]> jfr.im git - yt-dlp.git/blame - test/test_YoutubeDL.py
[outtmpl] Allow `\n` in replacements and default.
[yt-dlp.git] / test / test_YoutubeDL.py
CommitLineData
cc52de43 1#!/usr/bin/env python3
54007a45 2
5d254f77
PH
3# Allow direct execution
4import os
e028d0d1
JMF
5import sys
6import unittest
f8271158 7
5d254f77 8sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
e028d0d1 9
54007a45 10
0217c783 11import copy
7d1eb38a 12import json
ac668111 13import urllib.error
f8271158 14
ac668111 15from test.helper import FakeYDL, assertRegexpMatches
7a5c1cfe 16from yt_dlp import YoutubeDL
14f25df2 17from yt_dlp.compat import compat_os_name
7a5c1cfe
P
18from yt_dlp.extractor import YoutubeIE
19from yt_dlp.extractor.common import InfoExtractor
20from yt_dlp.postprocessor.common import PostProcessor
f8271158 21from yt_dlp.utils import (
22 ExtractorError,
23 LazyList,
7e88d7d7 24 OnDemandPagedList,
f8271158 25 int_or_none,
26 match_filter_func,
27)
e028d0d1 28
8508557e
JMF
29TEST_URL = 'http://localhost/sample.mp4'
30
e028d0d1
JMF
31
32class YDL(FakeYDL):
f4d96df0 33 def __init__(self, *args, **kwargs):
86e5f3ed 34 super().__init__(*args, **kwargs)
e028d0d1 35 self.downloaded_info_dicts = []
f4d96df0 36 self.msgs = []
5d254f77 37
e028d0d1 38 def process_info(self, info_dict):
09b49e1f 39 self.downloaded_info_dicts.append(info_dict.copy())
e028d0d1 40
f0500bd1 41 def to_screen(self, msg, *args, **kwargs):
f4d96df0
PH
42 self.msgs.append(msg)
43
b5ac45b1 44 def dl(self, *args, **kwargs):
45 assert False, 'Downloader must not be invoked for test_YoutubeDL'
46
5d254f77 47
3537b93d
PH
48def _make_result(formats, **kwargs):
49 res = {
50 'formats': formats,
51 'id': 'testid',
52 'title': 'testttitle',
53 'extractor': 'testex',
0396806f 54 'extractor_key': 'TestEx',
732044af 55 'webpage_url': 'http://example.com/watch?v=shenanigans',
3537b93d
PH
56 }
57 res.update(**kwargs)
58 return res
59
60
e028d0d1
JMF
61class TestFormatSelection(unittest.TestCase):
62 def test_prefer_free_formats(self):
63 # Same resolution => download webm
64 ydl = YDL()
65 ydl.params['prefer_free_formats'] = True
5d254f77 66 formats = [
8508557e
JMF
67 {'ext': 'webm', 'height': 460, 'url': TEST_URL},
68 {'ext': 'mp4', 'height': 460, 'url': TEST_URL},
5d254f77 69 ]
3537b93d 70 info_dict = _make_result(formats)
9f14daf2 71 ydl.sort_formats(info_dict)
e028d0d1
JMF
72 ydl.process_ie_result(info_dict)
73 downloaded = ydl.downloaded_info_dicts[0]
89087418 74 self.assertEqual(downloaded['ext'], 'webm')
e028d0d1
JMF
75
76 # Different resolution => download best quality (mp4)
77 ydl = YDL()
78 ydl.params['prefer_free_formats'] = True
5d254f77 79 formats = [
8508557e
JMF
80 {'ext': 'webm', 'height': 720, 'url': TEST_URL},
81 {'ext': 'mp4', 'height': 1080, 'url': TEST_URL},
5d254f77 82 ]
89087418 83 info_dict['formats'] = formats
9f14daf2 84 ydl.sort_formats(info_dict)
e028d0d1
JMF
85 ydl.process_ie_result(info_dict)
86 downloaded = ydl.downloaded_info_dicts[0]
89087418 87 self.assertEqual(downloaded['ext'], 'mp4')
e028d0d1 88
5d0c5371 89 # No prefer_free_formats => prefer mp4 and webm
e028d0d1
JMF
90 ydl = YDL()
91 ydl.params['prefer_free_formats'] = False
5d254f77 92 formats = [
8508557e
JMF
93 {'ext': 'webm', 'height': 720, 'url': TEST_URL},
94 {'ext': 'mp4', 'height': 720, 'url': TEST_URL},
95 {'ext': 'flv', 'height': 720, 'url': TEST_URL},
5d254f77 96 ]
89087418 97 info_dict['formats'] = formats
9f14daf2 98 ydl.sort_formats(info_dict)
3d4a70b8
PH
99 ydl.process_ie_result(info_dict)
100 downloaded = ydl.downloaded_info_dicts[0]
89087418 101 self.assertEqual(downloaded['ext'], 'mp4')
3d4a70b8
PH
102
103 ydl = YDL()
104 ydl.params['prefer_free_formats'] = False
105 formats = [
8508557e
JMF
106 {'ext': 'flv', 'height': 720, 'url': TEST_URL},
107 {'ext': 'webm', 'height': 720, 'url': TEST_URL},
3d4a70b8 108 ]
89087418 109 info_dict['formats'] = formats
9f14daf2 110 ydl.sort_formats(info_dict)
e028d0d1
JMF
111 ydl.process_ie_result(info_dict)
112 downloaded = ydl.downloaded_info_dicts[0]
5d0c5371 113 self.assertEqual(downloaded['ext'], 'webm')
e028d0d1 114
a9c58ad9
JMF
115 def test_format_selection(self):
116 formats = [
9f14daf2 117 {'format_id': '35', 'ext': 'mp4', 'preference': 0, 'url': TEST_URL},
232541df 118 {'format_id': 'example-with-dashes', 'ext': 'webm', 'preference': 1, 'url': TEST_URL},
8508557e
JMF
119 {'format_id': '45', 'ext': 'webm', 'preference': 2, 'url': TEST_URL},
120 {'format_id': '47', 'ext': 'webm', 'preference': 3, 'url': TEST_URL},
121 {'format_id': '2', 'ext': 'flv', 'preference': 4, 'url': TEST_URL},
a9c58ad9 122 ]
3537b93d 123 info_dict = _make_result(formats)
a9c58ad9 124
b5ac45b1 125 def test(inp, *expected, multi=False):
126 ydl = YDL({
127 'format': inp,
128 'allow_multiple_video_streams': multi,
129 'allow_multiple_audio_streams': multi,
130 })
131 ydl.process_ie_result(info_dict.copy())
132 downloaded = map(lambda x: x['format_id'], ydl.downloaded_info_dicts)
133 self.assertEqual(list(downloaded), list(expected))
134
135 test('20/47', '47')
136 test('20/71/worst', '35')
137 test(None, '2')
138 test('webm/mp4', '47')
139 test('3gp/40/mp4', '35')
140 test('example-with-dashes', 'example-with-dashes')
dd2a987d 141 test('all', '2', '47', '45', 'example-with-dashes', '35')
b5ac45b1 142 test('mergeall', '2+47+45+example-with-dashes+35', multi=True)
232541df 143
ba7678f9
PH
144 def test_format_selection_audio(self):
145 formats = [
8508557e
JMF
146 {'format_id': 'audio-low', 'ext': 'webm', 'preference': 1, 'vcodec': 'none', 'url': TEST_URL},
147 {'format_id': 'audio-mid', 'ext': 'webm', 'preference': 2, 'vcodec': 'none', 'url': TEST_URL},
148 {'format_id': 'audio-high', 'ext': 'flv', 'preference': 3, 'vcodec': 'none', 'url': TEST_URL},
149 {'format_id': 'vid', 'ext': 'mp4', 'preference': 4, 'url': TEST_URL},
ba7678f9 150 ]
3537b93d 151 info_dict = _make_result(formats)
ba7678f9 152
89087418 153 ydl = YDL({'format': 'bestaudio'})
ba7678f9
PH
154 ydl.process_ie_result(info_dict.copy())
155 downloaded = ydl.downloaded_info_dicts[0]
89087418 156 self.assertEqual(downloaded['format_id'], 'audio-high')
