]> jfr.im git - yt-dlp.git/blame - test/test_YoutubeDL.py
Update to ytdl-commit-ed5c44e7
[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)
3d4a70b8
PH
71 yie = YoutubeIE(ydl)
72 yie._sort_formats(info_dict['formats'])
e028d0d1
JMF
73 ydl.process_ie_result(info_dict)
74 downloaded = ydl.downloaded_info_dicts[0]
89087418 75 self.assertEqual(downloaded['ext'], 'webm')
e028d0d1
JMF
76
77 # Different resolution => download best quality (mp4)
78 ydl = YDL()
79 ydl.params['prefer_free_formats'] = True
5d254f77 80 formats = [
8508557e
JMF
81 {'ext': 'webm', 'height': 720, 'url': TEST_URL},
82 {'ext': 'mp4', 'height': 1080, 'url': TEST_URL},
5d254f77 83 ]
89087418 84 info_dict['formats'] = formats
3d4a70b8
PH
85 yie = YoutubeIE(ydl)
86 yie._sort_formats(info_dict['formats'])
e028d0d1
JMF
87 ydl.process_ie_result(info_dict)
88 downloaded = ydl.downloaded_info_dicts[0]
89087418 89 self.assertEqual(downloaded['ext'], 'mp4')
e028d0d1 90
5d0c5371 91 # No prefer_free_formats => prefer mp4 and webm
e028d0d1
JMF
92 ydl = YDL()
93 ydl.params['prefer_free_formats'] = False
5d254f77 94 formats = [
8508557e
JMF
95 {'ext': 'webm', 'height': 720, 'url': TEST_URL},
96 {'ext': 'mp4', 'height': 720, 'url': TEST_URL},
97 {'ext': 'flv', 'height': 720, 'url': TEST_URL},
5d254f77 98 ]
89087418 99 info_dict['formats'] = formats
3d4a70b8
PH
100 yie = YoutubeIE(ydl)
101 yie._sort_formats(info_dict['formats'])
102 ydl.process_ie_result(info_dict)
103 downloaded = ydl.downloaded_info_dicts[0]
89087418 104 self.assertEqual(downloaded['ext'], 'mp4')
3d4a70b8
PH
105
106 ydl = YDL()
107 ydl.params['prefer_free_formats'] = False
108 formats = [
8508557e
JMF
109 {'ext': 'flv', 'height': 720, 'url': TEST_URL},
110 {'ext': 'webm', 'height': 720, 'url': TEST_URL},
3d4a70b8 111 ]
89087418 112 info_dict['formats'] = formats
3d4a70b8
PH
113 yie = YoutubeIE(ydl)
114 yie._sort_formats(info_dict['formats'])
e028d0d1
JMF
115 ydl.process_ie_result(info_dict)
116 downloaded = ydl.downloaded_info_dicts[0]
5d0c5371 117 self.assertEqual(downloaded['ext'], 'webm')
e028d0d1 118
a9c58ad9
JMF
119 def test_format_selection(self):
120 formats = [
8508557e 121 {'format_id': '35', 'ext': 'mp4', 'preference': 1, 'url': TEST_URL},
232541df 122 {'format_id': 'example-with-dashes', 'ext': 'webm', 'preference': 1, 'url': TEST_URL},
8508557e
JMF
123 {'format_id': '45', 'ext': 'webm', 'preference': 2, 'url': TEST_URL},
124 {'format_id': '47', 'ext': 'webm', 'preference': 3, 'url': TEST_URL},
125 {'format_id': '2', 'ext': 'flv', 'preference': 4, 'url': TEST_URL},
a9c58ad9 126 ]
3537b93d 127 info_dict = _make_result(formats)
a9c58ad9 128
b5ac45b1 129 def test(inp, *expected, multi=False):
130 ydl = YDL({
131 'format': inp,
132 'allow_multiple_video_streams': multi,
133 'allow_multiple_audio_streams': multi,
134 })
135 ydl.process_ie_result(info_dict.copy())
136 downloaded = map(lambda x: x['format_id'], ydl.downloaded_info_dicts)
137 self.assertEqual(list(downloaded), list(expected))
138
139 test('20/47', '47')
140 test('20/71/worst', '35')
141 test(None, '2')
142 test('webm/mp4', '47')
143 test('3gp/40/mp4', '35')
144 test('example-with-dashes', 'example-with-dashes')
dd2a987d 145 test('all', '2', '47', '45', 'example-with-dashes', '35')
b5ac45b1 146 test('mergeall', '2+47+45+example-with-dashes+35', multi=True)
232541df 147
ba7678f9
PH
148 def test_format_selection_audio(self):
149 formats = [
8508557e
JMF
150 {'format_id': 'audio-low', 'ext': 'webm', 'preference': 1, 'vcodec': 'none', 'url': TEST_URL},
151 {'format_id': 'audio-mid', 'ext': 'webm', 'preference': 2, 'vcodec': 'none', 'url': TEST_URL},
152 {'format_id': 'audio-high', 'ext': 'flv', 'preference': 3, 'vcodec': 'none', 'url': TEST_URL},
153 {'format_id': 'vid', 'ext': 'mp4', 'preference': 4, 'url': TEST_URL},
ba7678f9 154 ]
3537b93d 155 info_dict = _make_result(formats)
ba7678f9 156
89087418 157 ydl = YDL({'format': 'bestaudio'})
ba7678f9
PH
158 ydl.process_ie_result(info_dict.copy())
159 downloaded = ydl.downloaded_info_dicts[0]
89087418 160 self.assertEqual(downloaded['format_id'], 'audio-high')
ba7678f9 161
89087418 162 ydl = YDL({'format': 'worstaudio'})
ba7678f9
PH
163 ydl.process_ie_result(info_dict.copy())
164 downloaded = ydl.downloaded_info_dicts[0]
89087418 165 self.assertEqual(downloaded['format_id'], 'audio-low')
ba7678f9
PH
166
167 formats = [
8508557e
JMF
168 {'format_id': 'vid-low', 'ext': 'mp4', 'preference': 1, 'url': TEST_URL},
169 {'format_id': 'vid-high', 'ext': 'mp4', 'preference': 2, 'url': TEST_URL},
ba7678f9 170 ]
3537b93d 171 info_dict = _make_result(formats)
ba7678f9 172
89087418 173 ydl = YDL({'format': 'bestaudio/worstaudio/best'})
ba7678f9
PH
174 ydl.process_ie_result(info_dict.copy())
175 downloaded = ydl.downloaded_info_dicts[0]
89087418 176 self.assertEqual(downloaded['format_id'], 'vid-high')
ba7678f9 177
0217c783
PH
178 def test_format_selection_audio_exts(self):
179 formats = [
180 {'format_id': 'mp3-64', 'ext': 'mp3', 'abr': 64, 'url': 'http://_', 'vcodec': 'none'},
181 {'format_id': 'ogg-64', 'ext': 'ogg', 'abr': 64, 'url': 'http://_', 'vcodec': 'none'},
182 {'format_id': 'aac-64', 'ext': 'aac', 'abr': 64, 'url': 'http://_', 'vcodec': 'none'},
183 {'format_id': 'mp3-32', 'ext': 'mp3', 'abr': 32, 'url': 'http://_', 'vcodec': 'none'},
184 {'format_id': 'aac-32', 'ext': 'aac', 'abr': 32, 'url': 'http://_', 'vcodec': 'none'},
185 ]
186
187 info_dict = _make_result(formats)
188 ydl = YDL({'format': 'best'})
189 ie = YoutubeIE(ydl)
