and results are returned in $this->results as an array. See the README for an example. + +-Monte + +RELEASE NOTE: v0.91 +February 22, 2000 + +In previous versions of Snoopy, $this->header was an array containing key/value pairs of headers returned from fetched content, not including HTTP and GET headers. If a key value was the same, the old value was overwritten (Two Set-Cookie: headers for example). This was overcome by making $this->header a simple array containing every header returned. Therefore, it will now be up to the programmer to split these headers into key/value pairs if so desired. + +-Monte diff --git a/modules/snoopy/Snoopy.class.php b/modules/snoopy/Snoopy.class.php new file mode 100644 index 00000000..53116105 --- /dev/null +++ b/modules/snoopy/Snoopy.class.php @@ -0,0 +1,1250 @@ +<?php + +/************************************************* + +Snoopy - the PHP net client +Author: Monte Ohrt <monte@ispi.net> +Copyright (c): 1999-2008 New Digital Group, all rights reserved +Version: 1.2.4 + + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library 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 + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + +You may contact the author of Snoopy by e-mail at: +monte@ohrt.com + +The latest version of Snoopy can be obtained from: +http://snoopy.sourceforge.net/ + +*************************************************/ + +class Snoopy +{ + /**** Public variables ****/ + + /* user definable vars */ + + var $host = "www.php.net"; // host name we are connecting to + var $port = 80; // port we are connecting to + var $proxy_host = ""; // proxy host to use + var $proxy_port = ""; // proxy port to use + var $proxy_user = ""; // proxy user to use + var $proxy_pass = ""; // proxy password to use + + var $agent = "Snoopy v1.2.4"; // agent we masquerade as + var $referer = ""; // referer info to pass + var $cookies = array(); // array of cookies to pass + // $cookies["username"]="joe"; + var $rawheaders = array(); // array of raw headers to send + // $rawheaders["Content-type"]="text/html"; + + var $maxredirs = 5; // http redirection depth maximum. 0 = disallow + var $lastredirectaddr = ""; // contains address of last redirected address + var $offsiteok = true; // allows redirection off-site + var $maxframes = 0; // frame content depth maximum. 0 = disallow + var $expandlinks = true; // expand links to fully qualified URLs. + // this only applies to fetchlinks() + // submitlinks(), and submittext() + var $passcookies = true; // pass set cookies back through redirects + // NOTE: this currently does not respect + // dates, domains or paths. + + var $user = ""; // user for http authentication + var $pass = ""; // password for http authentication + + // http accept types + var $accept = "image/gif, image/x-xbitmap, image/jpeg, image/pjpeg, */*"; + + var $results = ""; // where the content is put + + var $error = ""; // error messages sent here + var $response_code = ""; // response code returned from server + var $headers = array(); // headers returned from server sent here + var $maxlength = 500000; // max return data length (body) + var $read_timeout = 0; // timeout on read operations, in seconds + // supported only since PHP 4 Beta 4 + // set to 0 to disallow timeouts + var $timed_out = false; // if a read operation timed out + var $status = 0; // http request status + + var $temp_dir = "/tmp"; // temporary directory that the webserver + // has permission to write to. + // under Windows, this should be C:\temp + + var $curl_path = "/usr/local/bin/curl"; + // Snoopy will use cURL for fetching + // SSL content if a full system path to + // the cURL binary is supplied here. + // set to false if you do not have + // cURL installed. See http://curl.haxx.se + // for details on installing cURL. + // Snoopy does *not* use the cURL + // library functions built into php, + // as these functions are not stable + // as of this Snoopy release. + + /**** Private variables ****/ + + var $_maxlinelen = 4096; // max line length (headers) + + var $_httpmethod = "GET"; // default http request method + var $_httpversion = "HTTP/1.0"; // default http request version + var $_submit_method = "POST"; // default submit method + var $_submit_type = "application/x-www-form-urlencoded"; // default submit type + var $_mime_boundary = ""; // MIME boundary for multipart/form-data submit type + var $_redirectaddr = false; // will be set if page fetched is a redirect + var $_redirectdepth = 0; // increments on an http redirect + var $_frameurls = array(); // frame src urls + var $_framedepth = 0; // increments on frame depth + + var $_isproxy = false; // set if using a proxy server + var $_fp_timeout = 30; // timeout for socket connection + +/*======================================================================*\ + Function: fetch + Purpose: fetch the contents of a web page + (and possibly other protocols in the + future like ftp, nntp, gopher, etc.) + Input: $URI the location of the page to fetch + Output: $this->results the output text from the fetch +\*======================================================================*/ + + function fetch($URI) + { + + //preg_match("|^([^:]+)://([^:/]+)(:[\d]+)*(.