ba7678f9 157
89087418 158 ydl = YDL({'format': 'worstaudio'})
ba7678f9
PH
159 ydl.process_ie_result(info_dict.copy())
160 downloaded = ydl.downloaded_info_dicts[0]
89087418 161 self.assertEqual(downloaded['format_id'], 'audio-low')
ba7678f9
PH
162
163 formats = [
8508557e
JMF
164 {'format_id': 'vid-low', 'ext': 'mp4', 'preference': 1, 'url': TEST_URL},
165 {'format_id': 'vid-high', 'ext': 'mp4', 'preference': 2, 'url': TEST_URL},
ba7678f9 166 ]
3537b93d 167 info_dict = _make_result(formats)
ba7678f9 168
89087418 169 ydl = YDL({'format': 'bestaudio/worstaudio/best'})
ba7678f9
PH
170 ydl.process_ie_result(info_dict.copy())
171 downloaded = ydl.downloaded_info_dicts[0]
89087418 172 self.assertEqual(downloaded['format_id'], 'vid-high')
ba7678f9 173
0217c783
PH
174 def test_format_selection_audio_exts(self):
175 formats = [
176 {'format_id': 'mp3-64', 'ext': 'mp3', 'abr': 64, 'url': 'http://_', 'vcodec': 'none'},
177 {'format_id': 'ogg-64', 'ext': 'ogg', 'abr': 64, 'url': 'http://_', 'vcodec': 'none'},
178 {'format_id': 'aac-64', 'ext': 'aac', 'abr': 64, 'url': 'http://_', 'vcodec': 'none'},
179 {'format_id': 'mp3-32', 'ext': 'mp3', 'abr': 32, 'url': 'http://_', 'vcodec': 'none'},
180 {'format_id': 'aac-32', 'ext': 'aac', 'abr': 32, 'url': 'http://_', 'vcodec': 'none'},
181 ]
182
183 info_dict = _make_result(formats)
184 ydl = YDL({'format': 'best'})
9f14daf2 185 ydl.sort_formats(info_dict)
0217c783
PH
186 ydl.process_ie_result(copy.deepcopy(info_dict))
187 downloaded = ydl.downloaded_info_dicts[0]
188 self.assertEqual(downloaded['format_id'], 'aac-64')
189
190 ydl = YDL({'format': 'mp3'})
9f14daf2 191 ydl.sort_formats(info_dict)
0217c783
PH
192 ydl.process_ie_result(copy.deepcopy(info_dict))
193 downloaded = ydl.downloaded_info_dicts[0]
194 self.assertEqual(downloaded['format_id'], 'mp3-64')
195
196 ydl = YDL({'prefer_free_formats': True})
9f14daf2 197 ydl.sort_formats(info_dict)
0217c783
PH
198 ydl.process_ie_result(copy.deepcopy(info_dict))
199 downloaded = ydl.downloaded_info_dicts[0]
200 self.assertEqual(downloaded['format_id'], 'ogg-64')
201
bc6d5978
JMF
202 def test_format_selection_video(self):
203 formats = [
8508557e
JMF
204 {'format_id': 'dash-video-low', 'ext': 'mp4', 'preference': 1, 'acodec': 'none', 'url': TEST_URL},
205 {'format_id': 'dash-video-high', 'ext': 'mp4', 'preference': 2, 'acodec': 'none', 'url': TEST_URL},
206 {'format_id': 'vid', 'ext': 'mp4', 'preference': 3, 'url': TEST_URL},
bc6d5978 207 ]
3537b93d 208 info_dict = _make_result(formats)
bc6d5978
JMF
209
210 ydl = YDL({'format': 'bestvideo'})
211 ydl.process_ie_result(info_dict.copy())
212 downloaded = ydl.downloaded_info_dicts[0]
213 self.assertEqual(downloaded['format_id'], 'dash-video-high')
214
215 ydl = YDL({'format': 'worstvideo'})
216 ydl.process_ie_result(info_dict.copy())
217 downloaded = ydl.downloaded_info_dicts[0]
218 self.assertEqual(downloaded['format_id'], 'dash-video-low')
219
4c3b16d5
S
220 ydl = YDL({'format': 'bestvideo[format_id^=dash][format_id$=low]'})
221 ydl.process_ie_result(info_dict.copy())
222 downloaded = ydl.downloaded_info_dicts[0]
223 self.assertEqual(downloaded['format_id'], 'dash-video-low')
224
b913348d 225 formats = [
226 {'format_id': 'vid-vcodec-dot', 'ext': 'mp4', 'preference': 1, 'vcodec': 'avc1.123456', 'acodec': 'none', 'url': TEST_URL},
227 ]
228 info_dict = _make_result(formats)
229
230 ydl = YDL({'format': 'bestvideo[vcodec=avc1.123456]'})
231 ydl.process_ie_result(info_dict.copy())
232 downloaded = ydl.downloaded_info_dicts[0]
233 self.assertEqual(downloaded['format_id'], 'vid-vcodec-dot')
234
2cc779f4
S
235 def test_format_selection_string_ops(self):
236 formats = [
237 {'format_id': 'abc-cba', 'ext': 'mp4', 'url': TEST_URL},
e118a879 238 {'format_id': 'zxc-cxz', 'ext': 'webm', 'url': TEST_URL},
2cc779f4
S
239 ]
240 info_dict = _make_result(formats)
241
242 # equals (=)
243 ydl = YDL({'format': '[format_id=abc-cba]'})
244 ydl.process_ie_result(info_dict.copy())
245 downloaded = ydl.downloaded_info_dicts[0]
246 self.assertEqual(downloaded['format_id'], 'abc-cba')
247
248 # does not equal (!=)
249 ydl = YDL({'format': '[format_id!=abc-cba]'})
e118a879
S
250 ydl.process_ie_result(info_dict.copy())
251 downloaded = ydl.downloaded_info_dicts[0]
252 self.assertEqual(downloaded['format_id'], 'zxc-cxz')
253
254 ydl = YDL({'format': '[format_id!=abc-cba][format_id!=zxc-cxz]'})
2cc779f4
S
255 self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy())
256
257 # starts with (^=)
258 ydl = YDL({'format': '[format_id^=abc]'})
259 ydl.process_ie_result(info_dict.copy())
260 downloaded = ydl.downloaded_info_dicts[0]
261 self.assertEqual(downloaded['format_id'], 'abc-cba')
262
263 # does not start with (!^=)
e118a879
S
264 ydl = YDL({'format': '[format_id!^=abc]'})
265 ydl.process_ie_result(info_dict.copy())
266 downloaded = ydl.downloaded_info_dicts[0]
267 self.assertEqual(downloaded['format_id'], 'zxc-cxz')
268
269 ydl = YDL({'format': '[format_id!^=abc][format_id!^=zxc]'})
2cc779f4
S
270 self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy())
271
272 # ends with ($=)
273 ydl = YDL({'format': '[format_id$=cba]'})
274 ydl.process_ie_result(info_dict.copy())
275 downloaded = ydl.downloaded_info_dicts[0]
276 self.assertEqual(downloaded['format_id'], 'abc-cba')
277
278 # does not end with (!$=)
e118a879
S
279 ydl = YDL({'format': '[format_id!$=cba]'})
280 ydl.process_ie_result(info_dict.copy())
281 downloaded = ydl.downloaded_info_dicts[0]
282 self.assertEqual(downloaded['format_id'], 'zxc-cxz')
283
284 ydl = YDL({'format': '[format_id!$=cba][format_id!$=cxz]'})
2cc779f4
S
285 self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy())
286
287 # contains (*=)
e118a879 288 ydl = YDL({'format': '[format_id*=bc-cb]'})
2cc779f4
S
289 ydl.process_ie_result(info_dict.copy())
290 downloaded = ydl.downloaded_info_dicts[0]
291 self.assertEqual(downloaded['format_id'], 'abc-cba')
292
293 # does not contain (!*=)
e118a879
S
294 ydl = YDL({'format': '[format_id!*=bc-cb]'})
295 ydl.process_ie_result(info_dict.copy())
296 downloaded = ydl.downloaded_info_dicts[0]
