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_dl
.utils
import (
91 from youtube_dl
.compat
import (
93 compat_etree_fromstring
,
99 class TestUtil(unittest
.TestCase
):
100 def test_timeconvert(self
):
101 self
.assertTrue(timeconvert('') is None)
102 self
.assertTrue(timeconvert('bougrg') is None)
104 def test_sanitize_filename(self
):
105 self
.assertEqual(sanitize_filename('abc'), 'abc')
106 self
.assertEqual(sanitize_filename('abc_d-e'), 'abc_d-e')
108 self
.assertEqual(sanitize_filename('123'), '123')
110 self
.assertEqual('abc_de', sanitize_filename('abc/de'))
111 self
.assertFalse('/' in sanitize_filename('abc/de///'))
113 self
.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de'))
114 self
.assertEqual('xxx', sanitize_filename('xxx/<>\\*|'))
115 self
.assertEqual('yes no', sanitize_filename('yes? no'))
116 self
.assertEqual('this - that', sanitize_filename('this: that'))
118 self
.assertEqual(sanitize_filename('AT&T'), 'AT&T')
120 self
.assertEqual(sanitize_filename(aumlaut
), aumlaut
)
121 tests
= '\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430'
122 self
.assertEqual(sanitize_filename(tests
), tests
)
125 sanitize_filename('New World record at 0:12:34'),
126 'New World record at 0_12_34')
128 self
.assertEqual(sanitize_filename('--gasdgf'), '_-gasdgf')
129 self
.assertEqual(sanitize_filename('--gasdgf', is_id
=True), '--gasdgf')
130 self
.assertEqual(sanitize_filename('.gasdgf'), 'gasdgf')
131 self
.assertEqual(sanitize_filename('.gasdgf', is_id
=True), '.gasdgf')
135 for fbc
in forbidden
:
136 self
.assertTrue(fbc
not in sanitize_filename(fc
))
138 def test_sanitize_filename_restricted(self
):
139 self
.assertEqual(sanitize_filename('abc', restricted
=True), 'abc')
140 self
.assertEqual(sanitize_filename('abc_d-e', restricted
=True), 'abc_d-e')
142 self
.assertEqual(sanitize_filename('123', restricted
=True), '123')
144 self
.assertEqual('abc_de', sanitize_filename('abc/de', restricted
=True))
145 self
.assertFalse('/' in sanitize_filename('abc/de///', restricted
=True))
147 self
.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de', restricted
=True))
148 self
.assertEqual('xxx', sanitize_filename('xxx/<>\\*|', restricted
=True))
149 self
.assertEqual('yes_no', sanitize_filename('yes? no', restricted
=True))
150 self
.assertEqual('this_-_that', sanitize_filename('this: that', restricted
=True))
152 tests
= 'aäb\u4e2d\u56fd\u7684c'
153 self
.assertEqual(sanitize_filename(tests
, restricted
=True), 'aab_c')
154 self
.assertTrue(sanitize_filename('\xf6', restricted
=True) != '') # No empty filename
156 forbidden
= '"\0\\/&!: \'\t\n()[]{}$;`^,#'
158 for fbc
in forbidden
:
159 self
.assertTrue(fbc
not in sanitize_filename(fc
, restricted
=True))
161 # Handle a common case more neatly
162 self
.assertEqual(sanitize_filename('\u5927\u58f0\u5e26 - Song', restricted
=True), 'Song')
163 self
.assertEqual(sanitize_filename('\u603b\u7edf: Speech', restricted
=True), 'Speech')
164 # .. but make sure the file name is never empty
165 self
.assertTrue(sanitize_filename('-', restricted
=True) != '')
166 self
.assertTrue(sanitize_filename(':', restricted
=True) != '')
168 self
.assertEqual(sanitize_filename(
169 'ÂÃÄÀÁÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖŐØŒÙÚÛÜŰÝÞßàáâãäåæçèéêëìíîïðñòóôõöőøœùúûüűýþÿ', restricted
=True),
170 'AAAAAAAECEEEEIIIIDNOOOOOOOOEUUUUUYPssaaaaaaaeceeeeiiiionooooooooeuuuuuypy')
172 def test_sanitize_ids(self
):
173 self
.assertEqual(sanitize_filename('_n_cd26wFpw', is_id
=True), '_n_cd26wFpw')
174 self
.assertEqual(sanitize_filename('_BD_eEpuzXw', is_id
=True), '_BD_eEpuzXw')
175 self
.assertEqual(sanitize_filename('N0Y__7-UOdI', is_id
=True), 'N0Y__7-UOdI')
177 def test_sanitize_path(self
):
178 if sys
.platform
!= 'win32':
181 self
.assertEqual(sanitize_path('abc'), 'abc')
182 self
.assertEqual(sanitize_path('abc/def'), 'abc\\def')
183 self
.assertEqual(sanitize_path('abc\\def'), 'abc\\def')
184 self
.assertEqual(sanitize_path('abc|def'), 'abc#def')
185 self
.assertEqual(sanitize_path('<>:"|?*'), '#######')
186 self
.assertEqual(sanitize_path('C:/abc/def'), 'C:\\abc\\def')
187 self
.assertEqual(sanitize_path('C?:/abc/def'), 'C##\\abc\\def')
189 self
.assertEqual(sanitize_path('\\\\?\\UNC\\ComputerName\\abc'), '\\\\?\\UNC\\ComputerName\\abc')
190 self
.assertEqual(sanitize_path('\\\\?\\UNC/ComputerName/abc'), '\\\\?\\UNC\\ComputerName\\abc')
192 self
.assertEqual(sanitize_path('\\\\?\\C:\\abc'), '\\\\?\\C:\\abc')
193 self
.assertEqual(sanitize_path('\\\\?\\C:/abc'), '\\\\?\\C:\\abc')
194 self
.assertEqual(sanitize_path('\\\\?\\C:\\ab?c\\de:f'), '\\\\?\\C:\\ab#c\\de#f')
195 self
.assertEqual(sanitize_path('\\\\?\\C:\\abc'), '\\\\?\\C:\\abc')
198 sanitize_path('youtube/%(uploader)s/%(autonumber)s-%(title)s-%(upload_date)s.%(ext)s'),
199 'youtube\\%(uploader)s\\%(autonumber)s-%(title)s-%(upload_date)s.%(ext)s')
202 sanitize_path('youtube/TheWreckingYard ./00001-Not bad, Especially for Free! (1987 Yamaha 700)-20141116.mp4.part'),
203 'youtube\\TheWreckingYard #\\00001-Not bad, Especially for Free! (1987 Yamaha 700)-20141116.mp4.part')
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..#')
208 self
.assertEqual(sanitize_path('../abc'), '..\\abc')
209 self
.assertEqual(sanitize_path('../../abc'), '..\\..\\abc')
210 self
.assertEqual(sanitize_path('./abc'), 'abc')
211 self
.assertEqual(sanitize_path('./../abc'), '..\\abc')
213 def test_prepend_extension(self
):
214 self
.assertEqual(prepend_extension('abc.ext', 'temp'), 'abc.temp.ext')
215 self
.assertEqual(prepend_extension('abc.ext', 'temp', 'ext'), 'abc.temp.ext')
216 self
.assertEqual(prepend_extension('abc.unexpected_ext', 'temp', 'ext'), 'abc.unexpected_ext.temp')
217 self
.assertEqual(prepend_extension('abc', 'temp'), 'abc.temp')
