--- /dev/null
+ 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:
+
+ <program> Copyright (C) <year> <name of author>
+ 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>.
--- /dev/null
+#!/usr/bin/env python
+"""Universal feed parser
+
+Handles RSS 0.9x, RSS 1.0, RSS 2.0, CDF, Atom 0.3, and Atom 1.0 feeds
+
+Visit http://feedparser.org/ for the latest version
+Visit http://feedparser.org/docs/ for the latest documentation
+
+Required: Python 2.1 or later
+Recommended: Python 2.3 or later
+Recommended: CJKCodecs and iconv_codec <http://cjkpython.i18n.org/>
+"""
+
+__version__ = "4.1"# + "$Revision: 1.92 $"[11:15] + "-cvs"
+__license__ = """Copyright (c) 2002-2006, Mark Pilgrim, All rights reserved.
+
+Redistribution and use in source and binary forms, with or without modification,
+are permitted provided that the following conditions are met:
+
+* Redistributions of source code must retain the above copyright notice,
+ this list of conditions and the following disclaimer.
+* Redistributions in binary form must reproduce the above copyright notice,
+ this list of conditions and the following disclaimer in the documentation
+ and/or other materials provided with the distribution.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 'AS IS'
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE."""
+__author__ = "Mark Pilgrim <http://diveintomark.org/>"
+__contributors__ = ["Jason Diamond <http://injektilo.org/>",
+ "John Beimler <http://john.beimler.org/>",
+ "Fazal Majid <http://www.majid.info/mylos/weblog/>",
+ "Aaron Swartz <http://aaronsw.com/>",
+ "Kevin Marks <http://epeus.blogspot.com/>"]
+_debug = 0
+
+# HTTP "User-Agent" header to send to servers when downloading feeds.
+# If you are embedding feedparser in a larger application, you should
+# change this to your application name and URL.
+USER_AGENT = "UniversalFeedParser/%s +http://feedparser.org/" % __version__
+
+# HTTP "Accept" header to send to servers when downloading feeds. If you don't
+# want to send an Accept header, set this to None.
+ACCEPT_HEADER = "application/atom+xml,application/rdf+xml,application/rss+xml,application/x-netcdf,application/xml;q=0.9,text/xml;q=0.2,*/*;q=0.1"
+
+# List of preferred XML parsers, by SAX driver name. These will be tried first,
+# but if they're not installed, Python will keep searching through its own list
+# of pre-installed parsers until it finds one that supports everything we need.
+PREFERRED_XML_PARSERS = ["drv_libxml2"]
+
+# If you want feedparser to automatically run HTML markup through HTML Tidy, set
+# this to 1. Requires mxTidy <http://www.egenix.com/files/python/mxTidy.html>
+# or utidylib <http://utidylib.berlios.de/>.
+TIDY_MARKUP = 0
+
+# List of Python interfaces for HTML Tidy, in order of preference. Only useful
+# if TIDY_MARKUP = 1
+PREFERRED_TIDY_INTERFACES = ["uTidy", "mxTidy"]
+
+# ---------- required modules (should come with any Python distribution) ----------
+import sgmllib, re, sys, copy, urlparse, time, rfc822, types, cgi, urllib, urllib2
+try:
+ from cStringIO import StringIO as _StringIO
+except:
+ from StringIO import StringIO as _StringIO
+
+# ---------- optional modules (feedparser will work without these, but with reduced functionality) ----------
+
+# gzip is included with most Python distributions, but may not be available if you compiled your own
+try:
+ import gzip
+except:
+ gzip = None
+try:
+ import zlib
+except:
+ zlib = None
+
+# If a real XML parser is available, feedparser will attempt to use it. feedparser has
+# been tested with the built-in SAX parser, PyXML, and libxml2. On platforms where the
+# Python distribution does not come with an XML parser (such as Mac OS X 10.2 and some
+# versions of FreeBSD), feedparser will quietly fall back on regex-based parsing.
+try:
+ import xml.sax
+ xml.sax.make_parser(PREFERRED_XML_PARSERS) # test for valid parsers
+ from xml.sax.saxutils import escape as _xmlescape
+ _XML_AVAILABLE = 1
+except:
+ _XML_AVAILABLE = 0
+ def _xmlescape(data):
+ data = data.replace('&', '&')
+ data = data.replace('>', '>')
+ data = data.replace('<', '<')
+ return data
+
+# base64 support for Atom feeds that contain embedded binary data
+try:
+ import base64, binascii
+except:
+ base64 = binascii = None
+
+# cjkcodecs and iconv_codec provide support for more character encodings.
+# Both are available from http://cjkpython.i18n.org/
+try:
+ import cjkcodecs.aliases
+except:
+ pass
+try:
+ import iconv_codec
+except:
+ pass
+
+# chardet library auto-detects character encodings
+# Download from http://chardet.feedparser.org/
+try:
+ import chardet
+ if _debug:
+ import chardet.constants
+ chardet.constants._debug = 1
+except:
+ chardet = None
+
+# ---------- don't touch these ----------
+class ThingsNobodyCaresAboutButMe(Exception): pass
+class CharacterEncodingOverride(ThingsNobodyCaresAboutButMe): pass
+class CharacterEncodingUnknown(ThingsNobodyCaresAboutButMe): pass
+class NonXMLContentType(ThingsNobodyCaresAboutButMe): pass
+class UndeclaredNamespace(Exception): pass
+
+sgmllib.tagfind = re.compile('[a-zA-Z][-_.:a-zA-Z0-9]*')
+sgmllib.special = re.compile('<!')
+sgmllib.charref = re.compile('&#(x?[0-9A-Fa-f]+)[^0-9A-Fa-f]')
+
+SUPPORTED_VERSIONS = {'': 'unknown',
+ 'rss090': 'RSS 0.90',
+ 'rss091n': 'RSS 0.91 (Netscape)',
+ 'rss091u': 'RSS 0.91 (Userland)',
+ 'rss092': 'RSS 0.92',
+ 'rss093': 'RSS 0.93',
+ 'rss094': 'RSS 0.94',
+ 'rss20': 'RSS 2.0',
+ 'rss10': 'RSS 1.0',
+ 'rss': 'RSS (unknown version)',
+ 'atom01': 'Atom 0.1',
+ 'atom02': 'Atom 0.2',
+ 'atom03': 'Atom 0.3',
+ 'atom10': 'Atom 1.0',
+ 'atom': 'Atom (unknown version)',
+ 'cdf': 'CDF',
+ 'hotrss': 'Hot RSS'
+ }
+
+try:
+ UserDict = dict
+except NameError:
+ # Python 2.1 does not have dict
+ from UserDict import UserDict
+ def dict(aList):
+ rc = {}
+ for k, v in aList:
+ rc[k] = v
+ return rc
+
+class FeedParserDict(UserDict):
+ keymap = {'channel': 'feed',
+ 'items': 'entries',
+ 'guid': 'id',
+ 'date': 'updated',
+ 'date_parsed': 'updated_parsed',
+ 'description': ['subtitle', 'summary'],
+ 'url': ['href'],
+ 'modified': 'updated',
+ 'modified_parsed': 'updated_parsed',
+ 'issued': 'published',
+ 'issued_parsed': 'published_parsed',
+ 'copyright': 'rights',
+ 'copyright_detail': 'rights_detail',
+ 'tagline': 'subtitle',
+ 'tagline_detail': 'subtitle_detail'}
+ def __getitem__(self, key):
+ if key == 'category':
+ return UserDict.__getitem__(self, 'tags')[0]['term']
+ if key == 'categories':
+ return [(tag['scheme'], tag['term']) for tag in UserDict.__getitem__(self, 'tags')]
+ realkey = self.keymap.get(key, key)
+ if type(realkey) == types.ListType:
+ for k in realkey:
+ if UserDict.has_key(self, k):
+ return UserDict.__getitem__(self, k)
+ if UserDict.has_key(self, key):
+ return UserDict.__getitem__(self, key)
+ return UserDict.__getitem__(self, realkey)
+
+ def __setitem__(self, key, value):
+ for k in self.keymap.keys():
+ if key == k:
+ key = self.keymap[k]
+ if type(key) == types.ListType:
+ key = key[0]
+ return UserDict.__setitem__(self, key, value)
+
+ def get(self, key, default=None):
+ if self.has_key(key):
+ return self[key]
+ else:
+ return default
+
+ def setdefault(self, key, value):
+ if not self.has_key(key):
+ self[key] = value
+ return self[key]
+
+ def has_key(self, key):
+ try:
+ return hasattr(self, key) or UserDict.has_key(self, key)
+ except AttributeError:
+ return False
+
+ def __getattr__(self, key):
+ try:
+ return self.__dict__[key]
+ except KeyError:
+ pass
+ try:
+ assert not key.startswith('_')
+ return self.__getitem__(key)
+ except:
+ raise AttributeError, "object has no attribute '%s'" % key
+
+ def __setattr__(self, key, value):
+ if key.startswith('_') or key == 'data':
+ self.__dict__[key] = value
+ else:
+ return self.__setitem__(key, value)
+
+ def __contains__(self, key):
+ return self.has_key(key)
+
+def zopeCompatibilityHack():
+ global FeedParserDict
+ del FeedParserDict
+ def FeedParserDict(aDict=None):
+ rc = {}
+ if aDict:
+ rc.update(aDict)
+ return rc
+
+_ebcdic_to_ascii_map = None
+def _ebcdic_to_ascii(s):
+ global _ebcdic_to_ascii_map
+ if not _ebcdic_to_ascii_map:
+ emap = (
+ 0,1,2,3,156,9,134,127,151,141,142,11,12,13,14,15,
+ 16,17,18,19,157,133,8,135,24,25,146,143,28,29,30,31,
+ 128,129,130,131,132,10,23,27,136,137,138,139,140,5,6,7,
+ 144,145,22,147,148,149,150,4,152,153,154,155,20,21,158,26,
+ 32,160,161,162,163,164,165,166,167,168,91,46,60,40,43,33,
+ 38,169,170,171,172,173,174,175,176,177,93,36,42,41,59,94,
+ 45,47,178,179,180,181,182,183,184,185,124,44,37,95,62,63,
+ 186,187,188,189,190,191,192,193,194,96,58,35,64,39,61,34,
+ 195,97,98,99,100,101,102,103,104,105,196,197,198,199,200,201,
+ 202,106,107,108,109,110,111,112,113,114,203,204,205,206,207,208,
+ 209,126,115,116,117,118,119,120,121,122,210,211,212,213,214,215,
+ 216,217,218,219,220,221,222,223,224,225,226,227,228,229,230,231,
+ 123,65,66,67,68,69,70,71,72,73,232,233,234,235,236,237,
+ 125,74,75,76,77,78,79,80,81,82,238,239,240,241,242,243,
+ 92,159,83,84,85,86,87,88,89,90,244,245,246,247,248,249,
+ 48,49,50,51,52,53,54,55,56,57,250,251,252,253,254,255
+ )
+ import string
+ _ebcdic_to_ascii_map = string.maketrans( \
+ ''.join(map(chr, range(256))), ''.join(map(chr, emap)))
+ return s.translate(_ebcdic_to_ascii_map)
+
+_urifixer = re.compile('^([A-Za-z][A-Za-z0-9+-.]*://)(/*)(.*?)')
+def _urljoin(base, uri):
+ uri = _urifixer.sub(r'\1\3', uri)
+ return urlparse.urljoin(base, uri)
+
+class _FeedParserMixin:
+ namespaces = {'': '',
+ 'http://backend.userland.com/rss': '',
+ 'http://blogs.law.harvard.edu/tech/rss': '',
+ 'http://purl.org/rss/1.0/': '',
+ 'http://my.netscape.com/rdf/simple/0.9/': '',
+ 'http://example.com/newformat#': '',
+ 'http://example.com/necho': '',
+ 'http://purl.org/echo/': '',
+ 'uri/of/echo/namespace#': '',
+ 'http://purl.org/pie/': '',
+ 'http://purl.org/atom/ns#': '',
+ 'http://www.w3.org/2005/Atom': '',
+ 'http://purl.org/rss/1.0/modules/rss091#': '',
+
+ 'http://webns.net/mvcb/': 'admin',
+ 'http://purl.org/rss/1.0/modules/aggregation/': 'ag',
+ 'http://purl.org/rss/1.0/modules/annotate/': 'annotate',
+ 'http://media.tangent.org/rss/1.0/': 'audio',
+ 'http://backend.userland.com/blogChannelModule': 'blogChannel',
+ 'http://web.resource.org/cc/': 'cc',
+ 'http://backend.userland.com/creativeCommonsRssModule': 'creativeCommons',
+ 'http://purl.org/rss/1.0/modules/company': 'co',
+ 'http://purl.org/rss/1.0/modules/content/': 'content',
+ 'http://my.theinfo.org/changed/1.0/rss/': 'cp',
+ 'http://purl.org/dc/elements/1.1/': 'dc',
+ 'http://purl.org/dc/terms/': 'dcterms',
+ 'http://purl.org/rss/1.0/modules/email/': 'email',
+ 'http://purl.org/rss/1.0/modules/event/': 'ev',
+ 'http://rssnamespace.org/feedburner/ext/1.0': 'feedburner',
+ 'http://freshmeat.net/rss/fm/': 'fm',
+ 'http://xmlns.com/foaf/0.1/': 'foaf',
+ 'http://www.w3.org/2003/01/geo/wgs84_pos#': 'geo',
+ 'http://postneo.com/icbm/': 'icbm',
+ 'http://purl.org/rss/1.0/modules/image/': 'image',
+ 'http://www.itunes.com/DTDs/PodCast-1.0.dtd': 'itunes',
+ 'http://example.com/DTDs/PodCast-1.0.dtd': 'itunes',
+ 'http://purl.org/rss/1.0/modules/link/': 'l',
+ 'http://search.yahoo.com/mrss': 'media',
+ 'http://madskills.com/public/xml/rss/module/pingback/': 'pingback',
+ 'http://prismstandard.org/namespaces/1.2/basic/': 'prism',
+ 'http://www.w3.org/1999/02/22-rdf-syntax-ns#': 'rdf',
+ 'http://www.w3.org/2000/01/rdf-schema#': 'rdfs',
+ 'http://purl.org/rss/1.0/modules/reference/': 'ref',
+ 'http://purl.org/rss/1.0/modules/richequiv/': 'reqv',
+ 'http://purl.org/rss/1.0/modules/search/': 'search',
+ 'http://purl.org/rss/1.0/modules/slash/': 'slash',
+ 'http://schemas.xmlsoap.org/soap/envelope/': 'soap',
+ 'http://purl.org/rss/1.0/modules/servicestatus/': 'ss',
+ 'http://hacks.benhammersley.com/rss/streaming/': 'str',
+ 'http://purl.org/rss/1.0/modules/subscription/': 'sub',
+ 'http://purl.org/rss/1.0/modules/syndication/': 'sy',
+ 'http://purl.org/rss/1.0/modules/taxonomy/': 'taxo',
+ 'http://purl.org/rss/1.0/modules/threading/': 'thr',
+ 'http://purl.org/rss/1.0/modules/textinput/': 'ti',
+ 'http://madskills.com/public/xml/rss/module/trackback/':'trackback',
+ 'http://wellformedweb.org/commentAPI/': 'wfw',
+ 'http://purl.org/rss/1.0/modules/wiki/': 'wiki',
+ 'http://www.w3.org/1999/xhtml': 'xhtml',
+ 'http://www.w3.org/XML/1998/namespace': 'xml',
+ 'http://schemas.pocketsoap.com/rss/myDescModule/': 'szf'
+}
+ _matchnamespaces = {}
+
+ can_be_relative_uri = ['link', 'id', 'wfw_comment', 'wfw_commentrss', 'docs', 'url', 'href', 'comments', 'license', 'icon', 'logo']
+ can_contain_relative_uris = ['content', 'title', 'summary', 'info', 'tagline', 'subtitle', 'copyright', 'rights', 'description']
+ can_contain_dangerous_markup = ['content', 'title', 'summary', 'info', 'tagline', 'subtitle', 'copyright', 'rights', 'description']
+ html_types = ['text/html', 'application/xhtml+xml']
+
+ def __init__(self, baseuri=None, baselang=None, encoding='utf-8'):
+ if _debug: sys.stderr.write('initializing FeedParser\n')
+ if not self._matchnamespaces:
+ for k, v in self.namespaces.items():
+ self._matchnamespaces[k.lower()] = v
+ self.feeddata = FeedParserDict() # feed-level data
+ self.encoding = encoding # character encoding
+ self.entries = [] # list of entry-level data
+ self.version = '' # feed type/version, see SUPPORTED_VERSIONS
+ self.namespacesInUse = {} # dictionary of namespaces defined by the feed
+
+ # the following are used internally to track state;
+ # this is really out of control and should be refactored
+ self.infeed = 0
+ self.inentry = 0
+ self.incontent = 0
+ self.intextinput = 0
+ self.inimage = 0
+ self.inauthor = 0
+ self.incontributor = 0
+ self.inpublisher = 0
+ self.insource = 0
+ self.sourcedata = FeedParserDict()
+ self.contentparams = FeedParserDict()
+ self._summaryKey = None
+ self.namespacemap = {}
+ self.elementstack = []
+ self.basestack = []
+ self.langstack = []
+ self.baseuri = baseuri or ''
+ self.lang = baselang or None
+ if baselang:
+ self.feeddata['language'] = baselang
+
+ def unknown_starttag(self, tag, attrs):
+ if _debug: sys.stderr.write('start %s with %s\n' % (tag, attrs))
+ # normalize attrs
+ attrs = [(k.lower(), v) for k, v in attrs]
+ attrs = [(k, k in ('rel', 'type') and v.lower() or v) for k, v in attrs]
+
+ # track xml:base and xml:lang
+ attrsD = dict(attrs)
+ baseuri = attrsD.get('xml:base', attrsD.get('base')) or self.baseuri
+ self.baseuri = _urljoin(self.baseuri, baseuri)
+ lang = attrsD.get('xml:lang', attrsD.get('lang'))
+ if lang == '':
+ # xml:lang could be explicitly set to '', we need to capture that
+ lang = None
+ elif lang is None:
+ # if no xml:lang is specified, use parent lang
+ lang = self.lang
+ if lang:
+ if tag in ('feed', 'rss', 'rdf:RDF'):
+ self.feeddata['language'] = lang
+ self.lang = lang
+ self.basestack.append(self.baseuri)
+ self.langstack.append(lang)
+
+ # track namespaces
+ for prefix, uri in attrs:
+ if prefix.startswith('xmlns:'):
+ self.trackNamespace(prefix[6:], uri)
+ elif prefix == 'xmlns':
+ self.trackNamespace(None, uri)
+
+ # track inline content
+ if self.incontent and self.contentparams.has_key('type') and not self.contentparams.get('type', 'xml').endswith('xml'):
+ # element declared itself as escaped markup, but it isn't really
+ self.contentparams['type'] = 'application/xhtml+xml'
+ if self.incontent and self.contentparams.get('type') == 'application/xhtml+xml':
+ # Note: probably shouldn't simply recreate localname here, but
+ # our namespace handling isn't actually 100% correct in cases where
+ # the feed redefines the default namespace (which is actually
+ # the usual case for inline content, thanks Sam), so here we
+ # cheat and just reconstruct the element based on localname
+ # because that compensates for the bugs in our namespace handling.