190 ie._sort_formats(info_dict['formats'])
191 ydl.process_ie_result(copy.deepcopy(info_dict))
192 downloaded = ydl.downloaded_info_dicts[0]
193 self.assertEqual(downloaded['format_id'], 'aac-64')
194
195 ydl = YDL({'format': 'mp3'})
196 ie = YoutubeIE(ydl)
197 ie._sort_formats(info_dict['formats'])
198 ydl.process_ie_result(copy.deepcopy(info_dict))
199 downloaded = ydl.downloaded_info_dicts[0]
200 self.assertEqual(downloaded['format_id'], 'mp3-64')
201
202 ydl = YDL({'prefer_free_formats': True})
203 ie = YoutubeIE(ydl)
204 ie._sort_formats(info_dict['formats'])
205 ydl.process_ie_result(copy.deepcopy(info_dict))
206 downloaded = ydl.downloaded_info_dicts[0]
207 self.assertEqual(downloaded['format_id'], 'ogg-64')
208
bc6d5978
JMF
209 def test_format_selection_video(self):
210 formats = [
8508557e
JMF
211 {'format_id': 'dash-video-low', 'ext': 'mp4', 'preference': 1, 'acodec': 'none', 'url': TEST_URL},
212 {'format_id': 'dash-video-high', 'ext': 'mp4', 'preference': 2, 'acodec': 'none', 'url': TEST_URL},
213 {'format_id': 'vid', 'ext': 'mp4', 'preference': 3, 'url': TEST_URL},
bc6d5978 214 ]
3537b93d 215 info_dict = _make_result(formats)
bc6d5978
JMF
216
217 ydl = YDL({'format': 'bestvideo'})
218 ydl.process_ie_result(info_dict.copy())
219 downloaded = ydl.downloaded_info_dicts[0]
220 self.assertEqual(downloaded['format_id'], 'dash-video-high')
221
222 ydl = YDL({'format': 'worstvideo'})
223 ydl.process_ie_result(info_dict.copy())
224 downloaded = ydl.downloaded_info_dicts[0]
225 self.assertEqual(downloaded['format_id'], 'dash-video-low')
226
4c3b16d5
S
227 ydl = YDL({'format': 'bestvideo[format_id^=dash][format_id$=low]'})
228 ydl.process_ie_result(info_dict.copy())
229 downloaded = ydl.downloaded_info_dicts[0]
230 self.assertEqual(downloaded['format_id'], 'dash-video-low')
231
b913348d 232 formats = [
233 {'format_id': 'vid-vcodec-dot', 'ext': 'mp4', 'preference': 1, 'vcodec': 'avc1.123456', 'acodec': 'none', 'url': TEST_URL},
234 ]
235 info_dict = _make_result(formats)
236
237 ydl = YDL({'format': 'bestvideo[vcodec=avc1.123456]'})
238 ydl.process_ie_result(info_dict.copy())
239 downloaded = ydl.downloaded_info_dicts[0]
240 self.assertEqual(downloaded['format_id'], 'vid-vcodec-dot')
241
2cc779f4
S
242 def test_format_selection_string_ops(self):
243 formats = [
244 {'format_id': 'abc-cba', 'ext': 'mp4', 'url': TEST_URL},
e118a879 245 {'format_id': 'zxc-cxz', 'ext': 'webm', 'url': TEST_URL},
2cc779f4
S
246 ]
247 info_dict = _make_result(formats)
248
249 # equals (=)
250 ydl = YDL({'format': '[format_id=abc-cba]'})
251 ydl.process_ie_result(info_dict.copy())
252 downloaded = ydl.downloaded_info_dicts[0]
253 self.assertEqual(downloaded['format_id'], 'abc-cba')
254
255 # does not equal (!=)
256 ydl = YDL({'format': '[format_id!=abc-cba]'})
e118a879
S
257 ydl.process_ie_result(info_dict.copy())
258 downloaded = ydl.downloaded_info_dicts[0]
259 self.assertEqual(downloaded['format_id'], 'zxc-cxz')
260
261 ydl = YDL({'format': '[format_id!=abc-cba][format_id!=zxc-cxz]'})
2cc779f4
S
262 self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy())
263
264 # starts with (^=)
265 ydl = YDL({'format': '[format_id^=abc]'})
266 ydl.process_ie_result(info_dict.copy())
267 downloaded = ydl.downloaded_info_dicts[0]
268 self.assertEqual(downloaded['format_id'], 'abc-cba')
269
270 # does not start with (!^=)
e118a879
S
271 ydl = YDL({'format': '[format_id!^=abc]'})
272 ydl.process_ie_result(info_dict.copy())
273 downloaded = ydl.downloaded_info_dicts[0]
274 self.assertEqual(downloaded['format_id'], 'zxc-cxz')
275
276 ydl = YDL({'format': '[format_id!^=abc][format_id!^=zxc]'})
2cc779f4
S
277 self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy())
278
279 # ends with ($=)
280 ydl = YDL({'format': '[format_id$=cba]'})
281 ydl.process_ie_result(info_dict.copy())
282 downloaded = ydl.downloaded_info_dicts[0]
283 self.assertEqual(downloaded['format_id'], 'abc-cba')
284
285 # does not end with (!$=)
e118a879
S
286 ydl = YDL({'format': '[format_id!$=cba]'})
287 ydl.process_ie_result(info_dict.copy())
288 downloaded = ydl.downloaded_info_dicts[0]
289 self.assertEqual(downloaded['format_id'], 'zxc-cxz')
290
291 ydl = YDL({'format': '[format_id!$=cba][format_id!$=cxz]'})
2cc779f4
S
292 self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy())
293
294 # contains (*=)
e118a879 295 ydl = YDL({'format': '[format_id*=bc-cb]'})
2cc779f4
S
296 ydl.process_ie_result(info_dict.copy())
297 downloaded = ydl.downloaded_info_dicts[0]
298 self.assertEqual(downloaded['format_id'], 'abc-cba')
299
300 # does not contain (!*=)
e118a879
S
301 ydl = YDL({'format': '[format_id!*=bc-cb]'})
302 ydl.process_ie_result(info_dict.copy())
303 downloaded = ydl.downloaded_info_dicts[0]
304 self.assertEqual(downloaded['format_id'], 'zxc-cxz')
305
306 ydl = YDL({'format': '[format_id!*=abc][format_id!*=zxc]'})
307 self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy())
308
2cc779f4
S
309 ydl = YDL({'format': '[format_id!*=-]'})
310 self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy())
311
3d4a70b8 312 def test_youtube_format_selection(self):
a7191c6f 313 # FIXME: Rewrite in accordance with the new format sorting options
5d0c5371 314 return
5d0c5371 315
3d4a70b8 316 order = [
86bf2905 317 '38', '37', '46', '22', '45', '35', '44', '18', '34', '43', '6', '5', '17', '36', '13',
3d4a70b8
PH
318 # Apple HTTP Live Streaming
319 '96', '95', '94', '93', '92', '132', '151',
320 # 3D
321 '85', '84', '102', '83', '101', '82', '100',
