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 (
38 get_element_by_attribute
,
39 get_elements_by_class
,
40 get_elements_by_attribute
,
102 cli_valueless_option
,
106 from youtube_dl
.compat
import (
108 compat_etree_fromstring
,
117 class TestUtil(unittest
.TestCase
):
118 def test_timeconvert(self
):
119 self
.assertTrue(timeconvert('') is None)
120 self
.assertTrue(timeconvert('bougrg') is None)
122 def test_sanitize_filename(self
):
123 self
.assertEqual(sanitize_filename('abc'), 'abc')
124 self
.assertEqual(sanitize_filename('abc_d-e'), 'abc_d-e')
126 self
.assertEqual(sanitize_filename('123'), '123')
128 self
.assertEqual('abc_de', sanitize_filename('abc/de'))
129 self
.assertFalse('/' in sanitize_filename('abc/de///'))
131 self
.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de'))
132 self
.assertEqual('xxx', sanitize_filename('xxx/<>\\*|'))
133 self
.assertEqual('yes no', sanitize_filename('yes? no'))
134 self
.assertEqual('this - that', sanitize_filename('this: that'))
136 self
.assertEqual(sanitize_filename('AT&T'), 'AT&T')
138 self
.assertEqual(sanitize_filename(aumlaut
), aumlaut
)
139 tests
= '\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430'
140 self
.assertEqual(sanitize_filename(tests
), tests
)
143 sanitize_filename('New World record at 0:12:34'),
144 'New World record at 0_12_34')
146 self
.assertEqual(sanitize_filename('--gasdgf'), '_-gasdgf')
147 self
.assertEqual(sanitize_filename('--gasdgf', is_id
=True), '--gasdgf')
148 self
.assertEqual(sanitize_filename('.gasdgf'), 'gasdgf')
149 self
.assertEqual(sanitize_filename('.gasdgf', is_id
=True), '.gasdgf')
153 for fbc
in forbidden
:
154 self
.assertTrue(fbc
not in sanitize_filename(fc
))
156 def test_sanitize_filename_restricted(self
):
157 self
.assertEqual(sanitize_filename('abc', restricted
=True), 'abc')
158 self
.assertEqual(sanitize_filename('abc_d-e', restricted
=True), 'abc_d-e')
160 self
.assertEqual(sanitize_filename('123', restricted
=True), '123')
162 self
.assertEqual('abc_de', sanitize_filename('abc/de', restricted
=True))
163 self
.assertFalse('/' in sanitize_filename('abc/de///', restricted
=True))
165 self
.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de', restricted
=True))
166 self
.assertEqual('xxx', sanitize_filename('xxx/<>\\*|', restricted
=True))
167 self
.assertEqual('yes_no', sanitize_filename('yes? no', restricted
=True))
168 self
.assertEqual('this_-_that', sanitize_filename('this: that', restricted
=True))
170 tests
= 'aäb\u4e2d\u56fd\u7684c'
171 self
.assertEqual(sanitize_filename(tests
, restricted
=True), 'aab_c')
172 self
.assertTrue(sanitize_filename('\xf6', restricted
=True) != '') # No empty filename
174 forbidden
= '"\0\\/&!: \'\t\n()[]{}$;`^,#'
176 for fbc
in forbidden
:
177 self
.assertTrue(fbc
not in sanitize_filename(fc
, restricted
=True))
179 # Handle a common case more neatly
180 self
.assertEqual(sanitize_filename('\u5927\u58f0\u5e26 - Song', restricted
=True), 'Song')
181 self
.assertEqual(sanitize_filename('\u603b\u7edf: Speech', restricted
=True), 'Speech')
182 # .. but make sure the file name is never empty
183 self
.assertTrue(sanitize_filename('-', restricted
=True) != '')
184 self
.assertTrue(sanitize_filename(':', restricted
=True) != '')
186 self
.assertEqual(sanitize_filename(
187 'ÂÃÄÀÁÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖŐØŒÙÚÛÜŰÝÞßàáâãäåæçèéêëìíîïðñòóôõöőøœùúûüűýþÿ', restricted
=True),
188 'AAAAAAAECEEEEIIIIDNOOOOOOOOEUUUUUYTHssaaaaaaaeceeeeiiiionooooooooeuuuuuythy')
190 def test_sanitize_ids(self
):
191 self
.assertEqual(sanitize_filename('_n_cd26wFpw', is_id
=True), '_n_cd26wFpw')
192 self
.assertEqual(sanitize_filename('_BD_eEpuzXw', is_id
=True), '_BD_eEpuzXw')
193 self
.assertEqual(sanitize_filename('N0Y__7-UOdI', is_id
=True), 'N0Y__7-UOdI')
195 def test_sanitize_path(self
):
196 if sys
.platform
!= 'win32':
199 self
.assertEqual(sanitize_path('abc'), 'abc')
200 self
.assertEqual(sanitize_path('abc/def'), 'abc\\def')
201 self
.assertEqual(sanitize_path('abc\\def'), 'abc\\def')
202 self
.assertEqual(sanitize_path('abc|def'), 'abc#def')
203 self
.assertEqual(sanitize_path('<>:"|?*'), '#######')
204 self
.assertEqual(sanitize_path('C:/abc/def'), 'C:\\abc\\def')
205 self
.assertEqual(sanitize_path('C?:/abc/def'), 'C##\\abc\\def')
207 self
.assertEqual(sanitize_path('\\\\?\\UNC\\ComputerName\\abc'), '\\\\?\\UNC\\ComputerName\\abc')
208 self
.assertEqual(sanitize_path('\\\\?\\UNC/ComputerName/abc'), '\\\\?\\UNC\\ComputerName\\abc')
210 self
.assertEqual(sanitize_path('\\\\?\\C:\\abc'), '\\\\?\\C:\\abc')
211 self
.assertEqual(sanitize_path('\\\\?\\C:/abc'), '\\\\?\\C:\\abc')
212 self
.assertEqual(sanitize_path('\\\\?\\C:\\ab?c\\de:f'), '\\\\?\\C:\\ab#c\\de#f')
213 self
.assertEqual(sanitize_path('\\\\?\\C:\\abc'), '\\\\?\\C:\\abc')
216 sanitize_path('youtube/%(uploader)s/%(autonumber)s-%(title)s-%(upload_date)s.%(ext)s'),
217 'youtube\\%(uploader)s\\%(autonumber)s-%(title)s-%(upload_date)s.%(ext)s')
220 sanitize_path('youtube/TheWreckingYard ./00001-Not bad, Especially for Free! (1987 Yamaha 700)-20141116.mp4.part'),
221 'youtube\\TheWreckingYard #\\00001-Not bad, Especially for Free! (1987 Yamaha 700)-20141116.mp4.part')
222 self
.assertEqual(sanitize_path('abc/def...'), 'abc\\def..#')
223 self
.assertEqual(sanitize_path('abc.../def'), 'abc..#\\def')
224 self
.assertEqual(sanitize_path('abc.../def...'), 'abc..#\\def..#')
226 self
.assertEqual(sanitize_path('../abc'), '..\\abc')
227 self
.assertEqual(sanitize_path('../../abc'), '..\\..\\abc')
228 self
.assertEqual(sanitize_path('./abc'), 'abc')
229 self
.assertEqual(sanitize_path('./../abc'), '..\\abc')
231 def test_sanitize_url(self
):
232 self
.assertEqual(sanitize_url('//foo.bar'), 'http://foo.bar')
233 self
.assertEqual(sanitize_url('httpss://foo.bar'), 'https://foo.bar')
234 self
.assertEqual(sanitize_url('rmtps://foo.bar'), 'rtmps://foo.bar')
235 self
.assertEqual(sanitize_url('https://foo.bar'), 'https://foo.bar')
237 def test_expand_path(self
):
239 return '%{0}%'.format(var
) if sys
.platform
== 'win32' else '${0}'.format(var
)
241 compat_setenv('YOUTUBE_DL_EXPATH_PATH', 'expanded')
242 self
.assertEqual(expand_path(env('YOUTUBE_DL_EXPATH_PATH')), 'expanded')
243 self
.assertEqual(expand_path(env('HOME')), compat_getenv('HOME'))
244 self
.assertEqual(expand_path('~'), compat_getenv('HOME'))
246 expand_path('~/%s' % env('YOUTUBE_DL_EXPATH_PATH')),
247 '%s/expanded' % compat_getenv('HOME'))
249 def test_prepend_extension(self
):
250 self
.assertEqual(prepend_extension('abc.ext', 'temp'), 'abc.temp.ext')
251 self
.assertEqual(prepend_extension('abc.ext', 'temp', 'ext'), 'abc.temp.ext')
252 self
.assertEqual(prepend_extension('abc.unexpected_ext', 'temp', 'ext'), 'abc.unexpected_ext.temp')
253 self
.assertEqual(prepend_extension('abc', 'temp'), 'abc.temp')
254 self
