4 from __future__
import unicode_literals
6 # Allow direct execution
10 sys
.path
.insert(0, os
.path
.dirname(os
.path
.dirname(os
.path
.abspath(__file__
))))
13 # Various small unit tests
16 import xml
.etree
.ElementTree
18 from youtube_dlc
.utils
import (
40 get_element_by_attribute
,
41 get_elements_by_class
,
42 get_elements_by_attribute
,
102 parse_dfxp_time_expr
,
105 cli_valueless_option
,
110 from youtube_dlc
.compat
import (
112 compat_etree_fromstring
,
121 class TestUtil(unittest
.TestCase
):
122 def test_timeconvert(self
):
123 self
.assertTrue(timeconvert('') is None)
124 self
.assertTrue(timeconvert('bougrg') is None)
126 def test_sanitize_filename(self
):
127 self
.assertEqual(sanitize_filename('abc'), 'abc')
128 self
.assertEqual(sanitize_filename('abc_d-e'), 'abc_d-e')
130 self
.assertEqual(sanitize_filename('123'), '123')
132 self
.assertEqual('abc_de', sanitize_filename('abc/de'))
133 self
.assertFalse('/' in sanitize_filename('abc/de///'))
135 self
.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de'))
136 self
.assertEqual('xxx', sanitize_filename('xxx/<>\\*|'))
137 self
.assertEqual('yes no', sanitize_filename('yes? no'))
138 self
.assertEqual('this - that', sanitize_filename('this: that'))
140 self
.assertEqual(sanitize_filename('AT&T'), 'AT&T')
142 self
.assertEqual(sanitize_filename(aumlaut
), aumlaut
)
143 tests
= '\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430'
144 self
.assertEqual(sanitize_filename(tests
), tests
)
147 sanitize_filename('New World record at 0:12:34'),
148 'New World record at 0_12_34')
150 self
.assertEqual(sanitize_filename('--gasdgf'), '_-gasdgf')
151 self
.assertEqual(sanitize_filename('--gasdgf', is_id
=True), '--gasdgf')
152 self
.assertEqual(sanitize_filename('.gasdgf'), 'gasdgf')
153 self
.assertEqual(sanitize_filename('.gasdgf', is_id
=True), '.gasdgf')
157 for fbc
in forbidden
:
158 self
.assertTrue(fbc
not in sanitize_filename(fc
))
160 def test_sanitize_filename_restricted(self
):
161 self
.assertEqual(sanitize_filename('abc', restricted
=True), 'abc')
162 self
.assertEqual(sanitize_filename('abc_d-e', restricted
=True), 'abc_d-e')
164 self
.assertEqual(sanitize_filename('123', restricted
=True), '123')
166 self
.assertEqual('abc_de', sanitize_filename('abc/de', restricted
=True))
167 self
.assertFalse('/' in sanitize_filename('abc/de///', restricted
=True))
169 self
.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de', restricted
=True))
170 self
.assertEqual('xxx', sanitize_filename('xxx/<>\\*|', restricted
=True))
171 self
.assertEqual('yes_no', sanitize_filename('yes? no', restricted
=True))
172 self
.assertEqual('this_-_that', sanitize_filename('this: that', restricted
=True))
174 tests
= 'aäb\u4e2d\u56fd\u7684c'
175 self
.assertEqual(sanitize_filename(tests
, restricted
=True), 'aab_c')
176 self
.assertTrue(sanitize_filename('\xf6', restricted
=True) != '') # No empty filename
178 forbidden
= '"\0\\/&!: \'\t\n()[]{}$;`^,#'
180 for fbc
in forbidden
:
181 self
.assertTrue(fbc
not in sanitize_filename(fc
, restricted
=True))
183 # Handle a common case more neatly
184 self
.assertEqual(sanitize_filename('\u5927\u58f0\u5e26 - Song', restricted
=True), 'Song')
185 self
.assertEqual(sanitize_filename('\u603b\u7edf: Speech', restricted
=True), 'Speech')
186 # .. but make sure the file name is never empty
187 self
.assertTrue(sanitize_filename('-', restricted
=True) != '')
188 self
.assertTrue(sanitize_filename(':', restricted
=True) != '')
190 self
.assertEqual(sanitize_filename(
191 'ÂÃÄÀÁÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖŐØŒÙÚÛÜŰÝÞßàáâãäåæçèéêëìíîïðñòóôõöőøœùúûüűýþÿ', restricted
=True),
192 'AAAAAAAECEEEEIIIIDNOOOOOOOOEUUUUUYTHssaaaaaaaeceeeeiiiionooooooooeuuuuuythy')
194 def test_sanitize_ids(self
):
195 self
.assertEqual(sanitize_filename('_n_cd26wFpw', is_id
=True), '_n_cd26wFpw')
196 self
.assertEqual(sanitize_filename('_BD_eEpuzXw', is_id
=True), '_BD_eEpuzXw')
197 self
.assertEqual(sanitize_filename('N0Y__7-UOdI', is_id
=True), 'N0Y__7-UOdI')
199 def test_sanitize_path(self
):
200 if sys
.platform
!= 'win32':
203 self
.assertEqual(sanitize_path('abc'), 'abc')
204 self
.assertEqual(sanitize_path('abc/def'), 'abc\\def')
205 self
.assertEqual(sanitize_path('abc\\def'), 'abc\\def')
206 self
.assertEqual(sanitize_path('abc|def'), 'abc#def')
207 self
.assertEqual(sanitize_path('<>:"|?*'), '#######')
208 self
.assertEqual(sanitize_path('C:/abc/def'), 'C:\\abc\\def')
209 self
.assertEqual(sanitize_path('C?:/abc/def'), 'C##\\abc\\def')
211 self
.assertEqual(sanitize_path('\\\\?\\UNC\\ComputerName\\abc'), '\\\\?\\UNC\\ComputerName\\abc')
212 self
.assertEqual(sanitize_path('\\\\?\\UNC/ComputerName/abc'), '\\\\?\\UNC\\ComputerName\\abc')
214 self
.assertEqual(sanitize_path('\\\\?\\C:\\abc'), '\\\\?\\C:\\abc')
215 self
.assertEqual(sanitize_path('\\\\?\\C:/abc'), '\\\\?\\C:\\abc')
216 self
.assertEqual(sanitize_path('\\\\?\\C:\\ab?c\\de:f'), '\\\\?\\C:\\ab#c\\de#f')
217 self
.assertEqual(sanitize_path('\\\\?\\C:\\abc'), '\\\\?\\C:\\abc')
220 sanitize_path('youtube/%(uploader)s/%(autonumber)s-%(title)s-%(upload_date)s.%(ext)s'),
221 'youtube\\%(uploader)s\\%(autonumber)s-%(title)s-%(upload_date)s.%(ext)s')
224 sanitize_path('youtube/TheWreckingYard ./00001-Not bad, Especially for Free! (1987 Yamaha 700)-20141116.mp4.part'),
225 'youtube\\TheWreckingYard #\\00001-Not bad, Especially for Free! (1987 Yamaha 700)-20141116.mp4.part')
226 self
.assertEqual(sanitize_path('abc/def...'), 'abc\\def..#')
227 self
.assertEqual(sanitize_path('abc.../def'), 'abc..#\\def')
228 self
.assertEqual(sanitize_path('abc.../def...'), 'abc..#\\def..#')
230 self
.assertEqual(sanitize_path('../abc'), '..\\abc')
231 self
.assertEqual(sanitize_path('../../abc'), '..\\..\\abc')
232 self
.assertEqual(sanitize_path('./abc'), 'abc')
233 self
.assertEqual(sanitize_path('./../abc'), '..\\abc')
235 def test_sanitize_url(self
):
236 self
.assertEqual(sanitize_url('//foo.bar'), 'http://foo.bar')
237 self
.assertEqual(sanitize_url('httpss://foo.bar'), 'https://foo.bar')
238 self
.assertEqual(sanitize_url('rmtps://foo.bar'), 'rtmps://foo.bar')
239 self
.assertEqual(sanitize_url('https://foo.bar'), 'https://foo.bar')
241 def test_expand_path(self
):
243 return '%{0}%'.format(var
) if sys
.platform
== 'win32' else '${0}'.format(var
)
245 compat_setenv('youtube_dlc_EXPATH_PATH', 'expanded')
246 self
.assertEqual(expand_path(env('youtube_dlc_EXPATH_PATH')), 'expanded')
247 self
.assertEqual(expand_path(env('HOME')), compat_getenv('HOME'))
248 self
.assertEqual(expand_path('~'), compat_getenv('HOME'))
250 expand_path('~/%s' % env('youtube_dlc_EXPATH_PATH')),
251 '%s/expanded' % compat_getenv('HOME'))
253 def test_prepend_extension(self
):
254 self
.assertEqual(prepend_extension('abc.ext', 'temp'), 'abc.temp.ext')
255 self
.assertEqual(prepend_extension('abc.ext', 'temp', 'ext'), 'abc.temp.ext')
256 self
.assertEqual(prepend_extension('abc.unexpected_ext', 'temp', 'ext'), 'abc.unexpected_ext.temp')
257 self
.assertEqual(prepend_extension('abc', 'temp'), 'abc.temp')
258 self
.assertEqual(prepend_extension('.abc', 'temp'), '.abc.temp')
259 self
.assertEqual(prepend_extension('.abc.ext', 'temp'), '.abc.temp.ext')
261 def test_replace_extension(self
):
262 self
.assertEqual(replace_extension('abc.ext', 'temp'), 'abc.temp')
263 self
.assertEqual(replace_extension('abc.ext', 'temp', 'ext'), 'abc.temp')
264 self
.assertEqual(replace_extension('abc.unexpected_ext', 'temp', 'ext'), 'abc.unexpected_ext.temp')
265 self
.assertEqual(replace_extension('abc', 'temp'), 'abc.temp')
266 self
.assertEqual(replace_extension('.abc', 'temp'), '.abc.temp')
267 self
.assertEqual(replace_extension('.abc.ext', 'temp'), '.abc.temp')
