Hello community,
here is the log from the commit of package python-mechanize for
openSUSE:Factory checked in at 2019-09-13 14:58:41
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Comparing /work/SRC/openSUSE:Factory/python-mechanize (Old)
and /work/SRC/openSUSE:Factory/.python-mechanize.new.7948 (New)
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Package is "python-mechanize"
Fri Sep 13 14:58:41 2019 rev:23 rq:730131 version:0.4.3
Changes:
--------
--- /work/SRC/openSUSE:Factory/python-mechanize/python-mechanize.changes
2019-05-20 13:17:59.783927068 +0200
+++
/work/SRC/openSUSE:Factory/.python-mechanize.new.7948/python-mechanize.changes
2019-09-13 14:58:42.757278238 +0200
@@ -1,0 +2,9 @@
+Wed Sep 11 12:36:30 UTC 2019 - Tomáš Chvátal <[email protected]>
+
+- Update to 0.4.3:
+ * When filling forms with unicode strings automatically encode them into
+ the correct encoding fr the HTML page being viewed
+ * Guess content type when uploading files if not specified
+ * py3 compat - Have the version of simple cookies be 0 rather than None
+
+-------------------------------------------------------------------
Old:
----
mechanize-0.4.2.tar.gz
New:
----
mechanize-0.4.3.tar.gz
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Other differences:
------------------
++++++ python-mechanize.spec ++++++
--- /var/tmp/diff_new_pack.4Rsv6v/_old 2019-09-13 14:58:43.141278254 +0200
+++ /var/tmp/diff_new_pack.4Rsv6v/_new 2019-09-13 14:58:43.141278254 +0200
@@ -19,17 +19,16 @@
%define modname mechanize
%{?!python_module:%define python_module() python-%{**} python3-%{**}}
Name: python-mechanize
-Version: 0.4.2
+Version: 0.4.3
Release: 0
Summary: Stateful programmatic web browsing
License: (BSD-3-Clause OR ZPL-2.1) AND BSD-3-Clause
Group: Development/Languages/Python
URL: https://github.com/python-mechanize/mechanize
Source:
https://files.pythonhosted.org/packages/source/m/mechanize/%{modname}-%{version}.tar.gz
+BuildRequires: %{python_module Twisted}
BuildRequires: %{python_module html5lib}
BuildRequires: %{python_module setuptools}
-# For testing
-BuildRequires: %{python_module Twisted}
BuildRequires: %{python_module zope.interface}
BuildRequires: fdupes
BuildRequires: python
++++++ mechanize-0.4.2.tar.gz -> mechanize-0.4.3.tar.gz ++++++
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/mechanize-0.4.2/ChangeLog
new/mechanize-0.4.3/ChangeLog
--- old/mechanize-0.4.2/ChangeLog 1970-01-01 01:00:00.000000000 +0100
+++ new/mechanize-0.4.3/ChangeLog 2019-08-18 10:06:45.000000000 +0200
@@ -0,0 +1,639 @@
+This isn't really in proper GNU ChangeLog format, it just happens to
+look that way.
+
+2019-08-18 Kovid Goyal
+ * 0.4.3 release
+ * When filling forms with unicode strings automatically encode them into
+ the correct encoding fr the HTML page being viewed
+ * Guess content type when uploading files if not specified
+ * py3 compat - Have the version of simple cookies be 0 rather than None
+
+2019-04-12 Kovid Goyal
+ * 0.4.2 release
+ * A couple of python 3 specific fixes for proxy authorization and
+ * adding controls to forms
+
+
+2019-03-16 Kovid Goyal
+ * 0.4.1 release
+ * A couple of python 3 specific fixes for servers with missing
robots.txt
+ files and also errors when using basic/digest auth
+
+
+2019-01-16 Kovid Goyal
+ * 0.4.0 release
+ * Python 3 compatibility
+ * Add a finalize_request_headers callback to Browser to allow users full
+ control of what headers are sent with every request
+ * Preserve header ordering when making HTTP requests
+
+2018-09-11 Kovid Goyal
+ * 0.3.7 release
+ * Fix processing of http-equiv meta tags incorrectly lower casing the
content
+ * Fix error when a textbox contained within a form contains unicode
characters
+
+2017-10-13 Kovid Goyal
+ * 0.3.6 release.
+ * Use html5-parser for parsing HTML, when available instead of html5lib
+ for a big performance boost.
+ * Fix error when trying to submit forms with non-ascii values on systems
+ where the default encoding is ascii.
+ * Fix errors on python environments with broken threading
+
+2017-06-24 Kovid Goyal
+ * 0.3.5 release.
+ * Fix error when trying to open pages that contain HTML entities that
+ decode to unicode characters in their <head> sections
+
+2017-05-05 Kovid Goyal
+ * 0.3.3 release.
+ * Add get() and __getitem__ methods to the response object for
conveninent access to response headers
+
+2017-04-29 Kovid Goyal
+ * 0.3.2 release.
+ * Allow overriding of Host headers via addheaders
+ * Fix using unicode strings in addheaders and trying to send data with
a request failing
+
+2017-03-17 Kovid Goyal
+ * 0.3.1 release.
+ * Allow easily selecting forms based on HTML attributes of the <form>
tag
+ * Allow specifying the HTTP method when creating requests
+ * Convenience API to set headers
+ * Convenience API for dealing with cookies
+ * Create full documentation at:
https://mechanize.readthedocs.io/en/latest/
+
+2017-03-15 Kovid Goyal
+ * 0.3.0 release.
+ * Support HTML 5 (all html is now parsed using html5lib)
+ * Implement cloning of browser instances via Browser.__copy__()
+ * Make gzip content-encoding non-experimental. Always handle it if sent
by the server, regardless of set_handle_gzip().
+ * mechanize now requires python >= 2.7.0
+ * When processing cookies that have a blank (unset) path, assume the
path
+ is /. Mimics modern browser behavior.
+ * Support PyPy (added to continuous integration testing)
+ * Make the global urlopen/urlretrieve methods threadsafe
+ * Add support for user supplied CA certificates
+ * Fix gzip not being requested on HTTPS connections
+ * Normalize the case of HTTP headers in requests
+ * Fix proxy authentication for https connections not working
+ * Size of codebase reduced by 10,000 lines of code (40%)
+
+ * Backward incompatibility: The factory keyword argument to Browser is
no longer allowed
+ * Backward incompatibility: Browser.forms() and Browser.links() return
unicode strings instead of byte strings
+ * Backward incompatibility: When searching for a form control if more
than one control matches, an AmbiguityError is always raised
+ * Backward incompatibility: There is no longer a mechanize.ParseError
and mechanize.ParseResponse
+ class. Parsing now uses the HTML 5 algorithm, which is designed to
not fail on malformed markup.
+ * Backward incompatibility: For links that do not have any text the text
+ attribute is now always an empty string instead of None or an empty
string.
