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 (
82 from youtube_dl.compat import (
84 compat_etree_fromstring,
90 class TestUtil(unittest.TestCase):
91 def test_timeconvert(self):
92 self.assertTrue(timeconvert('') is None)
93 self.assertTrue(timeconvert('bougrg') is None)
95 def test_sanitize_filename(self):
96 self.assertEqual(sanitize_filename('abc'), 'abc')
97 self.assertEqual(sanitize_filename('abc_d-e'), 'abc_d-e')
99 self.assertEqual(sanitize_filename('123'), '123')
101 self.assertEqual('abc_de', sanitize_filename('abc/de'))
102 self.assertFalse('/' in sanitize_filename('abc/de///'))
104 self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de'))
105 self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|'))
106 self.assertEqual('yes no', sanitize_filename('yes? no'))
107 self.assertEqual('this - that', sanitize_filename('this: that'))
109 self.assertEqual(sanitize_filename('AT&T'), 'AT&T')
111 self.assertEqual(sanitize_filename(aumlaut), aumlaut)
112 tests = '\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430'
113 self.assertEqual(sanitize_filename(tests), tests)
116 sanitize_filename('New World record at 0:12:34'),
117 'New World record at 0_12_34')
119 self.assertEqual(sanitize_filename('--gasdgf'), '_-gasdgf')
120 self.assertEqual(sanitize_filename('--gasdgf', is_id=True), '--gasdgf')
121 self.assertEqual(sanitize_filename('.gasdgf'), 'gasdgf')
122 self.assertEqual(sanitize_filename('.gasdgf', is_id=True), '.gasdgf')
126 for fbc in forbidden:
127 self.assertTrue(fbc not in sanitize_filename(fc))
129 def test_sanitize_filename_restricted(self):
130 self.assertEqual(sanitize_filename('abc', restricted=True), 'abc')
131 self.assertEqual(sanitize_filename('abc_d-e', restricted=True), 'abc_d-e')
133 self.assertEqual(sanitize_filename('123', restricted=True), '123')
135 self.assertEqual('abc_de', sanitize_filename('abc/de', restricted=True))
136 self.assertFalse('/' in sanitize_filename('abc/de///', restricted=True))
138 self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de', restricted=True))
139 self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|', restricted=True))
140 self.assertEqual('yes_no', sanitize_filename('yes? no', restricted=True))
141 self.assertEqual('this_-_that', sanitize_filename('this: that', restricted=True))
143 tests = 'aäb\u4e2d\u56fd\u7684c'
144 self.assertEqual(sanitize_filename(tests, restricted=True), 'aab_c')
145 self.assertTrue(sanitize_filename('\xf6', restricted=True) != '') # No empty filename
147 forbidden = '"\0\\/&!: \'\t\n()[]{}$;`^,#'
149 for fbc in forbidden:
150 self.assertTrue(fbc not in sanitize_filename(fc, restricted=True))
152 # Handle a common case more neatly
153 self.assertEqual(sanitize_filename('\u5927\u58f0\u5e26 - Song', restricted=True), 'Song')
154 self.assertEqual(sanitize_filename('\u603b\u7edf: Speech', restricted=True), 'Speech')
155 # .. but make sure the file name is never empty
156 self.assertTrue(sanitize_filename('-', restricted=True) != '')
157 self.assertTrue(sanitize_filename(':', restricted=True) != '')
159 self.assertEqual(sanitize_filename(
160 'ÂÃÄÀÁÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖŐØŒÙÚÛÜŰÝÞßàáâãäåæçèéêëìíîïðñòóôõöőøœùúûüűýþÿ', restricted=True),
161 'AAAAAAAECEEEEIIIIDNOOOOOOOOEUUUUUYPssaaaaaaaeceeeeiiiionooooooooeuuuuuypy')
163 def test_sanitize_ids(self):
164 self.assertEqual(sanitize_filename('_n_cd26wFpw', is_id=True), '_n_cd26wFpw')
165 self.assertEqual(sanitize_filename('_BD_eEpuzXw', is_id=True), '_BD_eEpuzXw')
166 self.assertEqual(sanitize_filename('N0Y__7-UOdI', is_id=True), 'N0Y__7-UOdI')
168 def test_sanitize_path(self):
169 if sys.platform != 'win32':
172 self.assertEqual(sanitize_path('abc'), 'abc')
173 self.assertEqual(sanitize_path('abc/def'), 'abc\\def')
174 self.assertEqual(sanitize_path('abc\\def'), 'abc\\def')
175 self.assertEqual(sanitize_path('abc|def'), 'abc#def')
176 self.assertEqual(sanitize_path('<>:"|?*'), '#######')
177 self.assertEqual(sanitize_path('C:/abc/def'), 'C:\\abc\\def')
178 self.assertEqual(sanitize_path('C?:/abc/def'), 'C##\\abc\\def')
180 self.assertEqual(sanitize_path('\\\\?\\UNC\\ComputerName\\abc'), '\\\\?\\UNC\\ComputerName\\abc')
181 self.assertEqual(sanitize_path('\\\\?\\UNC/ComputerName/abc'), '\\\\?\\UNC\\ComputerName\\abc')
183 self.assertEqual(sanitize_path('\\\\?\\C:\\abc'), '\\\\?\\C:\\abc')
184 self.assertEqual(sanitize_path('\\\\?\\C:/abc'), '\\\\?\\C:\\abc')
185 self.assertEqual(sanitize_path('\\\\?\\C:\\ab?c\\de:f'), '\\\\?\\C:\\ab#c\\de#f')