297 self.assertEqual(downloaded['format_id'], 'zxc-cxz')
298
299 ydl = YDL({'format': '[format_id!*=abc][format_id!*=zxc]'})
300 self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy())
301
2cc779f4
S
302 ydl = YDL({'format': '[format_id!*=-]'})
303 self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy())
304
3d4a70b8 305 def test_youtube_format_selection(self):
a7191c6f 306 # FIXME: Rewrite in accordance with the new format sorting options
5d0c5371 307 return
5d0c5371 308
3d4a70b8 309 order = [
86bf2905 310 '38', '37', '46', '22', '45', '35', '44', '18', '34', '43', '6', '5', '17', '36', '13',
3d4a70b8
PH
311 # Apple HTTP Live Streaming
312 '96', '95', '94', '93', '92', '132', '151',
313 # 3D
314 '85', '84', '102', '83', '101', '82', '100',
315 # Dash video
c11125f9 316 '137', '248', '136', '247', '135', '246',
3d4a70b8
PH
317 '245', '244', '134', '243', '133', '242', '160',
318 # Dash audio
a053c349 319 '141', '172', '140', '171', '139',
3d4a70b8
PH
320 ]
321
67134eab
JMF
322 def format_info(f_id):
323 info = YoutubeIE._formats[f_id].copy()
1df41411 324
91cb6b50 325 # XXX: In real cases InfoExtractor._parse_mpd_formats() fills up 'acodec'
1df41411
YCH
326 # and 'vcodec', while in tests such information is incomplete since
327 # commit a6c2c24479e5f4827ceb06f64d855329c0a6f593
328 # test_YoutubeDL.test_youtube_format_selection is broken without
329 # this fix
330 if 'acodec' in info and 'vcodec' not in info:
331 info['vcodec'] = 'none'
332 elif 'vcodec' in info and 'acodec' not in info:
333 info['acodec'] = 'none'
334
67134eab
JMF
335 info['format_id'] = f_id
336 info['url'] = 'url:' + f_id
337 return info
338 formats_order = [format_info(f_id) for f_id in order]
339
340 info_dict = _make_result(list(formats_order), extractor='youtube')
341 ydl = YDL({'format': 'bestvideo+bestaudio'})
9f14daf2 342 ydl.sort_formats(info_dict)
67134eab
JMF
343 ydl.process_ie_result(info_dict)
344 downloaded = ydl.downloaded_info_dicts[0]
5d0c5371 345 self.assertEqual(downloaded['format_id'], '248+172')
67134eab 346 self.assertEqual(downloaded['ext'], 'mp4')
3d4a70b8 347
cf2ac6df
JMF
348 info_dict = _make_result(list(formats_order), extractor='youtube')
349 ydl = YDL({'format': 'bestvideo[height>=999999]+bestaudio/best'})
9f14daf2 350 ydl.sort_formats(info_dict)
cf2ac6df
JMF
351 ydl.process_ie_result(info_dict)
352 downloaded = ydl.downloaded_info_dicts[0]
353 self.assertEqual(downloaded['format_id'], '38')
354
f5f4a27a
JMF
355 info_dict = _make_result(list(formats_order), extractor='youtube')
356 ydl = YDL({'format': 'bestvideo/best,bestaudio'})
9f14daf2 357 ydl.sort_formats(info_dict)
f5f4a27a
JMF
358 ydl.process_ie_result(info_dict)
359 downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts]
360 self.assertEqual(downloaded_ids, ['137', '141'])
361
0130afb7
JMF
362 info_dict = _make_result(list(formats_order), extractor='youtube')
363 ydl = YDL({'format': '(bestvideo[ext=mp4],bestvideo[ext=webm])+bestaudio'})
9f14daf2 364 ydl.sort_formats(info_dict)
0130afb7
JMF
365 ydl.process_ie_result(info_dict)
366 downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts]
367 self.assertEqual(downloaded_ids, ['137+141', '248+141'])
368
369 info_dict = _make_result(list(formats_order), extractor='youtube')
370 ydl = YDL({'format': '(bestvideo[ext=mp4],bestvideo[ext=webm])[height<=720]+bestaudio'})
9f14daf2 371 ydl.sort_formats(info_dict)
0130afb7
JMF
372 ydl.process_ie_result(info_dict)
373 downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts]
374 self.assertEqual(downloaded_ids, ['136+141', '247+141'])
375
376 info_dict = _make_result(list(formats_order), extractor='youtube')
377 ydl = YDL({'format': '(bestvideo[ext=none]/bestvideo[ext=webm])+bestaudio'})
9f14daf2 378 ydl.sort_formats(info_dict)
0130afb7
JMF
379 ydl.process_ie_result(info_dict)
380 downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts]
381 self.assertEqual(downloaded_ids, ['248+141'])
382
67134eab 383 for f1, f2 in zip(formats_order, formats_order[1:]):
3537b93d 384 info_dict = _make_result([f1, f2], extractor='youtube')
8dd54188 385 ydl = YDL({'format': 'best/bestvideo'})
9f14daf2 386 ydl.sort_formats(info_dict)
3d4a70b8
PH
387 ydl.process_ie_result(info_dict)
388 downloaded = ydl.downloaded_info_dicts[0]
67134eab 389 self.assertEqual(downloaded['format_id'], f1['format_id'])
3d4a70b8 390
3537b93d 391 info_dict = _make_result([f2, f1], extractor='youtube')
8dd54188 392 ydl = YDL({'format': 'best/bestvideo'})
9f14daf2 393 ydl.sort_formats(info_dict)
3d4a70b8
PH
394 ydl.process_ie_result(info_dict)
395 downloaded = ydl.downloaded_info_dicts[0]
67134eab 396 self.assertEqual(downloaded['format_id'], f1['format_id'])
3d4a70b8 397
317f7ab6
S
398 def test_audio_only_extractor_format_selection(self):
399 # For extractors with incomplete formats (all formats are audio-only or
400 # video-only) best and worst should fallback to corresponding best/worst
401 # video-only or audio-only formats (as per
067aa17e 402 # https://github.com/ytdl-org/youtube-dl/pull/5556)
317f7ab6
S
403 formats = [
404 {'format_id': 'low', 'ext': 'mp3', 'preference': 1, 'vcodec': 'none', 'url': TEST_URL},
405 {'format_id': 'high', 'ext': 'mp3', 'preference': 2, 'vcodec': 'none', 'url': TEST_URL},
406 ]
407 info_dict = _make_result(formats)
408
409 ydl = YDL({'format': 'best'})
410 ydl.process_ie_result(info_dict.copy())
411 downloaded = ydl.downloaded_info_dicts[0]
412 self.assertEqual(downloaded['format_id'], 'high')
413
414 ydl = YDL({'format': 'worst'})
415 ydl.process_ie_result(info_dict.copy())
416 downloaded = ydl.downloaded_info_dicts[0]
417 self.assertEqual(downloaded['format_id'], 'low')
418
419 def test_format_not_available(self):
420 formats = [
421 {'format_id': 'regular', 'ext': 'mp4', 'height': 360, 'url': TEST_URL},
422 {'format_id': 'video', 'ext': 'mp4', 'height': 720, 'acodec': 'none', 'url': TEST_URL},
423 ]
424 info_dict = _make_result(formats)
425
426 # This must fail since complete video-audio format does not match filter
427 # and extractor does not provide incomplete only formats (i.e. only
428 # video-only or audio-only).