+ # This will horribly munge inline content with non-empty qnames,
+ # but nobody actually does that, so I'm not fixing it.
+ tag = tag.split(':')[-1]
+ return self.handle_data('<%s%s>' % (tag, ''.join([' %s="%s"' % t for t in attrs])), escape=0)
+
+ # match namespaces
+ if tag.find(':') <> -1:
+ prefix, suffix = tag.split(':', 1)
+ else:
+ prefix, suffix = '', tag
+ prefix = self.namespacemap.get(prefix, prefix)
+ if prefix:
+ prefix = prefix + '_'
+
+ # special hack for better tracking of empty textinput/image elements in illformed feeds
+ if (not prefix) and tag not in ('title', 'link', 'description', 'name'):
+ self.intextinput = 0
+ if (not prefix) and tag not in ('title', 'link', 'description', 'url', 'href', 'width', 'height'):
+ self.inimage = 0
+
+ # call special handler (if defined) or default handler
+ methodname = '_start_' + prefix + suffix
+ try:
+ method = getattr(self, methodname)
+ return method(attrsD)
+ except AttributeError:
+ return self.push(prefix + suffix, 1)
+
+ def unknown_endtag(self, tag):
+ if _debug: sys.stderr.write('end %s\n' % tag)
+ # match namespaces
+ if tag.find(':') <> -1:
+ prefix, suffix = tag.split(':', 1)
+ else:
+ prefix, suffix = '', tag
+ prefix = self.namespacemap.get(prefix, prefix)
+ if prefix:
+ prefix = prefix + '_'
+
+ # call special handler (if defined) or default handler
+ methodname = '_end_' + prefix + suffix
+ try:
+ method = getattr(self, methodname)
+ method()
+ except AttributeError:
+ self.pop(prefix + suffix)
+
+ # track inline content
+ if self.incontent and self.contentparams.has_key('type') and not self.contentparams.get('type', 'xml').endswith('xml'):
+ # element declared itself as escaped markup, but it isn't really
+ self.contentparams['type'] = 'application/xhtml+xml'
+ if self.incontent and self.contentparams.get('type') == 'application/xhtml+xml':
+ tag = tag.split(':')[-1]
+ self.handle_data('</%s>' % tag, escape=0)
+
+ # track xml:base and xml:lang going out of scope
+ if self.basestack:
+ self.basestack.pop()
+ if self.basestack and self.basestack[-1]:
+ self.baseuri = self.basestack[-1]
+ if self.langstack:
+ self.langstack.pop()
+ if self.langstack: # and (self.langstack[-1] is not None):
+ self.lang = self.langstack[-1]
+
+ def handle_charref(self, ref):
+ # called for each character reference, e.g. for ' ', ref will be '160'
+ if not self.elementstack: return
+ ref = ref.lower()
+ if ref in ('34', '38', '39', '60', '62', 'x22', 'x26', 'x27', 'x3c', 'x3e'):
+ text = '&#%s;' % ref
+ else:
+ if ref[0] == 'x':
+ c = int(ref[1:], 16)
+ else:
+ c = int(ref)
+ text = unichr(c).encode('utf-8')
+ self.elementstack[-1][2].append(text)
+
+ def handle_entityref(self, ref):
+ # called for each entity reference, e.g. for '©', ref will be 'copy'
+ if not self.elementstack: return
+ if _debug: sys.stderr.write('entering handle_entityref with %s\n' % ref)
+ if ref in ('lt', 'gt', 'quot', 'amp', 'apos'):
+ text = '&%s;' % ref
+ else:
+ # entity resolution graciously donated by Aaron Swartz
+ def name2cp(k):
+ import htmlentitydefs
+ if hasattr(htmlentitydefs, 'name2codepoint'): # requires Python 2.3
+ return htmlentitydefs.name2codepoint[k]
+ k = htmlentitydefs.entitydefs[k]
+ if k.startswith('&#') and k.endswith(';'):
+ return int(k[2:-1]) # not in latin-1
+ return ord(k)
+ try: name2cp(ref)
+ except KeyError: text = '&%s;' % ref
+ else: text = unichr(name2cp(ref)).encode('utf-8')
+ self.elementstack[-1][2].append(text)
+
+ def handle_data(self, text, escape=1):
+ # called for each block of plain text, i.e. outside of any tag and
+ # not containing any character or entity references
+ if not self.elementstack: return
+ if escape and self.contentparams.get('type') == 'application/xhtml+xml':
+ text = _xmlescape(text)
+ self.elementstack[-1][2].append(text)
+
+ def handle_comment(self, text):
+ # called for each comment, e.g. <!-- insert message here -->
+ pass
+
+ def handle_pi(self, text):
+ # called for each processing instruction, e.g. <?instruction>
+ pass
+
+ def handle_decl(self, text):
+ pass
+
+ def parse_declaration(self, i):
+ # override internal declaration handler to handle CDATA blocks
+ if _debug: sys.stderr.write('entering parse_declaration\n')
+ if self.rawdata[i:i+9] == '<![CDATA[':
+ k = self.rawdata.find(']]>', i)
+ if k == -1: k = len(self.rawdata)
+ self.handle_data(_xmlescape(self.rawdata[i+9:k]), 0)
+ return k+3
+ else:
+ k = self.rawdata.find('>', i)
+ return k+1
+
+ def mapContentType(self, contentType):
+ contentType = contentType.lower()
+ if contentType == 'text':
+ contentType = 'text/plain'
+ elif contentType == 'html':
+ contentType = 'text/html'
+ elif contentType == 'xhtml':
+ contentType = 'application/xhtml+xml'
+ return contentType
+
+ def trackNamespace(self, prefix, uri):
+ loweruri = uri.lower()
+ if (prefix, loweruri) == (None, 'http://my.netscape.com/rdf/simple/0.9/') and not self.version:
+ self.version = 'rss090'
+ if loweruri == 'http://purl.org/rss/1.0/' and not self.version:
+ self.version = 'rss10'
+ if loweruri == 'http://www.w3.org/2005/atom' and not self.version:
+ self.version = 'atom10'
+ if loweruri.find('backend.userland.com/rss') <> -1:
+ # match any backend.userland.com namespace
+ uri = 'http://backend.userland.com/rss'
+ loweruri = uri
+ if self._matchnamespaces.has_key(loweruri):
+ self.namespacemap[prefix] = self._matchnamespaces[loweruri]
+ self.namespacesInUse[self._matchnamespaces[loweruri]] = uri
+ else:
+ self.namespacesInUse[prefix or ''] = uri
+
+ def resolveURI(self, uri):
+ return _urljoin(self.baseuri or '', uri)
+
+ def decodeEntities(self, element, data):
+ return data
+
+ def push(self, element, expectingText):
+ self.elementstack.append([element, expectingText, []])
+
+ def pop(self, element, stripWhitespace=1):
+ if not self.elementstack: return
+ if self.elementstack[-1][0] != element: return
+
+ element, expectingText, pieces = self.elementstack.pop()
+ output = ''.join(pieces)
+ if stripWhitespace:
+ output = output.strip()
+ if not expectingText: return output
+
+ # decode base64 content
+ if base64 and self.contentparams.get('base64', 0):
+ try:
+ output = base64.decodestring(output)
+ except binascii.Error:
+ pass
+ except binascii.Incomplete:
+ pass
+
+ # resolve relative URIs
+ if (element in self.can_be_relative_uri) and output:
+ output = self.resolveURI(output)
+
+ # decode entities within embedded markup
+ if not self.contentparams.get('base64', 0):
+ output = self.decodeEntities(element, output)
+
+ # remove temporary cruft from contentparams
+ try:
+ del self.contentparams['mode']
+ except KeyError:
+ pass
+ try:
+ del self.contentparams['base64']
+ except KeyError:
+ pass
+
+ # resolve relative URIs within embedded markup
+ if self.mapContentType(self.contentparams.get('type', 'text/html')) in self.html_types:
+ if element in self.can_contain_relative_uris:
+ output = _resolveRelativeURIs(output, self.baseuri, self.encoding)
+
+ # sanitize embedded markup
+ if self.mapContentType(self.contentparams.get('type', 'text/html')) in self.html_types:
+ if element in self.can_contain_dangerous_markup:
+ output = _sanitizeHTML(output, self.encoding)
+
+ if self.encoding and type(output) != type(u''):
+ try:
+ output = unicode(output, self.encoding)
+ except:
+ pass
+
+ # categories/tags/keywords/whatever are handled in _end_category
+ if element == 'category':
+ return output
+
+ # store output in appropriate place(s)
+ if self.inentry and not self.insource:
+ if element == 'content':
+ self.entries[-1].setdefault(element, [])
+ contentparams = copy.deepcopy(self.contentparams)
+ contentparams['value'] = output
+ self.entries[-1][element].append(contentparams)
+ elif element == 'link':
+ self.entries[-1][element] = output
+ if output:
+ self.entries[-1]['links'][-1]['href'] = output
+ else:
+ if element == 'description':
+ element = 'summary'
+ self.entries[-1][element] = output
+ if self.incontent:
+ contentparams = copy.deepcopy(self.contentparams)
+ contentparams['value'] = output
+ self.entries[-1][element + '_detail'] = contentparams
+ elif (self.infeed or self.insource) and (not self.intextinput) and (not self.inimage):
+ context = self._getContext()
+ if element == 'description':
+ element = 'subtitle'
+ context[element] = output
+ if element == 'link':
+ context['links'][-1]['href'] = output
+ elif self.incontent:
+ contentparams = copy.deepcopy(self.contentparams)
+ contentparams['value'] = output
+ context[element + '_detail'] = contentparams
+ return output
+
+ def pushContent(self, tag, attrsD, defaultContentType, expectingText):
+ self.incontent += 1
+ self.contentparams = FeedParserDict({
+ 'type': self.mapContentType(attrsD.get('type', defaultContentType)),
+ 'language': self.lang,
+ 'base': self.baseuri})
+ self.contentparams['base64'] = self._isBase64(attrsD, self.contentparams)
+ self.push(tag, expectingText)
+
+ def popContent(self, tag):
+ value = self.pop(tag)
+ self.incontent -= 1
+ self.contentparams.clear()
+ return value
+
+ def _mapToStandardPrefix(self, name):
+ colonpos = name.find(':')
+ if colonpos <> -1:
+ prefix = name[:colonpos]
+ suffix = name[colonpos+1:]
+ prefix = self.namespacemap.get(prefix, prefix)
+ name = prefix + ':' + suffix
+ return name
+
+ def _getAttribute(self, attrsD, name):
+ return attrsD.get(self._mapToStandardPrefix(name))
+
+ def _isBase64(self, attrsD, contentparams):
+ if attrsD.get('mode', '') == 'base64':
+ return 1
+ if self.contentparams['type'].startswith('text/'):
+ return 0
+ if self.contentparams['type'].endswith('+xml'):
+ return 0
+ if self.contentparams['type'].endswith('/xml'):
+ return 0
+ return 1
+
+ def _itsAnHrefDamnIt(self, attrsD):
+ href = attrsD.get('url', attrsD.get('uri', attrsD.get('href', None)))
+ if href:
+ try:
+ del attrsD['url']
+ except KeyError:
+ pass
+ try:
+ del attrsD['uri']
+ except KeyError:
+ pass
+ attrsD['href'] = href
+ return attrsD
+
+ def _save(self, key, value):
+ context = self._getContext()
+ context.setdefault(key, value)
+
+ def _start_rss(self, attrsD):
+ versionmap = {'0.91': 'rss091u',
+ '0.92': 'rss092',
+ '0.93': 'rss093',
+ '0.94': 'rss094'}
+ if not self.version:
+ attr_version = attrsD.get('version', '')
+ version = versionmap.get(attr_version)
+ if version:
+ self.version = version
+ elif attr_version.startswith('2.'):
+ self.version = 'rss20'
+ else:
+ self.version = 'rss'
+
+ def _start_dlhottitles(self, attrsD):
+ self.version = 'hotrss'
+
+ def _start_channel(self, attrsD):
+ self.infeed = 1
+ self._cdf_common(attrsD)
+ _start_feedinfo = _start_channel
+
+ def _cdf_common(self, attrsD):
+ if attrsD.has_key('lastmod'):
+ self._start_modified({})
+ self.elementstack[-1][-1] = attrsD['lastmod']
+ self._end_modified()
+ if attrsD.has_key('href'):
+ self._start_link({})
+ self.elementstack[-1][-1] = attrsD['href']
+ self._end_link()
+
+ def _start_feed(self, attrsD):
+ self.infeed = 1
+ versionmap = {'0.1': 'atom01',
+ '0.2': 'atom02',
+ '0.3': 'atom03'}
+ if not self.version:
+ attr_version = attrsD.get('version')
+ version = versionmap.get(attr_version)
+ if version:
+ self.version = version
+ else:
+ self.version = 'atom'
+
+ def _end_channel(self):
+ self.infeed = 0
+ _end_feed = _end_channel
+
+ def _start_image(self, attrsD):
+ self.inimage = 1
+ self.push('image', 0)
+ context = self._getContext()
+ context.setdefault('image', FeedParserDict())
+
+ def _end_image(self):
+ self.pop('image')
+ self.inimage = 0
+
+ def _start_textinput(self, attrsD):
+ self.intextinput = 1
+ self.push('textinput', 0)
+ context = self._getContext()
+ context.setdefault('textinput', FeedParserDict())
+ _start_textInput = _start_textinput
+
+ def _end_textinput(self):
+ self.pop('textinput')
+ self.intextinput = 0
+ _end_textInput = _end_textinput
+
+ def _start_author(self, attrsD):
+ self.inauthor = 1
+ self.push('author', 1)
+ _start_managingeditor = _start_author
+ _start_dc_author = _start_author
+ _start_dc_creator = _start_author
+ _start_itunes_author = _start_author
+
+ def _end_author(self):
+ self.pop('author')
+ self.inauthor = 0
+ self._sync_author_detail()
+ _end_managingeditor = _end_author
+ _end_dc_author = _end_author
+ _end_dc_creator = _end_author
+ _end_itunes_author = _end_author
+
+ def _start_itunes_owner(self, attrsD):
+ self.inpublisher = 1
+ self.push('publisher', 0)
+
+ def _end_itunes_owner(self):
+ self.pop('publisher')
+ self.inpublisher = 0
+ self._sync_author_detail('publisher')
+
+ def _start_contributor(self, attrsD):
+ self.incontributor = 1
+ context = self._getContext()
+ context.setdefault('contributors', [])
+ context['contributors'].append(FeedParserDict())
+ self.push('contributor', 0)
+
+ def _end_contributor(self):
+ self.pop('contributor')
+ self.incontributor = 0
+
+ def _start_dc_contributor(self, attrsD):
+ self.incontributor = 1
+ context = self._getContext()
+ context.setdefault('contributors', [])
+ context['contributors'].append(FeedParserDict())
+ self.push('name', 0)
+
+ def _end_dc_contributor(self):
+ self._end_name()
+ self.incontributor = 0
+
+ def _start_name(self, attrsD):
+ self.push('name', 0)
+ _start_itunes_name = _start_name