.assertEqual(prepend_extension('.abc', 'temp'), '.abc.temp')
255 self
.assertEqual(prepend_extension('.abc.ext', 'temp'), '.abc.temp.ext')
257 def test_replace_extension(self
):
258 self
.assertEqual(replace_extension('abc.ext', 'temp'), 'abc.temp')
259 self
.assertEqual(replace_extension('abc.ext', 'temp', 'ext'), 'abc.temp')
260 self
.assertEqual(replace_extension('abc.unexpected_ext', 'temp', 'ext'), 'abc.unexpected_ext.temp')
261 self
.assertEqual(replace_extension('abc', 'temp'), 'abc.temp')
262 self
.assertEqual(replace_extension('.abc', 'temp'), '.abc.temp')
263 self
.assertEqual(replace_extension('.abc.ext', 'temp'), '.abc.temp')
265 def test_subtitles_filename(self
):
266 self
.assertEqual(subtitles_filename('abc.ext', 'en', 'vtt'), 'abc.en.vtt')
267 self
.assertEqual(subtitles_filename('abc.ext', 'en', 'vtt', 'ext'), 'abc.en.vtt')
268 self
.assertEqual(subtitles_filename('abc.unexpected_ext', 'en', 'vtt', 'ext'), 'abc.unexpected_ext.en.vtt')
270 def test_remove_start(self
):
271 self
.assertEqual(remove_start(None, 'A - '), None)
272 self
.assertEqual(remove_start('A - B', 'A - '), 'B')
273 self
.assertEqual(remove_start('B - A', 'A - '), 'B - A')
275 def test_remove_end(self
):
276 self
.assertEqual(remove_end(None, ' - B'), None)
277 self
.assertEqual(remove_end('A - B', ' - B'), 'A')
278 self
.assertEqual(remove_end('B - A', ' - B'), 'B - A')
280 def test_remove_quotes(self
):
281 self
.assertEqual(remove_quotes(None), None)
282 self
.assertEqual(remove_quotes('"'), '"')
283 self
.assertEqual(remove_quotes("'"), "'")
284 self
.assertEqual(remove_quotes(';'), ';')
285 self
.assertEqual(remove_quotes('";'), '";')
286 self
.assertEqual(remove_quotes('""'), '')
287 self
.assertEqual(remove_quotes('";"'), ';')
289 def test_ordered_set(self
):
290 self
.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7])
291 self
.assertEqual(orderedSet([]), [])
292 self
.assertEqual(orderedSet([1]), [1])
293 # keep the list ordered
294 self
.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1])
296 def test_unescape_html(self
):
297 self
.assertEqual(unescapeHTML('%20;'), '%20;')
298 self
.assertEqual(unescapeHTML('/'), '/')
299 self
.assertEqual(unescapeHTML('/'), '/')
300 self
.assertEqual(unescapeHTML('é'), 'é')
301 self
.assertEqual(unescapeHTML('�'), '�')
302 self
.assertEqual(unescapeHTML('&a"'), '&a"')
304 self
.assertEqual(unescapeHTML('.''), '.\'')
306 def test_date_from_str(self
):
307 self
.assertEqual(date_from_str('yesterday'), date_from_str('now-1day'))
308 self
.assertEqual(date_from_str('now+7day'), date_from_str('now+1week'))
309 self
.assertEqual(date_from_str('now+14day'), date_from_str('now+2week'))
310 self
.assertEqual(date_from_str('now+365day'), date_from_str('now+1year'))
311 self
.assertEqual(date_from_str('now+30day'), date_from_str('now+1month'))
313 def test_daterange(self
):
314 _20century
= DateRange("19000101", "20000101")
315 self
.assertFalse("17890714" in _20century
)
316 _ac
= DateRange("00010101")
317 self
.assertTrue("19690721" in _ac
)
318 _firstmilenium
= DateRange(end
="10000101")
319 self
.assertTrue("07110427" in _firstmilenium
)
321 def test_unified_dates(self
):
322 self
.assertEqual(unified_strdate('December 21, 2010'), '20101221')
323 self
.assertEqual(unified_strdate('8/7/2009'), '20090708')
324 self
.assertEqual(unified_strdate('Dec 14, 2012'), '20121214')
325 self
.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
326 self
.assertEqual(unified_strdate('1968 12 10'), '19681210')
327 self
.assertEqual(unified_strdate('1968-12-10'), '19681210')
328 self
.assertEqual(unified_strdate('28/01/2014 21:00:00 +0100'), '20140128')
330 unified_strdate('11/26/2014 11:30:00 AM PST', day_first
=False),
333 unified_strdate('2/2/2015 6:47:40 PM', day_first
=False),
335 self
.assertEqual(unified_strdate('Feb 14th 2016 5:45PM'), '20160214')
336 self
.assertEqual(unified_strdate('25-09-2014'), '20140925')
337 self
.assertEqual(unified_strdate('27.02.2016 17:30'), '20160227')
338 self
.assertEqual(unified_strdate('UNKNOWN DATE FORMAT'), None)
339 self
.assertEqual(unified_strdate('Feb 7, 2016 at 6:35 pm'), '20160207')
340 self
.assertEqual(unified_strdate('July 15th, 2013'), '20130715')
341 self
.assertEqual(unified_strdate('September 1st, 2013'), '20130901')
342 self
.assertEqual(unified_strdate('Sep 2nd, 2013'), '20130902')
344 def test_unified_timestamps(self
):
345 self
.assertEqual(unified_timestamp('December 21, 2010'), 1292889600)
346 self
.assertEqual(unified_timestamp('8/7/2009'), 1247011200)
347 self
.assertEqual(unified_timestamp('Dec 14, 2012'), 1355443200)
348 self
.assertEqual(unified_timestamp('2012/10/11 01:56:38 +0000'), 1349920598)
349 self
.assertEqual(unified_timestamp('1968 12 10'), -33436800)
350 self
.assertEqual(unified_timestamp('1968-12-10'), -33436800)
351 self
.assertEqual(unified_timestamp('28/01/2014 21:00:00 +0100'), 1390939200)
353 unified_timestamp('11/26/2014 11:30:00 AM PST', day_first
=False),
356 unified_timestamp('2/2/2015 6:47:40 PM', day_first
=False),
358 self
.assertEqual(unified_timestamp('Feb 14th 2016 5:45PM'), 1455471900)
359 self
.assertEqual(unified_timestamp('25-09-2014'), 1411603200)
360 self
.assertEqual(unified_timestamp('27.02.2016 17:30'), 1456594200)
361 self
.assertEqual(unified_timestamp('UNKNOWN DATE FORMAT'), None)
362 self
.assertEqual(unified_timestamp('May 16, 2016 11:15 PM'), 1463440500)
363 self
.assertEqual(unified_timestamp('Feb 7, 2016 at 6:35 pm'), 1454870100)
364 self
.assertEqual(unified_timestamp('2017-03-30T17:52:41Q'), 1490896361)
365 self
.assertEqual(unified_timestamp('Sep 11, 2013 | 5:49 AM'), 1378878540)
366 self
.assertEqual(unified_timestamp('December 15, 2017 at 7:49 am'), 1513324140)
367 self
.assertEqual(unified_timestamp('2018-03-14T08:32:43.1493874+00:00'), 1521016363)
369 def test_determine_ext(self
):
370 self
.assertEqual(determine_ext('http://example.com/foo/bar.mp4/?download'), 'mp4')
371 self
.assertEqual(determine_ext('http://example.com/foo/bar/?download', None), None)
372 self
.assertEqual(determine_ext('http://example.com/foo/bar.nonext/?download', None), None)
373 self
.assertEqual(determine_ext('http://example.com/foo/bar/mp4?download', None), None)
374 self
.assertEqual(determine_ext('http://example.com/foo/bar.m3u8//?download'), 'm3u8')
375 self
.assertEqual(determine_ext('foobar', None), None)
377 def test_find_xpath_attr(self
):
385 doc
= compat_etree_fromstring(testxml
)
387 self
.assertEqual(find_xpath_attr(doc
, './/fourohfour', 'n'), None)
388 self
.assertEqual(find_xpath_attr(doc
, './/fourohfour', 'n', 'v'), None)
389 self
.assertEqual(find_xpath_attr(doc
, './/node', 'n'), None)
390 self
.assertEqual(find_xpath_attr(doc
, './/node', 'n', 'v'), None)
391 self
.assertEqual(find_xpath_attr(doc
, './/node', 'x'), doc
[1])
392 self
.assertEqual(find_xpath_attr(doc
, './/node', 'x', 'a'), doc
[1])
393 self