322 # Dash video
c11125f9 323 '137', '248', '136', '247', '135', '246',
3d4a70b8
PH
324 '245', '244', '134', '243', '133', '242', '160',
325 # Dash audio
a053c349 326 '141', '172', '140', '171', '139',
3d4a70b8
PH
327 ]
328
67134eab
JMF
329 def format_info(f_id):
330 info = YoutubeIE._formats[f_id].copy()
1df41411 331
91cb6b50 332 # XXX: In real cases InfoExtractor._parse_mpd_formats() fills up 'acodec'
1df41411
YCH
333 # and 'vcodec', while in tests such information is incomplete since
334 # commit a6c2c24479e5f4827ceb06f64d855329c0a6f593
335 # test_YoutubeDL.test_youtube_format_selection is broken without
336 # this fix
337 if 'acodec' in info and 'vcodec' not in info:
338 info['vcodec'] = 'none'
339 elif 'vcodec' in info and 'acodec' not in info:
340 info['acodec'] = 'none'
341
67134eab
JMF
342 info['format_id'] = f_id
343 info['url'] = 'url:' + f_id
344 return info
345 formats_order = [format_info(f_id) for f_id in order]
346
347 info_dict = _make_result(list(formats_order), extractor='youtube')
348 ydl = YDL({'format': 'bestvideo+bestaudio'})
349 yie = YoutubeIE(ydl)
350 yie._sort_formats(info_dict['formats'])
351 ydl.process_ie_result(info_dict)
352 downloaded = ydl.downloaded_info_dicts[0]
5d0c5371 353 self.assertEqual(downloaded['format_id'], '248+172')
67134eab 354 self.assertEqual(downloaded['ext'], 'mp4')
3d4a70b8 355
cf2ac6df
JMF
356 info_dict = _make_result(list(formats_order), extractor='youtube')
357 ydl = YDL({'format': 'bestvideo[height>=999999]+bestaudio/best'})
358 yie = YoutubeIE(ydl)
359 yie._sort_formats(info_dict['formats'])
360 ydl.process_ie_result(info_dict)
361 downloaded = ydl.downloaded_info_dicts[0]
362 self.assertEqual(downloaded['format_id'], '38')
363
f5f4a27a
JMF
364 info_dict = _make_result(list(formats_order), extractor='youtube')
365 ydl = YDL({'format': 'bestvideo/best,bestaudio'})
366 yie = YoutubeIE(ydl)
367 yie._sort_formats(info_dict['formats'])
368 ydl.process_ie_result(info_dict)
369 downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts]
370 self.assertEqual(downloaded_ids, ['137', '141'])
371
0130afb7
JMF
372 info_dict = _make_result(list(formats_order), extractor='youtube')
373 ydl = YDL({'format': '(bestvideo[ext=mp4],bestvideo[ext=webm])+bestaudio'})
374 yie = YoutubeIE(ydl)
375 yie._sort_formats(info_dict['formats'])
376 ydl.process_ie_result(info_dict)
377 downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts]
378 self.assertEqual(downloaded_ids, ['137+141', '248+141'])
379
380 info_dict = _make_result(list(formats_order), extractor='youtube')
381 ydl = YDL({'format': '(bestvideo[ext=mp4],bestvideo[ext=webm])[height<=720]+bestaudio'})
382 yie = YoutubeIE(ydl)
383 yie._sort_formats(info_dict['formats'])
384 ydl.process_ie_result(info_dict)
385 downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts]
386 self.assertEqual(downloaded_ids, ['136+141', '247+141'])
387
388 info_dict = _make_result(list(formats_order), extractor='youtube')
389 ydl = YDL({'format': '(bestvideo[ext=none]/bestvideo[ext=webm])+bestaudio'})
390 yie = YoutubeIE(ydl)
391 yie._sort_formats(info_dict['formats'])
392 ydl.process_ie_result(info_dict)
393 downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts]
394 self.assertEqual(downloaded_ids, ['248+141'])
395
67134eab 396 for f1, f2 in zip(formats_order, formats_order[1:]):
3537b93d 397 info_dict = _make_result([f1, f2], extractor='youtube')
8dd54188 398 ydl = YDL({'format': 'best/bestvideo'})
3d4a70b8
PH
399 yie = YoutubeIE(ydl)
400 yie._sort_formats(info_dict['formats'])
401 ydl.process_ie_result(info_dict)
402 downloaded = ydl.downloaded_info_dicts[0]
67134eab 403 self.assertEqual(downloaded['format_id'], f1['format_id'])
3d4a70b8 404
3537b93d 405 info_dict = _make_result([f2, f1], extractor='youtube')
8dd54188 406 ydl = YDL({'format': 'best/bestvideo'})
3d4a70b8
PH
407 yie = YoutubeIE(ydl)
408 yie._sort_formats(info_dict['formats'])
409 ydl.process_ie_result(info_dict)
410 downloaded = ydl.downloaded_info_dicts[0]
67134eab 411 self.assertEqual(downloaded['format_id'], f1['format_id'])
3d4a70b8 412
317f7ab6
S
413 def test_audio_only_extractor_format_selection(self):
414 # For extractors with incomplete formats (all formats are audio-only or
415 # video-only) best and worst should fallback to corresponding best/worst
416 # video-only or audio-only formats (as per
067aa17e 417 # https://github.com/ytdl-org/youtube-dl/pull/5556)
317f7ab6
S
418 formats = [
419 {'format_id': 'low', 'ext': 'mp3', 'preference': 1, 'vcodec': 'none', 'url': TEST_URL},
420 {'format_id': 'high', 'ext': 'mp3', 'preference': 2, 'vcodec': 'none', 'url': TEST_URL},
421 ]
422 info_dict = _make_result(formats)
423
424 ydl = YDL({'format': 'best'})
425 ydl.process_ie_result(info_dict.copy())
426 downloaded = ydl.downloaded_info_dicts[0]
427 self.assertEqual(downloaded['format_id'], 'high')
428
429 ydl = YDL({'format': 'worst'})
430 ydl.process_ie_result(info_dict.copy())
431 downloaded = ydl.downloaded_info_dicts[0]
432 self.assertEqual(downloaded['format_id'], 'low')
433
434 def test_format_not_available(self):
435 formats = [
436 {'format_id': 'regular', 'ext': 'mp4', 'height': 360, 'url': TEST_URL},
437 {'format_id': 'video', 'ext': 'mp4', 'height': 720, 'acodec': 'none', 'url': TEST_URL},
438 ]
439 info_dict = _make_result(formats)
440
441 # This must fail since complete video-audio format does not match filter
442 # and extractor does not provide incomplete only formats (i.e. only
443 # video-only or audio-only).