+
+ def _end_name(self):
+ value = self.pop('name')
+ if self.inpublisher:
+ self._save_author('name', value, 'publisher')
+ elif self.inauthor:
+ self._save_author('name', value)
+ elif self.incontributor:
+ self._save_contributor('name', value)
+ elif self.intextinput:
+ context = self._getContext()
+ context['textinput']['name'] = value
+ _end_itunes_name = _end_name
+
+ def _start_width(self, attrsD):
+ self.push('width', 0)
+
+ def _end_width(self):
+ value = self.pop('width')
+ try:
+ value = int(value)
+ except:
+ value = 0
+ if self.inimage:
+ context = self._getContext()
+ context['image']['width'] = value
+
+ def _start_height(self, attrsD):
+ self.push('height', 0)
+
+ def _end_height(self):
+ value = self.pop('height')
+ try:
+ value = int(value)
+ except:
+ value = 0
+ if self.inimage:
+ context = self._getContext()
+ context['image']['height'] = value
+
+ def _start_url(self, attrsD):
+ self.push('href', 1)
+ _start_homepage = _start_url
+ _start_uri = _start_url
+
+ def _end_url(self):
+ value = self.pop('href')
+ if self.inauthor:
+ self._save_author('href', value)
+ elif self.incontributor:
+ self._save_contributor('href', value)
+ elif self.inimage:
+ context = self._getContext()
+ context['image']['href'] = value
+ elif self.intextinput:
+ context = self._getContext()
+ context['textinput']['link'] = value
+ _end_homepage = _end_url
+ _end_uri = _end_url
+
+ def _start_email(self, attrsD):
+ self.push('email', 0)
+ _start_itunes_email = _start_email
+
+ def _end_email(self):
+ value = self.pop('email')
+ if self.inpublisher:
+ self._save_author('email', value, 'publisher')
+ elif self.inauthor:
+ self._save_author('email', value)
+ elif self.incontributor:
+ self._save_contributor('email', value)
+ _end_itunes_email = _end_email
+
+ def _getContext(self):
+ if self.insource:
+ context = self.sourcedata
+ elif self.inentry:
+ context = self.entries[-1]
+ else:
+ context = self.feeddata
+ return context
+
+ def _save_author(self, key, value, prefix='author'):
+ context = self._getContext()
+ context.setdefault(prefix + '_detail', FeedParserDict())
+ context[prefix + '_detail'][key] = value
+ self._sync_author_detail()
+
+ def _save_contributor(self, key, value):
+ context = self._getContext()
+ context.setdefault('contributors', [FeedParserDict()])
+ context['contributors'][-1][key] = value
+
+ def _sync_author_detail(self, key='author'):
+ context = self._getContext()
+ detail = context.get('%s_detail' % key)
+ if detail:
+ name = detail.get('name')
+ email = detail.get('email')
+ if name and email:
+ context[key] = '%s (%s)' % (name, email)
+ elif name:
+ context[key] = name
+ elif email:
+ context[key] = email
+ else:
+ author = context.get(key)
+ if not author: return
+ emailmatch = re.search(r'''(([a-zA-Z0-9\_\-\.\+]+)@((\[[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}\.)|(([a-zA-Z0-9\-]+\.)+))([a-zA-Z]{2,4}|[0-9]{1,3})(\]?))''', author)
+ if not emailmatch: return
+ email = emailmatch.group(0)
+ # probably a better way to do the following, but it passes all the tests
+ author = author.replace(email, '')
+ author = author.replace('()', '')
+ author = author.strip()
+ if author and (author[0] == '('):
+ author = author[1:]
+ if author and (author[-1] == ')'):
+ author = author[:-1]
+ author = author.strip()
+ context.setdefault('%s_detail' % key, FeedParserDict())
+ context['%s_detail' % key]['name'] = author
+ context['%s_detail' % key]['email'] = email
+
+ def _start_subtitle(self, attrsD):
+ self.pushContent('subtitle', attrsD, 'text/plain', 1)
+ _start_tagline = _start_subtitle
+ _start_itunes_subtitle = _start_subtitle
+
+ def _end_subtitle(self):
+ self.popContent('subtitle')
+ _end_tagline = _end_subtitle
+ _end_itunes_subtitle = _end_subtitle
+
+ def _start_rights(self, attrsD):
+ self.pushContent('rights', attrsD, 'text/plain', 1)
+ _start_dc_rights = _start_rights
+ _start_copyright = _start_rights
+
+ def _end_rights(self):
+ self.popContent('rights')
+ _end_dc_rights = _end_rights
+ _end_copyright = _end_rights
+
+ def _start_item(self, attrsD):
+ self.entries.append(FeedParserDict())
+ self.push('item', 0)
+ self.inentry = 1
+ self.guidislink = 0
+ id = self._getAttribute(attrsD, 'rdf:about')
+ if id:
+ context = self._getContext()
+ context['id'] = id
+ self._cdf_common(attrsD)
+ _start_entry = _start_item
+ _start_product = _start_item
+
+ def _end_item(self):
+ self.pop('item')
+ self.inentry = 0
+ _end_entry = _end_item
+
+ def _start_dc_language(self, attrsD):
+ self.push('language', 1)
+ _start_language = _start_dc_language
+
+ def _end_dc_language(self):
+ self.lang = self.pop('language')
+ _end_language = _end_dc_language
+
+ def _start_dc_publisher(self, attrsD):
+ self.push('publisher', 1)
+ _start_webmaster = _start_dc_publisher
+
+ def _end_dc_publisher(self):
+ self.pop('publisher')
+ self._sync_author_detail('publisher')
+ _end_webmaster = _end_dc_publisher
+
+ def _start_published(self, attrsD):
+ self.push('published', 1)
+ _start_dcterms_issued = _start_published
+ _start_issued = _start_published
+
+ def _end_published(self):
+ value = self.pop('published')
+ self._save('published_parsed', _parse_date(value))
+ _end_dcterms_issued = _end_published
+ _end_issued = _end_published
+
+ def _start_updated(self, attrsD):
+ self.push('updated', 1)
+ _start_modified = _start_updated
+ _start_dcterms_modified = _start_updated
+ _start_pubdate = _start_updated
+ _start_dc_date = _start_updated
+
+ def _end_updated(self):
+ value = self.pop('updated')
+ parsed_value = _parse_date(value)
+ self._save('updated_parsed', parsed_value)
+ _end_modified = _end_updated
+ _end_dcterms_modified = _end_updated
+ _end_pubdate = _end_updated
+ _end_dc_date = _end_updated
+
+ def _start_created(self, attrsD):
+ self.push('created', 1)
+ _start_dcterms_created = _start_created
+
+ def _end_created(self):
+ value = self.pop('created')
+ self._save('created_parsed', _parse_date(value))
+ _end_dcterms_created = _end_created
+
+ def _start_expirationdate(self, attrsD):
+ self.push('expired', 1)
+
+ def _end_expirationdate(self):
+ self._save('expired_parsed', _parse_date(self.pop('expired')))
+
+ def _start_cc_license(self, attrsD):
+ self.push('license', 1)
+ value = self._getAttribute(attrsD, 'rdf:resource')
+ if value:
+ self.elementstack[-1][2].append(value)
+ self.pop('license')
+
+ def _start_creativecommons_license(self, attrsD):
+ self.push('license', 1)
+
+ def _end_creativecommons_license(self):
+ self.pop('license')
+
+ def _addTag(self, term, scheme, label):
+ context = self._getContext()
+ tags = context.setdefault('tags', [])
+ if (not term) and (not scheme) and (not label): return
+ value = FeedParserDict({'term': term, 'scheme': scheme, 'label': label})
+ if value not in tags:
+ tags.append(FeedParserDict({'term': term, 'scheme': scheme, 'label': label}))
+
+ def _start_category(self, attrsD):
+ if _debug: sys.stderr.write('entering _start_category with %s\n' % repr(attrsD))
+ term = attrsD.get('term')
+ scheme = attrsD.get('scheme', attrsD.get('domain'))
+ label = attrsD.get('label')
+ self._addTag(term, scheme, label)
+ self.push('category', 1)
+ _start_dc_subject = _start_category
+ _start_keywords = _start_category
+
+ def _end_itunes_keywords(self):
+ for term in self.pop('itunes_keywords').split():
+ self._addTag(term, 'http://www.itunes.com/', None)
+
+ def _start_itunes_category(self, attrsD):
+ self._addTag(attrsD.get('text'), 'http://www.itunes.com/', None)
+ self.push('category', 1)
+
+ def _end_category(self):
+ value = self.pop('category')
+ if not value: return
+ context = self._getContext()
+ tags = context['tags']
+ if value and len(tags) and not tags[-1]['term']:
+ tags[-1]['term'] = value
+ else:
+ self._addTag(value, None, None)
+ _end_dc_subject = _end_category
+ _end_keywords = _end_category
+ _end_itunes_category = _end_category
+
+ def _start_cloud(self, attrsD):
+ self._getContext()['cloud'] = FeedParserDict(attrsD)
+
+ def _start_link(self, attrsD):
+ attrsD.setdefault('rel', 'alternate')
+ attrsD.setdefault('type', 'text/html')
+ attrsD = self._itsAnHrefDamnIt(attrsD)
+ if attrsD.has_key('href'):
+ attrsD['href'] = self.resolveURI(attrsD['href'])
+ expectingText = self.infeed or self.inentry or self.insource
+ context = self._getContext()
+ context.setdefault('links', [])
+ context['links'].append(FeedParserDict(attrsD))
+ if attrsD['rel'] == 'enclosure':
+ self._start_enclosure(attrsD)
+ if attrsD.has_key('href'):
+ expectingText = 0
+ if (attrsD.get('rel') == 'alternate') and (self.mapContentType(attrsD.get('type')) in self.html_types):
+ context['link'] = attrsD['href']
+ else:
+ self.push('link', expectingText)
+ _start_producturl = _start_link
+
+ def _end_link(self):
+ value = self.pop('link')
+ context = self._getContext()
+ if self.intextinput:
+ context['textinput']['link'] = value
+ if self.inimage:
+ context['image']['link'] = value
+ _end_producturl = _end_link
+
+ def _start_guid(self, attrsD):
+ self.guidislink = (attrsD.get('ispermalink', 'true') == 'true')
+ self.push('id', 1)
+
+ def _end_guid(self):
+ value = self.pop('id')
+ self._save('guidislink', self.guidislink and not self._getContext().has_key('link'))
+ if self.guidislink:
+ # guid acts as link, but only if 'ispermalink' is not present or is 'true',
+ # and only if the item doesn't already have a link element
+ self._save('link', value)
+
+ def _start_title(self, attrsD):
+ self.pushContent('title', attrsD, 'text/plain', self.infeed or self.inentry or self.insource)
+ _start_dc_title = _start_title
+ _start_media_title = _start_title
+
+ def _end_title(self):
+ value = self.popContent('title')
+ context = self._getContext()
+ if self.intextinput:
+ context['textinput']['title'] = value
+ elif self.inimage:
+ context['image']['title'] = value
+ _end_dc_title = _end_title
+ _end_media_title = _end_title
+
+ def _start_description(self, attrsD):
+ context = self._getContext()
+ if context.has_key('summary'):
+ self._summaryKey = 'content'
+ self._start_content(attrsD)
+ else:
+ self.pushContent('description', attrsD, 'text/html', self.infeed or self.inentry or self.insource)
+
+ def _start_abstract(self, attrsD):
+ self.pushContent('description', attrsD, 'text/plain', self.infeed or self.inentry or self.insource)
+
+ def _end_description(self):
+ if self._summaryKey == 'content':
+ self._end_content()
+ else:
+ value = self.popContent('description')
+ context = self._getContext()
+ if self.intextinput:
+ context['textinput']['description'] = value
+ elif self.inimage:
+ context['image']['description'] = value
+ self._summaryKey = None
+ _end_abstract = _end_description
+
+ def _start_info(self, attrsD):
+ self.pushContent('info', attrsD, 'text/plain', 1)
+ _start_feedburner_browserfriendly = _start_info
+
+ def _end_info(self):
+ self.popContent('info')
+ _end_feedburner_browserfriendly = _end_info
+
+ def _start_generator(self, attrsD):
+ if attrsD:
+ attrsD = self._itsAnHrefDamnIt(attrsD)
+ if attrsD.has_key('href'):
+ attrsD['href'] = self.resolveURI(attrsD['href'])
+ self._getContext()['generator_detail'] = FeedParserDict(attrsD)
+ self.push('generator', 1)
+
+ def _end_generator(self):
+ value = self.pop('generator')
+ context = self._getContext()
+ if context.has_key('generator_detail'):
+ context['generator_detail']['name'] = value
+
+ def _start_admin_generatoragent(self, attrsD):
+ self.push('generator', 1)
+ value = self._getAttribute(attrsD, 'rdf:resource')
+ if value:
+ self.elementstack[-1][2].append(value)
+ self.pop('generator')
+ self._getContext()['generator_detail'] = FeedParserDict({'href': value})
+
+ def _start_admin_errorreportsto(self, attrsD):
+ self.push('errorreportsto', 1)
+ value = self._getAttribute(attrsD, 'rdf:resource')
+ if value:
+ self.elementstack[-1][2].append(value)
+ self.pop('errorreportsto')
+
+ def _start_summary(self, attrsD):
+ context = self._getContext()
+ if context.has_key('summary'):
+ self._summaryKey = 'content'
+ self._start_content(attrsD)
+ else:
+ self._summaryKey = 'summary'
+ self.pushContent(self._summaryKey, attrsD, 'text/plain', 1)
+ _start_itunes_summary = _start_summary
+
+ def _end_summary(self):
+ if self._summaryKey == 'content':
+ self._end_content()
+ else:
+ self.popContent(self._summaryKey or 'summary')
+ self._summaryKey = None
+ _end_itunes_summary = _end_summary
+
+ def _start_enclosure(self, attrsD):
+ attrsD = self._itsAnHrefDamnIt(attrsD)
+ self._getContext().setdefault('enclosures', []).append(FeedParserDict(attrsD))
+ href = attrsD.get('href')
+ if href:
+ context = self._getContext()
+ if not context.get('id'):
+ context['id'] = href
+
+ def _start_source(self, attrsD):
+ self.insource = 1
+
+ def _end_source(self):
+ self.insource = 0
+ self._getContext()['source'] = copy.deepcopy(self.sourcedata)
+ self.sourcedata.clear()
+
+ def _start_content(self, attrsD):
+ self.pushContent('content', attrsD, 'text/plain', 1)
+ src = attrsD.get('src')
+ if src:
+ self.contentparams['src'] = src
+ self.push('content', 1)
+
+ def _start_prodlink(self, attrsD):
+ self.pushContent('content', attrsD, 'text/html', 1)
