]> Raphaël G. Git Repositories - youtubedl/blob - test/test_utils.py
a1fe6fdb2cad56151ff1b21f210112269740cff1
[youtubedl] / test / test_utils.py
1 #!/usr/bin/env python
2 # coding: utf-8
3
4 from __future__ import unicode_literals
5
6 # Allow direct execution
7 import os
8 import sys
9 import unittest
10 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
11
12
13 # Various small unit tests
14 import io
15 import json
16 import xml.etree.ElementTree
17
18 from youtube_dl.utils import (
19 age_restricted,
20 args_to_str,
21 encode_base_n,
22 clean_html,
23 date_from_str,
24 DateRange,
25 detect_exe_version,
26 determine_ext,
27 dict_get,
28 encode_compat_str,
29 encodeFilename,
30 escape_rfc3986,
31 escape_url,
32 extract_attributes,
33 ExtractorError,
34 find_xpath_attr,
35 fix_xml_ampersands,
36 get_element_by_class,
37 get_element_by_attribute,
38 get_elements_by_class,
39 get_elements_by_attribute,
40 InAdvancePagedList,
41 intlist_to_bytes,
42 is_html,
43 js_to_json,
44 limit_length,
45 mimetype2ext,
46 month_by_name,
47 multipart_encode,
48 ohdave_rsa_encrypt,
49 OnDemandPagedList,
50 orderedSet,
51 parse_age_limit,
52 parse_duration,
53 parse_filesize,
54 parse_count,
55 parse_iso8601,
56 parse_resolution,
57 pkcs1pad,
58 read_batch_urls,
59 sanitize_filename,
60 sanitize_path,
61 sanitize_url,
62 expand_path,
63 prepend_extension,
64 replace_extension,
65 remove_start,
66 remove_end,
67 remove_quotes,
68 shell_quote,
69 smuggle_url,
70 str_to_int,
71 strip_jsonp,
72 timeconvert,
73 unescapeHTML,
74 unified_strdate,
75 unified_timestamp,
76 unsmuggle_url,
77 uppercase_escape,
78 lowercase_escape,
79 url_basename,
80 base_url,
81 urljoin,
82 urlencode_postdata,
83 urshift,
84 update_url_query,
85 version_tuple,
86 xpath_with_ns,
87 xpath_element,
88 xpath_text,
89 xpath_attr,
90 render_table,
91 match_str,
92 parse_dfxp_time_expr,
93 dfxp2srt,
94 cli_option,
95 cli_valueless_option,
96 cli_bool_option,
97 parse_codecs,
98 )
99 from youtube_dl.compat import (
100 compat_chr,
101 compat_etree_fromstring,
102 compat_getenv,
103 compat_os_name,
104 compat_setenv,
105 compat_urlparse,
106 compat_parse_qs,
107 )
108
109
110 class TestUtil(unittest.TestCase):
111 def test_timeconvert(self):
112 self.assertTrue(timeconvert('') is None)
113 self.assertTrue(timeconvert('bougrg') is None)
114
115 def test_sanitize_filename(self):
116 self.assertEqual(sanitize_filename('abc'), 'abc')
117 self.assertEqual(sanitize_filename('abc_d-e'), 'abc_d-e')
118
119 self.assertEqual(sanitize_filename('123'), '123')
120
121 self.assertEqual('abc_de', sanitize_filename('abc/de'))
122 self.assertFalse('/' in sanitize_filename('abc/de///'))
123
124 self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de'))
125 self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|'))
126 self.assertEqual('yes no', sanitize_filename('yes? no'))
127 self.assertEqual('this - that', sanitize_filename('this: that'))
128
129 self.assertEqual(sanitize_filename('AT&T'), 'AT&T')
130 aumlaut = 'ä'
131 self.assertEqual(sanitize_filename(aumlaut), aumlaut)
132 tests = '\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430'
133 self.assertEqual(sanitize_filename(tests), tests)
134
135 self.assertEqual(
136 sanitize_filename('New World record at 0:12:34'),
137 'New World record at 0_12_34')
138
139 self.assertEqual(sanitize_filename('--gasdgf'), '_-gasdgf')
140 self.assertEqual(sanitize_filename('--gasdgf', is_id=True), '--gasdgf')
141 self.assertEqual(sanitize_filename('.gasdgf'), 'gasdgf')
142 self.assertEqual(sanitize_filename('.gasdgf', is_id=True), '.gasdgf')
143
144 forbidden = '"\0\\/'
145 for fc in forbidden:
146 for fbc in forbidden:
147 self.assertTrue(fbc not in sanitize_filename(fc))
148
149 def test_sanitize_filename_restricted(self):
150 self.assertEqual(sanitize_filename('abc', restricted=True), 'abc')
151 self.assertEqual(sanitize_filename('abc_d-e', restricted=True), 'abc_d-e')
152
153 self.assertEqual(sanitize_filename('123', restricted=True), '123')
154
155 self.assertEqual('abc_de', sanitize_filename('abc/de', restricted=True))
156 self.assertFalse('/' in sanitize_filename('abc/de///', restricted=True))
157
158 self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de', restricted=True))
159 self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|', restricted=True))
160 self.assertEqual('yes_no', sanitize_filename('yes? no', restricted=True))
161 self.assertEqual('this_-_that', sanitize_filename('this: that', restricted=True))
162
163 tests = 'aäb\u4e2d\u56fd\u7684c'
164 self.assertEqual(sanitize_filename(tests, restricted=True), 'aab_c')
165 self.assertTrue(sanitize_filename('\xf6', restricted=True) != '') # No empty filename
166
167 forbidden = '"\0\\/&!: \'\t\n()[]{}$;`^,#'
168 for fc in forbidden:
169 for fbc in forbidden:
170 self.assertTrue(fbc not in sanitize_filename(fc, restricted=True))
171
172 # Handle a common case more neatly
173 self.assertEqual(sanitize_filename('\u5927\u58f0\u5e26 - Song', restricted=True), 'Song')
174 self.assertEqual(sanitize_filename('\u603b\u7edf: Speech', restricted=True), 'Speech')
175 # .. but make sure the file name is never empty
176 self.assertTrue(sanitize_filename('-', restricted=True) != '')
177 self.assertTrue(sanitize_filename(':', restricted=True) != '')
178
179 self.assertEqual(sanitize_filename(
180 'ÂÃÄÀÁÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖŐØŒÙÚÛÜŰÝÞßàáâãäåæçèéêëìíîïðñòóôõöőøœùúûüűýþÿ', restricted=True),
181 'AAAAAAAECEEEEIIIIDNOOOOOOOOEUUUUUYPssaaaaaaaeceeeeiiiionooooooooeuuuuuypy')
182
183 def test_sanitize_ids(self):
184 self.assertEqual(sanitize_filename('_n_cd26wFpw', is_id=True), '_n_cd26wFpw')
185 self.assertEqual(sanitize_filename('_BD_eEpuzXw', is_id=True), '_BD_eEpuzXw')
186 self.assertEqual(sanitize_filename('N0Y__7-UOdI', is_id=True), 'N0Y__7-UOdI')
187
188 def test_sanitize_path(self):
189 if sys.platform != 'win32':
190 return
191
192 self.assertEqual(sanitize_path('abc'), 'abc')
193 self.assertEqual(sanitize_path('abc/def'), 'abc\\def')
194 self.assertEqual(sanitize_path('abc\\def'), 'abc\\def')
195 self.assertEqual(sanitize_path('abc|def'), 'abc#def')
196 self.assertEqual(sanitize_path('<>:"|?*'), '#######')
197 self.assertEqual(sanitize_path('C:/abc/def'), 'C:\\abc\\def')
198 self.assertEqual(sanitize_path('C?:/abc/def'), 'C##\\abc\\def')
199
200 self.assertEqual(sanitize_path('\\\\?\\UNC\\ComputerName\\abc'), '\\\\?\\UNC\\ComputerName\\abc')
201 self.assertEqual(sanitize_path('\\\\?\\UNC/ComputerName/abc'), '\\\\?\\UNC\\ComputerName\\abc')
202
203 self.assertEqual(sanitize_path('\\\\?\\C:\\abc'), '\\\\?\\C:\\abc')
204 self.assertEqual(sanitize_path('\\\\?\\C:/abc'), '\\\\?\\C:\\abc')
205 self.assertEqual(sanitize_path('\\\\?\\C:\\ab?c\\de:f'), '\\\\?\\C:\\ab#c\\de#f')
206 self.assertEqual(sanitize_path('\\\\?\\C:\\abc'), '\\\\?\\C:\\abc')
207