218 self
.assertEqual(prepend_extension('.abc', 'temp'), '.abc.temp')
219 self
.assertEqual(prepend_extension('.abc.ext', 'temp'), '.abc.temp.ext')
221 def test_replace_extension(self
):
222 self
.assertEqual(replace_extension('abc.ext', 'temp'), 'abc.temp')
223 self
.assertEqual(replace_extension('abc.ext', 'temp', 'ext'), 'abc.temp')
224 self
.assertEqual(replace_extension('abc.unexpected_ext', 'temp', 'ext'), 'abc.unexpected_ext.temp')
225 self
.assertEqual(replace_extension('abc', 'temp'), 'abc.temp')
226 self
.assertEqual(replace_extension('.abc', 'temp'), '.abc.temp')
227 self
.assertEqual(replace_extension('.abc.ext', 'temp'), '.abc.temp')
229 def test_remove_start(self
):
230 self
.assertEqual(remove_start(None, 'A - '), None)
231 self
.assertEqual(remove_start('A - B', 'A - '), 'B')
232 self
.assertEqual(remove_start('B - A', 'A - '), 'B - A')
234 def test_remove_end(self
):
235 self
.assertEqual(remove_end(None, ' - B'), None)
236 self
.assertEqual(remove_end('A - B', ' - B'), 'A')
237 self
.assertEqual(remove_end('B - A', ' - B'), 'B - A')
239 def test_remove_quotes(self
):
240 self
.assertEqual(remove_quotes(None), None)
241 self
.assertEqual(remove_quotes('"'), '"')
242 self
.assertEqual(remove_quotes("'"), "'")
243 self
.assertEqual(remove_quotes(';'), ';')
244 self
.assertEqual(remove_quotes('";'), '";')
245 self
.assertEqual(remove_quotes('""'), '')
246 self
.assertEqual(remove_quotes('";"'), ';')
248 def test_ordered_set(self
):
249 self
.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7])
250 self
.assertEqual(orderedSet([]), [])
251 self
.assertEqual(orderedSet([1]), [1])
252 # keep the list ordered
253 self
.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1])
255 def test_unescape_html(self
):
256 self
.assertEqual(unescapeHTML('%20;'), '%20;')
257 self
.assertEqual(unescapeHTML('/'), '/')
258 self
.assertEqual(unescapeHTML('/'), '/')
259 self
.assertEqual(unescapeHTML('é'), 'é')
260 self
.assertEqual(unescapeHTML('�'), '�')
262 self
.assertEqual(unescapeHTML('.''), '.\'')
264 def test_date_from_str(self
):
265 self
.assertEqual(date_from_str('yesterday'), date_from_str('now-1day'))
266 self
.assertEqual(date_from_str('now+7day'), date_from_str('now+1week'))
267 self
.assertEqual(date_from_str('now+14day'), date_from_str('now+2week'))
268 self
.assertEqual(date_from_str('now+365day'), date_from_str('now+1year'))
269 self
.assertEqual(date_from_str('now+30day'), date_from_str('now+1month'))
271 def test_daterange(self
):
272 _20century
= DateRange("19000101", "20000101")
273 self
.assertFalse("17890714" in _20century
)
274 _ac
= DateRange("00010101")
275 self
.assertTrue("19690721" in _ac
)
276 _firstmilenium
= DateRange(end
="10000101")
277 self
.assertTrue("07110427" in _firstmilenium
)
279 def test_unified_dates(self
):
280 self
.assertEqual(unified_strdate('December 21, 2010'), '20101221')
281 self
.assertEqual(unified_strdate('8/7/2009'), '20090708')
282 self
.assertEqual(unified_strdate('Dec 14, 2012'), '20121214')
283 self
.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
284 self
.assertEqual(unified_strdate('1968 12 10'), '19681210')
285 self
.assertEqual(unified_strdate('1968-12-10'), '19681210')
286 self
.assertEqual(unified_strdate('28/01/2014 21:00:00 +0100'), '20140128')
288 unified_strdate('11/26/2014 11:30:00 AM PST', day_first
=False),
291 unified_strdate('2/2/2015 6:47:40 PM', day_first
=False),
293 self
.assertEqual(unified_strdate('Feb 14th 2016 5:45PM'), '20160214')
294 self
.assertEqual(unified_strdate('25-09-2014'), '20140925')
295 self
.assertEqual(unified_strdate('27.02.2016 17:30'), '20160227')
296 self
.assertEqual(unified_strdate('UNKNOWN DATE FORMAT'), None)
297 self
.assertEqual(unified_strdate('Feb 7, 2016 at 6:35 pm'), '20160207')
298 self
.assertEqual(unified_strdate('July 15th, 2013'), '20130715')
299 self
.assertEqual(unified_strdate('September 1st, 2013'), '20130901')
300 self
.assertEqual(unified_strdate('Sep 2nd, 2013'), '20130902')
302 def test_unified_timestamps(self
):
303 self
.assertEqual(unified_timestamp('December 21, 2010'), 1292889600)
304 self
.assertEqual(unified_timestamp('8/7/2009'), 1247011200)
305 self
.assertEqual(unified_timestamp('Dec 14, 2012'), 1355443200)
306 self
.assertEqual(unified_timestamp('2012/10/11 01:56:38 +0000'), 1349920598)
307 self
.assertEqual(unified_timestamp('1968 12 10'), -33436800)
308 self
.assertEqual(unified_timestamp('1968-12-10'), -33436800)
309 self
.assertEqual(unified_timestamp('28/01/2014 21:00:00 +0100'), 1390939200)
311 unified_timestamp('11/26/2014 11:30:00 AM PST', day_first
=False),
314 unified_timestamp('2/2/2015 6:47:40 PM', day_first
=False),
316 self
.assertEqual(unified_timestamp('Feb 14th 2016 5:45PM'), 1455471900)
317 self
.assertEqual(unified_timestamp('25-09-2014'), 1411603200)
318 self
.assertEqual(unified_timestamp('27.02.2016 17:30'), 1456594200)
319 self
.assertEqual(unified_timestamp('UNKNOWN DATE FORMAT'), None)
320 self
.assertEqual(unified_timestamp('May 16, 2016 11:15 PM'), 1463440500)
321 self
.assertEqual(unified_timestamp('Feb 7, 2016 at 6:35 pm'), 1454870100)
323 def test_determine_ext(self
):
324 self
.assertEqual(determine_ext('http://example.com/foo/bar.mp4/?download'), 'mp4')
325 self
.assertEqual(determine_ext('http://example.com/foo/bar/?download', None), None)
326 self
.assertEqual(determine_ext('http://example.com/foo/bar.nonext/?download', None), None)
327 self
.assertEqual(determine_ext('http://example.com/foo/bar/mp4?download', None), None)
328 self
.assertEqual(determine_ext('http://example.com/foo/bar.m3u8//?download'), 'm3u8')
330 def test_find_xpath_attr(self
):
338 doc
= compat_etree_fromstring(testxml
)
340 self
.assertEqual(find_xpath_attr(doc
, './/fourohfour', 'n'), None)
341 self