429 ydl = YDL({'format': 'best[height>360]'})
430 self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy())
431
8cda78ef 432 def test_format_selection_issue_10083(self):
067aa17e 433 # See https://github.com/ytdl-org/youtube-dl/issues/10083
8cda78ef
S
434 formats = [
435 {'format_id': 'regular', 'height': 360, 'url': TEST_URL},
436 {'format_id': 'video', 'height': 720, 'acodec': 'none', 'url': TEST_URL},
437 {'format_id': 'audio', 'vcodec': 'none', 'url': TEST_URL},
438 ]
439 info_dict = _make_result(formats)
440
441 ydl = YDL({'format': 'best[height>360]/bestvideo[height>360]+bestaudio'})
442 ydl.process_ie_result(info_dict.copy())
443 self.assertEqual(ydl.downloaded_info_dicts[0]['format_id'], 'video+audio')
444
0a31a350
JMF
445 def test_invalid_format_specs(self):
446 def assert_syntax_error(format_spec):
187986a8 447 self.assertRaises(SyntaxError, YDL, {'format': format_spec})
0a31a350
JMF
448
449 assert_syntax_error('bestvideo,,best')
450 assert_syntax_error('+bestaudio')
451 assert_syntax_error('bestvideo+')
d96d604e 452 assert_syntax_error('/')
187986a8 453 assert_syntax_error('[720<height]')
0a31a350 454
083c9df9
PH
455 def test_format_filtering(self):
456 formats = [
457 {'format_id': 'A', 'filesize': 500, 'width': 1000},
458 {'format_id': 'B', 'filesize': 1000, 'width': 500},
459 {'format_id': 'C', 'filesize': 1000, 'width': 400},
460 {'format_id': 'D', 'filesize': 2000, 'width': 600},
461 {'format_id': 'E', 'filesize': 3000},
462 {'format_id': 'F'},
463 {'format_id': 'G', 'filesize': 1000000},
464 ]
465 for f in formats:
466 f['url'] = 'http://_/'
467 f['ext'] = 'unknown'
9f14daf2 468 info_dict = _make_result(formats, _format_sort_fields=('id', ))
083c9df9
PH
469
470 ydl = YDL({'format': 'best[filesize<3000]'})
471 ydl.process_ie_result(info_dict)
472 downloaded = ydl.downloaded_info_dicts[0]
473 self.assertEqual(downloaded['format_id'], 'D')
474
475 ydl = YDL({'format': 'best[filesize<=3000]'})
476 ydl.process_ie_result(info_dict)
477 downloaded = ydl.downloaded_info_dicts[0]
478 self.assertEqual(downloaded['format_id'], 'E')
479
480 ydl = YDL({'format': 'best[filesize <= ? 3000]'})
481 ydl.process_ie_result(info_dict)
482 downloaded = ydl.downloaded_info_dicts[0]
483 self.assertEqual(downloaded['format_id'], 'F')
484
485 ydl = YDL({'format': 'best [filesize = 1000] [width>450]'})
486 ydl.process_ie_result(info_dict)
487 downloaded = ydl.downloaded_info_dicts[0]
488 self.assertEqual(downloaded['format_id'], 'B')
489
490 ydl = YDL({'format': 'best [filesize = 1000] [width!=450]'})
491 ydl.process_ie_result(info_dict)
492 downloaded = ydl.downloaded_info_dicts[0]
493 self.assertEqual(downloaded['format_id'], 'C')
494
495 ydl = YDL({'format': '[filesize>?1]'})
496 ydl.process_ie_result(info_dict)
497 downloaded = ydl.downloaded_info_dicts[0]
498 self.assertEqual(downloaded['format_id'], 'G')
499
500 ydl = YDL({'format': '[filesize<1M]'})
501 ydl.process_ie_result(info_dict)
502 downloaded = ydl.downloaded_info_dicts[0]
503 self.assertEqual(downloaded['format_id'], 'E')
504
505 ydl = YDL({'format': '[filesize<1MiB]'})
506 ydl.process_ie_result(info_dict)
507 downloaded = ydl.downloaded_info_dicts[0]
508 self.assertEqual(downloaded['format_id'], 'G')
509
5acfa126
JMF
510 ydl = YDL({'format': 'all[width>=400][width<=600]'})
511 ydl.process_ie_result(info_dict)
512 downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts]
dd2a987d 513 self.assertEqual(downloaded_ids, ['D', 'C', 'B'])
5acfa126 514
bb8e5536
JMF
515 ydl = YDL({'format': 'best[height<40]'})
516 try:
517 ydl.process_ie_result(info_dict)
518 except ExtractorError:
519 pass
520 self.assertEqual(ydl.downloaded_info_dicts, [])
521
0017d9ad
S
522 def test_default_format_spec(self):
523 ydl = YDL({'simulate': True})
5d0c5371 524 self.assertEqual(ydl._default_format_spec({}), 'bestvideo*+bestaudio/best')
0017d9ad 525
d08dcd2d
S
526 ydl = YDL({})
527 self.assertEqual(ydl._default_format_spec({'is_live': True}), 'best/bestvideo+bestaudio')
af0f7428 528
d08dcd2d 529 ydl = YDL({'simulate': True})
5d0c5371 530 self.assertEqual(ydl._default_format_spec({'is_live': True}), 'bestvideo*+bestaudio/best')
af0f7428 531
0017d9ad 532 ydl = YDL({'outtmpl': '-'})
af0f7428 533 self.assertEqual(ydl._default_format_spec({}), 'best/bestvideo+bestaudio')
0017d9ad
S
534
535 ydl = YDL({})
5d0c5371 536 self.assertEqual(ydl._default_format_spec({}, download=False), 'bestvideo*+bestaudio/best')
af0f7428 537 self.assertEqual(ydl._default_format_spec({'is_live': True}), 'best/bestvideo+bestaudio')
0017d9ad 538
f20bf146
JMF
539
540class TestYoutubeDL(unittest.TestCase):
ab84349b
JMF
541 def test_subtitles(self):
542 def s_formats(lang, autocaption=False):
543 return [{
544 'ext': ext,
86e5f3ed 545 'url': f'http://localhost/video.{lang}.{ext}',
ab84349b
JMF
546 '_auto': autocaption,
547 } for ext in ['vtt', 'srt', 'ass']]
86e5f3ed 548 subtitles = {l: s_formats(l) for l in ['en', 'fr', 'es']}
549 auto_captions = {l: s_formats(l, True) for l in ['it', 'pt', 'es']}
ab84349b
JMF
550 info_dict = {
551 'id': 'test',
552 'title': 'Test',
553 'url': 'http://localhost/video.mp4',
554 'subtitles': subtitles,
555 'automatic_captions': auto_captions,
556 'extractor': 'TEST',
732044af 557 'webpage_url': 'http://example.com/watch?v=shenanigans',
ab84349b
JMF
558 }
559
560 def get_info(params={}):
561 params.setdefault('simulate', True)
562 ydl = YDL(params)
563 ydl.report_warning = lambda *args, **kargs: None
564 return ydl.process_video_result(info_dict, download=False)
565
566 result = get_info()
567 self.assertFalse(result.get('requested_subtitles'))
568 self.assertEqual(result['subtitles'], subtitles)
569 self.assertEqual(result['automatic_captions'], auto_captions)
570
571 result = get_info({'writesubtitles': True})
572 subs = result['requested_subtitles']
573 self.assertTrue(subs)
86e5f3ed 574 self.assertEqual(set(subs.keys()), {'en'})
ab84349b
JMF
575 self.assertTrue(subs['en'].get('data') is None)
576 self.assertEqual(subs['en']['ext'], 'ass')
577
578 result = get_info({'writesubtitles': True, 'subtitlesformat': 'foo/srt'})
579 subs = result['requested_subtitles']
