]> jfr.im git - yt-dlp.git/blame - test/test_YoutubeDL.py
[compat] Fix `compat.WINDOWS_VT_MODE`
[yt-dlp.git] / test / test_YoutubeDL.py
CommitLineData
cc52de43 1#!/usr/bin/env python3
5d254f77
PH
2# Allow direct execution
3import os
e028d0d1
JMF
4import sys
5import unittest
f8271158 6
5d254f77 7sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
e028d0d1 8
0217c783 9import copy
7d1eb38a 10import json
c57f7757 11from test.helper import FakeYDL, assertRegexpMatches
f8271158 12
7a5c1cfe 13from yt_dlp import YoutubeDL
f8271158 14from yt_dlp.compat import (
15 compat_os_name,
16 compat_setenv,
17 compat_str,
18 compat_urllib_error,
19)
7a5c1cfe
P
20from yt_dlp.extractor import YoutubeIE
21from yt_dlp.extractor.common import InfoExtractor
22from yt_dlp.postprocessor.common import PostProcessor
f8271158 23from yt_dlp.utils import (
24 ExtractorError,
25 LazyList,
7e88d7d7 26 OnDemandPagedList,
f8271158 27 int_or_none,
28 match_filter_func,
29)
e028d0d1 30
8508557e
JMF
31TEST_URL = 'http://localhost/sample.mp4'
32
e028d0d1
JMF
33
34class YDL(FakeYDL):
f4d96df0 35 def __init__(self, *args, **kwargs):
86e5f3ed 36 super().__init__(*args, **kwargs)
e028d0d1 37 self.downloaded_info_dicts = []
f4d96df0 38 self.msgs = []
5d254f77 39
e028d0d1 40 def process_info(self, info_dict):
09b49e1f 41 self.downloaded_info_dicts.append(info_dict.copy())
e028d0d1 42
f0500bd1 43 def to_screen(self, msg, *args, **kwargs):
f4d96df0
PH
44 self.msgs.append(msg)
45
b5ac45b1 46 def dl(self, *args, **kwargs):
47 assert False, 'Downloader must not be invoked for test_YoutubeDL'
48
5d254f77 49
3537b93d
PH
50def _make_result(formats, **kwargs):
51 res = {
52 'formats': formats,
53 'id': 'testid',
54 'title': 'testttitle',
55 'extractor': 'testex',
0396806f 56 'extractor_key': 'TestEx',
732044af 57 'webpage_url': 'http://example.com/watch?v=shenanigans',
3537b93d
PH
58 }
59 res.update(**kwargs)
60 return res
61
62
e028d0d1
JMF
63class TestFormatSelection(unittest.TestCase):
64 def test_prefer_free_formats(self):
65 # Same resolution => download webm
66 ydl = YDL()
67 ydl.params['prefer_free_formats'] = True
5d254f77 68 formats = [
8508557e
JMF
69 {'ext': 'webm', 'height': 460, 'url': TEST_URL},
70 {'ext': 'mp4', 'height': 460, 'url': TEST_URL},
5d254f77 71 ]
3537b93d 72 info_dict = _make_result(formats)
3d4a70b8
PH
73 yie = YoutubeIE(ydl)
74 yie._sort_formats(info_dict['formats'])
e028d0d1
JMF
75 ydl.process_ie_result(info_dict)
76 downloaded = ydl.downloaded_info_dicts[0]
89087418 77 self.assertEqual(downloaded['ext'], 'webm')
e028d0d1
JMF
78
79 # Different resolution => download best quality (mp4)
80 ydl = YDL()
81 ydl.params['prefer_free_formats'] = True
5d254f77 82 formats = [
8508557e
JMF
83 {'ext': 'webm', 'height': 720, 'url': TEST_URL},
84 {'ext': 'mp4', 'height': 1080, 'url': TEST_URL},
5d254f77 85 ]
89087418 86 info_dict['formats'] = formats
3d4a70b8
PH
87 yie = YoutubeIE(ydl)
88 yie._sort_formats(info_dict['formats'])
e028d0d1
JMF
89 ydl.process_ie_result(info_dict)
90 downloaded = ydl.downloaded_info_dicts[0]
89087418 91 self.assertEqual(downloaded['ext'], 'mp4')
e028d0d1 92
5d0c5371 93 # No prefer_free_formats => prefer mp4 and webm
e028d0d1
JMF
94 ydl = YDL()
95 ydl.params['prefer_free_formats'] = False
5d254f77 96 formats = [
8508557e
JMF
97 {'ext': 'webm', 'height': 720, 'url': TEST_URL},
98 {'ext': 'mp4', 'height': 720, 'url': TEST_URL},
99 {'ext': 'flv', 'height': 720, 'url': TEST_URL},
5d254f77 100 ]
89087418 101 info_dict['formats'] = formats
3d4a70b8
PH
102 yie = YoutubeIE(ydl)
103 yie._sort_formats(info_dict['formats'])
104 ydl.process_ie_result(info_dict)
105 downloaded = ydl.downloaded_info_dicts[0]
89087418 106 self.assertEqual(downloaded['ext'], 'mp4')
3d4a70b8
PH
107
108 ydl = YDL()
109 ydl.params['prefer_free_formats'] = False
110 formats = [
8508557e
JMF
111 {'ext': 'flv', 'height': 720, 'url': TEST_URL},
112 {'ext': 'webm', 'height': 720, 'url': TEST_URL},
3d4a70b8 113 ]
89087418 114 info_dict['formats'] = formats
3d4a70b8
PH
115 yie = YoutubeIE(ydl)
116 yie._sort_formats(info_dict['formats'])
e028d0d1
JMF
117 ydl.process_ie_result(info_dict)
118 downloaded = ydl.downloaded_info_dicts[0]
5d0c5371 119 self.assertEqual(downloaded['ext'], 'webm')
e028d0d1 120
a9c58ad9
JMF
121 def test_format_selection(self):
122 formats = [
8508557e 123 {'format_id': '35', 'ext': 'mp4', 'preference': 1, 'url': TEST_URL},
232541df 124 {'format_id': 'example-with-dashes', 'ext': 'webm', 'preference': 1, 'url': TEST_URL},
8508557e
JMF
125 {'format_id': '45', 'ext': 'webm', 'preference': 2, 'url': TEST_URL},
126 {'format_id': '47', 'ext': 'webm', 'preference': 3, 'url': TEST_URL},
127 {'format_id': '2', 'ext': 'flv', 'preference': 4, 'url': TEST_URL},
a9c58ad9 128 ]
3537b93d 129 info_dict = _make_result(formats)
a9c58ad9 130
b5ac45b1 131 def test(inp, *expected, multi=False):
132 ydl = YDL({
133 'format': inp,
134 'allow_multiple_video_streams': multi,
135 'allow_multiple_audio_streams': multi,
136 })
137 ydl.process_ie_result(info_dict.copy())
138 downloaded = map(lambda x: x['format_id'], ydl.downloaded_info_dicts)
139 self.assertEqual(list(downloaded), list(expected))
140
141 test('20/47', '47')
142 test('20/71/worst', '35')
143 test(None, '2')
144 test('webm/mp4', '47')
145 test('3gp/40/mp4', '35')
146 test('example-with-dashes', 'example-with-dashes')
dd2a987d 147 test('all', '2', '47', '45', 'example-with-dashes', '35')
b5ac45b1 148 test('mergeall', '2+47+45+example-with-dashes+35', multi=True)
232541df 149
ba7678f9
PH
150 def test_format_selection_audio(self):
151 formats = [
8508557e
JMF
152 {'format_id': 'audio-low', 'ext': 'webm', 'preference': 1, 'vcodec': 'none', 'url': TEST_URL},
153 {'format_id': 'audio-mid', 'ext': 'webm', 'preference': 2, 'vcodec': 'none', 'url': TEST_URL},
154 {'format_id': 'audio-high', 'ext': 'flv', 'preference': 3, 'vcodec': 'none', 'url': TEST_URL},
155 {'format_id': 'vid', 'ext': 'mp4', 'preference': 4, 'url': TEST_URL},
ba7678f9 156 ]
3537b93d 157 info_dict = _make_result(formats)
ba7678f9 158
89087418 159 ydl = YDL({'format': 'bestaudio'})
ba7678f9
PH
160 ydl.process_ie_result(info_dict.copy())
161 downloaded = ydl.downloaded_info_dicts[0]
