]>
Commit | Line | Data |
---|---|---|
cc52de43 | 1 | #!/usr/bin/env python3 |
5d254f77 PH |
2 | # Allow direct execution |
3 | import os | |
e028d0d1 JMF |
4 | import sys |
5 | import unittest | |
5d254f77 | 6 | sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) |
e028d0d1 | 7 | |
0217c783 | 8 | import copy |
7d1eb38a | 9 | import json |
0217c783 | 10 | |
c57f7757 | 11 | from test.helper import FakeYDL, assertRegexpMatches |
7a5c1cfe | 12 | from yt_dlp import YoutubeDL |
901130bb | 13 | from yt_dlp.compat import compat_os_name, compat_setenv, compat_str, compat_urllib_error |
7a5c1cfe P |
14 | from yt_dlp.extractor import YoutubeIE |
15 | from yt_dlp.extractor.common import InfoExtractor | |
16 | from yt_dlp.postprocessor.common import PostProcessor | |
6e84b215 | 17 | from yt_dlp.utils import ExtractorError, int_or_none, match_filter_func, LazyList |
e028d0d1 | 18 | |
8508557e JMF |
19 | TEST_URL = 'http://localhost/sample.mp4' |
20 | ||
e028d0d1 JMF |
21 | |
22 | class YDL(FakeYDL): | |
f4d96df0 | 23 | def __init__(self, *args, **kwargs): |
86e5f3ed | 24 | super().__init__(*args, **kwargs) |
e028d0d1 | 25 | self.downloaded_info_dicts = [] |
f4d96df0 | 26 | self.msgs = [] |
5d254f77 | 27 | |
e028d0d1 | 28 | def process_info(self, info_dict): |
09b49e1f | 29 | self.downloaded_info_dicts.append(info_dict.copy()) |
e028d0d1 | 30 | |
f4d96df0 PH |
31 | def to_screen(self, msg): |
32 | self.msgs.append(msg) | |
33 | ||
b5ac45b1 | 34 | def dl(self, *args, **kwargs): |
35 | assert False, 'Downloader must not be invoked for test_YoutubeDL' | |
36 | ||
5d254f77 | 37 | |
3537b93d PH |
38 | def _make_result(formats, **kwargs): |
39 | res = { | |
40 | 'formats': formats, | |
41 | 'id': 'testid', | |
42 | 'title': 'testttitle', | |
43 | 'extractor': 'testex', | |
0396806f | 44 | 'extractor_key': 'TestEx', |
732044af | 45 | 'webpage_url': 'http://example.com/watch?v=shenanigans', |
3537b93d PH |
46 | } |
47 | res.update(**kwargs) | |
48 | return res | |
49 | ||
50 | ||
e028d0d1 JMF |
51 | class TestFormatSelection(unittest.TestCase): |
52 | def test_prefer_free_formats(self): | |
53 | # Same resolution => download webm | |
54 | ydl = YDL() | |
55 | ydl.params['prefer_free_formats'] = True | |
5d254f77 | 56 | formats = [ |
8508557e JMF |
57 | {'ext': 'webm', 'height': 460, 'url': TEST_URL}, |
58 | {'ext': 'mp4', 'height': 460, 'url': TEST_URL}, | |
5d254f77 | 59 | ] |
3537b93d | 60 | info_dict = _make_result(formats) |
3d4a70b8 PH |
61 | yie = YoutubeIE(ydl) |
62 | yie._sort_formats(info_dict['formats']) | |
e028d0d1 JMF |
63 | ydl.process_ie_result(info_dict) |
64 | downloaded = ydl.downloaded_info_dicts[0] | |
89087418 | 65 | self.assertEqual(downloaded['ext'], 'webm') |
e028d0d1 JMF |
66 | |
67 | # Different resolution => download best quality (mp4) | |
68 | ydl = YDL() | |
69 | ydl.params['prefer_free_formats'] = True | |
5d254f77 | 70 | formats = [ |
8508557e JMF |
71 | {'ext': 'webm', 'height': 720, 'url': TEST_URL}, |
72 | {'ext': 'mp4', 'height': 1080, 'url': TEST_URL}, | |
5d254f77 | 73 | ] |
89087418 | 74 | info_dict['formats'] = formats |
3d4a70b8 PH |
75 | yie = YoutubeIE(ydl) |