186 self.assertEqual(sanitize_path('\\\\?\\C:\\abc'), '\\\\?\\C:\\abc')
189 sanitize_path('youtube/%(uploader)s/%(autonumber)s-%(title)s-%(upload_date)s.%(ext)s'),
190 'youtube\\%(uploader)s\\%(autonumber)s-%(title)s-%(upload_date)s.%(ext)s')
193 sanitize_path('youtube/TheWreckingYard ./00001-Not bad, Especially for Free! (1987 Yamaha 700)-20141116.mp4.part'),
194 'youtube\\TheWreckingYard #\\00001-Not bad, Especially for Free! (1987 Yamaha 700)-20141116.mp4.part')
195 self.assertEqual(sanitize_path('abc/def...'), 'abc\\def..#')
196 self.assertEqual(sanitize_path('abc.../def'), 'abc..#\\def')
197 self.assertEqual(sanitize_path('abc.../def...'), 'abc..#\\def..#')
199 self.assertEqual(sanitize_path('../abc'), '..\\abc')
200 self.assertEqual(sanitize_path('../../abc'), '..\\..\\abc')
201 self.assertEqual(sanitize_path('./abc'), 'abc')
202 self.assertEqual(sanitize_path('./../abc'), '..\\abc')
204 def test_prepend_extension(self):
205 self.assertEqual(prepend_extension('abc.ext', 'temp'), 'abc.temp.ext')
206 self.assertEqual(prepend_extension('abc.ext', 'temp', 'ext'), 'abc.temp.ext')
207 self.assertEqual(prepend_extension('abc.unexpected_ext', 'temp', 'ext'), 'abc.unexpected_ext.temp')
208 self.assertEqual(prepend_extension('abc', 'temp'), 'abc.temp')
209 self.assertEqual(prepend_extension('.abc', 'temp'), '.abc.temp')
210 self.assertEqual(prepend_extension('.abc.ext', 'temp'), '.abc.temp.ext')
212 def test_replace_extension(self):
213 self.assertEqual(replace_extension('abc.ext', 'temp'), 'abc.temp')
214 self.assertEqual(replace_extension('abc.ext', 'temp', 'ext'), 'abc.temp')
215 self.assertEqual(replace_extension('abc.unexpected_ext', 'temp', 'ext'), 'abc.unexpected_ext.temp')
216 self.assertEqual(replace_extension('abc', 'temp'), 'abc.temp')
217 self.assertEqual(replace_extension('.abc', 'temp'), '.abc.temp')
218 self.assertEqual(replace_extension('.abc.ext', 'temp'), '.abc.temp')
220 def test_remove_start(self):
221 self.assertEqual(remove_start(None, 'A - '), None)
222 self.assertEqual(remove_start('A - B', 'A - '), 'B')
223 self.assertEqual(remove_start('B - A', 'A - '), 'B - A')
225 def test_remove_end(self):
226 self.assertEqual(remove_end(None, ' - B'), None)
227 self.assertEqual(remove_end('A - B', ' - B'), 'A')
228 self.assertEqual(remove_end('B - A', ' - B'), 'B - A')
230 def test_remove_quotes(self):
231 self.assertEqual(remove_quotes(None), None)
232 self.assertEqual(remove_quotes('"'), '"')
233 self.assertEqual(remove_quotes("'"), "'")
234 self.assertEqual(remove_quotes(';'), ';')
235 self.assertEqual(remove_quotes('";'), '";')
236 self.assertEqual(remove_quotes('""'), '')
237 self.assertEqual(remove_quotes('";"'), ';')
239 def test_ordered_set(self):
240 self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7])
241 self.assertEqual(orderedSet([]), [])
242 self.assertEqual(orderedSet([1]), [1])
243 # keep the list ordered
244 self.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1])
246 def test_unescape_html(self):
247 self.assertEqual(unescapeHTML('%20;'), '%20;')
248 self.assertEqual(unescapeHTML('/'), '/')
249 self.assertEqual(unescapeHTML('/'), '/')
250 self.assertEqual(unescapeHTML('é'), 'é')
251 self.assertEqual(unescapeHTML('�'), '�')
253 def test_date_from_str(self):
254 self.assertEqual(date_from_str('yesterday'), date_from_str('now-1day'))
255 self.assertEqual(date_from_str('now+7day'), date_from_str('now+1week'))
256 self.assertEqual(date_from_str('now+14day'), date_from_str('now+2week'))
257 self.assertEqual(date_from_str('now+365day'), date_from_str('now+1year'))
258 self.assertEqual(date_from_str('now+30day'), date_from_str('now+1month'))
260 def test_daterange(self):
261 _20century = DateRange("19000101", "20000101")
262 self.assertFalse("17890714" in _20century)
263 _ac = DateRange("00010101")
264 self.assertTrue("19690721" in _ac)
265 _firstmilenium = DateRange(end="10000101")
266 self.assertTrue("07110427" in _firstmilenium)
268 def test_unified_dates(self):
269 self.assertEqual(unified_strdate('December 21, 2010'), '20101221')
270 self.assertEqual(unified_strdate('8/7/2009'), '20090708')
271 self.assertEqual(unified_strdate('Dec 14, 2012'), '20121214')
272 self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
273 self.assertEqual(unified_strdate('1968 12 10'), '19681210')
274 self.assertEqual(unified_strdate('1968-12-10'), '19681210')
275 self.assertEqual(unified_strdate('28/01/2014 21:00:00 +0100'), '20140128')
277 unified_strdate('11/26/2014 11:30:00 AM PST', day_first=False),
280 unified_strdate('2/2/2015 6:47:40 PM', day_first=False),