.assertEqual(find_xpath_attr(doc
, './/fourohfour', 'n', 'v'), None)
342 self
.assertEqual(find_xpath_attr(doc
, './/node', 'n'), None)
343 self
.assertEqual(find_xpath_attr(doc
, './/node', 'n', 'v'), None)
344 self
.assertEqual(find_xpath_attr(doc
, './/node', 'x'), doc
[1])
345 self
.assertEqual(find_xpath_attr(doc
, './/node', 'x', 'a'), doc
[1])
346 self
.assertEqual(find_xpath_attr(doc
, './/node', 'x', 'b'), doc
[3])
347 self
.assertEqual(find_xpath_attr(doc
, './/node', 'y'), doc
[2])
348 self
.assertEqual(find_xpath_attr(doc
, './/node', 'y', 'c'), doc
[2])
349 self
.assertEqual(find_xpath_attr(doc
, './/node', 'y', 'd'), doc
[3])
350 self
.assertEqual(find_xpath_attr(doc
, './/node', 'x', ''), doc
[4])
352 def test_xpath_with_ns(self
):
353 testxml
= '''<root xmlns:media="http://example.com/">
355 <media:author>The Author</media:author>
356 <url>http://server.com/download.mp3</url>
359 doc
= compat_etree_fromstring(testxml
)
360 find
= lambda p
: doc
.find(xpath_with_ns(p
, {'media': 'http://example.com/'}))
361 self
.assertTrue(find('media:song') is not None)
362 self
.assertEqual(find('media:song/media:author').text
, 'The Author')
363 self
.assertEqual(find('media:song/url').text
, 'http://server.com/download.mp3')
365 def test_xpath_element(self
):
366 doc
= xml
.etree
.ElementTree
.Element('root')
367 div
= xml
.etree
.ElementTree
.SubElement(doc
, 'div')
368 p
= xml
.etree
.ElementTree
.SubElement(div
, 'p')
370 self
.assertEqual(xpath_element(doc
, 'div/p'), p
)
371 self
.assertEqual(xpath_element(doc
, ['div/p']), p
)
372 self
.assertEqual(xpath_element(doc
, ['div/bar', 'div/p']), p
)
373 self
.assertEqual(xpath_element(doc
, 'div/bar', default
='default'), 'default')
374 self
.assertEqual(xpath_element(doc
, ['div/bar'], default
='default'), 'default')
375 self
.assertTrue(xpath_element(doc
, 'div/bar') is None)
376 self
.assertTrue(xpath_element(doc
, ['div/bar']) is None)
377 self
.assertTrue(xpath_element(doc
, ['div/bar'], 'div/baz') is None)
378 self
.assertRaises(ExtractorError
, xpath_element
, doc
, 'div/bar', fatal
=True)
379 self
.assertRaises(ExtractorError
, xpath_element
, doc
, ['div/bar'], fatal
=True)
380 self
.assertRaises(ExtractorError
, xpath_element
, doc
, ['div/bar', 'div/baz'], fatal
=True)
382 def test_xpath_text(self
):
388 doc
= compat_etree_fromstring(testxml
)
389 self
.assertEqual(xpath_text(doc
, 'div/p'), 'Foo')
390 self
.assertEqual(xpath_text(doc
, 'div/bar', default
='default'), 'default')
391 self
.assertTrue(xpath_text(doc
, 'div/bar') is None)
392 self
.assertRaises(ExtractorError
, xpath_text
, doc
, 'div/bar', fatal
=True)
394 def test_xpath_attr(self
):
400 doc
= compat_etree_fromstring(testxml
)
401 self
.assertEqual(xpath_attr(doc
, 'div/p', 'x'), 'a')
402 self
.assertEqual(xpath_attr(doc
, 'div/bar', 'x'), None)
403 self
.assertEqual(xpath_attr(doc
, 'div/p', 'y'), None)
404 self
.assertEqual(xpath_attr(doc
, 'div/bar', 'x', default
='default'), 'default')
405 self
.assertEqual(xpath_attr(doc
, 'div/p', 'y', default
='default'), 'default')
406 self
.assertRaises(ExtractorError
, xpath_attr
, doc
, 'div/bar', 'x', fatal
=True)
407 self
.assertRaises(ExtractorError
, xpath_attr
, doc
, 'div/p', 'y', fatal
=True)
409 def test_smuggle_url(self
):
410 data
= {"ö": "ö", "abc": [3]}
411 url
= 'https://foo.bar/baz?x=y#a'
412 smug_url
= smuggle_url(url
, data
)
413 unsmug_url
, unsmug_data
= unsmuggle_url(smug_url
)
414 self
.assertEqual(url
, unsmug_url
)
415 self
.assertEqual(data
, unsmug_data
)
417 res_url
, res_data
= unsmuggle_url(url
)
418 self
.assertEqual(res_url
, url
)
419 self
.assertEqual(res_data
, None)
421 smug_url
= smuggle_url(url
, {'a': 'b'})
422 smug_smug_url
= smuggle_url(smug_url
, {'c': 'd'})
423 res_url
, res_data
= unsmuggle_url(smug_smug_url
)
424 self
.assertEqual(res_url
, url
)
425 self
.assertEqual(res_data
, {'a': 'b', 'c': 'd'})
427 def test_shell_quote(self
):
428 args
= ['ffmpeg', '-i', encodeFilename('ñ€ß\'.mp4')]
429 self
.assertEqual(shell_quote(args
), """ffmpeg -i 'ñ€ß'"'"'.mp4'""")
431 def test_str_to_int(self
):
432 self
.assertEqual(str_to_int('123,456'), 123456)
433 self
.assertEqual(str_to_int('123.456'), 123456)
435 def test_url_basename(self
):
436 self
.assertEqual(url_basename('http://foo.de/'), '')
437 self
.assertEqual(url_basename('http://foo.de/bar/baz'), 'baz')
438 self
.assertEqual(url_basename('http://foo.de/bar/baz?x=y'), 'baz')
439 self
.assertEqual(url_basename('http://foo.de/bar/baz#x=y'), 'baz')
440 self
.assertEqual(url_basename('http://foo.de/bar/baz/'), 'baz')
442 url_basename('http://media.w3.org/2010/05/sintel/trailer.mp4'),
445 def test_base_url(self
):
446 self
.assertEqual(base_url('http://foo.de/'), 'http://foo.de/')
447 self
.assertEqual(base_url('http://foo.de/bar'), 'http://foo.de/')
448 self
.assertEqual(base_url('http://foo.de/bar/'), 'http://foo.de/bar/')
449 self
.assertEqual(base_url('http://foo.de/bar/baz'), 'http://foo.de/bar/')
450 self
.assertEqual(base_url('http://foo.de/bar/baz?x=z/x/c'), 'http://foo.de/bar/')
452 def test_urljoin(self
):
453 self
.assertEqual(urljoin('http://foo.de/', '/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
454 self
.assertEqual(urljoin('//foo.de/', '/a/b/c.txt'), '//foo.de/a/b/c.txt')
455 self
.assertEqual(urljoin('http://foo.de/', 'a/b/c.txt'), 'http://foo.de/a/b/c.txt')
456 self
.assertEqual(urljoin('http://foo.de', '/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
457 self
.assertEqual(urljoin('http://foo.de', 'a/b/c.txt'), 'http://foo.de/a/b/c.txt')
458 self
.assertEqual(urljoin('http://foo.de/', 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
459 self
.assertEqual(urljoin('http://foo.de/', '//foo.de/a/b/c.txt'), '//foo.de/a/b/c.txt')
460 self
