]> Raphaël G. Git Repositories - youtubedl/blob - test/test_utils.py
aa4569b819e368381a9ee100a6060e38ae0ce065
[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 ohdave_rsa_encrypt,
48 OnDemandPagedList,
49 orderedSet,
50 parse_age_limit,
51 parse_duration,
52 parse_filesize,
53 parse_count,
54 parse_iso8601,
55 pkcs1pad,
56 read_batch_urls,
57 sanitize_filename,
58 sanitize_path,
59 expand_path,
60 prepend_extension,
61 replace_extension,
62 remove_start,
63 remove_end,
64 remove_quotes,
65 shell_quote,
66 smuggle_url,
67 str_to_int,
68 strip_jsonp,
69 timeconvert,
70 unescapeHTML,
71 unified_strdate,
72 unified_timestamp,
73 unsmuggle_url,
74 uppercase_escape,
75 lowercase_escape,
76 url_basename,
77 base_url,
78 urljoin,
79 urlencode_postdata,
80 urshift,
81 update_url_query,
82 version_tuple,
83 xpath_with_ns,
84 xpath_element,
85 xpath_text,
86 xpath_attr,
87 render_table,
88 match_str,
89 parse_dfxp_time_expr,
90 dfxp2srt,
91 cli_option,
92 cli_valueless_option,
93 cli_bool_option,
94 parse_codecs,
95 )
96 from youtube_dl.compat import (
97 compat_chr,
98 compat_etree_fromstring,
99 compat_getenv,
100 compat_setenv,
101 compat_urlparse,
102 compat_parse_qs,
103 )
104
105
106 class TestUtil(unittest.TestCase):
107 def test_timeconvert(self):
108 self.assertTrue(timeconvert('') is None)
109 self.assertTrue(timeconvert('bougrg') is None)
110
111 def test_sanitize_filename(self):
112 self.assertEqual(sanitize_filename('abc'), 'abc')
113 self.assertEqual(sanitize_filename('abc_d-e'), 'abc_d-e')
114
115 self.assertEqual(sanitize_filename('123'), '123')
116
117 self.assertEqual('abc_de', sanitize_filename('abc/de'))
118 self.assertFalse('/' in sanitize_filename('abc/de///'))
119
120 self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de'))
121 self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|'))
122 self.assertEqual('yes no', sanitize_filename('yes? no'))
123 self.assertEqual('this - that', sanitize_filename('this: that'))
124
125 self.assertEqual(sanitize_filename('AT&T'), 'AT&T')
126 aumlaut = 'ä'
127 self.assertEqual(sanitize_filename(aumlaut), aumlaut)
128 tests = '\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430'
129 self.assertEqual(sanitize_filename(tests), tests)
130
131 self.assertEqual(
132 sanitize_filename('New World record at 0:12:34'),
133 'New World record at 0_12_34')
134
135 self.assertEqual(sanitize_filename('--gasdgf'), '_-gasdgf')
136 self.assertEqual(sanitize_filename('--gasdgf', is_id=True), '--gasdgf')
137 self.assertEqual(sanitize_filename('.gasdgf'), 'gasdgf')
138 self.assertEqual(sanitize_filename('.gasdgf', is_id=True), '.gasdgf')
139
140 forbidden = '"\0\\/'
141 for fc in forbidden:
142 for fbc in forbidden:
143 self.assertTrue(fbc not in sanitize_filename(fc))
144
145 def test_sanitize_filename_restricted(self):
146 self.assertEqual(sanitize_filename('abc', restricted=True), 'abc')
147 self.assertEqual(sanitize_filename('abc_d-e', restricted=True), 'abc_d-e')
148
149 self.assertEqual(sanitize_filename('123', restricted=True), '123')
150
151 self.assertEqual('abc_de', sanitize_filename('abc/de', restricted=True))
152 self.assertFalse('/' in sanitize_filename('abc/de///', restricted=True))
153
154 self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de', restricted=True))
155 self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|', restricted=True))
156 self.assertEqual('yes_no', sanitize_filename('yes? no', restricted=True))
157 self.assertEqual('this_-_that', sanitize_filename('this: that', restricted=True))
158
159 tests = 'aäb\u4e2d\u56fd\u7684c'
160 self.assertEqual(sanitize_filename(tests, restricted=True), 'aab_c')
161 self.assertTrue(sanitize_filename('\xf6', restricted=True) != '') # No empty filename
162
163 forbidden = '"\0\\/&!: \'\t\n()[]{}$;`^,#'
164 for fc in forbidden:
165 for fbc in forbidden:
166 self.assertTrue(fbc not in sanitize_filename(fc, restricted=True))
167
168 # Handle a common case more neatly
169 self.assertEqual(sanitize_filename('\u5927\u58f0\u5e26 - Song', restricted=True), 'Song')
170 self.assertEqual(sanitize_filename('\u603b\u7edf: Speech', restricted=True), 'Speech')
171 # .. but make sure the file name is never empty
172 self.assertTrue(sanitize_filename('-', restricted=True) != '')
173 self.assertTrue(sanitize_filename(':', restricted=True) != '')
174
175 self.assertEqual(sanitize_filename(
176 'ÂÃÄÀÁÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖŐØŒÙÚÛÜŰÝÞßàáâãäåæçèéêëìíîïðñòóôõöőøœùúûüűýþÿ', restricted=True),
177 'AAAAAAAECEEEEIIIIDNOOOOOOOOEUUUUUYPssaaaaaaaeceeeeiiiionooooooooeuuuuuypy')
178
179 def test_sanitize_ids(self):
180 self.assertEqual(sanitize_filename('_n_cd26wFpw', is_id=True), '_n_cd26wFpw')
181 self.assertEqual(sanitize_filename('_BD_eEpuzXw', is_id=True), '_BD_eEpuzXw')
182 self.assertEqual(sanitize_filename('N0Y__7-UOdI', is_id=True), 'N0Y__7-UOdI')
183
184 def test_sanitize_path(self):
185 if sys.platform != 'win32':
186 return
187
188 self.assertEqual(sanitize_path('abc'), 'abc')
189 self.assertEqual(sanitize_path('abc/def'), 'abc\\def')
190 self.assertEqual(sanitize_path('abc\\def'), 'abc\\def')
191 self.assertEqual(sanitize_path('abc|def'), 'abc#def')
192 self.assertEqual(sanitize_path('<>:"|?*'), '#######')
193 self.assertEqual(sanitize_path('C:/abc/def'), 'C:\\abc\\def')
194 self.assertEqual(sanitize_path('C?:/abc/def'), 'C##\\abc\\def')
195
196 self.assertEqual(sanitize_path('\\\\?\\UNC\\ComputerName\\abc'), '\\\\?\\UNC\\ComputerName\\abc')
197 self.assertEqual(sanitize_path('\\\\?\\UNC/ComputerName/abc'), '\\\\?\\UNC\\ComputerName\\abc')
198
199 self.assertEqual(sanitize_path('\\\\?\\C:\\abc'), '\\\\?\\C:\\abc')
200 self.assertEqual(sanitize_path('\\\\?\\C:/abc'), '\\\\?\\C:\\abc')
201 self.assertEqual(sanitize_path('\\\\?\\C:\\ab?c\\de:f'), '\\\\?\\C:\\ab#c\\de#f')
202 self.assertEqual(sanitize_path('\\\\?\\C:\\abc'), '\\\\?\\C:\\abc')
203
204 self.assertEqual(
205 sanitize_path('youtube/%(uploader)s/%(autonumber)s-%(title)s-%(upload_date)s.%(ext)s'),
206 'youtube\\%(uploader)s\\%(autonumber)s-%(title)s-%(upload_date)s.%(ext)s')
207
208 self.assertEqual(
209 sanitize_path('youtube/TheWreckingYard ./00001-Not bad, Especially for Free! (1987 Yamaha 700)-20141116.mp4.part'),
210 'youtube\\TheWreckingYard #\\00001-Not bad, Especially for Free! (1987 Yamaha 700)-20141116.mp4.part')