+
+ def _start_body(self, attrsD):
+ self.pushContent('content', attrsD, 'application/xhtml+xml', 1)
+ _start_xhtml_body = _start_body
+
+ def _start_content_encoded(self, attrsD):
+ self.pushContent('content', attrsD, 'text/html', 1)
+ _start_fullitem = _start_content_encoded
+
+ def _end_content(self):
+ copyToDescription = self.mapContentType(self.contentparams.get('type')) in (['text/plain'] + self.html_types)
+ value = self.popContent('content')
+ if copyToDescription:
+ self._save('description', value)
+ _end_body = _end_content
+ _end_xhtml_body = _end_content
+ _end_content_encoded = _end_content
+ _end_fullitem = _end_content
+ _end_prodlink = _end_content
+
+ def _start_itunes_image(self, attrsD):
+ self.push('itunes_image', 0)
+ self._getContext()['image'] = FeedParserDict({'href': attrsD.get('href')})
+ _start_itunes_link = _start_itunes_image
+
+ def _end_itunes_block(self):
+ value = self.pop('itunes_block', 0)
+ self._getContext()['itunes_block'] = (value == 'yes') and 1 or 0
+
+ def _end_itunes_explicit(self):
+ value = self.pop('itunes_explicit', 0)
+ self._getContext()['itunes_explicit'] = (value == 'yes') and 1 or 0
+
+if _XML_AVAILABLE:
+ class _StrictFeedParser(_FeedParserMixin, xml.sax.handler.ContentHandler):
+ def __init__(self, baseuri, baselang, encoding):
+ if _debug: sys.stderr.write('trying StrictFeedParser\n')
+ xml.sax.handler.ContentHandler.__init__(self)
+ _FeedParserMixin.__init__(self, baseuri, baselang, encoding)
+ self.bozo = 0
+ self.exc = None
+
+ def startPrefixMapping(self, prefix, uri):
+ self.trackNamespace(prefix, uri)
+
+ def startElementNS(self, name, qname, attrs):
+ namespace, localname = name
+ lowernamespace = str(namespace or '').lower()
+ if lowernamespace.find('backend.userland.com/rss') <> -1:
+ # match any backend.userland.com namespace
+ namespace = 'http://backend.userland.com/rss'
+ lowernamespace = namespace
+ if qname and qname.find(':') > 0:
+ givenprefix = qname.split(':')[0]
+ else:
+ givenprefix = None
+ prefix = self._matchnamespaces.get(lowernamespace, givenprefix)
+ if givenprefix and (prefix == None or (prefix == '' and lowernamespace == '')) and not self.namespacesInUse.has_key(givenprefix):
+ raise UndeclaredNamespace, "'%s' is not associated with a namespace" % givenprefix
+ if prefix:
+ localname = prefix + ':' + localname
+ localname = str(localname).lower()
+ if _debug: sys.stderr.write('startElementNS: qname = %s, namespace = %s, givenprefix = %s, prefix = %s, attrs = %s, localname = %s\n' % (qname, namespace, givenprefix, prefix, attrs.items(), localname))
+
+ # qname implementation is horribly broken in Python 2.1 (it
+ # doesn't report any), and slightly broken in Python 2.2 (it
+ # doesn't report the xml: namespace). So we match up namespaces
+ # with a known list first, and then possibly override them with
+ # the qnames the SAX parser gives us (if indeed it gives us any
+ # at all). Thanks to MatejC for helping me test this and
+ # tirelessly telling me that it didn't work yet.
+ attrsD = {}
+ for (namespace, attrlocalname), attrvalue in attrs._attrs.items():
+ lowernamespace = (namespace or '').lower()
+ prefix = self._matchnamespaces.get(lowernamespace, '')
+ if prefix:
+ attrlocalname = prefix + ':' + attrlocalname
+ attrsD[str(attrlocalname).lower()] = attrvalue
+ for qname in attrs.getQNames():
+ attrsD[str(qname).lower()] = attrs.getValueByQName(qname)
+ self.unknown_starttag(localname, attrsD.items())
+
+ def characters(self, text):
+ self.handle_data(text)
+
+ def endElementNS(self, name, qname):
+ namespace, localname = name
+ lowernamespace = str(namespace or '').lower()
+ if qname and qname.find(':') > 0:
+ givenprefix = qname.split(':')[0]
+ else:
+ givenprefix = ''
+ prefix = self._matchnamespaces.get(lowernamespace, givenprefix)
+ if prefix:
+ localname = prefix + ':' + localname
+ localname = str(localname).lower()
+ self.unknown_endtag(localname)
+
+ def error(self, exc):
+ self.bozo = 1
+ self.exc = exc
+
+ def fatalError(self, exc):
+ self.error(exc)
+ raise exc
+
+class _BaseHTMLProcessor(sgmllib.SGMLParser):
+ elements_no_end_tag = ['area', 'base', 'basefont', 'br', 'col', 'frame', 'hr',
+ 'img', 'input', 'isindex', 'link', 'meta', 'param']
+
+ def __init__(self, encoding):
+ self.encoding = encoding
+ if _debug: sys.stderr.write('entering BaseHTMLProcessor, encoding=%s\n' % self.encoding)
+ sgmllib.SGMLParser.__init__(self)
+
+ def reset(self):
+ self.pieces = []
+ sgmllib.SGMLParser.reset(self)
+
+ def _shorttag_replace(self, match):
+ tag = match.group(1)
+ if tag in self.elements_no_end_tag:
+ return '<' + tag + ' />'
+ else:
+ return '<' + tag + '></' + tag + '>'
+
+ def feed(self, data):
+ data = re.compile(r'<!((?!DOCTYPE|--|\[))', re.IGNORECASE).sub(r'<!\1', data)
+ #data = re.sub(r'<(\S+?)\s*?/>', self._shorttag_replace, data) # bug [ 1399464 ] Bad regexp for _shorttag_replace
+ data = re.sub(r'<([^<\s]+?)\s*/>', self._shorttag_replace, data)
+ data = data.replace(''', "'")
+ data = data.replace('"', '"')
+ if self.encoding and type(data) == type(u''):
+ data = data.encode(self.encoding)
+ sgmllib.SGMLParser.feed(self, data)
+
+ def normalize_attrs(self, attrs):
+ # utility method to be called by descendants
+ attrs = [(k.lower(), v) for k, v in attrs]
+ attrs = [(k, k in ('rel', 'type') and v.lower() or v) for k, v in attrs]
+ return attrs
+
+ def unknown_starttag(self, tag, attrs):
+ # called for each start tag
+ # attrs is a list of (attr, value) tuples
+ # e.g. for <pre class='screen'>, tag='pre', attrs=[('class', 'screen')]
+ if _debug: sys.stderr.write('_BaseHTMLProcessor, unknown_starttag, tag=%s\n' % tag)
+ uattrs = []
+ # thanks to Kevin Marks for this breathtaking hack to deal with (valid) high-bit attribute values in UTF-8 feeds
+ for key, value in attrs:
+ if type(value) != type(u''):
+ value = unicode(value, self.encoding)
+ uattrs.append((unicode(key, self.encoding), value))
+ strattrs = u''.join([u' %s="%s"' % (key, value) for key, value in uattrs]).encode(self.encoding)
+ if tag in self.elements_no_end_tag:
+ self.pieces.append('<%(tag)s%(strattrs)s />' % locals())
+ else:
+ self.pieces.append('<%(tag)s%(strattrs)s>' % locals())
+
+ def unknown_endtag(self, tag):
+ # called for each end tag, e.g. for </pre>, tag will be 'pre'
+ # Reconstruct the original end tag.
+ if tag not in self.elements_no_end_tag:
+ self.pieces.append("</%(tag)s>" % locals())
+
+ def handle_charref(self, ref):
+ # called for each character reference, e.g. for ' ', ref will be '160'
+ # Reconstruct the original character reference.
+ self.pieces.append('&#%(ref)s;' % locals())
+
+ def handle_entityref(self, ref):
+ # called for each entity reference, e.g. for '©', ref will be 'copy'
+ # Reconstruct the original entity reference.
+ self.pieces.append('&%(ref)s;' % locals())
+
+ def handle_data(self, text):
+ # called for each block of plain text, i.e. outside of any tag and
+ # not containing any character or entity references
+ # Store the original text verbatim.
+ if _debug: sys.stderr.write('_BaseHTMLProcessor, handle_text, text=%s\n' % text)
+ self.pieces.append(text)
+
+ def handle_comment(self, text):
+ # called for each HTML comment, e.g. <!-- insert Javascript code here -->
+ # Reconstruct the original comment.
+ self.pieces.append('<!--%(text)s-->' % locals())
+
+ def handle_pi(self, text):
+ # called for each processing instruction, e.g. <?instruction>
+ # Reconstruct original processing instruction.
+ self.pieces.append('<?%(text)s>' % locals())
+
+ def handle_decl(self, text):
+ # called for the DOCTYPE, if present, e.g.
+ # <!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"
+ # "http://www.w3.org/TR/html4/loose.dtd">
+ # Reconstruct original DOCTYPE
+ self.pieces.append('<!%(text)s>' % locals())
+
+ _new_declname_match = re.compile(r'[a-zA-Z][-_.a-zA-Z0-9:]*\s*').match
+ def _scan_name(self, i, declstartpos):
+ rawdata = self.rawdata
+ n = len(rawdata)
+ if i == n:
+ return None, -1
+ m = self._new_declname_match(rawdata, i)
+ if m:
+ s = m.group()
+ name = s.strip()
+ if (i + len(s)) == n:
+ return None, -1 # end of buffer
+ return name.lower(), m.end()
+ else:
+ self.handle_data(rawdata)
+# self.updatepos(declstartpos, i)
+ return None, -1
+
+ def output(self):
+ '''Return processed HTML as a single string'''
+ return ''.join([str(p) for p in self.pieces])
+
+class _LooseFeedParser(_FeedParserMixin, _BaseHTMLProcessor):
+ def __init__(self, baseuri, baselang, encoding):
+ sgmllib.SGMLParser.__init__(self)
+ _FeedParserMixin.__init__(self, baseuri, baselang, encoding)
+
+ def decodeEntities(self, element, data):
+ data = data.replace('<', '<')
+ data = data.replace('<', '<')
+ data = data.replace('>', '>')
+ data = data.replace('>', '>')
+ data = data.replace('&', '&')
+ data = data.replace('&', '&')
+ data = data.replace('"', '"')
+ data = data.replace('"', '"')
+ data = data.replace(''', ''')
+ data = data.replace(''', ''')
+ if self.contentparams.has_key('type') and not self.contentparams.get('type', 'xml').endswith('xml'):
+ data = data.replace('<', '<')
+ data = data.replace('>', '>')
+ data = data.replace('&', '&')
+ data = data.replace('"', '"')
+ data = data.replace(''', "'")
+ return data
+
+class _RelativeURIResolver(_BaseHTMLProcessor):
+ relative_uris = [('a', 'href'),
+ ('applet', 'codebase'),
+ ('area', 'href'),
+ ('blockquote', 'cite'),
+ ('body', 'background'),
+ ('del', 'cite'),
+ ('form', 'action'),
+ ('frame', 'longdesc'),
+ ('frame', 'src'),
+ ('iframe', 'longdesc'),
+ ('iframe', 'src'),
+ ('head', 'profile'),
+ ('img', 'longdesc'),
+ ('img', 'src'),
+ ('img', 'usemap'),
+ ('input', 'src'),
+ ('input', 'usemap'),
+ ('ins', 'cite'),
+ ('link', 'href'),
+ ('object', 'classid'),
+ ('object', 'codebase'),
+ ('object', 'data'),
+ ('object', 'usemap'),
+ ('q', 'cite'),
+ ('script', 'src')]
+
+ def __init__(self, baseuri, encoding):
+ _BaseHTMLProcessor.__init__(self, encoding)
+ self.baseuri = baseuri
+
+ def resolveURI(self, uri):
+ return _urljoin(self.baseuri, uri)
+
+ def unknown_starttag(self, tag, attrs):
+ attrs = self.normalize_attrs(attrs)
+ attrs = [(key, ((tag, key) in self.relative_uris) and self.resolveURI(value) or value) for key, value in attrs]
+ _BaseHTMLProcessor.unknown_starttag(self, tag, attrs)
+
+def _resolveRelativeURIs(htmlSource, baseURI, encoding):
+ if _debug: sys.stderr.write('entering _resolveRelativeURIs\n')
+ p = _RelativeURIResolver(baseURI, encoding)
+ p.feed(htmlSource)
+ return p.output()
+
+class _HTMLSanitizer(_BaseHTMLProcessor):
+ acceptable_elements = ['a', 'abbr', 'acronym', 'address', 'area', 'b', 'big',
+ 'blockquote', 'br', 'button', 'caption', 'center', 'cite', 'code', 'col',
+ 'colgroup', 'dd', 'del', 'dfn', 'dir', 'div', 'dl', 'dt', 'em', 'fieldset',
+ 'font', 'form', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'hr', 'i', 'img', 'input',
+ 'ins', 'kbd', 'label', 'legend', 'li', 'map', 'menu', 'ol', 'optgroup',
+ 'option', 'p', 'pre', 'q', 's', 'samp', 'select', 'small', 'span', 'strike',
+ 'strong', 'sub', 'sup', 'table', 'tbody', 'td', 'textarea', 'tfoot', 'th',
+ 'thead', 'tr', 'tt', 'u', 'ul', 'var']
+
+ acceptable_attributes = ['abbr', 'accept', 'accept-charset', 'accesskey',
+ 'action', 'align', 'alt', 'axis', 'border', 'cellpadding', 'cellspacing',
+ 'char', 'charoff', 'charset', 'checked', 'cite', 'class', 'clear', 'cols',
+ 'colspan', 'color', 'compact', 'coords', 'datetime', 'dir', 'disabled',
+ 'enctype', 'for', 'frame', 'headers', 'height', 'href', 'hreflang', 'hspace',
+ 'id', 'ismap', 'label', 'lang', 'longdesc', 'maxlength', 'media', 'method',
+ 'multiple', 'name', 'nohref', 'noshade', 'nowrap', 'prompt', 'readonly',
+ 'rel', 'rev', 'rows', 'rowspan', 'rules', 'scope', 'selected', 'shape', 'size',
+ 'span', 'src', 'start', 'summary', 'tabindex', 'target', 'title', 'type',
+ 'usemap', 'valign', 'value', 'vspace', 'width']
+
+ unacceptable_elements_with_end_tag = ['script', 'applet']
+
+ def reset(self):
+ _BaseHTMLProcessor.reset(self)
+ self.unacceptablestack = 0
+
+ def unknown_starttag(self, tag, attrs):
+ if not tag in self.acceptable_elements:
+ if tag in self.unacceptable_elements_with_end_tag:
+ self.unacceptablestack += 1
+ return
+ attrs = self.normalize_attrs(attrs)
+ attrs = [(key, value) for key, value in attrs if key in self.acceptable_attributes]
+ _BaseHTMLProcessor.unknown_starttag(self, tag, attrs)
+
+ def unknown_endtag(self, tag):
+ if not tag in self.acceptable_elements:
+ if tag in self.unacceptable_elements_with_end_tag:
+ self.unacceptablestack -= 1
+ return
+ _BaseHTMLProcessor.unknown_endtag(self, tag)
+
+ def handle_pi(self, text):
+ pass
+
+ def handle_decl(self, text):
+ pass
+
+ def handle_data(self, text):
+ if not self.unacceptablestack:
+ _BaseHTMLProcessor.handle_data(self, text)
+
+def _sanitizeHTML(htmlSource, encoding):
+ p = _HTMLSanitizer(encoding)
+ p.feed(htmlSource)
+ data = p.output()
+ if TIDY_MARKUP:
+ # loop through list of preferred Tidy interfaces looking for one that's installed,
+ # then set up a common _tidy function to wrap the interface-specific API.