*)|",$URI,$URI_PARTS); + $URI_PARTS = parse_url($URI); + if (!empty($URI_PARTS["user"])) + $this->user = $URI_PARTS["user"]; + if (!empty($URI_PARTS["pass"])) + $this->pass = $URI_PARTS["pass"]; + if (empty($URI_PARTS["query"])) + $URI_PARTS["query"] = ''; + if (empty($URI_PARTS["path"])) + $URI_PARTS["path"] = ''; + + switch(strtolower($URI_PARTS["scheme"])) + { + case "http": + $this->host = $URI_PARTS["host"]; + if(!empty($URI_PARTS["port"])) + $this->port = $URI_PARTS["port"]; + if($this->_connect($fp)) + { + if($this->_isproxy) + { + // using proxy, send entire URI + $this->_httprequest($URI,$fp,$URI,$this->_httpmethod); + } + else + { + $path = $URI_PARTS["path"].($URI_PARTS["query"] ? "?".$URI_PARTS["query"] : ""); + // no proxy, send only the path + $this->_httprequest($path, $fp, $URI, $this->_httpmethod); + } + + $this->_disconnect($fp); + + if($this->_redirectaddr) + { + /* url was redirected, check if we've hit the max depth */ + if($this->maxredirs > $this->_redirectdepth) + { + // only follow redirect if it's on this site, or offsiteok is true + if(preg_match("|^http://".preg_quote($this->host)."|i",$this->_redirectaddr) || $this->offsiteok) + { + /* follow the redirect */ + $this->_redirectdepth++; + $this->lastredirectaddr=$this->_redirectaddr; + $this->fetch($this->_redirectaddr); + } + } + } + + if($this->_framedepth < $this->maxframes && count($this->_frameurls) > 0) + { + $frameurls = $this->_frameurls; + $this->_frameurls = array(); + + while(list(,$frameurl) = each($frameurls)) + { + if($this->_framedepth < $this->maxframes) + { + $this->fetch($frameurl); + $this->_framedepth++; + } + else + break; + } + } + } + else + { + return false; + } + return true; + break; + case "https": + if(!$this->curl_path) + return false; + if(function_exists("is_executable")) + if (!is_executable($this->curl_path)) + return false; + $this->host = $URI_PARTS["host"]; + if(!empty($URI_PARTS["port"])) + $this->port = $URI_PARTS["port"]; + if($this->_isproxy) + { + // using proxy, send entire URI + $this->_httpsrequest($URI,$URI,$this->_httpmethod); + } + else + { + $path = $URI_PARTS["path"].($URI_PARTS["query"] ? "?".$URI_PARTS["query"] : ""); + // no proxy, send only the path + $this->_httpsrequest($path, $URI, $this->_httpmethod); + } + + if($this->_redirectaddr) + { + /* url was redirected, check if we've hit the max depth */ + if($this->maxredirs > $this->_redirectdepth) + { + // only follow redirect if it's on this site, or offsiteok is true + if(preg_match("|^http://".preg_quote($this->host)."|i",$this->_redirectaddr) || $this->offsiteok) + { + /* follow the redirect */ + $this->_redirectdepth++; + $this->lastredirectaddr=$this->_redirectaddr; + $this->fetch($this->_redirectaddr); + } + } + } + + if($this->_framedepth < $this->maxframes && count($this->_frameurls) > 0) + { + $frameurls = $this->_frameurls; + $this->_frameurls = array(); + + while(list(,$frameurl) = each($frameurls)) + { + if($this->_framedepth < $this->maxframes) + { + $this->fetch($frameurl); + $this->_framedepth++; + } + else + break; + } + } + return true; + break; + default: + // not a valid protocol + $this->error = 'Invalid protocol "'.$URI_PARTS["scheme"].'"