211 self.assertEqual(sanitize_path('abc/def...'), 'abc\\def..#')
212 self.assertEqual(sanitize_path('abc.../def'), 'abc..#\\def')
213 self.assertEqual(sanitize_path('abc.../def...'), 'abc..#\\def..#')
214
215 self.assertEqual(sanitize_path('../abc'), '..\\abc')
216 self.assertEqual(sanitize_path('../../abc'), '..\\..\\abc')
217 self.assertEqual(sanitize_path('./abc'), 'abc')
218 self.assertEqual(sanitize_path('./../abc'), '..\\abc')
219
220 def test_expand_path(self):
221 def env(var):
222 return '%{0}%'.format(var) if sys.platform == 'win32' else '${0}'.format(var)
223
224 compat_setenv('YOUTUBE_DL_EXPATH_PATH', 'expanded')
225 self.assertEqual(expand_path(env('YOUTUBE_DL_EXPATH_PATH')), 'expanded')
226 self.assertEqual(expand_path(env('HOME')), compat_getenv('HOME'))
227 self.assertEqual(expand_path('~'), compat_getenv('HOME'))
228 self.assertEqual(
229 expand_path('~/%s' % env('YOUTUBE_DL_EXPATH_PATH')),
230 '%s/expanded' % compat_getenv('HOME'))
231
232 def test_prepend_extension(self):
233 self.assertEqual(prepend_extension('abc.ext', 'temp'), 'abc.temp.ext')
234 self.assertEqual(prepend_extension('abc.ext', 'temp', 'ext'), 'abc.temp.ext')
235 self.assertEqual(prepend_extension('abc.unexpected_ext', 'temp', 'ext'), 'abc.unexpected_ext.temp')
236 self.assertEqual(prepend_extension('abc', 'temp'), 'abc.temp')
237 self.assertEqual(prepend_extension('.abc', 'temp'), '.abc.temp')
238 self.assertEqual(prepend_extension('.abc.ext', 'temp'), '.abc.temp.ext')
239
240 def test_replace_extension(self):
241 self.assertEqual(replace_extension('abc.ext', 'temp'), 'abc.temp')
242 self.assertEqual(replace_extension('abc.ext', 'temp', 'ext'), 'abc.temp')
243 self.assertEqual(replace_extension('abc.unexpected_ext', 'temp', 'ext'), 'abc.unexpected_ext.temp')
244 self.assertEqual(replace_extension('abc', 'temp'), 'abc.temp')
245 self.assertEqual(replace_extension('.abc', 'temp'), '.abc.temp')
246 self.assertEqual(replace_extension('.abc.ext', 'temp'), '.abc.temp')
247
248 def test_remove_start(self):
249 self.assertEqual(remove_start(None, 'A - '), None)
250 self.assertEqual(remove_start('A - B', 'A - '), 'B')
251 self.assertEqual(remove_start('B - A', 'A - '), 'B - A')
252
253 def test_remove_end(self):
254 self.assertEqual(remove_end(None, ' - B'), None)
255 self.assertEqual(remove_end('A - B', ' - B'), 'A')
256 self.assertEqual(remove_end('B - A', ' - B'), 'B - A')
257
258 def test_remove_quotes(self):
259 self.assertEqual(remove_quotes(None), None)
260 self.assertEqual(remove_quotes('"'), '"')
261 self.assertEqual(remove_quotes("'"), "'")
262 self.assertEqual(remove_quotes(';'), ';')
263 self.assertEqual(remove_quotes('";'), '";')
264 self.assertEqual(remove_quotes('""'), '')
265 self.assertEqual(remove_quotes('";"'), ';')
266
267 def test_ordered_set(self):
268 self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7])
269 self.assertEqual(orderedSet([]), [])
270 self.assertEqual(orderedSet([1]), [1])
271 # keep the list ordered
272 self.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1])
273
274 def test_unescape_html(self):
275 self.assertEqual(unescapeHTML('%20;'), '%20;')
276 self.assertEqual(unescapeHTML('&#x2F;'), '/')
277 self.assertEqual(unescapeHTML('&#47;'), '/')
278 self.assertEqual(unescapeHTML('&eacute;'), 'é')
279 self.assertEqual(unescapeHTML('&#2013266066;'), '&#2013266066;')
280 # HTML5 entities
281 self.assertEqual(unescapeHTML('&period;&apos;'), '.\'')
282
283 def test_date_from_str(self):
284 self.assertEqual(date_from_str('yesterday'), date_from_str('now-1day'))
285 self.assertEqual(date_from_str('now+7day'), date_from_str('now+1week'))
286 self.assertEqual(date_from_str('now+14day'), date_from_str('now+2week'))
287 self.assertEqual(date_from_str('now+365day'), date_from_str('now+1year'))
288 self.assertEqual(date_from_str('now+30day'), date_from_str('now+1month'))
289
290 def test_daterange(self):
291 _20century = DateRange("19000101", "20000101")
292 self.assertFalse("17890714" in _20century)
293 _ac = DateRange("00010101")
294 self.assertTrue("19690721" in _ac)
295 _firstmilenium = DateRange(end="10000101")
296 self.assertTrue("07110427" in _firstmilenium)
297
298 def test_unified_dates(self):
299 self.assertEqual(unified_strdate('December 21, 2010'), '20101221')
300 self.assertEqual(unified_strdate('8/7/2009'), '20090708')
301 self.assertEqual(unified_strdate('Dec 14, 2012'), '20121214')
302 self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
303 self.assertEqual(unified_strdate('1968 12 10'), '19681210')
304 self.assertEqual(unified_strdate('1968-12-10'), '19681210')
305 self.assertEqual(unified_strdate('28/01/2014 21:00:00 +0100'), '20140128')
306 self.assertEqual(
307 unified_strdate('11/26/2014 11:30:00 AM PST', day_first=False),
308 '20141126')
309 self.assertEqual(
310 unified_strdate('2/2/2015 6:47:40 PM', day_first=False),
311 '20150202')
312 self.assertEqual(unified_strdate('Feb 14th 2016 5:45PM'), '20160214')
313 self.assertEqual(unified_strdate('25-09-2014'), '20140925')
314 self.assertEqual(unified_strdate('27.02.2016 17:30'), '20160227')
315 self.assertEqual(unified_strdate('UNKNOWN DATE FORMAT'), None)
316 self.assertEqual(unified_strdate('Feb 7, 2016 at 6:35 pm'), '20160207')
317 self.assertEqual(unified_strdate('July 15th, 2013'), '20130715')
318 self.assertEqual(unified_strdate('September 1st, 2013'), '20130901')
319 self.assertEqual(unified_strdate('Sep 2nd, 2013'), '20130902')
320
321 def test_unified_timestamps(self):
322 self.assertEqual(unified_timestamp('December 21, 2010'), 1292889600)
323 self.assertEqual(unified_timestamp('8/7/2009'), 1247011200)
324 self.assertEqual(unified_timestamp('Dec 14, 2012'), 1355443200)
325 self.assertEqual(unified_timestamp('2012/10/11 01:56:38 +0000'), 1349920598)
326 self.assertEqual(unified_timestamp('1968 12 10'), -33436800)
327 self.assertEqual(unified_timestamp('1968-12-10'), -33436800)
328 self.assertEqual(unified_timestamp('28/01/2014 21:00:00 +0100'), 1390939200)
329 self.assertEqual(
330 unified_timestamp('11/26/2014 11:30:00 AM PST', day_first=False),
331 1417001400)
332 self.assertEqual(
333 unified_timestamp('2/2/2015 6:47:40 PM', day_first=False),
334 1422902860)
335 self.assertEqual(unified_timestamp('Feb 14th 2016 5:45PM'), 1455471900)
336 self.assertEqual(unified_timestamp('25-09-2014'), 1411603200)