282 self.assertEqual(unified_strdate('Feb 14th 2016 5:45PM'), '20160214')
283 self.assertEqual(unified_strdate('25-09-2014'), '20140925')
284 self.assertEqual(unified_strdate('UNKNOWN DATE FORMAT'), None)
286 def test_determine_ext(self):
287 self.assertEqual(determine_ext('http://example.com/foo/bar.mp4/?download'), 'mp4')
288 self.assertEqual(determine_ext('http://example.com/foo/bar/?download', None), None)
289 self.assertEqual(determine_ext('http://example.com/foo/bar.nonext/?download', None), None)
290 self.assertEqual(determine_ext('http://example.com/foo/bar/mp4?download', None), None)
291 self.assertEqual(determine_ext('http://example.com/foo/bar.m3u8//?download'), 'm3u8')
293 def test_find_xpath_attr(self):
301 doc = compat_etree_fromstring(testxml)
303 self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n'), None)
304 self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n', 'v'), None)
305 self.assertEqual(find_xpath_attr(doc, './/node', 'n'), None)
306 self.assertEqual(find_xpath_attr(doc, './/node', 'n', 'v'), None)
307 self.assertEqual(find_xpath_attr(doc, './/node', 'x'), doc[1])
308 self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'a'), doc[1])
309 self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'b'), doc[3])
310 self.assertEqual(find_xpath_attr(doc, './/node', 'y'), doc[2])
311 self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'c'), doc[2])
312 self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'd'), doc[3])
313 self.assertEqual(find_xpath_attr(doc, './/node', 'x', ''), doc[4])
315 def test_xpath_with_ns(self):
316 testxml = '''<root xmlns:media="http://example.com/">
318 <media:author>The Author</media:author>
319 <url>http://server.com/download.mp3</url>
322 doc = compat_etree_fromstring(testxml)
323 find = lambda p: doc.find(xpath_with_ns(p, {'media': 'http://example.com/'}))
324 self.assertTrue(find('media:song') is not None)
325 self.assertEqual(find('media:song/media:author').text, 'The Author')
326 self.assertEqual(find('media:song/url').text, 'http://server.com/download.mp3')
328 def test_xpath_element(self):
329 doc = xml.etree.ElementTree.Element('root')
330 div = xml.etree.ElementTree.SubElement(doc, 'div')
331 p = xml.etree.ElementTree.SubElement(div, 'p')
333 self.assertEqual(xpath_element(doc, 'div/p'), p)
334 self.assertEqual(xpath_element(doc, ['div/p']), p)
335 self.assertEqual(xpath_element(doc, ['div/bar', 'div/p']), p)
336 self.assertEqual(xpath_element(doc, 'div/bar', default='default'), 'default')
337 self.assertEqual(xpath_element(doc, ['div/bar'], default='default'), 'default')
338 self.assertTrue(xpath_element(doc, 'div/bar') is None)
339 self.assertTrue(xpath_element(doc, ['div/bar']) is None)
340 self.assertTrue(xpath_element(doc, ['div/bar'], 'div/baz') is None)
341 self.assertRaises(ExtractorError, xpath_element, doc, 'div/bar', fatal=True)
342 self.assertRaises(ExtractorError, xpath_element, doc, ['div/bar'], fatal=True)
343 self.assertRaises(ExtractorError, xpath_element, doc, ['div/bar', 'div/baz'], fatal=True)
345 def test_xpath_text(self):
351 doc = compat_etree_fromstring(testxml)
352 self.assertEqual(xpath_text(doc, 'div/p'), 'Foo')
353 self.assertEqual(xpath_text(doc, 'div/bar', default='default'), 'default')
354 self.assertTrue(xpath_text(doc, 'div/bar') is None)
355 self.assertRaises(ExtractorError, xpath_text, doc, 'div/bar', fatal=True)
357 def test_xpath_attr(self):
363 doc = compat_etree_fromstring(testxml)
364 self.assertEqual(xpath_attr(doc, 'div/p', 'x'), 'a')
365 self.assertEqual(xpath_attr(doc, 'div/bar', 'x'), None)
366 self.assertEqual(xpath_attr(doc, 'div/p', 'y'), None)
367 self.assertEqual(xpath_attr(doc, 'div/bar', 'x', default='default'), 'default')
368 self.assertEqual(xpath_attr(doc, 'div/p', 'y', default='default'), 'default')
369 self.assertRaises(ExtractorError, xpath_attr, doc, 'div/bar', 'x', fatal=True)
370 self.assertRaises(ExtractorError, xpath_attr, doc, 'div/p', 'y', fatal=True)
372 def test_smuggle_url(self):
373 data = {"ö": "ö", "abc": [3]}
374 url = 'https://foo.bar/baz?x=y#a'
375 smug_url = smuggle_url(url, data)
376 unsmug_url, unsmug_data = unsmuggle_url(smug_url)
377 self.assertEqual(url, unsmug_url)
378 self.assertEqual(data, unsmug_data)
380 res_url, res_data = unsmuggle_url(url)
381 self.assertEqual(res_url, url)
382 self.assertEqual(res_data, None)
384 def test_shell_quote(self):
385 args = ['ffmpeg', '-i', encodeFilename('ñ€ß\'.mp4')]
386 self.assertEqual(shell_quote(args), """ffmpeg -i 'ñ€ß'"'"'.mp4'""")