444 ydl = YDL({'format': 'best[height>360]'})
445 self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy())
446
8cda78ef 447 def test_format_selection_issue_10083(self):
067aa17e 448 # See https://github.com/ytdl-org/youtube-dl/issues/10083
8cda78ef
S
449 formats = [
450 {'format_id': 'regular', 'height': 360, 'url': TEST_URL},
451 {'format_id': 'video', 'height': 720, 'acodec': 'none', 'url': TEST_URL},
452 {'format_id': 'audio', 'vcodec': 'none', 'url': TEST_URL},
453 ]
454 info_dict = _make_result(formats)
455
456 ydl = YDL({'format': 'best[height>360]/bestvideo[height>360]+bestaudio'})
457 ydl.process_ie_result(info_dict.copy())
458 self.assertEqual(ydl.downloaded_info_dicts[0]['format_id'], 'video+audio')
459
0a31a350
JMF
460 def test_invalid_format_specs(self):
461 def assert_syntax_error(format_spec):
187986a8 462 self.assertRaises(SyntaxError, YDL, {'format': format_spec})
0a31a350
JMF
463
464 assert_syntax_error('bestvideo,,best')
465 assert_syntax_error('+bestaudio')
466 assert_syntax_error('bestvideo+')
d96d604e 467 assert_syntax_error('/')
187986a8 468 assert_syntax_error('[720<height]')
0a31a350 469
083c9df9
PH
470 def test_format_filtering(self):
471 formats = [
472 {'format_id': 'A', 'filesize': 500, 'width': 1000},
473 {'format_id': 'B', 'filesize': 1000, 'width': 500},
474 {'format_id': 'C', 'filesize': 1000, 'width': 400},
475 {'format_id': 'D', 'filesize': 2000, 'width': 600},
476 {'format_id': 'E', 'filesize': 3000},
477 {'format_id': 'F'},
478 {'format_id': 'G', 'filesize': 1000000},
479 ]
480 for f in formats:
481 f['url'] = 'http://_/'
482 f['ext'] = 'unknown'
483 info_dict = _make_result(formats)
484
485 ydl = YDL({'format': 'best[filesize<3000]'})
486 ydl.process_ie_result(info_dict)
487 downloaded = ydl.downloaded_info_dicts[0]
488 self.assertEqual(downloaded['format_id'], 'D')
489
490 ydl = YDL({'format': 'best[filesize<=3000]'})
491 ydl.process_ie_result(info_dict)
492 downloaded = ydl.downloaded_info_dicts[0]
493 self.assertEqual(downloaded['format_id'], 'E')
494
495 ydl = YDL({'format': 'best[filesize <= ? 3000]'})
496 ydl.process_ie_result(info_dict)
497 downloaded = ydl.downloaded_info_dicts[0]
498 self.assertEqual(downloaded['format_id'], 'F')
499
500 ydl = YDL({'format': 'best [filesize = 1000] [width>450]'})
501 ydl.process_ie_result(info_dict)
502 downloaded = ydl.downloaded_info_dicts[0]
503 self.assertEqual(downloaded['format_id'], 'B')
504
505 ydl = YDL({'format': 'best [filesize = 1000] [width!=450]'})
506 ydl.process_ie_result(info_dict)
507 downloaded = ydl.downloaded_info_dicts[0]
508 self.assertEqual(downloaded['format_id'], 'C')
509
510 ydl = YDL({'format': '[filesize>?1]'})
511 ydl.process_ie_result(info_dict)
512 downloaded = ydl.downloaded_info_dicts[0]
513 self.assertEqual(downloaded['format_id'], 'G')
514
515 ydl = YDL({'format': '[filesize<1M]'})
516 ydl.process_ie_result(info_dict)
517 downloaded = ydl.downloaded_info_dicts[0]
518 self.assertEqual(downloaded['format_id'], 'E')
519
520 ydl = YDL({'format': '[filesize<1MiB]'})
521 ydl.process_ie_result(info_dict)
522 downloaded = ydl.downloaded_info_dicts[0]
523 self.assertEqual(downloaded['format_id'], 'G')
524
5acfa126
JMF
525 ydl = YDL({'format': 'all[width>=400][width<=600]'})
526 ydl.process_ie_result(info_dict)
527 downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts]
dd2a987d 528 self.assertEqual(downloaded_ids, ['D', 'C', 'B'])
5acfa126 529
bb8e5536
JMF
530 ydl = YDL({'format': 'best[height<40]'})
531 try:
532 ydl.process_ie_result(info_dict)
533 except ExtractorError:
534 pass
535 self.assertEqual(ydl.downloaded_info_dicts, [])
536
0017d9ad
S
537 def test_default_format_spec(self):
538 ydl = YDL({'simulate': True})
5d0c5371 539 self.assertEqual(ydl._default_format_spec({}), 'bestvideo*+bestaudio/best')
0017d9ad 540
d08dcd2d
S
541 ydl = YDL({})
542 self.assertEqual(ydl._default_format_spec({'is_live': True}), 'best/bestvideo+bestaudio')
af0f7428 543
d08dcd2d 544 ydl = YDL({'simulate': True})
5d0c5371 545 self.assertEqual(ydl._default_format_spec({'is_live': True}), 'bestvideo*+bestaudio/best')
af0f7428 546
0017d9ad 547 ydl = YDL({'outtmpl': '-'})
af0f7428 548 self.assertEqual(ydl._default_format_spec({}), 'best/bestvideo+bestaudio')
0017d9ad
S
549
550 ydl = YDL({})
5d0c5371 551 self.assertEqual(ydl._default_format_spec({}, download=False), 'bestvideo*+bestaudio/best')
af0f7428 552 self.assertEqual(ydl._default_format_spec({'is_live': True}), 'best/bestvideo+bestaudio')
0017d9ad 553
f20bf146
JMF
554
555class TestYoutubeDL(unittest.TestCase):
ab84349b
JMF
556 def test_subtitles(self):
557 def s_formats(lang, autocaption=False):
558 return [{
559 'ext': ext,
86e5f3ed 560 'url': f'http://localhost/video.{lang}.{ext}',
ab84349b
JMF
561 '_auto': autocaption,
562 } for ext in ['vtt', 'srt', 'ass']]
86e5f3ed 563 subtitles = {l: s_formats(l) for l in ['en', 'fr', 'es']}
564 auto_captions = {l: s_formats(l, True) for l in ['it', 'pt', 'es']}
ab84349b
JMF
565 info_dict = {
566 'id': 'test',
567 'title': 'Test',
568 'url': 'http://localhost/video.mp4',
569 'subtitles': subtitles,
570 'automatic_captions': auto_captions,
571 'extractor': 'TEST',
732044af 572 'webpage_url': 'http://example.com/watch?v=shenanigans',
ab84349b
JMF
573 }
574
575 def get_info(params={}):
576 params.setdefault('simulate', True)
577 ydl = YDL(params)
578 ydl.report_warning = lambda *args, **kargs: None
579 return ydl.process_video_result(info_dict, download=False)
580
581 result = get_info()
582 self.assertFalse(result.get('requested_subtitles'))
583 self.assertEqual(result['subtitles'], subtitles)
584 self.assertEqual(result['automatic_captions'], auto_captions)
585
586 result = get_info({'writesubtitles': True})
587 subs = result['requested_subtitles']
588 self.assertTrue(subs)
86e5f3ed 589 self.assertEqual(set(subs.keys()), {'en'})
ab84349b
JMF
590 self.assertTrue(subs['en'].get('data') is None)
591 self.assertEqual(subs['en']['ext'], 'ass')
592
593 result = get_info({'writesubtitles': True, 'subtitlesformat': 'foo/srt'})