+ _tidy = None
+ for tidy_interface in PREFERRED_TIDY_INTERFACES:
+ try:
+ if tidy_interface == "uTidy":
+ from tidy import parseString as _utidy
+ def _tidy(data, **kwargs):
+ return str(_utidy(data, **kwargs))
+ break
+ elif tidy_interface == "mxTidy":
+ from mx.Tidy import Tidy as _mxtidy
+ def _tidy(data, **kwargs):
+ nerrors, nwarnings, data, errordata = _mxtidy.tidy(data, **kwargs)
+ return data
+ break
+ except:
+ pass
+ if _tidy:
+ utf8 = type(data) == type(u'')
+ if utf8:
+ data = data.encode('utf-8')
+ data = _tidy(data, output_xhtml=1, numeric_entities=1, wrap=0, char_encoding="utf8")
+ if utf8:
+ data = unicode(data, 'utf-8')
+ if data.count('<body'):
+ data = data.split('<body', 1)[1]
+ if data.count('>'):
+ data = data.split('>', 1)[1]
+ if data.count('</body'):
+ data = data.split('</body', 1)[0]
+ data = data.strip().replace('\r\n', '\n')
+ return data
+
+class _FeedURLHandler(urllib2.HTTPDigestAuthHandler, urllib2.HTTPRedirectHandler, urllib2.HTTPDefaultErrorHandler):
+ def http_error_default(self, req, fp, code, msg, headers):
+ if ((code / 100) == 3) and (code != 304):
+ return self.http_error_302(req, fp, code, msg, headers)
+ infourl = urllib.addinfourl(fp, headers, req.get_full_url())
+ infourl.status = code
+ return infourl
+
+ def http_error_302(self, req, fp, code, msg, headers):
+ if headers.dict.has_key('location'):
+ infourl = urllib2.HTTPRedirectHandler.http_error_302(self, req, fp, code, msg, headers)
+ else:
+ infourl = urllib.addinfourl(fp, headers, req.get_full_url())
+ if not hasattr(infourl, 'status'):
+ infourl.status = code
+ return infourl
+
+ def http_error_301(self, req, fp, code, msg, headers):
+ if headers.dict.has_key('location'):
+ infourl = urllib2.HTTPRedirectHandler.http_error_301(self, req, fp, code, msg, headers)
+ else:
+ infourl = urllib.addinfourl(fp, headers, req.get_full_url())
+ if not hasattr(infourl, 'status'):
+ infourl.status = code
+ return infourl
+
+ http_error_300 = http_error_302
+ http_error_303 = http_error_302
+ http_error_307 = http_error_302
+
+ def http_error_401(self, req, fp, code, msg, headers):
+ # Check if
+ # - server requires digest auth, AND
+ # - we tried (unsuccessfully) with basic auth, AND
+ # - we're using Python 2.3.3 or later (digest auth is irreparably broken in earlier versions)
+ # If all conditions hold, parse authentication information
+ # out of the Authorization header we sent the first time
+ # (for the username and password) and the WWW-Authenticate
+ # header the server sent back (for the realm) and retry
+ # the request with the appropriate digest auth headers instead.
+ # This evil genius hack has been brought to you by Aaron Swartz.
+ host = urlparse.urlparse(req.get_full_url())[1]
+ try:
+ assert sys.version.split()[0] >= '2.3.3'
+ assert base64 != None
+ user, passw = base64.decodestring(req.headers['Authorization'].split(' ')[1]).split(':')
+ realm = re.findall('realm="([^"]*)"', headers['WWW-Authenticate'])[0]
+ self.add_password(realm, host, user, passw)
+ retry = self.http_error_auth_reqed('www-authenticate', host, req, headers)
+ self.reset_retry_count()
+ return retry
+ except:
+ return self.http_error_default(req, fp, code, msg, headers)
+
+def _open_resource(url_file_stream_or_string, etag, modified, agent, referrer, handlers):
+ """URL, filename, or string --> stream
+
+ This function lets you define parsers that take any input source
+ (URL, pathname to local or network file, or actual data as a string)
+ and deal with it in a uniform manner. Returned object is guaranteed
+ to have all the basic stdio read methods (read, readline, readlines).
+ Just .close() the object when you're done with it.
+
+ If the etag argument is supplied, it will be used as the value of an
+ If-None-Match request header.
+
+ If the modified argument is supplied, it must be a tuple of 9 integers
+ as returned by gmtime() in the standard Python time module. This MUST
+ be in GMT (Greenwich Mean Time). The formatted date/time will be used
+ as the value of an If-Modified-Since request header.
+
+ If the agent argument is supplied, it will be used as the value of a
+ User-Agent request header.
+
+ If the referrer argument is supplied, it will be used as the value of a
+ Referer[sic] request header.
+
+ If handlers is supplied, it is a list of handlers used to build a
+ urllib2 opener.
+ """
+
+ if hasattr(url_file_stream_or_string, 'read'):
+ return url_file_stream_or_string
+
+ if url_file_stream_or_string == '-':
+ return sys.stdin
+
+ if urlparse.urlparse(url_file_stream_or_string)[0] in ('http', 'https', 'ftp'):
+ if not agent:
+ agent = USER_AGENT
+ # test for inline user:password for basic auth
+ auth = None
+ if base64:
+ urltype, rest = urllib.splittype(url_file_stream_or_string)
+ realhost, rest = urllib.splithost(rest)
+ if realhost:
+ user_passwd, realhost = urllib.splituser(realhost)
+ if user_passwd:
+ url_file_stream_or_string = '%s://%s%s' % (urltype, realhost, rest)
+ auth = base64.encodestring(user_passwd).strip()
+ # try to open with urllib2 (to use optional headers)
+ request = urllib2.Request(url_file_stream_or_string)
+ request.add_header('User-Agent', agent)
+ if etag:
+ request.add_header('If-None-Match', etag)
+ if modified:
+ # format into an RFC 1123-compliant timestamp. We can't use
+ # time.strftime() since the %a and %b directives can be affected
+ # by the current locale, but RFC 2616 states that dates must be
+ # in English.
+ short_weekdays = ['Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun']
+ months = ['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec']
+ request.add_header('If-Modified-Since', '%s, %02d %s %04d %02d:%02d:%02d GMT' % (short_weekdays[modified[6]], modified[2], months[modified[1] - 1], modified[0], modified[3], modified[4], modified[5]))
+ if referrer:
+ request.add_header('Referer', referrer)
+ if gzip and zlib:
+ request.add_header('Accept-encoding', 'gzip, deflate')
+ elif gzip:
+ request.add_header('Accept-encoding', 'gzip')
+ elif zlib:
+ request.add_header('Accept-encoding', 'deflate')
+ else:
+ request.add_header('Accept-encoding', '')
+ if auth:
+ request.add_header('Authorization', 'Basic %s' % auth)
+ if ACCEPT_HEADER:
+ request.add_header('Accept', ACCEPT_HEADER)
+ request.add_header('A-IM', 'feed') # RFC 3229 support
+ opener = apply(urllib2.build_opener, tuple([_FeedURLHandler()] + handlers))
+ opener.addheaders = [] # RMK - must clear so we only send our custom User-Agent
+ try:
+ return opener.open(request)
+ finally:
+ opener.close() # JohnD
+
+ # try to open with native open function (if url_file_stream_or_string is a filename)
+ try:
+ return open(url_file_stream_or_string)
+ except:
+ pass
+
+ # treat url_file_stream_or_string as string
+ return _StringIO(str(url_file_stream_or_string))
+
+_date_handlers = []
+def registerDateHandler(func):
+ '''Register a date handler function (takes string, returns 9-tuple date in GMT)'''
+ _date_handlers.insert(0, func)
+
+# ISO-8601 date parsing routines written by Fazal Majid.
+# The ISO 8601 standard is very convoluted and irregular - a full ISO 8601
+# parser is beyond the scope of feedparser and would be a worthwhile addition
+# to the Python library.
+# A single regular expression cannot parse ISO 8601 date formats into groups
+# as the standard is highly irregular (for instance is 030104 2003-01-04 or
+# 0301-04-01), so we use templates instead.
+# Please note the order in templates is significant because we need a
+# greedy match.
+_iso8601_tmpl = ['YYYY-?MM-?DD', 'YYYY-MM', 'YYYY-?OOO',
+ 'YY-?MM-?DD', 'YY-?OOO', 'YYYY',
+ '-YY-?MM', '-OOO', '-YY',
+ '--MM-?DD', '--MM',
+ '---DD',
+ 'CC', '']
+_iso8601_re = [
+ tmpl.replace(
+ 'YYYY', r'(?P<year>\d{4})').replace(
+ 'YY', r'(?P<year>\d\d)').replace(
+ 'MM', r'(?P<month>[01]\d)').replace(
+ 'DD', r'(?P<day>[0123]\d)').replace(
+ 'OOO', r'(?P<ordinal>[0123]\d\d)').replace(
+ 'CC', r'(?P<century>\d\d$)')
+ + r'(T?(?P<hour>\d{2}):(?P<minute>\d{2})'
+ + r'(:(?P<second>\d{2}))?'
+ + r'(?P<tz>[+-](?P<tzhour>\d{2})(:(?P<tzmin>\d{2}))?|Z)?)?'
+ for tmpl in _iso8601_tmpl]
+del tmpl
+_iso8601_matches = [re.compile(regex).match for regex in _iso8601_re]
+del regex
+def _parse_date_iso8601(dateString):
+ '''Parse a variety of ISO-8601-compatible formats like 20040105'''
+ m = None
+ for _iso8601_match in _iso8601_matches:
+ m = _iso8601_match(dateString)
+ if m: break
+ if not m: return
+ if m.span() == (0, 0): return
+ params = m.groupdict()
+ ordinal = params.get('ordinal', 0)
+ if ordinal:
+ ordinal = int(ordinal)
+ else:
+ ordinal = 0
+ year = params.get('year', '--')
+ if not year or year == '--':
+ year = time.gmtime()[0]
+ elif len(year) == 2:
+ # ISO 8601 assumes current century, i.e. 93 -> 2093, NOT 1993
+ year = 100 * int(time.gmtime()[0] / 100) + int(year)
+ else:
+ year = int(year)
+ month = params.get('month', '-')
+ if not month or month == '-':
+ # ordinals are NOT normalized by mktime, we simulate them
+ # by setting month=1, day=ordinal
+ if ordinal:
+ month = 1
+ else:
+ month = time.gmtime()[1]
+ month = int(month)
+ day = params.get('day', 0)
+ if not day:
+ # see above
+ if ordinal:
+ day = ordinal
+ elif params.get('century', 0) or \
+ params.get('year', 0) or params.get('month', 0):
+ day = 1
+ else:
+ day = time.gmtime()[2]
+ else:
+ day = int(day)
+ # special case of the century - is the first year of the 21st century
+ # 2000 or 2001 ? The debate goes on...
+ if 'century' in params.keys():
+ year = (int(params['century']) - 1) * 100 + 1
+ # in ISO 8601 most fields are optional
+ for field in ['hour', 'minute', 'second', 'tzhour', 'tzmin']:
+ if not params.get(field, None):
+ params[field] = 0
+ hour = int(params.get('hour', 0))
+ minute = int(params.get('minute', 0))
+ second = int(params.get('second', 0))
+ # weekday is normalized by mktime(), we can ignore it
+ weekday = 0
+ # daylight savings is complex, but not needed for feedparser's purposes
+ # as time zones, if specified, include mention of whether it is active
+ # (e.g. PST vs. PDT, CET). Using -1 is implementation-dependent and
+ # and most implementations have DST bugs
+ daylight_savings_flag = 0
+ tm = [year, month, day, hour, minute, second, weekday,
+ ordinal, daylight_savings_flag]
+ # ISO 8601 time zone adjustments
+ tz = params.get('tz')
+ if tz and tz != 'Z':
+ if tz[0] == '-':
+ tm[3] += int(params.get('tzhour', 0))
+ tm[4] += int(params.get('tzmin', 0))
+ elif tz[0] == '+':
+ tm[3] -= int(params.get('tzhour', 0))
+ tm[4] -= int(params.get('tzmin', 0))
+ else:
+ return None
+ # Python's time.mktime() is a wrapper around the ANSI C mktime(3c)
+ # which is guaranteed to normalize d/m/y/h/m/s.
+ # Many implementations have bugs, but we'll pretend they don't.
+ return time.localtime(time.mktime(tm))
+registerDateHandler(_parse_date_iso8601)
+
+# 8-bit date handling routines written by ytrewq1.