388 def test_str_to_int(self):
389 self.assertEqual(str_to_int('123,456'), 123456)
390 self.assertEqual(str_to_int('123.456'), 123456)
392 def test_url_basename(self):
393 self.assertEqual(url_basename('http://foo.de/'), '')
394 self.assertEqual(url_basename('http://foo.de/bar/baz'), 'baz')
395 self.assertEqual(url_basename('http://foo.de/bar/baz?x=y'), 'baz')
396 self.assertEqual(url_basename('http://foo.de/bar/baz#x=y'), 'baz')
397 self.assertEqual(url_basename('http://foo.de/bar/baz/'), 'baz')
399 url_basename('http://media.w3.org/2010/05/sintel/trailer.mp4'),
402 def test_parse_duration(self):
403 self.assertEqual(parse_duration(None), None)
404 self.assertEqual(parse_duration(False), None)
405 self.assertEqual(parse_duration('invalid'), None)
406 self.assertEqual(parse_duration('1'), 1)
407 self.assertEqual(parse_duration('1337:12'), 80232)
408 self.assertEqual(parse_duration('9:12:43'), 33163)
409 self.assertEqual(parse_duration('12:00'), 720)
410 self.assertEqual(parse_duration('00:01:01'), 61)
411 self.assertEqual(parse_duration('x:y'), None)
412 self.assertEqual(parse_duration('3h11m53s'), 11513)
413 self.assertEqual(parse_duration('3h 11m 53s'), 11513)
414 self.assertEqual(parse_duration('3 hours 11 minutes 53 seconds'), 11513)
415 self.assertEqual(parse_duration('3 hours 11 mins 53 secs'), 11513)
416 self.assertEqual(parse_duration('62m45s'), 3765)
417 self.assertEqual(parse_duration('6m59s'), 419)
418 self.assertEqual(parse_duration('49s'), 49)
419 self.assertEqual(parse_duration('0h0m0s'), 0)
420 self.assertEqual(parse_duration('0m0s'), 0)
421 self.assertEqual(parse_duration('0s'), 0)
422 self.assertEqual(parse_duration('01:02:03.05'), 3723.05)
423 self.assertEqual(parse_duration('T30M38S'), 1838)
424 self.assertEqual(parse_duration('5 s'), 5)
425 self.assertEqual(parse_duration('3 min'), 180)
426 self.assertEqual(parse_duration('2.5 hours'), 9000)
427 self.assertEqual(parse_duration('02:03:04'), 7384)
428 self.assertEqual(parse_duration('01:02:03:04'), 93784)
429 self.assertEqual(parse_duration('1 hour 3 minutes'), 3780)
430 self.assertEqual(parse_duration('87 Min.'), 5220)
431 self.assertEqual(parse_duration('PT1H0.040S'), 3600.04)
433 def test_fix_xml_ampersands(self):
435 fix_xml_ampersands('"&x=y&z=a'), '"&x=y&z=a')
437 fix_xml_ampersands('"&x=y&wrong;&z=a'),
438 '"&x=y&wrong;&z=a')
440 fix_xml_ampersands('&'><"'),
441 '&'><"')
443 fix_xml_ampersands('Ӓ᪼'), 'Ӓ᪼')
444 self.assertEqual(fix_xml_ampersands('&#&#'), '&#&#')
446 def test_paged_list(self):
447 def testPL(size, pagesize, sliceargs, expected):
448 def get_page(pagenum):
449 firstid = pagenum * pagesize
450 upto = min(size, pagenum * pagesize + pagesize)
451 for i in range(firstid, upto):
454 pl = OnDemandPagedList(get_page, pagesize)
455 got = pl.getslice(*sliceargs)
456 self.assertEqual(got, expected)
458 iapl = InAdvancePagedList(get_page, size // pagesize + 1, pagesize)
459 got = iapl.getslice(*sliceargs)
460 self.assertEqual(got, expected)
462 testPL(5, 2, (), [0, 1, 2, 3, 4])
463 testPL(5, 2, (1,), [1, 2, 3, 4])
464 testPL(5, 2, (2,), [2, 3, 4])
465 testPL(5, 2, (4,), [4])
466 testPL(5, 2, (0, 3), [0, 1, 2])
467 testPL(5, 2, (1, 4), [1, 2, 3])
468 testPL(5, 2, (2, 99), [2, 3, 4])
469 testPL(5, 2, (20, 99), [])
471 def test_read_batch_urls(self):
472 f = io.StringIO('''\xef\xbb\xbf foo
475 # More after this line\r
478 self.assertEqual(read_batch_urls(f), ['foo', 'bar', 'baz', 'bam'])
480 def test_urlencode_postdata(self):
481 data = urlencode_postdata({'username': 'foo@bar.com', 'password': '1234'})
482 self.assertTrue(isinstance(data, bytes))
484 def test_update_url_query(self):
486 return compat_parse_qs(compat_urlparse.urlparse(url).query)
487 self.assertEqual(query_dict(update_url_query(
488 'http://example.com/path', {'quality': ['HD'], 'format': ['mp4']})),
489 query_dict('http://example.com/path?quality=HD&format=mp4'))
490 self.assertEqual(query_dict(update_url_query(
491 'http://example.com/path', {'system': ['LINUX', 'WINDOWS']})),
492 query_dict('http://example.com/path?system=LINUX&system=WINDOWS'))
493 self.assertEqual(query_dict(update_url_query(
494 'http://example.com/path', {'fields': 'id,formats,subtitles'})),
495 query_dict('http://example.com/path?fields=id,formats,subtitles'))
496 self.assertEqual(query_dict(update_url_query(
497 'http://example.com/path', {'fields': ('id,formats,subtitles', 'thumbnails')})),
498 query_dict('http://example.com/path?fields=id,formats,subtitles&fields=thumbnails'))
499 self.assertEqual(query_dict(update_url_query(
