urlgrabber-3.9.1/0000775000076400007640000000000011257176250013547 5ustar skvidalskvidalurlgrabber-3.9.1/makefile0000664000076400007640000000402311257172564015252 0ustar skvidalskvidalPACKAGE = urlgrabber RM = /bin/rm -rf GIT = /usr/bin/git WEBHOST = login.dulug.duke.edu WEBPATH = /home/groups/urlgrabber/web/download PYTHON = python PY_MODULE = $(PACKAGE) SCM_MODULE = $(PACKAGE) CLEANFILES = MANIFEST *~ build dist export release daily reference nonexistent_file ChangeLog.bak \ *.pyc urlgrabber/*.pyc scripts/*.pyc test/*.pyc test/nonexistent_file \ test/reference test/reference.part urlgrabber/*~ ############################################################################## VERSION = $(shell $(PYTHON) -c 'import $(PY_MODULE); print $(PY_MODULE).__version__') DATE = $(shell $(PYTHON) -c 'import $(PY_MODULE); print $(PY_MODULE).__date__') SCM_TAG = release-$(shell echo $(VERSION) | sed -e 's/\./_/g') PYTHON22 = $(shell /usr/bin/which python2.2 2>/dev/null) PYTHON23 = $(shell /usr/bin/which python2.3 2>/dev/null) PYTHON24 = $(shell /usr/bin/which python2.4 2>/dev/null) PYTHON25 = $(shell /usr/bin/which python2.5 2>/dev/null) TESTPYTHONS = $(PYTHON22) $(PYTHON23) $(PYTHON24) $(PYTHON25) ############################################################################## default: @echo TARGETS: changelog release clean test changelog: $(GIT) log --since=2006-12-01 --pretty --numstat --summary | maint/git2cl > ChangeLog # NOTE: do --manifest-only first even though we're about to force it. The # former ensures that MANIFEST exists (touch would also do the trick). If # the file 'MANIFEST' doesn't exist, then it won't be included the next time # it's built from MANIFEST.in release: FORCE pre-release-test @dir=$$PWD; $(PYTHON) setup.py sdist --manifest-only @dir=$$PWD; $(PYTHON) setup.py sdist --force-manifest @echo "The archive is in dist/${PACKAGE}-$(VERSION).tar.gz" pre-release-test: @echo "You should make sure you've updated the changelog" @echo "version = $(VERSION), date = $(DATE), tag = $(SCM_TAG)" test $(DATE) = `date +'%Y/%m/%d'` # verify release date is set to today clean: $(RM) $(CLEANFILES) test: FORCE @export PYTHONPATH=.; \ $(PYTHON) test/runtests.py -v 1; \ FORCE: urlgrabber-3.9.1/TODO0000664000076400007640000000404411150613414014227 0ustar skvidalskvidalALPHA 2: * web page - better examples page * threading/batch - (rt) propose an interface for threaded batch downloads - (mds) design a new progress-meter interface for threaded multi-file downloads - (rt) look at CacheFTPHandler and its implications for batch mode and byte-ranges/reget * progress meter stuff - support for retrying a file (in a MirrorGroup, for example) - failure support (done?) - support for when we have less information (no sizes, etc) - check compatibility with gui interfaces - starting a download with some parts already read (with reget, for example) * look at making the 'check_timestamp' reget mode work with ftp. Currently, we NEVER get a timestamp back, so we can't compare. We'll probably need to subclass/replace either the urllib2 FTP handler or the ftplib FTP object (or both, but I doubt it). It may or may not be worth it just for this one mode of reget. It fails safely - by getting the entire file. * cache dns lookups -- for a possible approach, see https://lists.dulug.duke.edu/pipermail/yum-devel/2004-March/000136.html Misc/Maybe: * BatchURLGrabber/BatchMirrorGroup for concurrent downloads and possibly to handle forking into secure/setuid sandbox. * Consider adding a progress_meter implementation that can be used in concurrent download situations (I have some ideas about this -mds) * Consider using CacheFTPHandler instead of FTPHandler in byterange.py. CacheFTPHandler reuses connections but this may lead to problems with ranges. I've tested CacheFTPHandler with ranges using vsftpd as a server and everything works fine but this needs more exhaustive tests or a fallback mechanism. Also, CacheFTPHandler breaks with multiple threads. * Consider some statistics tracking so that urlgrabber can record the speed/reliability of different servers. This could then be used by the mirror code for choosing optimal servers (slick, eh?) * check SSL certs. This may require PyOpenSSL. urlgrabber-3.9.1/test/0000775000076400007640000000000011257176250014526 5ustar skvidalskvidalurlgrabber-3.9.1/test/test_grabber.py0000664000076400007640000005122711257172042017545 0ustar skvidalskvidal#!/usr/bin/python -t # This library is free software; you can redistribute it and/or # modify it under the terms of the GNU Lesser General Public # License as published by the Free Software Foundation; either # version 2.1 of the License, or (at your option) any later version. # # This library is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU # Lesser General Public License for more details. # # You should have received a copy of the GNU Lesser General Public # License along with this library; if not, write to the # Free Software Foundation, Inc., # 59 Temple Place, Suite 330, # Boston, MA 02111-1307 USA # This file is part of urlgrabber, a high-level cross-protocol url-grabber # Copyright 2002-2004 Michael D. Stenner, Ryan Tomayko """grabber.py tests""" # $Id: test_grabber.py,v 1.31 2006/12/08 00:14:16 mstenner Exp $ import sys import os import string, tempfile, random, cStringIO, os import urllib2 import socket from base_test_code import * import urlgrabber import urlgrabber.grabber as grabber from urlgrabber.grabber import URLGrabber, URLGrabError, CallbackObject, \ URLParser from urlgrabber.progress import text_progress_meter class FileObjectTests(TestCase): def setUp(self): self.filename = tempfile.mktemp() fo = file(self.filename, 'wb') fo.write(reference_data) fo.close() self.fo_input = cStringIO.StringIO(reference_data) self.fo_output = cStringIO.StringIO() (url, parts) = grabber.default_grabber.opts.urlparser.parse( self.filename, grabber.default_grabber.opts) self.wrapper = grabber.PyCurlFileObject( url, self.fo_output, grabber.default_grabber.opts) def tearDown(self): self.wrapper.close() os.unlink(self.filename) def test_readall(self): "PYCurlFileObject .read() method" s = self.wrapper.read() self.fo_output.write(s) self.assert_(reference_data == self.fo_output.getvalue()) def test_readline(self): "PyCurlFileObject .readline() method" while 1: s = self.wrapper.readline() self.fo_output.write(s) if not s: break self.assert_(reference_data == self.fo_output.getvalue()) def test_readlines(self): "PyCurlFileObject .readlines() method" li = self.wrapper.readlines() self.fo_output.write(string.join(li, '')) self.assert_(reference_data == self.fo_output.getvalue()) def test_smallread(self): "PyCurlFileObject .read(N) with small N" while 1: s = self.wrapper.read(23) self.fo_output.write(s) if not s: break self.assert_(reference_data == self.fo_output.getvalue()) class HTTPTests(TestCase): def test_reference_file(self): "download refernce file via HTTP" filename = tempfile.mktemp() grabber.urlgrab(ref_http, filename) fo = file(filename, 'rb') contents = fo.read() fo.close() self.assert_(contents == reference_data) def test_post(self): "do an HTTP post" headers = (('Content-type', 'text/plain'),) ret = grabber.urlread(base_http + 'test_post.php', data=short_reference_data, http_headers=headers) self.assertEqual(ret, short_reference_data) class URLGrabberModuleTestCase(TestCase): """Test module level functions defined in grabber.py""" def setUp(self): pass def tearDown(self): pass def test_urlopen(self): "module-level urlopen() function" fo = urlgrabber.urlopen('http://www.python.org') fo.close() def test_urlgrab(self): "module-level urlgrab() function" outfile = tempfile.mktemp() filename = urlgrabber.urlgrab('http://www.python.org', filename=outfile) os.unlink(outfile) def test_urlread(self): "module-level urlread() function" s = urlgrabber.urlread('http://www.python.org') class URLGrabberTestCase(TestCase): """Test grabber.URLGrabber class""" def setUp(self): self.meter = text_progress_meter( fo=cStringIO.StringIO() ) pass def tearDown(self): pass def testKeywordArgs(self): """grabber.URLGrabber.__init__() **kwargs handling. This is a simple test that just passes some arbitrary values into the URLGrabber constructor and checks that they've been set properly. """ opener = urllib2.OpenerDirector() g = URLGrabber( progress_obj=self.meter, throttle=0.9, bandwidth=20, retry=20, retrycodes=[5,6,7], copy_local=1, close_connection=1, user_agent='test ua/1.0', proxies={'http' : 'http://www.proxy.com:9090'}, opener=opener ) opts = g.opts self.assertEquals( opts.progress_obj, self.meter ) self.assertEquals( opts.throttle, 0.9 ) self.assertEquals( opts.bandwidth, 20 ) self.assertEquals( opts.retry, 20 ) self.assertEquals( opts.retrycodes, [5,6,7] ) self.assertEquals( opts.copy_local, 1 ) self.assertEquals( opts.close_connection, 1 ) self.assertEquals( opts.user_agent, 'test ua/1.0' ) self.assertEquals( opts.proxies, {'http' : 'http://www.proxy.com:9090'} ) self.assertEquals( opts.opener, opener ) nopts = grabber.URLGrabberOptions(delegate=opts, throttle=0.5, copy_local=0) self.assertEquals( nopts.progress_obj, self.meter ) self.assertEquals( nopts.throttle, 0.5 ) self.assertEquals( nopts.bandwidth, 20 ) self.assertEquals( nopts.retry, 20 ) self.assertEquals( nopts.retrycodes, [5,6,7] ) self.assertEquals( nopts.copy_local, 0 ) self.assertEquals( nopts.close_connection, 1 ) self.assertEquals( nopts.user_agent, 'test ua/1.0' ) self.assertEquals( nopts.proxies, {'http' : 'http://www.proxy.com:9090'} ) nopts.opener = None self.assertEquals( nopts.opener, None ) def test_make_callback(self): """grabber.URLGrabber._make_callback() tests""" def cb(e): pass tup_cb = (cb, ('stuff'), {'some': 'dict'}) g = URLGrabber() self.assertEquals(g._make_callback(cb), (cb, (), {})) self.assertEquals(g._make_callback(tup_cb), tup_cb) class URLParserTestCase(TestCase): def setUp(self): pass def tearDown(self): pass def test_parse_url_with_prefix(self): """grabber.URLParser.parse() with opts.prefix""" base = 'http://foo.com/dir' bases = [base, base+'/'] filename = 'bar/baz' target = base + '/' + filename for b in bases: g = URLGrabber(prefix=b) (url, parts) = g.opts.urlparser.parse(filename, g.opts) self.assertEquals(url, target) def _test_url(self, urllist): g = URLGrabber() try: quote = urllist[3] except IndexError: quote = None g.opts.quote = quote (url, parts) = g.opts.urlparser.parse(urllist[0], g.opts) if 1: self.assertEquals(url, urllist[1]) self.assertEquals(parts, urllist[2]) else: if url == urllist[1] and parts == urllist[2]: print 'OK: %s' % urllist[0] else: print 'ERROR: %s' % urllist[0] print ' ' + urllist[1] print ' ' + url print ' ' + urllist[2] print ' ' + parts url_tests_all = ( ['http://host.com/path/basename.ext?arg1=val1&arg2=val2#hash', 'http://host.com/path/basename.ext?arg1=val1&arg2=val2#hash', ('http', 'host.com', '/path/basename.ext', '', 'arg1=val1&arg2=val2', 'hash')], ['http://host.com/Path With Spaces/', 'http://host.com/Path%20With%20Spaces/', ('http', 'host.com', '/Path%20With%20Spaces/', '', '', '')], ['http://host.com/Already%20Quoted', 'http://host.com/Already%20Quoted', ('http', 'host.com', '/Already%20Quoted', '', '', '')], ['http://host.com/Should Be Quoted', 'http://host.com/Should Be Quoted', ('http', 'host.com', '/Should Be Quoted', '', '', ''), 0], ['http://host.com/Should%20Not', 'http://host.com/Should%2520Not', ('http', 'host.com', '/Should%2520Not', '', '', ''), 1], ) url_tests_posix = ( ['/etc/passwd', 'file:///etc/passwd', ('file', '', '/etc/passwd', '', '', '')], ) url_tests_nt = ( [r'\\foo.com\path\file.ext', 'file://foo.com/path/file.ext', ('file', '', '//foo.com/path/file.ext', '', '', '')], [r'C:\path\file.ext', 'file:///C|/path/file.ext', ('file', '', '/C|/path/file.ext', '', '', '')], ) def test_url_parser_all_os(self): """test url parsing common to all OSs""" for f in self.url_tests_all: self._test_url(f) def test_url_parser_posix(self): """test url parsing on posix systems""" if not os.name == 'posix': self.skip() for f in self.url_tests_posix: self._test_url(f) def test_url_parser_nt(self): """test url parsing on windows systems""" if not os.name == 'nt': self.skip() for f in self.url_tests_nt: self._test_url(f) class FailureTestCase(TestCase): """Test failure behavior""" def _failure_callback(self, obj, *args, **kwargs): self.failure_callback_called = 1 self.obj = obj self.args = args self.kwargs = kwargs def test_failure_callback_called(self): "failure callback is called on retry" self.failure_callback_called = 0 g = grabber.URLGrabber(retry=2, retrycodes=[14], failure_callback=self._failure_callback) try: g.urlgrab(ref_404) except URLGrabError: pass self.assertEquals(self.failure_callback_called, 1) def test_failure_callback_args(self): "failure callback is called with the proper args" fc = (self._failure_callback, ('foo',), {'bar': 'baz'}) g = grabber.URLGrabber(retry=2, retrycodes=[14], failure_callback=fc) try: g.urlgrab(ref_404) except URLGrabError: pass self.assert_(hasattr(self, 'obj')) self.assert_(hasattr(self, 'args')) self.assert_(hasattr(self, 'kwargs')) self.assertEquals(self.args, ('foo',)) self.assertEquals(self.kwargs, {'bar': 'baz'}) self.assert_(isinstance(self.obj, CallbackObject)) self.assertEquals(self.obj.url, ref_404) self.assert_(isinstance(self.obj.exception, URLGrabError)) del self.obj class InterruptTestCase(TestCase): """Test interrupt callback behavior""" class InterruptProgress: def start(self, *args, **kwargs): pass def update(self, *args, **kwargs): raise KeyboardInterrupt def end(self, *args, **kwargs): pass class TestException(Exception): pass def _interrupt_callback(self, obj, *args, **kwargs): self.interrupt_callback_called = 1 self.obj = obj self.args = args self.kwargs = kwargs if kwargs.get('exception', None): raise kwargs['exception'] def test_interrupt_callback_called(self): "interrupt callback is called on retry" self.interrupt_callback_called = 0 ic = (self._interrupt_callback, (), {}) g = grabber.URLGrabber(progress_obj=self.InterruptProgress(), interrupt_callback=ic) try: g.urlgrab(ref_http) except KeyboardInterrupt: pass self.assertEquals(self.interrupt_callback_called, 1) def test_interrupt_callback_raises(self): "interrupt callback raises an exception" ic = (self._interrupt_callback, (), {'exception': self.TestException()}) g = grabber.URLGrabber(progress_obj=self.InterruptProgress(), interrupt_callback=ic) self.assertRaises(self.TestException, g.urlgrab, ref_http) class CheckfuncTestCase(TestCase): """Test checkfunc behavior""" def setUp(self): cf = (self._checkfunc, ('foo',), {'bar': 'baz'}) self.g = grabber.URLGrabber(checkfunc=cf) self.filename = tempfile.mktemp() self.data = short_reference_data def tearDown(self): try: os.unlink(self.filename) except: pass if hasattr(self, 'obj'): del self.obj def _checkfunc(self, obj, *args, **kwargs): self.obj = obj self.args = args self.kwargs = kwargs if hasattr(obj, 'filename'): # we used urlgrab fo = file(obj.filename) data = fo.read() fo.close() else: # we used urlread data = obj.data if data == self.data: return else: raise URLGrabError(-2, "data doesn't match") def _check_common_args(self): "check the args that are common to both urlgrab and urlread" self.assert_(hasattr(self, 'obj')) self.assert_(hasattr(self, 'args')) self.assert_(hasattr(self, 'kwargs')) self.assertEquals(self.args, ('foo',)) self.assertEquals(self.kwargs, {'bar': 'baz'}) self.assert_(isinstance(self.obj, CallbackObject)) self.assertEquals(self.obj.url, short_ref_http) def test_checkfunc_urlgrab_args(self): "check for proper args when used with urlgrab" self.g.urlgrab(short_ref_http, self.filename) self._check_common_args() self.assertEquals(self.obj.filename, self.filename) def test_checkfunc_urlread_args(self): "check for proper args when used with urlread" self.g.urlread(short_ref_http) self._check_common_args() self.assertEquals(self.obj.data, short_reference_data) def test_checkfunc_urlgrab_success(self): "check success with urlgrab checkfunc" self.data = short_reference_data self.g.urlgrab(short_ref_http, self.filename) def test_checkfunc_urlread_success(self): "check success with urlread checkfunc" self.data = short_reference_data self.g.urlread(short_ref_http) def test_checkfunc_urlgrab_failure(self): "check failure with urlgrab checkfunc" self.data = 'other data' self.assertRaises(URLGrabError, self.g.urlgrab, short_ref_http, self.filename) def test_checkfunc_urlread_failure(self): "check failure with urlread checkfunc" self.data = 'other data' self.assertRaises(URLGrabError, self.g.urlread, short_ref_http) class RegetTestBase: def setUp(self): self.ref = short_reference_data self.grabber = grabber.URLGrabber(reget='check_timestamp') self.filename = tempfile.mktemp() self.hl = len(self.ref) / 2 self.url = 'OVERRIDE THIS' def tearDown(self): try: os.unlink(self.filename) except: pass def _make_half_zero_file(self): fo = file(self.filename, 'wb') fo.write('0'*self.hl) fo.close() def _read_file(self): fo = file(self.filename, 'rb') data = fo.read() fo.close() return data class CommonRegetTests(RegetTestBase, TestCase): def test_bad_reget_type(self): "exception raised for illegal reget mode" self.assertRaises(URLGrabError, self.grabber.urlgrab, self.url, self.filename, reget='junk') class FTPRegetTests(RegetTestBase, TestCase): def setUp(self): RegetTestBase.setUp(self) self.url = short_ref_ftp # this tests to see if the server is available. If it's not, # then these tests will be skipped try: fo = urllib2.urlopen(self.url).close() except IOError: self.skip() def test_basic_reget(self): 'simple (forced) reget' self._make_half_zero_file() self.grabber.urlgrab(self.url, self.filename, reget='simple') data = self._read_file() self.assertEquals(data[:self.hl], '0'*self.hl) self.assertEquals(data[self.hl:], self.ref[self.hl:]) class HTTPRegetTests(FTPRegetTests): def setUp(self): RegetTestBase.setUp(self) self.url = short_ref_http def test_older_check_timestamp(self): try: # define this here rather than in the FTP tests because currently, # we get no timestamp information back from ftp servers. self._make_half_zero_file() ts = 1600000000 # set local timestamp to 2020 os.utime(self.filename, (ts, ts)) self.grabber.urlgrab(self.url, self.filename, reget='check_timestamp') data = self._read_file() self.assertEquals(data[:self.hl], '0'*self.hl) self.assertEquals(data[self.hl:], self.ref[self.hl:]) except NotImplementedError: self.skip() def test_newer_check_timestamp(self): try: # define this here rather than in the FTP tests because currently, # we get no timestamp information back from ftp servers. self._make_half_zero_file() ts = 1 # set local timestamp to 1969 os.utime(self.filename, (ts, ts)) self.grabber.urlgrab(self.url, self.filename, reget='check_timestamp') data = self._read_file() self.assertEquals(data, self.ref) except: self.skip() class FileRegetTests(HTTPRegetTests): def setUp(self): self.ref = short_reference_data tmp = tempfile.mktemp() tmpfo = file(tmp, 'wb') tmpfo.write(self.ref) tmpfo.close() self.tmp = tmp (url, parts) = grabber.default_grabber.opts.urlparser.parse( tmp, grabber.default_grabber.opts) self.url = url self.grabber = grabber.URLGrabber(reget='check_timestamp', copy_local=1) self.filename = tempfile.mktemp() self.hl = len(self.ref) / 2 def tearDown(self): try: os.unlink(self.filename) except: pass try: os.unlink(self.tmp) except: pass class ProFTPDSucksTests(TestCase): def setUp(self): self.url = ref_proftp try: fo = urllib2.urlopen(self.url).close() except IOError: self.skip() def test_restart_workaround(self): inst = grabber.URLGrabber() rslt = inst.urlread(self.url, range=(500, 1000)) class BaseProxyTests(TestCase): good_p = '%s://%s:%s@%s:%i' % (proxy_proto, proxy_user, good_proxy_pass, proxy_host, proxy_port) bad_p = '%s://%s:%s@%s:%i' % (proxy_proto, proxy_user, bad_proxy_pass, proxy_host, proxy_port) good_proxies = {'ftp': good_p, 'http': good_p} bad_proxies = {'ftp': bad_p, 'http': bad_p} def have_proxy(self): have_proxy = 1 s = socket.socket(socket.AF_INET, socket.SOCK_STREAM) try: s.connect((proxy_host, proxy_port)) s.close() except socket.error: have_proxy = 0 return have_proxy class ProxyHTTPAuthTests(BaseProxyTests): def setUp(self): self.url = ref_http if not self.have_proxy(): self.skip() self.g = URLGrabber() def test_good_password(self): self.g.urlopen(self.url, proxies=self.good_proxies) def test_bad_password(self): self.assertRaises(URLGrabError, self.g.urlopen, self.url, proxies=self.bad_proxies) class ProxyFTPAuthTests(ProxyHTTPAuthTests): def setUp(self): self.url = ref_ftp if not self.have_proxy(): self.skip() try: fo = urllib2.urlopen(self.url).close() except IOError: self.skip() self.g = URLGrabber() def suite(): tl = TestLoader() return tl.loadTestsFromModule(sys.modules[__name__]) if __name__ == '__main__': grabber.DEBUG = 0 runner = TextTestRunner(stream=sys.stdout,descriptions=1,verbosity=2) runner.run(suite()) urlgrabber-3.9.1/test/test_byterange.py0000664000076400007640000001376511150613414020121 0ustar skvidalskvidal#!/usr/bin/python -t # This library is free software; you can redistribute it and/or # modify it under the terms of the GNU Lesser General Public # License as published by the Free Software Foundation; either # version 2.1 of the License, or (at your option) any later version. # # This library is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU # Lesser General Public License for more details. # # You should have received a copy of the GNU Lesser General Public # License along with this library; if not, write to the # Free Software Foundation, Inc., # 59 Temple Place, Suite 330, # Boston, MA 02111-1307 USA # This file is part of urlgrabber, a high-level cross-protocol url-grabber # Copyright 2002-2004 Michael D. Stenner, Ryan Tomayko """byterange.py tests""" # $Id: test_byterange.py,v 1.6 2004/03/31 17:02:00 mstenner Exp $ import sys from StringIO import StringIO from urlgrabber.byterange import RangeableFileObject from base_test_code import * class RangeableFileObjectTestCase(TestCase): """Test range.RangeableFileObject class""" def setUp(self): # 0 1 2 3 4 5 6 7 8 9 # 0123456789012345678901234567890123456789012345678901234567 890123456789012345678901234567890 self.test = 'Why cannot we write the entire 24 volumes of Encyclopaedia\nBrittanica on the head of a pin?\n' self.fo = StringIO(self.test) self.rfo = RangeableFileObject(self.fo, (20,69)) def tearDown(self): pass def test_seek(self): """RangeableFileObject.seek()""" self.rfo.seek(11) self.assertEquals('24', self.rfo.read(2)) self.rfo.seek(14) self.assertEquals('volumes', self.rfo.read(7)) self.rfo.seek(1,1) self.assertEquals('of', self.rfo.read(2)) def test_poor_mans_seek(self): """RangeableFileObject.seek() poor mans version.. We just delete the seek method from StringIO so we can excercise RangeableFileObject when the file object supplied doesn't support seek. """ seek = StringIO.seek del(StringIO.seek) self.test_seek() StringIO.seek = seek def test_read(self): """RangeableFileObject.read()""" self.assertEquals('the', self.rfo.read(3)) self.assertEquals(' entire 24 volumes of ', self.rfo.read(22)) self.assertEquals('Encyclopaedia\nBrittanica', self.rfo.read(50)) self.assertEquals('', self.rfo.read()) def test_readall(self): """RangeableFileObject.read(): to end of file.""" rfo = RangeableFileObject(StringIO(self.test),(11,)) self.assertEquals(self.test[11:],rfo.read()) def test_readline(self): """RangeableFileObject.readline()""" self.assertEquals('the entire 24 volumes of Encyclopaedia\n', self.rfo.readline()) self.assertEquals('Brittanica', self.rfo.readline()) self.assertEquals('', self.rfo.readline()) def test_tell(self): """RangeableFileObject.tell()""" self.assertEquals(0,self.rfo.tell()) self.rfo.read(5) self.assertEquals(5,self.rfo.tell()) self.rfo.readline() self.assertEquals(39,self.rfo.tell()) class RangeModuleTestCase(TestCase): """Test module level functions defined in range.py""" def setUp(self): pass def tearDown(self): pass def test_range_tuple_normalize(self): """byterange.range_tuple_normalize()""" from urlgrabber.byterange import range_tuple_normalize from urlgrabber.byterange import RangeError tests = ( ((None,50), (0,50)), ((500,600), (500,600)), ((500,), (500,'')), ((500,None), (500,'')), (('',''), None), ((0,), None), (None, None) ) for test, ex in tests: self.assertEquals( range_tuple_normalize(test), ex ) try: range_tuple_normalize( (10,8) ) except RangeError: pass else: self.fail("range_tuple_normalize( (10,8) ) should have raised RangeError") def test_range_header_to_tuple(self): """byterange.range_header_to_tuple()""" from urlgrabber.byterange import range_header_to_tuple tests = ( ('bytes=500-600', (500,601)), ('bytes=500-', (500,'')), ('bla bla', ()), (None, None) ) for test, ex in tests: self.assertEquals( range_header_to_tuple(test), ex ) def test_range_tuple_to_header(self): """byterange.range_tuple_to_header()""" from urlgrabber.byterange import range_tuple_to_header tests = ( ((500,600), 'bytes=500-599'), ((500,''), 'bytes=500-'), ((500,), 'bytes=500-'), ((None,500), 'bytes=0-499'), (('',500), 'bytes=0-499'), (None, None), ) for test, ex in tests: self.assertEquals( range_tuple_to_header(test), ex ) try: range_tuple_to_header( ('not an int',500) ) except ValueError: pass else: self.fail("range_tuple_to_header( ('not an int',500) ) should have raised ValueError") try: range_tuple_to_header( (0,'not an int') ) except ValueError: pass else: self.fail("range_tuple_to_header( (0, 'not an int') ) should have raised ValueError") def suite(): tl = TestLoader() return tl.loadTestsFromModule(sys.modules[__name__]) if __name__ == '__main__': runner = TextTestRunner(stream=sys.stdout,descriptions=1,verbosity=2) runner.run(suite()) urlgrabber-3.9.1/test/munittest.py0000664000076400007640000010155111150613414017125 0ustar skvidalskvidal#!