76 | yie._sort_formats(info_dict['formats']) | |
e028d0d1 JMF |
77 | ydl.process_ie_result(info_dict) |
78 | downloaded = ydl.downloaded_info_dicts[0] | |
89087418 | 79 | self.assertEqual(downloaded['ext'], 'mp4') |
e028d0d1 | 80 | |
5d0c5371 | 81 | # No prefer_free_formats => prefer mp4 and webm |
e028d0d1 JMF |
82 | ydl = YDL() |
83 | ydl.params['prefer_free_formats'] = False | |
5d254f77 | 84 | formats = [ |
8508557e JMF |
85 | {'ext': 'webm', 'height': 720, 'url': TEST_URL}, |
86 | {'ext': 'mp4', 'height': 720, 'url': TEST_URL}, | |
87 | {'ext': 'flv', 'height': 720, 'url': TEST_URL}, | |
5d254f77 | 88 | ] |
89087418 | 89 | info_dict['formats'] = formats |
3d4a70b8 PH |
90 | yie = YoutubeIE(ydl) |
91 | yie._sort_formats(info_dict['formats']) | |
92 | ydl.process_ie_result(info_dict) | |
93 | downloaded = ydl.downloaded_info_dicts[0] | |
89087418 | 94 | self.assertEqual(downloaded['ext'], 'mp4') |
3d4a70b8 PH |
95 | |
96 | ydl = YDL() | |
97 | ydl.params['prefer_free_formats'] = False | |
98 | formats = [ | |
8508557e JMF |
99 | {'ext': 'flv', 'height': 720, 'url': TEST_URL}, |
100 | {'ext': 'webm', 'height': 720, 'url': TEST_URL}, | |
3d4a70b8 | 101 | ] |
89087418 | 102 | info_dict['formats'] = formats |
3d4a70b8 PH |
103 | yie = YoutubeIE(ydl) |
104 | yie._sort_formats(info_dict['formats']) | |
e028d0d1 JMF |
105 | ydl.process_ie_result(info_dict) |
106 | downloaded = ydl.downloaded_info_dicts[0] | |
5d0c5371 | 107 | self.assertEqual(downloaded['ext'], 'webm') |
e028d0d1 | 108 | |
a9c58ad9 JMF |
109 | def test_format_selection(self): |
110 | formats = [ | |
8508557e | 111 | {'format_id': '35', 'ext': 'mp4', 'preference': 1, 'url': TEST_URL}, |
232541df | 112 | {'format_id': 'example-with-dashes', 'ext': 'webm', 'preference': 1, 'url': TEST_URL}, |
8508557e JMF |
113 | {'format_id': '45', 'ext': 'webm', 'preference': 2, 'url': TEST_URL}, |
114 | {'format_id': '47', 'ext': 'webm', 'preference': 3, 'url': TEST_URL}, | |
115 | {'format_id': '2', 'ext': 'flv', 'preference': 4, 'url': TEST_URL}, | |
a9c58ad9 | 116 | ] |
3537b93d | 117 | info_dict = _make_result(formats) |
a9c58ad9 | 118 | |
b5ac45b1 | 119 | def test(inp, *expected, multi=False): |
120 | ydl = YDL({ | |
121 | 'format': inp, | |
122 | 'allow_multiple_video_streams': multi, | |
123 | 'allow_multiple_audio_streams': multi, | |
124 | }) | |
125 | ydl.process_ie_result(info_dict.copy()) | |
126 | downloaded = map(lambda x: x['format_id'], ydl.downloaded_info_dicts) | |
127 | self.assertEqual(list(downloaded), list(expected)) | |
128 | ||
129 | test('20/47', '47') | |
130 | test('20/71/worst', '35') | |
131 | test(None, '2') | |
132 | test('webm/mp4', '47') | |
133 | test('3gp/40/mp4', '35') | |
134 | test('example-with-dashes', 'example-with-dashes') | |
dd2a987d | 135 | test('all', '2', '47', '45', 'example-with-dashes', '35') |
b5ac45b1 | 136 | test('mergeall', '2+47+45+example-with-dashes+35', multi=True) |
232541df | 137 | |
ba7678f9 PH |
138 | def test_format_selection_audio(self): |
139 | formats = [ | |
8508557e JMF |
140 | {'format_id': 'audio-low', 'ext': 'webm', 'preference': 1, 'vcodec': 'none', 'url': TEST_URL}, |