500 'http://example.com/path?manifest=f4m', {'manifest': []})),
501 query_dict('http://example.com/path'))
502 self.assertEqual(query_dict(update_url_query(
503 'http://example.com/path?system=LINUX&system=WINDOWS', {'system': 'LINUX'})),
504 query_dict('http://example.com/path?system=LINUX'))
505 self.assertEqual(query_dict(update_url_query(
506 'http://example.com/path', {'fields': b'id,formats,subtitles'})),
507 query_dict('http://example.com/path?fields=id,formats,subtitles'))
508 self.assertEqual(query_dict(update_url_query(
509 'http://example.com/path', {'width': 1080, 'height': 720})),
510 query_dict('http://example.com/path?width=1080&height=720'))
511 self.assertEqual(query_dict(update_url_query(
512 'http://example.com/path', {'bitrate': 5020.43})),
513 query_dict('http://example.com/path?bitrate=5020.43'))
514 self.assertEqual(query_dict(update_url_query(
515 'http://example.com/path', {'test': '第二行тест'})),
516 query_dict('http://example.com/path?test=%E7%AC%AC%E4%BA%8C%E8%A1%8C%D1%82%D0%B5%D1%81%D1%82'))
518 def test_dict_get(self):
526 d = FALSE_VALUES.copy()
528 self.assertEqual(dict_get(d, 'a'), 42)
529 self.assertEqual(dict_get(d, 'b'), None)
530 self.assertEqual(dict_get(d, 'b', 42), 42)
531 self.assertEqual(dict_get(d, ('a', )), 42)
532 self.assertEqual(dict_get(d, ('b', 'a', )), 42)
533 self.assertEqual(dict_get(d, ('b', 'c', 'a', 'd', )), 42)
534 self.assertEqual(dict_get(d, ('b', 'c', )), None)
535 self.assertEqual(dict_get(d, ('b', 'c', ), 42), 42)
536 for key, false_value in FALSE_VALUES.items():
537 self.assertEqual(dict_get(d, ('b', 'c', key, )), None)
538 self.assertEqual(dict_get(d, ('b', 'c', key, ), skip_false_values=False), false_value)
540 def test_encode_compat_str(self):
541 self.assertEqual(encode_compat_str(b'\xd1\x82\xd0\xb5\xd1\x81\xd1\x82', 'utf-8'), 'тест')
542 self.assertEqual(encode_compat_str('тест', 'utf-8'), 'тест')
544 def test_parse_iso8601(self):
545 self.assertEqual(parse_iso8601('2014-03-23T23:04:26+0100'), 1395612266)
546 self.assertEqual(parse_iso8601('2014-03-23T22:04:26+0000'), 1395612266)
547 self.assertEqual(parse_iso8601('2014-03-23T22:04:26Z'), 1395612266)
548 self.assertEqual(parse_iso8601('2014-03-23T22:04:26.1234Z'), 1395612266)
549 self.assertEqual(parse_iso8601('2015-09-29T08:27:31.727'), 1443515251)
550 self.assertEqual(parse_iso8601('2015-09-29T08-27-31.727'), None)
552 def test_strip_jsonp(self):
553 stripped = strip_jsonp('cb ([ {"id":"532cb",\n\n\n"x":\n3}\n]\n);')
554 d = json.loads(stripped)
555 self.assertEqual(d, [{"id": "532cb", "x": 3}])
557 stripped = strip_jsonp('parseMetadata({"STATUS":"OK"})\n\n\n//epc')
558 d = json.loads(stripped)
559 self.assertEqual(d, {'STATUS': 'OK'})
561 stripped = strip_jsonp('ps.embedHandler({"status": "success"});')
562 d = json.loads(stripped)
563 self.assertEqual(d, {'status': 'success'})
565 def test_uppercase_escape(self):
566 self.assertEqual(uppercase_escape('aä'), 'aä')
567 self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐')
569 def test_lowercase_escape(self):
570 self.assertEqual(lowercase_escape('aä'), 'aä')
571 self.assertEqual(lowercase_escape('\\u0026'), '&')
573 def test_limit_length(self):
574 self.assertEqual(limit_length(None, 12), None)
575 self.assertEqual(limit_length('foo', 12), 'foo')
577 limit_length('foo bar baz asd', 12).startswith('foo bar'))
578 self.assertTrue('...' in limit_length('foo bar baz asd', 12))
580 def test_escape_rfc3986(self):
581 reserved = "!*'();:@&=+$,/?#[]"
582 unreserved = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_.~'
583 self.assertEqual(escape_rfc3986(reserved), reserved)
584 self.assertEqual(escape_rfc3986(unreserved), unreserved)
585 self.assertEqual(escape_rfc3986('тест'), '%D1%82%D0%B5%D1%81%D1%82')
586 self.assertEqual(escape_rfc3986('%D1%82%D0%B5%D1%81%D1%82'), '%D1%82%D0%B5%D1%81%D1%82')
587 self.assertEqual(escape_rfc3986('foo bar'), 'foo%20bar')
588 self.assertEqual(escape_rfc3986('foo%20bar'), 'foo%20bar')
590 def test_escape_url(self):
592 escape_url('http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavré_FD.mp4'),
593 'http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavre%CC%81_FD.mp4'
596 escape_url('http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erklärt/Das-Erste/Video?documentId=22673108&bcastId=5290'),
597 'http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erkl%C3%A4rt/Das-Erste/Video?documentId=22673108&bcastId=5290'
600 escape_url('http://тест.рф/фрагмент'),
601 'http://xn--e1aybc.xn--p1ai/%D1%84%D1%80%D0%B0%D0%B3%D0%BC%D0%B5%D0%BD%D1%82'