/usr/bin/env python """ This is a modified version of the unittest module has been modified by Michael D. Stenner from Steve Purcell's version (revision 1.46, as distributed with python 2.3.3) in the following ways: * the text formatting has been made much prettier by printing "nested" test suites * the test resulte "skip" has been added for skipping tests. A test can call any of the .skip() .skipUnless(), or .skipIf() methods from within the test method or the setUp method. * all attributes originally named with leading "__" have been changed to a single "_". This makes subclassing much easier. COMPATIBILITY It should be possible to drop this in as replacement for the standard unittest module simply by doing: import munittest as unittest In fact, the reverse is ALMOST true. Test code written for this module very nearly runs perfectly with the standard unittest module. Exceptions are: * The .skip() methods will obviously not work on the standard unittest. However, they will ERROR out and the error message will complain about missing .skip() attributes, so it will be obvious and will have the same effect as skipping. * the .setDescription method (or description argument) for TestSuite will not work. However, setting the .description attribute on a standard TestSuite instance does no harm, so if need to set them manually (you're not satisfied with the doc-string route) and you WANT to be compatible both ways, do that :) DESCRIPTIONS Names for suites in the pretty formatting are (like the test functions) slurped from the doc-strings of the corresponding object, or taken from the names of those objects. This applies to both TestCase-derived classes, and modules. Also, the TestSuite class description can be set manually in a number of ways (all of which achieve the same result): suite = TestSuite(test_list, 'this is the description') suite.setDescription('this is the description') suite.description = 'this is the description' Michael D. Stenner 2004/03/18 v0.1 =========================================================================== The original doc-string for this module follows: =========================================================================== Python unit testing framework, based on Erich Gamma's JUnit and Kent Beck's Smalltalk testing framework. This module contains the core framework classes that form the basis of specific test cases and suites (TestCase, TestSuite etc.), and also a text-based utility class for running the tests and reporting the results (TextTestRunner). Simple usage: import unittest class IntegerArithmenticTestCase(unittest.TestCase): def testAdd(self): ## test method names begin 'test*' self.assertEquals((1 + 2), 3) self.assertEquals(0 + 1, 1) def testMultiply(self): self.assertEquals((0 * 10), 0) self.assertEquals((5 * 8), 40) if __name__ == '__main__': unittest.main() Further information is available in the bundled documentation, and from http://pyunit.sourceforge.net/ Copyright (c) 1999, 2000, 2001 Steve Purcell This module is free software, and you may redistribute it and/or modify it under the same terms as Python itself, so long as this copyright message and disclaimer are retained in their original form. IN NO EVENT SHALL THE AUTHOR BE LIABLE TO ANY PARTY FOR DIRECT, INDIRECT, SPECIAL, INCIDENTAL, OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE USE OF THIS CODE, EVEN IF THE AUTHOR HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. THE AUTHOR SPECIFICALLY DISCLAIMS ANY WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE CODE PROVIDED HEREUNDER IS ON AN "AS IS" BASIS, AND THERE IS NO OBLIGATION WHATSOEVER TO PROVIDE MAINTENANCE, SUPPORT, UPDATES, ENHANCEMENTS, OR MODIFICATIONS. """ # $Id: munittest.py,v 1.2 2004/03/31 01:27:24 mstenner Exp $ import time import sys import traceback import string import os import types ############################################################################## # Exported classes and functions ############################################################################## __all__ = ['TestResult', 'TestCase', 'TestSuite', 'TextTestRunner', 'TestLoader', 'FunctionTestCase', 'main', 'defaultTestLoader'] # Expose obsolete functions for backwards compatability __all__.extend(['getTestCaseNames', 'makeSuite', 'findTestCases']) ############################################################################## # Test framework core ############################################################################## # All classes defined herein are 'new-style' classes, allowing use of 'super()' __metaclass__ = type def _strclass(cls): return "%s.%s" % (cls.__module__, cls.__name__) class TestResult: """Holder for test result information. Test results are automatically managed by the TestCase and TestSuite classes, and do not need to be explicitly manipulated by writers of tests. Each instance holds the total number of tests run, and collections of failures and errors that occurred among those test runs. The collections contain tuples of (testcase, exceptioninfo), where exceptioninfo is the formatted traceback of the error that occurred. """ def __init__(self): self.failures = [] self.errors = [] self.skipped = [] self.testsRun = 0 self.shouldStop = 0 def startTest(self, test): "Called when the given test is about to be run" self.testsRun = self.testsRun + 1 def stopTest(self, test): "Called when the given test has been run" pass def startSuite(self, suite): "Called when the given suite is about to be run" pass def stopSuit(self, suite): "Called when the tiven suite has been run" pass def addError(self, test, err): """Called when an error has occurred. 'err' is a tuple of values as returned by sys.exc_info(). """ self.errors.append((test, self._exc_info_to_string(err))) def addFailure(self, test, err): """Called when an error has occurred. 'err' is a tuple of values as returned by sys.exc_info().""" self.failures.append((test, self._exc_info_to_string(err))) def addSuccess(self, test): "Called when a test has completed successfully" pass def addSkip(self, test, err): "Called when the test has been skipped" self.skipped.append((test, self._exc_info_to_string(err))) def wasSuccessful(self): "Tells whether or not this result was a success" return len(self.failures) == len(self.errors) == 0 def stop(self): "Indicates that the tests should be aborted" self.shouldStop = 1 def _exc_info_to_string(self, err): """Converts a sys.exc_info()-style tuple of values into a string.""" return string.join(traceback.format_exception(*err), '') def __repr__(self): return "<%s run=%i errors=%i failures=%i>" % \ (_strclass(self.__class__), self.testsRun, len(self.errors), len(self.failures)) class TestCase: """A class whose instances are single test cases. By default, the test code itself should be placed in a method named 'runTest'. If the fixture may be used for many test cases, create as many test methods as are needed. When instantiating such a TestCase subclass, specify in the constructor arguments the name of the test method that the instance is to execute. Test authors should subclass TestCase for their own tests. Construction and deconstruction of the test's environment ('fixture') can be implemented by overriding the 'setUp' and 'tearDown' methods respectively. If it is necessary to override the __init__ method, the base class __init__ method must always be called. It is important that subclasses should not change the signature of their __init__ method, since instances of the classes are instantiated automatically by parts of the framework in order to be run. """ # This attribute determines which exception will be raised when # the instance's assertion methods fail; test methods raising this # exception will be deemed to have 'failed' rather than 'errored' failureException = AssertionError # test methods raising the following exception will be considered # skipped - this is neither pass, fail, or error. it should be # used when some resource needed to perform the test isn't avialable, # or when a lengthy test is deliberately skipped for time. class skipException(Exception): pass # whether receiving KeyboardInterrupt during setUp or the test causes # the test to be interpreted as skipped. The default is no. It's # probably best to do: # except KeyboardInterrupt: self.skip() # inside the test method interrupt_skips = 0 def __init__(self, methodName='runTest'): """Create an instance of the class that will use the named test method when executed. Raises a ValueError if the instance does not have a method with the specified name. """ try: self._testMethodName = methodName testMethod = getattr(self, methodName) self._testMethodDoc = testMethod.__doc__ except AttributeError: raise ValueError, "no such test method in %s: %s" % \ (self.__class__, methodName) def setUp(self): "Hook method for setting up the test fixture before exercising it." pass def tearDown(self): "Hook method for deconstructing the test fixture after testing it." pass def countTestCases(self): return 1 def defaultTestResult(self): return TestResult() def shortDescription(self): """Returns a one-line description of the test, or None if no description has been provided. The default implementation of this method returns the first line of the specified test method's docstring. """ doc = self._testMethodDoc return doc and string.strip(string.split(doc, "\n")[0]) or None def id(self): return "%s.%s" % (_strclass(self.__class__), self._testMethodName) def __str__(self): return "%s (%s)" % (self._testMethodName, _strclass(self.__class__)) def __repr__(self): return "<%s testMethod=%s>" % \ (_strclass(self.__class__), self._testMethodName) def run(self, result=None): return self(result) def __call__(self, result=None): if result is None: result = self.defaultTestResult() result.startTest(self) testMethod = getattr(self, self._testMethodName) try: try: self.setUp() except KeyboardInterrupt: if self.interrupt_skips: result.addSkip(self, self._exc_info()) return else: raise except self.skipException: result.addSkip(self, self._exc_info()) return except: result.addError(self, self._exc_info()) return ok = 0 try: testMethod() ok = 1 except self.failureException: result.addFailure(self, self._exc_info()) except KeyboardInterrupt: if self.interrupt_skips: result.addSkip(self, self._exc_info()) return else: raise except self.skipException: result.addSkip(self, self._exc_info()) return except: result.addError(self, self._exc_info()) try: self.tearDown() except KeyboardInterrupt: raise except: result.addError(self, self._exc_info()) ok = 0 if ok: result.addSuccess(self) finally: result.stopTest(self) def debug(self): """Run the test without collecting errors in a TestResult""" self.setUp() getattr(self, self._testMethodName)() self.tearDown() def _exc_info(self): """Return a version of sys.exc_info() with the traceback frame minimised; usually the top level of the traceback frame is not needed. """ exctype, excvalue, tb = sys.exc_info() if sys.platform[:4] == 'java': ## tracebacks look different in Jython return (exctype, excvalue, tb) newtb = tb.tb_next if newtb is None: return (exctype, excvalue, tb) return (exctype, excvalue, newtb) def fail(self, msg=None): """Fail immediately, with the given message.""" raise self.failureException, msg def failIf(self, expr, msg=None): "Fail the test if the expression is true." if expr: raise self.failureException, msg def failUnless(self, expr, msg=None): """Fail the test unless the expression is true.""" if not expr: raise self.failureException, msg def failUnlessRaises(self, excClass, callableObj, *args, **kwargs): """Fail unless an exception of class excClass is thrown by callableObj when invoked with arguments args and keyword arguments kwargs. If a different type of exception is thrown, it will not be caught, and the test case will be deemed to have suffered an error, exactly as for an unexpected exception. """ try: callableObj(*args, **kwargs) except excClass: return else: if hasattr(excClass,'__name__'): excName = excClass.