89087418 162 self.assertEqual(downloaded['format_id'], 'audio-high')
ba7678f9 163
89087418 164 ydl = YDL({'format': 'worstaudio'})
ba7678f9
PH
165 ydl.process_ie_result(info_dict.copy())
166 downloaded = ydl.downloaded_info_dicts[0]
89087418 167 self.assertEqual(downloaded['format_id'], 'audio-low')
ba7678f9
PH
168
169 formats = [
8508557e
JMF
170 {'format_id': 'vid-low', 'ext': 'mp4', 'preference': 1, 'url': TEST_URL},
171 {'format_id': 'vid-high', 'ext': 'mp4', 'preference': 2, 'url': TEST_URL},
ba7678f9 172 ]
3537b93d 173 info_dict = _make_result(formats)
ba7678f9 174
89087418 175 ydl = YDL({'format': 'bestaudio/worstaudio/best'})
ba7678f9
PH
176 ydl.process_ie_result(info_dict.copy())
177 downloaded = ydl.downloaded_info_dicts[0]
89087418 178 self.assertEqual(downloaded['format_id'], 'vid-high')
ba7678f9 179
0217c783
PH
180 def test_format_selection_audio_exts(self):
181 formats = [
182 {'format_id': 'mp3-64', 'ext': 'mp3', 'abr': 64, 'url': 'http://_', 'vcodec': 'none'},
183 {'format_id': 'ogg-64', 'ext': 'ogg', 'abr': 64, 'url': 'http://_', 'vcodec': 'none'},
184 {'format_id': 'aac-64', 'ext': 'aac', 'abr': 64, 'url': 'http://_', 'vcodec': 'none'},
185 {'format_id': 'mp3-32', 'ext': 'mp3', 'abr': 32, 'url': 'http://_', 'vcodec': 'none'},
186 {'format_id': 'aac-32', 'ext': 'aac', 'abr': 32, 'url': 'http://_', 'vcodec': 'none'},
187 ]
188
189 info_dict = _make_result(formats)
190 ydl = YDL({'format': 'best'})
191 ie = YoutubeIE(ydl)
192 ie._sort_formats(info_dict['formats'])
193 ydl.process_ie_result(copy.deepcopy(info_dict))
194 downloaded = ydl.downloaded_info_dicts[0]
195 self.assertEqual(downloaded['format_id'], 'aac-64')
196
197 ydl = YDL({'format': 'mp3'})
198 ie = YoutubeIE(ydl)
199 ie._sort_formats(info_dict['formats'])
200 ydl.process_ie_result(copy.deepcopy(info_dict))
201 downloaded = ydl.downloaded_info_dicts[0]
202 self.assertEqual(downloaded['format_id'], 'mp3-64')
203
204 ydl = YDL({'prefer_free_formats': True})
205 ie = YoutubeIE(ydl)
206 ie._sort_formats(info_dict['formats'])
207 ydl.process_ie_result(copy.deepcopy(info_dict))
208 downloaded = ydl.downloaded_info_dicts[0]
209 self.assertEqual(downloaded['format_id'], 'ogg-64')
210
bc6d5978
JMF
211 def test_format_selection_video(self):
212 formats = [
8508557e
JMF
213 {'format_id': 'dash-video-low', 'ext': 'mp4', 'preference': 1, 'acodec': 'none', 'url': TEST_URL},
214 {'format_id': 'dash-video-high', 'ext': 'mp4', 'preference': 2, 'acodec': 'none', 'url': TEST_URL},
215 {'format_id': 'vid', 'ext': 'mp4', 'preference': 3, 'url': TEST_URL},
bc6d5978 216 ]
3537b93d 217 info_dict = _make_result(formats)
bc6d5978
JMF
218
219 ydl = YDL({'format': 'bestvideo'})
220 ydl.process_ie_result(info_dict.copy())
221 downloaded = ydl.downloaded_info_dicts[0]
222 self.assertEqual(downloaded['format_id'], 'dash-video-high')
223
224 ydl = YDL({'format': 'worstvideo'})
225 ydl.process_ie_result(info_dict.copy())
226 downloaded = ydl.downloaded_info_dicts[0]
227 self.assertEqual(downloaded['format_id'], 'dash-video-low')
228
4c3b16d5
S
229 ydl = YDL({'format': 'bestvideo[format_id^=dash][format_id$=low]'})
230 ydl.process_ie_result(info_dict.copy())
231 downloaded = ydl.downloaded_info_dicts[0]
232 self.assertEqual(downloaded['format_id'], 'dash-video-low')
233
b913348d 234 formats = [
235 {'format_id': 'vid-vcodec-dot', 'ext': 'mp4', 'preference': 1, 'vcodec': 'avc1.123456', 'acodec': 'none', 'url': TEST_URL},
236 ]
237 info_dict = _make_result(formats)
238
239 ydl = YDL({'format': 'bestvideo[vcodec=avc1.123456]'})
240 ydl.process_ie_result(info_dict.copy())
241 downloaded = ydl.downloaded_info_dicts[0]
242 self.assertEqual(downloaded['format_id'], 'vid-vcodec-dot')
243
2cc779f4
S
244 def test_format_selection_string_ops(self):
245 formats = [
246 {'format_id': 'abc-cba', 'ext': 'mp4', 'url': TEST_URL},
e118a879 247 {'format_id': 'zxc-cxz', 'ext': 'webm', 'url': TEST_URL},
2cc779f4
S
248 ]
249 info_dict = _make_result(formats)
250
251 # equals (=)
252 ydl = YDL({'format': '[format_id=abc-cba]'})
253 ydl.process_ie_result(info_dict.copy())
254 downloaded = ydl.downloaded_info_dicts[0]
255 self.assertEqual(downloaded['format_id'], 'abc-cba')
256
257 # does not equal (!=)
258 ydl = YDL({'format': '[format_id!=abc-cba]'})
e118a879
S
259 ydl.process_ie_result(info_dict.copy())
260 downloaded = ydl.downloaded_info_dicts[0]
261 self.assertEqual(downloaded['format_id'], 'zxc-cxz')
262
263 ydl = YDL({'format': '[format_id!=abc-cba][format_id!=zxc-cxz]'})
2cc779f4
S
264 self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy())
265
266 # starts with (^=)
267 ydl = YDL({'format': '[format_id^=abc]'})
268 ydl.process_ie_result(info_dict.copy())
269 downloaded = ydl.downloaded_info_dicts[0]
270 self.assertEqual(downloaded['format_id'], 'abc-cba')
271
272 # does not start with (!^=)
e118a879
S
273 ydl = YDL({'format': '[format_id!^=abc]'})
274 ydl.process_ie_result(info_dict.copy())
275 downloaded = ydl.downloaded_info_dicts[0]
276 self.assertEqual(downloaded['format_id'], 'zxc-cxz')
277
278 ydl = YDL({'format': '[format_id!^=abc][format_id!^=zxc]'})
2cc779f4
S
279 self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy())
280
281 # ends with ($=)
282 ydl = YDL({'format': '[format_id$=cba]'})
283 ydl.process_ie_result(info_dict.copy())
284 downloaded = ydl.downloaded_info_dicts[0]
285 self.assertEqual(downloaded['format_id'], 'abc-cba')
286
287 # does not end with (!$=)
e118a879
S
288 ydl = YDL({'format': '[format_id!$=cba]'})
289 ydl.process_ie_result(info_dict.copy())
290 downloaded = ydl.downloaded_info_dicts[0]
291 self.assertEqual(downloaded['format_id'], 'zxc-cxz')
292
293 ydl = YDL({'format': '[format_id!$=cba][format_id!$=cxz]'})
2cc779f4
S
294 self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy())
295
296 # contains (*=)
e118a879 297 ydl = YDL({'format': '[format_id*=bc-cb]'})
2cc779f4
S
298 ydl.process_ie_result(info_dict.copy())
299 downloaded = ydl.downloaded_info_dicts[0]
300 self.assertEqual(downloaded['format_id'], 'abc-cba')
301
302 # does not contain (!*=)
e118a879
S
303 ydl = YDL({'format': '[format_id!*=bc-cb]'})
304 ydl.process_ie_result(info_dict.copy())
305 downloaded = ydl.downloaded_info_dicts[0]
306 self.assertEqual(downloaded['format_id'], 'zxc-cxz')