141 | {'format_id': 'audio-mid', 'ext': 'webm', 'preference': 2, 'vcodec': 'none', 'url': TEST_URL}, | |
142 | {'format_id': 'audio-high', 'ext': 'flv', 'preference': 3, 'vcodec': 'none', 'url': TEST_URL}, | |
143 | {'format_id': 'vid', 'ext': 'mp4', 'preference': 4, 'url': TEST_URL}, | |
ba7678f9 | 144 | ] |
3537b93d | 145 | info_dict = _make_result(formats) |
ba7678f9 | 146 | |
89087418 | 147 | ydl = YDL({'format': 'bestaudio'}) |
ba7678f9 PH |
148 | ydl.process_ie_result(info_dict.copy()) |
149 | downloaded = ydl.downloaded_info_dicts[0] | |
89087418 | 150 | self.assertEqual(downloaded['format_id'], 'audio-high') |
ba7678f9 | 151 | |
89087418 | 152 | ydl = YDL({'format': 'worstaudio'}) |
ba7678f9 PH |
153 | ydl.process_ie_result(info_dict.copy()) |
154 | downloaded = ydl.downloaded_info_dicts[0] | |
89087418 | 155 | self.assertEqual(downloaded['format_id'], 'audio-low') |
ba7678f9 PH |
156 | |
157 | formats = [ | |
8508557e JMF |
158 | {'format_id': 'vid-low', 'ext': 'mp4', 'preference': 1, 'url': TEST_URL}, |
159 | {'format_id': 'vid-high', 'ext': 'mp4', 'preference': 2, 'url': TEST_URL}, | |
ba7678f9 | 160 | ] |
3537b93d | 161 | info_dict = _make_result(formats) |
ba7678f9 | 162 | |
89087418 | 163 | ydl = YDL({'format': 'bestaudio/worstaudio/best'}) |
ba7678f9 PH |
164 | ydl.process_ie_result(info_dict.copy()) |
165 | downloaded = ydl.downloaded_info_dicts[0] | |
89087418 | 166 | self.assertEqual(downloaded['format_id'], 'vid-high') |
ba7678f9 | 167 | |
0217c783 PH |
168 | def test_format_selection_audio_exts(self): |
169 | formats = [ | |
170 | {'format_id': 'mp3-64', 'ext': 'mp3', 'abr': 64, 'url': 'http://_', 'vcodec': 'none'}, | |
171 | {'format_id': 'ogg-64', 'ext': 'ogg', 'abr': 64, 'url': 'http://_', 'vcodec': 'none'}, | |
172 | {'format_id': 'aac-64', 'ext': 'aac', 'abr': 64, 'url': 'http://_', 'vcodec': 'none'}, | |
173 | {'format_id': 'mp3-32', 'ext': 'mp3', 'abr': 32, 'url': 'http://_', 'vcodec': 'none'}, | |
174 | {'format_id': 'aac-32', 'ext': 'aac', 'abr': 32, 'url': 'http://_', 'vcodec': 'none'}, | |
175 | ] | |
176 | ||
177 | info_dict = _make_result(formats) | |
178 | ydl = YDL({'format': 'best'}) | |
179 | ie = YoutubeIE(ydl) | |
180 | ie._sort_formats(info_dict['formats']) | |
181 | ydl.process_ie_result(copy.deepcopy(info_dict)) | |
182 | downloaded = ydl.downloaded_info_dicts[0] | |
183 | self.assertEqual(downloaded['format_id'], 'aac-64') | |
184 | ||
185 | ydl = YDL({'format': 'mp3'}) | |
186 | ie = YoutubeIE(ydl) | |
187 | ie._sort_formats(info_dict['formats']) | |
188 | ydl.process_ie_result(copy.deepcopy(info_dict)) | |
189 | downloaded = ydl.downloaded_info_dicts[0] | |
190 | self.assertEqual(downloaded['format_id'], 'mp3-64') | |
191 | ||
192 | ydl = YDL({'prefer_free_formats': True}) | |
193 | ie = YoutubeIE(ydl) | |
194 | ie._sort_formats(info_dict['formats']) | |
195 | ydl.process_ie_result(copy.deepcopy(info_dict)) | |
196 | downloaded = ydl.downloaded_info_dicts[0] | |
197 | self.assertEqual(downloaded['format_id'], 'ogg-64') | |
198 | ||
bc6d5978 JMF |
199 | def test_format_selection_video(self): |
200 | formats = [ | |
8508557e JMF |
201 | {'format_id': 'dash-video-low', 'ext': 'mp4', 'preference': 1, 'acodec': 'none', 'url': TEST_URL}, |