\n'; + return false; + break; + } + return true; + } + +/*======================================================================*\ + Function: submit + Purpose: submit an http form + Input: $URI the location to post the data + $formvars the formvars to use. + format: $formvars["var"] = "val"; + $formfiles an array of files to submit + format: $formfiles["var"] = "/dir/filename.ext"; + Output: $this->results the text output from the post +\*======================================================================*/ + + function submit($URI, $formvars="", $formfiles="") + { + unset($postdata); + + $postdata = $this->_prepare_post_body($formvars, $formfiles); + + $URI_PARTS = parse_url($URI); + if (!empty($URI_PARTS["user"])) + $this->user = $URI_PARTS["user"]; + if (!empty($URI_PARTS["pass"])) + $this->pass = $URI_PARTS["pass"]; + if (empty($URI_PARTS["query"])) + $URI_PARTS["query"] = ''; + if (empty($URI_PARTS["path"])) + $URI_PARTS["path"] = ''; + + switch(strtolower($URI_PARTS["scheme"])) + { + case "http": + $this->host = $URI_PARTS["host"]; + if(!empty($URI_PARTS["port"])) + $this->port = $URI_PARTS["port"]; + if($this->_connect($fp)) + { + if($this->_isproxy) + { + // using proxy, send entire URI + $this->_httprequest($URI,$fp,$URI,$this->_submit_method,$this->_submit_type,$postdata); + } + else + { + $path = $URI_PARTS["path"].($URI_PARTS["query"] ? "?".$URI_PARTS["query"] : ""); + // no proxy, send only the path + $this->_httprequest($path, $fp, $URI, $this->_submit_method, $this->_submit_type, $postdata); + } + + $this->_disconnect($fp); + + if($this->_redirectaddr) + { + /* url was redirected, check if we've hit the max depth */ + if($this->maxredirs > $this->_redirectdepth) + { + if(!preg_match("|^".$URI_PARTS["scheme"]."://|", $this->_redirectaddr)) + $this->_redirectaddr = $this->_expandlinks($this->_redirectaddr,$URI_PARTS["scheme"]."://".$URI_PARTS["host"]); + + // only follow redirect if it's on this site, or offsiteok is true + if(preg_match("|^http://".preg_quote($this->host)."|i",$this->_redirectaddr) || $this->offsiteok) + { + /* follow the redirect */ + $this->_redirectdepth++; + $this->lastredirectaddr=$this->_redirectaddr; + if( strpos( $this->_redirectaddr, "?" ) > 0 ) + $this->fetch($this->_redirectaddr); // the redirect has changed the request method from post to get + else + $this->submit($this->_redirectaddr,$formvars, $formfiles); + } + } + } + + if($this->_framedepth < $this->maxframes && count($this->_frameurls) > 0) + { + $frameurls = $this->_frameurls; + $this->_frameurls = array(); + + while(list(,$frameurl) = each($frameurls)) + { + if($this->_framedepth < $this->maxframes) + { + $this->fetch($frameurl); + $this->_framedepth++; + } + else + break; + } + } + + } + else + { + return false; + } + return true; + break; + case "https": + if(!$this->curl_path) + return false; + if(function_exists("is_executable")) + if (!is_executable($this->curl_path)) + return false; + $this->host = $URI_PARTS["host"]; + if(!empty($URI_PARTS["port"])) + $this->port = $URI_PARTS["port"]; + if($this->_isproxy) + { + // using proxy, send entire URI + $this->_httpsrequest($URI, $URI, $this->_submit_method, $this->_submit_type, $postdata); + } + else + { + $path = $URI_PARTS["path"].($URI_PARTS["query"] ? "?".$URI_PARTS["query"] : ""); + // no proxy, send only the path + $this->_httpsrequest($path, $URI, $this->_submit_method, $this->_submit_type, $postdata); + } + + if($this->_redirectaddr) + { + /* url was redirected, check if we've hit the max depth */ + if($this->maxredirs > $this->_redirectdepth) + { + if(!preg_match("|^".$URI_PARTS["scheme"]."://|", $this->_redirectaddr)) + $this->_redirectaddr = $this->_expandlinks($this->_redirectaddr,$URI_PARTS["scheme"]."://".$URI_PARTS["host"]); + + // only follow redirect if it's on this site, or offsiteok is true + if(preg_match("|^http://".preg_quote($this->host)."|i",$this->_redirectaddr) || $this->offsiteok) + { + /* follow the redirect */ + $this->_redirectdepth++; + $this->lastredirectaddr=$this->_redirectaddr; + if( strpos( $this->_redirectaddr, "?" ) > 0 ) + $this->fetch($this->_redirectaddr); // the redirect has changed the request method from post to get + else + $this->submit($this->_redirectaddr,$formvars, $formfiles); + } + } + } + + if($this->_framedepth < $this->maxframes && count($this->_frameurls) > 0) + { + $frameurls = $this->_frameurls; + $this->_frameurls = array(); + + while(list(,$frameurl) = each($frameurls)) + { + if($this->_framedepth < $this->maxframes) + { + $this->fetch($frameurl); + $this->_framedepth++; + } + else + break; + } + } + return true; + break; + + default: + // not a valid protocol + $this->error = 'Invalid protocol "'.$URI_PARTS["scheme"].'"