307
308 ydl = YDL({'format': '[format_id!*=abc][format_id!*=zxc]'})
309 self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy())
310
2cc779f4
S
311 ydl = YDL({'format': '[format_id!*=-]'})
312 self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy())
313
3d4a70b8 314 def test_youtube_format_selection(self):
a7191c6f 315 # FIXME: Rewrite in accordance with the new format sorting options
5d0c5371 316 return
5d0c5371 317
3d4a70b8 318 order = [
86bf2905 319 '38', '37', '46', '22', '45', '35', '44', '18', '34', '43', '6', '5', '17', '36', '13',
3d4a70b8
PH
320 # Apple HTTP Live Streaming
321 '96', '95', '94', '93', '92', '132', '151',
322 # 3D
323 '85', '84', '102', '83', '101', '82', '100',
324 # Dash video
c11125f9 325 '137', '248', '136', '247', '135', '246',
3d4a70b8
PH
326 '245', '244', '134', '243', '133', '242', '160',
327 # Dash audio
a053c349 328 '141', '172', '140', '171', '139',
3d4a70b8
PH
329 ]
330
67134eab
JMF
331 def format_info(f_id):
332 info = YoutubeIE._formats[f_id].copy()
1df41411 333
91cb6b50 334 # XXX: In real cases InfoExtractor._parse_mpd_formats() fills up 'acodec'
1df41411
YCH
335 # and 'vcodec', while in tests such information is incomplete since
336 # commit a6c2c24479e5f4827ceb06f64d855329c0a6f593
337 # test_YoutubeDL.test_youtube_format_selection is broken without
338 # this fix
339 if 'acodec' in info and 'vcodec' not in info:
340 info['vcodec'] = 'none'
341 elif 'vcodec' in info and 'acodec' not in info:
342 info['acodec'] = 'none'
343
67134eab
JMF
344 info['format_id'] = f_id
345 info['url'] = 'url:' + f_id
346 return info
347 formats_order = [format_info(f_id) for f_id in order]
348
349 info_dict = _make_result(list(formats_order), extractor='youtube')
350 ydl = YDL({'format': 'bestvideo+bestaudio'})
351 yie = YoutubeIE(ydl)
352 yie._sort_formats(info_dict['formats'])
353 ydl.process_ie_result(info_dict)
354 downloaded = ydl.downloaded_info_dicts[0]
5d0c5371 355 self.assertEqual(downloaded['format_id'], '248+172')
67134eab 356 self.assertEqual(downloaded['ext'], 'mp4')
3d4a70b8 357
cf2ac6df
JMF
358 info_dict = _make_result(list(formats_order), extractor='youtube')
359 ydl = YDL({'format': 'bestvideo[height>=999999]+bestaudio/best'})
360 yie = YoutubeIE(ydl)
361 yie._sort_formats(info_dict['formats'])
362 ydl.process_ie_result(info_dict)
363 downloaded = ydl.downloaded_info_dicts[0]
364 self.assertEqual(downloaded['format_id'], '38')
365
f5f4a27a
JMF
366 info_dict = _make_result(list(formats_order), extractor='youtube')
367 ydl = YDL({'format': 'bestvideo/best,bestaudio'})
368 yie = YoutubeIE(ydl)
369 yie._sort_formats(info_dict['formats'])
370 ydl.process_ie_result(info_dict)
371 downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts]
372 self.assertEqual(downloaded_ids, ['137', '141'])
373
0130afb7
JMF
374 info_dict = _make_result(list(formats_order), extractor='youtube')
375 ydl = YDL({'format': '(bestvideo[ext=mp4],bestvideo[ext=webm])+bestaudio'})
376 yie = YoutubeIE(ydl)
377 yie._sort_formats(info_dict['formats'])
378 ydl.process_ie_result(info_dict)
379 downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts]
380 self.assertEqual(downloaded_ids, ['137+141', '248+141'])
381
382 info_dict = _make_result(list(formats_order), extractor='youtube')
383 ydl = YDL({'format': '(bestvideo[ext=mp4],bestvideo[ext=webm])[height<=720]+bestaudio'})
384 yie = YoutubeIE(ydl)
385 yie._sort_formats(info_dict['formats'])
386 ydl.process_ie_result(info_dict)
387 downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts]
388 self.assertEqual(downloaded_ids, ['136+141', '247+141'])
389
390 info_dict = _make_result(list(formats_order), extractor='youtube')
391 ydl = YDL({'format': '(bestvideo[ext=none]/bestvideo[ext=webm])+bestaudio'})
392 yie = YoutubeIE(ydl)
393 yie._sort_formats(info_dict['formats'])
394 ydl.process_ie_result(info_dict)
395 downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts]
396 self.assertEqual(downloaded_ids, ['248+141'])
397
67134eab 398 for f1, f2 in zip(formats_order, formats_order[1:]):
3537b93d 399 info_dict = _make_result([f1, f2], extractor='youtube')
8dd54188 400 ydl = YDL({'format': 'best/bestvideo'})
3d4a70b8
PH
401 yie = YoutubeIE(ydl)
402 yie._sort_formats(info_dict['formats'])
403 ydl.process_ie_result(info_dict)
404 downloaded = ydl.downloaded_info_dicts[0]
67134eab 405 self.assertEqual(downloaded['format_id'], f1['format_id'])
3d4a70b8 406
3537b93d 407 info_dict = _make_result([f2, f1], extractor='youtube')
8dd54188 408 ydl = YDL({'format': 'best/bestvideo'})
3d4a70b8
PH
409 yie = YoutubeIE(ydl)
410 yie._sort_formats(info_dict['formats'])
411 ydl.process_ie_result(info_dict)
412 downloaded = ydl.downloaded_info_dicts[0]
67134eab 413 self.assertEqual(downloaded['format_id'], f1['format_id'])
3d4a70b8 414
317f7ab6
S
415 def test_audio_only_extractor_format_selection(self):
416 # For extractors with incomplete formats (all formats are audio-only or
417 # video-only) best and worst should fallback to corresponding best/worst
418 # video-only or audio-only formats (as per
067aa17e 419 # https://github.com/ytdl-org/youtube-dl/pull/5556)
317f7ab6
S
420 formats = [
421 {'format_id': 'low', 'ext': 'mp3', 'preference': 1, 'vcodec': 'none', 'url': TEST_URL},
422 {'format_id': 'high', 'ext': 'mp3', 'preference': 2, 'vcodec': 'none', 'url': TEST_URL},
423 ]
424 info_dict = _make_result(formats)
425
426 ydl = YDL({'format': 'best'})
427 ydl.process_ie_result(info_dict.copy())
428 downloaded = ydl.downloaded_info_dicts[0]
429 self.assertEqual(downloaded['format_id'], 'high')
430
431 ydl = YDL({'format': 'worst'})
432 ydl.process_ie_result(info_dict.copy())
433 downloaded = ydl.downloaded_info_dicts[0]
434 self.assertEqual(downloaded['format_id'], 'low')
435
436 def test_format_not_available(self):
437 formats = [
438 {'format_id': 'regular', 'ext': 'mp4', 'height': 360, 'url': TEST_URL},
439 {'format_id': 'video', 'ext': 'mp4', 'height': 720, 'acodec': 'none', 'url': TEST_URL},
440 ]
441 info_dict = _make_result(formats)
442
443 # This must fail since complete video-audio format does not match filter
444 # and extractor does not provide incomplete only formats (i.e. only
445 # video-only or audio-only).