337 self.assertEqual(unified_timestamp('27.02.2016 17:30'), 1456594200)
338 self.assertEqual(unified_timestamp('UNKNOWN DATE FORMAT'), None)
339 self.assertEqual(unified_timestamp('May 16, 2016 11:15 PM'), 1463440500)
340 self.assertEqual(unified_timestamp('Feb 7, 2016 at 6:35 pm'), 1454870100)
341
342 def test_determine_ext(self):
343 self.assertEqual(determine_ext('http://example.com/foo/bar.mp4/?download'), 'mp4')
344 self.assertEqual(determine_ext('http://example.com/foo/bar/?download', None), None)
345 self.assertEqual(determine_ext('http://example.com/foo/bar.nonext/?download', None), None)
346 self.assertEqual(determine_ext('http://example.com/foo/bar/mp4?download', None), None)
347 self.assertEqual(determine_ext('http://example.com/foo/bar.m3u8//?download'), 'm3u8')
348
349 def test_find_xpath_attr(self):
350 testxml = '''<root>
351 <node/>
352 <node x="a"/>
353 <node x="a" y="c" />
354 <node x="b" y="d" />
355 <node x="" />
356 </root>'''
357 doc = compat_etree_fromstring(testxml)
358
359 self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n'), None)
360 self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n', 'v'), None)
361 self.assertEqual(find_xpath_attr(doc, './/node', 'n'), None)
362 self.assertEqual(find_xpath_attr(doc, './/node', 'n', 'v'), None)
363 self.assertEqual(find_xpath_attr(doc, './/node', 'x'), doc[1])
364 self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'a'), doc[1])
365 self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'b'), doc[3])
366 self.assertEqual(find_xpath_attr(doc, './/node', 'y'), doc[2])
367 self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'c'), doc[2])
368 self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'd'), doc[3])
369 self.assertEqual(find_xpath_attr(doc, './/node', 'x', ''), doc[4])
370
371 def test_xpath_with_ns(self):
372 testxml = '''<root xmlns:media="http://example.com/">
373 <media:song>
374 <media:author>The Author</media:author>
375 <url>http://server.com/download.mp3</url>
376 </media:song>
377 </root>'''
378 doc = compat_etree_fromstring(testxml)
379 find = lambda p: doc.find(xpath_with_ns(p, {'media': 'http://example.com/'}))
380 self.assertTrue(find('media:song') is not None)
381 self.assertEqual(find('media:song/media:author').text, 'The Author')
382 self.assertEqual(find('media:song/url').text, 'http://server.com/download.mp3')
383
384 def test_xpath_element(self):
385 doc = xml.etree.ElementTree.Element('root')
386 div = xml.etree.ElementTree.SubElement(doc, 'div')
387 p = xml.etree.ElementTree.SubElement(div, 'p')
388 p.text = 'Foo'
389 self.assertEqual(xpath_element(doc, 'div/p'), p)
390 self.assertEqual(xpath_element(doc, ['div/p']), p)
391 self.assertEqual(xpath_element(doc, ['div/bar', 'div/p']), p)
392 self.assertEqual(xpath_element(doc, 'div/bar', default='default'), 'default')
393 self.assertEqual(xpath_element(doc, ['div/bar'], default='default'), 'default')
394 self.assertTrue(xpath_element(doc, 'div/bar') is None)
395 self.assertTrue(xpath_element(doc, ['div/bar']) is None)
396 self.assertTrue(xpath_element(doc, ['div/bar'], 'div/baz') is None)
397 self.assertRaises(ExtractorError, xpath_element, doc, 'div/bar', fatal=True)
398 self.assertRaises(ExtractorError, xpath_element, doc, ['div/bar'], fatal=True)
399 self.assertRaises(ExtractorError, xpath_element, doc, ['div/bar', 'div/baz'], fatal=True)
400
401 def test_xpath_text(self):
402 testxml = '''<root>
403 <div>
404 <p>Foo</p>
405 </div>
406 </root>'''
407 doc = compat_etree_fromstring(testxml)
408 self.assertEqual(xpath_text(doc, 'div/p'), 'Foo')
409 self.assertEqual(xpath_text(doc, 'div/bar', default='default'), 'default')
410 self.assertTrue(xpath_text(doc, 'div/bar') is None)
411 self.assertRaises(ExtractorError, xpath_text, doc, 'div/bar', fatal=True)
412
413 def test_xpath_attr(self):
414 testxml = '''<root>
415 <div>
416 <p x="a">Foo</p>
417 </div>
418 </root>'''
419 doc = compat_etree_fromstring(testxml)
420 self.assertEqual(xpath_attr(doc, 'div/p', 'x'), 'a')
421 self.assertEqual(xpath_attr(doc, 'div/bar', 'x'), None)
422 self.assertEqual(xpath_attr(doc, 'div/p', 'y'), None)
423 self.assertEqual(xpath_attr(doc, 'div/bar', 'x', default='default'), 'default')
424 self.assertEqual(xpath_attr(doc, 'div/p', 'y', default='default'), 'default')
425 self.assertRaises(ExtractorError, xpath_attr, doc, 'div/bar', 'x', fatal=True)
426 self.assertRaises(ExtractorError, xpath_attr, doc, 'div/p', 'y', fatal=True)
427
428 def test_smuggle_url(self):
429 data = {"ö": "ö", "abc": [3]}
430 url = 'https://foo.bar/baz?x=y#a'
431 smug_url = smuggle_url(url, data)
432 unsmug_url, unsmug_data = unsmuggle_url(smug_url)
433 self.assertEqual(url, unsmug_url)
434 self.assertEqual(data, unsmug_data)
435
436 res_url, res_data = unsmuggle_url(url)
437 self.assertEqual(res_url, url)
438 self.assertEqual(res_data, None)
439
440 smug_url = smuggle_url(url, {'a': 'b'})
441 smug_smug_url = smuggle_url(smug_url, {'c': 'd'})
442 res_url, res_data = unsmuggle_url(smug_smug_url)
443 self.assertEqual(res_url, url)
444 self.assertEqual(res_data, {'a': 'b', 'c': 'd'})
445
446 def test_shell_quote(self):
447 args = ['ffmpeg', '-i', encodeFilename('ñ€ß\'.mp4')]
448 self.assertEqual(shell_quote(args), """ffmpeg -i 'ñ€ß'"'"'.mp4'""")
449
450 def test_str_to_int(self):
451 self.assertEqual(str_to_int('123,456'), 123456)
452 self.assertEqual(str_to_int('123.456'), 123456)
453
454 def test_url_basename(self):
455 self.assertEqual(url_basename('http://foo.de/'), '')
456 self.assertEqual(url_basename('http://foo.de/bar/baz'), 'baz')
457 self.assertEqual(url_basename('http://foo.de/bar/baz?x=y'), 'baz')
458 self.assertEqual(url_basename('http://foo.de/bar/baz#x=y'), 'baz')
459 self.assertEqual(url_basename('http://foo.de/bar/baz/'), 'baz')
460 self.assertEqual(
461 url_basename('http://media.w3.org/2010/05/sintel/trailer.mp4'),
462 'trailer.mp4')
463
464 def test_base_url(self):
465 self.assertEqual(base_url('http://foo.de/'), 'http://foo.de/')
466 self.assertEqual(base_url('http://foo.de/bar'), 'http://foo.de/')
467 self.assertEqual(base_url('http://foo.de/bar/'), 'http://foo.de/bar/')
468 self.assertEqual(base_url('http://foo.de/bar/baz'), 'http://foo.de/bar/')
469 self.assertEqual(base_url('http://foo.de/bar/baz?x=z/x/c'), 'http://foo.de/bar/')
470
471 def test_urljoin(self):
472 self.assertEqual(urljoin('http://foo.de/', '/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