\n'; + return false; + break; + } + return true; + } + +/*======================================================================*\ + Function: fetchlinks + Purpose: fetch the links from a web page + Input: $URI where you are fetching from + Output: $this->results an array of the URLs +\*======================================================================*/ + + function fetchlinks($URI) + { + if ($this->fetch($URI)) + { + if($this->lastredirectaddr) + $URI = $this->lastredirectaddr; + if(is_array($this->results)) + { + for($x=0;$x<count($this->results);$x++) + $this->results[$x] = $this->_striplinks($this->results[$x]); + } + else + $this->results = $this->_striplinks($this->results); + + if($this->expandlinks) + $this->results = $this->_expandlinks($this->results, $URI); + return true; + } + else + return false; + } + +/*======================================================================*\ + Function: fetchform + Purpose: fetch the form elements from a web page + Input: $URI where you are fetching from + Output: $this->results the resulting html form +\*======================================================================*/ + + function fetchform($URI) + { + + if ($this->fetch($URI)) + { + + if(is_array($this->results)) + { + for($x=0;$x<count($this->results);$x++) + $this->results[$x] = $this->_stripform($this->results[$x]); + } + else + $this->results = $this->_stripform($this->results); + + return true; + } + else + return false; + } + + +/*======================================================================*\ + Function: fetchtext + Purpose: fetch the text from a web page, stripping the links + Input: $URI where you are fetching from + Output: $this->results the text from the web page +\*======================================================================*/ + + function fetchtext($URI) + { + if($this->fetch($URI)) + { + if(is_array($this->results)) + { + for($x=0;$x<count($this->results);$x++) + $this->results[$x] = $this->_striptext($this->results[$x]); + } + else + $this->results = $this->_striptext($this->results); + return true; + } + else + return false; + } + +/*======================================================================*\ + Function: submitlinks + Purpose: grab links from a form submission + Input: $URI where you are submitting from + Output: $this->results an array of the links from the post +\*======================================================================*/ + + function submitlinks($URI, $formvars="", $formfiles="") + { + if($this->submit($URI,$formvars, $formfiles)) + { + if($this->lastredirectaddr) + $URI = $this->lastredirectaddr; + if(is_array($this->results)) + { + for($x=0;$x<count($this->results);$x++) + { + $this->results[$x] = $this->_striplinks($this->results[$x]); + if($this->expandlinks) + $this->results[$x] = $this->_expandlinks($this->results[$x],$URI); + } + } + else + { + $this->results = $this->_striplinks($this->results); + if($this->expandlinks) + $this->results = $this->_expandlinks($this->results,$URI); + } + return true; + } + else + return false; + } + +/*======================================================================*\ + Function: submittext + Purpose: grab text from a form submission + Input: $URI where you are submitting from + Output: $this->results the text from the web page +\*======================================================================*/ + + function submittext($URI, $formvars = "", $formfiles = "") + { + if($this->submit($URI,$formvars, $formfiles)) + { + if($this->lastredirectaddr) + $URI = $this->lastredirectaddr; + if(is_array($this->results)) + { + for($x=0;$x<count($this->results);$x++) + { + $this->results[$x] = $this->_striptext($this->results[$x]); + if($this->expandlinks) + $this->results[$x] = $this->_expandlinks($this->results[$x],$URI); + } + } + else + { + $this->results = $this->_striptext($this->results); + if($this->expandlinks) + $this->results = $this->_expandlinks($this->results,$URI); + } + return true; + } + else + return false; + } + + + +/*======================================================================*\ + Function: set_submit_multipart + Purpose: Set the form submission content type to + multipart/form-data +\*======================================================================*/ + function set_submit_multipart() + { + $this->_submit_type = "multipart/form-data"; + } + + +/*======================================================================*\ + Function: set_submit_normal + Purpose: Set the form submission content type to + application/x-www-form-urlencoded +\*======================================================================*/ + function set_submit_normal() + { + $this->_submit_type = "application/x-www-form-urlencoded"; + } + + + + +/*======================================================================*\ + Private functions +\*======================================================================*/ + + +/*======================================================================*\ + Function: _striplinks + Purpose: strip the hyperlinks from an html document + Input: $document document to strip. + Output: $match an array of the links +\*======================================================================*/ + + function _striplinks($document) + { + preg_match_all("'<\s*a\s.