269 def test_subtitles_filename(self
):
270 self
.assertEqual(subtitles_filename('abc.ext', 'en', 'vtt'), 'abc.en.vtt')
271 self
.assertEqual(subtitles_filename('abc.ext', 'en', 'vtt', 'ext'), 'abc.en.vtt')
272 self
.assertEqual(subtitles_filename('abc.unexpected_ext', 'en', 'vtt', 'ext'), 'abc.unexpected_ext.en.vtt')
274 def test_remove_start(self
):
275 self
.assertEqual(remove_start(None, 'A - '), None)
276 self
.assertEqual(remove_start('A - B', 'A - '), 'B')
277 self
.assertEqual(remove_start('B - A', 'A - '), 'B - A')
279 def test_remove_end(self
):
280 self
.assertEqual(remove_end(None, ' - B'), None)
281 self
.assertEqual(remove_end('A - B', ' - B'), 'A')
282 self
.assertEqual(remove_end('B - A', ' - B'), 'B - A')
284 def test_remove_quotes(self
):
285 self
.assertEqual(remove_quotes(None), None)
286 self
.assertEqual(remove_quotes('"'), '"')
287 self
.assertEqual(remove_quotes("'"), "'")
288 self
.assertEqual(remove_quotes(';'), ';')
289 self
.assertEqual(remove_quotes('";'), '";')
290 self
.assertEqual(remove_quotes('""'), '')
291 self
.assertEqual(remove_quotes('";"'), ';')
293 def test_ordered_set(self
):
294 self
.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7])
295 self
.assertEqual(orderedSet([]), [])
296 self
.assertEqual(orderedSet([1]), [1])
297 # keep the list ordered
298 self
.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1])
300 def test_unescape_html(self
):
301 self
.assertEqual(unescapeHTML('%20;'), '%20;')
302 self
.assertEqual(unescapeHTML('/'), '/')
303 self
.assertEqual(unescapeHTML('/'), '/')
304 self
.assertEqual(unescapeHTML('é'), 'é')
305 self
.assertEqual(unescapeHTML('�'), '�')
306 self
.assertEqual(unescapeHTML('&a"'), '&a"')
308 self
.assertEqual(unescapeHTML('.''), '.\'')
310 def test_date_from_str(self
):
311 self
.assertEqual(date_from_str('yesterday'), date_from_str('now-1day'))
312 self
.assertEqual(date_from_str('now+7day'), date_from_str('now+1week'))
313 self
.assertEqual(date_from_str('now+14day'), date_from_str('now+2week'))
314 self
.assertEqual(date_from_str('now+365day'), date_from_str('now+1year'))
315 self
.assertEqual(date_from_str('now+30day'), date_from_str('now+1month'))
317 def test_daterange(self
):
318 _20century
= DateRange("19000101", "20000101")
319 self
.assertFalse("17890714" in _20century
)
320 _ac
= DateRange("00010101")
321 self
.assertTrue("19690721" in _ac
)
322 _firstmilenium
= DateRange(end
="10000101")
323 self
.assertTrue("07110427" in _firstmilenium
)
325 def test_unified_dates(self
):
326 self
.assertEqual(unified_strdate('December 21, 2010'), '20101221')
327 self
.assertEqual(unified_strdate('8/7/2009'), '20090708')
328 self
.assertEqual(unified_strdate('Dec 14, 2012'), '20121214')
329 self
.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
330 self
.assertEqual(unified_strdate('1968 12 10'), '19681210')
331 self
.assertEqual(unified_strdate('1968-12-10'), '19681210')
332 self
.assertEqual(unified_strdate('28/01/2014 21:00:00 +0100'), '20140128')
334 unified_strdate('11/26/2014 11:30:00 AM PST', day_first
=False),
337 unified_strdate('2/2/2015 6:47:40 PM', day_first
=False),
339 self
.assertEqual(unified_strdate('Feb 14th 2016 5:45PM'), '20160214')
340 self
.assertEqual(unified_strdate('25-09-2014'), '20140925')
341 self
.assertEqual(unified_strdate('27.02.2016 17:30'), '20160227')
342 self
.assertEqual(unified_strdate('UNKNOWN DATE FORMAT'), None)
343 self
.assertEqual(unified_strdate('Feb 7, 2016 at 6:35 pm'), '20160207')
344 self
.assertEqual(unified_strdate('July 15th, 2013'), '20130715')
345 self
.assertEqual(unified_strdate('September 1st, 2013'), '20130901')
346 self
.assertEqual(unified_strdate('Sep 2nd, 2013'), '20130902')
347 self
.assertEqual(unified_strdate('November 3rd, 2019'), '20191103')
348 self
.assertEqual(unified_strdate('October 23rd, 2005'), '20051023')
350 def test_unified_timestamps(self
):
351 self
.assertEqual(unified_timestamp('December 21, 2010'), 1292889600)
352 self
.assertEqual(unified_timestamp('8/7/2009'), 1247011200)
353 self
.assertEqual(unified_timestamp('Dec 14, 2012'), 1355443200)
354 self
.assertEqual(unified_timestamp('2012/10/11 01:56:38 +0000'), 1349920598)
355 self
.assertEqual(unified_timestamp('1968 12 10'), -33436800)
356 self
.assertEqual(unified_timestamp('1968-12-10'), -33436800)
357 self
.assertEqual(unified_timestamp('28/01/2014 21:00:00 +0100'), 1390939200)
359 unified_timestamp('11/26/2014 11:30:00 AM PST', day_first
=False),
362 unified_timestamp('2/2/2015 6:47:40 PM', day_first
=False),
364 self
.assertEqual(unified_timestamp('Feb 14th 2016 5:45PM'), 1455471900)
365 self
.assertEqual(unified_timestamp('25-09-2014'), 1411603200)
366 self
.assertEqual(unified_timestamp('27.02.2016 17:30'), 1456594200)
367 self
.assertEqual(unified_timestamp('UNKNOWN DATE FORMAT'), None)
368 self
.assertEqual(unified_timestamp('May 16, 2016 11:15 PM'), 1463440500)
369 self
.assertEqual(unified_timestamp('Feb 7, 2016 at 6:35 pm'), 1454870100)
370 self
.assertEqual(unified_timestamp('2017-03-30T17:52:41Q'), 1490896361)
371 self
.assertEqual(unified_timestamp('Sep 11, 2013 | 5:49 AM'), 1378878540)
372 self
.assertEqual(unified_timestamp('December 15, 2017 at 7:49 am'), 1513324140)
373 self
.assertEqual(unified_timestamp('2018-03-14T08:32:43.1493874+00:00'), 1521016363)
375 def test_determine_ext(self
):
376 self
.assertEqual(determine_ext('http://example.com/foo/bar.mp4/?download'), 'mp4')
377 self
.assertEqual(determine_ext('http://example.com/foo/bar/?download', None), None)
378 self
.assertEqual(determine_ext('http://example.com/foo/bar.nonext/?download', None), None)
379 self
.assertEqual(determine_ext('http://example.com/foo/bar/mp4?download', None), None)
380 self
.assertEqual(determine_ext('http://example.com/foo/bar.m3u8//?download'), 'm3u8')
381 self
.assertEqual(determine_ext('foobar', None), None)
383 def test_find_xpath_attr(self
):
391 doc
= compat_etree_fromstring(testxml
)
393 self
.assertEqual(find_xpath_attr(doc
, './/fourohfour', 'n'), None)
394 self
.assertEqual(find_xpath_attr(doc
, './/fourohfour', 'n', 'v'), None)
395 self
.assertEqual(find_xpath_attr(doc
, './/node', 'n'), None)
396 self
.assertEqual(find_xpath_attr(doc
, './/node', 'n', 'v'), None)
397 self
.assertEqual(find_xpath_attr(doc
, './/node', 'x'), doc
[1])
398 self
.assertEqual(find_xpath_attr(doc
, './/node', 'x', 'a'), doc
[1])
399 self
.assertEqual(find_xpath_attr(doc
, './/node', 'x', 'b'), doc
[3])
400 self
.assertEqual(find_xpath_attr(doc
, './/node', 'y'), doc
[2])
401 self
.assertEqual(find_xpath_attr(doc
, './/node', 'y', 'c'), doc
[2])
402 self
.assertEqual(find_xpath_attr(doc
, './/node', 'y', 'd'), doc
[3])
403 self
.assertEqual(find_xpath_attr(doc
, './/node', 'x', ''), doc
[4])
405 def test_xpath_with_ns(self
):
406 testxml
= '''<root xmlns:media="http://example.com/">
408 <media:author>The Author</media:author>
409 <url>http://server.com/download.mp3</url>
412 doc
= compat_etree_fromstring(testxml
)
413 find
= lambda p
: doc
.find(xpath_with_ns(p
, {'media': 'http://example.com/'}
))
414 self
.assertTrue(find('media:song') is not None)
415 self
.assertEqual(find('media:song/media:author').text
, 'The Author')
416 self
.assertEqual(find('media:song/url').text
, 'http://server.com/download.mp3')
418 def test_xpath_element(self
):
419 doc
= xml
.etree
.ElementTree
.Element('root')
420 div
= xml
.etree
.ElementTree
.SubElement(doc
, 'div')
421 p
= xml
.etree
.ElementTree
.SubElement(div
, 'p')
423 self
.assertEqual(xpath_element(doc
, 'div/p'), p
)
424 self
.assertEqual(xpath_element(doc
, ['div/p']), p
)
425 self
.assertEqual(xpath_element(doc
, ['div/bar', 'div/p']), p
)
426 self
.assertEqual(xpath_element(doc
, 'div/bar', default