473 self.assertEqual(urljoin(b'http://foo.de/', '/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
474 self.assertEqual(urljoin('http://foo.de/', b'/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
475 self.assertEqual(urljoin(b'http://foo.de/', b'/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
476 self.assertEqual(urljoin('//foo.de/', '/a/b/c.txt'), '//foo.de/a/b/c.txt')
477 self.assertEqual(urljoin('http://foo.de/', 'a/b/c.txt'), 'http://foo.de/a/b/c.txt')
478 self.assertEqual(urljoin('http://foo.de', '/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
479 self.assertEqual(urljoin('http://foo.de', 'a/b/c.txt'), 'http://foo.de/a/b/c.txt')
480 self.assertEqual(urljoin('http://foo.de/', 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
481 self.assertEqual(urljoin('http://foo.de/', '//foo.de/a/b/c.txt'), '//foo.de/a/b/c.txt')
482 self.assertEqual(urljoin(None, 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
483 self.assertEqual(urljoin(None, '//foo.de/a/b/c.txt'), '//foo.de/a/b/c.txt')
484 self.assertEqual(urljoin('', 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
485 self.assertEqual(urljoin(['foobar'], 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
486 self.assertEqual(urljoin('http://foo.de/', None), None)
487 self.assertEqual(urljoin('http://foo.de/', ''), None)
488 self.assertEqual(urljoin('http://foo.de/', ['foobar']), None)
489 self.assertEqual(urljoin('http://foo.de/a/b/c.txt', '.././../d.txt'), 'http://foo.de/d.txt')
490
491 def test_parse_age_limit(self):
492 self.assertEqual(parse_age_limit(None), None)
493 self.assertEqual(parse_age_limit(False), None)
494 self.assertEqual(parse_age_limit('invalid'), None)
495 self.assertEqual(parse_age_limit(0), 0)
496 self.assertEqual(parse_age_limit(18), 18)
497 self.assertEqual(parse_age_limit(21), 21)
498 self.assertEqual(parse_age_limit(22), None)
499 self.assertEqual(parse_age_limit('18'), 18)
500 self.assertEqual(parse_age_limit('18+'), 18)
501 self.assertEqual(parse_age_limit('PG-13'), 13)
502 self.assertEqual(parse_age_limit('TV-14'), 14)
503 self.assertEqual(parse_age_limit('TV-MA'), 17)
504
505 def test_parse_duration(self):
506 self.assertEqual(parse_duration(None), None)
507 self.assertEqual(parse_duration(False), None)
508 self.assertEqual(parse_duration('invalid'), None)
509 self.assertEqual(parse_duration('1'), 1)
510 self.assertEqual(parse_duration('1337:12'), 80232)
511 self.assertEqual(parse_duration('9:12:43'), 33163)
512 self.assertEqual(parse_duration('12:00'), 720)
513 self.assertEqual(parse_duration('00:01:01'), 61)
514 self.assertEqual(parse_duration('x:y'), None)
515 self.assertEqual(parse_duration('3h11m53s'), 11513)
516 self.assertEqual(parse_duration('3h 11m 53s'), 11513)
517 self.assertEqual(parse_duration('3 hours 11 minutes 53 seconds'), 11513)
518 self.assertEqual(parse_duration('3 hours 11 mins 53 secs'), 11513)
519 self.assertEqual(parse_duration('62m45s'), 3765)
520 self.assertEqual(parse_duration('6m59s'), 419)
521 self.assertEqual(parse_duration('49s'), 49)
522 self.assertEqual(parse_duration('0h0m0s'), 0)
523 self.assertEqual(parse_duration('0m0s'), 0)
524 self.assertEqual(parse_duration('0s'), 0)
525 self.assertEqual(parse_duration('01:02:03.05'), 3723.05)
526 self.assertEqual(parse_duration('T30M38S'), 1838)
527 self.assertEqual(parse_duration('5 s'), 5)
528 self.assertEqual(parse_duration('3 min'), 180)
529 self.assertEqual(parse_duration('2.5 hours'), 9000)
530 self.assertEqual(parse_duration('02:03:04'), 7384)
531 self.assertEqual(parse_duration('01:02:03:04'), 93784)
532 self.assertEqual(parse_duration('1 hour 3 minutes'), 3780)
533 self.assertEqual(parse_duration('87 Min.'), 5220)
534 self.assertEqual(parse_duration('PT1H0.040S'), 3600.04)
535 self.assertEqual(parse_duration('PT00H03M30SZ'), 210)
536
537 def test_fix_xml_ampersands(self):
538 self.assertEqual(
539 fix_xml_ampersands('"&x=y&z=a'), '"&amp;x=y&amp;z=a')
540 self.assertEqual(
541 fix_xml_ampersands('"&amp;x=y&wrong;&z=a'),
542 '"&amp;x=y&amp;wrong;&amp;z=a')
543 self.assertEqual(
544 fix_xml_ampersands('&amp;&apos;&gt;&lt;&quot;'),
545 '&amp;&apos;&gt;&lt;&quot;')
546 self.assertEqual(
547 fix_xml_ampersands('&#1234;&#x1abC;'), '&#1234;&#x1abC;')
548 self.assertEqual(fix_xml_ampersands('&#&#'), '&amp;#&amp;#')
549
550 def test_paged_list(self):
551 def testPL(size, pagesize, sliceargs, expected):
552 def get_page(pagenum):
553 firstid = pagenum * pagesize
554 upto = min(size, pagenum * pagesize + pagesize)
555 for i in range(firstid, upto):
556 yield i
557
558 pl = OnDemandPagedList(get_page, pagesize)
559 got = pl.getslice(*sliceargs)
560 self.assertEqual(got, expected)
561
562 iapl = InAdvancePagedList(get_page, size // pagesize + 1, pagesize)
563 got = iapl.getslice(*sliceargs)
564 self.assertEqual(got, expected)
565
566 testPL(5, 2, (), [0, 1, 2, 3, 4])
567 testPL(5, 2, (1,), [1, 2, 3, 4])
568 testPL(5, 2, (2,), [2, 3, 4])
569 testPL(5, 2, (4,), [4])
570 testPL(5, 2, (0, 3), [0, 1, 2])
571 testPL(5, 2, (1, 4), [1, 2, 3])
572 testPL(5, 2, (2, 99), [2, 3, 4])
573 testPL(5, 2, (20, 99), [])
574
575 def test_read_batch_urls(self):
576 f = io.StringIO('''\xef\xbb\xbf foo
577 bar\r
578 baz
579 # More after this line\r
580 ; or after this
581 bam''')
582 self.assertEqual(read_batch_urls(f), ['foo', 'bar', 'baz', 'bam'])
583
584 def test_urlencode_postdata(self):
585 data = urlencode_postdata({'username': 'foo@bar.com', 'password': '1234'})
586 self.assertTrue(isinstance(data, bytes))
587
588 def test_update_url_query(self):
589 def query_dict(url):
590 return compat_parse_qs(compat_urlparse.urlparse(url).query)
591 self.assertEqual(query_dict(update_url_query(
592 'http://example.com/path', {'quality': ['HD'], 'format': ['mp4']})),
593 query_dict('http://example.com/path?quality=HD&format=mp4'))
594 self.assertEqual(query_dict(update_url_query(
595 'http://example.com/path', {'system': ['LINUX', 'WINDOWS']})),
596 query_dict('http://example.com/path?system=LINUX&system=WINDOWS'))
597 self.assertEqual(query_dict(update_url_query(
598 'http://example.com/path', {'fields': 'id,formats,subtitles'})),
599 query_dict('http://example.com/path?fields=id,formats,subtitles'))
600 self.assertEqual(query_dict(update_url_query(
601 'http://example.com/path', {'fields': ('id,formats,subtitles', 'thumbnails')})),