*?href\s*=\s* # find <a href= + ([\"\'])? # find single or double quote + (?(1) (.*?)\\1 | ([^\s\>]+)) # if quote found, match up to next matching + # quote, otherwise match up to next space + 'isx",$document,$links); + + + // catenate the non-empty matches from the conditional subpattern + + while(list($key,$val) = each($links[2])) + { + if(!empty($val)) + $match[] = $val; + } + + while(list($key,$val) = each($links[3])) + { + if(!empty($val)) + $match[] = $val; + } + + // return the links + return $match; + } + +/*======================================================================*\ + Function: _stripform + Purpose: strip the form elements from an html document + Input: $document document to strip. + Output: $match an array of the links +\*======================================================================*/ + + function _stripform($document) + { + preg_match_all("'<\/?(FORM|INPUT|SELECT|TEXTAREA|(OPTION))[^<>]*>(?(2)(.*(?=<\/?(option|select)[^<>]*>[\r\n]*)|(?=[\r\n]*))|(?=[\r\n]*))'Usi",$document,$elements); + + // catenate the matches + $match = implode("\r\n",$elements[0]); + + // return the links + return $match; + } + + + +/*======================================================================*\ + Function: _striptext + Purpose: strip the text from an html document + Input: $document document to strip. + Output: $text the resulting text +\*======================================================================*/ + + function _striptext($document) + { + + // I didn't use preg eval (//e) since that is only available in PHP 4.0. + // so, list your entities one by one here. I included some of the + // more common ones. + + $search = array("'<script[^>]*?>.*?</script>'si", // strip out javascript + "'<[\/\!]*?[^<>]*?>'si", // strip out html tags + "'([\r\n])[\s]+'", // strip out white space + "'&(quot|#34|#034|#x22);'i", // replace html entities + "'&(amp|#38|#038|#x26);'i", // added hexadecimal values + "'&(lt|#60|#060|#x3c);'i", + "'&(gt|#62|#062|#x3e);'i", + "'&(nbsp|#160|#xa0);'i", + "'&(iexcl|#161);'i", + "'&(cent|#162);'i", + "'&(pound|#163);'i", + "'&(copy|#169);'i", + "'&(reg|#174);'i", + "'&(deg|#176);'i", + "'&(#39|#039|#x27);'", + "'&(euro|#8364);'i", // europe + "'&a(uml|UML);'", // german + "'&o(uml|UML);'", + "'&u(uml|UML);'", + "'&A(uml|UML);'", + "'&O(uml|UML);'", + "'&U(uml|UML);'", + "'ß'i", + ); + $replace = array( "", + "", + "\\1", + "\"", + "&", + "<", + ">", + " ", + chr(161), + chr(162), + chr(163), + chr(169), + chr(174), + chr(176), + chr(39), + chr(128), + "ä", + "ö", + "ü", + "Ä", + "Ö", + "Ü", + "ß", + ); + + $text = preg_replace($search,$replace,$document); + + return $text; + } + +/*======================================================================*\ + Function: _expandlinks + Purpose: expand each link into a fully qualified URL + Input: $links the links to qualify + $URI the full URI to get the base from + Output: $expandedLinks the expanded links +\*======================================================================*/ + + function _expandlinks($links,$URI) + { + + preg_match("/^[^\?]+/",$URI,$match); + + $match = preg_replace("|/[^\/\.]+\.[^\/\.]+$|","",$match[0]); + $match = preg_replace("|/$|","",$match); + $match_part = parse_url($match); + $match_root = + $match_part["scheme"]."://".$match_part["host"]; + + $search = array( "|^http://".preg_quote($this->host)."|i", + "|^(\/)|i", + "|^(?!http://)(?!mailto:)|i", + "|/\./|", + "|/[^\/]+/\.\./|" + ); + + $replace = array( "", + $match_root."/", + $match."/", + "/", + "/" + ); + + $expandedLinks = preg_replace($search,$replace,$links); + + return $expandedLinks; + } + +/*======================================================================*\ + Function: _httprequest + Purpose: go get the http data from the server + Input: $url the url to fetch + $fp the current open file pointer + $URI the full URI + $body body contents to send if any (POST) + Output: +\*======================================================================*/ + + function _httprequest($url,$fp,$URI,$http_method,$content_type="",$body="") + { + $cookie_headers = ''; + if($this->passcookies && $this->_redirectaddr) + $this->setcookies(); + + $URI_PARTS = parse_url($URI); + if(empty($url)) + $url = "/"; + $headers = $http_method." ".