__name__ else: excName = str(excClass) raise self.failureException, excName def failUnlessEqual(self, first, second, msg=None): """Fail if the two objects are unequal as determined by the '==' operator. """ if not first == second: raise self.failureException, \ (msg or '%s != %s' % (`first`, `second`)) def failIfEqual(self, first, second, msg=None): """Fail if the two objects are equal as determined by the '==' operator. """ if first == second: raise self.failureException, \ (msg or '%s == %s' % (`first`, `second`)) def failUnlessAlmostEqual(self, first, second, places=7, msg=None): """Fail if the two objects are unequal as determined by their difference rounded to the given number of decimal places (default 7) and comparing to zero. Note that decimal places (from zero) is usually not the same as significant digits (measured from the most signficant digit). """ if round(second-first, places) != 0: raise self.failureException, \ (msg or '%s != %s within %s places' % (`first`, `second`, `places` )) def failIfAlmostEqual(self, first, second, places=7, msg=None): """Fail if the two objects are equal as determined by their difference rounded to the given number of decimal places (default 7) and comparing to zero. Note that decimal places (from zero) is usually not the same as significant digits (measured from the most signficant digit). """ if round(second-first, places) == 0: raise self.failureException, \ (msg or '%s == %s within %s places' % (`first`, `second`, `places`)) assertEqual = assertEquals = failUnlessEqual assertNotEqual = assertNotEquals = failIfEqual assertAlmostEqual = assertAlmostEquals = failUnlessAlmostEqual assertNotAlmostEqual = assertNotAlmostEquals = failIfAlmostEqual assertRaises = failUnlessRaises assert_ = failUnless def skip(self, msg=None): """Skip the test""" raise self.skipException, msg def skipIf(self, expr, msg=None): "Skip the test if the expression is true." if expr: raise self.skipException, msg def skipUnless(self, expr, msg=None): """Skip the test unless the expression is true.""" if not expr: raise self.skipException, msg class TestSuite: """A test suite is a composite test consisting of a number of TestCases. For use, create an instance of TestSuite, then add test case instances. When all tests have been added, the suite can be passed to a test runner, such as TextTestRunner. It will run the individual test cases in the order in which they were added, aggregating the results. When subclassing, do not forget to call the base class constructor. """ def __init__(self, tests=(), description=None): self._tests = [] self.addTests(tests) self.description = description or '(no description)' def __repr__(self): return "<%s tests=%s>" % (_strclass(self.__class__), self._tests) __str__ = __repr__ def shortDescription(self): return self.description def setDescription(self, description): self.description = description def countTestCases(self): cases = 0 for test in self._tests: cases = cases + test.countTestCases() return cases def addTest(self, test): self._tests.append(test) def addTests(self, tests): for test in tests: self.addTest(test) def run(self, result): return self(result) def __call__(self, result): try: result.startSuite(self) except AttributeError: pass for test in self._tests: if result.shouldStop: break test(result) try: result.endSuite(self) except AttributeError: pass return result def debug(self): """Run the tests without collecting errors in a TestResult""" for test in self._tests: test.debug() class FunctionTestCase(TestCase): """A test case that wraps a test function. This is useful for slipping pre-existing test functions into the PyUnit framework. Optionally, set-up and tidy-up functions can be supplied. As with TestCase, the tidy-up ('tearDown') function will always be called if the set-up ('setUp') function ran successfully. """ def __init__(self, testFunc, setUp=None, tearDown=None, description=None): TestCase.__init__(self) self._setUpFunc = setUp self._tearDownFunc = tearDown self._testFunc = testFunc self._description = description def setUp(self): if self._setUpFunc is not None: self._setUpFunc() def tearDown(self): if self._tearDownFunc is not None: self._tearDownFunc() def runTest(self): self._testFunc() def id(self): return self._testFunc.__name__ def __str__(self): return "%s (%s)" % (_strclass(self.__class__), self._testFunc.__name__) def __repr__(self): return "<%s testFunc=%s>" % (_strclass(self.__class__), self._testFunc) def shortDescription(self): if self._description is not None: return self._description doc = self._testFunc.__doc__ return doc and string.strip(string.split(doc, "\n")[0]) or None ############################################################################## # Locating and loading tests ############################################################################## class TestLoader: """This class is responsible for loading tests according to various criteria and returning them wrapped in a Test """ testMethodPrefix = 'test' sortTestMethodsUsing = cmp suiteClass = TestSuite def loadTestsFromTestCase(self, testCaseClass): """Return a suite of all tests cases contained in testCaseClass""" name_list = self.getTestCaseNames(testCaseClass) instance_list = map(testCaseClass, name_list) description = getattr(testCaseClass, '__doc__') \ or testCaseClass.__name__ description = (description.splitlines()[0]).strip() suite = self.suiteClass(instance_list, description) return suite def loadTestsFromModule(self, module): """Return a suite of all tests cases contained in the given module""" tests = [] for name in dir(module): obj = getattr(module, name) if (isinstance(obj, (type, types.ClassType)) and issubclass(obj, TestCase) and not obj in [TestCase, FunctionTestCase]): tests.append(self.loadTestsFromTestCase(obj)) description = getattr(module, '__doc__') \ or module.__name__ description = (description.splitlines()[0]).strip() return self.suiteClass(tests, description) def loadTestsFromName(self, name, module=None): """Return a suite of all tests cases given a string specifier. The name may resolve either to a module, a test case class, a test method within a test case class, or a callable object which returns a TestCase or TestSuite instance. The method optionally resolves the names relative to a given module. """ parts = string.split(name, '.') if module is None: if not parts: raise ValueError, "incomplete test name: %s" % name else: parts_copy = parts[:] while parts_copy: try: module = __import__(string.join(parts_copy,'.')) break except ImportError: del parts_copy[-1] if not parts_copy: raise parts = parts[1:] obj = module for part in parts: obj = getattr(obj, part) import unittest if type(obj) == types.ModuleType: return self.loadTestsFromModule(obj) elif (isinstance(obj, (type, types.ClassType)) and issubclass(obj, unittest.TestCase)): return self.loadTestsFromTestCase(obj) elif type(obj) == types.UnboundMethodType: return obj.im_class(obj.__name__) elif callable(obj): test = obj() if not isinstance(test, unittest.TestCase) and \ not isinstance(test, unittest.TestSuite): raise ValueError, \ "calling %s returned %s, not a test" % (obj,test) return test else: raise ValueError, "don't know how to make test from: %s" % obj def loadTestsFromNames(self, names, module=None): """Return a suite of all tests cases found using the given sequence of string specifiers. See 'loadTestsFromName()'. """ suites = [] for name in names: suites.append(self.loadTestsFromName(name, module)) return self.suiteClass(suites) def getTestCaseNames(self, testCaseClass): """Return a sorted sequence of method names found within testCaseClass """ testFnNames = filter(lambda n,p=self.testMethodPrefix: n[:len(p)] == p, dir(testCaseClass)) for baseclass in testCaseClass.__bases__: for testFnName in self.getTestCaseNames(baseclass): if testFnName not in testFnNames: # handle overridden methods testFnNames.append(testFnName) if self.sortTestMethodsUsing: testFnNames.sort(self.sortTestMethodsUsing) return testFnNames defaultTestLoader = TestLoader() ############################################################################## # Patches for old functions: these functions should be considered obsolete ############################################################################## def _makeLoader(prefix, sortUsing, suiteClass=None): loader = TestLoader() loader.sortTestMethodsUsing = sortUsing loader.testMethodPrefix = prefix if suiteClass: loader.suiteClass = suiteClass return loader def getTestCaseNames(testCaseClass, prefix, sortUsing=cmp): return _makeLoader(prefix, sortUsing).getTestCaseNames(testCaseClass) def makeSuite(testCaseClass, prefix='test', sortUsing=cmp, suiteClass=TestSuite): return _makeLoader(prefix, sortUsing, suiteClass).loadTestsFromTestCase(testCaseClass) def findTestCases(module, prefix='test', sortUsing=cmp, suiteClass=TestSuite): return _makeLoader(prefix, sortUsing, suiteClass).loadTestsFromModule(module) ############################################################################## # Text UI ############################################################################## class _WritelnDecorator: """Used to decorate file-like objects with a handy 'writeln' method""" def __init__(self,stream): self.stream = stream def __getattr__(self, attr): return getattr(self.stream,attr) def write(self, arg): self.stream.write(arg) self.stream.flush() def writeln(self, arg=None): if arg: self.write(arg) self.write('\n') # text-mode streams translate to \r\n if needed class _TextTestResult(TestResult): """A test result class that can print formatted text results to a stream. Used by TextTestRunner. """ separator1 = '=' * 79 separator2 = '-' * 79 def __init__(self, stream, descriptions, verbosity): TestResult.