.assertEqual(find_xpath_attr(doc
, './/node', 'x', 'b'), doc
[3])
394 self
.assertEqual(find_xpath_attr(doc
, './/node', 'y'), doc
[2])
395 self
.assertEqual(find_xpath_attr(doc
, './/node', 'y', 'c'), doc
[2])
396 self
.assertEqual(find_xpath_attr(doc
, './/node', 'y', 'd'), doc
[3])
397 self
.assertEqual(find_xpath_attr(doc
, './/node', 'x', ''), doc
[4])
399 def test_xpath_with_ns(self
):
400 testxml
= '''<root xmlns:media="http://example.com/">
402 <media:author>The Author</media:author>
403 <url>http://server.com/download.mp3</url>
406 doc
= compat_etree_fromstring(testxml
)
407 find
= lambda p
: doc
.find(xpath_with_ns(p
, {'media': 'http://example.com/'}
))
408 self
.assertTrue(find('media:song') is not None)
409 self
.assertEqual(find('media:song/media:author').text
, 'The Author')
410 self
.assertEqual(find('media:song/url').text
, 'http://server.com/download.mp3')
412 def test_xpath_element(self
):
413 doc
= xml
.etree
.ElementTree
.Element('root')
414 div
= xml
.etree
.ElementTree
.SubElement(doc
, 'div')
415 p
= xml
.etree
.ElementTree
.SubElement(div
, 'p')
417 self
.assertEqual(xpath_element(doc
, 'div/p'), p
)
418 self
.assertEqual(xpath_element(doc
, ['div/p']), p
)
419 self
.assertEqual(xpath_element(doc
, ['div/bar', 'div/p']), p
)
420 self
.assertEqual(xpath_element(doc
, 'div/bar', default
='default'), 'default')
421 self
.assertEqual(xpath_element(doc
, ['div/bar'], default
='default'), 'default')
422 self
.assertTrue(xpath_element(doc
, 'div/bar') is None)
423 self
.assertTrue(xpath_element(doc
, ['div/bar']) is None)
424 self
.assertTrue(xpath_element(doc
, ['div/bar'], 'div/baz') is None)
425 self
.assertRaises(ExtractorError
, xpath_element
, doc
, 'div/bar', fatal
=True)
426 self
.assertRaises(ExtractorError
, xpath_element
, doc
, ['div/bar'], fatal
=True)
427 self
.assertRaises(ExtractorError
, xpath_element
, doc
, ['div/bar', 'div/baz'], fatal
=True)
429 def test_xpath_text(self
):
435 doc
= compat_etree_fromstring(testxml
)
436 self
.assertEqual(xpath_text(doc
, 'div/p'), 'Foo')
437 self
.assertEqual(xpath_text(doc
, 'div/bar', default
='default'), 'default')
438 self
.assertTrue(xpath_text(doc
, 'div/bar') is None)
439 self
.assertRaises(ExtractorError
, xpath_text
, doc
, 'div/bar', fatal
=True)
441 def test_xpath_attr(self
):
447 doc
= compat_etree_fromstring(testxml
)
448 self
.assertEqual(xpath_attr(doc
, 'div/p', 'x'), 'a')
449 self
.assertEqual(xpath_attr(doc
, 'div/bar', 'x'), None)
450 self
.assertEqual(xpath_attr(doc
, 'div/p', 'y'), None)
451 self
.assertEqual(xpath_attr(doc
, 'div/bar', 'x', default
='default'), 'default')
452 self
.assertEqual(xpath_attr(doc
, 'div/p', 'y', default
='default'), 'default')
453 self
.assertRaises(ExtractorError
, xpath_attr
, doc
, 'div/bar', 'x', fatal
=True)
454 self
.assertRaises(ExtractorError
, xpath_attr
, doc
, 'div/p', 'y', fatal
=True)
456 def test_smuggle_url(self
):
457 data
= {"ö": "ö", "abc": [3]}
458 url
= 'https://foo.bar/baz?x=y#a'
459 smug_url
= smuggle_url(url
, data
)
460 unsmug_url
, unsmug_data
= unsmuggle_url(smug_url
)
461 self
.assertEqual(url
, unsmug_url
)
462 self
.assertEqual(data
, unsmug_data
)
464 res_url
, res_data
= unsmuggle_url(url
)
465 self
.assertEqual(res_url
, url
)
466 self
.assertEqual(res_data
, None)
468 smug_url
= smuggle_url(url
, {'a': 'b'}
)
469 smug_smug_url
= smuggle_url(smug_url
, {'c': 'd'}
)
470 res_url
, res_data
= unsmuggle_url(smug_smug_url
)
471 self
.assertEqual(res_url
, url
)
472 self
.assertEqual(res_data
, {'a': 'b', 'c': 'd'}
)
474 def test_shell_quote(self
):
475 args
= ['ffmpeg', '-i', encodeFilename('ñ€ß\'.mp4')]
478 """ffmpeg -i 'ñ€ß'"'"'.mp4'""" if compat_os_name
!= 'nt' else '''ffmpeg -i "ñ€ß'.mp4"''')
480 def test_float_or_none(self
):
481 self
.assertEqual(float_or_none('42.42'), 42.42)
482 self
.assertEqual(float_or_none('42'), 42.0)
483 self
.assertEqual(float_or_none(''), None)
484 self
.assertEqual(float_or_none(None), None)
485 self
.assertEqual(float_or_none([]), None)
486 self
.assertEqual(float_or_none(set()), None)
488 def test_int_or_none(self
):
489 self
.assertEqual(int_or_none('42'), 42)
490 self
.assertEqual(int_or_none(''), None)
491 self
.assertEqual(int_or_none(None), None)
492 self
.assertEqual(int_or_none([]), None)
493 self
.assertEqual(int_or_none(set()), None)
495 def test_str_to_int(self
):
496 self
.assertEqual(str_to_int('123,456'), 123456)
497 self
.assertEqual(str_to_int('123.456'), 123456)
499 def test_url_basename(self
):
500 self
.assertEqual(url_basename('http://foo.de/'), '')
501 self
.assertEqual(url_basename('http://foo.de/bar/baz'), 'baz')
502 self
.assertEqual(url_basename('http://foo.de/bar/baz?x=y'), 'baz')
503 self
.assertEqual(url_basename('http://foo.de/bar/baz#x=y'), 'baz')
504 self
.assertEqual(url_basename('http://foo.de/bar/baz/'), 'baz')
506 url_basename('http://media.w3.org/2010/05/sintel/trailer.mp4'),
509 def test_base_url(self
):
510 self
.assertEqual(base_url('http://foo.de/'), 'http://foo.de/')
511 self
.assertEqual(base_url('http://foo.de/bar'), 'http://foo.de/')
512 self
.assertEqual(base_url('http://foo.de/bar/'), 'http://foo.de/bar/')
513 self
.assertEqual(base_url('http://foo.de/bar/baz'), 'http://foo.de/bar/')
514 self
.assertEqual(base_url('http://foo.de/bar/baz?x=z/x/c'), 'http://foo.de/bar/')
516 def test_urljoin(self
):
517 self
.assertEqual(urljoin('http://foo.de/', '/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
518 self
.assertEqual(urljoin(b
'http://foo.de/', '/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
519 self
.assertEqual(urljoin('http://foo.de/', b
'/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
520 self
.assertEqual(urljoin(b
'http://foo.de/', b
'/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
521 self
.assertEqual(urljoin('//foo.de/', '/a/b/c.txt'), '//foo.de/a/b/c.txt')
522 self
.assertEqual(urljoin('http://foo.de/', 'a/b/c.txt'), 'http://foo.de/a/b/c.txt')
523 self
.assertEqual(urljoin('http://foo.de', '/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
524 self
.assertEqual(urljoin('http://foo.de', 'a/b/c.txt'), 'http://foo.de/a/b/c.txt')
525 self
.assertEqual(urljoin('http://foo.de/', 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
526 self
.assertEqual(urljoin('http://foo.de/', '//foo.de/a/b/c.txt'), '//foo.de/a/b/c.txt')
527 self
.assertEqual(urljoin(None, 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
528 self
.assertEqual(urljoin(None, '//foo.de/a/b/c.txt'), '//foo.de/a/b/c.txt')
529 self
.assertEqual(urljoin('', 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
530 self
.assertEqual(urljoin(['foobar'], 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
531 self
.assertEqual(urljoin('http://foo.de/', None), None)
532 self
.assertEqual(urljoin('http://foo.de/', ''), None)
533 self
.assertEqual(urljoin('http://foo.de/', ['foobar']), None)
534 self