202 | {'format_id': 'dash-video-high', 'ext': 'mp4', 'preference': 2, 'acodec': 'none', 'url': TEST_URL}, | |
203 | {'format_id': 'vid', 'ext': 'mp4', 'preference': 3, 'url': TEST_URL}, | |
bc6d5978 | 204 | ] |
3537b93d | 205 | info_dict = _make_result(formats) |
bc6d5978 JMF |
206 | |
207 | ydl = YDL({'format': 'bestvideo'}) | |
208 | ydl.process_ie_result(info_dict.copy()) | |
209 | downloaded = ydl.downloaded_info_dicts[0] | |
210 | self.assertEqual(downloaded['format_id'], 'dash-video-high') | |
211 | ||
212 | ydl = YDL({'format': 'worstvideo'}) | |
213 | ydl.process_ie_result(info_dict.copy()) | |
214 | downloaded = ydl.downloaded_info_dicts[0] | |
215 | self.assertEqual(downloaded['format_id'], 'dash-video-low') | |
216 | ||
4c3b16d5 S |
217 | ydl = YDL({'format': 'bestvideo[format_id^=dash][format_id$=low]'}) |
218 | ydl.process_ie_result(info_dict.copy()) | |
219 | downloaded = ydl.downloaded_info_dicts[0] | |
220 | self.assertEqual(downloaded['format_id'], 'dash-video-low') | |
221 | ||
b913348d | 222 | formats = [ |
223 | {'format_id': 'vid-vcodec-dot', 'ext': 'mp4', 'preference': 1, 'vcodec': 'avc1.123456', 'acodec': 'none', 'url': TEST_URL}, | |
224 | ] | |
225 | info_dict = _make_result(formats) | |
226 | ||
227 | ydl = YDL({'format': 'bestvideo[vcodec=avc1.123456]'}) | |
228 | ydl.process_ie_result(info_dict.copy()) | |
229 | downloaded = ydl.downloaded_info_dicts[0] | |
230 | self.assertEqual(downloaded['format_id'], 'vid-vcodec-dot') | |
231 | ||
2cc779f4 S |
232 | def test_format_selection_string_ops(self): |
233 | formats = [ | |
234 | {'format_id': 'abc-cba', 'ext': 'mp4', 'url': TEST_URL}, | |
e118a879 | 235 | {'format_id': 'zxc-cxz', 'ext': 'webm', 'url': TEST_URL}, |
2cc779f4 S |
236 | ] |
237 | info_dict = _make_result(formats) | |
238 | ||
239 | # equals (=) | |
240 | ydl = YDL({'format': '[format_id=abc-cba]'}) | |
241 | ydl.process_ie_result(info_dict.copy()) | |
242 | downloaded = ydl.downloaded_info_dicts[0] | |
243 | self.assertEqual(downloaded['format_id'], 'abc-cba') | |
244 | ||
245 | # does not equal (!=) | |
246 | ydl = YDL({'format': '[format_id!=abc-cba]'}) | |
e118a879 S |
247 | ydl.process_ie_result(info_dict.copy()) |
248 | downloaded = ydl.downloaded_info_dicts[0] | |
249 | self.assertEqual(downloaded['format_id'], 'zxc-cxz') | |
250 | ||
251 | ydl = YDL({'format': '[format_id!=abc-cba][format_id!=zxc-cxz]'}) | |
2cc779f4 S |
252 | self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy()) |
253 | ||
254 | # starts with (^=) | |
255 | ydl = YDL({'format': '[format_id^=abc]'}) | |
256 | ydl.process_ie_result(info_dict.copy()) | |
257 | downloaded = ydl.downloaded_info_dicts[0] | |
258 | self.assertEqual(downloaded['format_id'], 'abc-cba') | |
259 | ||
260 | # does not start with (!^=) | |
e118a879 S |
261 | ydl = YDL({'format': '[format_id!^=abc]'}) |
262 | ydl.process_ie_result(info_dict.copy()) | |
263 | downloaded = ydl.downloaded_info_dicts[0] | |
264 | self.assertEqual(downloaded['format_id'], 'zxc-cxz') | |
265 | ||
266 | ydl = YDL({'format': '[format_id!^=abc][format_id!^=zxc]'}) | |
2cc779f4 S |