__init__(self) self.stream = stream self.showAll = verbosity > 1 self.dots = verbosity == 1 self.descriptions = descriptions if descriptions: self.indent = ' ' else: self.indent = '' self.depth = 0 self.width = 80 def getDescription(self, test): if self.descriptions: return test.shortDescription() or str(test) else: return str(test) def startSuite(self, suite): if self.showAll and self.descriptions: self.stream.write(self.indent * self.depth) try: desc = self.getDescription(suite) except AttributeError: desc = '(no description)' self.stream.writeln(desc) self.depth += 1 def startTest(self, test): TestResult.startTest(self, test) if self.showAll: self.stream.write(self.indent * self.depth) d = self.getDescription(test) dwidth = self.width - len(self.indent) * self.depth - 11 format = "%%-%is" % dwidth self.stream.write(format % d) self.stream.write(" ... ") def addSuccess(self, test): TestResult.addSuccess(self, test) if self.showAll: self.stream.writeln("ok") elif self.dots: self.stream.write('.') def addError(self, test, err): TestResult.addError(self, test, err) if self.showAll: self.stream.writeln("ERROR") elif self.dots: self.stream.write('E') def addFailure(self, test, err): TestResult.addFailure(self, test, err) if self.showAll: self.stream.writeln("FAIL") elif self.dots: self.stream.write('F') def addSkip(self, test, err): TestResult.addSkip(self, test, err) if self.showAll: self.stream.writeln("skip") elif self.dots: self.stream.write('s') def endSuite(self, suite): self.depth -= 1 def printErrors(self): if self.dots or self.showAll: self.stream.writeln() self.printErrorList('ERROR', self.errors) self.printErrorList('FAIL', self.failures) def printErrorList(self, flavour, errors): for test, err in errors: self.stream.writeln(self.separator1) self.stream.writeln("%s: %s" % (flavour,self.getDescription(test))) self.stream.writeln(self.separator2) self.stream.writeln("%s" % err) class TextTestRunner: """A test runner class that displays results in textual form. It prints out the names of tests as they are run, errors as they occur, and a summary of the results at the end of the test run. """ def __init__(self, stream=sys.stderr, descriptions=1, verbosity=1): self.stream = _WritelnDecorator(stream) self.descriptions = descriptions self.verbosity = verbosity def _makeResult(self): return _TextTestResult(self.stream, self.descriptions, self.verbosity) def run(self, test): "Run the given test case or test suite." result = self._makeResult() startTime = time.time() test(result) stopTime = time.time() timeTaken = float(stopTime - startTime) result.printErrors() self.stream.writeln(result.separator2) run = result.testsRun self.stream.writeln("Ran %d test%s in %.3fs" % (run, run != 1 and "s" or "", timeTaken)) self.stream.writeln() if not result.wasSuccessful(): self.stream.write("FAILED (") failed, errored, skipped = map(len, \ (result.failures, result.errors, result.skipped)) if failed: self.stream.write("failures=%d" % failed) if errored: if failed: self.stream.write(", ") self.stream.write("errors=%d" % errored) if skipped: self.stream.write(", skipped=%d" % skipped) self.stream.writeln(")") else: if result.skipped: self.stream.writeln("OK (skipped=%d)" % len(result.skipped)) else: self.stream.writeln("OK") return result ############################################################################## # Facilities for running tests from the command line ############################################################################## class TestProgram: """A command-line program that runs a set of tests; this is primarily for making test modules conveniently executable. """ USAGE = """\ Usage: %(progName)s [options] [test] [...] Options: -h, --help Show this message -v, --verbose Verbose output -q, --quiet Minimal output Examples: %(progName)s - run default set of tests %(progName)s MyTestSuite - run suite 'MyTestSuite' %(progName)s MyTestCase.testSomething - run MyTestCase.testSomething %(progName)s MyTestCase - run all 'test*' test methods in MyTestCase """ def __init__(self, module='__main__', defaultTest=None, argv=None, testRunner=None, testLoader=defaultTestLoader): if type(module) == type(''): self.module = __import__(module) for part in string.split(module,'.')[1:]: self.module = getattr(self.module, part) else: self.module = module if argv is None: argv = sys.argv self.verbosity = 1 self.defaultTest = defaultTest self.testRunner = testRunner self.testLoader = testLoader self.progName = os.path.basename(argv[0]) self.parseArgs(argv) self.runTests() def usageExit(self, msg=None): if msg: print msg print self.USAGE % self.__dict__ sys.exit(2) def parseArgs(self, argv): import getopt try: options, args = getopt.getopt(argv[1:], 'hHvq', ['help','verbose','quiet']) for opt, value in options: if opt in ('-h','-H','--help'): self.usageExit() if opt in ('-q','--quiet'): self.verbosity = 0 if opt in ('-v','--verbose'): self.verbosity = 2 if len(args) == 0 and self.defaultTest is None: self.test = self.testLoader.loadTestsFromModule(self.module) return if len(args) > 0: self.testNames = args else: self.testNames = (self.defaultTest,) self.createTests() except getopt.error, msg: self.usageExit(msg) def createTests(self): self.test = self.testLoader.loadTestsFromNames(self.testNames, self.module) def runTests(self): if self.testRunner is None: self.testRunner = TextTestRunner(verbosity=self.verbosity) result = self.testRunner.run(self.test) sys.exit(not result.wasSuccessful()) main = TestProgram ############################################################################## # Executing this module from the command line ############################################################################## if __name__ == "__main__": main(module=None) urlgrabber-3.9.1/test/grabberperf.py0000664000076400007640000001064711150613414017357 0ustar skvidalskvidal#!/usr/bin/python -t # This library is free software; you can redistribute it and/or # modify it under the terms of the GNU Lesser General Public # License as published by the Free Software Foundation; either # version 2.1 of the License, or (at your option) any later version. # # This library is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU # Lesser General Public License for more details. # # You should have received a copy of the GNU Lesser General Public # License along with this library; if not, write to the # Free Software Foundation, Inc., # 59 Temple Place, Suite 330, # Boston, MA 02111-1307 USA # This file is part of urlgrabber, a high-level cross-protocol url-grabber # Copyright 2002-2004 Michael D. Stenner, Ryan Tomayko import sys import os from os.path import dirname, join as joinpath import tempfile import time import urlgrabber.grabber as grabber from urlgrabber.grabber import URLGrabber, urlgrab, urlopen, urlread from urlgrabber.progress import text_progress_meter tempsrc = '/tmp/ug-test-src' tempdst = '/tmp/ug-test-dst' # this isn't used but forces a proxy handler to be # added when creating the urllib2 opener. proxies = { 'http' : 'http://localhost' } DEBUG=0 def main(): speedtest(1024) # 1KB speedtest(10 * 1024) # 10 KB speedtest(100 * 1024) # 100 KB speedtest(1000 * 1024) # 1,000 KB (almost 1MB) #speedtest(10000 * 1024) # 10,000 KB (almost 10MB) # remove temp files os.unlink(tempsrc) os.unlink(tempdst) def setuptemp(size): if DEBUG: print 'writing %d KB to temporary file (%s).' % (size / 1024, tempsrc) file = open(tempsrc, 'w', 1024) chars = '0123456789' for i in range(size): file.write(chars[i % 10]) file.flush() file.close() def speedtest(size): setuptemp(size) full_times = [] raw_times = [] none_times = [] throttle = 2**40 # throttle to 1 TB/s :) try: from urlgrabber.progress import text_progress_meter except ImportError, e: tpm = None print 'not using progress meter' else: tpm = text_progress_meter(fo=open('/dev/null', 'w')) # to address concerns that the overhead from the progress meter # and throttling slow things down, we do this little test. # # using this test, you get the FULL overhead of the progress # meter and throttling, without the benefit: the meter is directed # to /dev/null and the throttle bandwidth is set EXTREMELY high. # # note: it _is_ even slower to direct the progress meter to a real # tty or file, but I'm just interested in the overhead from _this_ # module. # get it nicely cached before we start comparing if DEBUG: print 'pre-caching' for i in range(100): urlgrab(tempsrc, tempdst, copy_local=1, throttle=None, proxies=proxies) if DEBUG: print 'running speed test.' reps = 500 for i in range(reps): if DEBUG: print '\r%4i/%-4i' % (i+1, reps), sys.stdout.flush() t = time.time() urlgrab(tempsrc, tempdst, copy_local=1, progress_obj=tpm, throttle=throttle, proxies=proxies) full_times.append(1000 * (time.time() - t)) t = time.time() urlgrab(tempsrc, tempdst, copy_local=1, progress_obj=None, throttle=None, proxies=proxies) raw_times.append(1000 * (time.time() - t)) t = time.time() in_fo = open(tempsrc) out_fo = open(tempdst, 'wb') while 1: s = in_fo.read(1024 * 8) if not s: break out_fo.write(s) in_fo.close() out_fo.close() none_times.append(1000 * (time.time() - t)) if DEBUG: print '\r' print "%d KB Results:" % (size / 1024) print_result('full', full_times) print_result('raw', raw_times) print_result('none', none_times) def print_result(label, result_list): format = '[%4s] mean: %6.3f ms, median: %6.3f ms, ' \ 'min: %6.3f ms, max: %6.3f ms' result_list.sort() mean = 0.0 for i in result_list: mean += i mean = mean/len(result_list) median = result_list[int(len(result_list)/2)] print format % (label, mean, median, result_list[0], result_list[-1]) if __name__ == '__main__': main() urlgrabber-3.9.1/test/test_mirror.py0000664000076400007640000002306611150613414017446 0ustar skvidalskvidal#!/usr/bin/python -t # This library is free software; you can redistribute it and/or # modify it under the terms of the GNU Lesser General Public # License as published by the Free Software Foundation; either # version 2.1 of the License, or (at your option) any later version. # # This library is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU # Lesser General Public License for more details. # # You should have received a copy of the GNU Lesser General Public # License along with this library; if not, write to the # Free Software Foundation, Inc., # 59 Temple Place, Suite 330, # Boston, MA 02111-1307 USA # This file is part of urlgrabber, a high-level cross-protocol url-grabber # Copyright 2002-2004 Michael D. Stenner, Ryan Tomayko """mirror.py tests""" # $Id: test_mirror.py,v 1.12 2005/10/22 21:57:27 mstenner Exp $ import sys import os import string, tempfile, random, cStringIO, os import urlgrabber.grabber from urlgrabber.grabber import URLGrabber, URLGrabError import urlgrabber.mirror from urlgrabber.mirror import MirrorGroup, MGRandomStart, MGRandomOrder from base_test_code import * class FakeLogger: def __init__(self): self.logs = [] def debug(self, msg, *args): self.logs.append(msg % args) warn = warning = info = error = debug class BasicTests(TestCase): def setUp(self): self.g = URLGrabber() fullmirrors = [base_mirror_url + m + '/' for m in good_mirrors] self.mg = MirrorGroup(self.g, fullmirrors) def test_urlgrab(self): """MirrorGroup.urlgrab""" filename = tempfile.mktemp() url = 'short_reference' self.mg.urlgrab(url, filename) fo = open(filename) data = fo.read() fo.close() self.assertEqual(data, short_reference_data) def test_urlread(self): """MirrorGroup.urlread""" url = 'short_reference' data = self.mg.urlread(url) self.assertEqual(data, short_reference_data) def test_urlopen(self): """MirrorGroup.urlopen""" url = 'short_reference' fo = self.mg.urlopen(url) data = fo.read() fo.close() self.assertEqual(data, short_reference_data) class SubclassTests(TestCase): def setUp(self): self.g = URLGrabber() self.fullmirrors = [base_mirror_url + m + '/' for m in good_mirrors] def fetchwith(self, mgclass): self.mg = mgclass(self.g, self.fullmirrors) filename = tempfile.mktemp() url = 'short_reference' self.mg.urlgrab(url, filename) fo = open(filename) data = fo.read() fo.close() self.assertEqual(data, short_reference_data) def test_MGRandomStart(self): "MGRandomStart.urlgrab" self.fetchwith(MGRandomStart) def test_MGRandomOrder(self): "MGRandomOrder.urlgrab" self.fetchwith(MGRandomOrder) class CallbackTests(TestCase): def setUp(self): self.g = URLGrabber() fullmirrors = [base_mirror_url + m + '/' for m in \ (bad_mirrors + good_mirrors)] self.mg = MirrorGroup(self.g, fullmirrors) def test_failure_callback(self): "test that MG executes the failure callback correctly" tricky_list = [] def failure_callback(cb_obj, tl): tl.append(str(cb_obj.exception)) self.mg.failure_callback = failure_callback, (tricky_list, ), {} data = self.mg.urlread('reference') self.assert_(data == reference_data) self.assertEquals(tricky_list[0][:25], '[Errno 14] HTTP Error 403') def test_callback_reraise(self): "test that the callback can correctly re-raise the exception" def failure_callback(cb_obj): raise cb_obj.exception self.mg.failure_callback = failure_callback self.assertRaises(URLGrabError, self.mg.urlread, 'reference') class BadMirrorTests(TestCase): def setUp(self): self.g = URLGrabber() fullmirrors = [base_mirror_url + m + '/' for m in bad_mirrors] self.mg = MirrorGroup(self.g, fullmirrors) def test_simple_grab(self): """test that a bad mirror raises URLGrabError""" filename = tempfile.mktemp() url = 'reference' self.assertRaises(URLGrabError, self.mg.urlgrab, url, filename) class FailoverTests(TestCase): def setUp(self): self.g = URLGrabber() fullmirrors = [base_mirror_url + m + '/' for m in \ (bad_mirrors + good_mirrors)] self.mg = MirrorGroup(self.g, fullmirrors) def test_simple_grab(self): """test that a the MG fails over past a bad mirror""" filename = tempfile.mktemp() url = 'reference' elist = [] def cb(e, elist=elist): elist.append(e) self.mg.urlgrab(url, filename, failure_callback=cb) fo = open(filename) contents = fo.read() fo.close() # first be sure that the first mirror failed and that the # callback was called self.assertEqual(len(elist), 1) # now be sure that the second mirror succeeded and the correct # data was returned self.assertEqual(contents, reference_data) class FakeGrabber: def __init__(self, resultlist=None): self.resultlist = resultlist or [] self.index = 0 self.calls = [] def urlgrab(self, url, filename=None, **kwargs): self.calls.append( (url, filename) ) res = self.resultlist[self.index] self.index += 1 if isinstance(res, Exception): raise res else: return res class ActionTests(TestCase): def setUp(self): self.snarfed_logs = [] self.db = urlgrabber.mirror.DEBUG urlgrabber.mirror.DEBUG = FakeLogger() self.mirrors = ['a', 'b', 'c', 'd', 'e', 'f'] self.g = FakeGrabber([URLGrabError(3), URLGrabError(3), 'filename']) self.mg = MirrorGroup(self.g, self.mirrors) def tearDown(self): urlgrabber.mirror.DEBUG = self.db def test_defaults(self): 'test default action policy' self.mg.urlgrab('somefile') expected_calls = [ (m + '/' + 'somefile', None) \ for m in self.mirrors[:3] ] expected_logs = \ ['MIRROR: trying somefile -> a/somefile', 'MIRROR: failed', 'GR mirrors: [b c d e f] 0', 'MAIN mirrors: [a b c d e f] 1', 'MIRROR: trying somefile -> b/somefile', 'MIRROR: failed', 'GR mirrors: [c d e f] 0', 'MAIN mirrors: [a b c d e f] 2', 'MIRROR: trying somefile -> c/somefile'] self.assertEquals(self.g.calls, expected_calls) self.assertEquals(urlgrabber.mirror.DEBUG.logs, expected_logs) def test_instance_action(self): 'test the effects of passed-in default_action' self.mg.default_action = {'remove_master': 1} self.mg.urlgrab('somefile') expected_calls = [ (m + '/' + 'somefile', None) \ for m in self.mirrors[:3] ] expected_logs = \ ['MIRROR: trying somefile -> a/somefile', 'MIRROR: failed', 'GR mirrors: [b c d e f] 0', 'MAIN mirrors: [b c d e f] 0', 'MIRROR: trying somefile -> b/somefile', 'MIRROR: failed', 'GR mirrors: [c d e f] 0', 'MAIN mirrors: [c d e f] 0', 'MIRROR: trying somefile -> c/somefile'] self.assertEquals(self.g.calls, expected_calls) self.assertEquals(urlgrabber.mirror.DEBUG.logs, expected_logs) def test_method_action(self): 'test the effects of method-level default_action' self.mg.urlgrab('somefile', default_action={'remove_master': 1}) expected_calls = [ (m + '/' + 'somefile', None) \ for m in self.mirrors[:3] ] expected_logs = \ ['MIRROR: trying somefile -> a/somefile', 'MIRROR: failed', 'GR mirrors: [b c d e f] 0', 'MAIN mirrors: [b c d e f] 0', 'MIRROR: trying somefile -> b/somefile', 'MIRROR: failed', 'GR mirrors: [c d e f] 0', 'MAIN mirrors: [c d e f] 0', 'MIRROR: trying somefile -> c/somefile'] self.assertEquals(self.g.calls, expected_calls) self.assertEquals(urlgrabber.mirror.DEBUG.logs, expected_logs) def callback(self, e): return {'fail': 1} def test_callback_action(self): 'test the effects of a callback-returned action' self.assertRaises(URLGrabError, self.mg.urlgrab, 'somefile', failure_callback=self.callback) expected_calls = [ (m + '/' + 'somefile', None) \ for m in self.mirrors[:1] ] expected_logs = \ ['MIRROR: trying somefile -> a/somefile', 'MIRROR: failed', 'GR mirrors: [b c d e f] 0', 'MAIN mirrors: [a b c d e f] 1'] self.assertEquals(self.g.calls, expected_calls) self.assertEquals(urlgrabber.mirror.DEBUG.logs, expected_logs) def suite(): tl = TestLoader() return tl.loadTestsFromModule(sys.modules[__name__]) if __name__ == '__main__': runner = TextTestRunner(stream=sys.stdout,descriptions=1,verbosity=2) runner.run(suite()) urlgrabber-3.9.1/test/runtests.py0000664000076400007640000000360411257164072016771 0ustar skvidalskvidal#!/usr/bin/python """Usage: python runtests.py [OPTIONS] Quick script to run all unit tests from source directory (e.g. without having to install.) OPTIONS: -d, --descriptions=NUM Set to 0 to turn off printing test doc strings as descriptions. -v, --verbosity=NUM Output verbosity level. Defaults to 2 which is one line of info per test. Set to 1 to get one char of info per test or 0 to disable status output completely. """ # $Id: runtests.py,v 1.7 2004/03/31 17:02:00 mstenner Exp $ import sys from os.path import dirname, join as joinpath from getopt import getopt from base_test_code import * def main(): # setup sys.path so that we can run this from the source # directory. (descriptions, verbosity) = parse_args() dn = dirname(sys.argv[0]) sys.path.insert(0, joinpath(dn,'..')) sys.path.insert(0, dn) # it's okay to import now that sys.path is setup. import test_grabber, test_byterange, test_mirror suite = TestSuite( (test_grabber.suite(), test_byterange.suite(), test_mirror.suite()) ) suite.description = 'urlgrabber tests' runner = TextTestRunner(stream=sys.stdout, descriptions=descriptions, verbosity=verbosity) runner.run(suite) def parse_args(): descriptions = 1 verbosity = 2 opts, args = getopt(sys.argv[1:],'hd:v:',['descriptions=','help','verbosity=']) for o,a in opts: if o in ('-h', '--help'): usage() sys.exit(0) elif o in ('-d', '--descriptions'): descriptions = int(a) elif o in ('-v', '--verbosity'): verbosity = int(a) return (descriptions,verbosity) def usage(): print __doc__ if __name__ == '__main__': main() urlgrabber-3.9.1/test/threading/0000775000076400007640000000000011257176250016473 5ustar skvidalskvidalurlgrabber-3.9.1/test/threading/batchgrabber.py0000664000076400007640000000722611150613414021450 0ustar skvidalskvidal# This library is free software; you can redistribute it and/or # modify it under the terms of the GNU Lesser General Public # License as published by the Free Software Foundation; either # version 2.1 of the License, or (at your option) any later version. # # This library is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU # Lesser General Public License for more details. # # You should have received a copy of the GNU Lesser General Public # License along with this library; if not, write to the # Free Software Foundation, Inc., # 59 Temple Place, Suite 330, # Boston, MA 02111-1307 USA # This file is part of urlgrabber, a high-level cross-protocol url-grabber # Copyright 2002-2004 Michael D. Stenner, Ryan Tomayko """Module for testing urlgrabber under multiple threads. This module can be used from the command line. Each argument is a URL to grab. The BatchURLGrabber class has an interface similar to URLGrabber but instead of pulling files when urlgrab is called, the request is queued. Calling BatchURLGrabber.batchgrab causes all files to be pulled in multiple threads. """ import os.path, sys if __name__ == '__main__': print os.path.dirname(sys.argv[0]) sys.path.insert(0, (os.path.dirname(sys.argv[0]) or '.') + '/../..') from threading import Thread, Semaphore from urlgrabber.grabber import URLGrabber, URLGrabError from urlgrabber.progress import MultiFileMeter, TextMultiFileMeter from time import sleep, time DEBUG=0 class BatchURLGrabber: def __init__(self, maxthreads=5, **kwargs): self.maxthreads = 5 self.grabber = URLGrabber(**kwargs) self.queue = [] self.threads = [] self.sem = Semaphore() def urlgrab(self, url, filename=None, **kwargs): self.queue.append( (url, filename, kwargs) ) def batchgrab(self): if hasattr(self.grabber.opts.progress_obj, 'start'): self.grabber.opts.progress_obj.start(len(self.queue)) while self.queue or self.threads: if self.queue and (len(self.threads) < self.maxthreads): url, filename, kwargs = self.queue[0] del self.queue[0] thread = Worker(self, url, filename, kwargs) self.threads.append(thread) if DEBUG: print "starting worker: " + url thread.start() else: for t in self.threads: if not t.isAlive(): if DEBUG: print "cleaning up worker: " + t.url self.threads.remove(t) #if len(self.threads) == self.maxthreads: # sleep(0.2) sleep(0.2) class Worker(Thread): def __init__(self, parent, url, filename, kwargs): Thread.__init__(self) self.parent = parent self.url = url self.filename = filename self.kwargs = kwargs def run(self): if DEBUG: print "worker thread started." grabber = self.parent.grabber progress_obj = grabber.opts.progress_obj if isinstance(progress_obj, MultiFileMeter): self.kwargs['progress_obj'] = progress_obj.newMeter() try: rslt = self.parent.grabber.urlgrab(self.url, self.filename, **self.kwargs) except URLGrabError, e: print '%s, %s' % (e, self.url) def main(): progress_obj = None # uncomment to play with BatchProgressMeter (doesn't work right now) # progress_obj = TextMultiFileMeter() g = BatchURLGrabber(keepalive=1, progress_obj=progress_obj) for arg in sys.argv[1:]: g.urlgrab(arg) if DEBUG: print "before batchgrab" try: g.batchgrab() except KeyboardInterrupt: sys.exit(1) if DEBUG: print "after batchgrab" if __name__ == '__main__': main() urlgrabber-3.9.1/test/base_test_code.py0000664000076400007640000000204311150613414020030 0ustar skvidalskvidalfrom munittest import * base_http = 'http://www.linux.duke.edu/projects/urlgrabber/test/' base_ftp = 'ftp://localhost/test/' # set to a proftp server only. we're working around a couple of # bugs in their implementation in byterange.py. base_proftp = 'ftp://localhost/test/' reference_data = ''.join( [str(i)+'\n' for i in range(20000) ] ) ref_http = base_http + 'reference' ref_ftp = base_ftp + 'reference' ref_proftp = base_proftp + 'reference' short_reference_data = ' '.join( [str(i) for i in range(10) ] ) short_ref_http = base_http + 'short_reference' short_ref_ftp = base_ftp + 'short_reference' ref_200 = ref_http ref_404 = base_http + 'nonexistent_file' ref_403 = base_http + 'mirror/broken/' base_mirror_url = base_http + 'mirror/' good_mirrors = ['m1', 'm2', 'm3'] mirror_files = ['test1.txt', 'test2.txt'] bad_mirrors = ['broken'] bad_mirror_files = ['broken.txt'] proxy_proto = 'http' proxy_host = 'localhost' proxy_port = 8888 proxy_user = 'proxyuser' good_proxy_pass = 'proxypass' bad_proxy_pass = 'badproxypass' urlgrabber-3.9.1/setup.py0000664000076400007640000000312011150613414015243 0ustar skvidalskvidal# urlgrabber distutils setup import re as _re import urlgrabber as _urlgrabber name = "urlgrabber" description = "A high-level cross-protocol url-grabber" long_description = _urlgrabber.__doc__ license = "LGPL" version = _urlgrabber.__version__ _authors = _re.split(r',\s+', _urlgrabber.__author__) author = ', '.join([_re.sub(r'\s+<.*', r'', _) for _ in _authors]) author_email = ', '.join([_re.sub(r'(^.*<)|(>.*$)', r'', _) for _ in _authors]) url = _urlgrabber.__url__ packages = ['urlgrabber'] package_dir = {'urlgrabber':'urlgrabber'} scripts = ['scripts/urlgrabber'] data_files = [('share/doc/' + name + '-' + version, ['README','LICENSE', 'TODO', 'ChangeLog'])] options = { 'clean' : { 'all' : 1 } } classifiers = [ 'Development Status :: 4 - Beta', 'Environment :: Console', 'Environment :: Web Environment', 'Intended Audience :: Developers', 'Intended Audience :: System Administrators', 'License :: OSI Approved :: GNU Library or Lesser General Public License (LGPL)', 'Operating System :: POSIX', 'Operating System :: POSIX :: Linux', 'Programming Language :: Python', 'Topic :: Internet :: File Transfer Protocol (FTP)', 'Topic :: Internet :: WWW/HTTP', 'Topic :: Software Development :: Libraries :: Python Modules' ] # load up distutils if __name__ == '__main__': config = globals().copy() keys = config.keys() for k in keys: #print '%-20s -> %s' % (k, config[k]) if k.startswith('_'): del config[k] from distutils.core import setup setup(**config) urlgrabber-3.9.1/MANIFEST0000664000076400007640000000055211257176250014702 0ustar skvidalskvidalChangeLog LICENSE MANIFEST README TODO makefile setup.py scripts/urlgrabber test/base_test_code.py test/grabberperf.py test/munittest.py test/runtests.py test/test_byterange.py test/test_grabber.py test/test_mirror.py test/threading/batchgrabber.py urlgrabber/__init__.py urlgrabber/byterange.py urlgrabber/grabber.py urlgrabber/mirror.py urlgrabber/progress.py urlgrabber-3.9.1/LICENSE0000664000076400007640000005750511150613414014556 0ustar skvidalskvidal GNU LESSER GENERAL PUBLIC LICENSE Version 2.1, February 1999 Copyright (C) 1991, 1999 Free Software Foundation, Inc. 