208 self.assertEqual(
209 sanitize_path('youtube/%(uploader)s/%(autonumber)s-%(title)s-%(upload_date)s.%(ext)s'),
210 'youtube\\%(uploader)s\\%(autonumber)s-%(title)s-%(upload_date)s.%(ext)s')
211
212 self.assertEqual(
213 sanitize_path('youtube/TheWreckingYard ./00001-Not bad, Especially for Free! (1987 Yamaha 700)-20141116.mp4.part'),
214 'youtube\\TheWreckingYard #\\00001-Not bad, Especially for Free! (1987 Yamaha 700)-20141116.mp4.part')
215 self.assertEqual(sanitize_path('abc/def...'), 'abc\\def..#')
216 self.assertEqual(sanitize_path('abc.../def'), 'abc..#\\def')
217 self.assertEqual(sanitize_path('abc.../def...'), 'abc..#\\def..#')
218
219 self.assertEqual(sanitize_path('../abc'), '..\\abc')
220 self.assertEqual(sanitize_path('../../abc'), '..\\..\\abc')
221 self.assertEqual(sanitize_path('./abc'), 'abc')
222 self.assertEqual(sanitize_path('./../abc'), '..\\abc')
223
224 def test_sanitize_url(self):
225 self.assertEqual(sanitize_url('//foo.bar'), 'http://foo.bar')
226 self.assertEqual(sanitize_url('httpss://foo.bar'), 'https://foo.bar')
227 self.assertEqual(sanitize_url('rmtps://foo.bar'), 'rtmps://foo.bar')
228 self.assertEqual(sanitize_url('https://foo.bar'), 'https://foo.bar')
229
230 def test_expand_path(self):
231 def env(var):
232 return '%{0}%'.format(var) if sys.platform == 'win32' else '${0}'.format(var)
233
234 compat_setenv('YOUTUBE_DL_EXPATH_PATH', 'expanded')
235 self.assertEqual(expand_path(env('YOUTUBE_DL_EXPATH_PATH')), 'expanded')
236 self.assertEqual(expand_path(env('HOME')), compat_getenv('HOME'))
237 self.assertEqual(expand_path('~'), compat_getenv('HOME'))
238 self.assertEqual(
239 expand_path('~/%s' % env('YOUTUBE_DL_EXPATH_PATH')),
240 '%s/expanded' % compat_getenv('HOME'))
241
242 def test_prepend_extension(self):
243 self.assertEqual(prepend_extension('abc.ext', 'temp'), 'abc.temp.ext')
244 self.assertEqual(prepend_extension('abc.ext', 'temp', 'ext'), 'abc.temp.ext')
245 self.assertEqual(prepend_extension('abc.unexpected_ext', 'temp', 'ext'), 'abc.unexpected_ext.temp')
246 self.assertEqual(prepend_extension('abc', 'temp'), 'abc.temp')
247 self.assertEqual(prepend_extension('.abc', 'temp'), '.abc.temp')
248 self.assertEqual(prepend_extension('.abc.ext', 'temp'), '.abc.temp.ext')
249
250 def test_replace_extension(self):
251 self.assertEqual(replace_extension('abc.ext', 'temp'), 'abc.temp')
252 self.assertEqual(replace_extension('abc.ext', 'temp', 'ext'), 'abc.temp')
253 self.assertEqual(replace_extension('abc.unexpected_ext', 'temp', 'ext'), 'abc.unexpected_ext.temp')
254 self.assertEqual(replace_extension('abc', 'temp'), 'abc.temp')
255 self.assertEqual(replace_extension('.abc', 'temp'), '.abc.temp')
256 self.assertEqual(replace_extension('.abc.ext', 'temp'), '.abc.temp')
257
258 def test_remove_start(self):
259 self.assertEqual(remove_start(None, 'A - '), None)
260 self.assertEqual(remove_start('A - B', 'A - '), 'B')
261 self.assertEqual(remove_start('B - A', 'A - '), 'B - A')
262
263 def test_remove_end(self):
264 self.assertEqual(remove_end(None, ' - B'), None)
265 self.assertEqual(remove_end('A - B', ' - B'), 'A')
266 self.assertEqual(remove_end('B - A', ' - B'), 'B - A')
267
268 def test_remove_quotes(self):
269 self.assertEqual(remove_quotes(None), None)
270 self.assertEqual(remove_quotes('"'), '"')
271 self.assertEqual(remove_quotes("'"), "'")
272 self.assertEqual(remove_quotes(';'), ';')
273 self.assertEqual(remove_quotes('";'), '";')
274 self.assertEqual(remove_quotes('""'), '')
275 self.assertEqual(remove_quotes('";"'), ';')
276
277 def test_ordered_set(self):
278 self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7])
279 self.assertEqual(orderedSet([]), [])
280 self.assertEqual(orderedSet([1]), [1])
281 # keep the list ordered
282 self.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1])
283
284 def test_unescape_html(self):
285 self.assertEqual(unescapeHTML('%20;'), '%20;')
286 self.assertEqual(unescapeHTML('&#x2F;'), '/')
287 self.assertEqual(unescapeHTML('&#47;'), '/')
288 self.assertEqual(unescapeHTML('&eacute;'), 'é')
289 self.assertEqual(unescapeHTML('&#2013266066;'), '&#2013266066;')
290 self.assertEqual(unescapeHTML('&a&quot;'), '&a"')
291 # HTML5 entities
292 self.assertEqual(unescapeHTML('&period;&apos;'), '.\'')
293
294 def test_date_from_str(self):
295 self.assertEqual(date_from_str('yesterday'), date_from_str('now-1day'))
296 self.assertEqual(date_from_str('now+7day'), date_from_str('now+1week'))
297 self.assertEqual(date_from_str('now+14day'), date_from_str('now+2week'))
298 self.assertEqual(date_from_str('now+365day'), date_from_str('now+1year'))
299 self.assertEqual(date_from_str('now+30day'), date_from_str('now+1month'))
300
301 def test_daterange(self):
302 _20century = DateRange("19000101", "20000101")
303 self.assertFalse("17890714" in _20century)
304 _ac = DateRange("00010101")
305 self.assertTrue("19690721" in _ac)
306 _firstmilenium = DateRange(end="10000101")
307 self.assertTrue("07110427" in _firstmilenium)
308
309 def test_unified_dates(self):
310 self.assertEqual(unified_strdate('December 21, 2010'), '20101221')
311 self.assertEqual(unified_strdate('8/7/2009'), '20090708')
312 self.assertEqual(unified_strdate('Dec 14, 2012'), '20121214')
313 self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
314 self.assertEqual(unified_strdate('1968 12 10'), '19681210')
315 self.assertEqual(unified_strdate('1968-12-10'), '19681210')
316 self.assertEqual(unified_strdate('28/01/2014 21:00:00 +0100'), '20140128')
317 self.assertEqual(
318 unified_strdate('11/26/2014 11:30:00 AM PST', day_first=False),
319 '20141126')
320 self.assertEqual(
321 unified_strdate('2/2/2015 6:47:40 PM', day_first=False),
322 '20150202')
323 self.assertEqual(unified_strdate('Feb 14th 2016 5:45PM'), '20160214')
324 self.assertEqual(unified_strdate('25-09-2014'), '20140925')
325 self.assertEqual(unified_strdate('27.02.2016 17:30'), '20160227')
326 self.assertEqual(unified_strdate('UNKNOWN DATE FORMAT'), None)
327 self.assertEqual(unified_strdate('Feb 7, 2016 at 6:35 pm'), '20160207')
328 self.assertEqual(unified_strdate('July 15th, 2013'), '20130715')
329 self.assertEqual(unified_strdate('September 1st, 2013'), '20130901')
330 self.assertEqual(unified_strdate('Sep 2nd, 2013'), '20130902')
331
332 def test_unified_timestamps(self):
333 self.assertEqual(unified_timestamp('December 21, 2010'), 1292889600)
334 self.assertEqual(unified_timestamp('8/7/2009'), 1247011200)
335 self.assertEqual(unified_timestamp('Dec 14, 2012'), 1355443200)
336 self.assertEqual(unified_timestamp('2012/10/11 01:56:38 +0000'), 1349920598)
337 self.assertEqual(unified_timestamp('1968 12 10'), -33436800)
338 self.assertEqual(unified_timestamp('1968-12-10'), -33436800)
339 self.assertEqual(unified_timestamp('28/01/2014 21:00:00 +0100'), 1390939200)
340 self.assertEqual(
341 unified_timestamp('11/26/2014 11:30:00 AM PST', day_first=False),