594 subs = result['requested_subtitles']
595 self.assertEqual(subs['en']['ext'], 'srt')
596
597 result = get_info({'writesubtitles': True, 'subtitleslangs': ['es', 'fr', 'it']})
598 subs = result['requested_subtitles']
599 self.assertTrue(subs)
86e5f3ed 600 self.assertEqual(set(subs.keys()), {'es', 'fr'})
ab84349b 601
c32b0aab 602 result = get_info({'writesubtitles': True, 'subtitleslangs': ['all', '-en']})
603 subs = result['requested_subtitles']
604 self.assertTrue(subs)
86e5f3ed 605 self.assertEqual(set(subs.keys()), {'es', 'fr'})
c32b0aab 606
607 result = get_info({'writesubtitles': True, 'subtitleslangs': ['en', 'fr', '-en']})
608 subs = result['requested_subtitles']
609 self.assertTrue(subs)
86e5f3ed 610 self.assertEqual(set(subs.keys()), {'fr'})
c32b0aab 611
612 result = get_info({'writesubtitles': True, 'subtitleslangs': ['-en', 'en']})
613 subs = result['requested_subtitles']
614 self.assertTrue(subs)
86e5f3ed 615 self.assertEqual(set(subs.keys()), {'en'})
c32b0aab 616
617 result = get_info({'writesubtitles': True, 'subtitleslangs': ['e.+']})
618 subs = result['requested_subtitles']
619 self.assertTrue(subs)
86e5f3ed 620 self.assertEqual(set(subs.keys()), {'es', 'en'})
c32b0aab 621
ab84349b
JMF
622 result = get_info({'writesubtitles': True, 'writeautomaticsub': True, 'subtitleslangs': ['es', 'pt']})
623 subs = result['requested_subtitles']
624 self.assertTrue(subs)
86e5f3ed 625 self.assertEqual(set(subs.keys()), {'es', 'pt'})
ab84349b
JMF
626 self.assertFalse(subs['es']['_auto'])
627 self.assertTrue(subs['pt']['_auto'])
628
98c70d6f
JMF
629 result = get_info({'writeautomaticsub': True, 'subtitleslangs': ['es', 'pt']})
630 subs = result['requested_subtitles']
631 self.assertTrue(subs)
86e5f3ed 632 self.assertEqual(set(subs.keys()), {'es', 'pt'})
98c70d6f
JMF
633 self.assertTrue(subs['es']['_auto'])
634 self.assertTrue(subs['pt']['_auto'])
635
b6c45014
JMF
636 def test_add_extra_info(self):
637 test_dict = {
638 'extractor': 'Foo',
639 }
640 extra_info = {
641 'extractor': 'Bar',
642 'playlist': 'funny videos',
643 }
644 YDL.add_extra_info(test_dict, extra_info)
645 self.assertEqual(test_dict['extractor'], 'Foo')
646 self.assertEqual(test_dict['playlist'], 'funny videos')
647
752cda38 648 outtmpl_info = {
649 'id': '1234',
650 'ext': 'mp4',
651 'width': None,
652 'height': 1080,
abbeeebc 653 'filesize': 1024,
752cda38 654 'title1': '$PATH',
655 'title2': '%PATH%',
87ea7dfc 656 'title3': 'foo/bar\\test',
7d1eb38a 657 'title4': 'foo "bar" test',
524e2e4f 658 'title5': 'áéí 𝐀',
752cda38 659 'timestamp': 1618488000,
660 'duration': 100000,
661 'playlist_index': 1,
e6f21b3d 662 'playlist_autonumber': 2,
0a5a191a 663 '__last_playlist_index': 100,
752cda38 664 'n_entries': 10,
4476d2c7 665 'formats': [{'id': 'id 1'}, {'id': 'id 2'}, {'id': 'id 3'}]
752cda38 666 }
667
5c6542ce 668 def test_prepare_outtmpl_and_filename(self):
9fea350f 669 def test(tmpl, expected, *, info=None, **params):
752cda38 670 params['outtmpl'] = tmpl
671 ydl = YoutubeDL(params)
672 ydl._num_downloads = 1
5c6542ce 673 self.assertEqual(ydl.validate_outtmpl(tmpl), None)
752cda38 674
819e0531 675 out = ydl.evaluate_outtmpl(tmpl, info or self.outtmpl_info)
9fea350f 676 fname = ydl.prepare_filename(info or self.outtmpl_info)
5c6542ce 677
2b8a2973 678 if not isinstance(expected, (list, tuple)):
679 expected = (expected, expected)
680 for (name, got), expect in zip((('outtmpl', out), ('filename', fname)), expected):
681 if callable(expect):
682 self.assertTrue(expect(got), f'Wrong {name} from {tmpl}')
683 else:
684 self.assertEqual(got, expect, f'Wrong {name} from {tmpl}')
5c6542ce 685
6e84b215 686 # Side-effects
687 original_infodict = dict(self.outtmpl_info)
688 test('foo.bar', 'foo.bar')
689 original_infodict['epoch'] = self.outtmpl_info.get('epoch')
690 self.assertTrue(isinstance(original_infodict['epoch'], int))
691 test('%(epoch)d', int_or_none)
692 self.assertEqual(original_infodict, self.outtmpl_info)
693
5c6542ce 694 # Auto-generated fields
695 test('%(id)s.%(ext)s', '1234.mp4')
696 test('%(duration_string)s', ('27:46:40', '27-46-40'))
5c6542ce 697 test('%(resolution)s', '1080p')
698 test('%(playlist_index)s', '001')
e6f21b3d 699 test('%(playlist_autonumber)s', '02')
5c6542ce 700 test('%(autonumber)s', '00001')
701 test('%(autonumber+2)03d', '005', autonumber_start=3)
702 test('%(autonumber)s', '001', autonumber_size=3)
703
704 # Escaping %
901130bb 705 test('%', '%')
5c6542ce 706 test('%%', '%')
707 test('%%%%', '%%')
901130bb 708 test('%s', '%s')
709 test('%%%s', '%%s')
710 test('%d', '%d')
711 test('%abc%', '%abc%')
5c6542ce 712 test('%%(width)06d.%(ext)s', '%(width)06d.mp4')
901130bb 713 test('%%%(height)s', '%1080')
5c6542ce 714 test('%(width)06d.%(ext)s', 'NA.mp4')
715 test('%(width)06d.%%(ext)s', 'NA.%(ext)s')
716 test('%%(width)06d.%(ext)s', '%(width)06d.mp4')
717
9fea350f 718 # ID sanitization
719 test('%(id)s', '_abcd', info={'id': '_abcd'})
720 test('%(some_id)s', '_abcd', info={'some_id': '_abcd'})
721 test('%(formats.0.id)s', '_abcd', info={'formats': [{'id': '_abcd'}]})
722 test('%(id)s', '-abcd', info={'id': '-abcd'})
723 test('%(id)s', '.abcd', info={'id': '.abcd'})
724 test('%(id)s', 'ab__cd', info={'id': 'ab__cd'})
97d9c79e 725 test('%(id)s', ('ab:cd', 'ab:cd'), info={'id': 'ab:cd'})
e0fd9573 726 test('%(id.0)s', '-', info={'id': '--'})
9fea350f 727
5c6542ce 728 # Invalid templates
5c6542ce 729 self.assertTrue(isinstance(YoutubeDL.validate_outtmpl('%(title)'), ValueError))
730 test('%(invalid@tmpl|def)s', 'none', outtmpl_na_placeholder='none')
2b8a2973 731 test('%(..)s', 'NA')
732
733 # Entire info_dict
734 def expect_same_infodict(out):
735 got_dict = json.loads(out)
736 for info_field, expected in self.outtmpl_info.items():
737 self.assertEqual(got_dict.get(info_field), expected, info_field)
738 return True
739
740 test('%()j', (expect_same_infodict, str))
5c6542ce 741
742 # NA placeholder
752cda38 743 NA_TEST_OUTTMPL = '%(uploader_date)s-%(width)d-%(x|def)s-%(id)s.%(ext)s'
5c6542ce 744 test(NA_TEST_OUTTMPL, 'NA-NA-def-1234.mp4')