.assertEqual(urljoin(None, 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
461 self
.assertEqual(urljoin(None, '//foo.de/a/b/c.txt'), '//foo.de/a/b/c.txt')
462 self
.assertEqual(urljoin('', 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
463 self
.assertEqual(urljoin(['foobar'], 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
464 self
.assertEqual(urljoin('http://foo.de/', None), None)
465 self
.assertEqual(urljoin('http://foo.de/', ''), None)
466 self
.assertEqual(urljoin('http://foo.de/', ['foobar']), None)
467 self
.assertEqual(urljoin('http://foo.de/a/b/c.txt', '.././../d.txt'), 'http://foo.de/d.txt')
469 def test_parse_age_limit(self
):
470 self
.assertEqual(parse_age_limit(None), None)
471 self
.assertEqual(parse_age_limit(False), None)
472 self
.assertEqual(parse_age_limit('invalid'), None)
473 self
.assertEqual(parse_age_limit(0), 0)
474 self
.assertEqual(parse_age_limit(18), 18)
475 self
.assertEqual(parse_age_limit(21), 21)
476 self
.assertEqual(parse_age_limit(22), None)
477 self
.assertEqual(parse_age_limit('18'), 18)
478 self
.assertEqual(parse_age_limit('18+'), 18)
479 self
.assertEqual(parse_age_limit('PG-13'), 13)
480 self
.assertEqual(parse_age_limit('TV-14'), 14)
481 self
.assertEqual(parse_age_limit('TV-MA'), 17)
483 def test_parse_duration(self
):
484 self
.assertEqual(parse_duration(None), None)
485 self
.assertEqual(parse_duration(False), None)
486 self
.assertEqual(parse_duration('invalid'), None)
487 self
.assertEqual(parse_duration('1'), 1)
488 self
.assertEqual(parse_duration('1337:12'), 80232)
489 self
.assertEqual(parse_duration('9:12:43'), 33163)
490 self
.assertEqual(parse_duration('12:00'), 720)
491 self
.assertEqual(parse_duration('00:01:01'), 61)
492 self
.assertEqual(parse_duration('x:y'), None)
493 self
.assertEqual(parse_duration('3h11m53s'), 11513)
494 self
.assertEqual(parse_duration('3h 11m 53s'), 11513)
495 self
.assertEqual(parse_duration('3 hours 11 minutes 53 seconds'), 11513)
496 self
.assertEqual(parse_duration('3 hours 11 mins 53 secs'), 11513)
497 self
.assertEqual(parse_duration('62m45s'), 3765)
498 self
.assertEqual(parse_duration('6m59s'), 419)
499 self
.assertEqual(parse_duration('49s'), 49)
500 self
.assertEqual(parse_duration('0h0m0s'), 0)
501 self
.assertEqual(parse_duration('0m0s'), 0)
502 self
.assertEqual(parse_duration('0s'), 0)
503 self
.assertEqual(parse_duration('01:02:03.05'), 3723.05)
504 self
.assertEqual(parse_duration('T30M38S'), 1838)
505 self
.assertEqual(parse_duration('5 s'), 5)
506 self
.assertEqual(parse_duration('3 min'), 180)
507 self
.assertEqual(parse_duration('2.5 hours'), 9000)
508 self
.assertEqual(parse_duration('02:03:04'), 7384)
509 self
.assertEqual(parse_duration('01:02:03:04'), 93784)
510 self
.assertEqual(parse_duration('1 hour 3 minutes'), 3780)
511 self
.assertEqual(parse_duration('87 Min.'), 5220)
512 self
.assertEqual(parse_duration('PT1H0.040S'), 3600.04)
513 self
.assertEqual(parse_duration('PT00H03M30SZ'), 210)
515 def test_fix_xml_ampersands(self
):
517 fix_xml_ampersands('"&x=y&z=a'), '"&x=y&z=a')
519 fix_xml_ampersands('"&x=y&wrong;&z=a'),
520 '"&x=y&wrong;&z=a')
522 fix_xml_ampersands('&'><"'),
523 '&'><"')
525 fix_xml_ampersands('Ӓ᪼'), 'Ӓ᪼')
526 self
.assertEqual(fix_xml_ampersands('&#&#'), '&#&#')
528 def test_paged_list(self
):
529 def testPL(size
, pagesize
, sliceargs
, expected
):
530 def get_page(pagenum
):
531 firstid
= pagenum
* pagesize
532 upto
= min(size
, pagenum
* pagesize
+ pagesize
)
533 for i
in range(firstid
, upto
):
536 pl
= OnDemandPagedList(get_page
, pagesize
)
537 got
= pl
.getslice(*sliceargs
)
538 self
.assertEqual(got
, expected
)
540 iapl
= InAdvancePagedList(get_page
, size
// pagesize
+ 1, pagesize
)
541 got
= iapl
.getslice(*sliceargs
)
542 self
.assertEqual(got
, expected
)
544 testPL(5, 2, (), [0, 1, 2, 3, 4])
545 testPL(5, 2, (1,), [1, 2, 3, 4])
546 testPL(5, 2, (2,), [2, 3, 4])
547 testPL(5, 2, (4,), [4])
548 testPL(5, 2, (0, 3), [0, 1, 2])
549 testPL(5, 2, (1, 4), [1, 2, 3])
550 testPL(5, 2, (2, 99), [2, 3, 4])
551 testPL(5, 2, (20, 99), [])
553 def test_read_batch_urls(self
):
554 f
= io
.StringIO('''\xef\xbb\xbf foo
557 # More after this line\r
560 self
.assertEqual(read_batch_urls(f
), ['foo', 'bar', 'baz', 'bam'])
562 def test_urlencode_postdata(self
):
563 data
= urlencode_postdata({'username': 'foo@bar.com', 'password': '1234'})
564 self
.assertTrue(isinstance(data
, bytes))
566 def test_update_url_query(self
):
568 return compat_parse_qs(compat_urlparse
.urlparse(url
).query
)
569 self
.assertEqual(query_dict(update_url_query(
570 'http://example.com/path', {'quality': ['HD'], 'format': ['mp4']})),
571 query_dict('http://example.com/path?quality=HD&format=mp4'))
572 self
.assertEqual(query_dict(update_url_query(
573 'http://example.com/path', {'system': ['LINUX', 'WINDOWS']})),
574 query_dict('http://example.com/path?system=LINUX&system=WINDOWS'))
575 self
.assertEqual(query_dict(update_url_query(
576 'http://example.com/path', {'fields': 'id,formats,subtitles'})),
577 query_dict('http://example.com/path?fields=id,formats,subtitles'))
578 self
.assertEqual(query_dict(update_url_query(
579 'http://example.com/path', {'fields': ('id,formats,subtitles', 'thumbnails')})),
580 query_dict('http://example.com/path?fields=id,formats,subtitles&fields=thumbnails'))
581 self
.assertEqual(query_dict(update_url_query(
582 'http://example.com/path?manifest=f4m', {'manifest': []})),
583 query_dict('http://example.com/path'))
584 self
.assertEqual(query_dict(update_url_query(
585 'http://example.com/path?system=LINUX&system=WINDOWS', {'system': 'LINUX'})),
586 query_dict('http://example.com/path?system=LINUX'))
587 self
.assertEqual(query_dict(update_url_query(
588 'http://example.com/path', {'fields': b
'id,formats,subtitles'})),