+ * Backward incompatibility: Remove support for the <isindex> HTML tag
which was deprecated in HTML 4 and removed in HTML 5
+
+2011-03-31 John J Lee <[email protected]>
+ * 0.2.5 release.
+ * This is essentially a no-changes release to fix easy_install
+ breakage caused by a SourceForge issue
+ * Sourceforge is returning invalid HTTP responses, make download
+ links point to PyPI instead
+ * Include cookietest.cgi in source distribution
+ * Note new IETF cookie standardisation effort
+
+2010-10-28 John J Lee <[email protected]>
+ * 0.2.4 release.
+ * Fix IndexError on empty Content-type header value. (GH-18)
+ * Fall back to another encoding if an unknown one is declared.
+ Fixes traceback on unknown encoding in Content-type header.
+ (GH-30)
+
+2010-10-16 John J Lee <[email protected]>
+ * 0.2.3 release.
+ * Fix str(ParseError()) traceback. (GH-25)
+ * Add equality methods to mechanize.Cookie . (GH-29)
+
+2010-07-17 John J Lee <[email protected]>
+ * 0.2.2 release.
+ * Officially support Python 2.7 (no changes were required)
+ * Fix TypeError on .open()ing ftp: URL (only affects Python 2.4
+ and 2.5)
+ * Don't include HTTPSHandler in __all__ if it's not available
+
+2010-05-16 John J Lee <[email protected]>
+ * 0.2.1 release.
+ * API change: Change argument order of
+ HTTPRedirectHandler.redirect_request() to match urllib2.
+ * Fix failure to use bundled BeautifulSoup for forms. (GH-15)
+ * Fix default cookie path where request path has query containing
+ / character. (http://bugs.python.org/issue3704)
+ * Fix failure to raise on click for nonexistent label. (GH-16)
+ * Documentation fixes.
+
+2010-04-22 John J Lee <[email protected]>
+ * 0.2.0 release.
+ * Behaviour change: merged upstream urllib2 change (allegedly a
+ "bug fix") to return a response for all 2** HTTP responses (e.g.
+ 206 Partial Content). Previously, only 200 caused a response
+ object to be returned. All other HTTP response codes resulted
+ in a response object being raised as an exception.
+ * Behaviour change: Use of mechanize classes with `urllib2` (and
+ vice-versa) is no longer supported. However, existing classes
+ implementing the urllib2 Handler interface are likely to work
+ unchanged with mechanize. Removed RequestUpgradeProcessor,
+ ResponseUpgradeProcessor, SeekableProcessor.
+ * ClientForm has been merged into mechanize. This means that
+ mechanize has no dependencies other than Python itself. The
+ ClientForm API is still available -- to switch from ClientForm to
+ mechanize, just s/ClientForm/mechanize in your source code, and
+ ensure any use of the module logging logger named "ClientForm" is
+ updated to use the new logger name "mechanize.forms". I probably
+ won't do further standalone releases of ClientForm.
+ * Stop monkey-patching Python stdlib.
+ * Merge fixes from urllib2 trunk
+ * Close file objects on .read() failure in .retrieve()
+ * Fix a python 2.4 bug due to buggy urllib.splithost
+ * Fix Python 2.4 syntax error in _firefox3cookiejar
+ * Fix __init__.py typo that hid mechanize.seek_wrapped_response and
+ mechanize.str2time. Fixes
+ http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=465206
+ * Fix an obvious bug with experimental firefox 3 cookiejar support.
+ It's still experimental and not properly tested.
+ * Change documentation to not require a .port attribute on request
+ objects, since that's unused.
+ * Doc fixes
+ * Added mechanize.urljoin (RFC 3986 compliant function for joining
+ a base URI with a URI reference)
+ * Merge of ClientForm (see above).
+ * Moved to git (from SVN) http://github.com/jjlee/mechanize
+ * Created an issue tracker http://github.com/jjlee/mechanize/issues
+ * Docs are now in markdown format (thanks John Gabriele).
+ * Website rearranged. The old website has been archived at
+ http://wwwsearch.sourceforge.net/old/ . The new website is
+ essentially just the mechanize pages, rearranged and cleaned up a
+ bit.
+ * Source code rearranged for easier merging with upstream urllib2
+ * Fully automated release process.
+ * New test runner. Single test suite; tests create their own HTTP
+ server fixtures (server fixtures are cached where possible for
+ speed).
+
+2009-02-07 John J Lee <[email protected]>
+ * 0.1.11 release.
+ * Fix quadratic performance in number of .read() calls (and add an
+ automated performance test).
+
+2008-12-03 John J Lee <[email protected]>
+ * 0.1.10 release.
+ * Add support for Python 2.6: Raise URLError on file: URL errors,
+ not IOError (port of upstream urllib2 fix). Add support for
+ Python 2.6's per-connection timeouts: Add timeout arguments to
+ urlopen(), Request constructor, .open(), and .open_novisit().
+ * Drop support for Python 2.3
+ * Add Content-length header to Request object (httplib bug that
+ prevented doing that was fixed in Python 2.4). There's no
+ change is what is actually sent over the wire here, just in what
+ headers get added to the Request object.
+ * Fix AttributeError on .retrieve() with a Request (as opposed to
+ URL string) argument
+ * Don't change CookieJar state in .make_cookies().
+ * Fix AttributeError in case where .make_cookies() or
+ .cookies_for_request() is called before other methods like
+ .extract_cookies() or .make_cookie_header()
+ * Fixes affecting version cookie-attribute
+ (http://bugs.python.org/issue3924).
+ * Silence module logging's "no handlers could be found for logger
+ mechanize" warning in a way that doesn't clobber attempts to set
+ log level sometimes
+ * Don't use private attribute of request in request upgrade
+ handler (what was I thinking??)
+ * Don't call setup() on import of setup.py
+ * Add new public function effective_request_host
+ * Add .get_policy() method to CookieJar
+ * Add method CookieJar.cookies_for_request()
+ * Fix documented interface required of requests and responses (and
+ add some tests for this!)
+ * Allow either .is_unverifiable() or .unverifiable on request
+ objects (preferring the former)
+ * Note that there's a new functional test for digest auth, which
+ fails when run against the sourceforge site (which is the
+ default). It looks like this reflects the fact that digest auth
+ has been fairly broken since it was introduced in urllib2. I
+ don't plan to fix this myself.
+
+2008-09-24 John J Lee <[email protected]>
+ * 0.1.9 release.
+ * Fix ImportError if sqlite3 not available
+ * Fix a couple of functional tests not to wait 5 seconds each
+
+2008-09-13 John J Lee <[email protected]>
+ * 0.1.8 release.
+ * Close sockets. This only affects Python 2.5 (and later) -
+ earlier versions of Python were unaffected. See
+ http://bugs.python.org/issue1627441
+ * Make title parsing follow Firefox behaviour wrt child
+ elements (previously the behaviour differed between Factory and
+ RobustFactory).