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA Everyone is permitted to copy and distribute verbatim copies of this license document, but changing it is not allowed. [This is the first released version of the Lesser GPL. It also counts as the successor of the GNU Library Public License, version 2, hence the version number 2.1.] Preamble The licenses for most software are designed to take away your freedom to share and change it. By contrast, the GNU General Public Licenses are intended to guarantee your freedom to share and change free software--to make sure the software is free for all its users. This license, the Lesser General Public License, applies to some specially designated software packages--typically libraries--of the Free Software Foundation and other authors who decide to use it. You can use it too, but we suggest you first think carefully about whether this license or the ordinary General Public License is the better strategy to use in any particular case, based on the explanations below. When we speak of free software, we are referring to freedom of use, not price. Our General Public Licenses are designed to make sure that you have the freedom to distribute copies of free software (and charge for this service if you wish); that you receive source code or can get it if you want it; that you can change the software and use pieces of it in new free programs; and that you are informed that you can do these things. To protect your rights, we need to make restrictions that forbid distributors to deny you these rights or to ask you to surrender these rights. These restrictions translate to certain responsibilities for you if you distribute copies of the library or if you modify it. For example, if you distribute copies of the library, whether gratis or for a fee, you must give the recipients all the rights that we gave you. You must make sure that they, too, receive or can get the source code. If you link other code with the library, you must provide complete object files to the recipients, so that they can relink them with the library after making changes to the library and recompiling it. And you must show them these terms so they know their rights. We protect your rights with a two-step method: (1) we copyright the library, and (2) we offer you this license, which gives you legal permission to copy, distribute and/or modify the library. To protect each distributor, we want to make it very clear that there is no warranty for the free library. Also, if the library is modified by someone else and passed on, the recipients should know that what they have is not the original version, so that the original author's reputation will not be affected by problems that might be introduced by others. Finally, software patents pose a constant threat to the existence of any free program. We wish to make sure that a company cannot effectively restrict the users of a free program by obtaining a restrictive license from a patent holder. Therefore, we insist that any patent license obtained for a version of the library must be consistent with the full freedom of use specified in this license. Most GNU software, including some libraries, is covered by the ordinary GNU General Public License. This license, the GNU Lesser General Public License, applies to certain designated libraries, and is quite different from the ordinary General Public License. We use this license for certain libraries in order to permit linking those libraries into non-free programs. When a program is linked with a library, whether statically or using a shared library, the combination of the two is legally speaking a combined work, a derivative of the original library. The ordinary General Public License therefore permits such linking only if the entire combination fits its criteria of freedom. The Lesser General Public License permits more lax criteria for linking other code with the library. We call this license the "Lesser" General Public License because it does Less to protect the user's freedom than the ordinary General Public License. It also provides other free software developers Less of an advantage over competing non-free programs. These disadvantages are the reason we use the ordinary General Public License for many libraries. However, the Lesser license provides advantages in certain special circumstances. For example, on rare occasions, there may be a special need to encourage the widest possible use of a certain library, so that it becomes a de-facto standard. To achieve this, non-free programs must be allowed to use the library. A more frequent case is that a free library does the same job as widely used non-free libraries. In this case, there is little to gain by limiting the free library to free software only, so we use the Lesser General Public License. In other cases, permission to use a particular library in non-free programs enables a greater number of people to use a large body of free software. For example, permission to use the GNU C Library in non-free programs enables many more people to use the whole GNU operating system, as well as its variant, the GNU/Linux operating system. Although the Lesser General Public License is Less protective of the users' freedom, it does ensure that the user of a program that is linked with the Library has the freedom and the wherewithal to run that program using a modified version of the Library. The precise terms and conditions for copying, distribution and modification follow. Pay close attention to the difference between a "work based on the library" and a "work that uses the library". The former contains code derived from the library, whereas the latter must be combined with the library in order to run. GNU LESSER GENERAL PUBLIC LICENSE TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION 0. This License Agreement applies to any software library or other program which contains a notice placed by the copyright holder or other authorized party saying it may be distributed under the terms of this Lesser General Public License (also called "this License"). Each licensee is addressed as "you". A "library" means a collection of software functions and/or data prepared so as to be conveniently linked with application programs (which use some of those functions and data) to form executables. The "Library", below, refers to any such software library or work which has been distributed under these terms. A "work based on the Library" means either the Library or any derivative work under copyright law: that is to say, a work containing the Library or a portion of it, either verbatim or with modifications and/or translated straightforwardly into another language. (Hereinafter, translation is included without limitation in the term "modification".) "Source code" for a work means the preferred form of the work for making modifications to it. For a library, complete source code means all the source code for all modules it contains, plus any associated interface definition files, plus the scripts used to control compilation and installation of the library. Activities other than copying, distribution and modification are not covered by this License; they are outside its scope. The act of running a program using the Library is not restricted, and output from such a program is covered only if its contents constitute a work based on the Library (independent of the use of the Library in a tool for writing it). Whether that is true depends on what the Library does and what the program that uses the Library does. 1. You may copy and distribute verbatim copies of the Library's complete source code as you receive it, in any medium, provided that you conspicuously and appropriately publish on each copy an appropriate copyright notice and disclaimer of warranty; keep intact all the notices that refer to this License and to the absence of any warranty; and distribute a copy of this License along with the Library. You may charge a fee for the physical act of transferring a copy, and you may at your option offer warranty protection in exchange for a fee. 2. You may modify your copy or copies of the Library or any portion of it, thus forming a work based on the Library, and copy and distribute such modifications or work under the terms of Section 1 above, provided that you also meet all of these conditions: a) The modified work must itself be a software library. b) You must cause the files modified to carry prominent notices stating that you changed the files and the date of any change. c) You must cause the whole of the work to be licensed at no charge to all third parties under the terms of this License. d) If a facility in the modified Library refers to a function or a table of data to be supplied by an application program that uses the facility, other than as an argument passed when the facility is invoked, then you must make a good faith effort to ensure that, in the event an application does not supply such function or table, the facility still operates, and performs whatever part of its purpose remains meaningful. (For example, a function in a library to compute square roots has a purpose that is entirely well-defined independent of the application. Therefore, Subsection 2d requires that any application-supplied function or table used by this function must be optional: if the application does not supply it, the square root function must still compute square roots.) These requirements apply to the modified work as a whole. If identifiable sections of that work are not derived from the Library, and can be reasonably considered independent and separate works in themselves, then this License, and its terms, do not apply to those sections when you distribute them as separate works. But when you distribute the same sections as part of a whole which is a work based on the Library, the distribution of the whole must be on the terms of this License, whose permissions for other licensees extend to the entire whole, and thus to each and every part regardless of who wrote it. Thus, it is not the intent of this section to claim rights or contest your rights to work written entirely by you; rather, the intent is to exercise the right to control the distribution of derivative or collective works based on the Library. In addition, mere aggregation of another work not based on the Library with the Library (or with a work based on the Library) on a volume of a storage or distribution medium does not bring the other work under the scope of this License. 3. You may opt to apply the terms of the ordinary GNU General Public License instead of this License to a given copy of the Library. To do this, you must alter all the notices that refer to this License, so that they refer to the ordinary GNU General Public License, version 2, instead of to this License. (If a newer version than version 2 of the ordinary GNU General Public License has appeared, then you can specify that version instead if you wish.) Do not make any other change in these notices. Once this change is made in a given copy, it is irreversible for that copy, so the ordinary GNU General Public License applies to all subsequent copies and derivative works made from that copy. This option is useful when you wish to copy part of the code of the Library into a program that is not a library. 4. You may copy and distribute the Library (or a portion or derivative of it, under Section 2) in object code or executable form under the terms of Sections 1 and 2 above provided that you accompany it with the complete corresponding machine-readable source code, which must be distributed under the terms of Sections 1 and 2 above on a medium customarily used for software interchange. If distribution of object code is made by offering access to copy from a designated place, then offering equivalent access to copy the source code from the same place satisfies the requirement to distribute the source code, even though third parties are not compelled to copy the source along with the object code. 5. A program that contains no derivative of any portion of the Library, but is designed to work with the Library by being compiled or linked with it, is called a "work that uses the Library". Such a work, in isolation, is not a derivative work of the Library, and therefore falls outside the scope of this License. However, linking a "work that uses the Library" with the Library creates an executable that is a derivative of the Library (because it contains portions of the Library), rather than a "work that uses the library". The executable is therefore covered by this License. Section 6 states terms for distribution of such executables. When a "work that uses the Library" uses material from a header file that is part of the Library, the object code for the work may be a derivative work of the Library even though the source code is not. Whether this is true is especially significant if the work can be linked without the Library, or if the work is itself a library. The threshold for this to be true is not precisely defined by law. If such an object file uses only numerical parameters, data structure layouts and accessors, and small macros and small inline functions (ten lines or less in length), then the use of the object file is unrestricted, regardless of whether it is legally a derivative work. (Executables containing this object code plus portions of the Library will still fall under Section 6.) Otherwise, if the work is a derivative of the Library, you may distribute the object code for the work under the terms of Section 6. Any executables containing that work also fall under Section 6, whether or not they are linked directly with the Library itself. 