='default'), 'default')
427 self
.assertEqual(xpath_element(doc
, ['div/bar'], default
='default'), 'default')
428 self
.assertTrue(xpath_element(doc
, 'div/bar') is None)
429 self
.assertTrue(xpath_element(doc
, ['div/bar']) is None)
430 self
.assertTrue(xpath_element(doc
, ['div/bar'], 'div/baz') is None)
431 self
.assertRaises(ExtractorError
, xpath_element
, doc
, 'div/bar', fatal
=True)
432 self
.assertRaises(ExtractorError
, xpath_element
, doc
, ['div/bar'], fatal
=True)
433 self
.assertRaises(ExtractorError
, xpath_element
, doc
, ['div/bar', 'div/baz'], fatal
=True)
435 def test_xpath_text(self
):
441 doc
= compat_etree_fromstring(testxml
)
442 self
.assertEqual(xpath_text(doc
, 'div/p'), 'Foo')
443 self
.assertEqual(xpath_text(doc
, 'div/bar', default
='default'), 'default')
444 self
.assertTrue(xpath_text(doc
, 'div/bar') is None)
445 self
.assertRaises(ExtractorError
, xpath_text
, doc
, 'div/bar', fatal
=True)
447 def test_xpath_attr(self
):
453 doc
= compat_etree_fromstring(testxml
)
454 self
.assertEqual(xpath_attr(doc
, 'div/p', 'x'), 'a')
455 self
.assertEqual(xpath_attr(doc
, 'div/bar', 'x'), None)
456 self
.assertEqual(xpath_attr(doc
, 'div/p', 'y'), None)
457 self
.assertEqual(xpath_attr(doc
, 'div/bar', 'x', default
='default'), 'default')
458 self
.assertEqual(xpath_attr(doc
, 'div/p', 'y', default
='default'), 'default')
459 self
.assertRaises(ExtractorError
, xpath_attr
, doc
, 'div/bar', 'x', fatal
=True)
460 self
.assertRaises(ExtractorError
, xpath_attr
, doc
, 'div/p', 'y', fatal
=True)
462 def test_smuggle_url(self
):
463 data
= {"ö": "ö", "abc": [3]}
464 url
= 'https://foo.bar/baz?x=y#a'
465 smug_url
= smuggle_url(url
, data
)
466 unsmug_url
, unsmug_data
= unsmuggle_url(smug_url
)
467 self
.assertEqual(url
, unsmug_url
)
468 self
.assertEqual(data
, unsmug_data
)
470 res_url
, res_data
= unsmuggle_url(url
)
471 self
.assertEqual(res_url
, url
)
472 self
.assertEqual(res_data
, None)
474 smug_url
= smuggle_url(url
, {'a': 'b'}
)
475 smug_smug_url
= smuggle_url(smug_url
, {'c': 'd'}
)
476 res_url
, res_data
= unsmuggle_url(smug_smug_url
)
477 self
.assertEqual(res_url
, url
)
478 self
.assertEqual(res_data
, {'a': 'b', 'c': 'd'}
)
480 def test_shell_quote(self
):
481 args
= ['ffmpeg', '-i', encodeFilename('ñ€ß\'.mp4')]
484 """ffmpeg -i 'ñ€ß'"'"'.mp4'""" if compat_os_name
!= 'nt' else '''ffmpeg -i "ñ€ß'.mp4"''')
486 def test_float_or_none(self
):
487 self
.assertEqual(float_or_none('42.42'), 42.42)
488 self
.assertEqual(float_or_none('42'), 42.0)
489 self
.assertEqual(float_or_none(''), None)
490 self
.assertEqual(float_or_none(None), None)
491 self
.assertEqual(float_or_none([]), None)
492 self
.assertEqual(float_or_none(set()), None)
494 def test_int_or_none(self
):
495 self
.assertEqual(int_or_none('42'), 42)
496 self
.assertEqual(int_or_none(''), None)
497 self
.assertEqual(int_or_none(None), None)
498 self
.assertEqual(int_or_none([]), None)
499 self
.assertEqual(int_or_none(set()), None)
501 def test_str_to_int(self
):
502 self
.assertEqual(str_to_int('123,456'), 123456)
503 self
.assertEqual(str_to_int('123.456'), 123456)
504 self
.assertEqual(str_to_int(523), 523)
505 # Python 3 has no long
506 if sys
.version_info
< (3, 0):
507 eval('self.assertEqual(str_to_int(123456L), 123456)')
508 self
.assertEqual(str_to_int('noninteger'), None)
509 self
.assertEqual(str_to_int([]), None)
511 def test_url_basename(self
):
512 self
.assertEqual(url_basename('http://foo.de/'), '')
513 self
.assertEqual(url_basename('http://foo.de/bar/baz'), 'baz')
514 self
.assertEqual(url_basename('http://foo.de/bar/baz?x=y'), 'baz')
515 self
.assertEqual(url_basename('http://foo.de/bar/baz#x=y'), 'baz')
516 self
.assertEqual(url_basename('http://foo.de/bar/baz/'), 'baz')
518 url_basename('http://media.w3.org/2010/05/sintel/trailer.mp4'),
521 def test_base_url(self
):
522 self
.assertEqual(base_url('http://foo.de/'), 'http://foo.de/')
523 self
.assertEqual(base_url('http://foo.de/bar'), 'http://foo.de/')
524 self
.assertEqual(base_url('http://foo.de/bar/'), 'http://foo.de/bar/')
525 self
.assertEqual(base_url('http://foo.de/bar/baz'), 'http://foo.de/bar/')
526 self
.assertEqual(base_url('http://foo.de/bar/baz?x=z/x/c'), 'http://foo.de/bar/')
528 def test_urljoin(self
):
529 self
.assertEqual(urljoin('http://foo.de/', '/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
530 self
.assertEqual(urljoin(b
'http://foo.de/', '/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
531 self
.assertEqual(urljoin('http://foo.de/', b
'/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
532 self
.assertEqual(urljoin(b
'http://foo.de/', b
'/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
533 self
.assertEqual(urljoin('//foo.de/', '/a/b/c.txt'), '//foo.de/a/b/c.txt')
534 self
.assertEqual(urljoin('http://foo.de/', 'a/b/c.txt'), 'http://foo.de/a/b/c.txt')
535 self
.assertEqual(urljoin('http://foo.de', '/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
536 self
.assertEqual(urljoin('http://foo.de', 'a/b/c.txt'), 'http://foo.de/a/b/c.txt')
537 self
.assertEqual(urljoin('http://foo.de/', 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
538 self
.assertEqual(urljoin('http://foo.de/', '//foo.de/a/b/c.txt'), '//foo.de/a/b/c.txt')
539 self
.assertEqual(urljoin(None, 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
540 self
.assertEqual(urljoin(None, '//foo.de/a/b/c.txt'), '//foo.de/a/b/c.txt')
541 self
.assertEqual(urljoin('', 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
542 self
.assertEqual(urljoin(['foobar'], 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
543 self
.assertEqual(urljoin('http://foo.de/', None), None)
544 self
.assertEqual(urljoin('http://foo.de/', ''), None)
545 self
.assertEqual(urljoin('http://foo.de/', ['foobar']), None)
546 self
.assertEqual(urljoin('http://foo.de/a/b/c.txt', '.././../d.txt'), 'http://foo.de/d.txt')
547 self
.assertEqual(urljoin('http://foo.de/a/b/c.txt', 'rtmp://foo.de'), 'rtmp://foo.de')
548 self
.assertEqual(urljoin(None, 'rtmp://foo.de'), 'rtmp://foo.de')
550 def test_url_or_none(self
):
551 self
.assertEqual(url_or_none(None), None)
552 self
.assertEqual(url_or_none(''), None)
553 self
.assertEqual(url_or_none('foo'), None)
554 self
.assertEqual(url_or_none('http://foo.de'), 'http://foo.de')
555 self
.assertEqual(url_or_none('https://foo.de'), 'https://foo.de')
556 self
.assertEqual(url_or_none('http$://foo.de'), None)
557 self
.assertEqual(url_or_none('http://foo.de'), 'http://foo.de')
558 self
.assertEqual(url_or_none('//foo.de'), '//foo.de')
559 self
.assertEqual(url_or_none('s3://foo.de'), None)
560 self
.assertEqual(url_or_none('rtmpte://foo.de'), 'rtmpte://foo.de')
561 self
.assertEqual(url_or_none('mms://foo.de'), 'mms://foo.de')
562 self
.assertEqual(url_or_none('rtspu://foo.de'), 'rtspu://foo.de')
563 self
.assertEqual(url_or_none('ftps://foo.de'), 'ftps://foo.de')
565 def test_parse_age_limit(self
):
566 self
.assertEqual(parse_age_limit(None), None)
567 self
.assertEqual(parse_age_limit(False), None)
568 self
.assertEqual(parse_age_limit('invalid'), None)
569 self
.assertEqual(parse_age_limit(0), 0)
570 self
.assertEqual(parse_age_limit(18), 18)
571 self
.assertEqual(parse_age_limit(21), 21)
572 self
.assertEqual(parse_age_limit(22), None)
573 self
.assertEqual(parse_age_limit('18'), 18)
574 self
.assertEqual(parse_age_limit('18+'), 18)
575 self
.assertEqual(parse_age_limit('PG-13'), 13)
576 self
.assertEqual(parse_age_limit('TV-14'), 14)
577 self
.assertEqual(parse_age_limit('TV-MA'), 17)
578 self
.assertEqual(parse_age_limit('TV14'), 14)
579 self
.assertEqual(parse_age_limit('TV_G'), 0)
581 def test_parse_duration(self
):
582 self
.assertEqual(parse_duration(None), None)
583 self