602 query_dict('http://example.com/path?fields=id,formats,subtitles&fields=thumbnails'))
603 self.assertEqual(query_dict(update_url_query(
604 'http://example.com/path?manifest=f4m', {'manifest': []})),
605 query_dict('http://example.com/path'))
606 self.assertEqual(query_dict(update_url_query(
607 'http://example.com/path?system=LINUX&system=WINDOWS', {'system': 'LINUX'})),
608 query_dict('http://example.com/path?system=LINUX'))
609 self.assertEqual(query_dict(update_url_query(
610 'http://example.com/path', {'fields': b'id,formats,subtitles'})),
611 query_dict('http://example.com/path?fields=id,formats,subtitles'))
612 self.assertEqual(query_dict(update_url_query(
613 'http://example.com/path', {'width': 1080, 'height': 720})),
614 query_dict('http://example.com/path?width=1080&height=720'))
615 self.assertEqual(query_dict(update_url_query(
616 'http://example.com/path', {'bitrate': 5020.43})),
617 query_dict('http://example.com/path?bitrate=5020.43'))
618 self.assertEqual(query_dict(update_url_query(
619 'http://example.com/path', {'test': '第二行тест'})),
620 query_dict('http://example.com/path?test=%E7%AC%AC%E4%BA%8C%E8%A1%8C%D1%82%D0%B5%D1%81%D1%82'))
621
622 def test_dict_get(self):
623 FALSE_VALUES = {
624 'none': None,
625 'false': False,
626 'zero': 0,
627 'empty_string': '',
628 'empty_list': [],
629 }
630 d = FALSE_VALUES.copy()
631 d['a'] = 42
632 self.assertEqual(dict_get(d, 'a'), 42)
633 self.assertEqual(dict_get(d, 'b'), None)
634 self.assertEqual(dict_get(d, 'b', 42), 42)
635 self.assertEqual(dict_get(d, ('a', )), 42)
636 self.assertEqual(dict_get(d, ('b', 'a', )), 42)
637 self.assertEqual(dict_get(d, ('b', 'c', 'a', 'd', )), 42)
638 self.assertEqual(dict_get(d, ('b', 'c', )), None)
639 self.assertEqual(dict_get(d, ('b', 'c', ), 42), 42)
640 for key, false_value in FALSE_VALUES.items():
641 self.assertEqual(dict_get(d, ('b', 'c', key, )), None)
642 self.assertEqual(dict_get(d, ('b', 'c', key, ), skip_false_values=False), false_value)
643
644 def test_encode_compat_str(self):
645 self.assertEqual(encode_compat_str(b'\xd1\x82\xd0\xb5\xd1\x81\xd1\x82', 'utf-8'), 'тест')
646 self.assertEqual(encode_compat_str('тест', 'utf-8'), 'тест')
647
648 def test_parse_iso8601(self):
649 self.assertEqual(parse_iso8601('2014-03-23T23:04:26+0100'), 1395612266)
650 self.assertEqual(parse_iso8601('2014-03-23T22:04:26+0000'), 1395612266)
651 self.assertEqual(parse_iso8601('2014-03-23T22:04:26Z'), 1395612266)
652 self.assertEqual(parse_iso8601('2014-03-23T22:04:26.1234Z'), 1395612266)
653 self.assertEqual(parse_iso8601('2015-09-29T08:27:31.727'), 1443515251)
654 self.assertEqual(parse_iso8601('2015-09-29T08-27-31.727'), None)
655
656 def test_strip_jsonp(self):
657 stripped = strip_jsonp('cb ([ {"id":"532cb",\n\n\n"x":\n3}\n]\n);')
658 d = json.loads(stripped)
659 self.assertEqual(d, [{"id": "532cb", "x": 3}])
660
661 stripped = strip_jsonp('parseMetadata({"STATUS":"OK"})\n\n\n//epc')
662 d = json.loads(stripped)
663 self.assertEqual(d, {'STATUS': 'OK'})
664
665 stripped = strip_jsonp('ps.embedHandler({"status": "success"});')
666 d = json.loads(stripped)
667 self.assertEqual(d, {'status': 'success'})
668
669 def test_uppercase_escape(self):
670 self.assertEqual(uppercase_escape('aä'), 'aä')
671 self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐')
672
673 def test_lowercase_escape(self):
674 self.assertEqual(lowercase_escape('aä'), 'aä')
675 self.assertEqual(lowercase_escape('\\u0026'), '&')
676
677 def test_limit_length(self):
678 self.assertEqual(limit_length(None, 12), None)
679 self.assertEqual(limit_length('foo', 12), 'foo')
680 self.assertTrue(
681 limit_length('foo bar baz asd', 12).startswith('foo bar'))
682 self.assertTrue('...' in limit_length('foo bar baz asd', 12))
683
684 def test_mimetype2ext(self):
685 self.assertEqual(mimetype2ext(None), None)
686 self.assertEqual(mimetype2ext('video/x-flv'), 'flv')
687 self.assertEqual(mimetype2ext('application/x-mpegURL'), 'm3u8')
688 self.assertEqual(mimetype2ext('text/vtt'), 'vtt')
689 self.assertEqual(mimetype2ext('text/vtt;charset=utf-8'), 'vtt')
690 self.assertEqual(mimetype2ext('text/html; charset=utf-8'), 'html')
691
692 def test_month_by_name(self):
693 self.assertEqual(month_by_name(None), None)
694 self.assertEqual(month_by_name('December', 'en'), 12)
695 self.assertEqual(month_by_name('décembre', 'fr'), 12)
696 self.assertEqual(month_by_name('December'), 12)
697 self.assertEqual(month_by_name('décembre'), None)
698 self.assertEqual(month_by_name('Unknown', 'unknown'), None)
699
700 def test_parse_codecs(self):
701 self.assertEqual(parse_codecs(''), {})
702 self.assertEqual(parse_codecs('avc1.77.30, mp4a.40.2'), {
703 'vcodec': 'avc1.77.30',
704 'acodec': 'mp4a.40.2',
705 })
706 self.assertEqual(parse_codecs('mp4a.40.2'), {
707 'vcodec': 'none',
708 'acodec': 'mp4a.40.2',
709 })
710 self.assertEqual(parse_codecs('mp4a.40.5,avc1.42001e'), {
711 'vcodec': 'avc1.42001e',
712 'acodec': 'mp4a.40.5',
713 })
714 self.assertEqual(parse_codecs('avc3.640028'), {
715 'vcodec': 'avc3.640028',
716 'acodec': 'none',
717 })
718 self.assertEqual(parse_codecs(', h264,,newcodec,aac'), {
719 'vcodec': 'h264',
720 'acodec': 'aac',
721 })
722
723 def test_escape_rfc3986(self):
724 reserved = "!*'();:@&=+$,/?#[]"
725 unreserved = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_.~'
726 self.assertEqual(escape_rfc3986(reserved), reserved)
727 self.assertEqual(escape_rfc3986(unreserved), unreserved)
728 self.assertEqual(escape_rfc3986('тест'), '%D1%82%D0%B5%D1%81%D1%82')
729 self.assertEqual(escape_rfc3986('%D1%82%D0%B5%D1%81%D1%82'), '%D1%82%D0%B5%D1%81%D1%82')
730 self.assertEqual(escape_rfc3986('foo bar'), 'foo%20bar')
731 self.assertEqual(escape_rfc3986('foo%20bar'), 'foo%20bar')
732
733 def test_escape_url(self):
734 self.assertEqual(
735 escape_url('http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavré_FD.mp4'),
736 'http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavre%CC%81_FD.mp4'
737 )
738 self.assertEqual(
739 escape_url('http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erklärt/Das-Erste/Video?documentId=22673108&bcastId=5290'),
740 'http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erkl%C3%A4rt/Das-Erste/Video?documentId=22673108&bcastId=5290'
741 )
742 self.assertEqual(
743 escape_url('http://тест.рф/фрагмент'),