.assertEqual(urljoin('http://foo.de/a/b/c.txt', '.././../d.txt'), 'http://foo.de/d.txt')
535 self
.assertEqual(urljoin('http://foo.de/a/b/c.txt', 'rtmp://foo.de'), 'rtmp://foo.de')
536 self
.assertEqual(urljoin(None, 'rtmp://foo.de'), 'rtmp://foo.de')
538 def test_url_or_none(self
):
539 self
.assertEqual(url_or_none(None), None)
540 self
.assertEqual(url_or_none(''), None)
541 self
.assertEqual(url_or_none('foo'), None)
542 self
.assertEqual(url_or_none('http://foo.de'), 'http://foo.de')
543 self
.assertEqual(url_or_none('https://foo.de'), 'https://foo.de')
544 self
.assertEqual(url_or_none('http$://foo.de'), None)
545 self
.assertEqual(url_or_none('http://foo.de'), 'http://foo.de')
546 self
.assertEqual(url_or_none('//foo.de'), '//foo.de')
548 def test_parse_age_limit(self
):
549 self
.assertEqual(parse_age_limit(None), None)
550 self
.assertEqual(parse_age_limit(False), None)
551 self
.assertEqual(parse_age_limit('invalid'), None)
552 self
.assertEqual(parse_age_limit(0), 0)
553 self
.assertEqual(parse_age_limit(18), 18)
554 self
.assertEqual(parse_age_limit(21), 21)
555 self
.assertEqual(parse_age_limit(22), None)
556 self
.assertEqual(parse_age_limit('18'), 18)
557 self
.assertEqual(parse_age_limit('18+'), 18)
558 self
.assertEqual(parse_age_limit('PG-13'), 13)
559 self
.assertEqual(parse_age_limit('TV-14'), 14)
560 self
.assertEqual(parse_age_limit('TV-MA'), 17)
561 self
.assertEqual(parse_age_limit('TV14'), 14)
562 self
.assertEqual(parse_age_limit('TV_G'), 0)
564 def test_parse_duration(self
):
565 self
.assertEqual(parse_duration(None), None)
566 self
.assertEqual(parse_duration(False), None)
567 self
.assertEqual(parse_duration('invalid'), None)
568 self
.assertEqual(parse_duration('1'), 1)
569 self
.assertEqual(parse_duration('1337:12'), 80232)
570 self
.assertEqual(parse_duration('9:12:43'), 33163)
571 self
.assertEqual(parse_duration('12:00'), 720)
572 self
.assertEqual(parse_duration('00:01:01'), 61)
573 self
.assertEqual(parse_duration('x:y'), None)
574 self
.assertEqual(parse_duration('3h11m53s'), 11513)
575 self
.assertEqual(parse_duration('3h 11m 53s'), 11513)
576 self
.assertEqual(parse_duration('3 hours 11 minutes 53 seconds'), 11513)
577 self
.assertEqual(parse_duration('3 hours 11 mins 53 secs'), 11513)
578 self
.assertEqual(parse_duration('62m45s'), 3765)
579 self
.assertEqual(parse_duration('6m59s'), 419)
580 self
.assertEqual(parse_duration('49s'), 49)
581 self
.assertEqual(parse_duration('0h0m0s'), 0)
582 self
.assertEqual(parse_duration('0m0s'), 0)
583 self
.assertEqual(parse_duration('0s'), 0)
584 self
.assertEqual(parse_duration('01:02:03.05'), 3723.05)
585 self
.assertEqual(parse_duration('T30M38S'), 1838)
586 self
.assertEqual(parse_duration('5 s'), 5)
587 self
.assertEqual(parse_duration('3 min'), 180)
588 self
.assertEqual(parse_duration('2.5 hours'), 9000)
589 self
.assertEqual(parse_duration('02:03:04'), 7384)
590 self
.assertEqual(parse_duration('01:02:03:04'), 93784)
591 self
.assertEqual(parse_duration('1 hour 3 minutes'), 3780)
592 self
.assertEqual(parse_duration('87 Min.'), 5220)
593 self
.assertEqual(parse_duration('PT1H0.040S'), 3600.04)
594 self
.assertEqual(parse_duration('PT00H03M30SZ'), 210)
595 self
.assertEqual(parse_duration('P0Y0M0DT0H4M20.880S'), 260.88)
597 def test_fix_xml_ampersands(self
):
599 fix_xml_ampersands('"&x=y&z=a'), '"&x=y&z=a')
601 fix_xml_ampersands('"&x=y&wrong;&z=a'),
602 '"&x=y&wrong;&z=a')
604 fix_xml_ampersands('&'><"'),
605 '&'><"')
607 fix_xml_ampersands('Ӓ᪼'), 'Ӓ᪼')
608 self
.assertEqual(fix_xml_ampersands('&#&#'), '&#&#')
610 def test_paged_list(self
):
611 def testPL(size
, pagesize
, sliceargs
, expected
):
612 def get_page(pagenum
):
613 firstid
= pagenum
* pagesize
614 upto
= min(size
, pagenum
* pagesize
+ pagesize
)
615 for i
in range(firstid
, upto
):
618 pl
= OnDemandPagedList(get_page
, pagesize
)
619 got
= pl
.getslice(*sliceargs
)
620 self
.assertEqual(got
, expected
)
622 iapl
= InAdvancePagedList(get_page
, size
// pagesize
+ 1, pagesize
)
623 got
= iapl
.getslice(*sliceargs
)
624 self
.assertEqual(got
, expected
)
626 testPL(5, 2, (), [0, 1, 2, 3, 4])
627 testPL(5, 2, (1,), [1, 2, 3, 4])
628 testPL(5, 2, (2,), [2, 3, 4])
629 testPL(5, 2, (4,), [4])
630 testPL(5, 2, (0, 3), [0, 1, 2])
631 testPL(5, 2, (1, 4), [1, 2, 3])
632 testPL(5, 2, (2, 99), [2, 3, 4])
633 testPL(5, 2, (20, 99), [])
635 def test_read_batch_urls(self
):
636 f
= io
.StringIO('''\xef\xbb\xbf foo
639 # More after this line\r
642 self
.assertEqual(read_batch_urls(f
), ['foo', 'bar', 'baz', 'bam'])
644 def test_urlencode_postdata(self
):
645 data
= urlencode_postdata({'username': 'foo@bar.com', 'password': '1234'}
)
646 self
.assertTrue(isinstance(data
, bytes))
648 def test_update_url_query(self
):
650 return compat_parse_qs(compat_urlparse
.urlparse(url
).query
)
651 self
.assertEqual(query_dict(update_url_query(
652 'http://example.com/path', {'quality': ['HD'], 'format': ['mp4']}
)),
653 query_dict('http://example.com/path?quality=HD&format=mp4'))
654 self
.assertEqual(query_dict(update_url_query(
655 'http://example.com/path', {'system': ['LINUX', 'WINDOWS']}
)),
656 query_dict('http://example.com/path?system=LINUX&system=WINDOWS'))
657 self
.assertEqual(query_dict(update_url_query(
658 'http://example.com/path', {'fields': 'id,formats,subtitles'}
)),
659 query_dict('http://example.com/path?fields=id,formats,subtitles'))
660 self
.assertEqual(query_dict(update_url_query(
661 'http://example.com/path', {'fields': ('id,formats,subtitles', 'thumbnails')}
)),
662 query_dict('http://example.com/path?fields=id,formats,subtitles&fields=thumbnails'))
663 self
.assertEqual(query_dict(update_url_query(
664 'http://example.com/path?manifest=f4m', {'manifest': []}
)),
665 query_dict('http://example.com/path'))
666 self
.assertEqual(query_dict(update_url_query(
667 'http://example.com/path?system=LINUX&system=WINDOWS', {'system': 'LINUX'}
)),
668 query_dict('http://example.com/path?system=LINUX'))
669 self
.assertEqual(query_dict(update_url_query(
670 'http://example.com/path', {'fields': b'id,formats,subtitles'}
)),
671 query_dict('http://example.com/path?fields=id,formats,subtitles'))
672 self
.assertEqual(query_dict(update_url_query(
673 'http://example.com/path', {'width': 1080, 'height': 720}
)),
674 query_dict('http://example.com/path?width=1080&height=720'))
675 self
.assertEqual(query_dict(update_url_query(
676 'http://example.com/path', {'bitrate': 5020.43}
)),
677 query_dict('http://example.com/path?bitrate=5020.43'))
678 self
.assertEqual(query_dict(update_url_query(
679 'http://example.com/path', {'test': '第二行тест'}
)),
680 query_dict('http://example.com/path?test=%E7%AC%AC%E4%BA%8C%E8%A1%8C%D1%82%D0%B5%D1%81%D1%82'))
682 def test_multipart_encode(self
):
684 multipart_encode({b'field': b'value'}
, boundary
='AAAAAA')[0],
685 b