6. As an exception to the Sections above, you may also combine or link a "work that uses the Library" with the Library to produce a work containing portions of the Library, and distribute that work under terms of your choice, provided that the terms permit modification of the work for the customer's own use and reverse engineering for debugging such modifications. You must give prominent notice with each copy of the work that the Library is used in it and that the Library and its use are covered by this License. You must supply a copy of this License. If the work during execution displays copyright notices, you must include the copyright notice for the Library among them, as well as a reference directing the user to the copy of this License. Also, you must do one of these things: a) Accompany the work with the complete corresponding machine-readable source code for the Library including whatever changes were used in the work (which must be distributed under Sections 1 and 2 above); and, if the work is an executable linked with the Library, with the complete machine-readable "work that uses the Library", as object code and/or source code, so that the user can modify the Library and then relink to produce a modified executable containing the modified Library. (It is understood that the user who changes the contents of definitions files in the Library will not necessarily be able to recompile the application to use the modified definitions.) b) Use a suitable shared library mechanism for linking with the Library. A suitable mechanism is one that (1) uses at run time a copy of the library already present on the user's computer system, rather than copying library functions into the executable, and (2) will operate properly with a modified version of the library, if the user installs one, as long as the modified version is interface-compatible with the version that the work was made with. c) Accompany the work with a written offer, valid for at least three years, to give the same user the materials specified in Subsection 6a, above, for a charge no more than the cost of performing this distribution. d) If distribution of the work is made by offering access to copy from a designated place, offer equivalent access to copy the above specified materials from the same place. e) Verify that the user has already received a copy of these materials or that you have already sent this user a copy. For an executable, the required form of the "work that uses the Library" must include any data and utility programs needed for reproducing the executable from it. However, as a special exception, the materials to be distributed need not include anything that is normally distributed (in either source or binary form) with the major components (compiler, kernel, and so on) of the operating system on which the executable runs, unless that component itself accompanies the executable. It may happen that this requirement contradicts the license restrictions of other proprietary libraries that do not normally accompany the operating system. Such a contradiction means you cannot use both them and the Library together in an executable that you distribute. 7. You may place library facilities that are a work based on the Library side-by-side in a single library together with other library facilities not covered by this License, and distribute such a combined library, provided that the separate distribution of the work based on the Library and of the other library facilities is otherwise permitted, and provided that you do these two things: a) Accompany the combined library with a copy of the same work based on the Library, uncombined with any other library facilities. This must be distributed under the terms of the Sections above. b) Give prominent notice with the combined library of the fact that part of it is a work based on the Library, and explaining where to find the accompanying uncombined form of the same work. 8. You may not copy, modify, sublicense, link with, or distribute the Library except as expressly provided under this License. Any attempt otherwise to copy, modify, sublicense, link with, or distribute the Library is void, and will automatically terminate your rights under this License. However, parties who have received copies, or rights, from you under this License will not have their licenses terminated so long as such parties remain in full compliance. 9. You are not required to accept this License, since you have not signed it. However, nothing else grants you permission to modify or distribute the Library or its derivative works. These actions are prohibited by law if you do not accept this License. Therefore, by modifying or distributing the Library (or any work based on the Library), you indicate your acceptance of this License to do so, and all its terms and conditions for copying, distributing or modifying the Library or works based on it. 10. Each time you redistribute the Library (or any work based on the Library), the recipient automatically receives a license from the original licensor to copy, distribute, link with or modify the Library subject to these terms and conditions. You may not impose any further restrictions on the recipients' exercise of the rights granted herein. You are not responsible for enforcing compliance by third parties with this License. 11. If, as a consequence of a court judgment or allegation of patent infringement or for any other reason (not limited to patent issues), conditions are imposed on you (whether by court order, agreement or otherwise) that contradict the conditions of this License, they do not excuse you from the conditions of this License. If you cannot distribute so as to satisfy simultaneously your obligations under this License and any other pertinent obligations, then as a consequence you may not distribute the Library at all. For example, if a patent license would not permit royalty-free redistribution of the Library by all those who receive copies directly or indirectly through you, then the only way you could satisfy both it and this License would be to refrain entirely from distribution of the Library. If any portion of this section is held invalid or unenforceable under any particular circumstance, the balance of the section is intended to apply, and the section as a whole is intended to apply in other circumstances. It is not the purpose of this section to induce you to infringe any patents or other property right claims or to contest validity of any such claims; this section has the sole purpose of protecting the integrity of the free software distribution system which is implemented by public license practices. Many people have made generous contributions to the wide range of software distributed through that system in reliance on consistent application of that system; it is up to the author/donor to decide if he or she is willing to distribute software through any other system and a licensee cannot impose that choice. This section is intended to make thoroughly clear what is believed to be a consequence of the rest of this License. 12. If the distribution and/or use of the Library is restricted in certain countries either by patents or by copyrighted interfaces, the original copyright holder who places the Library under this License may add an explicit geographical distribution limitation excluding those countries, so that distribution is permitted only in or among countries not thus excluded. In such case, this License incorporates the limitation as if written in the body of this License. 13. The Free Software Foundation may publish revised and/or new versions of the Lesser General Public License from time to time. Such new versions will be similar in spirit to the present version, but may differ in detail to address new problems or concerns. Each version is given a distinguishing version number. If the Library specifies a version number of this License which applies to it and "any later version", you have the option of following the terms and conditions either of that version or of any later version published by the Free Software Foundation. If the Library does not specify a license version number, you may choose any version ever published by the Free Software Foundation. 14. If you wish to incorporate parts of the Library into other free programs whose distribution conditions are incompatible with these, write to the author to ask for permission. For software which is copyrighted by the Free Software Foundation, write to the Free Software Foundation; we sometimes make exceptions for this. Our decision will be guided by the two goals of preserving the free status of all derivatives of our free software and of promoting the sharing and reuse of software generally. NO WARRANTY 15. BECAUSE THE LIBRARY IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY FOR THE LIBRARY, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES PROVIDE THE LIBRARY "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE LIBRARY IS WITH YOU. SHOULD THE LIBRARY PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION. 16. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR REDISTRIBUTE THE LIBRARY AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE USE OR INABILITY TO USE THE LIBRARY (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD PARTIES OR A FAILURE OF THE LIBRARY TO OPERATE WITH ANY OTHER SOFTWARE), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES. END OF TERMS AND CONDITIONS urlgrabber-3.9.1/scripts/0000775000076400007640000000000011257176250015236 5ustar skvidalskvidalurlgrabber-3.9.1/scripts/urlgrabber0000664000076400007640000002766211203343174017315 0ustar skvidalskvidal#!/usr/bin/python -t # This library is free software; you can redistribute it and/or # modify it under the terms of the GNU Lesser General Public # License as published by the Free Software Foundation; either # version 2.1 of the License, or (at your option) any later version. # # This library is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU # Lesser General Public License for more details. # # You should have received a copy of the GNU Lesser General Public # License along with this library; if not, write to the # Free Software Foundation, Inc., # 59 Temple Place, Suite 330, # Boston, MA 02111-1307 USA # This file is part of urlgrabber, a high-level cross-protocol url-grabber # Copyright 2002-2006 Michael D. Stenner, Ryan Tomayko """NAME urlgrabber - a simple client for the urlgrabber python package DESCRIPTION This is a thin client for the urlgrabber python package. It is provided mainly for helping debug the python package. It provides low-level access to most urlgrabber features from the shell. There are two types of options available for this program. They are 'client options' and 'module options'. Client options apply specifically to the behavior of this client, whereas module options are built-in options to the urlgrabber module. Both of these are avaible from the client command line, but they're documented a little differently. Client options are documented here, and module options are documented through the '--help