589 query_dict('http://example.com/path?fields=id,formats,subtitles'))
590 self
.assertEqual(query_dict(update_url_query(
591 'http://example.com/path', {'width': 1080, 'height': 720})),
592 query_dict('http://example.com/path?width=1080&height=720'))
593 self
.assertEqual(query_dict(update_url_query(
594 'http://example.com/path', {'bitrate': 5020.43})),
595 query_dict('http://example.com/path?bitrate=5020.43'))
596 self
.assertEqual(query_dict(update_url_query(
597 'http://example.com/path', {'test': '第二行тест'})),
598 query_dict('http://example.com/path?test=%E7%AC%AC%E4%BA%8C%E8%A1%8C%D1%82%D0%B5%D1%81%D1%82'))
600 def test_dict_get(self
):
608 d
= FALSE_VALUES
.copy()
610 self
.assertEqual(dict_get(d
, 'a'), 42)
611 self
.assertEqual(dict_get(d
, 'b'), None)
612 self
.assertEqual(dict_get(d
, 'b', 42), 42)
613 self
.assertEqual(dict_get(d
, ('a', )), 42)
614 self
.assertEqual(dict_get(d
, ('b', 'a', )), 42)
615 self
.assertEqual(dict_get(d
, ('b', 'c', 'a', 'd', )), 42)
616 self
.assertEqual(dict_get(d
, ('b', 'c', )), None)
617 self
.assertEqual(dict_get(d
, ('b', 'c', ), 42), 42)
618 for key
, false_value
in FALSE_VALUES
.items():
619 self
.assertEqual(dict_get(d
, ('b', 'c', key
, )), None)
620 self
.assertEqual(dict_get(d
, ('b', 'c', key
, ), skip_false_values
=False), false_value
)
622 def test_encode_compat_str(self
):
623 self
.assertEqual(encode_compat_str(b
'\xd1\x82\xd0\xb5\xd1\x81\xd1\x82', 'utf-8'), 'тест')
624 self
.assertEqual(encode_compat_str('тест', 'utf-8'), 'тест')
626 def test_parse_iso8601(self
):
627 self
.assertEqual(parse_iso8601('2014-03-23T23:04:26+0100'), 1395612266)
628 self
.assertEqual(parse_iso8601('2014-03-23T22:04:26+0000'), 1395612266)
629 self
.assertEqual(parse_iso8601('2014-03-23T22:04:26Z'), 1395612266)
630 self
.assertEqual(parse_iso8601('2014-03-23T22:04:26.1234Z'), 1395612266)
631 self
.assertEqual(parse_iso8601('2015-09-29T08:27:31.727'), 1443515251)
632 self
.assertEqual(parse_iso8601('2015-09-29T08-27-31.727'), None)
634 def test_strip_jsonp(self
):
635 stripped
= strip_jsonp('cb ([ {"id":"532cb",\n\n\n"x":\n3}\n]\n);')
636 d
= json
.loads(stripped
)
637 self
.assertEqual(d
, [{"id": "532cb", "x": 3}])
639 stripped
= strip_jsonp('parseMetadata({"STATUS":"OK"})\n\n\n//epc')
640 d
= json
.loads(stripped
)
641 self
.assertEqual(d
, {'STATUS': 'OK'})
643 stripped
= strip_jsonp('ps.embedHandler({"status": "success"});')
644 d
= json
.loads(stripped
)
645 self
.assertEqual(d
, {'status': 'success'})
647 def test_uppercase_escape(self
):
648 self
.assertEqual(uppercase_escape('aä'), 'aä')
649 self
.assertEqual(uppercase_escape('\\U0001d550'), '𝕐')
651 def test_lowercase_escape(self
):
652 self
.assertEqual(lowercase_escape('aä'), 'aä')
653 self
.assertEqual(lowercase_escape('\\u0026'), '&')
655 def test_limit_length(self
):
656 self
.assertEqual(limit_length(None, 12), None)
657 self
.assertEqual(limit_length('foo', 12), 'foo')
659 limit_length('foo bar baz asd', 12).startswith('foo bar'))
660 self
.assertTrue('...' in limit_length('foo bar baz asd', 12))
662 def test_mimetype2ext(self
):
663 self
.assertEqual(mimetype2ext(None), None)
664 self
.assertEqual(mimetype2ext('video/x-flv'), 'flv')
665 self
.assertEqual(mimetype2ext('application/x-mpegURL'), 'm3u8')
666 self
.assertEqual(mimetype2ext('text/vtt'), 'vtt')
667 self
.assertEqual(mimetype2ext('text/vtt;charset=utf-8'), 'vtt')
668 self
.assertEqual(mimetype2ext('text/html; charset=utf-8'), 'html')
670 def test_month_by_name(self
):
671 self
.assertEqual(month_by_name(None), None)
672 self
.assertEqual(month_by_name('December', 'en'), 12)
673 self
.assertEqual(month_by_name('décembre', 'fr'), 12)
674 self
.assertEqual(month_by_name('December'), 12)
675 self
.assertEqual(month_by_name('décembre'), None)
676 self
.assertEqual(month_by_name('Unknown', 'unknown'), None)
678 def test_parse_codecs(self
):
679 self
.assertEqual(parse_codecs(''), {})
680 self
.assertEqual(parse_codecs('avc1.77.30, mp4a.40.2'), {
681 'vcodec': 'avc1.77.30',
682 'acodec': 'mp4a.40.2',
684 self
.assertEqual(parse_codecs('mp4a.40.2'), {
686 'acodec': 'mp4a.40.2',
688 self
.assertEqual(parse_codecs('mp4a.40.5,avc1.42001e'), {
689 'vcodec': 'avc1.42001e',
690 'acodec': 'mp4a.40.5',
692 self
.assertEqual(parse_codecs('avc3.640028'), {
693 'vcodec': 'avc3.640028',
696 self
.assertEqual(parse_codecs(', h264,,newcodec,aac'), {
701 def test_escape_rfc3986(self
):
702 reserved
= "!*'();:@&=+$,/?#[]"
703 unreserved
= 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_.~'
704 self
.assertEqual(escape_rfc3986(reserved
), reserved
)
705 self
.assertEqual(escape_rfc3986(unreserved
), unreserved
)
706 self
.assertEqual(escape_rfc3986('тест'), '%D1%82%D0%B5%D1%81%D1%82')
707 self
.assertEqual(escape_rfc3986('%D1%82%D0%B5%D1%81%D1%82'), '%D1%82%D0%B5%D1%81%D1%82')
708 self
.assertEqual(escape_rfc3986('foo bar'), 'foo%20bar')
709 self
.assertEqual(escape_rfc3986('foo%20bar'), 'foo%20bar')
711 def test_escape_url(self
):
713 escape_url('http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavré_FD.mp4'),
714 'http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavre%CC%81_FD.mp4'
717 escape_url('http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erklärt/Das-Erste/Video?documentId=22673108&bcastId=5290'),
718 'http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erkl%C3%A4rt/Das-Erste/Video?documentId=22673108&bcastId=5290'
721 escape_url('http://тест.рф/фрагмент'),
722 'http://xn--e1aybc.xn--p1ai/%D1%84%D1%80%D0%B0%D0%B3%D0%BC%D0%B5%D0%BD%D1%82'
725 escape_url('http://тест.рф/абв?абв=абв#абв'),
726 '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'
728 self
.assertEqual(escape_url('http://vimeo.com/56015672#at=0'), 'http://vimeo.com/56015672#at=0')