446 ydl = YDL({'format': 'best[height>360]'})
447 self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy())
448
8cda78ef 449 def test_format_selection_issue_10083(self):
067aa17e 450 # See https://github.com/ytdl-org/youtube-dl/issues/10083
8cda78ef
S
451 formats = [
452 {'format_id': 'regular', 'height': 360, 'url': TEST_URL},
453 {'format_id': 'video', 'height': 720, 'acodec': 'none', 'url': TEST_URL},
454 {'format_id': 'audio', 'vcodec': 'none', 'url': TEST_URL},
455 ]
456 info_dict = _make_result(formats)
457
458 ydl = YDL({'format': 'best[height>360]/bestvideo[height>360]+bestaudio'})
459 ydl.process_ie_result(info_dict.copy())
460 self.assertEqual(ydl.downloaded_info_dicts[0]['format_id'], 'video+audio')
461
0a31a350
JMF
462 def test_invalid_format_specs(self):
463 def assert_syntax_error(format_spec):
187986a8 464 self.assertRaises(SyntaxError, YDL, {'format': format_spec})
0a31a350
JMF
465
466 assert_syntax_error('bestvideo,,best')
467 assert_syntax_error('+bestaudio')
468 assert_syntax_error('bestvideo+')
d96d604e 469 assert_syntax_error('/')
187986a8 470 assert_syntax_error('[720<height]')
0a31a350 471
083c9df9
PH
472 def test_format_filtering(self):
473 formats = [
474 {'format_id': 'A', 'filesize': 500, 'width': 1000},
475 {'format_id': 'B', 'filesize': 1000, 'width': 500},
476 {'format_id': 'C', 'filesize': 1000, 'width': 400},
477 {'format_id': 'D', 'filesize': 2000, 'width': 600},
478 {'format_id': 'E', 'filesize': 3000},
479 {'format_id': 'F'},
480 {'format_id': 'G', 'filesize': 1000000},
481 ]
482 for f in formats:
483 f['url'] = 'http://_/'
484 f['ext'] = 'unknown'
485 info_dict = _make_result(formats)
486
487 ydl = YDL({'format': 'best[filesize<3000]'})
488 ydl.process_ie_result(info_dict)
489 downloaded = ydl.downloaded_info_dicts[0]
490 self.assertEqual(downloaded['format_id'], 'D')
491
492 ydl = YDL({'format': 'best[filesize<=3000]'})
493 ydl.process_ie_result(info_dict)
494 downloaded = ydl.downloaded_info_dicts[0]
495 self.assertEqual(downloaded['format_id'], 'E')
496
497 ydl = YDL({'format': 'best[filesize <= ? 3000]'})
498 ydl.process_ie_result(info_dict)
499 downloaded = ydl.downloaded_info_dicts[0]
500 self.assertEqual(downloaded['format_id'], 'F')
501
502 ydl = YDL({'format': 'best [filesize = 1000] [width>450]'})
503 ydl.process_ie_result(info_dict)
504 downloaded = ydl.downloaded_info_dicts[0]
505 self.assertEqual(downloaded['format_id'], 'B')
506
507 ydl = YDL({'format': 'best [filesize = 1000] [width!=450]'})
508 ydl.process_ie_result(info_dict)
509 downloaded = ydl.downloaded_info_dicts[0]
510 self.assertEqual(downloaded['format_id'], 'C')
511
512 ydl = YDL({'format': '[filesize>?1]'})
513 ydl.process_ie_result(info_dict)
514 downloaded = ydl.downloaded_info_dicts[0]
515 self.assertEqual(downloaded['format_id'], 'G')
516
517 ydl = YDL({'format': '[filesize<1M]'})
518 ydl.process_ie_result(info_dict)
519 downloaded = ydl.downloaded_info_dicts[0]
520 self.assertEqual(downloaded['format_id'], 'E')
521
522 ydl = YDL({'format': '[filesize<1MiB]'})
523 ydl.process_ie_result(info_dict)
524 downloaded = ydl.downloaded_info_dicts[0]
525 self.assertEqual(downloaded['format_id'], 'G')
526
5acfa126
JMF
527 ydl = YDL({'format': 'all[width>=400][width<=600]'})
528 ydl.process_ie_result(info_dict)
529 downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts]
dd2a987d 530 self.assertEqual(downloaded_ids, ['D', 'C', 'B'])
5acfa126 531
bb8e5536
JMF
532 ydl = YDL({'format': 'best[height<40]'})
533 try:
534 ydl.process_ie_result(info_dict)
535 except ExtractorError:
536 pass
537 self.assertEqual(ydl.downloaded_info_dicts, [])
538
0017d9ad
S
539 def test_default_format_spec(self):
540 ydl = YDL({'simulate': True})
5d0c5371 541 self.assertEqual(ydl._default_format_spec({}), 'bestvideo*+bestaudio/best')
0017d9ad 542
d08dcd2d
S
543 ydl = YDL({})
544 self.assertEqual(ydl._default_format_spec({'is_live': True}), 'best/bestvideo+bestaudio')
af0f7428 545
d08dcd2d 546 ydl = YDL({'simulate': True})
5d0c5371 547 self.assertEqual(ydl._default_format_spec({'is_live': True}), 'bestvideo*+bestaudio/best')
af0f7428 548
0017d9ad 549 ydl = YDL({'outtmpl': '-'})
af0f7428 550 self.assertEqual(ydl._default_format_spec({}), 'best/bestvideo+bestaudio')
0017d9ad
S
551
552 ydl = YDL({})
5d0c5371 553 self.assertEqual(ydl._default_format_spec({}, download=False), 'bestvideo*+bestaudio/best')
af0f7428 554 self.assertEqual(ydl._default_format_spec({'is_live': True}), 'best/bestvideo+bestaudio')
0017d9ad 555
f20bf146
JMF
556
557class TestYoutubeDL(unittest.TestCase):
ab84349b
JMF
558 def test_subtitles(self):
559 def s_formats(lang, autocaption=False):
560 return [{
561 'ext': ext,
86e5f3ed 562 'url': f'http://localhost/video.{lang}.{ext}',
ab84349b
JMF
563 '_auto': autocaption,
564 } for ext in ['vtt', 'srt', 'ass']]
86e5f3ed 565 subtitles = {l: s_formats(l) for l in ['en', 'fr', 'es']}
566 auto_captions = {l: s_formats(l, True) for l in ['it', 'pt', 'es']}
ab84349b
JMF
567 info_dict = {
568 'id': 'test',
569 'title': 'Test',
570 'url': 'http://localhost/video.mp4',
571 'subtitles': subtitles,
572 'automatic_captions': auto_captions,
573 'extractor': 'TEST',
732044af 574 'webpage_url': 'http://example.com/watch?v=shenanigans',
ab84349b
JMF
575 }
576
577 def get_info(params={}):
578 params.setdefault('simulate', True)
579 ydl = YDL(params)
580 ydl.report_warning = lambda *args, **kargs: None
581 return ydl.process_video_result(info_dict, download=False)
582
583 result = get_info()
584 self.assertFalse(result.get('requested_subtitles'))
585 self.assertEqual(result['subtitles'], subtitles)
586 self.assertEqual(result['automatic_captions'], auto_captions)
587
588 result = get_info({'writesubtitles': True})
589 subs = result['requested_subtitles']
590 self.assertTrue(subs)
86e5f3ed 591 self.assertEqual(set(subs.keys()), {'en'})
ab84349b
JMF
592 self.assertTrue(subs['en'].get('data') is None)
593 self.assertEqual(subs['en']['ext'], 'ass')
594
595 result = get_info({'writesubtitles': True, 'subtitlesformat': 'foo/srt'})