+ * Fix BeautifulSoup RobustLinksFactory (hence RobustFactory) link
+ text parsing for case of link text containing tags (Titus Brown)
+ * Fix issue where more tags after <title> caused default parser to
+ raise an exception
+ * Handle missing cookie max-age value. Previously, a warning was
+ emitted in this case.
+ * Fix thoroughly broken digest auth (still need functional
+ test!) (trebor74hr@...)
+ * Handle cookies containing embedded tabs in mozilla format files
+ * Remove an assertion about mozilla format cookies file
+ contents (raise LoadError instead)
+ * Fix MechanizeRobotFileParser.set_opener()
+ * Fix selection of global form using .select_form() (Titus Brown)
+ * Log skipped Refreshes
+ * Stop tests from clobbering files that happen to be lying around
+ in cwd (!)
+ * Use SO_REUSEADDR for local test server.
+ * Raise exception if local test server fails to start.
+ * Tests no longer (accidentally) depend on third-party coverage
+ module
+ * The usual docs and test fixes.
+ * Add convenience method Browser.open_local_file(filename)
+ * Add experimental support for Firefox 3 cookie jars
+ ("cookies.sqlite"). Requires Python 2.5
+ * Fix a _gzip.py NameError (gzip support is experimental)
+
+2007-05-31 John J Lee <[email protected]>
+ * 0.1.7b release.
+ * Sub-requests should not usually be visiting, so make it so. In
+ fact the visible behaviour wasn't really broken here, since
+ .back() skips over None responses (which is odd in itself, but
+ won't be changed until after stable release is branched).
+ However, this patch does change visible behaviour in that it
+ creates new Request objects for sub-requests (e.g. basic auth
+ retries) where previously we just mutated the existing Request
+ object.
+ * Changes to sort out abuse of by SeekableProcessor and
+ ResponseUpgradeProcessor (latter shouldn't have been public in
+ the first place) and resulting confusing / unclear / broken
+ behaviour. Deprecate SeekableProcessor and
+ ResponseUpgradeProcessor. Add SeekableResponseOpener. Remove
+ SeekableProcessor and ResponseUpgradeProcessor from Browser.
+ Move UserAgentBase.add_referer_header() to Browser (it was on by
+ default, breaking UserAgent, and should never really have been
+ there).
+ * Fix HTTP proxy support: r29110 meant that Request.get_selector()
+ didn't take into account the change to .__r_host
+ (Thanks tgates@...).
+ * Redirected robots.txt fetch no longer results in another
+ attempted robots.txt fetch to check the redirection is allowed!
+ * Fix exception raised by RFC 3986 implementation with
+ urljoin(base, '/..')
+ * Fix two multiple-response-wrapping bugs.
+ * Add missing import in tests (caused failure on Windows).
+ * Set svn:eol-style to native for all text files in SVN.
+ * Add some tests for upgrade_response().
+ * Add a functional test for 302 + 404 case.
+ * Add an -l option to run the functional tests against a local
+ twisted.web-based server (you need Twisted installed for this
+ to work). This is much faster than running against
+ wwwsearch.sourceforge.net
+ * Add -u switch to skip unittests (and only run the doctests).
+
+2007-01-07 John J Lee <[email protected]>
+
+ * 0.1.6b release
+ * Add mechanize.ParseError class, document it as part of the
+ mechanize.Factory interface, and raise it from all Factory
+ implementations. This is backwards-compatible, since the new
+ exception derives from the old exceptions.
+ * Bug fix: Truncation when there is no full .read() before
+ navigating to the next page, and an old response is read after
+ navigation. This happened e.g. with r = br.open();
+ r.readline(); br.open(url); r.read(); br.back() .
+ * Bug fix: when .back() caused a reload, it was returning the old
+ response, not the .reload()ed one.
+ * Bug fix: .back() was not returning a copy of the response, which
+ presumably would cause seek position problems.
+ * Bug fix: base tag without href attribute would override document
+ URL with a None value, causing a crash (thanks Nathan Eror).
+ * Fix .set_response() to close current response first.
+ * Fix non-idempotent behaviour of Factory.forms() / .links() .
+ Previously, if for example you got a ParseError during execution
+ of .forms(), you could call it again and have it not raise an
+ exception, because it started out where it left off!
+ * Add a missing copy.copy() to RobustFactory .
+ * Fix redirection to 'URIs' that contain characters that are not
+ allowed in URIs (thanks Riko Wichmann). Also, Request
+ constructor now logs a module logging warning about any such bad
+ URIs.
+ * Add .global_form() method to Browser to support form controls
+ whose HTML elements are not descendants of any FORM element.
+ * Add a new method .visit_response() . This creates a new history
+ entry from a response object, rather than just changing the
+ current visited response. This is useful e.g. when you want to
+ use Browser features in a handler.
+ * Misc minor bug fixes.
+
+2006-10-25 John J Lee <[email protected]>
+
+ * 0.1.5b release: Update setuptools dependencies to depend on
+ ClientForm>=0.2.5 (for an important bug fix affecting fragments
+ in URLs). There are no other changes in this release -- this
+ release was done purely so that people upgrading to the latest
+ version of mechanize will get the latest ClientForm too.
+
+2006-10-14 John J Lee <[email protected]>
+ * 0.1.4b release: (skipped a version deliberately for obscure
+ reasons)
+ * Improved auth & proxies support.
+ * Follow RFC 3986.
+ * Add a .set_cookie() method to Browser .
+ * Add Browser.open_novisit() and Request.visit to allow fetching
+ files without affecting Browser state.
+ * UserAgent and Browser are now subclasses of UserAgentBase.
+ UserAgent's only role in life above what UserAgentBase does is
+ to provide the .set_seekable_responses() method (it lives there
+ because Browser depends on seekable responses, because that's
+ how browser history is implemented).
+ * Bundle BeautifulSoup 2.1.1. No more dependency pain! Note that
+ BeautifulSoup is, and always was, optional, and that mechanize
+ will eventually switch to BeautifulSoup version 3, at which
+ point it may well stop bundling BeautifulSoup. Note also that
+ the module is only used internally, and is not available as a
+ public attribute of the package. If you dare, you can import it
+ ("from mechanize import _beautifulsoup"), but beware that it
+ will go away later, and that the API of BeautifulSoup will
+ change when the upgrade to 3 happens. Also, BeautifulSoup
+ support (mainly RobustFactory) is still a little experimental
+ and buggy.
+ * Fix HTTP-EQUIV with no content attribute case (thanks Pratik
+ Dam).
+ * Fix bug with quoted META Refresh URL (thanks Nilton Volpato).
+ * Fix crash with </base> tag (yajdbgr02@...).
+ * Somebody found a server that (incorrectly) depends on HTTP
+ header case, so follow the Title-Case convention. Note that the
+ Request headers interface(s), which were (somewhat oddly -- this
+ is an inheritance from urllib2 that should really be fixed in a
+ better way than it is currently) always case-sensitive still
+ are; the only thing that changed is what actually eventually
+ gets sent over the wire.
+ * Use mechanize (not urllib) to open robots.txt. Don't consult
+ RobotFileParser instance about non-HTTP URLs.