.assertEqual(parse_duration(False), None)
584 self
.assertEqual(parse_duration('invalid'), None)
585 self
.assertEqual(parse_duration('1'), 1)
586 self
.assertEqual(parse_duration('1337:12'), 80232)
587 self
.assertEqual(parse_duration('9:12:43'), 33163)
588 self
.assertEqual(parse_duration('12:00'), 720)
589 self
.assertEqual(parse_duration('00:01:01'), 61)
590 self
.assertEqual(parse_duration('x:y'), None)
591 self
.assertEqual(parse_duration('3h11m53s'), 11513)
592 self
.assertEqual(parse_duration('3h 11m 53s'), 11513)
593 self
.assertEqual(parse_duration('3 hours 11 minutes 53 seconds'), 11513)
594 self
.assertEqual(parse_duration('3 hours 11 mins 53 secs'), 11513)
595 self
.assertEqual(parse_duration('62m45s'), 3765)
596 self
.assertEqual(parse_duration('6m59s'), 419)
597 self
.assertEqual(parse_duration('49s'), 49)
598 self
.assertEqual(parse_duration('0h0m0s'), 0)
599 self
.assertEqual(parse_duration('0m0s'), 0)
600 self
.assertEqual(parse_duration('0s'), 0)
601 self
.assertEqual(parse_duration('01:02:03.05'), 3723.05)
602 self
.assertEqual(parse_duration('T30M38S'), 1838)
603 self
.assertEqual(parse_duration('5 s'), 5)
604 self
.assertEqual(parse_duration('3 min'), 180)
605 self
.assertEqual(parse_duration('2.5 hours'), 9000)
606 self
.assertEqual(parse_duration('02:03:04'), 7384)
607 self
.assertEqual(parse_duration('01:02:03:04'), 93784)
608 self
.assertEqual(parse_duration('1 hour 3 minutes'), 3780)
609 self
.assertEqual(parse_duration('87 Min.'), 5220)
610 self
.assertEqual(parse_duration('PT1H0.040S'), 3600.04)
611 self
.assertEqual(parse_duration('PT00H03M30SZ'), 210)
612 self
.assertEqual(parse_duration('P0Y0M0DT0H4M20.880S'), 260.88)
614 def test_fix_xml_ampersands(self
):
616 fix_xml_ampersands('"&x=y&z=a'), '"&x=y&z=a')
618 fix_xml_ampersands('"&x=y&wrong;&z=a'),
619 '"&x=y&wrong;&z=a')
621 fix_xml_ampersands('&'><"'),
622 '&'><"')
624 fix_xml_ampersands('Ӓ᪼'), 'Ӓ᪼')
625 self
.assertEqual(fix_xml_ampersands('&#&#'), '&#&#')
627 def test_paged_list(self
):
628 def testPL(size
, pagesize
, sliceargs
, expected
):
629 def get_page(pagenum
):
630 firstid
= pagenum
* pagesize
631 upto
= min(size
, pagenum
* pagesize
+ pagesize
)
632 for i
in range(firstid
, upto
):
635 pl
= OnDemandPagedList(get_page
, pagesize
)
636 got
= pl
.getslice(*sliceargs
)
637 self
.assertEqual(got
, expected
)
639 iapl
= InAdvancePagedList(get_page
, size
// pagesize
+ 1, pagesize
)
640 got
= iapl
.getslice(*sliceargs
)
641 self
.assertEqual(got
, expected
)
643 testPL(5, 2, (), [0, 1, 2, 3, 4])
644 testPL(5, 2, (1,), [1, 2, 3, 4])
645 testPL(5, 2, (2,), [2, 3, 4])
646 testPL(5, 2, (4,), [4])
647 testPL(5, 2, (0, 3), [0, 1, 2])
648 testPL(5, 2, (1, 4), [1, 2, 3])
649 testPL(5, 2, (2, 99), [2, 3, 4])
650 testPL(5, 2, (20, 99), [])
652 def test_read_batch_urls(self
):
653 f
= io
.StringIO('''\xef\xbb\xbf foo
656 # More after this line\r
659 self
.assertEqual(read_batch_urls(f
), ['foo', 'bar', 'baz', 'bam'])
661 def test_urlencode_postdata(self
):
662 data
= urlencode_postdata({'username': 'foo@bar.com', 'password': '1234'}
)
663 self
.assertTrue(isinstance(data
, bytes))
665 def test_update_url_query(self
):
667 return compat_parse_qs(compat_urlparse
.urlparse(url
).query
)
668 self
.assertEqual(query_dict(update_url_query(
669 'http://example.com/path', {'quality': ['HD'], 'format': ['mp4']}
)),
670 query_dict('http://example.com/path?quality=HD&format=mp4'))
671 self
.assertEqual(query_dict(update_url_query(
672 'http://example.com/path', {'system': ['LINUX', 'WINDOWS']}
)),
673 query_dict('http://example.com/path?system=LINUX&system=WINDOWS'))
674 self
.assertEqual(query_dict(update_url_query(
675 'http://example.com/path', {'fields': 'id,formats,subtitles'}
)),
676 query_dict('http://example.com/path?fields=id,formats,subtitles'))
677 self
.assertEqual(query_dict(update_url_query(
678 'http://example.com/path', {'fields': ('id,formats,subtitles', 'thumbnails')}
)),
679 query_dict('http://example.com/path?fields=id,formats,subtitles&fields=thumbnails'))
680 self
.assertEqual(query_dict(update_url_query(
681 'http://example.com/path?manifest=f4m', {'manifest': []}
)),
682 query_dict('http://example.com/path'))
683 self
.assertEqual(query_dict(update_url_query(
684 'http://example.com/path?system=LINUX&system=WINDOWS', {'system': 'LINUX'}
)),
685 query_dict('http://example.com/path?system=LINUX'))
686 self
.assertEqual(query_dict(update_url_query(
687 'http://example.com/path', {'fields': b'id,formats,subtitles'}
)),
688 query_dict('http://example.com/path?fields=id,formats,subtitles'))
689 self
.assertEqual(query_dict(update_url_query(
690 'http://example.com/path', {'width': 1080, 'height': 720}
)),
691 query_dict('http://example.com/path?width=1080&height=720'))
692 self
.assertEqual(query_dict(update_url_query(
693 'http://example.com/path', {'bitrate': 5020.43}
)),
694 query_dict('http://example.com/path?bitrate=5020.43'))
695 self
.assertEqual(query_dict(update_url_query(
696 'http://example.com/path', {'test': '第二行тест'}
)),
697 query_dict('http://example.com/path?test=%E7%AC%AC%E4%BA%8C%E8%A1%8C%D1%82%D0%B5%D1%81%D1%82'))
699 def test_multipart_encode(self
):
701 multipart_encode({b'field': b'value'}
, boundary
='AAAAAA')[0],
702 b
'--AAAAAA\r\nContent-Disposition: form-data; name="field"\r\n\r\nvalue\r\n--AAAAAA--\r\n')
704 multipart_encode({'欄位'.encode('utf-8'): '值'.encode('utf-8')}
, boundary
='AAAAAA')[0],
705 b
'--AAAAAA\r\nContent-Disposition: form-data; name="\xe6\xac\x84\xe4\xbd\x8d"\r\n\r\n\xe5\x80\xbc\r\n--AAAAAA--\r\n')
707 ValueError, multipart_encode
, {b'field': b'value'}
, boundary
='value')
709 def test_dict_get(self
):
717 d
= FALSE_VALUES
.copy()
719 self
.assertEqual(dict_get(d
, 'a'), 42)
720 self
.assertEqual(dict_get(d
, 'b'), None)
721 self
.assertEqual(dict_get(d
, 'b', 42), 42)
722 self
.assertEqual(dict_get(d
, ('a', )), 42)
723 self
.assertEqual(dict_get(d
, ('b', 'a', )), 42)
724 self
.assertEqual(dict_get(d
, ('b', 'c', 'a', 'd', )), 42)
725 self
.assertEqual(dict_get(d
, ('b', 'c', )), None)
726 self
.assertEqual(dict_get(d
, ('b', 'c', ), 42), 42)
727 for key
, false_value
in FALSE_VALUES
.items():
728 self
.assertEqual(dict_get(d
, ('b', 'c', key
, )), None)
729 self
.assertEqual(dict_get(d
, ('b', 'c', key
, ), skip_false_values
=False), false_value
)
731 def test_merge_dicts(self
):
732 self
.assertEqual(merge_dicts({'a': 1}
, {'b': 2}
), {'a': 1, 'b': 2}
)
733 self
.assertEqual(merge_dicts({'a': 1}
, {'a': 2}
), {'a': 1}
)
734 self
.assertEqual(merge_dicts({'a': 1}
, {'a': None}
), {'a': 1}
)
735 self
.assertEqual(merge_dicts({'a': 1}
, {'a': ''}
), {'a': 1}
)
736 self
.assertEqual(merge_dicts({'a': 1}
, {}), {'a': 1}
)
737 self
.assertEqual(merge_dicts({'a': None}
, {'a': 1}
), {'a': 1}
)
738 self
.assertEqual(merge_dicts({'a': ''}
, {'a': 1}
), {'a': ''}
)
739 self
.assertEqual(merge_dicts({'a': ''}
, {'a': 'abc'}
), {'a': 'abc'}
)
740 self
.assertEqual(merge_dicts({'a': None}
, {'a': ''}
, {'a': 'abc'}
), {'a': 'abc'}
)
742 def test_encode_compat_str(self
):
743 self
.assertEqual(encode_compat_str(b
'\xd1\x82\xd0\xb5\xd1\x81\xd1\x82', 'utf-8'), 'тест')
744 self
.assertEqual(encode_compat_str('тест', 'utf-8'), 'тест')
746 def test_parse_iso8601(self
):
747 self
.assertEqual(parse_iso8601('2014-03-23T23:04:26+0100'), 1395612266)
748 self
.assertEqual(parse_iso8601('2014-03-23T22:04:26+0000'), 1395612266)
749 self
.assertEqual(parse_iso8601('2014-03-23T22:04:26Z'), 1395612266)
750 self
.assertEqual(parse_iso8601('2014-03-23T22:04:26.1234Z'), 1395612266)
751 self
.assertEqual(parse_iso8601('2015-09-29T08:27:31.727'), 1443515251)
752 self
.assertEqual(parse_iso8601('2015-09-29T08-27-31.727'), None)
754 def test_strip_jsonp(self