580 self.assertEqual(subs['en']['ext'], 'srt')
581
582 result = get_info({'writesubtitles': True, 'subtitleslangs': ['es', 'fr', 'it']})
583 subs = result['requested_subtitles']
584 self.assertTrue(subs)
86e5f3ed 585 self.assertEqual(set(subs.keys()), {'es', 'fr'})
ab84349b 586
c32b0aab 587 result = get_info({'writesubtitles': True, 'subtitleslangs': ['all', '-en']})
588 subs = result['requested_subtitles']
589 self.assertTrue(subs)
86e5f3ed 590 self.assertEqual(set(subs.keys()), {'es', 'fr'})
c32b0aab 591
592 result = get_info({'writesubtitles': True, 'subtitleslangs': ['en', 'fr', '-en']})
593 subs = result['requested_subtitles']
594 self.assertTrue(subs)
86e5f3ed 595 self.assertEqual(set(subs.keys()), {'fr'})
c32b0aab 596
597 result = get_info({'writesubtitles': True, 'subtitleslangs': ['-en', 'en']})
598 subs = result['requested_subtitles']
599 self.assertTrue(subs)
86e5f3ed 600 self.assertEqual(set(subs.keys()), {'en'})
c32b0aab 601
602 result = get_info({'writesubtitles': True, 'subtitleslangs': ['e.+']})
603 subs = result['requested_subtitles']
604 self.assertTrue(subs)
86e5f3ed 605 self.assertEqual(set(subs.keys()), {'es', 'en'})
c32b0aab 606
ab84349b
JMF
607 result = get_info({'writesubtitles': True, 'writeautomaticsub': True, 'subtitleslangs': ['es', 'pt']})
608 subs = result['requested_subtitles']
609 self.assertTrue(subs)
86e5f3ed 610 self.assertEqual(set(subs.keys()), {'es', 'pt'})
ab84349b
JMF
611 self.assertFalse(subs['es']['_auto'])
612 self.assertTrue(subs['pt']['_auto'])
613
98c70d6f
JMF
614 result = get_info({'writeautomaticsub': True, 'subtitleslangs': ['es', 'pt']})
615 subs = result['requested_subtitles']
616 self.assertTrue(subs)
86e5f3ed 617 self.assertEqual(set(subs.keys()), {'es', 'pt'})
98c70d6f
JMF
618 self.assertTrue(subs['es']['_auto'])
619 self.assertTrue(subs['pt']['_auto'])
620
b6c45014
JMF
621 def test_add_extra_info(self):
622 test_dict = {
623 'extractor': 'Foo',
624 }
625 extra_info = {
626 'extractor': 'Bar',
627 'playlist': 'funny videos',
628 }
629 YDL.add_extra_info(test_dict, extra_info)
630 self.assertEqual(test_dict['extractor'], 'Foo')
631 self.assertEqual(test_dict['playlist'], 'funny videos')
632
752cda38 633 outtmpl_info = {
634 'id': '1234',
635 'ext': 'mp4',
636 'width': None,
637 'height': 1080,
abbeeebc 638 'filesize': 1024,
752cda38 639 'title1': '$PATH',
640 'title2': '%PATH%',
87ea7dfc 641 'title3': 'foo/bar\\test',
7d1eb38a 642 'title4': 'foo "bar" test',
524e2e4f 643 'title5': 'áéí 𝐀',
752cda38 644 'timestamp': 1618488000,
645 'duration': 100000,
646 'playlist_index': 1,
e6f21b3d 647 'playlist_autonumber': 2,
0a5a191a 648 '__last_playlist_index': 100,
752cda38 649 'n_entries': 10,
07a1250e 650 'formats': [
651 {'id': 'id 1', 'height': 1080, 'width': 1920},
652 {'id': 'id 2', 'height': 720},
653 {'id': 'id 3'}
654 ]
752cda38 655 }
656
5c6542ce 657 def test_prepare_outtmpl_and_filename(self):
9fea350f 658 def test(tmpl, expected, *, info=None, **params):
752cda38 659 params['outtmpl'] = tmpl
d2c8aadf 660 ydl = FakeYDL(params)
752cda38 661 ydl._num_downloads = 1
5c6542ce 662 self.assertEqual(ydl.validate_outtmpl(tmpl), None)
752cda38 663
819e0531 664 out = ydl.evaluate_outtmpl(tmpl, info or self.outtmpl_info)
9fea350f 665 fname = ydl.prepare_filename(info or self.outtmpl_info)
5c6542ce 666
2b8a2973 667 if not isinstance(expected, (list, tuple)):
668 expected = (expected, expected)
669 for (name, got), expect in zip((('outtmpl', out), ('filename', fname)), expected):
670 if callable(expect):
671 self.assertTrue(expect(got), f'Wrong {name} from {tmpl}')
672 else:
673 self.assertEqual(got, expect, f'Wrong {name} from {tmpl}')
5c6542ce 674
6e84b215 675 # Side-effects
676 original_infodict = dict(self.outtmpl_info)
677 test('foo.bar', 'foo.bar')
678 original_infodict['epoch'] = self.outtmpl_info.get('epoch')
679 self.assertTrue(isinstance(original_infodict['epoch'], int))
680 test('%(epoch)d', int_or_none)
681 self.assertEqual(original_infodict, self.outtmpl_info)
682
5c6542ce 683 # Auto-generated fields
684 test('%(id)s.%(ext)s', '1234.mp4')
685 test('%(duration_string)s', ('27:46:40', '27-46-40'))
5c6542ce 686 test('%(resolution)s', '1080p')
687 test('%(playlist_index)s', '001')
e6f21b3d 688 test('%(playlist_autonumber)s', '02')
5c6542ce 689 test('%(autonumber)s', '00001')
690 test('%(autonumber+2)03d', '005', autonumber_start=3)
691 test('%(autonumber)s', '001', autonumber_size=3)
692
693 # Escaping %
901130bb 694 test('%', '%')
5c6542ce 695 test('%%', '%')
696 test('%%%%', '%%')
901130bb 697 test('%s', '%s')
698 test('%%%s', '%%s')
699 test('%d', '%d')
700 test('%abc%', '%abc%')
5c6542ce 701 test('%%(width)06d.%(ext)s', '%(width)06d.mp4')
901130bb 702 test('%%%(height)s', '%1080')
5c6542ce 703 test('%(width)06d.%(ext)s', 'NA.mp4')
704 test('%(width)06d.%%(ext)s', 'NA.%(ext)s')
705 test('%%(width)06d.%(ext)s', '%(width)06d.mp4')
706
9fea350f 707 # ID sanitization
708 test('%(id)s', '_abcd', info={'id': '_abcd'})
709 test('%(some_id)s', '_abcd', info={'some_id': '_abcd'})
710 test('%(formats.0.id)s', '_abcd', info={'formats': [{'id': '_abcd'}]})
711 test('%(id)s', '-abcd', info={'id': '-abcd'})
712 test('%(id)s', '.abcd', info={'id': '.abcd'})
713 test('%(id)s', 'ab__cd', info={'id': 'ab__cd'})
97d9c79e 714 test('%(id)s', ('ab:cd', 'ab:cd'), info={'id': 'ab:cd'})
e0fd9573 715 test('%(id.0)s', '-', info={'id': '--'})
9fea350f 716
5c6542ce 717 # Invalid templates
5c6542ce 718 self.assertTrue(isinstance(YoutubeDL.validate_outtmpl('%(title)'), ValueError))
719 test('%(invalid@tmpl|def)s', 'none', outtmpl_na_placeholder='none')
2b8a2973 720 test('%(..)s', 'NA')
07a1250e 721 test('%(formats.{id)s', 'NA')
2b8a2973 722
723 # Entire info_dict
724 def expect_same_infodict(out):
725 got_dict = json.loads(out)
726 for info_field, expected in self.outtmpl_info.items():
727 self.assertEqual(got_dict.get(info_field), expected, info_field)
728 return True
729
730 test('%()j', (expect_same_infodict, str))
5c6542ce 731
732 # NA placeholder
752cda38 733 NA_TEST_OUTTMPL = '%(uploader_date)s-%(width)d-%(x|def)s-%(id)s.%(ext)s'
5c6542ce 734 test(NA_TEST_OUTTMPL, 'NA-NA-def-1234.mp4')