$url." ".$this->_httpversion."\r\n"; + if(!empty($this->agent)) + $headers .= "User-Agent: ".$this->agent."\r\n"; + if(!empty($this->host) && !isset($this->rawheaders['Host'])) { + $headers .= "Host: ".$this->host; + if(!empty($this->port)) + $headers .= ":".$this->port; + $headers .= "\r\n"; + } + if(!empty($this->accept)) + $headers .= "Accept: ".$this->accept."\r\n"; + if(!empty($this->referer)) + $headers .= "Referer: ".$this->referer."\r\n"; + if(!empty($this->cookies)) + { + if(!is_array($this->cookies)) + $this->cookies = (array)$this->cookies; + + reset($this->cookies); + if ( count($this->cookies) > 0 ) { + $cookie_headers .= 'Cookie: '; + foreach ( $this->cookies as $cookieKey => $cookieVal ) { + $cookie_headers .= $cookieKey."=".urlencode($cookieVal)."; "; + } + $headers .= substr($cookie_headers,0,-2) . "\r\n"; + } + } + if(!empty($this->rawheaders)) + { + if(!is_array($this->rawheaders)) + $this->rawheaders = (array)$this->rawheaders; + while(list($headerKey,$headerVal) = each($this->rawheaders)) + $headers .= $headerKey.": ".$headerVal."\r\n"; + } + if(!empty($content_type)) { + $headers .= "Content-type: $content_type"; + if ($content_type == "multipart/form-data") + $headers .= "; boundary=".$this->_mime_boundary; + $headers .= "\r\n"; + } + if(!empty($body)) + $headers .= "Content-length: ".strlen($body)."\r\n"; + if(!empty($this->user) || !empty($this->pass)) + $headers .= "Authorization: Basic ".base64_encode($this->user.":".$this->pass)."\r\n"; + + //add proxy auth headers + if(!empty($this->proxy_user)) + $headers .= 'Proxy-Authorization: ' . 'Basic ' . base64_encode($this->proxy_user . ':' . $this->proxy_pass)."\r\n"; + + + $headers .= "\r\n"; + + // set the read timeout if needed + if ($this->read_timeout > 0) + socket_set_timeout($fp, $this->read_timeout); + $this->timed_out = false; + + fwrite($fp,$headers.$body,strlen($headers.$body)); + + $this->_redirectaddr = false; + unset($this->headers); + + while($currentHeader = fgets($fp,$this->_maxlinelen)) + { + if ($this->read_timeout > 0 && $this->_check_timeout($fp)) + { + $this->status=-100; + return false; + } + + if($currentHeader == "\r\n") + break; + + // if a header begins with Location: or URI:, set the redirect + if(preg_match("/^(Location:|URI:)/i",$currentHeader)) + { + // get URL portion of the redirect + preg_match("/^(Location:|URI:)[ ]+(.*)/i",chop($currentHeader),$matches); + // look for :// in the Location header to see if hostname is included + if(!preg_match("|\:\/\/|",$matches[2])) + { + // no host in the path, so prepend + $this->_redirectaddr = $URI_PARTS["scheme"]."://".$this->host.":".$this->port; + // eliminate double slash + if(!preg_match("|^/|",$matches[2])) + $this->_redirectaddr .= "/".$matches[2]; + else + $this->_redirectaddr .= $matches[2]; + } + else + $this->_redirectaddr = $matches[2]; + } + + if(preg_match("|^HTTP/|",$currentHeader)) + { + if(preg_match("|^HTTP/[^\s]*\s(.*?)\s|",$currentHeader, $status)) + { + $this->status= $status[1]; + } + $this->response_code = $currentHeader; + } + + $this->headers[] = $currentHeader; + } + + $results = ''; + do { + $_data = fread($fp, $this->maxlength); + if (strlen($_data) == 0) { + break; + } + $results .= $_data; + } while(true); + + if ($this->read_timeout > 0 && $this->_check_timeout($fp)) + { + $this->status=-100; + return false; + } + + // check if there is a a redirect meta tag + + if(preg_match("'<meta[\s]*http-equiv[^>]*?content[\s]*=[\s]*[\"\']?\d+;[\s]*URL[\s]*=[\s]*([^\"\']*?)[\"\']?>'i",$results,$match)) + + { + $this->_redirectaddr = $this->_expandlinks($match[1],$URI); + } + + // have we hit our frame depth and is there frame src to fetch? + if(($this->_framedepth < $this->maxframes) && preg_match_all("'<frame\s+.*src[\s]*=[\'\"]?([^\'\"\>]+)'i",$results,$match)) + { + $this->results[] = $results; + for($x=0; $x<count($match[1]); $x++) + $this->_frameurls[] = $this->_expandlinks($match[1][$x],$URI_PARTS["scheme"]."://".$this->host); + } + // have we already fetched framed content? + elseif(is_array($this->results)) + $this->results[] = $results; + // no framed content + else + $this->results = $results; + + return true; + } + +/*======================================================================*\ + Function: _httpsrequest + Purpose: go get the https data from the server using curl + Input: $url the url to fetch + $URI the full URI + $body body contents to send if any (POST) + Output: +\*======================================================================*/ + + function _httpsrequest($url,$URI,$http_method,$content_type="",$body="") + { + if($this->passcookies && $this->_redirectaddr) + $this->setcookies(); + + $headers = array(); + + $URI_PARTS = parse_url($URI); + if(empty($url)) + $url = "/"; + // GET ... header not needed for curl + //$headers[] = $http_method." ".