):
755 stripped
= strip_jsonp('cb ([ {"id":"532cb",\n\n\n"x":\n3}\n]\n);')
756 d
= json
.loads(stripped
)
757 self
.assertEqual(d
, [{"id": "532cb", "x": 3}
])
759 stripped
= strip_jsonp('parseMetadata({"STATUS":"OK"})\n\n\n//epc')
760 d
= json
.loads(stripped
)
761 self
.assertEqual(d
, {'STATUS': 'OK'}
)
763 stripped
= strip_jsonp('ps.embedHandler({"status": "success"});')
764 d
= json
.loads(stripped
)
765 self
.assertEqual(d
, {'status': 'success'}
)
767 stripped
= strip_jsonp('window.cb && window.cb({"status": "success"});')
768 d
= json
.loads(stripped
)
769 self
.assertEqual(d
, {'status': 'success'}
)
771 stripped
= strip_jsonp('window.cb && cb({"status": "success"});')
772 d
= json
.loads(stripped
)
773 self
.assertEqual(d
, {'status': 'success'}
)
775 stripped
= strip_jsonp('({"status": "success"});')
776 d
= json
.loads(stripped
)
777 self
.assertEqual(d
, {'status': 'success'}
)
779 def test_strip_or_none(self
):
780 self
.assertEqual(strip_or_none(' abc'), 'abc')
781 self
.assertEqual(strip_or_none('abc '), 'abc')
782 self
.assertEqual(strip_or_none(' abc '), 'abc')
783 self
.assertEqual(strip_or_none('\tabc\t'), 'abc')
784 self
.assertEqual(strip_or_none('\n\tabc\n\t'), 'abc')
785 self
.assertEqual(strip_or_none('abc'), 'abc')
786 self
.assertEqual(strip_or_none(''), '')
787 self
.assertEqual(strip_or_none(None), None)
788 self
.assertEqual(strip_or_none(42), None)
789 self
.assertEqual(strip_or_none([]), None)
791 def test_uppercase_escape(self
):
792 self
.assertEqual(uppercase_escape('aä'), 'aä')
793 self
.assertEqual(uppercase_escape('\\U0001d550'), '𝕐')
795 def test_lowercase_escape(self
):
796 self
.assertEqual(lowercase_escape('aä'), 'aä')
797 self
.assertEqual(lowercase_escape('\\u0026'), '&')
799 def test_limit_length(self
):
800 self
.assertEqual(limit_length(None, 12), None)
801 self
.assertEqual(limit_length('foo', 12), 'foo')
803 limit_length('foo bar baz asd', 12).startswith('foo bar'))
804 self
.assertTrue('...' in limit_length('foo bar baz asd', 12))
806 def test_mimetype2ext(self
):
807 self
.assertEqual(mimetype2ext(None), None)
808 self
.assertEqual(mimetype2ext('video/x-flv'), 'flv')
809 self
.assertEqual(mimetype2ext('application/x-mpegURL'), 'm3u8')
810 self
.assertEqual(mimetype2ext('text/vtt'), 'vtt')
811 self
.assertEqual(mimetype2ext('text/vtt;charset=utf-8'), 'vtt')
812 self
.assertEqual(mimetype2ext('text/html; charset=utf-8'), 'html')
813 self
.assertEqual(mimetype2ext('audio/x-wav'), 'wav')
814 self
.assertEqual(mimetype2ext('audio/x-wav;codec=pcm'), 'wav')
816 def test_month_by_name(self
):
817 self
.assertEqual(month_by_name(None), None)
818 self
.assertEqual(month_by_name('December', 'en'), 12)
819 self
.assertEqual(month_by_name('décembre', 'fr'), 12)
820 self
.assertEqual(month_by_name('December'), 12)
821 self
.assertEqual(month_by_name('décembre'), None)
822 self
.assertEqual(month_by_name('Unknown', 'unknown'), None)
824 def test_parse_codecs(self
):
825 self
.assertEqual(parse_codecs(''), {})
826 self
.assertEqual(parse_codecs('avc1.77.30, mp4a.40.2'), {
827 'vcodec': 'avc1.77.30',
828 'acodec': 'mp4a.40.2',
830 self
.assertEqual(parse_codecs('mp4a.40.2'), {
832 'acodec': 'mp4a.40.2',
834 self
.assertEqual(parse_codecs('mp4a.40.5,avc1.42001e'), {
835 'vcodec': 'avc1.42001e',
836 'acodec': 'mp4a.40.5',
838 self
.assertEqual(parse_codecs('avc3.640028'), {
839 'vcodec': 'avc3.640028',
842 self
.assertEqual(parse_codecs(', h264,,newcodec,aac'), {
846 self
.assertEqual(parse_codecs('av01.0.05M.08'), {
847 'vcodec': 'av01.0.05M.08',
850 self
.assertEqual(parse_codecs('theora, vorbis'), {
854 self
.assertEqual(parse_codecs('unknownvcodec, unknownacodec'), {
855 'vcodec': 'unknownvcodec',
856 'acodec': 'unknownacodec',
858 self
.assertEqual(parse_codecs('unknown'), {})
860 def test_escape_rfc3986(self
):
861 reserved
= "!*'();:@&=+$,/?#[]"
862 unreserved
= 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_.~'
863 self
.assertEqual(escape_rfc3986(reserved
), reserved
)
864 self
.assertEqual(escape_rfc3986(unreserved
), unreserved
)
865 self
.assertEqual(escape_rfc3986('тест'), '%D1%82%D0%B5%D1%81%D1%82')
866 self
.assertEqual(escape_rfc3986('%D1%82%D0%B5%D1%81%D1%82'), '%D1%82%D0%B5%D1%81%D1%82')
867 self
.assertEqual(escape_rfc3986('foo bar'), 'foo%20bar')
868 self
.assertEqual(escape_rfc3986('foo%20bar'), 'foo%20bar')
870 def test_escape_url(self
):
872 escape_url('http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavré_FD.mp4'),
873 'http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavre%CC%81_FD.mp4'
876 escape_url('http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erklärt/Das-Erste/Video?documentId=22673108&bcastId=5290'),
877 'http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erkl%C3%A4rt/Das-Erste/Video?documentId=22673108&bcastId=5290'
880 escape_url('http://тест.рф/фрагмент'),
881 'http://xn--e1aybc.xn--p1ai/%D1%84%D1%80%D0%B0%D0%B3%D0%BC%D0%B5%D0%BD%D1%82'
884 escape_url('http://тест.рф/абв?абв=абв#абв'),
885 'http://xn--e1aybc.xn--p1ai/%D0%B0%D0%B1%D0%B2?%D0%B0%D0%B1%D0%B2=%D0%B0%D0%B1%D0%B2#%D0%B0%D0%B1%D0%B2'
887 self
.assertEqual(escape_url('http://vimeo.com/56015672#at=0'), 'http://vimeo.com/56015672#at=0')
889 def test_js_to_json_realworld(self
):
891 'clip':{'provider':'pseudo'}
893 self
.assertEqual(js_to_json(inp
), '''{
894 "clip":{"provider":"pseudo"}
896 json
.loads(js_to_json(inp
))
899 'playlist':[{'controls':{'all':null}}]
901 self
.assertEqual(js_to_json(inp
), '''{
902 "playlist":[{"controls":{"all":null}}]
905 inp
= '''"The CW\\'s \\'Crazy Ex-Girlfriend\\'"'''
906 self
.assertEqual(js_to_json(inp
), '''"The CW's 'Crazy Ex-Girlfriend'"''')
908 inp
= '"SAND Number: SAND 2013-7800P\\nPresenter: Tom Russo\\nHabanero Software Training - Xyce Software\\nXyce, Sandia\\u0027s"'
909 json_code
= js_to_json(inp
)
910 self
.assertEqual(json
.loads(json_code
), json
.loads(inp
))
913 0:{src:'skipped', type: 'application/dash+xml'},
914 1:{src:'skipped', type: 'application/vnd.apple.mpegURL'},
916 self
.assertEqual(js_to_json(inp
), '''{
917 "0":{"src":"skipped", "type": "application/dash+xml"},
918 "1":{"src":"skipped", "type": "application/vnd.apple.mpegURL"}
921 inp
= '''{"foo":101}'''
922 self
.assertEqual(js_to_json(inp
), '''{"foo":101}''')
924 inp
= '''{"duration": "00:01:07"}'''
925 self
.assertEqual(js_to_json(inp
), '''{"duration": "00:01:07"}''')
927 inp
= '''{segments: [{"offset":-3.885780586188048e-16,"duration":39.75000000000001}]}'''
928 self
.assertEqual(js_to_json(inp
), '''{"segments": [{"offset":-3.885780586188048e-16,"duration":39.75000000000001}]}''')
930 def test_js_to_json_edgecases(self
):
931 on
= js_to_json("{abc_def:'1\\'\\\\2\\\\\\'3\"4'}")
932 self
.assertEqual(json
.loads(on
), {"abc_def": "1'\\2\\'3\"4"}
)
934 on
= js_to_json('{"abc": true}')
935 self
.assertEqual(json
.loads(on
), {'abc': True}
)
937 # Ignore JavaScript code as well
944 self
.assertEqual(d
['x'], 1)
945 self
.assertEqual(d
['y'], 'a')
947 # Just drop ! prefix for now though this results in a wrong value
958 self
.assertEqual(json
.loads(on
), {
969 on
= js_to_json('["abc", "def",]')
970 self
.assertEqual(json
.loads(on
), ['abc', 'def'])
972 on
= js_to_json('[/*comment\n*/"abc"/*comment\n*/,/*comment\n*/"def",/*comment\n*/]')
973 self
.assertEqual(json
.loads(on
), ['abc', 'def'])
975 on
= js_to_json('[//comment\n"abc" //comment\n,//comment\n"def",//comment\n]')
976 self
.assertEqual(json
.loads(on
), ['abc', 'def'])
978 on
= js_to_json('{"abc": "def",}')
979 self
.assertEqual(json
.loads(on
), {'abc': 'def'}
)
981 on
= js_to_json('{/*comment\n*/"abc"/*comment\n*/:/*comment\n*/"def"/*comment\n*/,/*comment\n*/}')
982 self
.assertEqual(json
.loads(on
), {'abc': 'def'}
)
984 on