+ * Fix OpenerDirector.retrieve(), which was very broken (thanks
+ Duncan Booth).
+ * Crash in a much more obvious way if trying to use OpenerDirector
+ after .close() .
+ * .reload() on .back() if necessary (necessary iff response was
+ not fully .read() on first .open()ing ) * Strip fragments before
+ retrieving URLs (fixed Request.get_selector() to strip fragment)
+ * Fix catching HTTPError subclasses while still preserving all
+ their response behaviour
+ * Correct over-enthusiastic documented guarantees of
+ closeable_response .
+ * Fix assumption that httplib.HTTPMessage treats dict-style
+ __setitem__ as append rather than set (where on earth did I get
+ that from?).
+ * Expose History in mechanize/__init__.py (though interface is
+ still experimental).
+ * Lots of other "internals" bugs fixed (thanks to reports /
+ patches from Benji York especially, also Titus Brown, Duncan
+ Booth, and me ;-), where I'm not 100% sure exactly when they
+ were introduced, so not listing them here in detail.
+ * Numerous other minor fixes.
+ * Some code cleanup.
+
+2006-05-21 John J Lee <[email protected]>
+ * 0.1.2b release:
+ * mechanize now exports the whole urllib2 interface.
+ * Pull in bugfixed auth/proxy support code from Python 2.5.
+ * Bugfix: strip leading and trailing whitespace from link URLs
+ * Fix .any_response() / .any_request() methods to have ordering.
+ consistent with rest of handlers rather than coming before all
+ of them.
+ * Tell cookie-handling code about new TLDs.
+ * Remove Browser.set_seekable_responses() (they always are
+ anyway).
+ * Show in web page examples how to munge responses and how to do
+ proxy/auth.
+ * Rename 0.1.* changes document 0.1.0-changes.txt -->
+ 0.1-changes.txt.
+ * In 0.1 changes document, note change of logger name from
+ "ClientCookie" to "mechanize"
+ * Add something about response objects to changes document
+ * Improve Browser.__str__
+ * Accept regexp strings as well as regexp objects when finding
+ links.
+ * Add crappy gzip transfer encoding support. This is off by
+ default and warns if you turn it on (hopefully will get better
+ later :-).
+ * A bit of internal cleanup following merge with pullparser /
+ ClientCookie.
+
+2006-05-06 John J Lee <[email protected]>
+ * 0.1.1a release:
+ * Merge ClientCookie and pullparser with mechanize.
+ * Response object fixes.
+ * Remove accidental dependency on BeautifulSoup introduced in
+ 0.1.0a (the BeautifulSoup support is still here, but
+ BeautifulSoup is not required to use mechanize).
+
+2006-05-03 John J Lee <[email protected]>
+ * 0.1.0a release:
+ * Stop trying to record precise dates in changelog, since that's
+ silly ;-)
+ * A fair number of interface changes: see 0.1.0-changes.txt.
+ * Depend on recent ClientCookie with copy.copy()able response
+ objects.
+ * Don't do broken XHTML handling by default (need to review code
+ before switching this back on, e.g. should use a real XML parser
+ for first-try at parsing). To get the old behaviour, pass
+ i_want_broken_xhtml_support=True to mechanize.DefaultFactory /
+ .RobustFactory constructor.
+ * Numerous small bug fixes.
+ * Documentation & setup.py fixes.
+ * Don't use cookielib, to avoid having to work around Python 2.4
+ RFC 2109 bug, and to avoid my braindead thread synchronisation
+ code in cookielib :-((((( (I haven't encountered specific
+ breakage due to latter, but since it's braindead I may as well
+ avoid it).
+
+2005-11-30 John J Lee <[email protected]>
+ * Fixed setuptools support.
+ * Release 0.0.11a.
+
+2005-11-19 John J Lee <[email protected]>
+ * Release 0.0.10a.
+
+2005-11-17 John J Lee <[email protected]>
+ * Fix set_handle_referer.
+
+2005-11-12 John J Lee <[email protected]>
+ * Fix history (Gary Poster).
+ * Close responses on reload (Gary Poster).
+ * Don't depend on SSL support (Gary Poster).
+
+2005-10-31 John J Lee <[email protected]>
+ * Add setuptools support.
+
+2005-10-30 John J Lee <[email protected]>
+ * Don't mask AttributeError exception messages from ClientForm.
+ * Document intent of .links() vs. .get_links_iter(); Rename
+ LinksFactory method.
+ * Remove pullparser import dependency.
+ * Remove Browser.urltags (now an argument to LinksFactory).
+ * Document Browser constructor as taking keyword args only (and
+ change positional arg spec).
+ * Cleanup of lazy parsing (may fix bugs, not sure...).
+
+2005-10-28 John J Lee <[email protected]>
+ * Support ClientForm backwards_compat switch.
+
+2005-08-28 John J Lee <[email protected]>
+ * Apply optimisation patch (Stephan Richter).
+
+2005-08-15 John J Lee <[email protected]>
+ * Close responses (ie. close the file handles but leave response
+ still .read()able &c., thanks to the response objects we're
+ using) ([email protected]).
+
+2005-08-14 John J Lee <[email protected]>
+ * Add missing argument to UserAgent's _add_referer_header stub.
+ * Doc and comment improvements.
+
+2005-06-28 John J Lee <[email protected]>
+ * Allow specifying parser class for equiv handling.
+ * Ensure correct default constructor args are passed to
+ HTTPRefererProcessor.
+ * Allow configuring details of Refresh handling.
+ * Switch to tolerant parser.
+
+2005-06-11 John J Lee <[email protected]>
+ * Do .seek(0) after link parsing in a finally block.
+ * Regard text/xhtml as HTML.
+ * Fix 2.4-compatibility bugs.
+ * Fix spelling of '_equiv' feature string.
+
+2005-05-30 John J Lee <[email protected]>
+ * Turn on Referer, Refresh and HTTP-Equiv handling by default.
+
+2005-05-08 John J Lee <[email protected]>
+ * Fix .reload() to not update history (thanks to Titus Brown).
+ * Use cookielib where available
+
+2005-03-01 John J Lee <[email protected]>
+ * Fix referer bugs: Don't send URL fragments; Don't add in Referer
+ header in redirected request unless original request had a
+ Referer header.
+
+2005-02-19 John J Lee <[email protected]>
+ * Allow supplying own mechanize.FormsFactory, so eg. can use
+ ClientForm.XHTMLFormParser. Also allow supplying own Request
+ class, and use sensible defaults for this. Now depends on
+ ClientForm 0.1.17. Side effect is that, since we use the
+ correct Request class by default, there's (I hope) no need for
+ using RequestUpgradeProcessor in Browser._add_referer_header()
+ :-)
+
+2005-01-30 John J Lee <[email protected]>
+ * Released 0.0.9a.
+
+2005-01-05 John J Lee <[email protected]>
+ * Fix examples (scraped sites have changed).