+_korean_year = u'\ub144' # b3e2 in euc-kr
+_korean_month = u'\uc6d4' # bff9 in euc-kr
+_korean_day = u'\uc77c' # c0cf in euc-kr
+_korean_am = u'\uc624\uc804' # bfc0 c0fc in euc-kr
+_korean_pm = u'\uc624\ud6c4' # bfc0 c8c4 in euc-kr
+
+_korean_onblog_date_re = \
+ re.compile('(\d{4})%s\s+(\d{2})%s\s+(\d{2})%s\s+(\d{2}):(\d{2}):(\d{2})' % \
+ (_korean_year, _korean_month, _korean_day))
+_korean_nate_date_re = \
+ re.compile(u'(\d{4})-(\d{2})-(\d{2})\s+(%s|%s)\s+(\d{,2}):(\d{,2}):(\d{,2})' % \
+ (_korean_am, _korean_pm))
+def _parse_date_onblog(dateString):
+ '''Parse a string according to the OnBlog 8-bit date format'''
+ m = _korean_onblog_date_re.match(dateString)
+ if not m: return
+ w3dtfdate = '%(year)s-%(month)s-%(day)sT%(hour)s:%(minute)s:%(second)s%(zonediff)s' % \
+ {'year': m.group(1), 'month': m.group(2), 'day': m.group(3),\
+ 'hour': m.group(4), 'minute': m.group(5), 'second': m.group(6),\
+ 'zonediff': '+09:00'}
+ if _debug: sys.stderr.write('OnBlog date parsed as: %s\n' % w3dtfdate)
+ return _parse_date_w3dtf(w3dtfdate)
+registerDateHandler(_parse_date_onblog)
+
+def _parse_date_nate(dateString):
+ '''Parse a string according to the Nate 8-bit date format'''
+ m = _korean_nate_date_re.match(dateString)
+ if not m: return
+ hour = int(m.group(5))
+ ampm = m.group(4)
+ if (ampm == _korean_pm):
+ hour += 12
+ hour = str(hour)
+ if len(hour) == 1:
+ hour = '0' + hour
+ w3dtfdate = '%(year)s-%(month)s-%(day)sT%(hour)s:%(minute)s:%(second)s%(zonediff)s' % \
+ {'year': m.group(1), 'month': m.group(2), 'day': m.group(3),\
+ 'hour': hour, 'minute': m.group(6), 'second': m.group(7),\
+ 'zonediff': '+09:00'}
+ if _debug: sys.stderr.write('Nate date parsed as: %s\n' % w3dtfdate)
+ return _parse_date_w3dtf(w3dtfdate)
+registerDateHandler(_parse_date_nate)
+
+_mssql_date_re = \
+ re.compile('(\d{4})-(\d{2})-(\d{2})\s+(\d{2}):(\d{2}):(\d{2})(\.\d+)?')
+def _parse_date_mssql(dateString):
+ '''Parse a string according to the MS SQL date format'''
+ m = _mssql_date_re.match(dateString)
+ if not m: return
+ w3dtfdate = '%(year)s-%(month)s-%(day)sT%(hour)s:%(minute)s:%(second)s%(zonediff)s' % \
+ {'year': m.group(1), 'month': m.group(2), 'day': m.group(3),\
+ 'hour': m.group(4), 'minute': m.group(5), 'second': m.group(6),\
+ 'zonediff': '+09:00'}
+ if _debug: sys.stderr.write('MS SQL date parsed as: %s\n' % w3dtfdate)
+ return _parse_date_w3dtf(w3dtfdate)
+registerDateHandler(_parse_date_mssql)
+
+# Unicode strings for Greek date strings
+_greek_months = \
+ { \
+ u'\u0399\u03b1\u03bd': u'Jan', # c9e1ed in iso-8859-7
+ u'\u03a6\u03b5\u03b2': u'Feb', # d6e5e2 in iso-8859-7
+ u'\u039c\u03ac\u03ce': u'Mar', # ccdcfe in iso-8859-7
+ u'\u039c\u03b1\u03ce': u'Mar', # cce1fe in iso-8859-7
+ u'\u0391\u03c0\u03c1': u'Apr', # c1f0f1 in iso-8859-7
+ u'\u039c\u03ac\u03b9': u'May', # ccdce9 in iso-8859-7
+ u'\u039c\u03b1\u03ca': u'May', # cce1fa in iso-8859-7
+ u'\u039c\u03b1\u03b9': u'May', # cce1e9 in iso-8859-7
+ u'\u0399\u03bf\u03cd\u03bd': u'Jun', # c9effded in iso-8859-7
+ u'\u0399\u03bf\u03bd': u'Jun', # c9efed in iso-8859-7
+ u'\u0399\u03bf\u03cd\u03bb': u'Jul', # c9effdeb in iso-8859-7
+ u'\u0399\u03bf\u03bb': u'Jul', # c9f9eb in iso-8859-7
+ u'\u0391\u03cd\u03b3': u'Aug', # c1fde3 in iso-8859-7
+ u'\u0391\u03c5\u03b3': u'Aug', # c1f5e3 in iso-8859-7
+ u'\u03a3\u03b5\u03c0': u'Sep', # d3e5f0 in iso-8859-7
+ u'\u039f\u03ba\u03c4': u'Oct', # cfeaf4 in iso-8859-7
+ u'\u039d\u03bf\u03ad': u'Nov', # cdefdd in iso-8859-7
+ u'\u039d\u03bf\u03b5': u'Nov', # cdefe5 in iso-8859-7
+ u'\u0394\u03b5\u03ba': u'Dec', # c4e5ea in iso-8859-7
+ }
+
+_greek_wdays = \
+ { \
+ u'\u039a\u03c5\u03c1': u'Sun', # caf5f1 in iso-8859-7
+ u'\u0394\u03b5\u03c5': u'Mon', # c4e5f5 in iso-8859-7
+ u'\u03a4\u03c1\u03b9': u'Tue', # d4f1e9 in iso-8859-7
+ u'\u03a4\u03b5\u03c4': u'Wed', # d4e5f4 in iso-8859-7
+ u'\u03a0\u03b5\u03bc': u'Thu', # d0e5ec in iso-8859-7
+ u'\u03a0\u03b1\u03c1': u'Fri', # d0e1f1 in iso-8859-7
+ u'\u03a3\u03b1\u03b2': u'Sat', # d3e1e2 in iso-8859-7
+ }
+
+_greek_date_format_re = \
+ re.compile(u'([^,]+),\s+(\d{2})\s+([^\s]+)\s+(\d{4})\s+(\d{2}):(\d{2}):(\d{2})\s+([^\s]+)')
+
+def _parse_date_greek(dateString):
+ '''Parse a string according to a Greek 8-bit date format.'''
+ m = _greek_date_format_re.match(dateString)
+ if not m: return
+ try:
+ wday = _greek_wdays[m.group(1)]
+ month = _greek_months[m.group(3)]
+ except:
+ return
+ rfc822date = '%(wday)s, %(day)s %(month)s %(year)s %(hour)s:%(minute)s:%(second)s %(zonediff)s' % \
+ {'wday': wday, 'day': m.group(2), 'month': month, 'year': m.group(4),\
+ 'hour': m.group(5), 'minute': m.group(6), 'second': m.group(7),\
+ 'zonediff': m.group(8)}
+ if _debug: sys.stderr.write('Greek date parsed as: %s\n' % rfc822date)
+ return _parse_date_rfc822(rfc822date)
+registerDateHandler(_parse_date_greek)
+
+# Unicode strings for Hungarian date strings
+_hungarian_months = \
+ { \
+ u'janu\u00e1r': u'01', # e1 in iso-8859-2
+ u'febru\u00e1ri': u'02', # e1 in iso-8859-2
+ u'm\u00e1rcius': u'03', # e1 in iso-8859-2
+ u'\u00e1prilis': u'04', # e1 in iso-8859-2
+ u'm\u00e1ujus': u'05', # e1 in iso-8859-2
+ u'j\u00fanius': u'06', # fa in iso-8859-2
+ u'j\u00falius': u'07', # fa in iso-8859-2
+ u'augusztus': u'08',
+ u'szeptember': u'09',
+ u'okt\u00f3ber': u'10', # f3 in iso-8859-2
+ u'november': u'11',
+ u'december': u'12',
+ }
+
+_hungarian_date_format_re = \
+ re.compile(u'(\d{4})-([^-]+)-(\d{,2})T(\d{,2}):(\d{2})((\+|-)(\d{,2}:\d{2}))')
+
+def _parse_date_hungarian(dateString):
+ '''Parse a string according to a Hungarian 8-bit date format.'''
+ m = _hungarian_date_format_re.match(dateString)
+ if not m: return
+ try:
+ month = _hungarian_months[m.group(2)]
+ day = m.group(3)
+ if len(day) == 1:
+ day = '0' + day
+ hour = m.group(4)
+ if len(hour) == 1:
+ hour = '0' + hour
+ except:
+ return
+ w3dtfdate = '%(year)s-%(month)s-%(day)sT%(hour)s:%(minute)s%(zonediff)s' % \
+ {'year': m.group(1), 'month': month, 'day': day,\
+ 'hour': hour, 'minute': m.group(5),\
+ 'zonediff': m.group(6)}
+ if _debug: sys.stderr.write('Hungarian date parsed as: %s\n' % w3dtfdate)
+ return _parse_date_w3dtf(w3dtfdate)
+registerDateHandler(_parse_date_hungarian)
+
+# W3DTF-style date parsing adapted from PyXML xml.utils.iso8601, written by
+# Drake and licensed under the Python license. Removed all range checking
+# for month, day, hour, minute, and second, since mktime will normalize
+# these later
+def _parse_date_w3dtf(dateString):
+ def __extract_date(m):
+ year = int(m.group('year'))
+ if year < 100:
+ year = 100 * int(time.gmtime()[0] / 100) + int(year)
+ if year < 1000:
+ return 0, 0, 0
+ julian = m.group('julian')
+ if julian:
+ julian = int(julian)
+ month = julian / 30 + 1
+ day = julian % 30 + 1
+ jday = None
+ while jday != julian:
+ t = time.mktime((year, month, day, 0, 0, 0, 0, 0, 0))
+ jday = time.gmtime(t)[-2]
+ diff = abs(jday - julian)
+ if jday > julian:
+ if diff < day:
+ day = day - diff
+ else:
+ month = month - 1
+ day = 31
+ elif jday < julian:
+ if day + diff < 28:
+ day = day + diff
+ else:
+ month = month + 1
+ return year, month, day
+ month = m.group('month')
+ day = 1
+ if month is None:
+ month = 1
+ else:
+ month = int(month)
+ day = m.group('day')
+ if day:
+ day = int(day)
+ else:
+ day = 1
+ return year, month, day
+
+ def __extract_time(m):
+ if not m:
+ return 0, 0, 0
+ hours = m.group('hours')
+ if not hours:
+ return 0, 0, 0
+ hours = int(hours)
+ minutes = int(m.group('minutes'))
+ seconds = m.group('seconds')
+ if seconds:
+ seconds = int(seconds)
+ else:
+ seconds = 0
+ return hours, minutes, seconds
+
+ def __extract_tzd(m):
+ '''Return the Time Zone Designator as an offset in seconds from UTC.'''
+ if not m:
+ return 0
+ tzd = m.group('tzd')
+ if not tzd:
+ return 0
+ if tzd == 'Z':
+ return 0
+ hours = int(m.group('tzdhours'))
+ minutes = m.group('tzdminutes')
+ if minutes:
+ minutes = int(minutes)
+ else:
+ minutes = 0
+ offset = (hours*60 + minutes) * 60
+ if tzd[0] == '+':
+ return -offset
+ return offset
+
+ __date_re = ('(?P<year>\d\d\d\d)'
+ '(?:(?P<dsep>-|)'
+ '(?:(?P<julian>\d\d\d)'
+ '|(?P<month>\d\d)(?:(?P=dsep)(?P<day>\d\d))?))?')
+ __tzd_re = '(?P<tzd>[-+](?P<tzdhours>\d\d)(?::?(?P<tzdminutes>\d\d))|Z)'
+ __tzd_rx = re.compile(__tzd_re)
+ __time_re = ('(?P<hours>\d\d)(?P<tsep>:|)(?P<minutes>\d\d)'
+ '(?:(?P=tsep)(?P<seconds>\d\d(?:[.,]\d+)?))?'
+ + __tzd_re)
+ __datetime_re = '%s(?:T%s)?' % (__date_re, __time_re)
+ __datetime_rx = re.compile(__datetime_re)
+ m = __datetime_rx.match(dateString)
+ if (m is None) or (m.group() != dateString): return
+ gmt = __extract_date(m) + __extract_time(m) + (0, 0, 0)
+ if gmt[0] == 0: return
+ return time.gmtime(time.mktime(gmt) + __extract_tzd(m) - time.timezone)
+registerDateHandler(_parse_date_w3dtf)
+
+def _parse_date_rfc822(dateString):
+ '''Parse an RFC822, RFC1123, RFC2822, or asctime-style date'''
+ data = dateString.split()
+ if data[0][-1] in (',', '.') or data[0].lower() in rfc822._daynames:
+ del data[0]
+ if len(data) == 4:
+ s = data[3]
+ i = s.find('+')
+ if i > 0:
+ data[3:] = [s[:i], s[i+1:]]
+ else:
+ data.append('')
+ dateString = " ".join(data)
+ if len(data) < 5:
+ dateString += ' 00:00:00 GMT'
+ tm = rfc822.parsedate_tz(dateString)
+ if tm:
+ return time.gmtime(rfc822.mktime_tz(tm))
+# rfc822.py defines several time zones, but we define some extra ones.
+# 'ET' is equivalent to 'EST', etc.
+_additional_timezones = {'AT': -400, 'ET': -500, 'CT': -600, 'MT': -700, 'PT': -800}
+rfc822._timezones.update(_additional_timezones)
+registerDateHandler(_parse_date_rfc822)
+
+def _parse_date(dateString):
+ '''Parses a variety of date formats into a 9-tuple in GMT'''
+ for handler in _date_handlers:
+ try:
+ date9tuple = handler(dateString)
+ if not date9tuple: continue
+ if len(date9tuple) != 9:
+ if _debug: sys.stderr.write('date handler function must return 9-tuple\n')
+ raise ValueError
+ map(int, date9tuple)
+ return date9tuple
+ except Exception, e:
+ if _debug: sys.stderr.write('%s raised %s\n' % (handler.__name__, repr(e)))
+ pass
+ return None
+
+def _getCharacterEncoding(http_headers, xml_data):
+ '''Get the character encoding of the XML document
+
+ http_headers is a dictionary
+ xml_data is a raw string (not Unicode)
+
+ This is so much trickier than it sounds, it's not even funny.
+ According to RFC 3023 ('XML Media Types'), if the HTTP Content-Type
+ is application/xml, application/*+xml,
+ application/xml-external-parsed-entity, or application/xml-dtd,
+ the encoding given in the charset parameter of the HTTP Content-Type
+ takes precedence over the encoding given in the XML prefix within the
+ document, and defaults to 'utf-8' if neither are specified. But, if
+ the HTTP Content-Type is text/xml, text/*+xml, or
+ text/xml-external-parsed-entity, the encoding given in the XML prefix
+ within the document is ALWAYS IGNORED and only the encoding given in
+ the charset parameter of the HTTP Content-Type header should be
+ respected, and it defaults to 'us-ascii' if not specified.
+
+ Furthermore, discussion on the atom-syntax mailing list with the
+ author of RFC 3023 leads me to the conclusion that any document
+ served with a Content-Type of text/* and no charset parameter
+ must be treated as us-ascii. (We now do this.) And also that it
+ must always be flagged as non-well-formed. (We now do this too.)
+
+ If Content-Type is unspecified (input was local file or non-HTTP source)
+ or unrecognized (server just got it totally wrong), then go by the
+ encoding given in the XML prefix of the document and default to
+ 'iso-8859-1' as per the HTTP specification (RFC 2616).
+
+ Then, assuming we didn't find a character encoding in the HTTP headers
+ (and the HTTP Content-type allowed us to look in the body), we need
+ to sniff the first few bytes of the XML data and try to determine
+ whether the encoding is ASCII-compatible. Section F of the XML
+ specification shows the way here:
+ http://www.w3.org/TR/REC-xml/#sec-guessing-no-ext-info
+
+ If the sniffed encoding is not ASCII-compatible, we need to make it
+ ASCII compatible so that we can sniff further into the XML declaration
+ to find the encoding attribute, which will tell us the true encoding.