= js_to_json('{ 0: /* " \n */ ",]" , }')
985 self
.assertEqual(json
.loads(on
), {'0': ',]'}
)
987 on
= js_to_json('{ /*comment\n*/0/*comment\n*/: /* " \n */ ",]" , }')
988 self
.assertEqual(json
.loads(on
), {'0': ',]'}
)
990 on
= js_to_json('{ 0: // comment\n1 }')
991 self
.assertEqual(json
.loads(on
), {'0': 1}
)
993 on
= js_to_json(r
'["<p>x<\/p>"]')
994 self
.assertEqual(json
.loads(on
), ['<p>x</p>'])
996 on
= js_to_json(r
'["\xaa"]')
997 self
.assertEqual(json
.loads(on
), ['\u00aa'])
999 on
= js_to_json("['a\\\nb']")
1000 self
.assertEqual(json
.loads(on
), ['ab'])
1002 on
= js_to_json("/*comment\n*/[/*comment\n*/'a\\\nb'/*comment\n*/]/*comment\n*/")
1003 self
.assertEqual(json
.loads(on
), ['ab'])
1005 on
= js_to_json('{0xff:0xff}')
1006 self
.assertEqual(json
.loads(on
), {'255': 255}
)
1008 on
= js_to_json('{/*comment\n*/0xff/*comment\n*/:/*comment\n*/0xff/*comment\n*/}')
1009 self
.assertEqual(json
.loads(on
), {'255': 255}
)
1011 on
= js_to_json('{077:077}')
1012 self
.assertEqual(json
.loads(on
), {'63': 63}
)
1014 on
= js_to_json('{/*comment\n*/077/*comment\n*/:/*comment\n*/077/*comment\n*/}')
1015 self
.assertEqual(json
.loads(on
), {'63': 63}
)
1017 on
= js_to_json('{42:42}')
1018 self
.assertEqual(json
.loads(on
), {'42': 42}
)
1020 on
= js_to_json('{/*comment\n*/42/*comment\n*/:/*comment\n*/42/*comment\n*/}')
1021 self
.assertEqual(json
.loads(on
), {'42': 42}
)
1023 on
= js_to_json('{42:4.2e1}')
1024 self
.assertEqual(json
.loads(on
), {'42': 42.0}
)
1026 on
= js_to_json('{ "0x40": "0x40" }')
1027 self
.assertEqual(json
.loads(on
), {'0x40': '0x40'}
)
1029 on
= js_to_json('{ "040": "040" }')
1030 self
.assertEqual(json
.loads(on
), {'040': '040'}
)
1032 def test_js_to_json_malformed(self
):
1033 self
.assertEqual(js_to_json('42a1'), '42"a1"')
1034 self
.assertEqual(js_to_json('42a-1'), '42"a"-1')
1036 def test_extract_attributes(self
):
1037 self
.assertEqual(extract_attributes('<e x="y">'), {'x': 'y'}
)
1038 self
.assertEqual(extract_attributes("<e x='y'>"), {'x': 'y'}
)
1039 self
.assertEqual(extract_attributes('<e x=y>'), {'x': 'y'}
)
1040 self
.assertEqual(extract_attributes('<e x="a \'b\' c">'), {'x': "a 'b' c"}
)
1041 self
.assertEqual(extract_attributes('<e x=\'a "b" c\'>'), {'x': 'a "b" c'}
)
1042 self
.assertEqual(extract_attributes('<e x="y">'), {'x': 'y'}
)
1043 self
.assertEqual(extract_attributes('<e x="y">'), {'x': 'y'}
)
1044 self
.assertEqual(extract_attributes('<e x="&">'), {'x': '&'}
) # XML
1045 self
.assertEqual(extract_attributes('<e x=""">'), {'x': '"'}
)
1046 self
.assertEqual(extract_attributes('<e x="£">'), {'x': '£'}
) # HTML 3.2
1047 self
.assertEqual(extract_attributes('<e x="λ">'), {'x': 'λ'}
) # HTML 4.0
1048 self
.assertEqual(extract_attributes('<e x="&foo">'), {'x': '&foo'}
)
1049 self
.assertEqual(extract_attributes('<e x="\'">'), {'x': "'"}
)
1050 self
.assertEqual(extract_attributes('<e x=\'"\'>'), {'x': '"'}
)
1051 self
.assertEqual(extract_attributes('<e x >'), {'x': None}
)
1052 self
.assertEqual(extract_attributes('<e x=y a>'), {'x': 'y', 'a': None}
)
1053 self
.assertEqual(extract_attributes('<e x= y>'), {'x': 'y'}
)
1054 self
.assertEqual(extract_attributes('<e x=1 y=2 x=3>'), {'y': '2', 'x': '3'}
)
1055 self
.assertEqual(extract_attributes('<e \nx=\ny\n>'), {'x': 'y'}
)
1056 self
.assertEqual(extract_attributes('<e \nx=\n"y"\n>'), {'x': 'y'}
)
1057 self
.assertEqual(extract_attributes("<e \nx=\n'y'\n>"), {'x': 'y'}
)
1058 self
.assertEqual(extract_attributes('<e \nx="\ny\n">'), {'x': '\ny\n'}
)
1059 self
.assertEqual(extract_attributes('<e CAPS=x>'), {'caps': 'x'}
) # Names lowercased
1060 self
.assertEqual(extract_attributes('<e x=1 X=2>'), {'x': '2'}
)
1061 self
.assertEqual(extract_attributes('<e X=1 x=2>'), {'x': '2'}
)
1062 self
.assertEqual(extract_attributes('<e _:funny-name1=1>'), {'_:funny-name1': '1'}
)
1063 self
.assertEqual(extract_attributes('<e x="Fáilte 世界 \U0001f600">'), {'x': 'Fáilte 世界 \U0001f600'}
)
1064 self
.assertEqual(extract_attributes('<e x="décomposé">'), {'x': 'décompose\u0301'}
)
1065 # "Narrow" Python builds don't support unicode code points outside BMP.
1068 supports_outside_bmp
= True
1070 supports_outside_bmp
= False
1071 if supports_outside_bmp
:
1072 self
.assertEqual(extract_attributes('<e x="Smile 😀!">'), {'x': 'Smile \U0001f600!'}
)
1073 # Malformed HTML should not break attributes extraction on older Python
1074 self
.assertEqual(extract_attributes('<mal"formed/>'), {})
1076 def test_clean_html(self
):
1077 self
.assertEqual(clean_html('a:\nb'), 'a: b')
1078 self
.assertEqual(clean_html('a:\n "b"'), 'a: "b"')
1079 self
.assertEqual(clean_html('a<br>\xa0b'), 'a\nb')
1081 def test_intlist_to_bytes(self
):
1083 intlist_to_bytes([0, 1, 127, 128, 255]),
1084 b
'\x00\x01\x7f\x80\xff')
1086 def test_args_to_str(self
):
1088 args_to_str(['foo', 'ba/r', '-baz', '2 be', '']),
1089 'foo ba/r -baz \'2 be\' \'\'' if compat_os_name
!= 'nt' else 'foo ba/r -baz "2 be" ""'
1092 def test_parse_filesize(self
):
1093 self
.assertEqual(parse_filesize(None), None)
1094 self
.assertEqual(parse_filesize(''), None)
1095 self
.assertEqual(parse_filesize('91 B'), 91)
1096 self
.assertEqual(parse_filesize('foobar'), None)
1097 self
.assertEqual(parse_filesize('2 MiB'), 2097152)
1098 self
.assertEqual(parse_filesize('5 GB'), 5000000000)
1099 self
.assertEqual(parse_filesize('1.2Tb'), 1200000000000)
1100 self
.assertEqual(parse_filesize('1.2tb'), 1200000000000)
1101 self
.assertEqual(parse_filesize('1,24 KB'), 1240)
1102 self
.assertEqual(parse_filesize('1,24 kb'), 1240)
1103 self
.assertEqual(parse_filesize('8.5 megabytes'), 8500000)
1105 def test_parse_count(self
):
1106 self
.assertEqual(parse_count(None), None)
1107 self
.assertEqual(parse_count(''), None)
1108 self
.assertEqual(parse_count('0'), 0)
1109 self
.assertEqual(parse_count('1000'), 1000)
1110 self
.assertEqual(parse_count('1.000'), 1000)
1111 self
.assertEqual(parse_count('1.1k'), 1100)
1112 self
.assertEqual(parse_count('1.1kk'), 1100000)
1113 self
.assertEqual(parse_count('1.1kk '), 1100000)
1114 self
.assertEqual(parse_count('1.1kk views'), 1100000)
1116 def test_parse_resolution(self
):
1117 self
.assertEqual(parse_resolution(None), {})
1118 self
.assertEqual(parse_resolution(''), {})
1119 self
.assertEqual(parse_resolution('1920x1080'), {'width': 1920, 'height': 1080}
)
1120 self
.assertEqual(parse_resolution('1920×1080'), {'width': 1920, 'height': 1080}
)
1121 self
.assertEqual(parse_resolution('1920 x 1080'), {'width': 1920, 'height': 1080}
)
1122 self
.assertEqual(parse_resolution('720p'), {'height': 720}
)
1123 self
.assertEqual(parse_resolution('4k'), {'height': 2160}
)
1124 self
.assertEqual(parse_resolution('8K'), {'height': 4320}
)
1126 def test_parse_bitrate(self
):
1127 self
.assertEqual(parse_bitrate(None), None)
1128 self
.assertEqual(parse_bitrate(''), None)
1129 self
.assertEqual(parse_bitrate('300kbps'), 300)
1130 self
.assertEqual(parse_bitrate('1500kbps'), 1500)
1131 self
.assertEqual(parse_bitrate('300 kbps'), 300)
1133 def test_version_tuple(self
):
1134 self
.assertEqual(version_tuple('1'), (1,))
1135 self
.assertEqual(version_tuple('10.23.344'), (10, 23, 344))
1136 self
.assertEqual(version_tuple('10.1-6'), (10, 1, 6)) # avconv style
1138 def test_detect_exe_version(self
):
1139 self
.assertEqual(detect_exe_version('''ffmpeg version 1.2.1
1140 built on May 27 2013 08:37:26 with gcc 4.7 (Debian 4.7.3-4)
1141 configuration: --prefix=/usr --extra-'''), '1.2.1')
1142 self
.assertEqual(detect_exe_version('''ffmpeg version N-63176-g1fb4685
1143 built on May 15 2014 22:09:06 with gcc 4.8.2 (GCC)'''), 'N-63176-g1fb4685')
1144 self
.assertEqual(detect_exe_version('''X server found. dri2 connection failed!