596 subs = result['requested_subtitles']
597 self.assertEqual(subs['en']['ext'], 'srt')
598
599 result = get_info({'writesubtitles': True, 'subtitleslangs': ['es', 'fr', 'it']})
600 subs = result['requested_subtitles']
601 self.assertTrue(subs)
86e5f3ed 602 self.assertEqual(set(subs.keys()), {'es', 'fr'})
ab84349b 603
c32b0aab 604 result = get_info({'writesubtitles': True, 'subtitleslangs': ['all', '-en']})
605 subs = result['requested_subtitles']
606 self.assertTrue(subs)
86e5f3ed 607 self.assertEqual(set(subs.keys()), {'es', 'fr'})
c32b0aab 608
609 result = get_info({'writesubtitles': True, 'subtitleslangs': ['en', 'fr', '-en']})
610 subs = result['requested_subtitles']
611 self.assertTrue(subs)
86e5f3ed 612 self.assertEqual(set(subs.keys()), {'fr'})
c32b0aab 613
614 result = get_info({'writesubtitles': True, 'subtitleslangs': ['-en', 'en']})
615 subs = result['requested_subtitles']
616 self.assertTrue(subs)
86e5f3ed 617 self.assertEqual(set(subs.keys()), {'en'})
c32b0aab 618
619 result = get_info({'writesubtitles': True, 'subtitleslangs': ['e.+']})
620 subs = result['requested_subtitles']
621 self.assertTrue(subs)
86e5f3ed 622 self.assertEqual(set(subs.keys()), {'es', 'en'})
c32b0aab 623
ab84349b
JMF
624 result = get_info({'writesubtitles': True, 'writeautomaticsub': True, 'subtitleslangs': ['es', 'pt']})
625 subs = result['requested_subtitles']
626 self.assertTrue(subs)
86e5f3ed 627 self.assertEqual(set(subs.keys()), {'es', 'pt'})
ab84349b
JMF
628 self.assertFalse(subs['es']['_auto'])
629 self.assertTrue(subs['pt']['_auto'])
630
98c70d6f
JMF
631 result = get_info({'writeautomaticsub': True, 'subtitleslangs': ['es', 'pt']})
632 subs = result['requested_subtitles']
633 self.assertTrue(subs)
86e5f3ed 634 self.assertEqual(set(subs.keys()), {'es', 'pt'})
98c70d6f
JMF
635 self.assertTrue(subs['es']['_auto'])
636 self.assertTrue(subs['pt']['_auto'])
637
b6c45014
JMF
638 def test_add_extra_info(self):
639 test_dict = {
640 'extractor': 'Foo',
641 }
642 extra_info = {
643 'extractor': 'Bar',
644 'playlist': 'funny videos',
645 }
646 YDL.add_extra_info(test_dict, extra_info)
647 self.assertEqual(test_dict['extractor'], 'Foo')
648 self.assertEqual(test_dict['playlist'], 'funny videos')
649
752cda38 650 outtmpl_info = {
651 'id': '1234',
652 'ext': 'mp4',
653 'width': None,
654 'height': 1080,
abbeeebc 655 'filesize': 1024,
752cda38 656 'title1': '$PATH',
657 'title2': '%PATH%',
87ea7dfc 658 'title3': 'foo/bar\\test',
7d1eb38a 659 'title4': 'foo "bar" test',
524e2e4f 660 'title5': 'áéí 𝐀',
752cda38 661 'timestamp': 1618488000,
662 'duration': 100000,
663 'playlist_index': 1,
e6f21b3d 664 'playlist_autonumber': 2,
0a5a191a 665 '__last_playlist_index': 100,
752cda38 666 'n_entries': 10,
4476d2c7 667 'formats': [{'id': 'id 1'}, {'id': 'id 2'}, {'id': 'id 3'}]
752cda38 668 }
669
5c6542ce 670 def test_prepare_outtmpl_and_filename(self):
9fea350f 671 def test(tmpl, expected, *, info=None, **params):
752cda38 672 params['outtmpl'] = tmpl
673 ydl = YoutubeDL(params)
674 ydl._num_downloads = 1
5c6542ce 675 self.assertEqual(ydl.validate_outtmpl(tmpl), None)
752cda38 676
819e0531 677 out = ydl.evaluate_outtmpl(tmpl, info or self.outtmpl_info)
9fea350f 678 fname = ydl.prepare_filename(info or self.outtmpl_info)
5c6542ce 679
2b8a2973 680 if not isinstance(expected, (list, tuple)):
681 expected = (expected, expected)
682 for (name, got), expect in zip((('outtmpl', out), ('filename', fname)), expected):
683 if callable(expect):
684 self.assertTrue(expect(got), f'Wrong {name} from {tmpl}')
685 else:
686 self.assertEqual(got, expect, f'Wrong {name} from {tmpl}')
5c6542ce 687
6e84b215 688 # Side-effects
689 original_infodict = dict(self.outtmpl_info)
690 test('foo.bar', 'foo.bar')
691 original_infodict['epoch'] = self.outtmpl_info.get('epoch')
692 self.assertTrue(isinstance(original_infodict['epoch'], int))
693 test('%(epoch)d', int_or_none)
694 self.assertEqual(original_infodict, self.outtmpl_info)
695
5c6542ce 696 # Auto-generated fields
697 test('%(id)s.%(ext)s', '1234.mp4')
698 test('%(duration_string)s', ('27:46:40', '27-46-40'))
5c6542ce 699 test('%(resolution)s', '1080p')
700 test('%(playlist_index)s', '001')
e6f21b3d 701 test('%(playlist_autonumber)s', '02')
5c6542ce 702 test('%(autonumber)s', '00001')
703 test('%(autonumber+2)03d', '005', autonumber_start=3)
704 test('%(autonumber)s', '001', autonumber_size=3)
705
706 # Escaping %
901130bb 707 test('%', '%')
5c6542ce 708 test('%%', '%')
709 test('%%%%', '%%')
901130bb 710 test('%s', '%s')
711 test('%%%s', '%%s')
712 test('%d', '%d')
713 test('%abc%', '%abc%')
5c6542ce 714 test('%%(width)06d.%(ext)s', '%(width)06d.mp4')
901130bb 715 test('%%%(height)s', '%1080')
5c6542ce 716 test('%(width)06d.%(ext)s', 'NA.mp4')
717 test('%(width)06d.%%(ext)s', 'NA.%(ext)s')
718 test('%%(width)06d.%(ext)s', '%(width)06d.mp4')
719
9fea350f 720 # ID sanitization
721 test('%(id)s', '_abcd', info={'id': '_abcd'})
722 test('%(some_id)s', '_abcd', info={'some_id': '_abcd'})
723 test('%(formats.0.id)s', '_abcd', info={'formats': [{'id': '_abcd'}]})
724 test('%(id)s', '-abcd', info={'id': '-abcd'})
725 test('%(id)s', '.abcd', info={'id': '.abcd'})
726 test('%(id)s', 'ab__cd', info={'id': 'ab__cd'})
727 test('%(id)s', ('ab:cd', 'ab -cd'), info={'id': 'ab:cd'})
e0fd9573 728 test('%(id.0)s', '-', info={'id': '--'})
9fea350f 729
5c6542ce 730 # Invalid templates
5c6542ce 731 self.assertTrue(isinstance(YoutubeDL.validate_outtmpl('%(title)'), ValueError))
732 test('%(invalid@tmpl|def)s', 'none', outtmpl_na_placeholder='none')
2b8a2973 733 test('%(..)s', 'NA')
734
735 # Entire info_dict
736 def expect_same_infodict(out):
737 got_dict = json.loads(out)
738 for info_field, expected in self.outtmpl_info.items():
739 self.assertEqual(got_dict.get(info_field), expected, info_field)
740 return True
741
742 test('%()j', (expect_same_infodict, str))
5c6542ce 743
744 # NA placeholder
752cda38 745 NA_TEST_OUTTMPL = '%(uploader_date)s-%(width)d-%(x|def)s-%(id)s.%(ext)s'