+ * Fix .set_*() method boolean arguments.
+ * The .response attribute is now a method, .response()
+ * Don't depend on BaseProcessor (no longer exists).
+
+2004-05-18 John J Lee <[email protected]>
+ * Released 0.0.8a:
+ * Added robots.txt observance, controlled by
+ * BASE element has attribute 'href', not 'uri'! (patch from Jochen
+ Knuth)
+ * Fixed several bugs in handling of Referer header.
+ * Link.__eq__ now returns False instead of raising AttributeError
+ on comparison with non-Link (patch from Jim Jewett)
+ * Removed dependencies on HTTPS support in Python and on
+ ClientCookie.HTTPRobotRulesProcessor
+
+2004-01-18 John J Lee <[email protected]>
+ * Added robots.txt observance, controlled by
+ UserAgent.set_handle_robots(). This is now on by default.
+ * Removed set_persistent_headers() method -- just use .addheaders,
+ as in base class.
+
+2004-01-09 John J Lee <[email protected]>
+ * Removed unnecessary dependence on SSL support in Python. Thanks
+ to Krzysztof Kowalczyk for bug report.
+ * Released 0.0.7a.
+
+2004-01-06 John J Lee <[email protected]>
+ * Link instances may now be passed to .click_link() and
+ .follow_link().
+ * Added a new example program, pypi.py.
+
+2004-01-05 John J Lee <[email protected]>
+ * Released 0.0.5a.
+ * If <title> tag was missing, links and forms would not be parsed.
+ Also, base element (giving base URI) was ignored. Now parse
+ title lazily, and get base URI while parsing links. Also, fixed
+ ClientForm to take note of base element. Thanks to Phillip J.
+ Eby for bug report.
+ * Released 0.0.6a.
+
+2004-01-04 John J Lee <[email protected]>
+ * Fixed _useragent._replace_handler() to update self.handlers
+ correctly.
+ * Updated required pullparser version check.
+ * Visiting a URL now deselects form (sets self.form to None).
+ * Only first Content-Type header is now checked by
+ ._viewing_html(), if there are more than one.
+ * Stopped using getheaders from ClientCookie -- don't need it,
+ since depend on Python 2.2, which has .getheaders() method on
+ responses. Improved comments.
+ * .open() now resets .response to None. Also rearranged .open() a
+ bit so instance remains in consistent state on failure.
+ * .geturl() now checks for non-None .response, and raises Browser.
+ * .back() now checks for non-None .response, and doesn't attempt
+ to parse if it's None.
+ * .reload() no longer adds new history item.
+ * Documented tag argument to .find_link().
+ * Fixed a few places where non-keyword arguments for .find_link()
+ were silently ignored. Now raises ValueError.
+
+2004-01-02 John J Lee <[email protected]>
+ * Use response_seek_wrapper instead of seek_wrapper, which broke
+ use of reponses after they're closed.
+ * (Fixed response_seek_wrapper in ClientCookie.)
+ * Fixed adding of Referer header. Thanks to Per Cederqvist for
+ bug report.
+ * Released 0.0.4a.
+ * Updated required ClientCookie version check.
+
+2003-12-30 John J Lee <[email protected]>
+ * Added support for character encodings (for matching link text).
+ * Released 0.0.3a.
+
+2003-12-28 John J Lee <[email protected]>
+ * Attribute lookups are no longer forwarded to .response --
+ you have to do it explicitly.
+ * Added .geturl() method, which just delegates to .response.
+ * Big rehash of UserAgent, which was broken. Added a test.
+ * Discovered that zip() doesn't raise an exception when its
+ arguments are of different length, so several tests could pass
+ when they should have failed. Fixed.
+ * Fixed <A/> case in ._parse_html().
+ * Released 0.0.2a.
+
+2003-12-27 John J Lee <[email protected]>
+ * Added and improved docstrings.
+ * Browser.form is now a public attribute. Also documented
+ Browser's public attributes.
+ * Added base_url and absolute_url attributes to Link.
+ * Tidied up .open(). Relative URL Request objects are no longer
+ converted to absolute URLs -- they should probably be absolute
+ in the first place anyway.
+ * Added proper Referer handling (the handler in ClientCookie is a
+ hack that only covers a restricted case).
+ * Added click_link method, for symmetry with .click() / .submit()
+ methods (which latter apply to forms). Of these methods,
+ .click/.click_link() returns a request, and .submit/
+ .follow_link() actually .open()s the request.
+ * Updated broken example code.
+
+2003-12-24 John J Lee <[email protected]>
+ * Modified setup.py so can easily register with PyPI.
+
+2003-12-22 John J Lee <[email protected]>
+ * Released 0.0.1a.
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/mechanize-0.4.2/MANIFEST.in
new/mechanize-0.4.3/MANIFEST.in
--- old/mechanize-0.4.2/MANIFEST.in 2017-03-14 19:53:44.000000000 +0100
+++ new/mechanize-0.4.3/MANIFEST.in 2019-04-17 16:26:28.000000000 +0200
@@ -2,6 +2,7 @@
include COPYRIGHT
include MANIFEST.in
include README.rst
+include ChangeLog
include *.py
recursive-include examples *.py
recursive-include examples/forms *.dat *.txt *.html *.cgi *.py
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/mechanize-0.4.2/PKG-INFO new/mechanize-0.4.3/PKG-INFO
--- old/mechanize-0.4.2/PKG-INFO 2019-04-12 07:20:14.000000000 +0200
+++ new/mechanize-0.4.3/PKG-INFO 2019-08-18 10:08:08.000000000 +0200
@@ -1,12 +1,12 @@
Metadata-Version: 2.1
Name: mechanize
-Version: 0.4.2
+Version: 0.4.3
Summary: Stateful programmatic web browsing.
Home-page: https://github.com/python-mechanize/mechanize
Author: Kovid Goyal
Author-email: [email protected]
License: BSD
-Download-URL:
https://pypi.python.org/packages/source/m/mechanize/mechanize-0.4.2.tar.gz
+Download-URL:
https://pypi.python.org/packages/source/m/mechanize/mechanize-0.4.3.tar.gz
Description: Stateful programmatic web browsing, after Andy Lester's Perl
module
WWW::Mechanize.
@@ -35,9 +35,6 @@
Classifier: Natural Language :: English
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python
-Classifier: Programming Language :: Python :: 2
-Classifier: Programming Language :: Python :: 2.7
-Classifier: Programming Language :: Python :: 2 :: Only
Classifier: Topic :: Internet
Classifier: Topic :: Internet :: File Transfer Protocol (FTP)
Classifier: Topic :: Internet :: WWW/HTTP
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/mechanize-0.4.2/mechanize/_auth.py
new/mechanize-0.4.3/mechanize/_auth.py
--- old/mechanize-0.4.2/mechanize/_auth.py 2018-03-23 05:19:38.000000000
+0100
+++ new/mechanize-0.4.3/mechanize/_auth.py 2019-04-16 11:16:55.000000000
+0200
@@ -4,7 +4,7 @@
Copyright 2006 John J. Lee <[email protected]>
This code is free software; you can redistribute it and/or modify it under
-the terms of the BSD or ZPL 2.1 licenses (see the file COPYING.txt
+the terms of the BSD or ZPL 2.1 licenses (see the file LICENSE
included with the distribution).