730 def test_js_to_json_realworld(self
):
732 'clip':{'provider':'pseudo'}
734 self
.assertEqual(js_to_json(inp
), '''{
735 "clip":{"provider":"pseudo"}
737 json
.loads(js_to_json(inp
))
740 'playlist':[{'controls':{'all':null}}]
742 self
.assertEqual(js_to_json(inp
), '''{
743 "playlist":[{"controls":{"all":null}}]
746 inp
= '''"The CW\\'s \\'Crazy Ex-Girlfriend\\'"'''
747 self
.assertEqual(js_to_json(inp
), '''"The CW's 'Crazy Ex-Girlfriend'"''')
749 inp
= '"SAND Number: SAND 2013-7800P\\nPresenter: Tom Russo\\nHabanero Software Training - Xyce Software\\nXyce, Sandia\\u0027s"'
750 json_code
= js_to_json(inp
)
751 self
.assertEqual(json
.loads(json_code
), json
.loads(inp
))
754 0:{src:'skipped', type: 'application/dash+xml'},
755 1:{src:'skipped', type: 'application/vnd.apple.mpegURL'},
757 self
.assertEqual(js_to_json(inp
), '''{
758 "0":{"src":"skipped", "type": "application/dash+xml"},
759 "1":{"src":"skipped", "type": "application/vnd.apple.mpegURL"}
762 inp
= '''{"foo":101}'''
763 self
.assertEqual(js_to_json(inp
), '''{"foo":101}''')
765 inp
= '''{"duration": "00:01:07"}'''
766 self
.assertEqual(js_to_json(inp
), '''{"duration": "00:01:07"}''')
768 def test_js_to_json_edgecases(self
):
769 on
= js_to_json("{abc_def:'1\\'\\\\2\\\\\\'3\"4'}")
770 self
.assertEqual(json
.loads(on
), {"abc_def": "1'\\2\\'3\"4"})
772 on
= js_to_json('{"abc": true}')
773 self
.assertEqual(json
.loads(on
), {'abc': True})
775 # Ignore JavaScript code as well
782 self
.assertEqual(d
['x'], 1)
783 self
.assertEqual(d
['y'], 'a')
785 on
= js_to_json('["abc", "def",]')
786 self
.assertEqual(json
.loads(on
), ['abc', 'def'])
788 on
= js_to_json('[/*comment\n*/"abc"/*comment\n*/,/*comment\n*/"def",/*comment\n*/]')
789 self
.assertEqual(json
.loads(on
), ['abc', 'def'])
791 on
= js_to_json('[//comment\n"abc" //comment\n,//comment\n"def",//comment\n]')
792 self
.assertEqual(json
.loads(on
), ['abc', 'def'])
794 on
= js_to_json('{"abc": "def",}')
795 self
.assertEqual(json
.loads(on
), {'abc': 'def'})
797 on
= js_to_json('{/*comment\n*/"abc"/*comment\n*/:/*comment\n*/"def"/*comment\n*/,/*comment\n*/}')
798 self
.assertEqual(json
.loads(on
), {'abc': 'def'})
800 on
= js_to_json('{ 0: /* " \n */ ",]" , }')
801 self
.assertEqual(json
.loads(on
), {'0': ',]'})
803 on
= js_to_json('{ /*comment\n*/0/*comment\n*/: /* " \n */ ",]" , }')
804 self
.assertEqual(json
.loads(on
), {'0': ',]'})
806 on
= js_to_json('{ 0: // comment\n1 }')
807 self
.assertEqual(json
.loads(on
), {'0': 1})
809 on
= js_to_json(r
'["<p>x<\/p>"]')
810 self
.assertEqual(json
.loads(on
), ['<p>x</p>'])
812 on
= js_to_json(r
'["\xaa"]')
813 self
.assertEqual(json
.loads(on
), ['\u00aa'])
815 on
= js_to_json("['a\\\nb']")
816 self
.assertEqual(json
.loads(on
), ['ab'])
818 on
= js_to_json("/*comment\n*/[/*comment\n*/'a\\\nb'/*comment\n*/]/*comment\n*/")
819 self
.assertEqual(json
.loads(on
), ['ab'])
821 on
= js_to_json('{0xff:0xff}')
822 self
.assertEqual(json
.loads(on
), {'255': 255})
824 on
= js_to_json('{/*comment\n*/0xff/*comment\n*/:/*comment\n*/0xff/*comment\n*/}')
825 self
.assertEqual(json
.loads(on
), {'255': 255})
827 on
= js_to_json('{077:077}')
828 self
.assertEqual(json
.loads(on
), {'63': 63})
830 on
= js_to_json('{/*comment\n*/077/*comment\n*/:/*comment\n*/077/*comment\n*/}')
831 self
.assertEqual(json
.loads(on
), {'63': 63})
833 on
= js_to_json('{42:42}')
834 self
.assertEqual(json
.loads(on
), {'42': 42})
836 on
= js_to_json('{/*comment\n*/42/*comment\n*/:/*comment\n*/42/*comment\n*/}')
837 self
.assertEqual(json
.loads(on
), {'42': 42})
839 def test_extract_attributes(self
):
840 self
.assertEqual(extract_attributes('<e x="y">'), {'x': 'y'})
841 self
.assertEqual(extract_attributes("<e x='y'>"), {'x': 'y'})
842 self
.assertEqual(extract_attributes('<e x=y>'), {'x': 'y'})
843 self
.assertEqual(extract_attributes('<e x="a \'b\' c">'), {'x': "a 'b' c"})
844 self
.assertEqual(extract_attributes('<e x=\'a "b" c\'>'), {'x': 'a "b" c'})
845 self
.assertEqual(extract_attributes('<e x="y">'), {'x': 'y'})
846 self
.assertEqual(extract_attributes('<e x="y">'), {'x': 'y'})
847 self
.assertEqual(extract_attributes('<e x="&">'), {'x': '&'}) # XML
848 self
.assertEqual(extract_attributes('<e x=""">'), {'x': '"'})
849 self
.assertEqual(extract_attributes('<e x="£">'), {'x': '£'}) # HTML 3.2
850 self
.assertEqual(extract_attributes('<e x="λ">'), {'x': 'λ'}) # HTML 4.0
851 self
.assertEqual(extract_attributes('<e x="&foo">'), {'x': '&foo'})
852 self
.assertEqual(extract_attributes('<e x="\'">'), {'x': "'"})
853 self
.assertEqual(extract_attributes('<e x=\'"\'>'), {'x': '"'})
854 self
.assertEqual(extract_attributes('<e x >'), {'x': None})
855 self
.assertEqual(extract_attributes('<e x=y a>'), {'x': 'y', 'a': None})
856 self
.assertEqual(extract_attributes('<e x= y>'), {'x': 'y'})
857 self
.assertEqual(extract_attributes('<e x=1 y=2 x=3>'), {'y': '2', 'x': '3'})
858 self
.assertEqual(extract_attributes('<e \nx=\ny\n>'), {'x': 'y'})
859 self
.assertEqual(extract_attributes('<e \nx=\n"y"\n>'), {'x': 'y'})
860 self
.assertEqual(extract_attributes("<e \nx=\n'y'\n>"), {'x': 'y'})
861 self
.assertEqual(extract_attributes('<e \nx="\ny\n">'), {'x': '\ny\n'})
862 self
.assertEqual(extract_attributes('<e CAPS=x>'), {'caps': 'x'}) # Names lowercased
863 self
.assertEqual(extract_attributes('<e x=1 X=2>'), {'x': '2'})
864 self
.assertEqual(extract_attributes('<e X=1 x=2>'), {'x': '2'})
865 self
.assertEqual(extract_attributes('<e _:funny-name1=1>'), {'_:funny-name1': '1'})
866 self
.assertEqual(extract_attributes('<e x="Fáilte 世界 \U0001f600">'), {'x': 'Fáilte 世界 \U0001f600'})
867 self
.assertEqual(extract_attributes('<e x="décomposé">'), {'x': 'décompose\u0301'})
868 # "Narrow" Python builds don't support unicode code points outside BMP.