342 1417001400)
343 self.assertEqual(
344 unified_timestamp('2/2/2015 6:47:40 PM', day_first=False),
345 1422902860)
346 self.assertEqual(unified_timestamp('Feb 14th 2016 5:45PM'), 1455471900)
347 self.assertEqual(unified_timestamp('25-09-2014'), 1411603200)
348 self.assertEqual(unified_timestamp('27.02.2016 17:30'), 1456594200)
349 self.assertEqual(unified_timestamp('UNKNOWN DATE FORMAT'), None)
350 self.assertEqual(unified_timestamp('May 16, 2016 11:15 PM'), 1463440500)
351 self.assertEqual(unified_timestamp('Feb 7, 2016 at 6:35 pm'), 1454870100)
352 self.assertEqual(unified_timestamp('2017-03-30T17:52:41Q'), 1490896361)
353 self.assertEqual(unified_timestamp('Sep 11, 2013 | 5:49 AM'), 1378878540)
354 self.assertEqual(unified_timestamp('December 15, 2017 at 7:49 am'), 1513324140)
355 self.assertEqual(unified_timestamp('2018-03-14T08:32:43.1493874+00:00'), 1521016363)
356
357 def test_determine_ext(self):
358 self.assertEqual(determine_ext('http://example.com/foo/bar.mp4/?download'), 'mp4')
359 self.assertEqual(determine_ext('http://example.com/foo/bar/?download', None), None)
360 self.assertEqual(determine_ext('http://example.com/foo/bar.nonext/?download', None), None)
361 self.assertEqual(determine_ext('http://example.com/foo/bar/mp4?download', None), None)
362 self.assertEqual(determine_ext('http://example.com/foo/bar.m3u8//?download'), 'm3u8')
363
364 def test_find_xpath_attr(self):
365 testxml = '''<root>
366 <node/>
367 <node x="a"/>
368 <node x="a" y="c" />
369 <node x="b" y="d" />
370 <node x="" />
371 </root>'''
372 doc = compat_etree_fromstring(testxml)
373
374 self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n'), None)
375 self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n', 'v'), None)
376 self.assertEqual(find_xpath_attr(doc, './/node', 'n'), None)
377 self.assertEqual(find_xpath_attr(doc, './/node', 'n', 'v'), None)
378 self.assertEqual(find_xpath_attr(doc, './/node', 'x'), doc[1])
379 self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'a'), doc[1])
380 self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'b'), doc[3])
381 self.assertEqual(find_xpath_attr(doc, './/node', 'y'), doc[2])
382 self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'c'), doc[2])
383 self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'd'), doc[3])
384 self.assertEqual(find_xpath_attr(doc, './/node', 'x', ''), doc[4])
385
386 def test_xpath_with_ns(self):
387 testxml = '''<root xmlns:media="http://example.com/">
388 <media:song>
389 <media:author>The Author</media:author>
390 <url>http://server.com/download.mp3</url>
391 </media:song>
392 </root>'''
393 doc = compat_etree_fromstring(testxml)
394 find = lambda p: doc.find(xpath_with_ns(p, {'media': 'http://example.com/'}))
395 self.assertTrue(find('media:song') is not None)
396 self.assertEqual(find('media:song/media:author').text, 'The Author')
397 self.assertEqual(find('media:song/url').text, 'http://server.com/download.mp3')
398
399 def test_xpath_element(self):
400 doc = xml.etree.ElementTree.Element('root')
401 div = xml.etree.ElementTree.SubElement(doc, 'div')
402 p = xml.etree.ElementTree.SubElement(div, 'p')
403 p.text = 'Foo'
404 self.assertEqual(xpath_element(doc, 'div/p'), p)
405 self.assertEqual(xpath_element(doc, ['div/p']), p)
406 self.assertEqual(xpath_element(doc, ['div/bar', 'div/p']), p)
407 self.assertEqual(xpath_element(doc, 'div/bar', default='default'), 'default')
408 self.assertEqual(xpath_element(doc, ['div/bar'], default='default'), 'default')
409 self.assertTrue(xpath_element(doc, 'div/bar') is None)
410 self.assertTrue(xpath_element(doc, ['div/bar']) is None)
411 self.assertTrue(xpath_element(doc, ['div/bar'], 'div/baz') is None)
412 self.assertRaises(ExtractorError, xpath_element, doc, 'div/bar', fatal=True)
413 self.assertRaises(ExtractorError, xpath_element, doc, ['div/bar'], fatal=True)
414 self.assertRaises(ExtractorError, xpath_element, doc, ['div/bar', 'div/baz'], fatal=True)
415
416 def test_xpath_text(self):
417 testxml = '''<root>
418 <div>
419 <p>Foo</p>
420 </div>
421 </root>'''
422 doc = compat_etree_fromstring(testxml)
423 self.assertEqual(xpath_text(doc, 'div/p'), 'Foo')
424 self.assertEqual(xpath_text(doc, 'div/bar', default='default'), 'default')
425 self.assertTrue(xpath_text(doc, 'div/bar') is None)
426 self.assertRaises(ExtractorError, xpath_text, doc, 'div/bar', fatal=True)
427
428 def test_xpath_attr(self):
429 testxml = '''<root>
430 <div>
431 <p x="a">Foo</p>
432 </div>
433 </root>'''
434 doc = compat_etree_fromstring(testxml)
435 self.assertEqual(xpath_attr(doc, 'div/p', 'x'), 'a')
436 self.assertEqual(xpath_attr(doc, 'div/bar', 'x'), None)
437 self.assertEqual(xpath_attr(doc, 'div/p', 'y'), None)
438 self.assertEqual(xpath_attr(doc, 'div/bar', 'x', default='default'), 'default')
439 self.assertEqual(xpath_attr(doc, 'div/p', 'y', default='default'), 'default')
440 self.assertRaises(ExtractorError, xpath_attr, doc, 'div/bar', 'x', fatal=True)
441 self.assertRaises(ExtractorError, xpath_attr, doc, 'div/p', 'y', fatal=True)
442
443 def test_smuggle_url(self):
444 data = {"ö": "ö", "abc": [3]}
445 url = 'https://foo.bar/baz?x=y#a'
446 smug_url = smuggle_url(url, data)
447 unsmug_url, unsmug_data = unsmuggle_url(smug_url)
448 self.assertEqual(url, unsmug_url)
449 self.assertEqual(data, unsmug_data)
450
451 res_url, res_data = unsmuggle_url(url)
452 self.assertEqual(res_url, url)
453 self.assertEqual(res_data, None)
454
455 smug_url = smuggle_url(url, {'a': 'b'})
456 smug_smug_url = smuggle_url(smug_url, {'c': 'd'})
457 res_url, res_data = unsmuggle_url(smug_smug_url)
458 self.assertEqual(res_url, url)
459 self.assertEqual(res_data, {'a': 'b', 'c': 'd'})
460
461 def test_shell_quote(self):
462 args = ['ffmpeg', '-i', encodeFilename('ñ€ß\'.mp4')]
463 self.assertEqual(
464 shell_quote(args),
465 """ffmpeg -i 'ñ€ß'"'"'.mp4'""" if compat_os_name != 'nt' else '''ffmpeg -i "ñ€ß'.mp4"''')
466
467 def test_str_to_int(self):
468 self.assertEqual(str_to_int('123,456'), 123456)
469 self.assertEqual(str_to_int('123.456'), 123456)
470
471 def test_url_basename(self):
472 self.assertEqual(url_basename('http://foo.de/'), '')
473 self.assertEqual(url_basename('http://foo.de/bar/baz'), 'baz')
474 self.assertEqual(url_basename('http://foo.de/bar/baz?x=y'), 'baz')
475 self.assertEqual(url_basename('http://foo.de/bar/baz#x=y'), 'baz')
476 self.assertEqual(url_basename('http://foo.de/bar/baz/'), 'baz')
477 self.assertEqual(
478 url_basename('http://media.w3.org/2010/05/sintel/trailer.mp4'),
479 'trailer.mp4')
480
481 def test_base_url(self):
482 self.assertEqual(base_url('http://foo.de/'), 'http://foo.de/')
483 self.assertEqual(base_url('http://foo.de/bar'), 'http://foo.de/')
484 self.assertEqual(base_url('http://foo.de/bar/'), 'http://foo.de/bar/')
485 self.assertEqual(base_url('http://foo.de/bar/baz'), 'http://foo.de/bar/')