744 'http://xn--e1aybc.xn--p1ai/%D1%84%D1%80%D0%B0%D0%B3%D0%BC%D0%B5%D0%BD%D1%82'
745 )
746 self.assertEqual(
747 escape_url('http://тест.рф/абв?абв=абв#абв'),
748 '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'
749 )
750 self.assertEqual(escape_url('http://vimeo.com/56015672#at=0'), 'http://vimeo.com/56015672#at=0')
751
752 def test_js_to_json_realworld(self):
753 inp = '''{
754 'clip':{'provider':'pseudo'}
755 }'''
756 self.assertEqual(js_to_json(inp), '''{
757 "clip":{"provider":"pseudo"}
758 }''')
759 json.loads(js_to_json(inp))
760
761 inp = '''{
762 'playlist':[{'controls':{'all':null}}]
763 }'''
764 self.assertEqual(js_to_json(inp), '''{
765 "playlist":[{"controls":{"all":null}}]
766 }''')
767
768 inp = '''"The CW\\'s \\'Crazy Ex-Girlfriend\\'"'''
769 self.assertEqual(js_to_json(inp), '''"The CW's 'Crazy Ex-Girlfriend'"''')
770
771 inp = '"SAND Number: SAND 2013-7800P\\nPresenter: Tom Russo\\nHabanero Software Training - Xyce Software\\nXyce, Sandia\\u0027s"'
772 json_code = js_to_json(inp)
773 self.assertEqual(json.loads(json_code), json.loads(inp))
774
775 inp = '''{
776 0:{src:'skipped', type: 'application/dash+xml'},
777 1:{src:'skipped', type: 'application/vnd.apple.mpegURL'},
778 }'''
779 self.assertEqual(js_to_json(inp), '''{
780 "0":{"src":"skipped", "type": "application/dash+xml"},
781 "1":{"src":"skipped", "type": "application/vnd.apple.mpegURL"}
782 }''')
783
784 inp = '''{"foo":101}'''
785 self.assertEqual(js_to_json(inp), '''{"foo":101}''')
786
787 inp = '''{"duration": "00:01:07"}'''
788 self.assertEqual(js_to_json(inp), '''{"duration": "00:01:07"}''')
789
790 def test_js_to_json_edgecases(self):
791 on = js_to_json("{abc_def:'1\\'\\\\2\\\\\\'3\"4'}")
792 self.assertEqual(json.loads(on), {"abc_def": "1'\\2\\'3\"4"})
793
794 on = js_to_json('{"abc": true}')
795 self.assertEqual(json.loads(on), {'abc': True})
796
797 # Ignore JavaScript code as well
798 on = js_to_json('''{
799 "x": 1,
800 y: "a",
801 z: some.code
802 }''')
803 d = json.loads(on)
804 self.assertEqual(d['x'], 1)
805 self.assertEqual(d['y'], 'a')
806
807 on = js_to_json('["abc", "def",]')
808 self.assertEqual(json.loads(on), ['abc', 'def'])
809
810 on = js_to_json('[/*comment\n*/"abc"/*comment\n*/,/*comment\n*/"def",/*comment\n*/]')
811 self.assertEqual(json.loads(on), ['abc', 'def'])
812
813 on = js_to_json('[//comment\n"abc" //comment\n,//comment\n"def",//comment\n]')
814 self.assertEqual(json.loads(on), ['abc', 'def'])
815
816 on = js_to_json('{"abc": "def",}')
817 self.assertEqual(json.loads(on), {'abc': 'def'})
818
819 on = js_to_json('{/*comment\n*/"abc"/*comment\n*/:/*comment\n*/"def"/*comment\n*/,/*comment\n*/}')
820 self.assertEqual(json.loads(on), {'abc': 'def'})
821
822 on = js_to_json('{ 0: /* " \n */ ",]" , }')
823 self.assertEqual(json.loads(on), {'0': ',]'})
824
825 on = js_to_json('{ /*comment\n*/0/*comment\n*/: /* " \n */ ",]" , }')
826 self.assertEqual(json.loads(on), {'0': ',]'})
827
828 on = js_to_json('{ 0: // comment\n1 }')
829 self.assertEqual(json.loads(on), {'0': 1})
830
831 on = js_to_json(r'["<p>x<\/p>"]')
832 self.assertEqual(json.loads(on), ['<p>x</p>'])
833
834 on = js_to_json(r'["\xaa"]')
835 self.assertEqual(json.loads(on), ['\u00aa'])
836
837 on = js_to_json("['a\\\nb']")
838 self.assertEqual(json.loads(on), ['ab'])
839
840 on = js_to_json("/*comment\n*/[/*comment\n*/'a\\\nb'/*comment\n*/]/*comment\n*/")
841 self.assertEqual(json.loads(on), ['ab'])
842
843 on = js_to_json('{0xff:0xff}')
844 self.assertEqual(json.loads(on), {'255': 255})
845
846 on = js_to_json('{/*comment\n*/0xff/*comment\n*/:/*comment\n*/0xff/*comment\n*/}')
847 self.assertEqual(json.loads(on), {'255': 255})
848
849 on = js_to_json('{077:077}')
850 self.assertEqual(json.loads(on), {'63': 63})
851
852 on = js_to_json('{/*comment\n*/077/*comment\n*/:/*comment\n*/077/*comment\n*/}')
853 self.assertEqual(json.loads(on), {'63': 63})
854
855 on = js_to_json('{42:42}')
856 self.assertEqual(json.loads(on), {'42': 42})
857
858 on = js_to_json('{/*comment\n*/42/*comment\n*/:/*comment\n*/42/*comment\n*/}')
859 self.assertEqual(json.loads(on), {'42': 42})
860
861 def test_extract_attributes(self):
862 self.assertEqual(extract_attributes('<e x="y">'), {'x': 'y'})
863 self.assertEqual(extract_attributes("<e x='y'>"), {'x': 'y'})
864 self.assertEqual(extract_attributes('<e x=y>'), {'x': 'y'})
865 self.assertEqual(extract_attributes('<e x="a \'b\' c">'), {'x': "a 'b' c"})
866 self.assertEqual(extract_attributes('<e x=\'a "b" c\'>'), {'x': 'a "b" c'})
867 self.assertEqual(extract_attributes('<e x="&#121;">'), {'x': 'y'})
868 self.assertEqual(extract_attributes('<e x="&#x79;">'), {'x': 'y'})
869 self.assertEqual(extract_attributes('<e x="&amp;">'), {'x': '&'}) # XML
870 self.assertEqual(extract_attributes('<e x="&quot;">'), {'x': '"'})
871 self.assertEqual(extract_attributes('<e x="&pound;">'), {'x': '£'}) # HTML 3.2
872 self.assertEqual(extract_attributes('<e x="&lambda;">'), {'x': 'λ'}) # HTML 4.0
873 self.assertEqual(extract_attributes('<e x="&foo">'), {'x': '&foo'})
874 self.assertEqual(extract_attributes('<e x="\'">'), {'x': "'"})
875 self.assertEqual(extract_attributes('<e x=\'"\'>'), {'x': '"'})
876 self.assertEqual(extract_attributes('<e x >'), {'x': None})
877 self.assertEqual(extract_attributes('<e x=y a>'), {'x': 'y', 'a': None})
878 self.assertEqual(extract_attributes('<e x= y>'), {'x': 'y'})
879 self.assertEqual(extract_attributes('<e x=1 y=2 x=3>'), {'y': '2', 'x': '3'})
880 self.assertEqual(extract_attributes('<e \nx=\ny\n>'), {'x': 'y'})
881 self.assertEqual(extract_attributes('<e \nx=\n"y"\n>'), {'x': 'y'})
882 self.assertEqual(extract_attributes("<e \nx=\n'y'\n>"), {'x': 'y'})
883 self.assertEqual(extract_attributes('<e \nx="\ny\n">'), {'x': '\ny\n'})
884 self.assertEqual(extract_attributes('<e CAPS=x>'), {'caps': 'x'}) # Names lowercased
885 self.assertEqual(extract_attributes('<e x=1 X=2>'), {'x': '2'})
886 self.assertEqual(extract_attributes('<e X=1 x=2>'), {'x': '2'})
887 self.assertEqual(extract_attributes('<e _:funny-name1=1>'), {'_:funny-name1': '1'})
888 self.assertEqual(extract_attributes('<e x="Fáilte 世界 \U0001f600">'), {'x': 'Fáilte 世界 \U0001f600'})
889 self.assertEqual(extract_attributes('<e x="décompose&#769;">'), {'x': 'décompose\u0301'})
890 # "Narrow" Python builds don't support unicode code points outside BMP.