871 supports_outside_bmp
= True
873 supports_outside_bmp
= False
874 if supports_outside_bmp
:
875 self
.assertEqual(extract_attributes('<e x="Smile 😀!">'), {'x': 'Smile \U0001f600!'})
877 def test_clean_html(self
):
878 self
.assertEqual(clean_html('a:\nb'), 'a: b')
879 self
.assertEqual(clean_html('a:\n "b"'), 'a: "b"')
881 def test_intlist_to_bytes(self
):
883 intlist_to_bytes([0, 1, 127, 128, 255]),
884 b
'\x00\x01\x7f\x80\xff')
886 def test_args_to_str(self
):
888 args_to_str(['foo', 'ba/r', '-baz', '2 be', '']),
889 'foo ba/r -baz \'2 be\' \'\''
892 def test_parse_filesize(self
):
893 self
.assertEqual(parse_filesize(None), None)
894 self
.assertEqual(parse_filesize(''), None)
895 self
.assertEqual(parse_filesize('91 B'), 91)
896 self
.assertEqual(parse_filesize('foobar'), None)
897 self
.assertEqual(parse_filesize('2 MiB'), 2097152)
898 self
.assertEqual(parse_filesize('5 GB'), 5000000000)
899 self
.assertEqual(parse_filesize('1.2Tb'), 1200000000000)
900 self
.assertEqual(parse_filesize('1.2tb'), 1200000000000)
901 self
.assertEqual(parse_filesize('1,24 KB'), 1240)
902 self
.assertEqual(parse_filesize('1,24 kb'), 1240)
903 self
.assertEqual(parse_filesize('8.5 megabytes'), 8500000)
905 def test_parse_count(self
):
906 self
.assertEqual(parse_count(None), None)
907 self
.assertEqual(parse_count(''), None)
908 self
.assertEqual(parse_count('0'), 0)
909 self
.assertEqual(parse_count('1000'), 1000)
910 self
.assertEqual(parse_count('1.000'), 1000)
911 self
.assertEqual(parse_count('1.1k'), 1100)
912 self
.assertEqual(parse_count('1.1kk'), 1100000)
913 self
.assertEqual(parse_count('1.1kk '), 1100000)
914 self
.assertEqual(parse_count('1.1kk views'), 1100000)
916 def test_version_tuple(self
):
917 self
.assertEqual(version_tuple('1'), (1,))
918 self
.assertEqual(version_tuple('10.23.344'), (10, 23, 344))
919 self
.assertEqual(version_tuple('10.1-6'), (10, 1, 6)) # avconv style
921 def test_detect_exe_version(self
):
922 self
.assertEqual(detect_exe_version('''ffmpeg version 1.2.1
923 built on May 27 2013 08:37:26 with gcc 4.7 (Debian 4.7.3-4)
924 configuration: --prefix=/usr --extra-'''), '1.2.1')
925 self
.assertEqual(detect_exe_version('''ffmpeg version N-63176-g1fb4685
926 built on May 15 2014 22:09:06 with gcc 4.8.2 (GCC)'''), 'N-63176-g1fb4685')
927 self
.assertEqual(detect_exe_version('''X server found. dri2 connection failed!
928 Trying to open render node...
929 Success at /dev/dri/renderD128.
930 ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')
932 def test_age_restricted(self
):
933 self
.assertFalse(age_restricted(None, 10)) # unrestricted content
934 self
.assertFalse(age_restricted(1, None)) # unrestricted policy
935 self
.assertFalse(age_restricted(8, 10))
936 self
.assertTrue(age_restricted(18, 14))
937 self
.assertFalse(age_restricted(18, 18))
939 def test_is_html(self
):
940 self
.assertFalse(is_html(b
'\x49\x44\x43<html'))
941 self
.assertTrue(is_html(b
'<!DOCTYPE foo>\xaaa'))
942 self
.assertTrue(is_html( # UTF-8 with BOM
943 b
'\xef\xbb\xbf<!DOCTYPE foo>\xaaa'))
944 self
.assertTrue(is_html( # UTF-16-LE
945 b
'\xff\xfe<\x00h\x00t\x00m\x00l\x00>\x00\xe4\x00'
947 self
.assertTrue(is_html( # UTF-16-BE
948 b
'\xfe\xff\x00<\x00h\x00t\x00m\x00l\x00>\x00\xe4'
950 self
.assertTrue(is_html( # UTF-32-BE
951 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'))
952 self
.assertTrue(is_html( # UTF-32-LE
953 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'))
955 def test_render_table(self
):
959 [[123, 4], [9999, 51]]),
964 def test_match_str(self
):
965 self
.assertRaises(ValueError, match_str
, 'xy>foobar', {})
966 self
.assertFalse(match_str('xy', {'x': 1200}))
967 self
.assertTrue(match_str('!xy', {'x': 1200}))
968 self
.assertTrue(match_str('x', {'x': 1200}))
969 self
.assertFalse(match_str('!x', {'x': 1200}))
970 self
.assertTrue(match_str('x', {'x': 0}))
971 self
.assertFalse(match_str('x>0', {'x': 0}))
972 self
.assertFalse(match_str('x>0', {}))
973 self
.assertTrue(match_str('x>?0', {}))
974 self
.assertTrue(match_str('x>1K', {'x': 1200}))
975 self
.assertFalse(match_str('x>2K', {'x': 1200}))
976 self
.assertTrue(match_str('x>=1200 & x < 1300', {'x': 1200}))
977 self
.assertFalse(match_str('x>=1100 & x < 1200', {'x': 1200}))
978 self
.assertFalse(match_str('y=a212', {'y': 'foobar42'}))
979 self
.assertTrue(match_str('y=foobar42', {'y': 'foobar42'}))
980 self
.assertFalse(match_str('y!=foobar42', {'y': 'foobar42'}))
981 self
.assertTrue(match_str('y!=foobar2', {'y': 'foobar42'}))
982 self
.assertFalse(match_str(
983 'like_count > 100 & dislike_count <? 50 & description',
984 {'like_count': 90, 'description': 'foo'}))
985 self
.assertTrue(match_str(
986 'like_count > 100 & dislike_count <? 50 & description',
987 {'like_count': 190, 'description': 'foo'}))
988 self
.assertFalse(match_str(
989 'like_count > 100 & dislike_count <? 50 & description',
990 {'like_count': 190, 'dislike_count': 60, 'description': 'foo'}))
991 self
.assertFalse(match_str(