5c6542ce 746 test(NA_TEST_OUTTMPL, 'NA-NA-def-1234.mp4')
747 test(NA_TEST_OUTTMPL, 'none-none-def-1234.mp4', outtmpl_na_placeholder='none')
748 test(NA_TEST_OUTTMPL, '--def-1234.mp4', outtmpl_na_placeholder='')
582fad70 749 test('%(non_existent.0)s', 'NA')
752cda38 750
5c6542ce 751 # String formatting
752cda38 752 FMT_TEST_OUTTMPL = '%%(height)%s.%%(ext)s'
5c6542ce 753 test(FMT_TEST_OUTTMPL % 's', '1080.mp4')
754 test(FMT_TEST_OUTTMPL % 'd', '1080.mp4')
755 test(FMT_TEST_OUTTMPL % '6d', ' 1080.mp4')
756 test(FMT_TEST_OUTTMPL % '-6d', '1080 .mp4')
757 test(FMT_TEST_OUTTMPL % '06d', '001080.mp4')
758 test(FMT_TEST_OUTTMPL % ' 06d', ' 01080.mp4')
759 test(FMT_TEST_OUTTMPL % ' 06d', ' 01080.mp4')
760 test(FMT_TEST_OUTTMPL % '0 6d', ' 01080.mp4')
761 test(FMT_TEST_OUTTMPL % '0 6d', ' 01080.mp4')
762 test(FMT_TEST_OUTTMPL % ' 0 6d', ' 01080.mp4')
763
764 # Type casting
765 test('%(id)d', '1234')
766 test('%(height)c', '1')
767 test('%(ext)c', 'm')
768 test('%(id)d %(id)r', "1234 '1234'")
769 test('%(id)r %(height)r', "'1234' 1080")
770 test('%(ext)s-%(ext|def)d', 'mp4-def')
771 test('%(width|0)04d', '0000')
772 test('a%(width|)d', 'a', outtmpl_na_placeholder='none')
773
752cda38 774 FORMATS = self.outtmpl_info['formats']
4476d2c7 775 sanitize = lambda x: x.replace(':', ' -').replace('"', "'").replace('\n', ' ')
7d1eb38a 776
777 # Custom type casting
4476d2c7 778 test('%(formats.:.id)l', 'id 1, id 2, id 3')
779 test('%(formats.:.id)#l', ('id 1\nid 2\nid 3', 'id 1 id 2 id 3'))
7d1eb38a 780 test('%(ext)l', 'mp4')
4476d2c7 781 test('%(formats.:.id) 18l', ' id 1, id 2, id 3')
7d1eb38a 782 test('%(formats)j', (json.dumps(FORMATS), sanitize(json.dumps(FORMATS))))
4476d2c7 783 test('%(formats)#j', (json.dumps(FORMATS, indent=4), sanitize(json.dumps(FORMATS, indent=4))))
f5aa5cfb 784 test('%(title5).3B', 'á')
524e2e4f 785 test('%(title5)U', 'áéí 𝐀')
786 test('%(title5)#U', 'a\u0301e\u0301i\u0301 𝐀')
787 test('%(title5)+U', 'áéí A')
788 test('%(title5)+#U', 'a\u0301e\u0301i\u0301 A')
abbeeebc 789 test('%(height)D', '1k')
790 test('%(filesize)#D', '1Ki')
791 test('%(height)5.2D', ' 1.08k')
37893bb0 792 test('%(title4)#S', 'foo_bar_test')
793 test('%(title4).10S', ('foo \'bar\' ', 'foo \'bar\'' + ('#' if compat_os_name == 'nt' else ' ')))
7d1eb38a 794 if compat_os_name == 'nt':
795 test('%(title4)q', ('"foo \\"bar\\" test"', "'foo _'bar_' test'"))
4476d2c7 796 test('%(formats.:.id)#q', ('"id 1" "id 2" "id 3"', "'id 1' 'id 2' 'id 3'"))
797 test('%(formats.0.id)#q', ('"id 1"', "'id 1'"))
7d1eb38a 798 else:
799 test('%(title4)q', ('\'foo "bar" test\'', "'foo 'bar' test'"))
4476d2c7 800 test('%(formats.:.id)#q', "'id 1' 'id 2' 'id 3'")
801 test('%(formats.0.id)#q', "'id 1'")
7d1eb38a 802
803 # Internal formatting
5c6542ce 804 test('%(timestamp-1000>%H-%M-%S)s', '11-43-20')
901130bb 805 test('%(title|%)s %(title|%%)s', '% %%')
5c6542ce 806 test('%(id+1-height+3)05d', '00158')
807 test('%(width+100)05d', 'NA')
7d1eb38a 808 test('%(formats.0) 15s', ('% 15s' % FORMATS[0], '% 15s' % sanitize(str(FORMATS[0]))))
809 test('%(formats.0)r', (repr(FORMATS[0]), sanitize(repr(FORMATS[0]))))
5c6542ce 810 test('%(height.0)03d', '001')
811 test('%(-height.0)04d', '-001')
812 test('%(formats.-1.id)s', FORMATS[-1]['id'])
813 test('%(formats.0.id.-1)d', FORMATS[0]['id'][-1])
814 test('%(formats.3)s', 'NA')
815 test('%(formats.:2:-1)r', repr(FORMATS[:2:-1]))
816 test('%(formats.0.id.-1+id)f', '1235.000000')
385a27fa 817 test('%(formats.0.id.-1+formats.1.id.-1)d', '3')
5c6542ce 818
7c37ff97 819 # Alternates
820 test('%(title,id)s', '1234')
821 test('%(width-100,height+20|def)d', '1100')
822 test('%(width-100,height+width|def)s', 'def')
823 test('%(timestamp-x>%H\\,%M\\,%S,timestamp>%H\\,%M\\,%S)s', '12,00,00')
824
e0fd9573 825 # Replacement
826 test('%(id&foo)s.bar', 'foo.bar')
827 test('%(title&foo)s.bar', 'NA.bar')
828 test('%(title&foo|baz)s.bar', 'baz.bar')
34baa9fd 829 test('%(x,id&foo|baz)s.bar', 'foo.bar')
830 test('%(x,title&foo|baz)s.bar', 'baz.bar')
e0fd9573 831
6e84b215 832 # Laziness
833 def gen():
834 yield from range(5)
835 raise self.assertTrue(False, 'LazyList should not be evaluated till here')
836 test('%(key.4)s', '4', info={'key': LazyList(gen())})
837
5c6542ce 838 # Empty filename
839 test('%(foo|)s-%(bar|)s.%(ext)s', '-.mp4')
840 # test('%(foo|)s.%(ext)s', ('.mp4', '_.mp4')) # fixme
841 # test('%(foo|)s', ('', '_')) # fixme
842
901130bb 843 # Environment variable expansion for prepare_filename
844 compat_setenv('__yt_dlp_var', 'expanded')
845 envvar = '%__yt_dlp_var%' if compat_os_name == 'nt' else '$__yt_dlp_var'
846 test(envvar, (envvar, 'expanded'))
b836dc94 847 if compat_os_name == 'nt':
848 test('%s%', ('%s%', '%s%'))
849 compat_setenv('s', 'expanded')
850 test('%s%', ('%s%', 'expanded')) # %s% should be expanded before escaping %s
851 compat_setenv('(test)s', 'expanded')
852 test('%(test)s%', ('NA%', 'expanded')) # Environment should take priority over template
901130bb 853
5c6542ce 854 # Path expansion and escaping
855 test('Hello %(title1)s', 'Hello $PATH')
856 test('Hello %(title2)s', 'Hello %PATH%')
857 test('%(title3)s', ('foo/bar\\test', 'foo_bar_test'))
858 test('folder/%(title3)s', ('folder/foo/bar\\test', 'folder%sfoo_bar_test' % os.path.sep))
26e63931 859
c57f7757
PH
860 def test_format_note(self):
861 ydl = YoutubeDL()
862 self.assertEqual(ydl._format_note({}), '')
863 assertRegexpMatches(self, ydl._format_note({
864 'vbr': 10,
398dea32 865 }), r'^\s*10k$')
5d583bdf
S
866 assertRegexpMatches(self, ydl._format_note({
867 'fps': 30,
398dea32 868 }), r'^30fps$')
5d583bdf 869
2b4ecde2
JMF
870 def test_postprocessors(self):
871 filename = 'post-processor-testfile.mp4'
872 audiofile = filename + '.mp3'
873
874 class SimplePP(PostProcessor):
875 def run(self, info):
2b4ecde2
JMF
876 with open(audiofile, 'wt') as f:
877 f.write('EXAMPLE')
592e97e8 878 return [info['filepath']], info
2b4ecde2 879
592e97e8 880 def run_pp(params, PP):
2b4ecde2
JMF
881 with open(filename, 'wt') as f:
882 f.write('EXAMPLE')
883 ydl = YoutubeDL(params)
592e97e8 884 ydl.add_post_processor(PP())
2b4ecde2
JMF
885 ydl.post_process(filename, {'filepath': filename})
886
592e97e8 887 run_pp({'keepvideo': True}, SimplePP)
2b4ecde2
JMF
888 self.assertTrue(os.path.exists(filename), '%s doesn\'t exist' % filename)
889 self.assertTrue(os.path.exists(audiofile), '%s doesn\'t exist' % audiofile)
890 os.unlink(filename)
891 os.unlink(audiofile)
892
592e97e8 893 run_pp({'keepvideo': False}, SimplePP)
2b4ecde2
JMF
894 self.assertFalse(os.path.exists(filename), '%s exists' % filename)
895 self.assertTrue(os.path.exists(audiofile), '%s doesn\'t exist' % audiofile)
896 os.unlink(audiofile)
897
592e97e8
JMF
898 class ModifierPP(PostProcessor):
899 def run(self, info):
900 with open(info['filepath'], 'wt') as f:
901 f.write('MODIFIED')
902 return [], info
903
904 run_pp({'keepvideo': False}, ModifierPP)
905 self.assertTrue(os.path.exists(filename), '%s doesn\'t exist' % filename)
906 os.unlink(filename)
907
531980d8 908 def test_match_filter(self):
531980d8
JMF
909 first = {
910 'id': '1',
911 'url': TEST_URL,
912 'title': 'one',
913 'extractor': 'TEST',
914 'duration': 30,
915 'filesize': 10 * 1024,
e5a088dc 916 'playlist_id': '42',
db13c16e
S
917 'uploader': "變態妍字幕版 太妍 тест",
918 'creator': "тест ' 123 ' тест--",
732044af 919 'webpage_url': 'http://example.com/watch?v=shenanigans',
531980d8
JMF
920 }
921 second = {
922 'id': '2',
923 'url': TEST_URL,
924 'title': 'two',
925 'extractor': 'TEST',
926 'duration': 10,
927 'description': 'foo',
928 'filesize': 5 * 1024,
e5a088dc 929 'playlist_id': '43',
db13c16e 930 'uploader': "тест 123",
732044af 931 'webpage_url': 'http://example.com/watch?v=SHENANIGANS',
531980d8
JMF
932 }
933 videos = [first, second]
934
935 def get_videos(filter_=None):
09b49e1f 936 ydl = YDL({'match_filter': filter_, 'simulate': True})
531980d8
JMF
937 for v in videos:
938 ydl.process_ie_result(v, download=True)
939 return [v['id'] for v in ydl.downloaded_info_dicts]
940
941 res = get_videos()
942 self.assertEqual(res, ['1', '2'])
943
6db9c4d5 944 def f(v, incomplete):
531980d8
JMF
945 if v['id'] == '1':
946 return None
947 else:
948 return 'Video id is not 1'
949 res = get_videos(f)
950 self.assertEqual(res, ['1'])
951
952 f = match_filter_func('duration < 30')
953 res = get_videos(f)
954 self.assertEqual(res, ['2'])
955
956 f = match_filter_func('description = foo')
957 res = get_videos(f)
958 self.assertEqual(res, ['2'])
959
960 f = match_filter_func('description =? foo')
961 res = get_videos(f)
962 self.assertEqual(res, ['1', '2'])
963
964 f = match_filter_func('filesize > 5KiB')
965 res = get_videos(f)
966 self.assertEqual(res, ['1'])
967
e5a088dc
S
968 f = match_filter_func('playlist_id = 42')
969 res = get_videos(f)
970 self.assertEqual(res, ['1'])
971
db13c16e
S
972 f = match_filter_func('uploader = "變態妍字幕版 太妍 тест"')
973 res = get_videos(f)
974 self.assertEqual(res, ['1'])
975
976 f = match_filter_func('uploader != "變態妍字幕版 太妍 тест"')
977 res = get_videos(f)
978 self.assertEqual(res, ['2'])
979
980 f = match_filter_func('creator = "тест \' 123 \' тест--"')
981 res = get_videos(f)
982 self.assertEqual(res, ['1'])
983
984 f = match_filter_func("creator = 'тест \\' 123 \\' тест--'")
985 res = get_videos(f)
986 self.assertEqual(res, ['1'])
987
988 f = match_filter_func(r"creator = 'тест \' 123 \' тест--' & duration > 30")
989 res = get_videos(f)
990 self.assertEqual(res, [])
991
e9eaf3fb 992 def test_playlist_items_selection(self):
7e88d7d7 993 INDICES, PAGE_SIZE = list(range(1, 11)), 3
994
995 def entry(i, evaluated):
996 evaluated.append(i)
997 return {
998 'id': str(i),
999 'title': str(i),
1000 'url': TEST_URL,
1001 }
1002
1003 def pagedlist_entries(evaluated):
1004 def page_func(n):
1005 start = PAGE_SIZE * n
1006 for i in INDICES[start: start + PAGE_SIZE]:
1007 yield entry(i, evaluated)
1008 return OnDemandPagedList(page_func, PAGE_SIZE)
1009
1010 def page_num(i):
1011 return (i + PAGE_SIZE - 1) // PAGE_SIZE
e9eaf3fb 1012
7e88d7d7 1013 def generator_entries(evaluated):
1014 for i in INDICES:
1015 yield entry(i, evaluated)
1016
1017 def list_entries(evaluated):
1018 return list(generator_entries(evaluated))
1019
1020 def lazylist_entries(evaluated):
1021 return LazyList(generator_entries(evaluated))
1022
1023 def get_downloaded_info_dicts(params, entries):
e9eaf3fb 1024 ydl = YDL(params)
7e88d7d7 1025 ydl.process_ie_result({
1026 '_type': 'playlist',
1027 'id': 'test',
1028 'extractor': 'test:playlist',
1029 'extractor_key': 'test:playlist',
1030 'webpage_url': 'http://example.com',
1031 'entries': entries,
1032 })
4e9e1e24
S
1033 return ydl.downloaded_info_dicts
1034
7e88d7d7 1035 def test_selection(params, expected_ids, evaluate_all=False):
1036 expected_ids = list(expected_ids)
1037 if evaluate_all:
1038 generator_eval = pagedlist_eval = INDICES
1039 elif not expected_ids:
1040 generator_eval = pagedlist_eval = []
1041 else:
1042 generator_eval = INDICES[0: max(expected_ids)]
1043 pagedlist_eval = INDICES[PAGE_SIZE * page_num(min(expected_ids)) - PAGE_SIZE:
1044 PAGE_SIZE * page_num(max(expected_ids))]
1045
1046 for name, func, expected_eval in (
1047 ('list', list_entries, INDICES),
1048 ('Generator', generator_entries, generator_eval),
7e9a6125 1049 # ('LazyList', lazylist_entries, generator_eval), # Generator and LazyList follow the exact same code path
7e88d7d7 1050 ('PagedList', pagedlist_entries, pagedlist_eval),
1051 ):
1052 evaluated = []
1053 entries = func(evaluated)
1054 results = [(v['playlist_autonumber'] - 1, (int(v['id']), v['playlist_index']))
1055 for v in get_downloaded_info_dicts(params, entries)]
1056 self.assertEqual(results, list(enumerate(zip(expected_ids, expected_ids))), f'Entries of {name} for {params}')
1057 self.assertEqual(sorted(evaluated), expected_eval, f'Evaluation of {name} for {params}')
1058 test_selection({}, INDICES)
1059 test_selection({'playlistend': 20}, INDICES, True)
1060 test_selection({'playlistend': 2}, INDICES[:2])