891 try:
892 compat_chr(0x10000)
893 supports_outside_bmp = True
894 except ValueError:
895 supports_outside_bmp = False
896 if supports_outside_bmp:
897 self.assertEqual(extract_attributes('<e x="Smile &#128512;!">'), {'x': 'Smile \U0001f600!'})
898
899 def test_clean_html(self):
900 self.assertEqual(clean_html('a:\nb'), 'a: b')
901 self.assertEqual(clean_html('a:\n "b"'), 'a: "b"')
902
903 def test_intlist_to_bytes(self):
904 self.assertEqual(
905 intlist_to_bytes([0, 1, 127, 128, 255]),
906 b'\x00\x01\x7f\x80\xff')
907
908 def test_args_to_str(self):
909 self.assertEqual(
910 args_to_str(['foo', 'ba/r', '-baz', '2 be', '']),
911 'foo ba/r -baz \'2 be\' \'\''
912 )
913
914 def test_parse_filesize(self):
915 self.assertEqual(parse_filesize(None), None)
916 self.assertEqual(parse_filesize(''), None)
917 self.assertEqual(parse_filesize('91 B'), 91)
918 self.assertEqual(parse_filesize('foobar'), None)
919 self.assertEqual(parse_filesize('2 MiB'), 2097152)
920 self.assertEqual(parse_filesize('5 GB'), 5000000000)
921 self.assertEqual(parse_filesize('1.2Tb'), 1200000000000)
922 self.assertEqual(parse_filesize('1.2tb'), 1200000000000)
923 self.assertEqual(parse_filesize('1,24 KB'), 1240)
924 self.assertEqual(parse_filesize('1,24 kb'), 1240)
925 self.assertEqual(parse_filesize('8.5 megabytes'), 8500000)
926
927 def test_parse_count(self):
928 self.assertEqual(parse_count(None), None)
929 self.assertEqual(parse_count(''), None)
930 self.assertEqual(parse_count('0'), 0)
931 self.assertEqual(parse_count('1000'), 1000)
932 self.assertEqual(parse_count('1.000'), 1000)
933 self.assertEqual(parse_count('1.1k'), 1100)
934 self.assertEqual(parse_count('1.1kk'), 1100000)
935 self.assertEqual(parse_count('1.1kk '), 1100000)
936 self.assertEqual(parse_count('1.1kk views'), 1100000)
937
938 def test_version_tuple(self):
939 self.assertEqual(version_tuple('1'), (1,))
940 self.assertEqual(version_tuple('10.23.344'), (10, 23, 344))
941 self.assertEqual(version_tuple('10.1-6'), (10, 1, 6)) # avconv style
942
943 def test_detect_exe_version(self):
944 self.assertEqual(detect_exe_version('''ffmpeg version 1.2.1
945 built on May 27 2013 08:37:26 with gcc 4.7 (Debian 4.7.3-4)
946 configuration: --prefix=/usr --extra-'''), '1.2.1')
947 self.assertEqual(detect_exe_version('''ffmpeg version N-63176-g1fb4685
948 built on May 15 2014 22:09:06 with gcc 4.8.2 (GCC)'''), 'N-63176-g1fb4685')
949 self.assertEqual(detect_exe_version('''X server found. dri2 connection failed!
950 Trying to open render node...
951 Success at /dev/dri/renderD128.
952 ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')
953
954 def test_age_restricted(self):
955 self.assertFalse(age_restricted(None, 10)) # unrestricted content
956 self.assertFalse(age_restricted(1, None)) # unrestricted policy
957 self.assertFalse(age_restricted(8, 10))
958 self.assertTrue(age_restricted(18, 14))
959 self.assertFalse(age_restricted(18, 18))
960
961 def test_is_html(self):
962 self.assertFalse(is_html(b'\x49\x44\x43<html'))
963 self.assertTrue(is_html(b'<!DOCTYPE foo>\xaaa'))
964 self.assertTrue(is_html( # UTF-8 with BOM
965 b'\xef\xbb\xbf<!DOCTYPE foo>\xaaa'))
966 self.assertTrue(is_html( # UTF-16-LE
967 b'\xff\xfe<\x00h\x00t\x00m\x00l\x00>\x00\xe4\x00'
968 ))
969 self.assertTrue(is_html( # UTF-16-BE
970 b'\xfe\xff\x00<\x00h\x00t\x00m\x00l\x00>\x00\xe4'
971 ))
972 self.assertTrue(is_html( # UTF-32-BE
973 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'))
974 self.assertTrue(is_html( # UTF-32-LE
975 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'))
976
977 def test_render_table(self):
978 self.assertEqual(
979 render_table(
980 ['a', 'bcd'],
981 [[123, 4], [9999, 51]]),
982 'a bcd\n'
983 '123 4\n'
984 '9999 51')
985
986 def test_match_str(self):
987 self.assertRaises(ValueError, match_str, 'xy>foobar', {})
988 self.assertFalse(match_str('xy', {'x': 1200}))
989 self.assertTrue(match_str('!xy', {'x': 1200}))
990 self.assertTrue(match_str('x', {'x': 1200}))
991 self.assertFalse(match_str('!x', {'x': 1200}))
992 self.assertTrue(match_str('x', {'x': 0}))
993 self.assertFalse(match_str('x>0', {'x': 0}))
994 self.assertFalse(match_str('x>0', {}))
995 self.assertTrue(match_str('x>?0', {}))
996 self.assertTrue(match_str('x>1K', {'x': 1200}))
997 self.assertFalse(match_str('x>2K', {'x': 1200}))
998 self.assertTrue(match_str('x>=1200 & x < 1300', {'x': 1200}))
999 self.assertFalse(match_str('x>=1100 & x < 1200', {'x': 1200}))
1000 self.assertFalse(match_str('y=a212', {'y': 'foobar42'}))
1001 self.assertTrue(match_str('y=foobar42', {'y': 'foobar42'}))
1002 self.assertFalse(match_str('y!=foobar42', {'y': 'foobar42'}))
1003 self.assertTrue(match_str('y!=foobar2', {'y': 'foobar42'}))
1004 self.assertFalse(match_str(
1005 'like_count > 100 & dislike_count <? 50 & description',
1006 {'like_count': 90, 'description': 'foo'}))
1007 self.assertTrue(match_str(
1008 'like_count > 100 & dislike_count <? 50 & description',
1009 {'like_count': 190, 'description': 'foo'}))
1010 self.assertFalse(match_str(
1011 'like_count > 100 & dislike_count <? 50 & description',
1012 {'like_count': 190, 'dislike_count': 60, 'description': 'foo'}))
1013 self.assertFalse(match_str(
1014 'like_count > 100 & dislike_count <? 50 & description',
1015 {'like_count': 190, 'dislike_count': 10}))
1016
1017 def test_parse_dfxp_time_expr(self):
1018 self.assertEqual(parse_dfxp_time_expr(None), None)
1019 self.assertEqual(parse_dfxp_time_expr(''), None)
1020 self.assertEqual(parse_dfxp_time_expr('0.1'), 0.1)
1021 self.assertEqual(parse_dfxp_time_expr('0.1s'), 0.1)
1022 self.assertEqual(parse_dfxp_time_expr('00:00:01'), 1.0)
1023 self.assertEqual(parse_dfxp_time_expr('00:00:01.100'), 1.1)
1024 self.assertEqual(parse_dfxp_time_expr('00:00:01:100'), 1.1)
1025
1026 def test_dfxp2srt(self):
1027 dfxp_data = '''<?xml version="1.0" encoding="UTF-8"?>
1028 <tt xmlns="http://www.w3.org/ns/ttml" xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter">
1029 <body>
1030 <div xml:lang="en">
1031 <p begin="0" end="1">The following line contains Chinese characters and special symbols</p>
1032 <p begin="1" end="2">第二行<br/>♪♪</p>