+
+ Of course, none of this guarantees that we will be able to parse the
+ feed in the declared character encoding (assuming it was declared
+ correctly, which many are not). CJKCodecs and iconv_codec help a lot;
+ you should definitely install them if you can.
+ http://cjkpython.i18n.org/
+ '''
+
+ def _parseHTTPContentType(content_type):
+ '''takes HTTP Content-Type header and returns (content type, charset)
+
+ If no charset is specified, returns (content type, '')
+ If no content type is specified, returns ('', '')
+ Both return parameters are guaranteed to be lowercase strings
+ '''
+ content_type = content_type or ''
+ content_type, params = cgi.parse_header(content_type)
+ return content_type, params.get('charset', '').replace("'", '')
+
+ sniffed_xml_encoding = ''
+ xml_encoding = ''
+ true_encoding = ''
+ http_content_type, http_encoding = _parseHTTPContentType(http_headers.get('content-type'))
+ # Must sniff for non-ASCII-compatible character encodings before
+ # searching for XML declaration. This heuristic is defined in
+ # section F of the XML specification:
+ # http://www.w3.org/TR/REC-xml/#sec-guessing-no-ext-info
+ try:
+ if xml_data[:4] == '\x4c\x6f\xa7\x94':
+ # EBCDIC
+ xml_data = _ebcdic_to_ascii(xml_data)
+ elif xml_data[:4] == '\x00\x3c\x00\x3f':
+ # UTF-16BE
+ sniffed_xml_encoding = 'utf-16be'
+ xml_data = unicode(xml_data, 'utf-16be').encode('utf-8')
+ elif (len(xml_data) >= 4) and (xml_data[:2] == '\xfe\xff') and (xml_data[2:4] != '\x00\x00'):
+ # UTF-16BE with BOM
+ sniffed_xml_encoding = 'utf-16be'
+ xml_data = unicode(xml_data[2:], 'utf-16be').encode('utf-8')
+ elif xml_data[:4] == '\x3c\x00\x3f\x00':
+ # UTF-16LE
+ sniffed_xml_encoding = 'utf-16le'
+ xml_data = unicode(xml_data, 'utf-16le').encode('utf-8')
+ elif (len(xml_data) >= 4) and (xml_data[:2] == '\xff\xfe') and (xml_data[2:4] != '\x00\x00'):
+ # UTF-16LE with BOM
+ sniffed_xml_encoding = 'utf-16le'
+ xml_data = unicode(xml_data[2:], 'utf-16le').encode('utf-8')
+ elif xml_data[:4] == '\x00\x00\x00\x3c':
+ # UTF-32BE
+ sniffed_xml_encoding = 'utf-32be'
+ xml_data = unicode(xml_data, 'utf-32be').encode('utf-8')
+ elif xml_data[:4] == '\x3c\x00\x00\x00':
+ # UTF-32LE
+ sniffed_xml_encoding = 'utf-32le'
+ xml_data = unicode(xml_data, 'utf-32le').encode('utf-8')
+ elif xml_data[:4] == '\x00\x00\xfe\xff':
+ # UTF-32BE with BOM
+ sniffed_xml_encoding = 'utf-32be'
+ xml_data = unicode(xml_data[4:], 'utf-32be').encode('utf-8')
+ elif xml_data[:4] == '\xff\xfe\x00\x00':
+ # UTF-32LE with BOM
+ sniffed_xml_encoding = 'utf-32le'
+ xml_data = unicode(xml_data[4:], 'utf-32le').encode('utf-8')
+ elif xml_data[:3] == '\xef\xbb\xbf':
+ # UTF-8 with BOM
+ sniffed_xml_encoding = 'utf-8'
+ xml_data = unicode(xml_data[3:], 'utf-8').encode('utf-8')
+ else:
+ # ASCII-compatible
+ pass
+ xml_encoding_match = re.compile('^<\?.*encoding=[\'"](.*?)[\'"].*\?>').match(xml_data)
+ except:
+ xml_encoding_match = None
+ if xml_encoding_match:
+ xml_encoding = xml_encoding_match.groups()[0].lower()
+ if sniffed_xml_encoding and (xml_encoding in ('iso-10646-ucs-2', 'ucs-2', 'csunicode', 'iso-10646-ucs-4', 'ucs-4', 'csucs4', 'utf-16', 'utf-32', 'utf_16', 'utf_32', 'utf16', 'u16')):
+ xml_encoding = sniffed_xml_encoding
+ acceptable_content_type = 0
+ application_content_types = ('application/xml', 'application/xml-dtd', 'application/xml-external-parsed-entity')
+ text_content_types = ('text/xml', 'text/xml-external-parsed-entity')
+ if (http_content_type in application_content_types) or \
+ (http_content_type.startswith('application/') and http_content_type.endswith('+xml')):
+ acceptable_content_type = 1
+ true_encoding = http_encoding or xml_encoding or 'utf-8'
+ elif (http_content_type in text_content_types) or \
+ (http_content_type.startswith('text/')) and http_content_type.endswith('+xml'):
+ acceptable_content_type = 1
+ true_encoding = http_encoding or 'us-ascii'
+ elif http_content_type.startswith('text/'):
+ true_encoding = http_encoding or 'us-ascii'
+ elif http_headers and (not http_headers.has_key('content-type')):
+ true_encoding = xml_encoding or 'iso-8859-1'
+ else:
+ true_encoding = xml_encoding or 'utf-8'
+ return true_encoding, http_encoding, xml_encoding, sniffed_xml_encoding, acceptable_content_type
+
+def _toUTF8(data, encoding):
+ '''Changes an XML data stream on the fly to specify a new encoding
+
+ data is a raw sequence of bytes (not Unicode) that is presumed to be in %encoding already
+ encoding is a string recognized by encodings.aliases
+ '''
+ if _debug: sys.stderr.write('entering _toUTF8, trying encoding %s\n' % encoding)
+ # strip Byte Order Mark (if present)
+ if (len(data) >= 4) and (data[:2] == '\xfe\xff') and (data[2:4] != '\x00\x00'):
+ if _debug:
+ sys.stderr.write('stripping BOM\n')
+ if encoding != 'utf-16be':
+ sys.stderr.write('trying utf-16be instead\n')
+ encoding = 'utf-16be'
+ data = data[2:]
+ elif (len(data) >= 4) and (data[:2] == '\xff\xfe') and (data[2:4] != '\x00\x00'):
+ if _debug:
+ sys.stderr.write('stripping BOM\n')
+ if encoding != 'utf-16le':
+ sys.stderr.write('trying utf-16le instead\n')
+ encoding = 'utf-16le'
+ data = data[2:]
+ elif data[:3] == '\xef\xbb\xbf':
+ if _debug:
+ sys.stderr.write('stripping BOM\n')
+ if encoding != 'utf-8':
+ sys.stderr.write('trying utf-8 instead\n')
+ encoding = 'utf-8'
+ data = data[3:]
+ elif data[:4] == '\x00\x00\xfe\xff':
+ if _debug:
+ sys.stderr.write('stripping BOM\n')
+ if encoding != 'utf-32be':
+ sys.stderr.write('trying utf-32be instead\n')
+ encoding = 'utf-32be'
+ data = data[4:]
+ elif data[:4] == '\xff\xfe\x00\x00':
+ if _debug:
+ sys.stderr.write('stripping BOM\n')
+ if encoding != 'utf-32le':
+ sys.stderr.write('trying utf-32le instead\n')
+ encoding = 'utf-32le'
+ data = data[4:]
+ newdata = unicode(data, encoding)
+ if _debug: sys.stderr.write('successfully converted %s data to unicode\n' % encoding)
+ declmatch = re.compile('^<\?xml[^>]*?>')
+ newdecl = '''<?xml version='1.0' encoding='utf-8'?>'''
+ if declmatch.search(newdata):
+ newdata = declmatch.sub(newdecl, newdata)
+ else:
+ newdata = newdecl + u'\n' + newdata
+ return newdata.encode('utf-8')
+
+def _stripDoctype(data):
+ '''Strips DOCTYPE from XML document, returns (rss_version, stripped_data)
+
+ rss_version may be 'rss091n' or None
+ stripped_data is the same XML document, minus the DOCTYPE
+ '''
+ entity_pattern = re.compile(r'<!ENTITY([^>]*?)>', re.MULTILINE)
+ data = entity_pattern.sub('', data)
+ doctype_pattern = re.compile(r'<!DOCTYPE([^>]*?)>', re.MULTILINE)
+ doctype_results = doctype_pattern.findall(data)
+ doctype = doctype_results and doctype_results[0] or ''
+ if doctype.lower().count('netscape'):
+ version = 'rss091n'
+ else:
+ version = None
+ data = doctype_pattern.sub('', data)
+ return version, data
+
+def parse(url_file_stream_or_string, etag=None, modified=None, agent=None, referrer=None, handlers=[]):
+ '''Parse a feed from a URL, file, stream, or string'''
+ result = FeedParserDict()
+ result['feed'] = FeedParserDict()
+ result['entries'] = []
+ if _XML_AVAILABLE:
+ result['bozo'] = 0
+ if type(handlers) == types.InstanceType:
+ handlers = [handlers]
+ try:
+ f = _open_resource(url_file_stream_or_string, etag, modified, agent, referrer, handlers)
+ data = f.read()
+ except Exception, e:
+ result['bozo'] = 1
+ result['bozo_exception'] = e
+ data = ''
+ f = None
+
+ # if feed is gzip-compressed, decompress it
+ if f and data and hasattr(f, 'headers'):
+ if gzip and f.headers.get('content-encoding', '') == 'gzip':
+ try:
+ data = gzip.GzipFile(fileobj=_StringIO(data)).read()
+ except Exception, e:
+ # Some feeds claim to be gzipped but they're not, so
+ # we get garbage. Ideally, we should re-request the
+ # feed without the 'Accept-encoding: gzip' header,
+ # but we don't.
+ result['bozo'] = 1
+ result['bozo_exception'] = e
+ data = ''
+ elif zlib and f.headers.get('content-encoding', '') == 'deflate':
+ try:
+ data = zlib.decompress(data, -zlib.MAX_WBITS)
+ except Exception, e:
+ result['bozo'] = 1
+ result['bozo_exception'] = e
+ data = ''
+
+ # save HTTP headers
+ if hasattr(f, 'info'):
+ info = f.info()
+ result['etag'] = info.getheader('ETag')
+ last_modified = info.getheader('Last-Modified')
+ if last_modified:
+ result['modified'] = _parse_date(last_modified)
+ if hasattr(f, 'url'):
+ result['href'] = f.url
+ result['status'] = 200
+ if hasattr(f, 'status'):
+ result['status'] = f.status
+ if hasattr(f, 'headers'):
+ result['headers'] = f.headers.dict
+ if hasattr(f, 'close'):
+ f.close()
+
+ # there are four encodings to keep track of:
+ # - http_encoding is the encoding declared in the Content-Type HTTP header
+ # - xml_encoding is the encoding declared in the <?xml declaration
+ # - sniffed_encoding is the encoding sniffed from the first 4 bytes of the XML data
+ # - result['encoding'] is the actual encoding, as per RFC 3023 and a variety of other conflicting specifications
+ http_headers = result.get('headers', {})
+ result['encoding'], http_encoding, xml_encoding, sniffed_xml_encoding, acceptable_content_type = \
+ _getCharacterEncoding(http_headers, data)
+ if http_headers and (not acceptable_content_type):
+ if http_headers.has_key('content-type'):
+ bozo_message = '%s is not an XML media type' % http_headers['content-type']
+ else:
+ bozo_message = 'no Content-type specified'
+ result['bozo'] = 1
+ result['bozo_exception'] = NonXMLContentType(bozo_message)
+
+ result['version'], data = _stripDoctype(data)
+
+ baseuri = http_headers.get('content-location', result.get('href'))
+ baselang = http_headers.get('content-language', None)
+
+ # if server sent 304, we're done
+ if result.get('status', 0) == 304:
+ result['version'] = ''
+ result['debug_message'] = 'The feed has not changed since you last checked, ' + \
+ 'so the server sent no data. This is a feature, not a bug!'
+ return result
+
+ # if there was a problem downloading, we're done
+ if not data:
+ return result
+
+ # determine character encoding
+ use_strict_parser = 0
+ known_encoding = 0
+ tried_encodings = []
+ # try: HTTP encoding, declared XML encoding, encoding sniffed from BOM
+ for proposed_encoding in (result['encoding'], xml_encoding, sniffed_xml_encoding):
+ if not proposed_encoding: continue
+ if proposed_encoding in tried_encodings: continue
+ tried_encodings.append(proposed_encoding)
+ try:
+ data = _toUTF8(data, proposed_encoding)
+ known_encoding = use_strict_parser = 1
+ break
+ except:
+ pass
+ # if no luck and we have auto-detection library, try that
+ if (not known_encoding) and chardet:
+ try:
+ proposed_encoding = chardet.detect(data)['encoding']
+ if proposed_encoding and (proposed_encoding not in tried_encodings):
+ tried_encodings.append(proposed_encoding)
+ data = _toUTF8(data, proposed_encoding)
+ known_encoding = use_strict_parser = 1
+ except:
+ pass
+ # if still no luck and we haven't tried utf-8 yet, try that
+ if (not known_encoding) and ('utf-8' not in tried_encodings):
+ try:
+ proposed_encoding = 'utf-8'
+ tried_encodings.append(proposed_encoding)
+ data = _toUTF8(data, proposed_encoding)
+ known_encoding = use_strict_parser = 1
+ except:
+ pass
+ # if still no luck and we haven't tried windows-1252 yet, try that
+ if (not known_encoding) and ('windows-1252' not in tried_encodings):
+ try:
+ proposed_encoding = 'windows-1252'
+ tried_encodings.append(proposed_encoding)
+ data = _toUTF8(data, proposed_encoding)
+ known_encoding = use_strict_parser = 1
+ except:
+ pass
+ # if still no luck, give up
+ if not known_encoding:
+ result['bozo'] = 1
+ result['bozo_exception'] = CharacterEncodingUnknown( \
+ 'document encoding unknown, I tried ' + \
+ '%s, %s, utf-8, and windows-1252 but nothing worked' % \
+ (result['encoding'], xml_encoding))
+ result['encoding'] = ''
+ elif proposed_encoding != result['encoding']:
+ result['bozo'] = 1
+ result['bozo_exception'] = CharacterEncodingOverride( \
+ 'documented declared as %s, but parsed as %s' % \
+ (result['encoding'], proposed_encoding))
+ result['encoding'] = proposed_encoding
+
+ if not _XML_AVAILABLE:
+ use_strict_parser = 0
+ if use_strict_parser:
+ # initialize the SAX parser
+ feedparser = _StrictFeedParser(baseuri, baselang, 'utf-8')
+ saxparser = xml.sax.make_parser(PREFERRED_XML_PARSERS)
+ saxparser.setFeature(xml.sax.handler.feature_namespaces, 1)
+ saxparser.setContentHandler(feedparser)
+ saxparser.setErrorHandler(feedparser)
+ source = xml.sax.xmlreader.InputSource()
+ source.setByteStream(_StringIO(data))
+ if hasattr(saxparser, '_ns_stack'):
+ # work around bug in built-in SAX parser (doesn't recognize xml: namespace)
+ # PyXML doesn't have this problem, and it doesn't have _ns_stack either
+ saxparser._ns_stack.append({'http://www.w3.org/XML/1998/namespace':'xml'})
+ try:
+ saxparser.parse(source)
+ except Exception, e:
+ if _debug:
+ import traceback
+ traceback.print_stack()
+ traceback.print_exc()
+ sys.stderr.write('xml parsing failed\n')
+ result['bozo'] = 1
+ result['bozo_exception'] = feedparser.exc or e
+ use_strict_parser = 0
+ if not use_strict_parser:
+ feedparser = _LooseFeedParser(baseuri, baselang, known_encoding and 'utf-8' or '')
+ feedparser.feed(data)
+ result['feed'] = feedparser.feeddata
+ result['entries'] = feedparser.entries
+ result['version'] = result['version'] or feedparser.version
+ result['namespaces'] = feedparser.namespacesInUse
+ return result
+
+if __name__ == '__main__':
+ if not sys.argv[1:]:
+ print __doc__
+ sys.exit(0)
+ else:
+ urls = sys.argv[1:]
+ zopeCompatibilityHack()
+ from pprint import pprint
+ for url in urls:
+ print url
+ print
+ result = parse(url)
+ pprint(result)
+ print
+
+#REVISION HISTORY
+#1.0 - 9/27/2002 - MAP - fixed namespace processing on prefixed RSS 2.0 elements,
+# added Simon Fell's test suite
+#1.1 - 9/29/2002 - MAP - fixed infinite loop on incomplete CDATA sections
+#2.0 - 10/19/2002
+# JD - use inchannel to watch out for image and textinput elements which can
+# also contain title, link, and description elements
+# JD - check for isPermaLink='false' attribute on guid elements
+# JD - replaced openAnything with open_resource supporting ETag and
+# If-Modified-Since request headers
+# JD - parse now accepts etag, modified, agent, and referrer optional
+# arguments
+# JD - modified parse to return a dictionary instead of a tuple so that any
+# etag or modified information can be returned and cached by the caller
+#2.0.1 - 10/21/2002 - MAP - changed parse() so that if we don't get anything
+# because of etag/modified, return the old etag/modified to the caller to
+# indicate why nothing is being returned
+#2.0.2 - 10/21/2002 - JB - added the inchannel to the if statement, otherwise its
+# useless. Fixes the problem JD was addressing by adding it.