"""
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/mechanize-0.4.2/mechanize/_form.py
new/mechanize-0.4.3/mechanize/_form.py
--- old/mechanize-0.4.2/mechanize/_form.py 2019-01-06 13:00:24.000000000
+0100
+++ new/mechanize-0.4.3/mechanize/_form.py 2019-05-23 14:30:56.000000000
+0200
@@ -76,10 +76,10 @@
return ctype, name, {'__select': attrs}
-def parse_forms(root, base_url, request_class=None, select_default=False):
+def parse_forms(root, base_url, request_class=None, select_default=False,
encoding=None):
if request_class is None:
request_class = Request
- global_form = HTMLForm(base_url)
+ global_form = HTMLForm(base_url, encoding=encoding)
forms, labels = [], []
form_elems = []
form_id_map = {}
@@ -124,7 +124,7 @@
else:
action = base_url
form = HTMLForm(action, method, enctype, name, form_elem.attrib,
- request_class, forms, labels, id_to_labels)
+ request_class, forms, labels, id_to_labels,
encoding=encoding)
forms_map[form_elem] = form
forms.append(form)
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/mechanize-0.4.2/mechanize/_form_controls.py
new/mechanize-0.4.3/mechanize/_form_controls.py
--- old/mechanize-0.4.2/mechanize/_form_controls.py 2019-04-02
08:25:15.000000000 +0200
+++ new/mechanize-0.4.3/mechanize/_form_controls.py 2019-06-17
06:20:14.000000000 +0200
@@ -7,10 +7,11 @@
import sys
import warnings
from io import BytesIO
+from mimetypes import guess_type
from . import _request
-from .polyglot import (as_unicode, is_py2, iteritems, urlencode, urlparse,
- urlunparse)
+from .polyglot import (as_unicode, is_py2, iteritems, unicode_type, urlencode,
+ urlparse, urlunparse)
if is_py2:
from cStringIO import StringIO
@@ -59,12 +60,13 @@
def isstringlike(x):
+ if isinstance(x, (bytes, unicode_type)):
+ return True
try:
x + ""
+ return True
except Exception:
return False
- else:
- return True
def choose_boundary():
@@ -525,7 +527,9 @@
if filename is not None and not isstringlike(filename):
raise TypeError("filename must be None or string-like")
if content_type is None:
- content_type = "application/octet-stream"
+ if getattr(file_object, 'name', None):
+ content_type = guess_type(file_object.name)[0]
+ content_type = content_type or "application/octet-stream"
self._upload_data.append((file_object, content_type, filename))
def _totally_ordered_pairs(self):
@@ -1836,7 +1840,8 @@
request_class=_request.Request,
forms=None,
labels=None,
- id_to_labels=None):
+ id_to_labels=None,
+ encoding=None):
"""
In the usual case, use ParseResponse (or ParseFile) to create new
HTMLForm objects.
@@ -1851,6 +1856,7 @@
self.action = action
self.method = method
self.enctype = enctype
+ self.form_encoding = encoding or 'utf-8'
self.name = name
if attrs is not None:
self.attrs = dict(attrs)
@@ -1932,6 +1938,7 @@
"""
for control in self.controls:
control.fixup()
+ control.form_encoding = self.form_encoding
# ---------------------------------------------------
@@ -2504,13 +2511,13 @@
rest, (query, frag) = parts[:-2], parts[-2:]
frag
- def as_utf8(x):
- if not isinstance(x, bytes):
- x = x.encode('utf-8')
+ def encode_data(x):
+ if isinstance(x, unicode_type):
+ x = x.encode(self.form_encoding)
return x
def encode_query():
- p = [(as_utf8(k), as_utf8(v)) for k, v in self._pairs()]
+ p = [(encode_data(k), encode_data(v)) for k, v in self._pairs()]
return urlencode(p)
if method == "GET":
@@ -2534,7 +2541,7 @@
"form-data", add_to_http_hdrs=True, prefix=0)
for ii, k, v, control_index in self._pairs_and_controls():
self.controls[control_index]._write_mime_data(
- mw, as_utf8(k), as_utf8(v))
+ mw, encode_data(k), encode_data(v))
mw.lastpart()
return uri, data.getvalue(), http_hdrs
else:
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/mechanize-0.4.2/mechanize/_headersutil.py
new/mechanize-0.4.3/mechanize/_headersutil.py
--- old/mechanize-0.4.2/mechanize/_headersutil.py 2019-01-06
13:00:24.000000000 +0100
+++ new/mechanize-0.4.3/mechanize/_headersutil.py 2019-04-16
11:16:55.000000000 +0200
@@ -5,7 +5,7 @@
This code is free software; you can redistribute it and/or modify it
under the terms of the BSD or ZPL 2.1 licenses (see the file
-COPYING.txt included with the distribution).
+LICENSE included with the distribution).