1033 <p begin="2" dur="1"><span>Third<br/>Line</span></p>
1034 <p begin="3" end="-1">Lines with invalid timestamps are ignored</p>
1035 <p begin="-1" end="-1">Ignore, two</p>
1036 <p begin="3" dur="-1">Ignored, three</p>
1037 </div>
1038 </body>
1039 </tt>'''
1040 srt_data = '''1
1041 00:00:00,000 --> 00:00:01,000
1042 The following line contains Chinese characters and special symbols
1043
1044 2
1045 00:00:01,000 --> 00:00:02,000
1046 第二行
1047 ♪♪
1048
1049 3
1050 00:00:02,000 --> 00:00:03,000
1051 Third
1052 Line
1053
1054 '''
1055 self.assertEqual(dfxp2srt(dfxp_data), srt_data)
1056
1057 dfxp_data_no_default_namespace = '''<?xml version="1.0" encoding="UTF-8"?>
1058 <tt xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter">
1059 <body>
1060 <div xml:lang="en">
1061 <p begin="0" end="1">The first line</p>
1062 </div>
1063 </body>
1064 </tt>'''
1065 srt_data = '''1
1066 00:00:00,000 --> 00:00:01,000
1067 The first line
1068
1069 '''
1070 self.assertEqual(dfxp2srt(dfxp_data_no_default_namespace), srt_data)
1071
1072 def test_cli_option(self):
1073 self.assertEqual(cli_option({'proxy': '127.0.0.1:3128'}, '--proxy', 'proxy'), ['--proxy', '127.0.0.1:3128'])
1074 self.assertEqual(cli_option({'proxy': None}, '--proxy', 'proxy'), [])
1075 self.assertEqual(cli_option({}, '--proxy', 'proxy'), [])
1076 self.assertEqual(cli_option({'retries': 10}, '--retries', 'retries'), ['--retries', '10'])
1077
1078 def test_cli_valueless_option(self):
1079 self.assertEqual(cli_valueless_option(
1080 {'downloader': 'external'}, '--external-downloader', 'downloader', 'external'), ['--external-downloader'])
1081 self.assertEqual(cli_valueless_option(
1082 {'downloader': 'internal'}, '--external-downloader', 'downloader', 'external'), [])
1083 self.assertEqual(cli_valueless_option(
1084 {'nocheckcertificate': True}, '--no-check-certificate', 'nocheckcertificate'), ['--no-check-certificate'])
1085 self.assertEqual(cli_valueless_option(
1086 {'nocheckcertificate': False}, '--no-check-certificate', 'nocheckcertificate'), [])
1087 self.assertEqual(cli_valueless_option(
1088 {'checkcertificate': True}, '--no-check-certificate', 'checkcertificate', False), [])
1089 self.assertEqual(cli_valueless_option(
1090 {'checkcertificate': False}, '--no-check-certificate', 'checkcertificate', False), ['--no-check-certificate'])
1091
1092 def test_cli_bool_option(self):
1093 self.assertEqual(
1094 cli_bool_option(
1095 {'nocheckcertificate': True}, '--no-check-certificate', 'nocheckcertificate'),
1096 ['--no-check-certificate', 'true'])
1097 self.assertEqual(
1098 cli_bool_option(
1099 {'nocheckcertificate': True}, '--no-check-certificate', 'nocheckcertificate', separator='='),
1100 ['--no-check-certificate=true'])
1101 self.assertEqual(
1102 cli_bool_option(
1103 {'nocheckcertificate': True}, '--check-certificate', 'nocheckcertificate', 'false', 'true'),
1104 ['--check-certificate', 'false'])
1105 self.assertEqual(
1106 cli_bool_option(
1107 {'nocheckcertificate': True}, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='),
1108 ['--check-certificate=false'])
1109 self.assertEqual(
1110 cli_bool_option(
1111 {'nocheckcertificate': False}, '--check-certificate', 'nocheckcertificate', 'false', 'true'),
1112 ['--check-certificate', 'true'])
1113 self.assertEqual(
1114 cli_bool_option(
1115 {'nocheckcertificate': False}, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='),
1116 ['--check-certificate=true'])
1117
1118 def test_ohdave_rsa_encrypt(self):
1119 N = 0xab86b6371b5318aaa1d3c9e612a9f1264f372323c8c0f19875b5fc3b3fd3afcc1e5bec527aa94bfa85bffc157e4245aebda05389a5357b75115ac94f074aefcd
1120 e = 65537
1121
1122 self.assertEqual(
1123 ohdave_rsa_encrypt(b'aa111222', e, N),
1124 '726664bd9a23fd0c70f9f1b84aab5e3905ce1e45a584e9cbcf9bcc7510338fc1986d6c599ff990d923aa43c51c0d9013cd572e13bc58f4ae48f2ed8c0b0ba881')
1125
1126 def test_pkcs1pad(self):
1127 data = [1, 2, 3]
1128 padded_data = pkcs1pad(data, 32)
1129 self.assertEqual(padded_data[:2], [0, 2])
1130 self.assertEqual(padded_data[28:], [0, 1, 2, 3])
1131
1132 self.assertRaises(ValueError, pkcs1pad, data, 8)
1133
1134 def test_encode_base_n(self):
1135 self.assertEqual(encode_base_n(0, 30), '0')
1136 self.assertEqual(encode_base_n(80, 30), '2k')
1137
1138 custom_table = '9876543210ZYXWVUTSRQPONMLKJIHGFEDCBA'
1139 self.assertEqual(encode_base_n(0, 30, custom_table), '9')
1140 self.assertEqual(encode_base_n(80, 30, custom_table), '7P')
1141
1142 self.assertRaises(ValueError, encode_base_n, 0, 70)
1143 self.assertRaises(ValueError, encode_base_n, 0, 60, custom_table)
1144
1145 def test_urshift(self):
1146 self.assertEqual(urshift(3, 1), 1)
1147 self.assertEqual(urshift(-3, 1), 2147483646)
1148
1149 def test_get_element_by_class(self):
1150 html = '''
1151 <span class="foo bar">nice</span>
1152 '''
1153
1154 self.assertEqual(get_element_by_class('foo', html), 'nice')
1155 self.assertEqual(get_element_by_class('no-such-class', html), None)
1156
1157 def test_get_element_by_attribute(self):
1158 html = '''
1159 <span class="foo bar">nice</span>
1160 '''
1161
1162 self.assertEqual(get_element_by_attribute('class', 'foo bar', html), 'nice')
1163 self.assertEqual(get_element_by_attribute('class', 'foo', html), None)
1164 self.assertEqual(get_element_by_attribute('class', 'no-such-foo', html), None)
1165
1166 def test_get_elements_by_class(self):
1167 html = '''
1168 <span class="foo bar">nice</span><span class="foo bar">also nice</span>
1169 '''
1170
1171 self.assertEqual(get_elements_by_class('foo', html), ['nice', 'also nice'])
1172 self.assertEqual(get_elements_by_class('no-such-class', html), [])
1173
1174 def test_get_elements_by_attribute(self):
1175 html = '''
1176 <span class="foo bar">nice</span><span class="foo bar">also nice</span>
1177 '''
1178
1179 self.assertEqual(get_elements_by_attribute('class', 'foo bar', html), ['nice', 'also nice'])
1180 self.assertEqual(get_elements_by_attribute('class', 'foo', html), [])
1181 self.assertEqual(get_elements_by_attribute('class', 'no-such-foo', html), [])
1182
1183
1184 if __name__ == '__main__':
1185 unittest.main()