486 self.assertEqual(base_url('http://foo.de/bar/baz?x=z/x/c'), 'http://foo.de/bar/')
487
488 def test_urljoin(self):
489 self.assertEqual(urljoin('http://foo.de/', '/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
490 self.assertEqual(urljoin(b'http://foo.de/', '/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
491 self.assertEqual(urljoin('http://foo.de/', b'/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
492 self.assertEqual(urljoin(b'http://foo.de/', b'/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
493 self.assertEqual(urljoin('//foo.de/', '/a/b/c.txt'), '//foo.de/a/b/c.txt')
494 self.assertEqual(urljoin('http://foo.de/', 'a/b/c.txt'), 'http://foo.de/a/b/c.txt')
495 self.assertEqual(urljoin('http://foo.de', '/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
496 self.assertEqual(urljoin('http://foo.de', 'a/b/c.txt'), 'http://foo.de/a/b/c.txt')
497 self.assertEqual(urljoin('http://foo.de/', 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
498 self.assertEqual(urljoin('http://foo.de/', '//foo.de/a/b/c.txt'), '//foo.de/a/b/c.txt')
499 self.assertEqual(urljoin(None, 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
500 self.assertEqual(urljoin(None, '//foo.de/a/b/c.txt'), '//foo.de/a/b/c.txt')
501 self.assertEqual(urljoin('', 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
502 self.assertEqual(urljoin(['foobar'], 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
503 self.assertEqual(urljoin('http://foo.de/', None), None)
504 self.assertEqual(urljoin('http://foo.de/', ''), None)
505 self.assertEqual(urljoin('http://foo.de/', ['foobar']), None)
506 self.assertEqual(urljoin('http://foo.de/a/b/c.txt', '.././../d.txt'), 'http://foo.de/d.txt')
507
508 def test_parse_age_limit(self):
509 self.assertEqual(parse_age_limit(None), None)
510 self.assertEqual(parse_age_limit(False), None)
511 self.assertEqual(parse_age_limit('invalid'), None)
512 self.assertEqual(parse_age_limit(0), 0)
513 self.assertEqual(parse_age_limit(18), 18)
514 self.assertEqual(parse_age_limit(21), 21)
515 self.assertEqual(parse_age_limit(22), None)
516 self.assertEqual(parse_age_limit('18'), 18)
517 self.assertEqual(parse_age_limit('18+'), 18)
518 self.assertEqual(parse_age_limit('PG-13'), 13)
519 self.assertEqual(parse_age_limit('TV-14'), 14)
520 self.assertEqual(parse_age_limit('TV-MA'), 17)
521
522 def test_parse_duration(self):
523 self.assertEqual(parse_duration(None), None)
524 self.assertEqual(parse_duration(False), None)
525 self.assertEqual(parse_duration('invalid'), None)
526 self.assertEqual(parse_duration('1'), 1)
527 self.assertEqual(parse_duration('1337:12'), 80232)
528 self.assertEqual(parse_duration('9:12:43'), 33163)
529 self.assertEqual(parse_duration('12:00'), 720)
530 self.assertEqual(parse_duration('00:01:01'), 61)
531 self.assertEqual(parse_duration('x:y'), None)
532 self.assertEqual(parse_duration('3h11m53s'), 11513)
533 self.assertEqual(parse_duration('3h 11m 53s'), 11513)
534 self.assertEqual(parse_duration('3 hours 11 minutes 53 seconds'), 11513)
535 self.assertEqual(parse_duration('3 hours 11 mins 53 secs'), 11513)
536 self.assertEqual(parse_duration('62m45s'), 3765)
537 self.assertEqual(parse_duration('6m59s'), 419)
538 self.assertEqual(parse_duration('49s'), 49)
539 self.assertEqual(parse_duration('0h0m0s'), 0)
540 self.assertEqual(parse_duration('0m0s'), 0)
541 self.assertEqual(parse_duration('0s'), 0)
542 self.assertEqual(parse_duration('01:02:03.05'), 3723.05)
543 self.assertEqual(parse_duration('T30M38S'), 1838)
544 self.assertEqual(parse_duration('5 s'), 5)
545 self.assertEqual(parse_duration('3 min'), 180)
546 self.assertEqual(parse_duration('2.5 hours'), 9000)
547 self.assertEqual(parse_duration('02:03:04'), 7384)
548 self.assertEqual(parse_duration('01:02:03:04'), 93784)
549 self.assertEqual(parse_duration('1 hour 3 minutes'), 3780)
550 self.assertEqual(parse_duration('87 Min.'), 5220)
551 self.assertEqual(parse_duration('PT1H0.040S'), 3600.04)
552 self.assertEqual(parse_duration('PT00H03M30SZ'), 210)
553 self.assertEqual(parse_duration('P0Y0M0DT0H4M20.880S'), 260.88)
554
555 def test_fix_xml_ampersands(self):
556 self.assertEqual(
557 fix_xml_ampersands('"&x=y&z=a'), '"&amp;x=y&amp;z=a')
558 self.assertEqual(
559 fix_xml_ampersands('"&amp;x=y&wrong;&z=a'),
560 '"&amp;x=y&amp;wrong;&amp;z=a')
561 self.assertEqual(
562 fix_xml_ampersands('&amp;&apos;&gt;&lt;&quot;'),
563 '&amp;&apos;&gt;&lt;&quot;')
564 self.assertEqual(
565 fix_xml_ampersands('&#1234;&#x1abC;'), '&#1234;&#x1abC;')
566 self.assertEqual(fix_xml_ampersands('&#&#'), '&amp;#&amp;#')
567
568 def test_paged_list(self):
569 def testPL(size, pagesize, sliceargs, expected):
570 def get_page(pagenum):
571 firstid = pagenum * pagesize
572 upto = min(size, pagenum * pagesize + pagesize)
573 for i in range(firstid, upto):
574 yield i
575
576 pl = OnDemandPagedList(get_page, pagesize)
577 got = pl.getslice(*sliceargs)
578 self.assertEqual(got, expected)
579
580 iapl = InAdvancePagedList(get_page, size // pagesize + 1, pagesize)
581 got = iapl.getslice(*sliceargs)
582 self.assertEqual(got, expected)
583
584 testPL(5, 2, (), [0, 1, 2, 3, 4])
585 testPL(5, 2, (1,), [1, 2, 3, 4])
586 testPL(5, 2, (2,), [2, 3, 4])
587 testPL(5, 2, (4,), [4])
588 testPL(5, 2, (0, 3), [0, 1, 2])
589 testPL(5, 2, (1, 4), [1, 2, 3])
590 testPL(5, 2, (2, 99), [2, 3, 4])
591 testPL(5, 2, (20, 99), [])
592
593 def test_read_batch_urls(self):
594 f = io.StringIO('''\xef\xbb\xbf foo
595 bar\r
596 baz
597 # More after this line\r
598 ; or after this
599 bam''')
600 self.assertEqual(read_batch_urls(f), ['foo', 'bar', 'baz', 'bam'])
601
602 def test_urlencode_postdata(self):
603 data = urlencode_postdata({'username': 'foo@bar.com', 'password': '1234'})
604 self.assertTrue(isinstance(data, bytes))
605
606 def test_update_url_query(self):
607 def query_dict(url):
608 return compat_parse_qs(compat_urlparse.urlparse(url).query)
609 self.assertEqual(query_dict(update_url_query(
610 'http://example.com/path', {'quality': ['HD'], 'format': ['mp4']})),
611 query_dict('http://example.com/path?quality=HD&format=mp4'))
612 self.assertEqual(query_dict(update_url_query(
613 'http://example.com/path', {'system': ['LINUX', 'WINDOWS']})),
614 query_dict('http://example.com/path?system=LINUX&system=WINDOWS'))
615 self.assertEqual(query_dict(update_url_query(
616 'http://example.com/path', {'fields': 'id,formats,subtitles'})),
617 query_dict('http://example.com/path?fields=id,formats,subtitles'))
618 self.assertEqual(query_dict(update_url_query(
619 'http://example.com/path', {'fields': ('id,formats,subtitles', 'thumbnails')})),
620 query_dict('http://example.com/path?fields=id,formats,subtitles&fields=thumbnails'))
621 self.assertEqual(query_dict(update_url_query(
622 'http://example.com/path?manifest=f4m', {'manifest': []})),