+#2.1 - 11/14/2002 - MAP - added gzip support
+#2.2 - 1/27/2003 - MAP - added attribute support, admin:generatorAgent.
+# start_admingeneratoragent is an example of how to handle elements with
+# only attributes, no content.
+#2.3 - 6/11/2003 - MAP - added USER_AGENT for default (if caller doesn't specify);
+# also, make sure we send the User-Agent even if urllib2 isn't available.
+# Match any variation of backend.userland.com/rss namespace.
+#2.3.1 - 6/12/2003 - MAP - if item has both link and guid, return both as-is.
+#2.4 - 7/9/2003 - MAP - added preliminary Pie/Atom/Echo support based on Sam Ruby's
+# snapshot of July 1 <http://www.intertwingly.net/blog/1506.html>; changed
+# project name
+#2.5 - 7/25/2003 - MAP - changed to Python license (all contributors agree);
+# removed unnecessary urllib code -- urllib2 should always be available anyway;
+# return actual url, status, and full HTTP headers (as result['url'],
+# result['status'], and result['headers']) if parsing a remote feed over HTTP --
+# this should pass all the HTTP tests at <http://diveintomark.org/tests/client/http/>;
+# added the latest namespace-of-the-week for RSS 2.0
+#2.5.1 - 7/26/2003 - RMK - clear opener.addheaders so we only send our custom
+# User-Agent (otherwise urllib2 sends two, which confuses some servers)
+#2.5.2 - 7/28/2003 - MAP - entity-decode inline xml properly; added support for
+# inline <xhtml:body> and <xhtml:div> as used in some RSS 2.0 feeds
+#2.5.3 - 8/6/2003 - TvdV - patch to track whether we're inside an image or
+# textInput, and also to return the character encoding (if specified)
+#2.6 - 1/1/2004 - MAP - dc:author support (MarekK); fixed bug tracking
+# nested divs within content (JohnD); fixed missing sys import (JohanS);
+# fixed regular expression to capture XML character encoding (Andrei);
+# added support for Atom 0.3-style links; fixed bug with textInput tracking;
+# added support for cloud (MartijnP); added support for multiple
+# category/dc:subject (MartijnP); normalize content model: 'description' gets
+# description (which can come from description, summary, or full content if no
+# description), 'content' gets dict of base/language/type/value (which can come
+# from content:encoded, xhtml:body, content, or fullitem);
+# fixed bug matching arbitrary Userland namespaces; added xml:base and xml:lang
+# tracking; fixed bug tracking unknown tags; fixed bug tracking content when
+# <content> element is not in default namespace (like Pocketsoap feed);
+# resolve relative URLs in link, guid, docs, url, comments, wfw:comment,
+# wfw:commentRSS; resolve relative URLs within embedded HTML markup in
+# description, xhtml:body, content, content:encoded, title, subtitle,
+# summary, info, tagline, and copyright; added support for pingback and
+# trackback namespaces
+#2.7 - 1/5/2004 - MAP - really added support for trackback and pingback
+# namespaces, as opposed to 2.6 when I said I did but didn't really;
+# sanitize HTML markup within some elements; added mxTidy support (if
+# installed) to tidy HTML markup within some elements; fixed indentation
+# bug in _parse_date (FazalM); use socket.setdefaulttimeout if available
+# (FazalM); universal date parsing and normalization (FazalM): 'created', modified',
+# 'issued' are parsed into 9-tuple date format and stored in 'created_parsed',
+# 'modified_parsed', and 'issued_parsed'; 'date' is duplicated in 'modified'
+# and vice-versa; 'date_parsed' is duplicated in 'modified_parsed' and vice-versa
+#2.7.1 - 1/9/2004 - MAP - fixed bug handling " and '. fixed memory
+# leak not closing url opener (JohnD); added dc:publisher support (MarekK);
+# added admin:errorReportsTo support (MarekK); Python 2.1 dict support (MarekK)
+#2.7.4 - 1/14/2004 - MAP - added workaround for improperly formed <br/> tags in
+# encoded HTML (skadz); fixed unicode handling in normalize_attrs (ChrisL);
+# fixed relative URI processing for guid (skadz); added ICBM support; added
+# base64 support
+#2.7.5 - 1/15/2004 - MAP - added workaround for malformed DOCTYPE (seen on many
+# blogspot.com sites); added _debug variable
+#2.7.6 - 1/16/2004 - MAP - fixed bug with StringIO importing
+#3.0b3 - 1/23/2004 - MAP - parse entire feed with real XML parser (if available);
+# added several new supported namespaces; fixed bug tracking naked markup in
+# description; added support for enclosure; added support for source; re-added
+# support for cloud which got dropped somehow; added support for expirationDate
+#3.0b4 - 1/26/2004 - MAP - fixed xml:lang inheritance; fixed multiple bugs tracking
+# xml:base URI, one for documents that don't define one explicitly and one for
+# documents that define an outer and an inner xml:base that goes out of scope
+# before the end of the document
+#3.0b5 - 1/26/2004 - MAP - fixed bug parsing multiple links at feed level
+#3.0b6 - 1/27/2004 - MAP - added feed type and version detection, result['version']
+# will be one of SUPPORTED_VERSIONS.keys() or empty string if unrecognized;
+# added support for creativeCommons:license and cc:license; added support for
+# full Atom content model in title, tagline, info, copyright, summary; fixed bug
+# with gzip encoding (not always telling server we support it when we do)
+#3.0b7 - 1/28/2004 - MAP - support Atom-style author element in author_detail
+# (dictionary of 'name', 'url', 'email'); map author to author_detail if author
+# contains name + email address
+#3.0b8 - 1/28/2004 - MAP - added support for contributor
+#3.0b9 - 1/29/2004 - MAP - fixed check for presence of dict function; added
+# support for summary
+#3.0b10 - 1/31/2004 - MAP - incorporated ISO-8601 date parsing routines from
+# xml.util.iso8601
+#3.0b11 - 2/2/2004 - MAP - added 'rights' to list of elements that can contain
+# dangerous markup; fiddled with decodeEntities (not right); liberalized
+# date parsing even further
+#3.0b12 - 2/6/2004 - MAP - fiddled with decodeEntities (still not right);
+# added support to Atom 0.2 subtitle; added support for Atom content model
+# in copyright; better sanitizing of dangerous HTML elements with end tags
+# (script, frameset)
+#3.0b13 - 2/8/2004 - MAP - better handling of empty HTML tags (br, hr, img,
+# etc.) in embedded markup, in either HTML or XHTML form (<br>, <br/>, <br />)
+#3.0b14 - 2/8/2004 - MAP - fixed CDATA handling in non-wellformed feeds under
+# Python 2.1
+#3.0b15 - 2/11/2004 - MAP - fixed bug resolving relative links in wfw:commentRSS;
+# fixed bug capturing author and contributor URL; fixed bug resolving relative
+# links in author and contributor URL; fixed bug resolvin relative links in
+# generator URL; added support for recognizing RSS 1.0; passed Simon Fell's
+# namespace tests, and included them permanently in the test suite with his
+# permission; fixed namespace handling under Python 2.1
+#3.0b16 - 2/12/2004 - MAP - fixed support for RSS 0.90 (broken in b15)
+#3.0b17 - 2/13/2004 - MAP - determine character encoding as per RFC 3023
+#3.0b18 - 2/17/2004 - MAP - always map description to summary_detail (Andrei);
+# use libxml2 (if available)
+#3.0b19 - 3/15/2004 - MAP - fixed bug exploding author information when author
+# name was in parentheses; removed ultra-problematic mxTidy support; patch to
+# workaround crash in PyXML/expat when encountering invalid entities
+# (MarkMoraes); support for textinput/textInput
+#3.0b20 - 4/7/2004 - MAP - added CDF support
+#3.0b21 - 4/14/2004 - MAP - added Hot RSS support
+#3.0b22 - 4/19/2004 - MAP - changed 'channel' to 'feed', 'item' to 'entries' in
+# results dict; changed results dict to allow getting values with results.key
+# as well as results[key]; work around embedded illformed HTML with half
+# a DOCTYPE; work around malformed Content-Type header; if character encoding
+# is wrong, try several common ones before falling back to regexes (if this
+# works, bozo_exception is set to CharacterEncodingOverride); fixed character
+# encoding issues in BaseHTMLProcessor by tracking encoding and converting
+# from Unicode to raw strings before feeding data to sgmllib.SGMLParser;
+# convert each value in results to Unicode (if possible), even if using
+# regex-based parsing
+#3.0b23 - 4/21/2004 - MAP - fixed UnicodeDecodeError for feeds that contain
+# high-bit characters in attributes in embedded HTML in description (thanks
+# Thijs van de Vossen); moved guid, date, and date_parsed to mapped keys in
+# FeedParserDict; tweaked FeedParserDict.has_key to return True if asking
+# about a mapped key
+#3.0fc1 - 4/23/2004 - MAP - made results.entries[0].links[0] and
+# results.entries[0].enclosures[0] into FeedParserDict; fixed typo that could
+# cause the same encoding to be tried twice (even if it failed the first time);
+# fixed DOCTYPE stripping when DOCTYPE contained entity declarations;
+# better textinput and image tracking in illformed RSS 1.0 feeds
+#3.0fc2 - 5/10/2004 - MAP - added and passed Sam's amp tests; added and passed
+# my blink tag tests
+#3.0fc3 - 6/18/2004 - MAP - fixed bug in _changeEncodingDeclaration that
+# failed to parse utf-16 encoded feeds; made source into a FeedParserDict;
+# duplicate admin:generatorAgent/@rdf:resource in generator_detail.url;
+# added support for image; refactored parse() fallback logic to try other
+# encodings if SAX parsing fails (previously it would only try other encodings
+# if re-encoding failed); remove unichr madness in normalize_attrs now that
+# we're properly tracking encoding in and out of BaseHTMLProcessor; set
+# feed.language from root-level xml:lang; set entry.id from rdf:about;
+# send Accept header
+#3.0 - 6/21/2004 - MAP - don't try iso-8859-1 (can't distinguish between
+# iso-8859-1 and windows-1252 anyway, and most incorrectly marked feeds are
+# windows-1252); fixed regression that could cause the same encoding to be
+# tried twice (even if it failed the first time)
+#3.0.1 - 6/22/2004 - MAP - default to us-ascii for all text/* content types;
+# recover from malformed content-type header parameter with no equals sign
+# ('text/xml; charset:iso-8859-1')
+#3.1 - 6/28/2004 - MAP - added and passed tests for converting HTML entities
+# to Unicode equivalents in illformed feeds (aaronsw); added and
+# passed tests for converting character entities to Unicode equivalents
+# in illformed feeds (aaronsw); test for valid parsers when setting
+# XML_AVAILABLE; make version and encoding available when server returns
+# a 304; add handlers parameter to pass arbitrary urllib2 handlers (like
+# digest auth or proxy support); add code to parse username/password
+# out of url and send as basic authentication; expose downloading-related
+# exceptions in bozo_exception (aaronsw); added __contains__ method to
+# FeedParserDict (aaronsw); added publisher_detail (aaronsw)
+#3.2 - 7/3/2004 - MAP - use cjkcodecs and iconv_codec if available; always
+# convert feed to UTF-8 before passing to XML parser; completely revamped
+# logic for determining character encoding and attempting XML parsing
+# (much faster); increased default timeout to 20 seconds; test for presence
+# of Location header on redirects; added tests for many alternate character
+# encodings; support various EBCDIC encodings; support UTF-16BE and
+# UTF16-LE with or without a BOM; support UTF-8 with a BOM; support
+# UTF-32BE and UTF-32LE with or without a BOM; fixed crashing bug if no
+# XML parsers are available; added support for 'Content-encoding: deflate';
+# send blank 'Accept-encoding: ' header if neither gzip nor zlib modules
+# are available
+#3.3 - 7/15/2004 - MAP - optimize EBCDIC to ASCII conversion; fix obscure
+# problem tracking xml:base and xml:lang if element declares it, child
+# doesn't, first grandchild redeclares it, and second grandchild doesn't;
+# refactored date parsing; defined public registerDateHandler so callers
+# can add support for additional date formats at runtime; added support
+# for OnBlog, Nate, MSSQL, Greek, and Hungarian dates (ytrewq1); added
+# zopeCompatibilityHack() which turns FeedParserDict into a regular
+# dictionary, required for Zope compatibility, and also makes command-
+# line debugging easier because pprint module formats real dictionaries
+# better than dictionary-like objects; added NonXMLContentType exception,
+# which is stored in bozo_exception when a feed is served with a non-XML
+# media type such as 'text/plain'; respect Content-Language as default
+# language if not xml:lang is present; cloud dict is now FeedParserDict;
+# generator dict is now FeedParserDict; better tracking of xml:lang,
+# including support for xml:lang='' to unset the current language;
+# recognize RSS 1.0 feeds even when RSS 1.0 namespace is not the default
+# namespace; don't overwrite final status on redirects (scenarios:
+# redirecting to a URL that returns 304, redirecting to a URL that
+# redirects to another URL with a different type of redirect); add
+# support for HTTP 303 redirects
+#4.0 - MAP - support for relative URIs in xml:base attribute; fixed
+# encoding issue with mxTidy (phopkins); preliminary support for RFC 3229;
+# support for Atom 1.0; support for iTunes extensions; new 'tags' for
+# categories/keywords/etc. as array of dict
+# {'term': term, 'scheme': scheme, 'label': label} to match Atom 1.0
+# terminology; parse RFC 822-style dates with no time; lots of other
+# bug fixes
+#4.1 - MAP - removed socket timeout; added support for chardet library
projects / feedingit / commitdiff