604 escape_url('http://тест.рф/абв?абв=абв#абв'),
605 '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'
607 self.assertEqual(escape_url('http://vimeo.com/56015672#at=0'), 'http://vimeo.com/56015672#at=0')
609 def test_js_to_json_realworld(self):
611 'clip':{'provider':'pseudo'}
613 self.assertEqual(js_to_json(inp), '''{
614 "clip":{"provider":"pseudo"}
616 json.loads(js_to_json(inp))
619 'playlist':[{'controls':{'all':null}}]
621 self.assertEqual(js_to_json(inp), '''{
622 "playlist":[{"controls":{"all":null}}]
625 inp = '''"The CW\\'s \\'Crazy Ex-Girlfriend\\'"'''
626 self.assertEqual(js_to_json(inp), '''"The CW's 'Crazy Ex-Girlfriend'"''')
628 inp = '"SAND Number: SAND 2013-7800P\\nPresenter: Tom Russo\\nHabanero Software Training - Xyce Software\\nXyce, Sandia\\u0027s"'
629 json_code = js_to_json(inp)
630 self.assertEqual(json.loads(json_code), json.loads(inp))
633 0:{src:'skipped', type: 'application/dash+xml'},
634 1:{src:'skipped', type: 'application/vnd.apple.mpegURL'},
636 self.assertEqual(js_to_json(inp), '''{
637 "0":{"src":"skipped", "type": "application/dash+xml"},
638 "1":{"src":"skipped", "type": "application/vnd.apple.mpegURL"}
641 def test_js_to_json_edgecases(self):
642 on = js_to_json("{abc_def:'1\\'\\\\2\\\\\\'3\"4'}")
643 self.assertEqual(json.loads(on), {"abc_def": "1'\\2\\'3\"4"})
645 on = js_to_json('{"abc": true}')
646 self.assertEqual(json.loads(on), {'abc': True})
648 # Ignore JavaScript code as well
655 self.assertEqual(d['x'], 1)
656 self.assertEqual(d['y'], 'a')
658 on = js_to_json('["abc", "def",]')
659 self.assertEqual(json.loads(on), ['abc', 'def'])
661 on = js_to_json('{"abc": "def",}')
662 self.assertEqual(json.loads(on), {'abc': 'def'})
664 on = js_to_json('{ 0: /* " \n */ ",]" , }')
665 self.assertEqual(json.loads(on), {'0': ',]'})
667 on = js_to_json(r'["<p>x<\/p>"]')
668 self.assertEqual(json.loads(on), ['<p>x</p>'])
670 on = js_to_json(r'["\xaa"]')
671 self.assertEqual(json.loads(on), ['\u00aa'])
673 on = js_to_json("['a\\\nb']")
674 self.assertEqual(json.loads(on), ['ab'])
676 on = js_to_json('{0xff:0xff}')
677 self.assertEqual(json.loads(on), {'255': 255})
679 on = js_to_json('{077:077}')
680 self.assertEqual(json.loads(on), {'63': 63})
682 on = js_to_json('{42:42}')
683 self.assertEqual(json.loads(on), {'42': 42})
685 def test_extract_attributes(self):
686 self.assertEqual(extract_attributes('<e x="y">'), {'x': 'y'})
687 self.assertEqual(extract_attributes("<e x='y'>"), {'x': 'y'})
688 self.assertEqual(extract_attributes('<e x=y>'), {'x': 'y'})
689 self.assertEqual(extract_attributes('<e x="a \'b\' c">'), {'x': "a 'b' c"})
690 self.assertEqual(extract_attributes('<e x=\'a "b" c\'>'), {'x': 'a "b" c'})
691 self.assertEqual(extract_attributes('<e x="y">'), {'x': 'y'})
692 self.assertEqual(extract_attributes('<e x="y">'), {'x': 'y'})
693 self.assertEqual(extract_attributes('<e x="&">'), {'x': '&'}) # XML
694 self.assertEqual(extract_attributes('<e x=""">'), {'x': '"'})
695 self.assertEqual(extract_attributes('<e x="£">'), {'x': '£'}) # HTML 3.2
696 self.assertEqual(extract_attributes('<e x="λ">'), {'x': 'λ'}) # HTML 4.0
697 self.assertEqual(extract_attributes('<e x="&foo">'), {'x': '&foo'})
698 self.assertEqual(extract_attributes('<e x="\'">'), {'x': "'"})
699 self.assertEqual(extract_attributes('<e x=\'"\'>'), {'x': '"'})
700 self.assertEqual(extract_attributes('<e x >'), {'x': None})
701 self.assertEqual(extract_attributes('<e x=y a>'), {'x': 'y', 'a': None})
702 self.assertEqual(extract_attributes('<e x= y>'), {'x': 'y'})
703 self.assertEqual(extract_attributes('<e x=1 y=2 x=3>'), {'y': '2', 'x': '3'})
704 self.assertEqual(extract_attributes('<e \nx=\ny\n>'), {'x': 'y'})
705 self.assertEqual(extract_attributes('<e \nx=\n"y"\n>'), {'x': 'y'})
706 self.assertEqual(extract_attributes("<e \nx=\n'y'\n>"), {'x': 'y'})
707 self.assertEqual(extract_attributes('<e \nx="\ny\n">'), {'x': '\ny\n'})
708 self.assertEqual(extract_attributes('<e CAPS=x>'), {'caps': 'x'}) # Names lowercased
709 self.assertEqual(extract_attributes('<e x=1 X=2>'), {'x': '2'})
710 self.assertEqual(extract_attributes('<e X=1 x=2>'), {'x': '2'})
711 self.assertEqual(extract_attributes('<e _:funny-name1=1>'), {'_:funny-name1': '1'})
712 self.assertEqual(extract_attributes('<e x="Fáilte 世界 \U0001f600">'), {'x': 'Fáilte 世界 \U0001f600'})
713 self.assertEqual(extract_attributes('<e x="décomposé">'), {'x': 'décompose\u0301'})
714 # "Narrow" Python builds don't support unicode code points outside BMP.