623 query_dict('http://example.com/path'))
624 self.assertEqual(query_dict(update_url_query(
625 'http://example.com/path?system=LINUX&system=WINDOWS', {'system': 'LINUX'})),
626 query_dict('http://example.com/path?system=LINUX'))
627 self.assertEqual(query_dict(update_url_query(
628 'http://example.com/path', {'fields': b'id,formats,subtitles'})),
629 query_dict('http://example.com/path?fields=id,formats,subtitles'))
630 self.assertEqual(query_dict(update_url_query(
631 'http://example.com/path', {'width': 1080, 'height': 720})),
632 query_dict('http://example.com/path?width=1080&height=720'))
633 self.assertEqual(query_dict(update_url_query(
634 'http://example.com/path', {'bitrate': 5020.43})),
635 query_dict('http://example.com/path?bitrate=5020.43'))
636 self.assertEqual(query_dict(update_url_query(
637 'http://example.com/path', {'test': '第二行тест'})),
638 query_dict('http://example.com/path?test=%E7%AC%AC%E4%BA%8C%E8%A1%8C%D1%82%D0%B5%D1%81%D1%82'))
639
640 def test_multipart_encode(self):
641 self.assertEqual(
642 multipart_encode({b'field': b'value'}, boundary='AAAAAA')[0],
643 b'--AAAAAA\r\nContent-Disposition: form-data; name="field"\r\n\r\nvalue\r\n--AAAAAA--\r\n')
644 self.assertEqual(
645 multipart_encode({'欄位'.encode('utf-8'): '值'.encode('utf-8')}, boundary='AAAAAA')[0],
646 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')
647 self.assertRaises(
648 ValueError, multipart_encode, {b'field': b'value'}, boundary='value')
649
650 def test_dict_get(self):
651 FALSE_VALUES = {
652 'none': None,
653 'false': False,
654 'zero': 0,
655 'empty_string': '',
656 'empty_list': [],
657 }
658 d = FALSE_VALUES.copy()
659 d['a'] = 42
660 self.assertEqual(dict_get(d, 'a'), 42)
661 self.assertEqual(dict_get(d, 'b'), None)
662 self.assertEqual(dict_get(d, 'b', 42), 42)
663 self.assertEqual(dict_get(d, ('a', )), 42)
664 self.assertEqual(dict_get(d, ('b', 'a', )), 42)
665 self.assertEqual(dict_get(d, ('b', 'c', 'a', 'd', )), 42)
666 self.assertEqual(dict_get(d, ('b', 'c', )), None)
667 self.assertEqual(dict_get(d, ('b', 'c', ), 42), 42)
668 for key, false_value in FALSE_VALUES.items():
669 self.assertEqual(dict_get(d, ('b', 'c', key, )), None)
670 self.assertEqual(dict_get(d, ('b', 'c', key, ), skip_false_values=False), false_value)
671
672 def test_encode_compat_str(self):
673 self.assertEqual(encode_compat_str(b'\xd1\x82\xd0\xb5\xd1\x81\xd1\x82', 'utf-8'), 'тест')
674 self.assertEqual(encode_compat_str('тест', 'utf-8'), 'тест')
675
676 def test_parse_iso8601(self):
677 self.assertEqual(parse_iso8601('2014-03-23T23:04:26+0100'), 1395612266)
678 self.assertEqual(parse_iso8601('2014-03-23T22:04:26+0000'), 1395612266)
679 self.assertEqual(parse_iso8601('2014-03-23T22:04:26Z'), 1395612266)
680 self.assertEqual(parse_iso8601('2014-03-23T22:04:26.1234Z'), 1395612266)
681 self.assertEqual(parse_iso8601('2015-09-29T08:27:31.727'), 1443515251)
682 self.assertEqual(parse_iso8601('2015-09-29T08-27-31.727'), None)
683
684 def test_strip_jsonp(self):
685 stripped = strip_jsonp('cb ([ {"id":"532cb",\n\n\n"x":\n3}\n]\n);')
686 d = json.loads(stripped)
687 self.assertEqual(d, [{"id": "532cb", "x": 3}])
688
689 stripped = strip_jsonp('parseMetadata({"STATUS":"OK"})\n\n\n//epc')
690 d = json.loads(stripped)
691 self.assertEqual(d, {'STATUS': 'OK'})
692
693 stripped = strip_jsonp('ps.embedHandler({"status": "success"});')
694 d = json.loads(stripped)
695 self.assertEqual(d, {'status': 'success'})
696
697 stripped = strip_jsonp('window.cb && window.cb({"status": "success"});')
698 d = json.loads(stripped)
699 self.assertEqual(d, {'status': 'success'})
700
701 stripped = strip_jsonp('window.cb && cb({"status": "success"});')
702 d = json.loads(stripped)
703 self.assertEqual(d, {'status': 'success'})
704
705 def test_uppercase_escape(self):
706 self.assertEqual(uppercase_escape('aä'), 'aä')
707 self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐')
708
709 def test_lowercase_escape(self):
710 self.assertEqual(lowercase_escape('aä'), 'aä')
711 self.assertEqual(lowercase_escape('\\u0026'), '&')
712
713 def test_limit_length(self):
714 self.assertEqual(limit_length(None, 12), None)
715 self.assertEqual(limit_length('foo', 12), 'foo')
716 self.assertTrue(
717 limit_length('foo bar baz asd', 12).startswith('foo bar'))
718 self.assertTrue('...' in limit_length('foo bar baz asd', 12))
719
720 def test_mimetype2ext(self):
721 self.assertEqual(mimetype2ext(None), None)
722 self.assertEqual(mimetype2ext('video/x-flv'), 'flv')
723 self.assertEqual(mimetype2ext('application/x-mpegURL'), 'm3u8')
724 self.assertEqual(mimetype2ext('text/vtt'), 'vtt')
725 self.assertEqual(mimetype2ext('text/vtt;charset=utf-8'), 'vtt')
726 self.assertEqual(mimetype2ext('text/html; charset=utf-8'), 'html')
727
728 def test_month_by_name(self):
729 self.assertEqual(month_by_name(None), None)
730 self.assertEqual(month_by_name('December', 'en'), 12)
731 self.assertEqual(month_by_name('décembre', 'fr'), 12)
732 self.assertEqual(month_by_name('December'), 12)
733 self.assertEqual(month_by_name('décembre'), None)
734 self.assertEqual(month_by_name('Unknown', 'unknown'), None)
735
736 def test_parse_codecs(self):
737 self.assertEqual(parse_codecs(''), {})
738 self.assertEqual(parse_codecs('avc1.77.30, mp4a.40.2'), {
739 'vcodec': 'avc1.77.30',
740 'acodec': 'mp4a.40.2',
741 })
742 self.assertEqual(parse_codecs('mp4a.40.2'), {
743 'vcodec': 'none',
744 'acodec': 'mp4a.40.2',
745 })
746 self.assertEqual(parse_codecs('mp4a.40.5,avc1.42001e'), {
747 'vcodec': 'avc1.42001e',
748 'acodec': 'mp4a.40.5',
749 })
750 self.assertEqual(parse_codecs('avc3.640028'), {
751 'vcodec': 'avc3.640028',
752 'acodec': 'none',
753 })
754 self.assertEqual(parse_codecs(', h264,,newcodec,aac'), {
755 'vcodec': 'h264',
756 'acodec': 'aac',
757 })
758
759 def test_escape_rfc3986(self):
760 reserved = "!*'();:@&=+$,/?#[]"
761 unreserved = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_.~'
762 self.assertEqual(escape_rfc3986(reserved), reserved)
763 self.assertEqual(escape_rfc3986(unreserved), unreserved)
764 self.assertEqual(escape_rfc3986('тест'), '%D1%82%D0%B5%D1%81%D1%82')
765 self.assertEqual(escape_rfc3986('%D1%82%D0%B5%D1%81%D1%82'), '%D1%82%D0%B5%D1%81%D1%82')
766 self.assertEqual(escape_rfc3986('foo bar'), 'foo%20bar')
767 self.assertEqual(escape_rfc3986('foo%20bar'), 'foo%20bar')
768
769 def test_escape_url(self):
770 self.assertEqual(
771 escape_url('http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavré_FD.mp4'),
772 'http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavre%CC%81_FD.mp4'
773 )
774 self.assertEqual(
775 escape_url('http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erklärt/Das-Erste/Video?documentId=22673108&bcastId=5290'),
776 'http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erkl%C3%A4rt/Das-Erste/Video?documentId=22673108&bcastId=5290'
777 )
778 self.assertEqual(