735 test(NA_TEST_OUTTMPL, 'none-none-def-1234.mp4', outtmpl_na_placeholder='none')
736 test(NA_TEST_OUTTMPL, '--def-1234.mp4', outtmpl_na_placeholder='')
582fad70 737 test('%(non_existent.0)s', 'NA')
752cda38 738
5c6542ce 739 # String formatting
752cda38 740 FMT_TEST_OUTTMPL = '%%(height)%s.%%(ext)s'
5c6542ce 741 test(FMT_TEST_OUTTMPL % 's', '1080.mp4')
742 test(FMT_TEST_OUTTMPL % 'd', '1080.mp4')
743 test(FMT_TEST_OUTTMPL % '6d', ' 1080.mp4')
744 test(FMT_TEST_OUTTMPL % '-6d', '1080 .mp4')
745 test(FMT_TEST_OUTTMPL % '06d', '001080.mp4')
746 test(FMT_TEST_OUTTMPL % ' 06d', ' 01080.mp4')
747 test(FMT_TEST_OUTTMPL % ' 06d', ' 01080.mp4')
748 test(FMT_TEST_OUTTMPL % '0 6d', ' 01080.mp4')
749 test(FMT_TEST_OUTTMPL % '0 6d', ' 01080.mp4')
750 test(FMT_TEST_OUTTMPL % ' 0 6d', ' 01080.mp4')
751
752 # Type casting
753 test('%(id)d', '1234')
754 test('%(height)c', '1')
755 test('%(ext)c', 'm')
756 test('%(id)d %(id)r', "1234 '1234'")
757 test('%(id)r %(height)r', "'1234' 1080")
758 test('%(ext)s-%(ext|def)d', 'mp4-def')
759 test('%(width|0)04d', '0000')
760 test('a%(width|)d', 'a', outtmpl_na_placeholder='none')
761
752cda38 762 FORMATS = self.outtmpl_info['formats']
97d9c79e 763 sanitize = lambda x: x.replace(':', ':').replace('"', """).replace('\n', ' ')
7d1eb38a 764
765 # Custom type casting
4476d2c7 766 test('%(formats.:.id)l', 'id 1, id 2, id 3')
767 test('%(formats.:.id)#l', ('id 1\nid 2\nid 3', 'id 1 id 2 id 3'))
7d1eb38a 768 test('%(ext)l', 'mp4')
4476d2c7 769 test('%(formats.:.id) 18l', ' id 1, id 2, id 3')
7d1eb38a 770 test('%(formats)j', (json.dumps(FORMATS), sanitize(json.dumps(FORMATS))))
4476d2c7 771 test('%(formats)#j', (json.dumps(FORMATS, indent=4), sanitize(json.dumps(FORMATS, indent=4))))
f5aa5cfb 772 test('%(title5).3B', 'á')
524e2e4f 773 test('%(title5)U', 'áéí 𝐀')
774 test('%(title5)#U', 'a\u0301e\u0301i\u0301 𝐀')
775 test('%(title5)+U', 'áéí A')
776 test('%(title5)+#U', 'a\u0301e\u0301i\u0301 A')
abbeeebc 777 test('%(height)D', '1k')
778 test('%(filesize)#D', '1Ki')
779 test('%(height)5.2D', ' 1.08k')
37893bb0 780 test('%(title4)#S', 'foo_bar_test')
97d9c79e 781 test('%(title4).10S', ('foo "bar" ', 'foo "bar"' + ('#' if compat_os_name == 'nt' else ' ')))
7d1eb38a 782 if compat_os_name == 'nt':
97d9c79e 783 test('%(title4)q', ('"foo \\"bar\\" test"', ""foo ⧹"bar⧹" test""))
784 test('%(formats.:.id)#q', ('"id 1" "id 2" "id 3"', '"id 1" "id 2" "id 3"'))
785 test('%(formats.0.id)#q', ('"id 1"', '"id 1"'))
7d1eb38a 786 else:
97d9c79e 787 test('%(title4)q', ('\'foo "bar" test\'', '\'foo "bar" test\''))
4476d2c7 788 test('%(formats.:.id)#q', "'id 1' 'id 2' 'id 3'")
789 test('%(formats.0.id)#q', "'id 1'")
7d1eb38a 790
791 # Internal formatting
5c6542ce 792 test('%(timestamp-1000>%H-%M-%S)s', '11-43-20')
901130bb 793 test('%(title|%)s %(title|%%)s', '% %%')
5c6542ce 794 test('%(id+1-height+3)05d', '00158')
795 test('%(width+100)05d', 'NA')
7d1eb38a 796 test('%(formats.0) 15s', ('% 15s' % FORMATS[0], '% 15s' % sanitize(str(FORMATS[0]))))
797 test('%(formats.0)r', (repr(FORMATS[0]), sanitize(repr(FORMATS[0]))))
5c6542ce 798 test('%(height.0)03d', '001')
799 test('%(-height.0)04d', '-001')
800 test('%(formats.-1.id)s', FORMATS[-1]['id'])
801 test('%(formats.0.id.-1)d', FORMATS[0]['id'][-1])
802 test('%(formats.3)s', 'NA')
803 test('%(formats.:2:-1)r', repr(FORMATS[:2:-1]))
804 test('%(formats.0.id.-1+id)f', '1235.000000')
385a27fa 805 test('%(formats.0.id.-1+formats.1.id.-1)d', '3')
07a1250e 806 out = json.dumps([{'id': f['id'], 'height.:2': str(f['height'])[:2]}
807 if 'height' in f else {'id': f['id']}
808 for f in FORMATS])
809 test('%(formats.:.{id,height.:2})j', (out, sanitize(out)))
810 test('%(formats.:.{id,height}.id)l', ', '.join(f['id'] for f in FORMATS))
811 test('%(.{id,title})j', ('{"id": "1234"}', '{"id": "1234"}'))
5c6542ce 812
7c37ff97 813 # Alternates
814 test('%(title,id)s', '1234')
815 test('%(width-100,height+20|def)d', '1100')
816 test('%(width-100,height+width|def)s', 'def')
817 test('%(timestamp-x>%H\\,%M\\,%S,timestamp>%H\\,%M\\,%S)s', '12,00,00')
818
e0fd9573 819 # Replacement
820 test('%(id&foo)s.bar', 'foo.bar')
821 test('%(title&foo)s.bar', 'NA.bar')
822 test('%(title&foo|baz)s.bar', 'baz.bar')
34baa9fd 823 test('%(x,id&foo|baz)s.bar', 'foo.bar')
824 test('%(x,title&foo|baz)s.bar', 'baz.bar')
78fde6e3 825 test('%(title&\n|)s', '\n')
e0fd9573 826
6e84b215 827 # Laziness
828 def gen():
829 yield from range(5)
830 raise self.assertTrue(False, 'LazyList should not be evaluated till here')
831 test('%(key.4)s', '4', info={'key': LazyList(gen())})
832
5c6542ce 833 # Empty filename
834 test('%(foo|)s-%(bar|)s.%(ext)s', '-.mp4')
835 # test('%(foo|)s.%(ext)s', ('.mp4', '_.mp4')) # fixme
836 # test('%(foo|)s', ('', '_')) # fixme
837
901130bb 838 # Environment variable expansion for prepare_filename
ac668111 839 os.environ['__yt_dlp_var'] = 'expanded'
901130bb 840 envvar = '%__yt_dlp_var%' if compat_os_name == 'nt' else '$__yt_dlp_var'
841 test(envvar, (envvar, 'expanded'))
b836dc94 842 if compat_os_name == 'nt':
843 test('%s%', ('%s%', '%s%'))
ac668111 844 os.environ['s'] = 'expanded'
b836dc94 845 test('%s%', ('%s%', 'expanded')) # %s% should be expanded before escaping %s
ac668111 846 os.environ['(test)s'] = 'expanded'
b836dc94 847 test('%(test)s%', ('NA%', 'expanded')) # Environment should take priority over template
901130bb 848
5c6542ce 849 # Path expansion and escaping
850 test('Hello %(title1)s', 'Hello $PATH')
851 test('Hello %(title2)s', 'Hello %PATH%')
97d9c79e 852 test('%(title3)s', ('foo/bar\\test', 'foo⧸bar⧹test'))
853 test('folder/%(title3)s', ('folder/foo/bar\\test', 'folder%sfoo⧸bar⧹test' % os.path.sep))
26e63931 854
c57f7757
PH
855 def test_format_note(self):
856 ydl = YoutubeDL()
857 self.assertEqual(ydl._format_note({}), '')
858 assertRegexpMatches(self, ydl._format_note({
859 'vbr': 10,
398dea32 860 }), r'^\s*10k$')
5d583bdf
S
861 assertRegexpMatches(self, ydl._format_note({
862 'fps': 30,
398dea32 863 }), r'^30fps$')
5d583bdf 864
2b4ecde2
JMF
865 def test_postprocessors(self):
866 filename = 'post-processor-testfile.mp4'
867 audiofile = filename + '.mp3'
868
869 class SimplePP(PostProcessor):