717 supports_outside_bmp = True
719 supports_outside_bmp = False
720 if supports_outside_bmp:
721 self.assertEqual(extract_attributes('<e x="Smile 😀!">'), {'x': 'Smile \U0001f600!'})
723 def test_clean_html(self):
724 self.assertEqual(clean_html('a:\nb'), 'a: b')
725 self.assertEqual(clean_html('a:\n "b"'), 'a: "b"')
727 def test_intlist_to_bytes(self):
729 intlist_to_bytes([0, 1, 127, 128, 255]),
730 b'\x00\x01\x7f\x80\xff')
732 def test_args_to_str(self):
734 args_to_str(['foo', 'ba/r', '-baz', '2 be', '']),
735 'foo ba/r -baz \'2 be\' \'\''
738 def test_parse_filesize(self):
739 self.assertEqual(parse_filesize(None), None)
740 self.assertEqual(parse_filesize(''), None)
741 self.assertEqual(parse_filesize('91 B'), 91)
742 self.assertEqual(parse_filesize('foobar'), None)
743 self.assertEqual(parse_filesize('2 MiB'), 2097152)
744 self.assertEqual(parse_filesize('5 GB'), 5000000000)
745 self.assertEqual(parse_filesize('1.2Tb'), 1200000000000)
746 self.assertEqual(parse_filesize('1,24 KB'), 1240)
748 def test_parse_count(self):
749 self.assertEqual(parse_count(None), None)
750 self.assertEqual(parse_count(''), None)
751 self.assertEqual(parse_count('0'), 0)
752 self.assertEqual(parse_count('1000'), 1000)
753 self.assertEqual(parse_count('1.000'), 1000)
754 self.assertEqual(parse_count('1.1k'), 1100)
755 self.assertEqual(parse_count('1.1kk'), 1100000)
756 self.assertEqual(parse_count('1.1kk '), 1100000)
757 self.assertEqual(parse_count('1.1kk views'), 1100000)
759 def test_version_tuple(self):
760 self.assertEqual(version_tuple('1'), (1,))
761 self.assertEqual(version_tuple('10.23.344'), (10, 23, 344))
762 self.assertEqual(version_tuple('10.1-6'), (10, 1, 6)) # avconv style
764 def test_detect_exe_version(self):
765 self.assertEqual(detect_exe_version('''ffmpeg version 1.2.1
766 built on May 27 2013 08:37:26 with gcc 4.7 (Debian 4.7.3-4)
767 configuration: --prefix=/usr --extra-'''), '1.2.1')
768 self.assertEqual(detect_exe_version('''ffmpeg version N-63176-g1fb4685
769 built on May 15 2014 22:09:06 with gcc 4.8.2 (GCC)'''), 'N-63176-g1fb4685')
770 self.assertEqual(detect_exe_version('''X server found. dri2 connection failed!
771 Trying to open render node...
772 Success at /dev/dri/renderD128.
773 ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')
775 def test_age_restricted(self):
776 self.assertFalse(age_restricted(None, 10)) # unrestricted content
777 self.assertFalse(age_restricted(1, None)) # unrestricted policy
778 self.assertFalse(age_restricted(8, 10))
779 self.assertTrue(age_restricted(18, 14))
780 self.assertFalse(age_restricted(18, 18))
782 def test_is_html(self):
783 self.assertFalse(is_html(b'\x49\x44\x43<html'))
784 self.assertTrue(is_html(b'<!DOCTYPE foo>\xaaa'))
785 self.assertTrue(is_html( # UTF-8 with BOM
786 b'\xef\xbb\xbf<!DOCTYPE foo>\xaaa'))
787 self.assertTrue(is_html( # UTF-16-LE
788 b'\xff\xfe<\x00h\x00t\x00m\x00l\x00>\x00\xe4\x00'
790 self.assertTrue(is_html( # UTF-16-BE
791 b'\xfe\xff\x00<\x00h\x00t\x00m\x00l\x00>\x00\xe4'
793 self.assertTrue(is_html( # UTF-32-BE
794 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'))
795 self.assertTrue(is_html( # UTF-32-LE
796 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'))
798 def test_render_table(self):
802 [[123, 4], [9999, 51]]),
807 def test_match_str(self):
808 self.assertRaises(ValueError, match_str, 'xy>foobar', {})
809 self.assertFalse(match_str('xy', {'x': 1200}))
810 self.assertTrue(match_str('!xy', {'x': 1200}))
811 self.assertTrue(match_str('x', {'x': 1200}))
812 self.assertFalse(match_str('!x', {'x': 1200}))
813 self.assertTrue(match_str('x', {'x': 0}))
814 self.assertFalse(match_str('x>0', {'x': 0}))
815 self.assertFalse(match_str('x>0', {}))
816 self.assertTrue(match_str('x>?0', {}))
817 self.assertTrue(match_str('x>1K', {'x': 1200}))
818 self.assertFalse(match_str('x>2K', {'x': 1200}))
819 self.assertTrue(match_str('x>=1200 & x < 1300', {'x': 1200}))
820 self.assertFalse(match_str('x>=1100 & x < 1200', {'x': 1200}))
821 self.assertFalse(match_str('y=a212', {'y': 'foobar42'}))
822 self.assertTrue(match_str('y=foobar42', {'y': 'foobar42'}))
823 self.assertFalse(match_str('y!=foobar42', {'y': 'foobar42'}))
824 self.assertTrue(match_str('y!=foobar2', {'y': 'foobar42'}))
825 self.assertFalse(match_str(
826 'like_count > 100 & dislike_count <? 50 & description',
827 {'like_count': 90, 'description': 'foo'}))
828 self.assertTrue(match_str(
829 'like_count > 100 & dislike_count <? 50 & description',
830 {'like_count': 190, 'description': 'foo'}))
831 self.assertFalse(match_str(