'--AAAAAA\r\nContent-Disposition: form-data; name="field"\r\n\r\nvalue\r\n--AAAAAA--\r\n')
687 multipart_encode({'欄位'.encode('utf-8'): '值'.encode('utf-8')}
, boundary
='AAAAAA')[0],
688 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')
690 ValueError, multipart_encode
, {b'field': b'value'}
, boundary
='value')
692 def test_dict_get(self
):
700 d
= FALSE_VALUES
.copy()
702 self
.assertEqual(dict_get(d
, 'a'), 42)
703 self
.assertEqual(dict_get(d
, 'b'), None)
704 self
.assertEqual(dict_get(d
, 'b', 42), 42)
705 self
.assertEqual(dict_get(d
, ('a', )), 42)
706 self
.assertEqual(dict_get(d
, ('b', 'a', )), 42)
707 self
.assertEqual(dict_get(d
, ('b', 'c', 'a', 'd', )), 42)
708 self
.assertEqual(dict_get(d
, ('b', 'c', )), None)
709 self
.assertEqual(dict_get(d
, ('b', 'c', ), 42), 42)
710 for key
, false_value
in FALSE_VALUES
.items():
711 self
.assertEqual(dict_get(d
, ('b', 'c', key
, )), None)
712 self
.assertEqual(dict_get(d
, ('b', 'c', key
, ), skip_false_values
=False), false_value
)
714 def test_merge_dicts(self
):
715 self
.assertEqual(merge_dicts({'a': 1}
, {'b': 2}
), {'a': 1, 'b': 2}
)
716 self
.assertEqual(merge_dicts({'a': 1}
, {'a': 2}
), {'a': 1}
)
717 self
.assertEqual(merge_dicts({'a': 1}
, {'a': None}
), {'a': 1}
)
718 self
.assertEqual(merge_dicts({'a': 1}
, {'a': ''}
), {'a': 1}
)
719 self
.assertEqual(merge_dicts({'a': 1}
, {}), {'a': 1}
)
720 self
.assertEqual(merge_dicts({'a': None}
, {'a': 1}
), {'a': 1}
)
721 self
.assertEqual(merge_dicts({'a': ''}
, {'a': 1}
), {'a': ''}
)
722 self
.assertEqual(merge_dicts({'a': ''}
, {'a': 'abc'}
), {'a': 'abc'}
)
723 self
.assertEqual(merge_dicts({'a': None}
, {'a': ''}
, {'a': 'abc'}
), {'a': 'abc'}
)
725 def test_encode_compat_str(self
):
726 self
.assertEqual(encode_compat_str(b
'\xd1\x82\xd0\xb5\xd1\x81\xd1\x82', 'utf-8'), 'тест')
727 self
.assertEqual(encode_compat_str('тест', 'utf-8'), 'тест')
729 def test_parse_iso8601(self
):
730 self
.assertEqual(parse_iso8601('2014-03-23T23:04:26+0100'), 1395612266)
731 self
.assertEqual(parse_iso8601('2014-03-23T22:04:26+0000'), 1395612266)
732 self
.assertEqual(parse_iso8601('2014-03-23T22:04:26Z'), 1395612266)
733 self
.assertEqual(parse_iso8601('2014-03-23T22:04:26.1234Z'), 1395612266)
734 self
.assertEqual(parse_iso8601('2015-09-29T08:27:31.727'), 1443515251)
735 self
.assertEqual(parse_iso8601('2015-09-29T08-27-31.727'), None)
737 def test_strip_jsonp(self
):
738 stripped
= strip_jsonp('cb ([ {"id":"532cb",\n\n\n"x":\n3}\n]\n);')
739 d
= json
.loads(stripped
)
740 self
.assertEqual(d
, [{"id": "532cb", "x": 3}
])
742 stripped
= strip_jsonp('parseMetadata({"STATUS":"OK"})\n\n\n//epc')
743 d
= json
.loads(stripped
)
744 self
.assertEqual(d
, {'STATUS': 'OK'}
)
746 stripped
= strip_jsonp('ps.embedHandler({"status": "success"});')
747 d
= json
.loads(stripped
)
748 self
.assertEqual(d
, {'status': 'success'}
)
750 stripped
= strip_jsonp('window.cb && window.cb({"status": "success"});')
751 d
= json
.loads(stripped
)
752 self
.assertEqual(d
, {'status': 'success'}
)
754 stripped
= strip_jsonp('window.cb && cb({"status": "success"});')
755 d
= json
.loads(stripped
)
756 self
.assertEqual(d
, {'status': 'success'}
)
758 stripped
= strip_jsonp('({"status": "success"});')
759 d
= json
.loads(stripped
)
760 self
.assertEqual(d
, {'status': 'success'}
)
762 def test_strip_or_none(self
):
763 self
.assertEqual(strip_or_none(' abc'), 'abc')
764 self
.assertEqual(strip_or_none('abc '), 'abc')
765 self
.assertEqual(strip_or_none(' abc '), 'abc')
766 self
.assertEqual(strip_or_none('\tabc\t'), 'abc')
767 self
.assertEqual(strip_or_none('\n\tabc\n\t'), 'abc')
768 self
.assertEqual(strip_or_none('abc'), 'abc')
769 self
.assertEqual(strip_or_none(''), '')
770 self
.assertEqual(strip_or_none(None), None)
771 self
.assertEqual(strip_or_none(42), None)
772 self
.assertEqual(strip_or_none([]), None)
774 def test_uppercase_escape(self
):
775 self
.assertEqual(uppercase_escape('aä'), 'aä')
776 self
.assertEqual(uppercase_escape('\\U0001d550'), '𝕐')
778 def test_lowercase_escape(self
):
779 self
.assertEqual(lowercase_escape('aä'), 'aä')
780 self
.assertEqual(lowercase_escape('\\u0026'), '&')
782 def test_limit_length(self
):
783 self
.assertEqual(limit_length(None, 12), None)
784 self
.assertEqual(limit_length('foo', 12), 'foo')
786 limit_length('foo bar baz asd', 12).startswith('foo bar'))
787 self
.assertTrue('...' in limit_length('foo bar baz asd', 12))
789 def test_mimetype2ext(self
):
790 self
.assertEqual(mimetype2ext(None), None)
791 self
.assertEqual(mimetype2ext('video/x-flv'), 'flv')
792 self
.assertEqual(mimetype2ext('application/x-mpegURL'), 'm3u8')
793 self
.assertEqual(mimetype2ext('text/vtt'), 'vtt')
794 self
.assertEqual(mimetype2ext('text/vtt;charset=utf-8'), 'vtt')
795 self
.assertEqual(mimetype2ext('text/html; charset=utf-8'), 'html')
797 def test_month_by_name(self
):
798 self
.assertEqual(month_by_name(None), None)
799 self
.assertEqual(month_by_name('December', 'en'), 12)
800 self
.assertEqual(month_by_name('décembre', 'fr'), 12)
801 self
.assertEqual(month_by_name('December'), 12)
802 self
.assertEqual(month_by_name('décembre'), None)
803 self
.assertEqual(month_by_name('Unknown', 'unknown'), None)
805 def test_parse_codecs(self
):
806 self
.assertEqual(parse_codecs(''), {})
807 self
.assertEqual(parse_codecs('avc1.77.30, mp4a.40.2'), {
808 'vcodec': 'avc1.77.30',
809 'acodec': 'mp4a.40.2',
811 self
.assertEqual(parse_codecs('mp4a.40.2'), {
813 'acodec': 'mp4a.40.2',
815 self
.assertEqual(parse_codecs('mp4a.40.5,avc1.42001e'), {
816 'vcodec': 'avc1.42001e',
817 'acodec': 'mp4a.40.5',
819 self
.assertEqual(parse_codecs('avc3.640028'), {
820 'vcodec': 'avc3.640028',
823 self
.assertEqual(parse_codecs(', h264,,newcodec,aac'), {
827 self
.assertEqual(parse_codecs('av01.0.05M.08'), {
828 'vcodec': 'av01.0.05M.08',
831 self
.assertEqual(parse_codecs('theora, vorbis'), {
835 self
.assertEqual(parse_codecs('unknownvcodec, unknownacodec'), {
836 'vcodec': 'unknownvcodec',
837 'acodec': 'unknownacodec',
839 self
.assertEqual(parse_codecs('unknown'), {})
841 def test_escape_rfc3986(self
):
842 reserved
= "!*'();:@&=+$,/?#[]"
843 unreserved
= 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_.~'
844 self
.assertEqual(escape_rfc3986(reserved
), reserved
)
845 self
.assertEqual(escape_rfc3986(unreserved
), unreserved
)
846 self
.assertEqual(escape_rfc3986('тест'), '%D1%82%D0%B5%D1%81%D1%82')
847 self
.assertEqual(escape_rfc3986('%D1%82%D0%B5%D1%81%D1%82'), '%D1%82%D0%B5%D1%81%D1%82')
848 self
.assertEqual(escape_rfc3986('foo bar'), 'foo%20bar')
849 self
.assertEqual(escape_rfc3986('foo%20bar'), 'foo%20bar')
851 def test_escape_url(self
):
853 escape_url('http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavré_FD.mp4'),
854 'http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavre%CC%81_FD.mp4'