"""
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/mechanize-0.4.2/mechanize/_html.py
new/mechanize-0.4.3/mechanize/_html.py
--- old/mechanize-0.4.2/mechanize/_html.py 2019-01-10 11:34:12.000000000
+0100
+++ new/mechanize-0.4.3/mechanize/_html.py 2019-05-23 14:30:56.000000000
+0200
@@ -11,6 +11,48 @@
from .polyglot import is_string
DEFAULT_ENCODING = "utf-8"
+_encoding_pats = (
+ # XML declaration
+ r'<\?[^<>]+encoding\s*=\s*[\'"](.*?)[\'"][^<>]*>',
+ # HTML 5 charset
+ r'''<meta\s+charset=['"]([-_a-z0-9]+)['"][^<>]*>(?:\s*</meta>){0,1}''',
+ # HTML 4 Pragma directive
+
r'''<meta\s+?[^<>]*?content\s*=\s*['"][^'"]*?charset=([-_a-z0-9]+)[^'"]*?['"][^<>]*>(?:\s*</meta>){0,1}''',
+)
+
+
+def compile_pats(binary):
+ for raw in _encoding_pats:
+ if binary:
+ raw = raw.encode('ascii')
+ yield re.compile(raw, flags=re.IGNORECASE)
+
+
+class LazyEncodingPats(object):
+
+ def __call__(self, binary=False):
+ attr = 'binary_pats' if binary else 'unicode_pats'
+ pats = getattr(self, attr, None)
+ if pats is None:
+ pats = tuple(compile_pats(binary))
+ setattr(self, attr, pats)
+ for pat in pats:
+ yield pat
+
+
+lazy_encoding_pats = LazyEncodingPats()
+
+
+def find_declared_encoding(raw, limit=50*1024):
+ prefix = raw[:limit]
+ is_binary = isinstance(raw, bytes)
+ for pat in lazy_encoding_pats(is_binary):
+ m = pat.search(prefix)
+ if m is not None:
+ ans = m.group(1)
+ if is_binary:
+ ans = ans.decode('ascii', 'replace')
+ return ans
def elem_text(elem):
@@ -203,6 +245,7 @@
"""
self._encoding_finder = EncodingFinder(default_encoding)
+ self.form_encoding = default_encoding
self._response_type_finder = ResponseTypeFinder(
allow_xhtml=allow_xhtml)
self._content_parser = content_parser
@@ -243,14 +286,18 @@
def root(self):
if self._root is lazy:
response = self._response
+ raw = self._response.read() if self._response else b''
+ default_encoding = self._encoding_finder._default_encoding
+ transport_encoding = get_encoding_from_response(response,
verify=False)
+ declared_encoding = find_declared_encoding(raw)
+ self.form_encoding = declared_encoding or transport_encoding or
default_encoding
self._root = self._content_parser(
- self._response.read() if self._response else b'',
+ raw,
url=response.geturl() if response else None,
response_info=response.info() if response else None,
- default_encoding=self._encoding_finder._default_encoding,
+ default_encoding=default_encoding,
is_html=self.is_html,
- transport_encoding=get_encoding_from_response(
- response, verify=False))
+ transport_encoding=transport_encoding)
return self._root
@property
@@ -288,4 +335,4 @@
if self.root is None:
return (), None
return parse_forms(self.root,
- self._response.geturl(), self._request_class)
+ self._response.geturl(), self._request_class,
encoding=self.form_encoding)
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/mechanize-0.4.2/mechanize/_http.py
new/mechanize-0.4.3/mechanize/_http.py
--- old/mechanize-0.4.2/mechanize/_http.py 2019-03-07 16:34:29.000000000
+0100
+++ new/mechanize-0.4.3/mechanize/_http.py 2019-04-16 11:16:55.000000000
+0200
@@ -8,7 +8,7 @@
This code is free software; you can redistribute it and/or modify it
under the terms of the BSD or ZPL 2.1 licenses (see the file
-COPYING.txt included with the distribution).
+LICENSE included with the distribution).
"""
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/mechanize-0.4.2/mechanize/_mechanize.py
new/mechanize-0.4.3/mechanize/_mechanize.py
--- old/mechanize-0.4.2/mechanize/_mechanize.py 2019-01-07 06:52:06.000000000
+0100
+++ new/mechanize-0.4.3/mechanize/_mechanize.py 2019-08-18 10:06:45.000000000
+0200
@@ -4,7 +4,7 @@
Copyright 2003 Andy Lester (original Perl code)
This code is free software; you can redistribute it and/or modify it
-under the terms of the BSD or ZPL 2.1 licenses (see the file COPYING.txt
+under the terms of the BSD or ZPL 2.1 licenses (see the file LICENSE
included with the distribution).
"""
@@ -468,7 +468,7 @@
path='/some-page')
'''
self.cookiejar.set_cookie(
- Cookie(None, name, value, None, False, domain, True, False, path,
+ Cookie(0, name, value, None, False, domain, True, False, path,
True, False, None, False, None, None, None))
@property
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/mechanize-0.4.2/mechanize/_opener.py
new/mechanize-0.4.3/mechanize/_opener.py
--- old/mechanize-0.4.2/mechanize/_opener.py 2019-01-10 11:34:12.000000000
+0100
+++ new/mechanize-0.4.3/mechanize/_opener.py 2019-04-16 11:16:55.000000000
+0200
@@ -4,7 +4,7 @@
This code is free software; you can redistribute it and/or modify it
under the terms of the BSD or ZPL 2.1 licenses (see the file
-COPYING.txt included with the distribution).
+LICENSE included with the distribution).
"""
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/mechanize-0.4.2/mechanize/_request.py
new/mechanize-0.4.3/mechanize/_request.py
--- old/mechanize-0.4.2/mechanize/_request.py 2018-03-23 05:19:38.000000000
+0100
+++ new/mechanize-0.4.3/mechanize/_request.py 2019-04-16 11:16:55.000000000
+0200
@@ -4,7 +4,7 @@
This code is free software; you can redistribute it and/or modify it
under the terms of the BSD or ZPL 2.1 licenses (see the file
-COPYING.txt included with the distribution).
+LICENSE included with the distribution).
"""
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/mechanize-0.4.2/mechanize/_response.py
new/mechanize-0.4.3/mechanize/_response.py
--- old/mechanize-0.4.2/mechanize/_response.py 2019-01-10 11:34:12.000000000
+0100
+++ new/mechanize-0.4.3/mechanize/_response.py 2019-04-16 11:16:55.000000000
+0200
@@ -11,7 +11,7 @@
Copyright 2006 John J. Lee <[email protected]>
This code is free software; you can redistribute it and/or modify it
-under the terms of the BSD or ZPL 2.1 licenses (see the file COPYING.txt
+under the terms of the BSD or ZPL 2.1 licenses (see the file LICENSE
included with the distribution).
"""
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/mechanize-0.4.2/mechanize/_rfc3986.py
new/mechanize-0.4.3/mechanize/_rfc3986.py
--- old/mechanize-0.4.2/mechanize/_rfc3986.py 2019-01-07 06:52:06.000000000
+0100
+++ new/mechanize-0.4.3/mechanize/_rfc3986.py 2019-04-16 11:16:55.000000000
+0200
@@ -5,7 +5,7 @@
Copyright 2006 John J. Lee <[email protected]>
This code is free software; you can redistribute it and/or modify it under
-the terms of the BSD or ZPL 2.1 licenses (see the file COPYING.txt
+the terms of the BSD or ZPL 2.1 licenses (see the file LICENSE
included with the distribution).
"""
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/mechanize-0.4.2/mechanize/_urllib2_fork.py
new/mechanize-0.4.3/mechanize/_urllib2_fork.py
--- old/mechanize-0.4.2/mechanize/_urllib2_fork.py 2019-03-28
08:00:21.000000000 +0100
+++ new/mechanize-0.4.3/mechanize/_urllib2_fork.py 2019-04-16
11:16:55.000000000 +0200
@@ -10,7 +10,7 @@
This code is free software; you can redistribute it and/or modify it
under the terms of the BSD or ZPL 2.1 licenses (see the file
-COPYING.txt included with the distribution).
+LICENSE included with the distribution).
"""
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/mechanize-0.4.2/mechanize/_useragent.py
new/mechanize-0.4.3/mechanize/_useragent.py
--- old/mechanize-0.4.2/mechanize/_useragent.py 2018-04-23 13:22:35.000000000
+0200
+++ new/mechanize-0.4.3/mechanize/_useragent.py 2019-04-16 11:16:55.000000000
+0200
@@ -6,7 +6,7 @@
Copyright 2003-2006 John J. Lee <[email protected]>
This code is free software; you can redistribute it and/or modify it under
-the terms of the BSD or ZPL 2.1 licenses (see the file COPYING.txt
+the terms of the BSD or ZPL 2.1 licenses (see the file LICENSE
included with the distribution).