779 escape_url('http://тест.рф/фрагмент'),
780 'http://xn--e1aybc.xn--p1ai/%D1%84%D1%80%D0%B0%D0%B3%D0%BC%D0%B5%D0%BD%D1%82'
781 )
782 self.assertEqual(
783 escape_url('http://тест.рф/абв?абв=абв#абв'),
784 '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'
785 )
786 self.assertEqual(escape_url('http://vimeo.com/56015672#at=0'), 'http://vimeo.com/56015672#at=0')
787
788 def test_js_to_json_realworld(self):
789 inp = '''{
790 'clip':{'provider':'pseudo'}
791 }'''
792 self.assertEqual(js_to_json(inp), '''{
793 "clip":{"provider":"pseudo"}
794 }''')
795 json.loads(js_to_json(inp))
796
797 inp = '''{
798 'playlist':[{'controls':{'all':null}}]
799 }'''
800 self.assertEqual(js_to_json(inp), '''{
801 "playlist":[{"controls":{"all":null}}]
802 }''')
803
804 inp = '''"The CW\\'s \\'Crazy Ex-Girlfriend\\'"'''
805 self.assertEqual(js_to_json(inp), '''"The CW's 'Crazy Ex-Girlfriend'"''')
806
807 inp = '"SAND Number: SAND 2013-7800P\\nPresenter: Tom Russo\\nHabanero Software Training - Xyce Software\\nXyce, Sandia\\u0027s"'
808 json_code = js_to_json(inp)
809 self.assertEqual(json.loads(json_code), json.loads(inp))
810
811 inp = '''{
812 0:{src:'skipped', type: 'application/dash+xml'},
813 1:{src:'skipped', type: 'application/vnd.apple.mpegURL'},
814 }'''
815 self.assertEqual(js_to_json(inp), '''{
816 "0":{"src":"skipped", "type": "application/dash+xml"},
817 "1":{"src":"skipped", "type": "application/vnd.apple.mpegURL"}
818 }''')
819
820 inp = '''{"foo":101}'''
821 self.assertEqual(js_to_json(inp), '''{"foo":101}''')
822
823 inp = '''{"duration": "00:01:07"}'''
824 self.assertEqual(js_to_json(inp), '''{"duration": "00:01:07"}''')
825
826 inp = '''{segments: [{"offset":-3.885780586188048e-16,"duration":39.75000000000001}]}'''
827 self.assertEqual(js_to_json(inp), '''{"segments": [{"offset":-3.885780586188048e-16,"duration":39.75000000000001}]}''')
828
829 def test_js_to_json_edgecases(self):
830 on = js_to_json("{abc_def:'1\\'\\\\2\\\\\\'3\"4'}")
831 self.assertEqual(json.loads(on), {"abc_def": "1'\\2\\'3\"4"})
832
833 on = js_to_json('{"abc": true}')
834 self.assertEqual(json.loads(on), {'abc': True})
835
836 # Ignore JavaScript code as well
837 on = js_to_json('''{
838 "x": 1,
839 y: "a",
840 z: some.code
841 }''')
842 d = json.loads(on)
843 self.assertEqual(d['x'], 1)
844 self.assertEqual(d['y'], 'a')
845
846 on = js_to_json('["abc", "def",]')
847 self.assertEqual(json.loads(on), ['abc', 'def'])
848
849 on = js_to_json('[/*comment\n*/"abc"/*comment\n*/,/*comment\n*/"def",/*comment\n*/]')
850 self.assertEqual(json.loads(on), ['abc', 'def'])
851
852 on = js_to_json('[//comment\n"abc" //comment\n,//comment\n"def",//comment\n]')
853 self.assertEqual(json.loads(on), ['abc', 'def'])
854
855 on = js_to_json('{"abc": "def",}')
856 self.assertEqual(json.loads(on), {'abc': 'def'})
857
858 on = js_to_json('{/*comment\n*/"abc"/*comment\n*/:/*comment\n*/"def"/*comment\n*/,/*comment\n*/}')
859 self.assertEqual(json.loads(on), {'abc': 'def'})
860
861 on = js_to_json('{ 0: /* " \n */ ",]" , }')
862 self.assertEqual(json.loads(on), {'0': ',]'})
863
864 on = js_to_json('{ /*comment\n*/0/*comment\n*/: /* " \n */ ",]" , }')
865 self.assertEqual(json.loads(on), {'0': ',]'})
866
867 on = js_to_json('{ 0: // comment\n1 }')
868 self.assertEqual(json.loads(on), {'0': 1})
869
870 on = js_to_json(r'["<p>x<\/p>"]')
871 self.assertEqual(json.loads(on), ['<p>x</p>'])
872
873 on = js_to_json(r'["\xaa"]')
874 self.assertEqual(json.loads(on), ['\u00aa'])
875
876 on = js_to_json("['a\\\nb']")
877 self.assertEqual(json.loads(on), ['ab'])
878
879 on = js_to_json("/*comment\n*/[/*comment\n*/'a\\\nb'/*comment\n*/]/*comment\n*/")
880 self.assertEqual(json.loads(on), ['ab'])
881
882 on = js_to_json('{0xff:0xff}')
883 self.assertEqual(json.loads(on), {'255': 255})
884
885 on = js_to_json('{/*comment\n*/0xff/*comment\n*/:/*comment\n*/0xff/*comment\n*/}')
886 self.assertEqual(json.loads(on), {'255': 255})
887
888 on = js_to_json('{077:077}')
889 self.assertEqual(json.loads(on), {'63': 63})
890
891 on = js_to_json('{/*comment\n*/077/*comment\n*/:/*comment\n*/077/*comment\n*/}')
892 self.assertEqual(json.loads(on), {'63': 63})
893
894 on = js_to_json('{42:42}')
895 self.assertEqual(json.loads(on), {'42': 42})
896
897 on = js_to_json('{/*comment\n*/42/*comment\n*/:/*comment\n*/42/*comment\n*/}')
898 self.assertEqual(json.loads(on), {'42': 42})
899
900 on = js_to_json('{42:4.2e1}')
901 self.assertEqual(json.loads(on), {'42': 42.0})
902
903 def test_js_to_json_malformed(self):
904 self.assertEqual(js_to_json('42a1'), '42"a1"')
905 self.assertEqual(js_to_json('42a-1'), '42"a"-1')
906
907 def test_extract_attributes(self):
908 self.assertEqual(extract_attributes('<e x="y">'), {'x': 'y'})
909 self.assertEqual(extract_attributes("<e x='y'>"), {'x': 'y'})
910 self.assertEqual(extract_attributes('<e x=y>'), {'x': 'y'})
911 self.assertEqual(extract_attributes('<e x="a \'b\' c">'), {'x': "a 'b' c"})
912 self.assertEqual(extract_attributes('<e x=\'a "b" c\'>'), {'x': 'a "b" c'})
913 self.assertEqual(extract_attributes('<e x="&#121;">'), {'x': 'y'})
914 self.assertEqual(extract_attributes('<e x="&#x79;">'), {'x': 'y'})
915 self.assertEqual(extract_attributes('<e x="&amp;">'), {'x': '&'}) # XML
916 self.assertEqual(extract_attributes('<e x="&quot;">'), {'x': '"'})
917 self.assertEqual(extract_attributes('<e x="&pound;">'), {'x': '£'}) # HTML 3.2
918 self.assertEqual(extract_attributes('<e x="&lambda;">'), {'x': 'λ'}) # HTML 4.0
919 self.assertEqual(extract_attributes('<e x="&foo">'), {'x': '&foo'})
920 self.assertEqual(extract_attributes('<e x="\'">'), {'x': "'"})
921 self.assertEqual(extract_attributes('<e x=\'"\'>'), {'x': '"'})
922 self.assertEqual(extract_attributes('<e x >'), {'x': None})
923 self.assertEqual(extract_attributes('<e x=y a>'), {'x': 'y', 'a': None})
924 self.assertEqual(extract_attributes('<e x= y>'), {'x': 'y'})
925 self.assertEqual(extract_attributes('<e x=1 y=2 x=3>'), {'y': '2', 'x': '3'})
926 self.assertEqual(extract_attributes('<e \nx=\ny\n>'), {'x': 'y'})
927 self.assertEqual(extract_attributes('<e \nx=\n"y"\n>'), {'x': 'y'})
928 self.assertEqual(extract_attributes("<e \nx=\n'y'\n>"), {'x': 'y'})
929 self.assertEqual(extract_attributes('<e \nx="\ny\n">'), {'x': '\ny\n'})
930 self.assertEqual(extract_attributes('<e CAPS=x>'), {'caps': 'x'}) # Names lowercased
931 self.assertEqual(extract_attributes('<e x=1 X=2>'), {'x': '2'})
932 self.assertEqual(extract_attributes('<e X=1 x=2>'), {'x': '2'})
933 self.assertEqual(extract_attributes('<e _:funny-name1=1>'), {'_:funny-name1': '1'})
934 self.assertEqual(extract_attributes('<e x="Fáilte 世界 \U0001f600">'), {'x': 'Fáilte 世界 \U0001f600'})
935 self.assertEqual(extract_attributes('<e x="décompose&#769;">'), {'x': 'décompose\u0301'})
936 # "Narrow" Python builds don't support unicode code points outside BMP.