745 test(NA_TEST_OUTTMPL, 'none-none-def-1234.mp4', outtmpl_na_placeholder='none')
746 test(NA_TEST_OUTTMPL, '--def-1234.mp4', outtmpl_na_placeholder='')
582fad70 747 test('%(non_existent.0)s', 'NA')
752cda38 748
5c6542ce 749 # String formatting
752cda38 750 FMT_TEST_OUTTMPL = '%%(height)%s.%%(ext)s'
5c6542ce 751 test(FMT_TEST_OUTTMPL % 's', '1080.mp4')
752 test(FMT_TEST_OUTTMPL % 'd', '1080.mp4')
753 test(FMT_TEST_OUTTMPL % '6d', ' 1080.mp4')
754 test(FMT_TEST_OUTTMPL % '-6d', '1080 .mp4')
755 test(FMT_TEST_OUTTMPL % '06d', '001080.mp4')
756 test(FMT_TEST_OUTTMPL % ' 06d', ' 01080.mp4')
757 test(FMT_TEST_OUTTMPL % ' 06d', ' 01080.mp4')
758 test(FMT_TEST_OUTTMPL % '0 6d', ' 01080.mp4')
759 test(FMT_TEST_OUTTMPL % '0 6d', ' 01080.mp4')
760 test(FMT_TEST_OUTTMPL % ' 0 6d', ' 01080.mp4')
761
762 # Type casting
763 test('%(id)d', '1234')
764 test('%(height)c', '1')
765 test('%(ext)c', 'm')
766 test('%(id)d %(id)r', "1234 '1234'")
767 test('%(id)r %(height)r', "'1234' 1080")
768 test('%(ext)s-%(ext|def)d', 'mp4-def')
769 test('%(width|0)04d', '0000')
770 test('a%(width|)d', 'a', outtmpl_na_placeholder='none')
771
752cda38 772 FORMATS = self.outtmpl_info['formats']
97d9c79e 773 sanitize = lambda x: x.replace(':', ':').replace('"', """).replace('\n', ' ')
7d1eb38a 774
775 # Custom type casting
4476d2c7 776 test('%(formats.:.id)l', 'id 1, id 2, id 3')
777 test('%(formats.:.id)#l', ('id 1\nid 2\nid 3', 'id 1 id 2 id 3'))
7d1eb38a 778 test('%(ext)l', 'mp4')
4476d2c7 779 test('%(formats.:.id) 18l', ' id 1, id 2, id 3')
7d1eb38a 780 test('%(formats)j', (json.dumps(FORMATS), sanitize(json.dumps(FORMATS))))
4476d2c7 781 test('%(formats)#j', (json.dumps(FORMATS, indent=4), sanitize(json.dumps(FORMATS, indent=4))))
f5aa5cfb 782 test('%(title5).3B', 'á')
524e2e4f 783 test('%(title5)U', 'áéí 𝐀')
784 test('%(title5)#U', 'a\u0301e\u0301i\u0301 𝐀')
785 test('%(title5)+U', 'áéí A')
786 test('%(title5)+#U', 'a\u0301e\u0301i\u0301 A')
abbeeebc 787 test('%(height)D', '1k')
788 test('%(filesize)#D', '1Ki')
789 test('%(height)5.2D', ' 1.08k')
37893bb0 790 test('%(title4)#S', 'foo_bar_test')
97d9c79e 791 test('%(title4).10S', ('foo "bar" ', 'foo "bar"' + ('#' if compat_os_name == 'nt' else ' ')))
7d1eb38a 792 if compat_os_name == 'nt':
97d9c79e 793 test('%(title4)q', ('"foo \\"bar\\" test"', ""foo ⧹"bar⧹" test""))
794 test('%(formats.:.id)#q', ('"id 1" "id 2" "id 3"', '"id 1" "id 2" "id 3"'))
795 test('%(formats.0.id)#q', ('"id 1"', '"id 1"'))
7d1eb38a 796 else:
97d9c79e 797 test('%(title4)q', ('\'foo "bar" test\'', '\'foo "bar" test\''))
4476d2c7 798 test('%(formats.:.id)#q', "'id 1' 'id 2' 'id 3'")
799 test('%(formats.0.id)#q', "'id 1'")
7d1eb38a 800
801 # Internal formatting
5c6542ce 802 test('%(timestamp-1000>%H-%M-%S)s', '11-43-20')
901130bb 803 test('%(title|%)s %(title|%%)s', '% %%')
5c6542ce 804 test('%(id+1-height+3)05d', '00158')
805 test('%(width+100)05d', 'NA')
7d1eb38a 806 test('%(formats.0) 15s', ('% 15s' % FORMATS[0], '% 15s' % sanitize(str(FORMATS[0]))))
807 test('%(formats.0)r', (repr(FORMATS[0]), sanitize(repr(FORMATS[0]))))
5c6542ce 808 test('%(height.0)03d', '001')
809 test('%(-height.0)04d', '-001')
810 test('%(formats.-1.id)s', FORMATS[-1]['id'])
811 test('%(formats.0.id.-1)d', FORMATS[0]['id'][-1])
812 test('%(formats.3)s', 'NA')
813 test('%(formats.:2:-1)r', repr(FORMATS[:2:-1]))
814 test('%(formats.0.id.-1+id)f', '1235.000000')
385a27fa 815 test('%(formats.0.id.-1+formats.1.id.-1)d', '3')
5c6542ce 816
7c37ff97 817 # Alternates
818 test('%(title,id)s', '1234')
819 test('%(width-100,height+20|def)d', '1100')
820 test('%(width-100,height+width|def)s', 'def')
821 test('%(timestamp-x>%H\\,%M\\,%S,timestamp>%H\\,%M\\,%S)s', '12,00,00')
822
e0fd9573 823 # Replacement
824 test('%(id&foo)s.bar', 'foo.bar')
825 test('%(title&foo)s.bar', 'NA.bar')
826 test('%(title&foo|baz)s.bar', 'baz.bar')
34baa9fd 827 test('%(x,id&foo|baz)s.bar', 'foo.bar')
828 test('%(x,title&foo|baz)s.bar', 'baz.bar')
e0fd9573 829
6e84b215 830 # Laziness
831 def gen():
832 yield from range(5)
833 raise self.assertTrue(False, 'LazyList should not be evaluated till here')
834 test('%(key.4)s', '4', info={'key': LazyList(gen())})
835
5c6542ce 836 # Empty filename
837 test('%(foo|)s-%(bar|)s.%(ext)s', '-.mp4')
838 # test('%(foo|)s.%(ext)s', ('.mp4', '_.mp4')) # fixme
839 # test('%(foo|)s', ('', '_')) # fixme
840
901130bb 841 # Environment variable expansion for prepare_filename
ac668111 842 os.environ['__yt_dlp_var'] = 'expanded'
901130bb 843 envvar = '%__yt_dlp_var%' if compat_os_name == 'nt' else '$__yt_dlp_var'
844 test(envvar, (envvar, 'expanded'))
b836dc94 845 if compat_os_name == 'nt':
846 test('%s%', ('%s%', '%s%'))
ac668111 847 os.environ['s'] = 'expanded'
b836dc94 848 test('%s%', ('%s%', 'expanded')) # %s% should be expanded before escaping %s
ac668111 849 os.environ['(test)s'] = 'expanded'
b836dc94 850 test('%(test)s%', ('NA%', 'expanded')) # Environment should take priority over template
901130bb 851
5c6542ce 852 # Path expansion and escaping
853 test('Hello %(title1)s', 'Hello $PATH')
854 test('Hello %(title2)s', 'Hello %PATH%')
97d9c79e 855 test('%(title3)s', ('foo/bar\\test', 'foo⧸bar⧹test'))
856 test('folder/%(title3)s', ('folder/foo/bar\\test', 'folder%sfoo⧸bar⧹test' % os.path.sep))
26e63931 857
c57f7757
PH
858 def test_format_note(self):
859 ydl = YoutubeDL()
860 self.assertEqual(ydl._format_note({}), '')
861 assertRegexpMatches(self, ydl._format_note({
862 'vbr': 10,
398dea32 863 }), r'^\s*10k$')
5d583bdf
S
864 assertRegexpMatches(self, ydl._format_note({
865 'fps': 30,
398dea32 866 }), r'^30fps$')
5d583bdf 867
2b4ecde2
JMF
868 def test_postprocessors(self):
869 filename = 'post-processor-testfile.mp4'
870 audiofile = filename + '.mp3'
871
872 class SimplePP(PostProcessor):
873 def run(self, info):
2b4ecde2
JMF
874 with open(audiofile, 'wt') as f:
875 f.write('EXAMPLE')
592e97e8 876 return [info['filepath']], info
2b4ecde2 877
592e97e8 878 def run_pp(params, PP):
2b4ecde2
JMF
879 with open(filename, 'wt') as f:
880 f.write('EXAMPLE')
881 ydl = YoutubeDL(params)
592e97e8 882 ydl.add_post_processor(PP())
2b4ecde2
JMF
883 ydl.post_process(filename, {'filepath': filename})
884
592e97e8 885 run_pp({'keepvideo': True}, SimplePP)
2b4ecde2
JMF
886 self.assertTrue(os.path.exists(filename), '%s doesn\'t exist' % filename)
887 self.assertTrue(os.path.exists(audiofile), '%s doesn\'t exist' % audiofile)
888 os.unlink(filename)
889 os.unlink(audiofile)
890
592e97e8 891 run_pp({'keepvideo': False}, SimplePP)
2b4ecde2
JMF
892 self.assertFalse(os.path.exists(filename), '%s exists' % filename)
893 self.assertTrue(os.path.exists(audiofile), '%s doesn\'t exist' % audiofile)
894 os.unlink(audiofile)
895
592e97e8
JMF
896 class ModifierPP(PostProcessor):
897 def run(self, info):
898 with open(info['filepath'], 'wt') as f:
899 f.write('MODIFIED')
900 return [], info
901
902 run_pp({'keepvideo': False}, ModifierPP)
903 self.assertTrue(os.path.exists(filename), '%s doesn\'t exist' % filename)
904 os.unlink(filename)
905
531980d8 906 def test_match_filter(self):
531980d8
JMF
907 first = {
908 'id': '1',
909 'url': TEST_URL,
910 'title': 'one',
911 'extractor': 'TEST',
912 'duration': 30,
913 'filesize': 10 * 1024,
e5a088dc 914 'playlist_id': '42',
db13c16e
S
915 'uploader': "變態妍字幕版 太妍 тест",
916 'creator': "тест ' 123 ' тест--",
732044af 917 'webpage_url': 'http://example.com/watch?v=shenanigans',
531980d8
JMF
918 }
919 second = {
920 'id': '2',
921 'url': TEST_URL,
922 'title': 'two',
923 'extractor': 'TEST',
924 'duration': 10,
925 'description': 'foo',
926 'filesize': 5 * 1024,
e5a088dc 927 'playlist_id': '43',
db13c16e 928 'uploader': "тест 123",
732044af 929 'webpage_url': 'http://example.com/watch?v=SHENANIGANS',
531980d8
JMF
930 }
931 videos = [first, second]
932
933 def get_videos(filter_=None):
09b49e1f 934 ydl = YDL({'match_filter': filter_, 'simulate': True})
531980d8
JMF
935 for v in videos:
936 ydl.process_ie_result(v, download=True)
937 return [v['id'] for v in ydl.downloaded_info_dicts]
938
939 res = get_videos()
940 self.assertEqual(res, ['1', '2'])
941
6db9c4d5 942 def f(v, incomplete):
531980d8
JMF
943 if v['id'] == '1':
944 return None
945 else:
946 return 'Video id is not 1'
947 res = get_videos(f)
948 self.assertEqual(res, ['1'])
949
950 f = match_filter_func('duration < 30')
951 res = get_videos(f)
952 self.assertEqual(res, ['2'])
953
954 f = match_filter_func('description = foo')
955 res = get_videos(f)
956 self.assertEqual(res, ['2'])
957
958 f = match_filter_func('description =? foo')
959 res = get_videos(f)
960 self.assertEqual(res, ['1', '2'])
961
962 f = match_filter_func('filesize > 5KiB')
963 res = get_videos(f)
964 self.assertEqual(res, ['1'])
965
e5a088dc
S
966 f = match_filter_func('playlist_id = 42')
967 res = get_videos(f)
968 self.assertEqual(res, ['1'])
969
db13c16e
S
970 f = match_filter_func('uploader = "變態妍字幕版 太妍 тест"')
971 res = get_videos(f)
972 self.assertEqual(res, ['1'])
973
974 f = match_filter_func('uploader != "變態妍字幕版 太妍 тест"')
975 res = get_videos(f)
976 self.assertEqual(res, ['2'])
977
978 f = match_filter_func('creator = "тест \' 123 \' тест--"')
979 res = get_videos(f)
980 self.assertEqual(res, ['1'])
981
982 f = match_filter_func("creator = 'тест \\' 123 \\' тест--'")
983 res = get_videos(f)
984 self.assertEqual(res, ['1'])
985
986 f = match_filter_func(r"creator = 'тест \' 123 \' тест--' & duration > 30")
987 res = get_videos(f)
988 self.assertEqual(res, [])
989
e9eaf3fb 990 def test_playlist_items_selection(self):
7e88d7d7 991 INDICES, PAGE_SIZE = list(range(1, 11)), 3
992
993 def entry(i, evaluated):
994 evaluated.append(i)
995 return {
996 'id': str(i),
997 'title': str(i),
998 'url': TEST_URL,
999 }
1000
1001 def pagedlist_entries(evaluated):
1002 def page_func(n):
1003 start = PAGE_SIZE * n
1004 for i in INDICES[start: start + PAGE_SIZE]:
1005 yield entry(i, evaluated)
1006 return OnDemandPagedList(page_func, PAGE_SIZE)
1007
1008 def page_num(i):
1009 return (i + PAGE_SIZE - 1) // PAGE_SIZE
e9eaf3fb 1010
7e88d7d7 1011 def generator_entries(evaluated):
1012 for i in INDICES:
1013 yield entry(i, evaluated)
1014
1015 def list_entries(evaluated):
1016 return list(generator_entries(evaluated))
1017
1018 def lazylist_entries(evaluated):
1019 return LazyList(generator_entries(evaluated))
1020
1021 def get_downloaded_info_dicts(params, entries):
e9eaf3fb 1022 ydl = YDL(params)
7e88d7d7 1023 ydl.process_ie_result({
1024 '_type': 'playlist',
1025 'id': 'test',
1026 'extractor': 'test:playlist',
1027 'extractor_key': 'test:playlist',
1028 'webpage_url': 'http://example.com',
1029 'entries': entries,
1030 })
4e9e1e24
S
1031 return ydl.downloaded_info_dicts
1032
7e88d7d7 1033 def test_selection(params, expected_ids, evaluate_all=False):
1034 expected_ids = list(expected_ids)
1035 if evaluate_all:
1036 generator_eval = pagedlist_eval = INDICES
1037 elif not expected_ids:
1038 generator_eval = pagedlist_eval = []
1039 else:
1040 generator_eval = INDICES[0: max(expected_ids)]
1041 pagedlist_eval = INDICES[PAGE_SIZE * page_num(min(expected_ids)) - PAGE_SIZE:
1042 PAGE_SIZE * page_num(max(expected_ids))]
1043
1044 for name, func, expected_eval in (
1045 ('list', list_entries, INDICES),
1046 ('Generator', generator_entries, generator_eval),
7e9a6125 1047 # ('LazyList', lazylist_entries, generator_eval), # Generator and LazyList follow the exact same code path
7e88d7d7 1048 ('PagedList', pagedlist_entries, pagedlist_eval),
1049 ):
1050 evaluated = []
1051 entries = func(evaluated)
1052 results = [(v['playlist_autonumber'] - 1, (int(v['id']), v['playlist_index']))
1053 for v in get_downloaded_info_dicts(params, entries)]
1054 self.assertEqual(results, list(enumerate(zip(expected_ids, expected_ids))), f'Entries of {name} for {params}')
1055 self.assertEqual(sorted(evaluated), expected_eval, f'Evaluation of {name} for {params}')
f2df4071 1056
7e88d7d7 1057 test_selection({}, INDICES)
1058 test_selection({'playlistend': 20}, INDICES, True)
1059 test_selection({'playlistend': 2}, INDICES[:2])