870 def run(self, info):
2b4ecde2
JMF
871 with open(audiofile, 'wt') as f:
872 f.write('EXAMPLE')
592e97e8 873 return [info['filepath']], info
2b4ecde2 874
592e97e8 875 def run_pp(params, PP):
2b4ecde2
JMF
876 with open(filename, 'wt') as f:
877 f.write('EXAMPLE')
878 ydl = YoutubeDL(params)
592e97e8 879 ydl.add_post_processor(PP())
2b4ecde2
JMF
880 ydl.post_process(filename, {'filepath': filename})
881
592e97e8 882 run_pp({'keepvideo': True}, SimplePP)
2b4ecde2
JMF
883 self.assertTrue(os.path.exists(filename), '%s doesn\'t exist' % filename)
884 self.assertTrue(os.path.exists(audiofile), '%s doesn\'t exist' % audiofile)
885 os.unlink(filename)
886 os.unlink(audiofile)
887
592e97e8 888 run_pp({'keepvideo': False}, SimplePP)
2b4ecde2
JMF
889 self.assertFalse(os.path.exists(filename), '%s exists' % filename)
890 self.assertTrue(os.path.exists(audiofile), '%s doesn\'t exist' % audiofile)
891 os.unlink(audiofile)
892
592e97e8
JMF
893 class ModifierPP(PostProcessor):
894 def run(self, info):
895 with open(info['filepath'], 'wt') as f:
896 f.write('MODIFIED')
897 return [], info
898
899 run_pp({'keepvideo': False}, ModifierPP)
900 self.assertTrue(os.path.exists(filename), '%s doesn\'t exist' % filename)
901 os.unlink(filename)
902
531980d8 903 def test_match_filter(self):
531980d8
JMF
904 first = {
905 'id': '1',
906 'url': TEST_URL,
907 'title': 'one',
908 'extractor': 'TEST',
909 'duration': 30,
910 'filesize': 10 * 1024,
e5a088dc 911 'playlist_id': '42',
db13c16e
S
912 'uploader': "變態妍字幕版 太妍 тест",
913 'creator': "тест ' 123 ' тест--",
732044af 914 'webpage_url': 'http://example.com/watch?v=shenanigans',
531980d8
JMF
915 }
916 second = {
917 'id': '2',
918 'url': TEST_URL,
919 'title': 'two',
920 'extractor': 'TEST',
921 'duration': 10,
922 'description': 'foo',
923 'filesize': 5 * 1024,
e5a088dc 924 'playlist_id': '43',
db13c16e 925 'uploader': "тест 123",
732044af 926 'webpage_url': 'http://example.com/watch?v=SHENANIGANS',
531980d8
JMF
927 }
928 videos = [first, second]
929
930 def get_videos(filter_=None):
09b49e1f 931 ydl = YDL({'match_filter': filter_, 'simulate': True})
531980d8
JMF
932 for v in videos:
933 ydl.process_ie_result(v, download=True)
934 return [v['id'] for v in ydl.downloaded_info_dicts]
935
936 res = get_videos()
937 self.assertEqual(res, ['1', '2'])
938
6db9c4d5 939 def f(v, incomplete):
531980d8
JMF
940 if v['id'] == '1':
941 return None
942 else:
943 return 'Video id is not 1'
944 res = get_videos(f)
945 self.assertEqual(res, ['1'])
946
947 f = match_filter_func('duration < 30')
948 res = get_videos(f)
949 self.assertEqual(res, ['2'])
950
951 f = match_filter_func('description = foo')
952 res = get_videos(f)
953 self.assertEqual(res, ['2'])
954
955 f = match_filter_func('description =? foo')
956 res = get_videos(f)
957 self.assertEqual(res, ['1', '2'])
958
959 f = match_filter_func('filesize > 5KiB')
960 res = get_videos(f)
961 self.assertEqual(res, ['1'])
962
e5a088dc
S
963 f = match_filter_func('playlist_id = 42')
964 res = get_videos(f)
965 self.assertEqual(res, ['1'])
966
db13c16e
S
967 f = match_filter_func('uploader = "變態妍字幕版 太妍 тест"')
968 res = get_videos(f)
969 self.assertEqual(res, ['1'])
970
971 f = match_filter_func('uploader != "變態妍字幕版 太妍 тест"')
972 res = get_videos(f)
973 self.assertEqual(res, ['2'])
974
975 f = match_filter_func('creator = "тест \' 123 \' тест--"')
976 res = get_videos(f)
977 self.assertEqual(res, ['1'])
978
979 f = match_filter_func("creator = 'тест \\' 123 \\' тест--'")
980 res = get_videos(f)
981 self.assertEqual(res, ['1'])
982
983 f = match_filter_func(r"creator = 'тест \' 123 \' тест--' & duration > 30")
984 res = get_videos(f)
985 self.assertEqual(res, [])
986
e9eaf3fb 987 def test_playlist_items_selection(self):
7e88d7d7 988 INDICES, PAGE_SIZE = list(range(1, 11)), 3
989
990 def entry(i, evaluated):
991 evaluated.append(i)
992 return {
993 'id': str(i),
994 'title': str(i),
995 'url': TEST_URL,
996 }
997
998 def pagedlist_entries(evaluated):
999 def page_func(n):
1000 start = PAGE_SIZE * n
1001 for i in INDICES[start: start + PAGE_SIZE]:
1002 yield entry(i, evaluated)
1003 return OnDemandPagedList(page_func, PAGE_SIZE)
1004
1005 def page_num(i):
1006 return (i + PAGE_SIZE - 1) // PAGE_SIZE
e9eaf3fb 1007
7e88d7d7 1008 def generator_entries(evaluated):
1009 for i in INDICES:
1010 yield entry(i, evaluated)
1011
1012 def list_entries(evaluated):
1013 return list(generator_entries(evaluated))
1014
1015 def lazylist_entries(evaluated):
1016 return LazyList(generator_entries(evaluated))
1017
1018 def get_downloaded_info_dicts(params, entries):
e9eaf3fb 1019 ydl = YDL(params)
7e88d7d7 1020 ydl.process_ie_result({
1021 '_type': 'playlist',
1022 'id': 'test',
1023 'extractor': 'test:playlist',
1024 'extractor_key': 'test:playlist',
1025 'webpage_url': 'http://example.com',
1026 'entries': entries,
1027 })
4e9e1e24
S
1028 return ydl.downloaded_info_dicts
1029
7e88d7d7 1030 def test_selection(params, expected_ids, evaluate_all=False):
1031 expected_ids = list(expected_ids)
1032 if evaluate_all:
1033 generator_eval = pagedlist_eval = INDICES
1034 elif not expected_ids:
1035 generator_eval = pagedlist_eval = []
1036 else:
1037 generator_eval = INDICES[0: max(expected_ids)]
1038 pagedlist_eval = INDICES[PAGE_SIZE * page_num(min(expected_ids)) - PAGE_SIZE:
1039 PAGE_SIZE * page_num(max(expected_ids))]
1040
1041 for name, func, expected_eval in (
1042 ('list', list_entries, INDICES),
1043 ('Generator', generator_entries, generator_eval),
7e9a6125 1044 # ('LazyList', lazylist_entries, generator_eval), # Generator and LazyList follow the exact same code path
7e88d7d7 1045 ('PagedList', pagedlist_entries, pagedlist_eval),
1046 ):
1047 evaluated = []
1048 entries = func(evaluated)
1049 results = [(v['playlist_autonumber'] - 1, (int(v['id']), v['playlist_index']))
1050 for v in get_downloaded_info_dicts(params, entries)]
1051 self.assertEqual(results, list(enumerate(zip(expected_ids, expected_ids))), f'Entries of {name} for {params}')
1052 self.assertEqual(sorted(evaluated), expected_eval, f'Evaluation of {name} for {params}')
f2df4071 1053
7e88d7d7 1054 test_selection({}, INDICES)