267 | self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy()) |
268 | ||
269 | # ends with ($=) | |
270 | ydl = YDL({'format': '[format_id$=cba]'}) | |
271 | ydl.process_ie_result(info_dict.copy()) | |
272 | downloaded = ydl.downloaded_info_dicts[0] | |
273 | self.assertEqual(downloaded['format_id'], 'abc-cba') | |
274 | ||
275 | # does not end with (!$=) | |
e118a879 S |
276 | ydl = YDL({'format': '[format_id!$=cba]'}) |
277 | ydl.process_ie_result(info_dict.copy()) | |
278 | downloaded = ydl.downloaded_info_dicts[0] | |
279 | self.assertEqual(downloaded['format_id'], 'zxc-cxz') | |
280 | ||
281 | ydl = YDL({'format': '[format_id!$=cba][format_id!$=cxz]'}) | |
2cc779f4 S |
282 | self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy()) |
283 | ||
284 | # contains (*=) | |
e118a879 | 285 | ydl = YDL({'format': '[format_id*=bc-cb]'}) |
2cc779f4 S |
286 | ydl.process_ie_result(info_dict.copy()) |
287 | downloaded = ydl.downloaded_info_dicts[0] | |
288 | self.assertEqual(downloaded['format_id'], 'abc-cba') | |
289 | ||
290 | # does not contain (!*=) | |
e118a879 S |
291 | ydl = YDL({'format': '[format_id!*=bc-cb]'}) |
292 | ydl.process_ie_result(info_dict.copy()) | |
293 | downloaded = ydl.downloaded_info_dicts[0] | |
294 | self.assertEqual(downloaded['format_id'], 'zxc-cxz') | |
295 | ||
296 | ydl = YDL({'format': '[format_id!*=abc][format_id!*=zxc]'}) | |
297 | self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy()) | |
298 | ||
2cc779f4 S |
299 | ydl = YDL({'format': '[format_id!*=-]'}) |
300 | self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy()) | |
301 | ||
3d4a70b8 | 302 | def test_youtube_format_selection(self): |
a7191c6f | 303 | # FIXME: Rewrite in accordance with the new format sorting options |
5d0c5371 | 304 | return |
5d0c5371 | 305 | |
3d4a70b8 | 306 | order = [ |
86bf2905 | 307 | '38', '37', '46', '22', '45', '35', '44', '18', '34', '43', '6', '5', '17', '36', '13', |
3d4a70b8 PH |
308 | # Apple HTTP Live Streaming |
309 | '96', '95', '94', '93', '92', '132', '151', | |
310 | # 3D | |
311 | '85', '84', '102', '83', '101', '82', '100', | |
312 | # Dash video | |
c11125f9 | 313 | '137', '248', '136', '247', '135', '246', |
3d4a70b8 PH |
314 | '245', '244', '134', '243', '133', '242', '160', |
315 | # Dash audio | |
a053c349 | 316 | '141', '172', '140', '171', '139', |
3d4a70b8 PH |
317 | ] |
318 | ||
67134eab JMF |
319 | def format_info(f_id): |
320 | info = YoutubeIE._formats[f_id].copy() | |
1df41411 | 321 | |
91cb6b50 | 322 | # XXX: In real cases InfoExtractor._parse_mpd_formats() fills up 'acodec' |
1df41411 YCH |
323 | # and 'vcodec', while in tests such information is incomplete since |
324 | # commit a6c2c24479e5f4827ceb06f64d855329c0a6f593 | |
325 | # test_YoutubeDL.test_youtube_format_selection is broken without | |
326 | # this fix | |
327 | if 'acodec' in info and 'vcodec' not in info: | |
328 | info['vcodec'] = 'none' | |
329 | elif 'vcodec' in info and 'acodec' not in info: | |
330 | info['acodec'] = 'none' | |
331 | ||
67134eab JMF |
332 | info['format_id'] = f_id |
333 | info['url'] = 'url:' + f_id | |
334 | return info | |