$url." ".$this->_httpversion; + if(!empty($this->agent)) + $headers[] = "User-Agent: ".$this->agent; + if(!empty($this->host)) + if(!empty($this->port)) + $headers[] = "Host: ".$this->host.":".$this->port; + else + $headers[] = "Host: ".$this->host; + if(!empty($this->accept)) + $headers[] = "Accept: ".$this->accept; + if(!empty($this->referer)) + $headers[] = "Referer: ".$this->referer; + if(!empty($this->cookies)) + { + if(!is_array($this->cookies)) + $this->cookies = (array)$this->cookies; + + reset($this->cookies); + if ( count($this->cookies) > 0 ) { + $cookie_str = 'Cookie: '; + foreach ( $this->cookies as $cookieKey => $cookieVal ) { + $cookie_str .= $cookieKey."=".urlencode($cookieVal)."; "; + } + $headers[] = substr($cookie_str,0,-2); + } + } + if(!empty($this->rawheaders)) + { + if(!is_array($this->rawheaders)) + $this->rawheaders = (array)$this->rawheaders; + while(list($headerKey,$headerVal) = each($this->rawheaders)) + $headers[] = $headerKey.": ".$headerVal; + } + if(!empty($content_type)) { + if ($content_type == "multipart/form-data") + $headers[] = "Content-type: $content_type; boundary=".$this->_mime_boundary; + else + $headers[] = "Content-type: $content_type"; + } + if(!empty($body)) + $headers[] = "Content-length: ".strlen($body); + if(!empty($this->user) || !empty($this->pass)) + $headers[] = "Authorization: BASIC ".base64_encode($this->user.":".$this->pass); + + for($curr_header = 0; $curr_header < count($headers); $curr_header++) { + $safer_header = strtr( $headers[$curr_header], "\"", " " ); + $cmdline_params .= " -H \"".$safer_header."\""; + } + + if(!empty($body)) + $cmdline_params .= " -d \"$body\""; + + if($this->read_timeout > 0) + $cmdline_params .= " -m ".$this->read_timeout; + + $headerfile = tempnam($temp_dir, "sno"); + + exec($this->curl_path." -k -D \"$headerfile\"".$cmdline_params." \"".escapeshellcmd($URI)."\"",$results,$return); + + if($return) + { + $this->error = "Error: cURL could not retrieve the document, error $return."; + return false; + } + + + $results = implode("\r\n",$results); + + $result_headers = file("$headerfile"); + + $this->_redirectaddr = false; + unset($this->headers); + + for($currentHeader = 0; $currentHeader < count($result_headers); $currentHeader++) + { + + // if a header begins with Location: or URI:, set the redirect + if(preg_match("/^(Location: |URI: )/i",$result_headers[$currentHeader])) + { + // get URL portion of the redirect + preg_match("/^(Location: |URI:)\s+(.*)/",chop($result_headers[$currentHeader]),$matches); + // look for :// in the Location header to see if hostname is included + if(!preg_match("|\:\/\/|",$matches[2])) + { + // no host in the path, so prepend + $this->_redirectaddr = $URI_PARTS["scheme"]."://".$this->host.":".$this->port; + // eliminate double slash + if(!preg_match("|^/|",$matches[2])) + $this->_redirectaddr .= "/".$matches[2]; + else + $this->_redirectaddr .= $matches[2]; + } + else + $this->_redirectaddr = $matches[2]; + } + + if(preg_match("|^HTTP/|",$result_headers[$currentHeader])) + $this->response_code = $result_headers[$currentHeader]; + + $this->headers[] = $result_headers[$currentHeader]; + } + + // check if there is a a redirect meta tag + + if(preg_match("'<meta[\s]*http-equiv[^>]*?content[\s]*=[\s]*[\"\']?\d+;[\s]*URL[\s]*=[\s]*([^\"\']*?)[\"\']?>'i",$results,$match)) + { + $this->_redirectaddr = $this->_expandlinks($match[1],$URI); + } + + // have we hit our frame depth and is there frame src to fetch? + if(($this->_framedepth < $this->maxframes) && preg_match_all("'<frame\s+.*src[\s]*=[\'\"]?([^\'\"\>]+)'i",$results,$match)) + { + $this->results[] = $results; + for($x=0; $x<count($match[1]); $x++) + $this->_frameurls[] = $this->_expandlinks($match[1][$x],$URI_PARTS["scheme"]."://".