992 'like_count > 100 & dislike_count <? 50 & description',
993 {'like_count': 190, 'dislike_count': 10}))
995 def test_parse_dfxp_time_expr(self
):
996 self
.assertEqual(parse_dfxp_time_expr(None), None)
997 self
.assertEqual(parse_dfxp_time_expr(''), None)
998 self
.assertEqual(parse_dfxp_time_expr('0.1'), 0.1)
999 self
.assertEqual(parse_dfxp_time_expr('0.1s'), 0.1)
1000 self
.assertEqual(parse_dfxp_time_expr('00:00:01'), 1.0)
1001 self
.assertEqual(parse_dfxp_time_expr('00:00:01.100'), 1.1)
1002 self
.assertEqual(parse_dfxp_time_expr('00:00:01:100'), 1.1)
1004 def test_dfxp2srt(self
):
1005 dfxp_data
= '''<?xml version="1.0" encoding="UTF-8"?>
1006 <tt xmlns="http://www.w3.org/ns/ttml" xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter">
1009 <p begin="0" end="1">The following line contains Chinese characters and special symbols</p>
1010 <p begin="1" end="2">第二行<br/>♪♪</p>
1011 <p begin="2" dur="1"><span>Third<br/>Line</span></p>
1012 <p begin="3" end="-1">Lines with invalid timestamps are ignored</p>
1013 <p begin="-1" end="-1">Ignore, two</p>
1014 <p begin="3" dur="-1">Ignored, three</p>
1019 00:00:00,000 --> 00:00:01,000
1020 The following line contains Chinese characters and special symbols
1023 00:00:01,000 --> 00:00:02,000
1028 00:00:02,000 --> 00:00:03,000
1033 self
.assertEqual(dfxp2srt(dfxp_data
), srt_data
)
1035 dfxp_data_no_default_namespace
= '''<?xml version="1.0" encoding="UTF-8"?>
1036 <tt xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter">
1039 <p begin="0" end="1">The first line</p>
1044 00:00:00,000 --> 00:00:01,000
1048 self
.assertEqual(dfxp2srt(dfxp_data_no_default_namespace
), srt_data
)
1050 def test_cli_option(self
):
1051 self
.assertEqual(cli_option({'proxy': '127.0.0.1:3128'}, '--proxy', 'proxy'), ['--proxy', '127.0.0.1:3128'])
1052 self
.assertEqual(cli_option({'proxy': None}, '--proxy', 'proxy'), [])
1053 self
.assertEqual(cli_option({}, '--proxy', 'proxy'), [])
1054 self
.assertEqual(cli_option({'retries': 10}, '--retries', 'retries'), ['--retries', '10'])
1056 def test_cli_valueless_option(self
):
1057 self
.assertEqual(cli_valueless_option(
1058 {'downloader': 'external'}, '--external-downloader', 'downloader', 'external'), ['--external-downloader'])
1059 self
.assertEqual(cli_valueless_option(
1060 {'downloader': 'internal'}, '--external-downloader', 'downloader', 'external'), [])
1061 self
.assertEqual(cli_valueless_option(
1062 {'nocheckcertificate': True}, '--no-check-certificate', 'nocheckcertificate'), ['--no-check-certificate'])
1063 self
.assertEqual(cli_valueless_option(
1064 {'nocheckcertificate': False}, '--no-check-certificate', 'nocheckcertificate'), [])
1065 self
.assertEqual(cli_valueless_option(
1066 {'checkcertificate': True}, '--no-check-certificate', 'checkcertificate', False), [])
1067 self
.assertEqual(cli_valueless_option(
1068 {'checkcertificate': False}, '--no-check-certificate', 'checkcertificate', False), ['--no-check-certificate'])
1070 def test_cli_bool_option(self
):
1073 {'nocheckcertificate': True}, '--no-check-certificate', 'nocheckcertificate'),
1074 ['--no-check-certificate', 'true'])
1077 {'nocheckcertificate': True}, '--no-check-certificate', 'nocheckcertificate', separator
='='),
1078 ['--no-check-certificate=true'])
1081 {'nocheckcertificate': True}, '--check-certificate', 'nocheckcertificate', 'false', 'true'),
1082 ['--check-certificate', 'false'])
1085 {'nocheckcertificate': True}, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='),
1086 ['--check-certificate=false'])
1089 {'nocheckcertificate': False}, '--check-certificate', 'nocheckcertificate', 'false', 'true'),
1090 ['--check-certificate', 'true'])
1093 {'nocheckcertificate': False}, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='),
1094 ['--check-certificate=true'])
1096 def test_ohdave_rsa_encrypt(self
):
1097 N
= 0xab86b6371b5318aaa1d3c9e612a9f1264f372323c8c0f19875b5fc3b3fd3afcc1e5bec527aa94bfa85bffc157e4245aebda05389a5357b75115ac94f074aefcd
1101 ohdave_rsa_encrypt(b
'aa111222', e
, N
),
1102 '726664bd9a23fd0c70f9f1b84aab5e3905ce1e45a584e9cbcf9bcc7510338fc1986d6c599ff990d923aa43c51c0d9013cd572e13bc58f4ae48f2ed8c0b0ba881')
1104 def test_encode_base_n(self
):
1105 self
.assertEqual(encode_base_n(0, 30), '0')
1106 self
.assertEqual(encode_base_n(80, 30), '2k')
1108 custom_table
= '9876543210ZYXWVUTSRQPONMLKJIHGFEDCBA'
1109 self
.assertEqual(encode_base_n(0, 30, custom_table
), '9')
1110 self
.assertEqual(encode_base_n(80, 30, custom_table
), '7P')
1112 self
.assertRaises(ValueError, encode_base_n
, 0, 70)
1113 self
.assertRaises(ValueError, encode_base_n
, 0, 60, custom_table
)
1115 def test_urshift(self
):
1116 self
.assertEqual(urshift(3, 1), 1)
1117 self
.assertEqual(urshift(-3, 1), 2147483646)
1119 def test_get_element_by_class(self
):
1121 <span class="foo bar">nice</span>
1124 self
.assertEqual(get_element_by_class('foo', html
), 'nice')
1125 self
.assertEqual(get_element_by_class('no-such-class', html
), None)
1128 if __name__
== '__main__':