335 | formats_order = [format_info(f_id) for f_id in order] | |
336 | ||
337 | info_dict = _make_result(list(formats_order), extractor='youtube') | |
338 | ydl = YDL({'format': 'bestvideo+bestaudio'}) | |
339 | yie = YoutubeIE(ydl) | |
340 | yie._sort_formats(info_dict['formats']) | |
341 | ydl.process_ie_result(info_dict) | |
342 | downloaded = ydl.downloaded_info_dicts[0] | |
5d0c5371 | 343 | self.assertEqual(downloaded['format_id'], '248+172') |
67134eab | 344 | self.assertEqual(downloaded['ext'], 'mp4') |
3d4a70b8 | 345 | |
cf2ac6df JMF |
346 | info_dict = _make_result(list(formats_order), extractor='youtube') |
347 | ydl = YDL({'format': 'bestvideo[height>=999999]+bestaudio/best'}) | |
348 | yie = YoutubeIE(ydl) | |
349 | yie._sort_formats(info_dict['formats']) | |
350 | ydl.process_ie_result(info_dict) | |
351 | downloaded = ydl.downloaded_info_dicts[0] | |
352 | self.assertEqual(downloaded['format_id'], '38') | |
353 | ||
f5f4a27a JMF |
354 | info_dict = _make_result(list(formats_order), extractor='youtube') |
355 | ydl = YDL({'format': 'bestvideo/best,bestaudio'}) | |
356 | yie = YoutubeIE(ydl) | |
357 | yie._sort_formats(info_dict['formats']) | |
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'}) | |
364 | yie = YoutubeIE(ydl) | |
365 | yie._sort_formats(info_dict['formats']) | |
366 | ydl.process_ie_result(info_dict) | |
367 | downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts] | |
368 | self.assertEqual(downloaded_ids, ['137+141', '248+141']) | |
369 | ||
370 | info_dict = _make_result(list(formats_order), extractor='youtube') | |
371 | ydl = YDL({'format': '(bestvideo[ext=mp4],bestvideo[ext=webm])[height<=720]+bestaudio'}) | |
372 | yie = YoutubeIE(ydl) | |
373 | yie._sort_formats(info_dict['formats']) | |
374 | ydl.process_ie_result(info_dict) | |
375 | downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts] | |
376 | self.assertEqual(downloaded_ids, ['136+141', '247+141']) | |
377 | ||
378 | info_dict = _make_result(list(formats_order), extractor='youtube') | |
379 | ydl = YDL({'format': '(bestvideo[ext=none]/bestvideo[ext=webm])+bestaudio'}) | |
380 | yie = YoutubeIE(ydl) | |
381 | yie._sort_formats(info_dict['formats']) | |
382 | ydl.process_ie_result(info_dict) | |
383 | downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts] | |
384 | self.assertEqual(downloaded_ids, ['248+141']) | |
385 | ||
67134eab | 386 | for f1, f2 in zip(formats_order, formats_order[1:]): |
3537b93d | 387 | info_dict = _make_result([f1, f2], extractor='youtube') |
8dd54188 | 388 | ydl = YDL({'format': 'best/bestvideo'}) |
3d4a70b8 PH |
389 | yie = YoutubeIE(ydl) |
390 | yie._sort_formats(info_dict['formats']) | |
391 | ydl.process_ie_result(info_dict) | |
392 | downloaded = ydl.downloaded_info_dicts[0] | |
67134eab | 393 | self.assertEqual(downloaded['format_id'], f1['format_id']) |
3d4a70b8 | 394 | |
3537b93d | 395 | info_dict = _make_result([f2, f1], extractor='youtube') |
8dd54188 | 396 | ydl = YDL({'format': 'best/bestvideo'}) |
3d4a70b8 PH |
397 | yie = YoutubeIE(ydl) |
398 | yie._sort_formats(info_dict['formats']) | |
399 | ydl.process_ie_result(info_dict) | |
400 | downloaded = ydl.downloaded_info_dicts[0] | |