1145 Trying to open render node...
1146 Success at /dev/dri/renderD128.
1147 ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')
1149 def test_age_restricted(self
):
1150 self
.assertFalse(age_restricted(None, 10)) # unrestricted content
1151 self
.assertFalse(age_restricted(1, None)) # unrestricted policy
1152 self
.assertFalse(age_restricted(8, 10))
1153 self
.assertTrue(age_restricted(18, 14))
1154 self
.assertFalse(age_restricted(18, 18))
1156 def test_is_html(self
):
1157 self
.assertFalse(is_html(b
'\x49\x44\x43<html'))
1158 self
.assertTrue(is_html(b
'<!DOCTYPE foo>\xaaa'))
1159 self
.assertTrue(is_html( # UTF-8 with BOM
1160 b
'\xef\xbb\xbf<!DOCTYPE foo>\xaaa'))
1161 self
.assertTrue(is_html( # UTF-16-LE
1162 b
'\xff\xfe<\x00h\x00t\x00m\x00l\x00>\x00\xe4\x00'
1164 self
.assertTrue(is_html( # UTF-16-BE
1165 b
'\xfe\xff\x00<\x00h\x00t\x00m\x00l\x00>\x00\xe4'
1167 self
.assertTrue(is_html( # UTF-32-BE
1168 b
'\x00\x00\xFE\xFF\x00\x00\x00<\x00\x00\x00h\x00\x00\x00t\x00\x00\x00m\x00\x00\x00l\x00\x00\x00>\x00\x00\x00\xe4'))
1169 self
.assertTrue(is_html( # UTF-32-LE
1170 b
'\xFF\xFE\x00\x00<\x00\x00\x00h\x00\x00\x00t\x00\x00\x00m\x00\x00\x00l\x00\x00\x00>\x00\x00\x00\xe4\x00\x00\x00'))
1172 def test_render_table(self
):
1176 [[123, 4], [9999, 51]]),
1181 def test_match_str(self
):
1182 self
.assertRaises(ValueError, match_str
, 'xy>foobar', {})
1183 self
.assertFalse(match_str('xy', {'x': 1200}
))
1184 self
.assertTrue(match_str('!xy', {'x': 1200}
))
1185 self
.assertTrue(match_str('x', {'x': 1200}
))
1186 self
.assertFalse(match_str('!x', {'x': 1200}
))
1187 self
.assertTrue(match_str('x', {'x': 0}
))
1188 self
.assertFalse(match_str('x>0', {'x': 0}
))
1189 self
.assertFalse(match_str('x>0', {}))
1190 self
.assertTrue(match_str('x>?0', {}))
1191 self
.assertTrue(match_str('x>1K', {'x': 1200}
))
1192 self
.assertFalse(match_str('x>2K', {'x': 1200}
))
1193 self
.assertTrue(match_str('x>=1200 & x < 1300', {'x': 1200}
))
1194 self
.assertFalse(match_str('x>=1100 & x < 1200', {'x': 1200}
))
1195 self
.assertFalse(match_str('y=a212', {'y': 'foobar42'}
))
1196 self
.assertTrue(match_str('y=foobar42', {'y': 'foobar42'}
))
1197 self
.assertFalse(match_str('y!=foobar42', {'y': 'foobar42'}
))
1198 self
.assertTrue(match_str('y!=foobar2', {'y': 'foobar42'}
))
1199 self
.assertFalse(match_str(
1200 'like_count > 100 & dislike_count <? 50 & description',
1201 {'like_count': 90, 'description': 'foo'}
))
1202 self
.assertTrue(match_str(
1203 'like_count > 100 & dislike_count <? 50 & description',
1204 {'like_count': 190, 'description': 'foo'}
))
1205 self
.assertFalse(match_str(
1206 'like_count > 100 & dislike_count <? 50 & description',
1207 {'like_count': 190, 'dislike_count': 60, 'description': 'foo'}
))
1208 self
.assertFalse(match_str(
1209 'like_count > 100 & dislike_count <? 50 & description',
1210 {'like_count': 190, 'dislike_count': 10}
))
1211 self
.assertTrue(match_str('is_live', {'is_live': True}
))
1212 self
.assertFalse(match_str('is_live', {'is_live': False}
))
1213 self
.assertFalse(match_str('is_live', {'is_live': None}
))
1214 self
.assertFalse(match_str('is_live', {}))
1215 self
.assertFalse(match_str('!is_live', {'is_live': True}
))
1216 self
.assertTrue(match_str('!is_live', {'is_live': False}
))
1217 self
.assertTrue(match_str('!is_live', {'is_live': None}
))
1218 self
.assertTrue(match_str('!is_live', {}))
1219 self
.assertTrue(match_str('title', {'title': 'abc'}
))
1220 self
.assertTrue(match_str('title', {'title': ''}
))
1221 self
.assertFalse(match_str('!title', {'title': 'abc'}
))
1222 self
.assertFalse(match_str('!title', {'title': ''}
))
1224 def test_parse_dfxp_time_expr(self
):
1225 self
.assertEqual(parse_dfxp_time_expr(None), None)
1226 self
.assertEqual(parse_dfxp_time_expr(''), None)
1227 self
.assertEqual(parse_dfxp_time_expr('0.1'), 0.1)
1228 self
.assertEqual(parse_dfxp_time_expr('0.1s'), 0.1)
1229 self
.assertEqual(parse_dfxp_time_expr('00:00:01'), 1.0)
1230 self
.assertEqual(parse_dfxp_time_expr('00:00:01.100'), 1.1)
1231 self
.assertEqual(parse_dfxp_time_expr('00:00:01:100'), 1.1)
1233 def test_dfxp2srt(self
):
1234 dfxp_data
= '''<?xml version="1.0" encoding="UTF-8"?>
1235 <tt xmlns="http://www.w3.org/ns/ttml" xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter">
1238 <p begin="0" end="1">The following line contains Chinese characters and special symbols</p>
1239 <p begin="1" end="2">第二行<br/>♪♪</p>
1240 <p begin="2" dur="1"><span>Third<br/>Line</span></p>
1241 <p begin="3" end="-1">Lines with invalid timestamps are ignored</p>
1242 <p begin="-1" end="-1">Ignore, two</p>
1243 <p begin="3" dur="-1">Ignored, three</p>
1246 </tt>'''.encode('utf-8')
1248 00:00:00,000 --> 00:00:01,000
1249 The following line contains Chinese characters and special symbols
1252 00:00:01,000 --> 00:00:02,000
1257 00:00:02,000 --> 00:00:03,000
1262 self
.assertEqual(dfxp2srt(dfxp_data
), srt_data
)
1264 dfxp_data_no_default_namespace
= '''<?xml version="1.0" encoding="UTF-8"?>
1265 <tt xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter">
1268 <p begin="0" end="1">The first line</p>
1271 </tt>'''.encode('utf-8')
1273 00:00:00,000 --> 00:00:01,000
1277 self
.assertEqual(dfxp2srt(dfxp_data_no_default_namespace
), srt_data
)
1279 dfxp_data_with_style
= '''<?xml version="1.0" encoding="utf-8"?>
1280 <tt xmlns="http://www.w3.org/2006/10/ttaf1" xmlns:ttp="http://www.w3.org/2006/10/ttaf1#parameter" ttp:timeBase="media" xmlns:tts="http://www.w3.org/2006/10/ttaf1#style" xml:lang="en" xmlns:ttm="http://www.w3.org/2006/10/ttaf1#metadata">
1283 <style id="s2" style="s0" tts:color="cyan" tts:fontWeight="bold" />
1284 <style id="s1" style="s0" tts:color="yellow" tts:fontStyle="italic" />
1285 <style id="s3" style="s0" tts:color="lime" tts:textDecoration="underline" />
1286 <style id="s0" tts:backgroundColor="black" tts:fontStyle="normal" tts:fontSize="16" tts:fontFamily="sansSerif" tts:color="white" />
1289 <body tts:textAlign="center" style="s0">
1291 <p begin="00:00:02.08" id="p0" end="00:00:05.84">default style<span tts:color="red">custom style</span></p>
1292 <p style="s2" begin="00:00:02.08" id="p0" end="00:00:05.84"><span tts:color="lime">part 1<br /></span><span tts:color="cyan">part 2</span></p>
1293 <p style="s3" begin="00:00:05.84" id="p1" end="00:00:09.56">line 3<br />part 3</p>
1294 <p style="s1" tts:textDecoration="underline" begin="00:00:09.56" id="p2" end="00:00:12.36"><span style="s2" tts:color="lime">inner<br /> </span>style</p>
1297 </tt>'''.encode('utf-8')
1299 00:00:02,080 --> 00:00:05,839
1300 <font color="white" face="sansSerif" size="16">default style<font color="red">custom style</font></font>
1303 00:00:02,080 --> 00:00:05,839
1304 <b><font color="cyan" face="sansSerif" size="16"><font color="lime">part 1
1305 </font>part 2</font></b>
1308 00:00:05,839 --> 00:00:09,560
1309 <u><font color="lime">line 3
1313 00:00:09,560 --> 00:00:12,359
1314 <i><u><font color="yellow"><font color="lime">inner
1315 </font>style</font></u></i>
1318 self
.assertEqual(dfxp2srt(dfxp_data_with_style
), srt_data
)
1320 dfxp_data_non_utf8
= '''<?xml version="1.0" encoding="UTF-16"?>
1321 <tt xmlns="http://www.w3.org/ns/ttml" xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter">
1324 <p begin="0" end="1">Line 1</p>
1325 <p begin="1" end="2">第二行</p>
1328 </tt>'''.encode('utf-16')
1330 00:00:00,000 --> 00:00:01,000