"""
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/mechanize-0.4.2/mechanize/_util.py
new/mechanize-0.4.3/mechanize/_util.py
--- old/mechanize-0.4.2/mechanize/_util.py 2019-01-10 11:34:12.000000000
+0100
+++ new/mechanize-0.4.3/mechanize/_util.py 2019-04-16 11:16:55.000000000
+0200
@@ -4,7 +4,7 @@
This code is free software; you can redistribute it and/or modify it
under the terms of the BSD or ZPL 2.1 licenses (see the file
-COPYING.txt included with the distribution).
+LICENSE included with the distribution).
"""
from __future__ import absolute_import
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/mechanize-0.4.2/mechanize/_version.py
new/mechanize-0.4.3/mechanize/_version.py
--- old/mechanize-0.4.2/mechanize/_version.py 2019-04-12 07:20:03.000000000
+0200
+++ new/mechanize-0.4.3/mechanize/_version.py 2019-08-18 10:06:45.000000000
+0200
@@ -1,2 +1,2 @@
-"0.4.2"
-__version__ = (0, 4, 2, None, None)
+"0.4.3"
+__version__ = (0, 4, 3, None, None)
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/mechanize-0.4.2/mechanize.egg-info/PKG-INFO
new/mechanize-0.4.3/mechanize.egg-info/PKG-INFO
--- old/mechanize-0.4.2/mechanize.egg-info/PKG-INFO 2019-04-12
07:20:14.000000000 +0200
+++ new/mechanize-0.4.3/mechanize.egg-info/PKG-INFO 2019-08-18
10:08:08.000000000 +0200
@@ -1,12 +1,12 @@
Metadata-Version: 2.1
Name: mechanize
-Version: 0.4.2
+Version: 0.4.3
Summary: Stateful programmatic web browsing.
Home-page: https://github.com/python-mechanize/mechanize
Author: Kovid Goyal
Author-email: [email protected]
License: BSD
-Download-URL:
https://pypi.python.org/packages/source/m/mechanize/mechanize-0.4.2.tar.gz
+Download-URL:
https://pypi.python.org/packages/source/m/mechanize/mechanize-0.4.3.tar.gz
Description: Stateful programmatic web browsing, after Andy Lester's Perl
module
WWW::Mechanize.
@@ -35,9 +35,6 @@
Classifier: Natural Language :: English
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python
-Classifier: Programming Language :: Python :: 2
-Classifier: Programming Language :: Python :: 2.7
-Classifier: Programming Language :: Python :: 2 :: Only
Classifier: Topic :: Internet
Classifier: Topic :: Internet :: File Transfer Protocol (FTP)
Classifier: Topic :: Internet :: WWW/HTTP
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/mechanize-0.4.2/mechanize.egg-info/SOURCES.txt
new/mechanize-0.4.3/mechanize.egg-info/SOURCES.txt
--- old/mechanize-0.4.2/mechanize.egg-info/SOURCES.txt 2019-04-12
07:20:14.000000000 +0200
+++ new/mechanize-0.4.3/mechanize.egg-info/SOURCES.txt 2019-08-18
10:08:08.000000000 +0200
@@ -1,4 +1,5 @@
COPYRIGHT
+ChangeLog
LICENSE
MANIFEST.in
README.rst
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/mechanize-0.4.2/setup.py new/mechanize-0.4.3/setup.py
--- old/mechanize-0.4.2/setup.py 2019-01-10 11:34:12.000000000 +0100
+++ new/mechanize-0.4.3/setup.py 2019-08-10 07:37:07.000000000 +0200
@@ -42,9 +42,6 @@
Natural Language :: English
Operating System :: OS Independent
Programming Language :: Python
-Programming Language :: Python :: 2
-Programming Language :: Python :: 2.7
-Programming Language :: Python :: 2 :: Only
Topic :: Internet
Topic :: Internet :: File Transfer Protocol (FTP)
Topic :: Internet :: WWW/HTTP
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/mechanize-0.4.2/test/test_cookies.py
new/mechanize-0.4.3/test/test_cookies.py
--- old/mechanize-0.4.2/test/test_cookies.py 2019-01-10 11:34:12.000000000
+0100
+++ new/mechanize-0.4.3/test/test_cookies.py 2019-06-29 06:44:24.000000000
+0200
@@ -1931,7 +1931,7 @@
counter[key] = counter[key] + 1
assert not (
- # a permanent cookie got lost accidently
+ # a permanent cookie got lost accidentally
counter["perm_after"] != counter["perm_before"] or
# a session cookie hasn't been cleared
counter["session_after"] != 0 or
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/mechanize-0.4.2/test/test_form.py
new/mechanize-0.4.3/test/test_form.py
--- old/mechanize-0.4.2/test/test_form.py 2019-04-02 08:25:15.000000000
+0200
+++ new/mechanize-0.4.3/test/test_form.py 2019-05-23 14:30:56.000000000
+0200
@@ -1,5 +1,5 @@
#!/usr/bin/env python
-# -*- coding: iso-8859-1 -*-
+# -*- coding: utf-8 -*-
# Copyright 2002-2005 John J. Lee <[email protected]>
# Copyright 2005 Gary Poster
@@ -18,7 +18,7 @@
import mechanize._testcase as _testcase
from mechanize import (AmbiguityError, ControlNotFoundError, ItemCountError,
ItemNotFoundError)
-from mechanize._html import content_parser
+from mechanize._html import content_parser, find_declared_encoding
from mechanize._util import get1
from mechanize.polyglot import codepoint_to_chr
@@ -96,11 +96,12 @@
add_global=True):
raw = file.read()
root = content_parser(raw, transport_encoding=encoding)
+ form_encoding = find_declared_encoding(raw) or encoding
forms, global_form = _form.parse_forms(
root,
base_uri,
select_default=select_default,
- request_class=request_class)
+ request_class=request_class, encoding=form_encoding)
if not add_global:
return list(forms)
return [global_form] + list(forms)
@@ -209,6 +210,23 @@
req.get_full_url() == "http://localhost/abc?firstname=Gisle+Aas";)
+class EncodingTests(unittest.TestCase):
+
+ def _forms(self):
+ file = BytesIO(
+ b'<meta charset="iso-8859-1"><form method="POST">'
+ b'<input name="name" value=""><input name="unicode"
value=""></form>')
+ return parse_file(file, "http://localhost/";, backwards_compat=False)
+
+ def testFillFormEncoding(self):
+ forms = self._forms()
+ form = forms[0]
+ form["name"] = u"Räuber Hotzenplotz".encode('iso-8859-1')
+ form["unicode"] = u"Räuber Hotzenplotz"
+ req = form.click()
+ self.assertEqual(req.get_data(),
'name={0}&unicode={0}'.format('R%E4uber+Hotzenplotz'))
+
+
def get_header(req, name):
try:
return req.get_header(name)