1060 test_selection({'playliststart': 11}, [], True)
1061 test_selection({'playliststart': 2}, INDICES[1:])
1062 test_selection({'playlist_items': '2-4'}, INDICES[1:4])
9e598870 1063 test_selection({'playlist_items': '2,4'}, [2, 4])
7e88d7d7 1064 test_selection({'playlist_items': '20'}, [], True)
ff1c7fc9 1065 test_selection({'playlist_items': '0'}, [])
cd6fc19e 1066
4e9e1e24 1067 # Tests for https://github.com/ytdl-org/youtube-dl/issues/10591
9e598870 1068 test_selection({'playlist_items': '2-4,3-4,3'}, [2, 3, 4])
1069 test_selection({'playlist_items': '4,2'}, [4, 2])
1070
1071 # Tests for https://github.com/yt-dlp/yt-dlp/issues/720
1072 # https://github.com/yt-dlp/yt-dlp/issues/302
7e88d7d7 1073 test_selection({'playlistreverse': True}, INDICES[::-1])
1074 test_selection({'playliststart': 2, 'playlistreverse': True}, INDICES[:0:-1])
9e598870 1075 test_selection({'playlist_items': '2,4', 'playlistreverse': True}, [4, 2])
1076 test_selection({'playlist_items': '4,2'}, [4, 2])
4e9e1e24 1077
7e88d7d7 1078 # Tests for --playlist-items start:end:step
1079 test_selection({'playlist_items': ':'}, INDICES, True)
1080 test_selection({'playlist_items': '::1'}, INDICES, True)
1081 test_selection({'playlist_items': '::-1'}, INDICES[::-1], True)
1082 test_selection({'playlist_items': ':6'}, INDICES[:6])
1083 test_selection({'playlist_items': ':-6'}, INDICES[:-5], True)
1084 test_selection({'playlist_items': '-1:6:-2'}, INDICES[:4:-2], True)
1085 test_selection({'playlist_items': '9:-6:-2'}, INDICES[8:3:-2], True)
1086
1087 test_selection({'playlist_items': '1:inf:2'}, INDICES[::2], True)
1088 test_selection({'playlist_items': '-2:inf'}, INDICES[-2:], True)
1089 test_selection({'playlist_items': ':inf:-1'}, [], True)
1090 test_selection({'playlist_items': '0-2:2'}, [2])
1091 test_selection({'playlist_items': '1-:2'}, INDICES[::2], True)
1092 test_selection({'playlist_items': '0--2:2'}, INDICES[1:-1:2], True)
1093
1094 test_selection({'playlist_items': '10::3'}, [10], True)
1095 test_selection({'playlist_items': '-1::3'}, [10], True)
1096 test_selection({'playlist_items': '11::3'}, [], True)
1097 test_selection({'playlist_items': '-15::2'}, INDICES[1::2], True)
1098 test_selection({'playlist_items': '-15::15'}, [], True)
1099
e37afbe0 1100 def test_urlopen_no_file_protocol(self):
067aa17e 1101 # see https://github.com/ytdl-org/youtube-dl/issues/8227
e37afbe0 1102 ydl = YDL()
ac668111 1103 self.assertRaises(urllib.error.URLError, ydl.urlopen, 'file:///etc/passwd')
e37afbe0 1104
b286f201
YCH
1105 def test_do_not_override_ie_key_in_url_transparent(self):
1106 ydl = YDL()
1107
1108 class Foo1IE(InfoExtractor):
1109 _VALID_URL = r'foo1:'
1110
1111 def _real_extract(self, url):
1112 return {
1113 '_type': 'url_transparent',
1114 'url': 'foo2:',
1115 'ie_key': 'Foo2',
0396806f
S
1116 'title': 'foo1 title',
1117 'id': 'foo1_id',
b286f201
YCH
1118 }
1119
1120 class Foo2IE(InfoExtractor):
1121 _VALID_URL = r'foo2:'
1122
1123 def _real_extract(self, url):
1124 return {
1125 '_type': 'url',
1126 'url': 'foo3:',
1127 'ie_key': 'Foo3',
1128 }
1129
1130 class Foo3IE(InfoExtractor):
1131 _VALID_URL = r'foo3:'
1132
1133 def _real_extract(self, url):
51350db5 1134 return _make_result([{'url': TEST_URL}], title='foo3 title')
b286f201
YCH
1135
1136 ydl.add_info_extractor(Foo1IE(ydl))
1137 ydl.add_info_extractor(Foo2IE(ydl))
1138 ydl.add_info_extractor(Foo3IE(ydl))
1139 ydl.extract_info('foo1:')
1140 downloaded = ydl.downloaded_info_dicts[0]
1141 self.assertEqual(downloaded['url'], TEST_URL)
51350db5 1142 self.assertEqual(downloaded['title'], 'foo1 title')
0396806f
S
1143 self.assertEqual(downloaded['id'], 'testid')
1144 self.assertEqual(downloaded['extractor'], 'testex')
1145 self.assertEqual(downloaded['extractor_key'], 'TestEx')
b286f201 1146
a0566bbf 1147 # Test case for https://github.com/ytdl-org/youtube-dl/issues/27064
1148 def test_ignoreerrors_for_playlist_with_url_transparent_iterable_entries(self):
1149
1150 class _YDL(YDL):
1151 def __init__(self, *args, **kwargs):
86e5f3ed 1152 super().__init__(*args, **kwargs)
a0566bbf 1153
1154 def trouble(self, s, tb=None):
1155 pass
1156
1157 ydl = _YDL({
1158 'format': 'extra',
1159 'ignoreerrors': True,
1160 })
1161
1162 class VideoIE(InfoExtractor):
1163 _VALID_URL = r'video:(?P<id>\d+)'
1164
1165 def _real_extract(self, url):
1166 video_id = self._match_id(url)
1167 formats = [{
1168 'format_id': 'default',
1169 'url': 'url:',
1170 }]
1171 if video_id == '0':
1172 raise ExtractorError('foo')
1173 if video_id == '2':
1174 formats.append({
1175 'format_id': 'extra',
1176 'url': TEST_URL,
1177 })
1178 return {
1179 'id': video_id,
1180 'title': 'Video %s' % video_id,
1181 'formats': formats,
1182 }
1183
1184 class PlaylistIE(InfoExtractor):
1185 _VALID_URL = r'playlist:'
1186
1187 def _entries(self):
1188 for n in range(3):
14f25df2 1189 video_id = str(n)
a0566bbf 1190 yield {
1191 '_type': 'url_transparent',
1192 'ie_key': VideoIE.ie_key(),
1193 'id': video_id,
1194 'url': 'video:%s' % video_id,
1195 'title': 'Video Transparent %s' % video_id,
1196 }
1197
1198 def _real_extract(self, url):
1199 return self.playlist_result(self._entries())
1200
1201 ydl.add_info_extractor(VideoIE(ydl))
1202 ydl.add_info_extractor(PlaylistIE(ydl))
1203 info = ydl.extract_info('playlist:')
1204 entries = info['entries']
1205 self.assertEqual(len(entries), 3)
1206 self.assertTrue(entries[0] is None)
1207 self.assertTrue(entries[1] is None)
1208 self.assertEqual(len(ydl.downloaded_info_dicts), 1)
1209 downloaded = ydl.downloaded_info_dicts[0]
9e907ebd 1210 entries[2].pop('requested_downloads', None)
a0566bbf 1211 self.assertEqual(entries[2], downloaded)
1212 self.assertEqual(downloaded['url'], TEST_URL)
1213 self.assertEqual(downloaded['title'], 'Video Transparent 2')
1214 self.assertEqual(downloaded['id'], '2')
1215 self.assertEqual(downloaded['extractor'], 'Video')
1216 self.assertEqual(downloaded['extractor_key'], 'Video')
1217
2b4ecde2 1218
e028d0d1
JMF
1219if __name__ == '__main__':
1220 unittest.main()