857 escape_url('http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erklärt/Das-Erste/Video?documentId=22673108&bcastId=5290'),
858 'http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erkl%C3%A4rt/Das-Erste/Video?documentId=22673108&bcastId=5290'
861 escape_url('http://тест.рф/фрагмент'),
862 'http://xn--e1aybc.xn--p1ai/%D1%84%D1%80%D0%B0%D0%B3%D0%BC%D0%B5%D0%BD%D1%82'
865 escape_url('http://тест.рф/абв?абв=абв#абв'),
866 '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'
868 self
.assertEqual(escape_url('http://vimeo.com/56015672#at=0'), 'http://vimeo.com/56015672#at=0')
870 def test_js_to_json_realworld(self
):
872 'clip':{'provider':'pseudo'}
874 self
.assertEqual(js_to_json(inp
), '''{
875 "clip":{"provider":"pseudo"}
877 json
.loads(js_to_json(inp
))
880 'playlist':[{'controls':{'all':null}}]
882 self
.assertEqual(js_to_json(inp
), '''{
883 "playlist":[{"controls":{"all":null}}]
886 inp
= '''"The CW\\'s \\'Crazy Ex-Girlfriend\\'"'''
887 self
.assertEqual(js_to_json(inp
), '''"The CW's 'Crazy Ex-Girlfriend'"''')
889 inp
= '"SAND Number: SAND 2013-7800P\\nPresenter: Tom Russo\\nHabanero Software Training - Xyce Software\\nXyce, Sandia\\u0027s"'
890 json_code
= js_to_json(inp
)
891 self
.assertEqual(json
.loads(json_code
), json
.loads(inp
))
894 0:{src:'skipped', type: 'application/dash+xml'},
895 1:{src:'skipped', type: 'application/vnd.apple.mpegURL'},
897 self
.assertEqual(js_to_json(inp
), '''{
898 "0":{"src":"skipped", "type": "application/dash+xml"},
899 "1":{"src":"skipped", "type": "application/vnd.apple.mpegURL"}
902 inp
= '''{"foo":101}'''
903 self
.assertEqual(js_to_json(inp
), '''{"foo":101}''')
905 inp
= '''{"duration": "00:01:07"}'''
906 self
.assertEqual(js_to_json(inp
), '''{"duration": "00:01:07"}''')
908 inp
= '''{segments: [{"offset":-3.885780586188048e-16,"duration":39.75000000000001}]}'''
909 self
.assertEqual(js_to_json(inp
), '''{"segments": [{"offset":-3.885780586188048e-16,"duration":39.75000000000001}]}''')
911 def test_js_to_json_edgecases(self
):
912 on
= js_to_json("{abc_def:'1\\'\\\\2\\\\\\'3\"4'}")
913 self
.assertEqual(json
.loads(on
), {"abc_def": "1'\\2\\'3\"4"}
)
915 on
= js_to_json('{"abc": true}')
916 self
.assertEqual(json
.loads(on
), {'abc': True}
)
918 # Ignore JavaScript code as well
925 self
.assertEqual(d
['x'], 1)
926 self
.assertEqual(d
['y'], 'a')
928 on
= js_to_json('["abc", "def",]')
929 self
.assertEqual(json
.loads(on
), ['abc', 'def'])
931 on
= js_to_json('[/*comment\n*/"abc"/*comment\n*/,/*comment\n*/"def",/*comment\n*/]')
932 self
.assertEqual(json
.loads(on
), ['abc', 'def'])
934 on
= js_to_json('[//comment\n"abc" //comment\n,//comment\n"def",//comment\n]')
935 self
.assertEqual(json
.loads(on
), ['abc', 'def'])
937 on
= js_to_json('{"abc": "def",}')
938 self
.assertEqual(json
.loads(on
), {'abc': 'def'}
)
940 on
= js_to_json('{/*comment\n*/"abc"/*comment\n*/:/*comment\n*/"def"/*comment\n*/,/*comment\n*/}')
941 self
.assertEqual(json
.loads(on
), {'abc': 'def'}
)
943 on
= js_to_json('{ 0: /* " \n */ ",]" , }')
944 self
.assertEqual(json
.loads(on
), {'0': ',]'}
)
946 on
= js_to_json('{ /*comment\n*/0/*comment\n*/: /* " \n */ ",]" , }')
947 self
.assertEqual(json
.loads(on
), {'0': ',]'}
)
949 on
= js_to_json('{ 0: // comment\n1 }')
950 self
.assertEqual(json
.loads(on
), {'0': 1}
)
952 on
= js_to_json(r
'["<p>x<\/p>"]')
953 self
.assertEqual(json
.loads(on
), ['<p>x</p>'])
955 on
= js_to_json(r
'["\xaa"]')
956 self
.assertEqual(json
.loads(on
), ['\u00aa'])
958 on
= js_to_json("['a\\\nb']")
959 self
.assertEqual(json
.loads(on
), ['ab'])
961 on
= js_to_json("/*comment\n*/[/*comment\n*/'a\\\nb'/*comment\n*/]/*comment\n*/")
962 self
.assertEqual(json
.loads(on
), ['ab'])
964 on
= js_to_json('{0xff:0xff}')
965 self
.assertEqual(json
.loads(on
), {'255': 255}
)
967 on
= js_to_json('{/*comment\n*/0xff/*comment\n*/:/*comment\n*/0xff/*comment\n*/}')
968 self
.assertEqual(json
.loads(on
), {'255': 255}
)
970 on
= js_to_json('{077:077}')
971 self
.assertEqual(json
.loads(on
), {'63': 63}
)
973 on
= js_to_json('{/*comment\n*/077/*comment\n*/:/*comment\n*/077/*comment\n*/}')
974 self
.assertEqual(json
.loads(on
), {'63': 63}
)
976 on
= js_to_json('{42:42}')
977 self
.assertEqual(json
.loads(on
), {'42': 42}
)
979 on
= js_to_json('{/*comment\n*/42/*comment\n*/:/*comment\n*/42/*comment\n*/}')
980 self
.assertEqual(json
.loads(on
), {'42': 42}
)
982 on
= js_to_json('{42:4.2e1}')
983 self
.assertEqual(json
.loads(on
), {'42': 42.0}
)
985 def test_js_to_json_malformed(self
):
986 self
.assertEqual(js_to_json('42a1'), '42"a1"')
987 self
.assertEqual(js_to_json('42a-1'), '42"a"-1')
989 def test_extract_attributes(self
):
990 self
.assertEqual(extract_attributes('<e x="y">'), {'x': 'y'}
)
991 self
.assertEqual(extract_attributes("<e x='y'>"), {'x': 'y'}
)
992 self
.assertEqual(extract_attributes('<e x=y>'), {'x': 'y'}
)
993 self
.assertEqual(extract_attributes('<e x="a \'b\' c">'), {'x': "a 'b' c"}
)
994 self
.assertEqual(extract_attributes('<e x=\'a "b" c\'>'), {'x': 'a "b" c'}
)
995 self
.assertEqual(extract_attributes('<e x="y">'), {'x': 'y'}
)
996 self
.assertEqual(extract_attributes('<e x="y">'), {'x': 'y'}
)
997 self
.assertEqual(extract_attributes('<e x="&">'), {'x': '&'}
) # XML
998 self
.assertEqual(extract_attributes('<e x=""">'), {'x': '"'}
)
999 self
.assertEqual(extract_attributes('<e x="£">'), {'x': '£'}
) # HTML 3.2
1000 self
.assertEqual(extract_attributes('<e x="λ">'), {'x': 'λ'}
) # HTML 4.0
1001 self
.assertEqual(extract_attributes('<e x="&foo">'), {'x': '&foo'}
)
1002 self
.assertEqual(extract_attributes('<e x="\'">'), {'x': "'"}
)
1003 self
.assertEqual(extract_attributes('<e x=\'"\'>'), {'x': '"'}
)
1004 self
.assertEqual(extract_attributes('<e x >'), {'x': None}
)
1005 self
.assertEqual(extract_attributes('<e x=y a>'), {'x': 'y', 'a': None}
)
1006 self
.assertEqual(extract_attributes('<e x= y>'), {'x': 'y'}
)
1007 self
.assertEqual(extract_attributes('<e x=1 y=2 x=3>'), {'y': '2', 'x': '3'}
)
1008 self
.assertEqual(extract_attributes('<e \nx=\ny\n>'), {'x': 'y'}
)
1009 self
.assertEqual(extract_attributes('<e \nx=\n"y"\n>'), {'x': 'y'}
)
1010 self
.assertEqual(extract_attributes("<e \nx=\n'y'\n>"), {'x': 'y'}
)
1011 self
.assertEqual(extract_attributes('<e \nx="\ny\n">'), {'x': '\ny\n'}
)
1012 self
.assertEqual(extract_attributes('<e CAPS=x>'), {'caps': 'x'}
) # Names lowercased
1013 self
.assertEqual(extract_attributes('<e x=1 X=2>'), {'x': '2'}
)
1014 self
.assertEqual(extract_attributes('<e X=1 x=2>'), {'x': '2'}
)
1015 self
.assertEqual(extract_attributes('<e _:funny-name1=1>'), {'_:funny-name1': '1'}
)
1016 self
.assertEqual(extract_attributes('<e x="Fáilte 世界 \U0001f600">'), {'x': 'Fáilte 世界 \U0001f600'}
)
1017 self
.assertEqual(extract_attributes('<e x="décomposé">'), {'x': 'décompose\u0301'}
)
1018 # "Narrow" Python builds don't support unicode code points outside BMP.