1334 00:00:01,000 --> 00:00:02,000
1338 self
.assertEqual(dfxp2srt(dfxp_data_non_utf8
), srt_data
)
1340 def test_cli_option(self
):
1341 self
.assertEqual(cli_option({'proxy': '127.0.0.1:3128'}
, '--proxy', 'proxy'), ['--proxy', '127.0.0.1:3128'])
1342 self
.assertEqual(cli_option({'proxy': None}
, '--proxy', 'proxy'), [])
1343 self
.assertEqual(cli_option({}, '--proxy', 'proxy'), [])
1344 self
.assertEqual(cli_option({'retries': 10}
, '--retries', 'retries'), ['--retries', '10'])
1346 def test_cli_valueless_option(self
):
1347 self
.assertEqual(cli_valueless_option(
1348 {'downloader': 'external'}
, '--external-downloader', 'downloader', 'external'), ['--external-downloader'])
1349 self
.assertEqual(cli_valueless_option(
1350 {'downloader': 'internal'}
, '--external-downloader', 'downloader', 'external'), [])
1351 self
.assertEqual(cli_valueless_option(
1352 {'nocheckcertificate': True}
, '--no-check-certificate', 'nocheckcertificate'), ['--no-check-certificate'])
1353 self
.assertEqual(cli_valueless_option(
1354 {'nocheckcertificate': False}
, '--no-check-certificate', 'nocheckcertificate'), [])
1355 self
.assertEqual(cli_valueless_option(
1356 {'checkcertificate': True}
, '--no-check-certificate', 'checkcertificate', False), [])
1357 self
.assertEqual(cli_valueless_option(
1358 {'checkcertificate': False}
, '--no-check-certificate', 'checkcertificate', False), ['--no-check-certificate'])
1360 def test_cli_bool_option(self
):
1363 {'nocheckcertificate': True}
, '--no-check-certificate', 'nocheckcertificate'),
1364 ['--no-check-certificate', 'true'])
1367 {'nocheckcertificate': True}
, '--no-check-certificate', 'nocheckcertificate', separator
='='),
1368 ['--no-check-certificate=true'])
1371 {'nocheckcertificate': True}
, '--check-certificate', 'nocheckcertificate', 'false', 'true'),
1372 ['--check-certificate', 'false'])
1375 {'nocheckcertificate': True}
, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='),
1376 ['--check-certificate=false'])
1379 {'nocheckcertificate': False}
, '--check-certificate', 'nocheckcertificate', 'false', 'true'),
1380 ['--check-certificate', 'true'])
1383 {'nocheckcertificate': False}
, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='),
1384 ['--check-certificate=true'])
1387 {}, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='),
1390 def test_ohdave_rsa_encrypt(self
):
1391 N
= 0xab86b6371b5318aaa1d3c9e612a9f1264f372323c8c0f19875b5fc3b3fd3afcc1e5bec527aa94bfa85bffc157e4245aebda05389a5357b75115ac94f074aefcd
1395 ohdave_rsa_encrypt(b
'aa111222', e
, N
),
1396 '726664bd9a23fd0c70f9f1b84aab5e3905ce1e45a584e9cbcf9bcc7510338fc1986d6c599ff990d923aa43c51c0d9013cd572e13bc58f4ae48f2ed8c0b0ba881')
1398 def test_pkcs1pad(self
):
1400 padded_data
= pkcs1pad(data
, 32)
1401 self
.assertEqual(padded_data
[:2], [0, 2])
1402 self
.assertEqual(padded_data
[28:], [0, 1, 2, 3])
1404 self
.assertRaises(ValueError, pkcs1pad
, data
, 8)
1406 def test_encode_base_n(self
):
1407 self
.assertEqual(encode_base_n(0, 30), '0')
1408 self
.assertEqual(encode_base_n(80, 30), '2k')
1410 custom_table
= '9876543210ZYXWVUTSRQPONMLKJIHGFEDCBA'
1411 self
.assertEqual(encode_base_n(0, 30, custom_table
), '9')
1412 self
.assertEqual(encode_base_n(80, 30, custom_table
), '7P')
1414 self
.assertRaises(ValueError, encode_base_n
, 0, 70)
1415 self
.assertRaises(ValueError, encode_base_n
, 0, 60, custom_table
)
1417 def test_caesar(self
):
1418 self
.assertEqual(caesar('ace', 'abcdef', 2), 'cea')
1419 self
.assertEqual(caesar('cea', 'abcdef', -2), 'ace')
1420 self
.assertEqual(caesar('ace', 'abcdef', -2), 'eac')
1421 self
.assertEqual(caesar('eac', 'abcdef', 2), 'ace')
1422 self
.assertEqual(caesar('ace', 'abcdef', 0), 'ace')
1423 self
.assertEqual(caesar('xyz', 'abcdef', 2), 'xyz')
1424 self
.assertEqual(caesar('abc', 'acegik', 2), 'ebg')
1425 self
.assertEqual(caesar('ebg', 'acegik', -2), 'abc')
1427 def test_rot47(self
):
1428 self
.assertEqual(rot47('youtube-dlc'), r
'J@FEF36\5=4')
1429 self
.assertEqual(rot47('YOUTUBE-DLC'), r
'*~&%&qt\s{r')
1431 def test_urshift(self
):
1432 self
.assertEqual(urshift(3, 1), 1)
1433 self
.assertEqual(urshift(-3, 1), 2147483646)
1435 def test_get_element_by_class(self
):
1437 <span class="foo bar">nice</span>
1440 self
.assertEqual(get_element_by_class('foo', html
), 'nice')
1441 self
.assertEqual(get_element_by_class('no-such-class', html
), None)
1443 def test_get_element_by_attribute(self
):
1445 <span class="foo bar">nice</span>
1448 self
.assertEqual(get_element_by_attribute('class', 'foo bar', html
), 'nice')
1449 self
.assertEqual(get_element_by_attribute('class', 'foo', html
), None)
1450 self
.assertEqual(get_element_by_attribute('class', 'no-such-foo', html
), None)
1453 <div itemprop="author" itemscope>foo</div>
1456 self
.assertEqual(get_element_by_attribute('itemprop', 'author', html
), 'foo')
1458 def test_get_elements_by_class(self
):
1460 <span class="foo bar">nice</span><span class="foo bar">also nice</span>
1463 self
.assertEqual(get_elements_by_class('foo', html
), ['nice', 'also nice'])
1464 self
.assertEqual(get_elements_by_class('no-such-class', html
), [])
1466 def test_get_elements_by_attribute(self
):
1468 <span class="foo bar">nice</span><span class="foo bar">also nice</span>
1471 self
.assertEqual(get_elements_by_attribute('class', 'foo bar', html
), ['nice', 'also nice'])
1472 self
.assertEqual(get_elements_by_attribute('class', 'foo', html
), [])
1473 self
.assertEqual(get_elements_by_attribute('class', 'no-such-foo', html
), [])
1475 def test_iri_to_uri(self
):
1477 iri_to_uri('https://www.google.com/search?q=foo&ie=utf-8&oe=utf-8&client=firefox-b'),
1478 'https://www.google.com/search?q=foo&ie=utf-8&oe=utf-8&client=firefox-b') # Same
1480 iri_to_uri('https://www.google.com/search?q=Käsesoßenrührlöffel'), # German for cheese sauce stirring spoon
1481 'https://www.google.com/search?q=K%C3%A4seso%C3%9Fenr%C3%BChrl%C3%B6ffel')
1483 iri_to_uri('https://www.google.com/search?q=lt<+gt>+eq%3D+amp%26+percent%25+hash%23+colon%3A+tilde~#trash=?&garbage=#'),
1484 'https://www.google.com/search?q=lt%3C+gt%3E+eq%3D+amp%26+percent%25+hash%23+colon%3A+tilde~#trash=?&garbage=#')
1486 iri_to_uri('http://правозащита38.рф/category/news/'),
1487 'http://xn--38-6kcaak9aj5chl4a3g.xn--p1ai/category/news/')
1489 iri_to_uri('http://www.правозащита38.рф/category/news/'),
1490 'http://www.xn--38-6kcaak9aj5chl4a3g.xn--p1ai/category/news/')
1492 iri_to_uri('https://i❤.ws/emojidomain/👍👏🤝💪'),
1493 'https://xn--i-7iq.ws/emojidomain/%F0%9F%91%8D%F0%9F%91%8F%F0%9F%A4%9D%F0%9F%92%AA')
1495 iri_to_uri('http://日本語.jp/'),
1496 'http://xn--wgv71a119e.jp/')
1498 iri_to_uri('http://导航.中国/'),
1499 'http://xn--fet810g.xn--fiqs8s/')
1501 def test_clean_podcast_url(self
):
1502 self
.assertEqual(clean_podcast_url('https://www.podtrac.com/pts/redirect.mp3/chtbl.com/track/5899E/traffic.megaphone.fm/HSW7835899191.mp3'), 'https://traffic.megaphone.fm/HSW7835899191.mp3')
1503 self
.assertEqual(clean_podcast_url('https://play.podtrac.com/npr-344098539/edge1.pod.npr.org/anon.npr-podcasts/podcast/npr/waitwait/2020/10/20201003_waitwait_wwdtmpodcast201003-015621a5-f035-4eca-a9a1-7c118d90bc3c.mp3'), 'https://edge1.pod.npr.org/anon.npr-podcasts/podcast/npr/waitwait/2020/10/20201003_waitwait_wwdtmpodcast201003-015621a5-f035-4eca-a9a1-7c118d90bc3c.mp3')
1506 if __name__
== '__main__':