937 try:
938 compat_chr(0x10000)
939 supports_outside_bmp = True
940 except ValueError:
941 supports_outside_bmp = False
942 if supports_outside_bmp:
943 self.assertEqual(extract_attributes('<e x="Smile &#128512;!">'), {'x': 'Smile \U0001f600!'})
944 # Malformed HTML should not break attributes extraction on older Python
945 self.assertEqual(extract_attributes('<mal"formed/>'), {})
946
947 def test_clean_html(self):
948 self.assertEqual(clean_html('a:\nb'), 'a: b')
949 self.assertEqual(clean_html('a:\n "b"'), 'a: "b"')
950 self.assertEqual(clean_html('a<br>\xa0b'), 'a\nb')
951
952 def test_intlist_to_bytes(self):
953 self.assertEqual(
954 intlist_to_bytes([0, 1, 127, 128, 255]),
955 b'\x00\x01\x7f\x80\xff')
956
957 def test_args_to_str(self):
958 self.assertEqual(
959 args_to_str(['foo', 'ba/r', '-baz', '2 be', '']),
960 'foo ba/r -baz \'2 be\' \'\'' if compat_os_name != 'nt' else 'foo ba/r -baz "2 be" ""'
961 )
962
963 def test_parse_filesize(self):
964 self.assertEqual(parse_filesize(None), None)
965 self.assertEqual(parse_filesize(''), None)
966 self.assertEqual(parse_filesize('91 B'), 91)
967 self.assertEqual(parse_filesize('foobar'), None)
968 self.assertEqual(parse_filesize('2 MiB'), 2097152)
969 self.assertEqual(parse_filesize('5 GB'), 5000000000)
970 self.assertEqual(parse_filesize('1.2Tb'), 1200000000000)
971 self.assertEqual(parse_filesize('1.2tb'), 1200000000000)
972 self.assertEqual(parse_filesize('1,24 KB'), 1240)
973 self.assertEqual(parse_filesize('1,24 kb'), 1240)
974 self.assertEqual(parse_filesize('8.5 megabytes'), 8500000)
975
976 def test_parse_count(self):
977 self.assertEqual(parse_count(None), None)
978 self.assertEqual(parse_count(''), None)
979 self.assertEqual(parse_count('0'), 0)
980 self.assertEqual(parse_count('1000'), 1000)
981 self.assertEqual(parse_count('1.000'), 1000)
982 self.assertEqual(parse_count('1.1k'), 1100)
983 self.assertEqual(parse_count('1.1kk'), 1100000)
984 self.assertEqual(parse_count('1.1kk '), 1100000)
985 self.assertEqual(parse_count('1.1kk views'), 1100000)
986
987 def test_parse_resolution(self):
988 self.assertEqual(parse_resolution(None), {})
989 self.assertEqual(parse_resolution(''), {})
990 self.assertEqual(parse_resolution('1920x1080'), {'width': 1920, 'height': 1080})
991 self.assertEqual(parse_resolution('1920×1080'), {'width': 1920, 'height': 1080})
992 self.assertEqual(parse_resolution('1920 x 1080'), {'width': 1920, 'height': 1080})
993 self.assertEqual(parse_resolution('720p'), {'height': 720})
994 self.assertEqual(parse_resolution('4k'), {'height': 2160})
995 self.assertEqual(parse_resolution('8K'), {'height': 4320})
996
997 def test_version_tuple(self):
998 self.assertEqual(version_tuple('1'), (1,))
999 self.assertEqual(version_tuple('10.23.344'), (10, 23, 344))
1000 self.assertEqual(version_tuple('10.1-6'), (10, 1, 6)) # avconv style
1001
1002 def test_detect_exe_version(self):
1003 self.assertEqual(detect_exe_version('''ffmpeg version 1.2.1
1004 built on May 27 2013 08:37:26 with gcc 4.7 (Debian 4.7.3-4)
1005 configuration: --prefix=/usr --extra-'''), '1.2.1')
1006 self.assertEqual(detect_exe_version('''ffmpeg version N-63176-g1fb4685
1007 built on May 15 2014 22:09:06 with gcc 4.8.2 (GCC)'''), 'N-63176-g1fb4685')
1008 self.assertEqual(detect_exe_version('''X server found. dri2 connection failed!
1009 Trying to open render node...
1010 Success at /dev/dri/renderD128.
1011 ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')
1012
1013 def test_age_restricted(self):
1014 self.assertFalse(age_restricted(None, 10)) # unrestricted content
1015 self.assertFalse(age_restricted(1, None)) # unrestricted policy
1016 self.assertFalse(age_restricted(8, 10))
1017 self.assertTrue(age_restricted(18, 14))
1018 self.assertFalse(age_restricted(18, 18))
1019
1020 def test_is_html(self):
1021 self.assertFalse(is_html(b'\x49\x44\x43<html'))
1022 self.assertTrue(is_html(b'<!DOCTYPE foo>\xaaa'))
1023 self.assertTrue(is_html( # UTF-8 with BOM
1024 b'\xef\xbb\xbf<!DOCTYPE foo>\xaaa'))
1025 self.assertTrue(is_html( # UTF-16-LE
1026 b'\xff\xfe<\x00h\x00t\x00m\x00l\x00>\x00\xe4\x00'
1027 ))
1028 self.assertTrue(is_html( # UTF-16-BE
1029 b'\xfe\xff\x00<\x00h\x00t\x00m\x00l\x00>\x00\xe4'
1030 ))
1031 self.assertTrue(is_html( # UTF-32-BE
1032 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'))
1033 self.assertTrue(is_html( # UTF-32-LE
1034 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'))
1035
1036 def test_render_table(self):
1037 self.assertEqual(
1038 render_table(
1039 ['a', 'bcd'],
1040 [[123, 4], [9999, 51]]),
1041 'a bcd\n'
1042 '123 4\n'
1043 '9999 51')
1044
1045 def test_match_str(self):
1046 self.assertRaises(ValueError, match_str, 'xy>foobar', {})
1047 self.assertFalse(match_str('xy', {'x': 1200}))
1048 self.assertTrue(match_str('!xy', {'x': 1200}))
1049 self.assertTrue(match_str('x', {'x': 1200}))
1050 self.assertFalse(match_str('!x', {'x': 1200}))
1051 self.assertTrue(match_str('x', {'x': 0}))
1052 self.assertFalse(match_str('x>0', {'x': 0}))
1053 self.assertFalse(match_str('x>0', {}))
1054 self.assertTrue(match_str('x>?0', {}))
1055 self.assertTrue(match_str('x>1K', {'x': 1200}))
1056 self.assertFalse(match_str('x>2K', {'x': 1200}))
1057 self.assertTrue(match_str('x>=1200 & x < 1300', {'x': 1200}))
1058 self.assertFalse(match_str('x>=1100 & x < 1200', {'x': 1200}))
1059 self.assertFalse(match_str('y=a212', {'y': 'foobar42'}))
1060 self.assertTrue(match_str('y=foobar42', {'y': 'foobar42'}))
1061 self.assertFalse(match_str('y!=foobar42', {'y': 'foobar42'}))
1062 self.assertTrue(match_str('y!=foobar2', {'y': 'foobar42'}))
1063 self.assertFalse(match_str(
1064 'like_count > 100 & dislike_count <? 50 & description',
1065 {'like_count': 90, 'description': 'foo'}))
1066 self.assertTrue(match_str(
1067 'like_count > 100 & dislike_count <? 50 & description',
1068 {'like_count': 190, 'description': 'foo'}))
1069 self.assertFalse(match_str(
1070 'like_count > 100 & dislike_count <? 50 & description',
1071 {'like_count': 190, 'dislike_count': 60, 'description': 'foo'}))
1072 self.assertFalse(match_str(
1073 'like_count > 100 & dislike_count <? 50 & description',
1074 {'like_count': 190, 'dislike_count': 10}))
1075
1076 def test_parse_dfxp_time_expr(self):
1077 self.assertEqual(parse_dfxp_time_expr(None), None)
1078 self.assertEqual(parse_dfxp_time_expr(''), None)
1079 self.assertEqual(parse_dfxp_time_expr('0.1'), 0.1)
1080 self.assertEqual(parse_dfxp_time_expr('0.1s'), 0.1)
1081 self.assertEqual(parse_dfxp_time_expr('00:00:01'), 1.0)
1082 self.assertEqual(parse_dfxp_time_expr('00:00:01.100'), 1.1)
1083 self.assertEqual(parse_dfxp_time_expr('00:00:01:100'), 1.1)
1084
1085 def test_dfxp2srt(self):
1086 dfxp_data = '''<?xml version="1.0" encoding="UTF-8"?>
1087 <tt xmlns="http://www.w3.org/ns/ttml" xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter">
1088 <body>
1089 <div xml:lang="en">
1090 <p begin="0" end="1">The following line contains Chinese characters and special symbols</p>
1091 <p begin="1" end="2">第二行<br/>♪♪</p>
1092 <p begin="2" dur="1"><span>Third<br/>Line</span></p>
1093 <p begin="3" end="-1">Lines with invalid timestamps are ignored</p>
1094 <p begin="-1" end="-1">Ignore, two</p>
1095 <p begin="3" dur="-1">Ignored, three</p>
1096 </div>
1097 </body>
1098 </tt>'''.encode('utf-8')
1099 srt_data = '''1
1100 00:00:00,000 --> 00:00:01,000
1101 The following line contains Chinese characters and special symbols
1102
1103 2
1104 00:00:01,000 --> 00:00:02,000
1105 第二行
1106 ♪♪
1107
1108 3
1109 00:00:02,000 --> 00:00:03,000
1110 Third
1111 Line
1112
1113 '''
1114 self.assertEqual(dfxp2srt(dfxp_data), srt_data)
1115
1116 dfxp_data_no_default_namespace = '''<?xml version="1.0" encoding="UTF-8"?>
1117 <tt xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter">
1118 <body>
1119 <div xml:lang="en">