832 'like_count > 100 & dislike_count <? 50 & description',
833 {'like_count': 190, 'dislike_count': 60, 'description': 'foo'}))
834 self.assertFalse(match_str(
835 'like_count > 100 & dislike_count <? 50 & description',
836 {'like_count': 190, 'dislike_count': 10}))
838 def test_parse_dfxp_time_expr(self):
839 self.assertEqual(parse_dfxp_time_expr(None), None)
840 self.assertEqual(parse_dfxp_time_expr(''), None)
841 self.assertEqual(parse_dfxp_time_expr('0.1'), 0.1)
842 self.assertEqual(parse_dfxp_time_expr('0.1s'), 0.1)
843 self.assertEqual(parse_dfxp_time_expr('00:00:01'), 1.0)
844 self.assertEqual(parse_dfxp_time_expr('00:00:01.100'), 1.1)
845 self.assertEqual(parse_dfxp_time_expr('00:00:01:100'), 1.1)
847 def test_dfxp2srt(self):
848 dfxp_data = '''<?xml version="1.0" encoding="UTF-8"?>
849 <tt xmlns="http://www.w3.org/ns/ttml" xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter">
852 <p begin="0" end="1">The following line contains Chinese characters and special symbols</p>
853 <p begin="1" end="2">第二行<br/>♪♪</p>
854 <p begin="2" dur="1"><span>Third<br/>Line</span></p>
855 <p begin="3" end="-1">Lines with invalid timestamps are ignored</p>
856 <p begin="-1" end="-1">Ignore, two</p>
857 <p begin="3" dur="-1">Ignored, three</p>
862 00:00:00,000 --> 00:00:01,000
863 The following line contains Chinese characters and special symbols
866 00:00:01,000 --> 00:00:02,000
871 00:00:02,000 --> 00:00:03,000
876 self.assertEqual(dfxp2srt(dfxp_data), srt_data)
878 dfxp_data_no_default_namespace = '''<?xml version="1.0" encoding="UTF-8"?>
879 <tt xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter">
882 <p begin="0" end="1">The first line</p>
887 00:00:00,000 --> 00:00:01,000
891 self.assertEqual(dfxp2srt(dfxp_data_no_default_namespace), srt_data)
893 def test_cli_option(self):
894 self.assertEqual(cli_option({'proxy': '127.0.0.1:3128'}, '--proxy', 'proxy'), ['--proxy', '127.0.0.1:3128'])
895 self.assertEqual(cli_option({'proxy': None}, '--proxy', 'proxy'), [])
896 self.assertEqual(cli_option({}, '--proxy', 'proxy'), [])
898 def test_cli_valueless_option(self):
899 self.assertEqual(cli_valueless_option(
900 {'downloader': 'external'}, '--external-downloader', 'downloader', 'external'), ['--external-downloader'])
901 self.assertEqual(cli_valueless_option(
902 {'downloader': 'internal'}, '--external-downloader', 'downloader', 'external'), [])
903 self.assertEqual(cli_valueless_option(
904 {'nocheckcertificate': True}, '--no-check-certificate', 'nocheckcertificate'), ['--no-check-certificate'])
905 self.assertEqual(cli_valueless_option(
906 {'nocheckcertificate': False}, '--no-check-certificate', 'nocheckcertificate'), [])
907 self.assertEqual(cli_valueless_option(
908 {'checkcertificate': True}, '--no-check-certificate', 'checkcertificate', False), [])
909 self.assertEqual(cli_valueless_option(
910 {'checkcertificate': False}, '--no-check-certificate', 'checkcertificate', False), ['--no-check-certificate'])
912 def test_cli_bool_option(self):
915 {'nocheckcertificate': True}, '--no-check-certificate', 'nocheckcertificate'),
916 ['--no-check-certificate', 'true'])
919 {'nocheckcertificate': True}, '--no-check-certificate', 'nocheckcertificate', separator='='),
920 ['--no-check-certificate=true'])
923 {'nocheckcertificate': True}, '--check-certificate', 'nocheckcertificate', 'false', 'true'),
924 ['--check-certificate', 'false'])
927 {'nocheckcertificate': True}, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='),
928 ['--check-certificate=false'])
931 {'nocheckcertificate': False}, '--check-certificate', 'nocheckcertificate', 'false', 'true'),
932 ['--check-certificate', 'true'])
935 {'nocheckcertificate': False}, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='),
936 ['--check-certificate=true'])
938 def test_ohdave_rsa_encrypt(self):
939 N = 0xab86b6371b5318aaa1d3c9e612a9f1264f372323c8c0f19875b5fc3b3fd3afcc1e5bec527aa94bfa85bffc157e4245aebda05389a5357b75115ac94f074aefcd
943 ohdave_rsa_encrypt(b'aa111222', e, N),
944 '726664bd9a23fd0c70f9f1b84aab5e3905ce1e45a584e9cbcf9bcc7510338fc1986d6c599ff990d923aa43c51c0d9013cd572e13bc58f4ae48f2ed8c0b0ba881')
946 def test_encode_base_n(self):
947 self.assertEqual(encode_base_n(0, 30), '0')
948 self.assertEqual(encode_base_n(80, 30), '2k')
950 custom_table = '9876543210ZYXWVUTSRQPONMLKJIHGFEDCBA'
951 self.assertEqual(encode_base_n(0, 30, custom_table), '9')
952 self.assertEqual(encode_base_n(80, 30, custom_table), '7P')
954 self.assertRaises(ValueError, encode_base_n, 0, 70)
955 self.assertRaises(ValueError, encode_base_n, 0, 60, custom_table)
957 if __name__ == '__main__':