1061 test_selection({'playliststart': 11}, [], True)
1062 test_selection({'playliststart': 2}, INDICES[1:])
1063 test_selection({'playlist_items': '2-4'}, INDICES[1:4])
9e598870 1064 test_selection({'playlist_items': '2,4'}, [2, 4])
7e88d7d7 1065 test_selection({'playlist_items': '20'}, [], True)
ff1c7fc9 1066 test_selection({'playlist_items': '0'}, [])
cd6fc19e 1067
4e9e1e24 1068 # Tests for https://github.com/ytdl-org/youtube-dl/issues/10591
9e598870 1069 test_selection({'playlist_items': '2-4,3-4,3'}, [2, 3, 4])
1070 test_selection({'playlist_items': '4,2'}, [4, 2])
1071
1072 # Tests for https://github.com/yt-dlp/yt-dlp/issues/720
1073 # https://github.com/yt-dlp/yt-dlp/issues/302
7e88d7d7 1074 test_selection({'playlistreverse': True}, INDICES[::-1])
1075 test_selection({'playliststart': 2, 'playlistreverse': True}, INDICES[:0:-1])
9e598870 1076 test_selection({'playlist_items': '2,4', 'playlistreverse': True}, [4, 2])
1077 test_selection({'playlist_items': '4,2'}, [4, 2])
4e9e1e24 1078
7e88d7d7 1079 # Tests for --playlist-items start:end:step
1080 test_selection({'playlist_items': ':'}, INDICES, True)
1081 test_selection({'playlist_items': '::1'}, INDICES, True)
1082 test_selection({'playlist_items': '::-1'}, INDICES[::-1], True)
1083 test_selection({'playlist_items': ':6'}, INDICES[:6])
1084 test_selection({'playlist_items': ':-6'}, INDICES[:-5], True)
1085 test_selection({'playlist_items': '-1:6:-2'}, INDICES[:4:-2], True)
1086 test_selection({'playlist_items': '9:-6:-2'}, INDICES[8:3:-2], True)
1087
1088 test_selection({'playlist_items': '1:inf:2'}, INDICES[::2], True)
1089 test_selection({'playlist_items': '-2:inf'}, INDICES[-2:], True)
1090 test_selection({'playlist_items': ':inf:-1'}, [], True)
1091 test_selection({'playlist_items': '0-2:2'}, [2])
1092 test_selection({'playlist_items': '1-:2'}, INDICES[::2], True)
1093 test_selection({'playlist_items': '0--2:2'}, INDICES[1:-1:2], True)
1094
1095 test_selection({'playlist_items': '10::3'}, [10], True)
1096 test_selection({'playlist_items': '-1::3'}, [10], True)
1097 test_selection({'playlist_items': '11::3'}, [], True)
1098 test_selection({'playlist_items': '-15::2'}, INDICES[1::2], True)
1099 test_selection({'playlist_items': '-15::15'}, [], True)
1100
e37afbe0 1101 def test_urlopen_no_file_protocol(self):
067aa17e 1102 # see https://github.com/ytdl-org/youtube-dl/issues/8227
e37afbe0
JMF
1103 ydl = YDL()
1104 self.assertRaises(compat_urllib_error.URLError, ydl.urlopen, 'file:///etc/passwd')
1105
b286f201
YCH
1106 def test_do_not_override_ie_key_in_url_transparent(self):
1107 ydl = YDL()
1108
1109 class Foo1IE(InfoExtractor):
1110 _VALID_URL = r'foo1:'
1111
1112 def _real_extract(self, url):
1113 return {
1114 '_type': 'url_transparent',
1115 'url': 'foo2:',
1116 'ie_key': 'Foo2',
0396806f
S
1117 'title': 'foo1 title',
1118 'id': 'foo1_id',
b286f201
YCH
1119 }
1120
1121 class Foo2IE(InfoExtractor):
1122 _VALID_URL = r'foo2:'
1123
1124 def _real_extract(self, url):
1125 return {
1126 '_type': 'url',
1127 'url': 'foo3:',
1128 'ie_key': 'Foo3',
1129 }
1130
1131 class Foo3IE(InfoExtractor):
1132 _VALID_URL = r'foo3:'
1133
1134 def _real_extract(self, url):
51350db5 1135 return _make_result([{'url': TEST_URL}], title='foo3 title')
b286f201
YCH
1136
1137 ydl.add_info_extractor(Foo1IE(ydl))
1138 ydl.add_info_extractor(Foo2IE(ydl))
1139 ydl.add_info_extractor(Foo3IE(ydl))
1140 ydl.extract_info('foo1:')
1141 downloaded = ydl.downloaded_info_dicts[0]
1142 self.assertEqual(downloaded['url'], TEST_URL)
51350db5 1143 self.assertEqual(downloaded['title'], 'foo1 title')
0396806f
S
1144 self.assertEqual(downloaded['id'], 'testid')
1145 self.assertEqual(downloaded['extractor'], 'testex')
1146 self.assertEqual(downloaded['extractor_key'], 'TestEx')
b286f201 1147
a0566bbf 1148 # Test case for https://github.com/ytdl-org/youtube-dl/issues/27064
1149 def test_ignoreerrors_for_playlist_with_url_transparent_iterable_entries(self):
1150
1151 class _YDL(YDL):
1152 def __init__(self, *args, **kwargs):
86e5f3ed 1153 super().__init__(*args, **kwargs)
a0566bbf 1154
1155 def trouble(self, s, tb=None):
1156 pass
1157
1158 ydl = _YDL({
1159 'format': 'extra',
1160 'ignoreerrors': True,
1161 })
1162
1163 class VideoIE(InfoExtractor):
1164 _VALID_URL = r'video:(?P<id>\d+)'
1165
1166 def _real_extract(self, url):
1167 video_id = self._match_id(url)
1168 formats = [{
1169 'format_id': 'default',
1170 'url': 'url:',
1171 }]
1172 if video_id == '0':
1173 raise ExtractorError('foo')
1174 if video_id == '2':
1175 formats.append({
1176 'format_id': 'extra',
1177 'url': TEST_URL,
1178 })
1179 return {
1180 'id': video_id,
1181 'title': 'Video %s' % video_id,
1182 'formats': formats,
1183 }
1184
1185 class PlaylistIE(InfoExtractor):
1186 _VALID_URL = r'playlist:'
1187
1188 def _entries(self):
1189 for n in range(3):
1190 video_id = compat_str(n)
1191 yield {
1192 '_type': 'url_transparent',
1193 'ie_key': VideoIE.ie_key(),
1194 'id': video_id,
1195 'url': 'video:%s' % video_id,
1196 'title': 'Video Transparent %s' % video_id,
1197 }
1198
1199 def _real_extract(self, url):
1200 return self.playlist_result(self._entries())
1201
1202 ydl.add_info_extractor(VideoIE(ydl))
1203 ydl.add_info_extractor(PlaylistIE(ydl))
1204 info = ydl.extract_info('playlist:')
1205 entries = info['entries']
1206 self.assertEqual(len(entries), 3)
1207 self.assertTrue(entries[0] is None)
1208 self.assertTrue(entries[1] is None)
1209 self.assertEqual(len(ydl.downloaded_info_dicts), 1)
1210 downloaded = ydl.downloaded_info_dicts[0]
9e907ebd 1211 entries[2].pop('requested_downloads', None)
a0566bbf 1212 self.assertEqual(entries[2], downloaded)
1213 self.assertEqual(downloaded['url'], TEST_URL)
1214 self.assertEqual(downloaded['title'], 'Video Transparent 2')
1215 self.assertEqual(downloaded['id'], '2')
1216 self.assertEqual(downloaded['extractor'], 'Video')
1217 self.assertEqual(downloaded['extractor_key'], 'Video')
1218
2b4ecde2 1219
e028d0d1
JMF
1220if __name__ == '__main__':
1221 unittest.main()