1120 <p begin="0" end="1">The first line</p>
1121 </div>
1122 </body>
1123 </tt>'''.encode('utf-8')
1124 srt_data = '''1
1125 00:00:00,000 --> 00:00:01,000
1126 The first line
1127
1128 '''
1129 self.assertEqual(dfxp2srt(dfxp_data_no_default_namespace), srt_data)
1130
1131 dfxp_data_with_style = '''<?xml version="1.0" encoding="utf-8"?>
1132 <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">
1133 <head>
1134 <styling>
1135 <style id="s2" style="s0" tts:color="cyan" tts:fontWeight="bold" />
1136 <style id="s1" style="s0" tts:color="yellow" tts:fontStyle="italic" />
1137 <style id="s3" style="s0" tts:color="lime" tts:textDecoration="underline" />
1138 <style id="s0" tts:backgroundColor="black" tts:fontStyle="normal" tts:fontSize="16" tts:fontFamily="sansSerif" tts:color="white" />
1139 </styling>
1140 </head>
1141 <body tts:textAlign="center" style="s0">
1142 <div>
1143 <p begin="00:00:02.08" id="p0" end="00:00:05.84">default style<span tts:color="red">custom style</span></p>
1144 <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>
1145 <p style="s3" begin="00:00:05.84" id="p1" end="00:00:09.56">line 3<br />part 3</p>
1146 <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>
1147 </div>
1148 </body>
1149 </tt>'''.encode('utf-8')
1150 srt_data = '''1
1151 00:00:02,080 --> 00:00:05,839
1152 <font color="white" face="sansSerif" size="16">default style<font color="red">custom style</font></font>
1153
1154 2
1155 00:00:02,080 --> 00:00:05,839
1156 <b><font color="cyan" face="sansSerif" size="16"><font color="lime">part 1
1157 </font>part 2</font></b>
1158
1159 3
1160 00:00:05,839 --> 00:00:09,560
1161 <u><font color="lime">line 3
1162 part 3</font></u>
1163
1164 4
1165 00:00:09,560 --> 00:00:12,359
1166 <i><u><font color="yellow"><font color="lime">inner
1167 </font>style</font></u></i>
1168
1169 '''
1170 self.assertEqual(dfxp2srt(dfxp_data_with_style), srt_data)
1171
1172 dfxp_data_non_utf8 = '''<?xml version="1.0" encoding="UTF-16"?>
1173 <tt xmlns="http://www.w3.org/ns/ttml" xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter">
1174 <body>
1175 <div xml:lang="en">
1176 <p begin="0" end="1">Line 1</p>
1177 <p begin="1" end="2">第二行</p>
1178 </div>
1179 </body>
1180 </tt>'''.encode('utf-16')
1181 srt_data = '''1
1182 00:00:00,000 --> 00:00:01,000
1183 Line 1
1184
1185 2
1186 00:00:01,000 --> 00:00:02,000
1187 第二行
1188
1189 '''
1190 self.assertEqual(dfxp2srt(dfxp_data_non_utf8), srt_data)
1191
1192 def test_cli_option(self):
1193 self.assertEqual(cli_option({'proxy': '127.0.0.1:3128'}, '--proxy', 'proxy'), ['--proxy', '127.0.0.1:3128'])
1194 self.assertEqual(cli_option({'proxy': None}, '--proxy', 'proxy'), [])
1195 self.assertEqual(cli_option({}, '--proxy', 'proxy'), [])
1196 self.assertEqual(cli_option({'retries': 10}, '--retries', 'retries'), ['--retries', '10'])
1197
1198 def test_cli_valueless_option(self):
1199 self.assertEqual(cli_valueless_option(
1200 {'downloader': 'external'}, '--external-downloader', 'downloader', 'external'), ['--external-downloader'])
1201 self.assertEqual(cli_valueless_option(
1202 {'downloader': 'internal'}, '--external-downloader', 'downloader', 'external'), [])
1203 self.assertEqual(cli_valueless_option(
1204 {'nocheckcertificate': True}, '--no-check-certificate', 'nocheckcertificate'), ['--no-check-certificate'])
1205 self.assertEqual(cli_valueless_option(
1206 {'nocheckcertificate': False}, '--no-check-certificate', 'nocheckcertificate'), [])
1207 self.assertEqual(cli_valueless_option(
1208 {'checkcertificate': True}, '--no-check-certificate', 'checkcertificate', False), [])
1209 self.assertEqual(cli_valueless_option(
1210 {'checkcertificate': False}, '--no-check-certificate', 'checkcertificate', False), ['--no-check-certificate'])
1211
1212 def test_cli_bool_option(self):
1213 self.assertEqual(
1214 cli_bool_option(
1215 {'nocheckcertificate': True}, '--no-check-certificate', 'nocheckcertificate'),
1216 ['--no-check-certificate', 'true'])
1217 self.assertEqual(
1218 cli_bool_option(
1219 {'nocheckcertificate': True}, '--no-check-certificate', 'nocheckcertificate', separator='='),
1220 ['--no-check-certificate=true'])
1221 self.assertEqual(
1222 cli_bool_option(
1223 {'nocheckcertificate': True}, '--check-certificate', 'nocheckcertificate', 'false', 'true'),
1224 ['--check-certificate', 'false'])
1225 self.assertEqual(
1226 cli_bool_option(
1227 {'nocheckcertificate': True}, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='),
1228 ['--check-certificate=false'])
1229 self.assertEqual(
1230 cli_bool_option(
1231 {'nocheckcertificate': False}, '--check-certificate', 'nocheckcertificate', 'false', 'true'),
1232 ['--check-certificate', 'true'])
1233 self.assertEqual(
1234 cli_bool_option(
1235 {'nocheckcertificate': False}, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='),
1236 ['--check-certificate=true'])
1237 self.assertEqual(
1238 cli_bool_option(
1239 {}, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='),
1240 [])
1241
1242 def test_ohdave_rsa_encrypt(self):
1243 N = 0xab86b6371b5318aaa1d3c9e612a9f1264f372323c8c0f19875b5fc3b3fd3afcc1e5bec527aa94bfa85bffc157e4245aebda05389a5357b75115ac94f074aefcd
1244 e = 65537
1245
1246 self.assertEqual(
1247 ohdave_rsa_encrypt(b'aa111222', e, N),
1248 '726664bd9a23fd0c70f9f1b84aab5e3905ce1e45a584e9cbcf9bcc7510338fc1986d6c599ff990d923aa43c51c0d9013cd572e13bc58f4ae48f2ed8c0b0ba881')
1249
1250 def test_pkcs1pad(self):
1251 data = [1, 2, 3]
1252 padded_data = pkcs1pad(data, 32)
1253 self.assertEqual(padded_data[:2], [0, 2])
1254 self.assertEqual(padded_data[28:], [0, 1, 2, 3])
1255
1256 self.assertRaises(ValueError, pkcs1pad, data, 8)
1257
1258 def test_encode_base_n(self):
1259 self.assertEqual(encode_base_n(0, 30), '0')
1260 self.assertEqual(encode_base_n(80, 30), '2k')
1261
1262 custom_table = '9876543210ZYXWVUTSRQPONMLKJIHGFEDCBA'
1263 self.assertEqual(encode_base_n(0, 30, custom_table), '9')
1264 self.assertEqual(encode_base_n(80, 30, custom_table), '7P')
1265
1266 self.assertRaises(ValueError, encode_base_n, 0, 70)
1267 self.assertRaises(ValueError, encode_base_n, 0, 60, custom_table)
1268
1269 def test_urshift(self):
1270 self.assertEqual(urshift(3, 1), 1)
1271 self.assertEqual(urshift(-3, 1), 2147483646)
1272
1273 def test_get_element_by_class(self):
1274 html = '''
1275 <span class="foo bar">nice</span>
1276 '''
1277
1278 self.assertEqual(get_element_by_class('foo', html), 'nice')
1279 self.assertEqual(get_element_by_class('no-such-class', html), None)
1280
1281 def test_get_element_by_attribute(self):
1282 html = '''
1283 <span class="foo bar">nice</span>
1284 '''
1285
1286 self.assertEqual(get_element_by_attribute('class', 'foo bar', html), 'nice')
1287 self.assertEqual(get_element_by_attribute('class', 'foo', html), None)
1288 self.assertEqual(get_element_by_attribute('class', 'no-such-foo', html), None)
1289
1290 html = '''
1291 <div itemprop="author" itemscope>foo</div>
1292 '''
1293
1294 self.assertEqual(get_element_by_attribute('itemprop', 'author', html), 'foo')
1295
1296 def test_get_elements_by_class(self):
1297 html = '''
1298 <span class="foo bar">nice</span><span class="foo bar">also nice</span>
1299 '''
1300
1301 self.assertEqual(get_elements_by_class('foo', html), ['nice', 'also nice'])
1302 self.assertEqual(get_elements_by_class('no-such-class', html), [])
1303
1304 def test_get_elements_by_attribute(self):
1305 html = '''
1306 <span class="foo bar">nice</span><span class="foo bar">also nice</span>
1307 '''
1308
1309 self.assertEqual(get_elements_by_attribute('class', 'foo bar', html), ['nice', 'also nice'])
1310 self.assertEqual(get_elements_by_attribute('class', 'foo', html), [])
1311 self.assertEqual(get_elements_by_attribute('class', 'no-such-foo', html), [])
1312
1313
1314 if __name__ == '__main__':
1315 unittest.main()