1021 supports_outside_bmp
= True
1023 supports_outside_bmp
= False
1024 if supports_outside_bmp
:
1025 self
.assertEqual(extract_attributes('<e x="Smile 😀!">'), {'x': 'Smile \U0001f600!'}
)
1026 # Malformed HTML should not break attributes extraction on older Python
1027 self
.assertEqual(extract_attributes('<mal"formed/>'), {})
1029 def test_clean_html(self
):
1030 self
.assertEqual(clean_html('a:\nb'), 'a: b')
1031 self
.assertEqual(clean_html('a:\n "b"'), 'a: "b"')
1032 self
.assertEqual(clean_html('a<br>\xa0b'), 'a\nb')
1034 def test_intlist_to_bytes(self
):
1036 intlist_to_bytes([0, 1, 127, 128, 255]),
1037 b
'\x00\x01\x7f\x80\xff')
1039 def test_args_to_str(self
):
1041 args_to_str(['foo', 'ba/r', '-baz', '2 be', '']),
1042 'foo ba/r -baz \'2 be\' \'\'' if compat_os_name
!= 'nt' else 'foo ba/r -baz "2 be" ""'
1045 def test_parse_filesize(self
):
1046 self
.assertEqual(parse_filesize(None), None)
1047 self
.assertEqual(parse_filesize(''), None)
1048 self
.assertEqual(parse_filesize('91 B'), 91)
1049 self
.assertEqual(parse_filesize('foobar'), None)
1050 self
.assertEqual(parse_filesize('2 MiB'), 2097152)
1051 self
.assertEqual(parse_filesize('5 GB'), 5000000000)
1052 self
.assertEqual(parse_filesize('1.2Tb'), 1200000000000)
1053 self
.assertEqual(parse_filesize('1.2tb'), 1200000000000)
1054 self
.assertEqual(parse_filesize('1,24 KB'), 1240)
1055 self
.assertEqual(parse_filesize('1,24 kb'), 1240)
1056 self
.assertEqual(parse_filesize('8.5 megabytes'), 8500000)
1058 def test_parse_count(self
):
1059 self
.assertEqual(parse_count(None), None)
1060 self
.assertEqual(parse_count(''), None)
1061 self
.assertEqual(parse_count('0'), 0)
1062 self
.assertEqual(parse_count('1000'), 1000)
1063 self
.assertEqual(parse_count('1.000'), 1000)
1064 self
.assertEqual(parse_count('1.1k'), 1100)
1065 self
.assertEqual(parse_count('1.1kk'), 1100000)
1066 self
.assertEqual(parse_count('1.1kk '), 1100000)
1067 self
.assertEqual(parse_count('1.1kk views'), 1100000)
1069 def test_parse_resolution(self
):
1070 self
.assertEqual(parse_resolution(None), {})
1071 self
.assertEqual(parse_resolution(''), {})
1072 self
.assertEqual(parse_resolution('1920x1080'), {'width': 1920, 'height': 1080}
)
1073 self
.assertEqual(parse_resolution('1920×1080'), {'width': 1920, 'height': 1080}
)
1074 self
.assertEqual(parse_resolution('1920 x 1080'), {'width': 1920, 'height': 1080}
)
1075 self
.assertEqual(parse_resolution('720p'), {'height': 720}
)
1076 self
.assertEqual(parse_resolution('4k'), {'height': 2160}
)
1077 self
.assertEqual(parse_resolution('8K'), {'height': 4320}
)
1079 def test_parse_bitrate(self
):
1080 self
.assertEqual(parse_bitrate(None), None)
1081 self
.assertEqual(parse_bitrate(''), None)
1082 self
.assertEqual(parse_bitrate('300kbps'), 300)
1083 self
.assertEqual(parse_bitrate('1500kbps'), 1500)
1084 self
.assertEqual(parse_bitrate('300 kbps'), 300)
1086 def test_version_tuple(self
):
1087 self
.assertEqual(version_tuple('1'), (1,))
1088 self
.assertEqual(version_tuple('10.23.344'), (10, 23, 344))
1089 self
.assertEqual(version_tuple('10.1-6'), (10, 1, 6)) # avconv style
1091 def test_detect_exe_version(self
):
1092 self
.assertEqual(detect_exe_version('''ffmpeg version 1.2.1
1093 built on May 27 2013 08:37:26 with gcc 4.7 (Debian 4.7.3-4)
1094 configuration: --prefix=/usr --extra-'''), '1.2.1')
1095 self
.assertEqual(detect_exe_version('''ffmpeg version N-63176-g1fb4685
1096 built on May 15 2014 22:09:06 with gcc 4.8.2 (GCC)'''), 'N-63176-g1fb4685')
1097 self
.assertEqual(detect_exe_version('''X server found. dri2 connection failed!
1098 Trying to open render node...
1099 Success at /dev/dri/renderD128.
1100 ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')
1102 def test_age_restricted(self
):
1103 self
.assertFalse(age_restricted(None, 10)) # unrestricted content
1104 self
.assertFalse(age_restricted(1, None)) # unrestricted policy
1105 self
.assertFalse(age_restricted(8, 10))
1106 self
.assertTrue(age_restricted(18, 14))
1107 self
.assertFalse(age_restricted(18, 18))
1109 def test_is_html(self
):
1110 self
.assertFalse(is_html(b
'\x49\x44\x43<html'))
1111 self
.assertTrue(is_html(b
'<!DOCTYPE foo>\xaaa'))
1112 self
.assertTrue(is_html( # UTF-8 with BOM
1113 b
'\xef\xbb\xbf<!DOCTYPE foo>\xaaa'))
1114 self
.assertTrue(is_html( # UTF-16-LE
1115 b
'\xff\xfe<\x00h\x00t\x00m\x00l\x00>\x00\xe4\x00'
1117 self
.assertTrue(is_html( # UTF-16-BE
1118 b
'\xfe\xff\x00<\x00h\x00t\x00m\x00l\x00>\x00\xe4'
1120 self
.assertTrue(is_html( # UTF-32-BE
1121 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'))
1122 self
.assertTrue(is_html( # UTF-32-LE
1123 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'))
1125 def test_render_table(self
):
1129 [[123, 4], [9999, 51]]),
1134 def test_match_str(self
):
1135 self
.assertRaises(ValueError, match_str
, 'xy>foobar', {})
1136 self
.assertFalse(match_str('xy', {'x': 1200}
))
1137 self
.assertTrue(match_str('!xy', {'x': 1200}
))
1138 self
.assertTrue(match_str('x', {'x': 1200}
))
1139 self
.assertFalse(match_str('!x', {'x': 1200}
))
1140 self
.assertTrue(match_str('x', {'x': 0}
))
1141 self
.assertFalse(match_str('x>0', {'x': 0}
))
1142 self
.assertFalse(match_str('x>0', {}))
1143 self
.assertTrue(match_str('x>?0', {}))
1144 self
.assertTrue(match_str('x>1K', {'x': 1200}
))
1145 self
.assertFalse(match_str('x>2K', {'x': 1200}
))
1146 self
.assertTrue(match_str('x>=1200 & x < 1300', {'x': 1200}
))
1147 self
.assertFalse(match_str('x>=1100 & x < 1200', {'x': 1200}
))
1148 self
.assertFalse(match_str('y=a212', {'y': 'foobar42'}
))
1149 self
.assertTrue(match_str('y=foobar42', {'y': 'foobar42'}
))
1150 self
.assertFalse(match_str('y!=foobar42', {'y': 'foobar42'}
))
1151 self
.assertTrue(match_str('y!=foobar2', {'y': 'foobar42'}
))
1152 self
.assertFalse(match_str(
1153 'like_count > 100 & dislike_count <? 50 & description',
1154 {'like_count': 90, 'description': 'foo'}
))
1155 self
.assertTrue(match_str(
1156 'like_count > 100 & dislike_count <? 50 & description',
1157 {'like_count': 190, 'description': 'foo'}
))
1158 self
.assertFalse(match_str(
1159 'like_count > 100 & dislike_count <? 50 & description',
1160 {'like_count': 190, 'dislike_count': 60, 'description': 'foo'}
))
1161 self
.assertFalse(match_str(
1162 'like_count > 100 & dislike_count <? 50 & description',
1163 {'like_count': 190, 'dislike_count': 10}
))
1164 self
.assertTrue(match_str('is_live', {'is_live': True}
))
1165 self
.assertFalse(match_str('is_live', {'is_live': False}
))
1166 self
.assertFalse(match_str('is_live', {'is_live': None}
))
1167 self
.assertFalse(match_str('is_live', {}))
1168 self
.assertFalse(match_str('!is_live', {'is_live': True}
))
1169 self
.assertTrue(match_str('!is_live', {'is_live': False}
))
1170 self
.assertTrue(match_str('!is_live', {'is_live': None}
))
1171 self
.assertTrue(match_str('!is_live', {}))
1172 self
.assertTrue(match_str('title', {'title': 'abc'}
))
1173 self
.assertTrue(match_str('title', {'title': ''}
))
1174 self
.assertFalse(match_str('!title', {'title': 'abc'}
))
1175 self
.assertFalse(match_str('!title', {'title': ''}
))
1177 def test_parse_dfxp_time_expr(self
):
1178 self
.assertEqual(parse_dfxp_time_expr(None), None)
1179 self
.assertEqual(parse_dfxp_time_expr(''), None)
1180 self
.assertEqual(parse_dfxp_time_expr('0.1'), 0.1)
1181 self
.assertEqual(parse_dfxp_time_expr('0.1s'), 0.1)
1182 self
.assertEqual(parse_dfxp_time_expr('00:00:01'), 1.0)
1183 self
.assertEqual(parse_dfxp_time_expr('00:00:01.100'), 1.1)
1184 self
.assertEqual(parse_dfxp_time_expr('00:00:01:100'), 1.1)
1186 def test_dfxp2srt(self
):
1187 dfxp_data
= '''<?xml version="1.0" encoding="UTF-8"?>