$this->host); + } + // have we already fetched framed content? + elseif(is_array($this->results)) + $this->results[] = $results; + // no framed content + else + $this->results = $results; + + unlink("$headerfile"); + + return true; + } + +/*======================================================================*\ + Function: setcookies() + Purpose: set cookies for a redirection +\*======================================================================*/ + + function setcookies() + { + for($x=0; $x<count($this->headers); $x++) + { + if(preg_match('/^set-cookie:[\s]+([^=]+)=([^;]+)/i', $this->headers[$x],$match)) + $this->cookies[$match[1]] = urldecode($match[2]); + } + } + + +/*======================================================================*\ + Function: _check_timeout + Purpose: checks whether timeout has occurred + Input: $fp file pointer +\*======================================================================*/ + + function _check_timeout($fp) + { + if ($this->read_timeout > 0) { + $fp_status = socket_get_status($fp); + if ($fp_status["timed_out"]) { + $this->timed_out = true; + return true; + } + } + return false; + } + +/*======================================================================*\ + Function: _connect + Purpose: make a socket connection + Input: $fp file pointer +\*======================================================================*/ + + function _connect(&$fp) + { + if(!empty($this->proxy_host) && !empty($this->proxy_port)) + { + $this->_isproxy = true; + + $host = $this->proxy_host; + $port = $this->proxy_port; + } + else + { + $host = $this->host; + $port = $this->port; + } + + $this->status = 0; + + if($fp = fsockopen( + $host, + $port, + $errno, + $errstr, + $this->_fp_timeout + )) + { + // socket connection succeeded + + return true; + } + else + { + // socket connection failed + $this->status = $errno; + switch($errno) + { + case -3: + $this->error="socket creation failed (-3)"; + case -4: + $this->error="dns lookup failure (-4)"; + case -5: + $this->error="connection refused or timed out (-5)"; + default: + $this->error="connection failed (".$errno.")"; + } + return false; + } + } +/*======================================================================*\ + Function: _disconnect + Purpose: disconnect a socket connection + Input: $fp file pointer +\*======================================================================*/ + + function _disconnect($fp) + { + return(fclose($fp)); + } + + +/*======================================================================*\ + Function: _prepare_post_body + Purpose: Prepare post body according to encoding type + Input: $formvars - form variables + $formfiles - form upload files + Output: post body +\*======================================================================*/ + + function _prepare_post_body($formvars, $formfiles) + { + settype($formvars, "array"); + settype($formfiles, "array"); + $postdata = ''; + + if (count($formvars) == 0 && count($formfiles) == 0) + return; + + switch ($this->_submit_type) { + case "application/x-www-form-urlencoded": + reset($formvars); + while(list($key,$val) = each($formvars)) { + if (is_array($val) || is_object($val)) { + while (list($cur_key, $cur_val) = each($val)) { + $postdata .= urlencode($key)."[]=".urlencode($cur_val)."&"; + } + } else + $postdata .= urlencode($key)."=".urlencode($val)."&"; + } + break; + + case "multipart/form-data": + $this->_mime_boundary = "Snoopy".md5(uniqid(microtime())); + + reset($formvars); + while(list($key,$val) = each($formvars)) { + if (is_array($val) || is_object($val)) { + while (list($cur_key, $cur_val) = each($val)) { + $postdata .= "--".$this->_mime_boundary."\r\n"; + $postdata .= "Content-Disposition: form-data; name=\"$key\[\]\"\r\n\r\n"; + $postdata .= "$cur_val\r\n"; + } + } else { + $postdata .= "--".$this->_mime_boundary."\r\n"; + $postdata .= "Content-Disposition: form-data; name=\"$key\"\r\n\r\n"; + $postdata .= "$val\r\n"; + } + } + + reset($formfiles); + while (list($field_name, $file_names) = each($formfiles)) { + settype($file_names, "array"); + while (list(, $file_name) = each($file_names)) { + if (!is_readable($file_name)) continue; + + $fp = fopen($file_name, "r"); + $file_content = fread($fp, filesize($file_name)); + fclose($fp); + $base_name = basename($file_name); + + $postdata .= "--".$this->_mime_boundary."\r\n"; + $postdata .= "Content-Disposition: form-data; name=\"$field_name\"; filename=\"$base_name\"\r\n\r\n"; + $postdata .= "$file_content\r\n"; + } + } + $postdata .= "--".$this->_mime_boundary."--\r\n"; + break; + } + + return $postdata; + } +} + +?> diff --git a/modules/snoopy/TODO b/modules/snoopy/TODO new file mode 100644 index 00000000..d46738c1 --- /dev/null +++ b/modules/snoopy/TODO @@ -0,0 +1,9 @@ +* fetch other types of protocols such as ftp, nntp, gopher, etc. +* post forms with http file upload (I didn't have this need, + but it should be fairly straightforward) +* expand links, image tags, and form actions to fully + qualified URLs + +Bugs +---- +* none known |