1055 test_selection({'playlistend': 20}, INDICES, True)
1056 test_selection({'playlistend': 2}, INDICES[:2])
1057 test_selection({'playliststart': 11}, [], True)
1058 test_selection({'playliststart': 2}, INDICES[1:])
1059 test_selection({'playlist_items': '2-4'}, INDICES[1:4])
9e598870 1060 test_selection({'playlist_items': '2,4'}, [2, 4])
7e88d7d7 1061 test_selection({'playlist_items': '20'}, [], True)
ff1c7fc9 1062 test_selection({'playlist_items': '0'}, [])
cd6fc19e 1063
4e9e1e24 1064 # Tests for https://github.com/ytdl-org/youtube-dl/issues/10591
9e598870 1065 test_selection({'playlist_items': '2-4,3-4,3'}, [2, 3, 4])
1066 test_selection({'playlist_items': '4,2'}, [4, 2])
1067
1068 # Tests for https://github.com/yt-dlp/yt-dlp/issues/720
1069 # https://github.com/yt-dlp/yt-dlp/issues/302
7e88d7d7 1070 test_selection({'playlistreverse': True}, INDICES[::-1])
1071 test_selection({'playliststart': 2, 'playlistreverse': True}, INDICES[:0:-1])
9e598870 1072 test_selection({'playlist_items': '2,4', 'playlistreverse': True}, [4, 2])
1073 test_selection({'playlist_items': '4,2'}, [4, 2])
4e9e1e24 1074
7e88d7d7 1075 # Tests for --playlist-items start:end:step
1076 test_selection({'playlist_items': ':'}, INDICES, True)
1077 test_selection({'playlist_items': '::1'}, INDICES, True)
1078 test_selection({'playlist_items': '::-1'}, INDICES[::-1], True)
1079 test_selection({'playlist_items': ':6'}, INDICES[:6])
1080 test_selection({'playlist_items': ':-6'}, INDICES[:-5], True)
1081 test_selection({'playlist_items': '-1:6:-2'}, INDICES[:4:-2], True)
1082 test_selection({'playlist_items': '9:-6:-2'}, INDICES[8:3:-2], True)
1083
1084 test_selection({'playlist_items': '1:inf:2'}, INDICES[::2], True)
1085 test_selection({'playlist_items': '-2:inf'}, INDICES[-2:], True)
1086 test_selection({'playlist_items': ':inf:-1'}, [], True)
1087 test_selection({'playlist_items': '0-2:2'}, [2])
1088 test_selection({'playlist_items': '1-:2'}, INDICES[::2], True)
1089 test_selection({'playlist_items': '0--2:2'}, INDICES[1:-1:2], True)
1090
1091 test_selection({'playlist_items': '10::3'}, [10], True)
1092 test_selection({'playlist_items': '-1::3'}, [10], True)
1093 test_selection({'playlist_items': '11::3'}, [], True)
1094 test_selection({'playlist_items': '-15::2'}, INDICES[1::2], True)
1095 test_selection({'playlist_items': '-15::15'}, [], True)
1096
e37afbe0 1097 def test_urlopen_no_file_protocol(self):
067aa17e 1098 # see https://github.com/ytdl-org/youtube-dl/issues/8227
e37afbe0 1099 ydl = YDL()
ac668111 1100 self.assertRaises(urllib.error.URLError, ydl.urlopen, 'file:///etc/passwd')
e37afbe0 1101
b286f201
YCH
1102 def test_do_not_override_ie_key_in_url_transparent(self):
1103 ydl = YDL()
1104
1105 class Foo1IE(InfoExtractor):
1106 _VALID_URL = r'foo1:'
1107
1108 def _real_extract(self, url):
1109 return {
1110 '_type': 'url_transparent',
1111 'url': 'foo2:',
1112 'ie_key': 'Foo2',
0396806f
S
1113 'title': 'foo1 title',
1114 'id': 'foo1_id',
b286f201
YCH
1115 }
1116
1117 class Foo2IE(InfoExtractor):
1118 _VALID_URL = r'foo2:'
1119
1120 def _real_extract(self, url):
1121 return {
1122 '_type': 'url',
1123 'url': 'foo3:',
1124 'ie_key': 'Foo3',
1125 }
1126
1127 class Foo3IE(InfoExtractor):
1128 _VALID_URL = r'foo3:'
1129
1130 def _real_extract(self, url):
51350db5 1131 return _make_result([{'url': TEST_URL}], title='foo3 title')
b286f201
YCH
1132
1133 ydl.add_info_extractor(Foo1IE(ydl))
1134 ydl.add_info_extractor(Foo2IE(ydl))
1135 ydl.add_info_extractor(Foo3IE(ydl))
1136 ydl.extract_info('foo1:')
1137 downloaded = ydl.downloaded_info_dicts[0]
1138 self.assertEqual(downloaded['url'], TEST_URL)
51350db5 1139 self.assertEqual(downloaded['title'], 'foo1 title')
0396806f
S
1140 self.assertEqual(downloaded['id'], 'testid')
1141 self.assertEqual(downloaded['extractor'], 'testex')
1142 self.assertEqual(downloaded['extractor_key'], 'TestEx')
b286f201 1143
a0566bbf 1144 # Test case for https://github.com/ytdl-org/youtube-dl/issues/27064
1145 def test_ignoreerrors_for_playlist_with_url_transparent_iterable_entries(self):
1146
1147 class _YDL(YDL):
1148 def __init__(self, *args, **kwargs):
86e5f3ed 1149 super().__init__(*args, **kwargs)
a0566bbf 1150
1151 def trouble(self, s, tb=None):
1152 pass
1153
1154 ydl = _YDL({
1155 'format': 'extra',
1156 'ignoreerrors': True,
1157 })
1158
1159 class VideoIE(InfoExtractor):
1160 _VALID_URL = r'video:(?P<id>\d+)'
1161
1162 def _real_extract(self, url):
1163 video_id = self._match_id(url)
1164 formats = [{
1165 'format_id': 'default',
1166 'url': 'url:',
1167 }]
1168 if video_id == '0':
1169 raise ExtractorError('foo')
1170 if video_id == '2':
1171 formats.append({
1172 'format_id': 'extra',
1173 'url': TEST_URL,
1174 })
1175 return {
1176 'id': video_id,
1177 'title': 'Video %s' % video_id,
1178 'formats': formats,
1179 }
1180
1181 class PlaylistIE(InfoExtractor):
1182 _VALID_URL = r'playlist:'
1183
1184 def _entries(self):
1185 for n in range(3):
14f25df2 1186 video_id = str(n)
a0566bbf 1187 yield {
1188 '_type': 'url_transparent',
1189 'ie_key': VideoIE.ie_key(),
1190 'id': video_id,
1191 'url': 'video:%s' % video_id,
1192 'title': 'Video Transparent %s' % video_id,
1193 }
1194
1195 def _real_extract(self, url):
1196 return self.playlist_result(self._entries())
1197
1198 ydl.add_info_extractor(VideoIE(ydl))
1199 ydl.add_info_extractor(PlaylistIE(ydl))
1200 info = ydl.extract_info('playlist:')
1201 entries = info['entries']
1202 self.assertEqual(len(entries), 3)
1203 self.assertTrue(entries[0] is None)
1204 self.assertTrue(entries[1] is None)
1205 self.assertEqual(len(ydl.downloaded_info_dicts), 1)
1206 downloaded = ydl.downloaded_info_dicts[0]
9e907ebd 1207 entries[2].pop('requested_downloads', None)
a0566bbf 1208 self.assertEqual(entries[2], downloaded)
1209 self.assertEqual(downloaded['url'], TEST_URL)
1210 self.assertEqual(downloaded['title'], 'Video Transparent 2')
1211 self.assertEqual(downloaded['id'], '2')
1212 self.assertEqual(downloaded['extractor'], 'Video')
1213 self.assertEqual(downloaded['extractor_key'], 'Video')
1214
2b4ecde2 1215
e028d0d1
JMF
1216if __name__ == '__main__':
1217 unittest.main()