1188 <tt xmlns="http://www.w3.org/ns/ttml" xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter">
1191 <p begin="0" end="1">The following line contains Chinese characters and special symbols</p>
1192 <p begin="1" end="2">第二行<br/>♪♪</p>
1193 <p begin="2" dur="1"><span>Third<br/>Line</span></p>
1194 <p begin="3" end="-1">Lines with invalid timestamps are ignored</p>
1195 <p begin="-1" end="-1">Ignore, two</p>
1196 <p begin="3" dur="-1">Ignored, three</p>
1199 </tt>'''.encode('utf-8')
1201 00:00:00,000 --> 00:00:01,000
1202 The following line contains Chinese characters and special symbols
1205 00:00:01,000 --> 00:00:02,000
1210 00:00:02,000 --> 00:00:03,000
1215 self
.assertEqual(dfxp2srt(dfxp_data
), srt_data
)
1217 dfxp_data_no_default_namespace
= '''<?xml version="1.0" encoding="UTF-8"?>
1218 <tt xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter">
1221 <p begin="0" end="1">The first line</p>
1224 </tt>'''.encode('utf-8')
1226 00:00:00,000 --> 00:00:01,000
1230 self
.assertEqual(dfxp2srt(dfxp_data_no_default_namespace
), srt_data
)
1232 dfxp_data_with_style
= '''<?xml version="1.0" encoding="utf-8"?>
1233 <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">
1236 <style id="s2" style="s0" tts:color="cyan" tts:fontWeight="bold" />
1237 <style id="s1" style="s0" tts:color="yellow" tts:fontStyle="italic" />
1238 <style id="s3" style="s0" tts:color="lime" tts:textDecoration="underline" />
1239 <style id="s0" tts:backgroundColor="black" tts:fontStyle="normal" tts:fontSize="16" tts:fontFamily="sansSerif" tts:color="white" />
1242 <body tts:textAlign="center" style="s0">
1244 <p begin="00:00:02.08" id="p0" end="00:00:05.84">default style<span tts:color="red">custom style</span></p>
1245 <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>
1246 <p style="s3" begin="00:00:05.84" id="p1" end="00:00:09.56">line 3<br />part 3</p>
1247 <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>
1250 </tt>'''.encode('utf-8')
1252 00:00:02,080 --> 00:00:05,839
1253 <font color="white" face="sansSerif" size="16">default style<font color="red">custom style</font></font>
1256 00:00:02,080 --> 00:00:05,839
1257 <b><font color="cyan" face="sansSerif" size="16"><font color="lime">part 1
1258 </font>part 2</font></b>
1261 00:00:05,839 --> 00:00:09,560
1262 <u><font color="lime">line 3
1266 00:00:09,560 --> 00:00:12,359
1267 <i><u><font color="yellow"><font color="lime">inner
1268 </font>style</font></u></i>
1271 self
.assertEqual(dfxp2srt(dfxp_data_with_style
), srt_data
)
1273 dfxp_data_non_utf8
= '''<?xml version="1.0" encoding="UTF-16"?>
1274 <tt xmlns="http://www.w3.org/ns/ttml" xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter">
1277 <p begin="0" end="1">Line 1</p>
1278 <p begin="1" end="2">第二行</p>
1281 </tt>'''.encode('utf-16')
1283 00:00:00,000 --> 00:00:01,000
1287 00:00:01,000 --> 00:00:02,000
1291 self
.assertEqual(dfxp2srt(dfxp_data_non_utf8
), srt_data
)
1293 def test_cli_option(self
):
1294 self
.assertEqual(cli_option({'proxy': '127.0.0.1:3128'}
, '--proxy', 'proxy'), ['--proxy', '127.0.0.1:3128'])
1295 self
.assertEqual(cli_option({'proxy': None}
, '--proxy', 'proxy'), [])
1296 self
.assertEqual(cli_option({}, '--proxy', 'proxy'), [])
1297 self
.assertEqual(cli_option({'retries': 10}
, '--retries', 'retries'), ['--retries', '10'])
1299 def test_cli_valueless_option(self
):
1300 self
.assertEqual(cli_valueless_option(
1301 {'downloader': 'external'}
, '--external-downloader', 'downloader', 'external'), ['--external-downloader'])
1302 self
.assertEqual(cli_valueless_option(
1303 {'downloader': 'internal'}
, '--external-downloader', 'downloader', 'external'), [])
1304 self
.assertEqual(cli_valueless_option(
1305 {'nocheckcertificate': True}
, '--no-check-certificate', 'nocheckcertificate'), ['--no-check-certificate'])
1306 self
.assertEqual(cli_valueless_option(
1307 {'nocheckcertificate': False}
, '--no-check-certificate', 'nocheckcertificate'), [])
1308 self
.assertEqual(cli_valueless_option(
1309 {'checkcertificate': True}
, '--no-check-certificate', 'checkcertificate', False), [])
1310 self
.assertEqual(cli_valueless_option(
1311 {'checkcertificate': False}
, '--no-check-certificate', 'checkcertificate', False), ['--no-check-certificate'])
1313 def test_cli_bool_option(self
):
1316 {'nocheckcertificate': True}
, '--no-check-certificate', 'nocheckcertificate'),
1317 ['--no-check-certificate', 'true'])
1320 {'nocheckcertificate': True}
, '--no-check-certificate', 'nocheckcertificate', separator
='='),
1321 ['--no-check-certificate=true'])
1324 {'nocheckcertificate': True}
, '--check-certificate', 'nocheckcertificate', 'false', 'true'),
1325 ['--check-certificate', 'false'])
1328 {'nocheckcertificate': True}
, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='),
1329 ['--check-certificate=false'])
1332 {'nocheckcertificate': False}
, '--check-certificate', 'nocheckcertificate', 'false', 'true'),
1333 ['--check-certificate', 'true'])
1336 {'nocheckcertificate': False}
, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='),
1337 ['--check-certificate=true'])
1340 {}, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='),
1343 def test_ohdave_rsa_encrypt(self
):
1344 N
= 0xab86b6371b5318aaa1d3c9e612a9f1264f372323c8c0f19875b5fc3b3fd3afcc1e5bec527aa94bfa85bffc157e4245aebda05389a5357b75115ac94f074aefcd
1348 ohdave_rsa_encrypt(b
'aa111222', e
, N
),
1349 '726664bd9a23fd0c70f9f1b84aab5e3905ce1e45a584e9cbcf9bcc7510338fc1986d6c599ff990d923aa43c51c0d9013cd572e13bc58f4ae48f2ed8c0b0ba881')
1351 def test_pkcs1pad(self
):
1353 padded_data
= pkcs1pad(data
, 32)
1354 self
.assertEqual(padded_data
[:2], [0, 2])
1355 self
.assertEqual(padded_data
[28:], [0, 1, 2, 3])
1357 self
.assertRaises(ValueError, pkcs1pad
, data
, 8)
1359 def test_encode_base_n(self
):
1360 self
.assertEqual(encode_base_n(0, 30), '0')
1361 self
.assertEqual(encode_base_n(80, 30), '2k')
1363 custom_table
= '9876543210ZYXWVUTSRQPONMLKJIHGFEDCBA'
1364 self
.assertEqual(encode_base_n(0, 30, custom_table
), '9')
1365 self
.assertEqual(encode_base_n(80, 30, custom_table
), '7P')
1367 self
.assertRaises(ValueError, encode_base_n
, 0, 70)
1368 self
.assertRaises(ValueError, encode_base_n
, 0, 60, custom_table
)
1370 def test_urshift(self
):
1371 self
.assertEqual(urshift(3, 1), 1)
1372 self
.assertEqual(urshift(-3, 1), 2147483646)
1374 def test_get_element_by_class(self
):
1376 <span class="foo bar">nice</span>
1379 self
.assertEqual(get_element_by_class('foo', html
), 'nice')
1380 self
.assertEqual(get_element_by_class('no-such-class', html
), None)
1382 def test_get_element_by_attribute(self
):
1384 <span class="foo bar">nice</span>
1387 self
.assertEqual(get_element_by_attribute('class', 'foo bar', html
), 'nice')
1388 self
.assertEqual(get_element_by_attribute('class', 'foo', html
), None)
1389 self
.assertEqual(get_element_by_attribute('class', 'no-such-foo', html
), None)
1392 <div itemprop="author" itemscope>foo</div>
1395 self
.assertEqual(get_element_by_attribute('itemprop', 'author', html
), 'foo')
1397 def test_get_elements_by_class(self
):
1399 <span class="foo bar">nice</span><span class="foo bar">also nice</span>
1402 self
.assertEqual(get_elements_by_class('foo', html
), ['nice', 'also nice'])
1403 self
.assertEqual(get_elements_by_class('no-such-class', html
), [])
1405 def test_get_elements_by_attribute(self
):
1407 <span class="foo bar">nice</span><span class="foo bar">also nice</span>
1410 self
.assertEqual(get_elements_by_attribute('class', 'foo bar', html
), ['nice', 'also nice'])
1411 self
.assertEqual(get_elements_by_attribute('class', 'foo', html
), [])
1412 self
.assertEqual(get_elements_by_attribute('class', 'no-such-foo', html
), [])
1415 if __name__
== '__main__':