67134eab | 401 | self.assertEqual(downloaded['format_id'], f1['format_id']) |
3d4a70b8 | 402 | |
317f7ab6 S |
403 | def test_audio_only_extractor_format_selection(self): |
404 | # For extractors with incomplete formats (all formats are audio-only or | |
405 | # video-only) best and worst should fallback to corresponding best/worst | |
406 | # video-only or audio-only formats (as per | |
067aa17e | 407 | # https://github.com/ytdl-org/youtube-dl/pull/5556) |
317f7ab6 S |
408 | formats = [ |
409 | {'format_id': 'low', 'ext': 'mp3', 'preference': 1, 'vcodec': 'none', 'url': TEST_URL}, | |
410 | {'format_id': 'high', 'ext': 'mp3', 'preference': 2, 'vcodec': 'none', 'url': TEST_URL}, | |
411 | ] | |
412 | info_dict = _make_result(formats) | |
413 | ||
414 | ydl = YDL({'format': 'best'}) | |
415 | ydl.process_ie_result(info_dict.copy()) | |
416 | downloaded = ydl.downloaded_info_dicts[0] | |
417 | self.assertEqual(downloaded['format_id'], 'high') | |
418 | ||
419 | ydl = YDL({'format': 'worst'}) | |
420 | ydl.process_ie_result(info_dict.copy()) | |
421 | downloaded = ydl.downloaded_info_dicts[0] | |
422 | self.assertEqual(downloaded['format_id'], 'low') | |
423 | ||
424 | def test_format_not_available(self): | |
425 | formats = [ | |
426 | {'format_id': 'regular', 'ext': 'mp4', 'height': 360, 'url': TEST_URL}, | |
427 | {'format_id': 'video', 'ext': 'mp4', 'height': 720, 'acodec': 'none', 'url': TEST_URL}, | |
428 | ] | |
429 | info_dict = _make_result(formats) | |
430 | ||
431 | # This must fail since complete video-audio format does not match filter | |
432 | # and extractor does not provide incomplete only formats (i.e. only | |
433 | # video-only or audio-only). | |
434 | ydl = YDL({'format': 'best[height>360]'}) | |
435 | self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy()) | |
436 | ||
8cda78ef | 437 | def test_format_selection_issue_10083(self): |
067aa17e | 438 | # See https://github.com/ytdl-org/youtube-dl/issues/10083 |
8cda78ef S |
439 | formats = [ |
440 | {'format_id': 'regular', 'height': 360, 'url': TEST_URL}, | |
441 | {'format_id': 'video', 'height': 720, 'acodec': 'none', 'url': TEST_URL}, | |
442 | {'format_id': 'audio', 'vcodec': 'none', 'url': TEST_URL}, | |
443 | ] | |
444 | info_dict = _make_result(formats) | |
445 | ||
446 | ydl = YDL({'format': 'best[height>360]/bestvideo[height>360]+bestaudio'}) | |
447 | ydl.process_ie_result(info_dict.copy()) | |
448 | self.assertEqual(ydl.downloaded_info_dicts[0]['format_id'], 'video+audio') | |
449 | ||
0a31a350 JMF |
450 | def test_invalid_format_specs(self): |
451 | def assert_syntax_error(format_spec): | |
187986a8 | 452 | self.assertRaises(SyntaxError, YDL, {'format': format_spec}) |
0a31a350 JMF |
453 | |
454 | assert_syntax_error('bestvideo,,best') | |
455 | assert_syntax_error('+bestaudio') | |
456 | assert_syntax_error('bestvideo+') | |
d96d604e | 457 | assert_syntax_error('/') |
187986a8 | 458 | assert_syntax_error('[720<height]') |
0a31a350 | 459 | |
083c9df9 PH |
460 | def test_format_filtering(self): |
461 | formats = [ | |
462 | {'format_id': 'A', 'filesize': 500, 'width': 1000}, | |
463 | {'format_id': 'B', 'filesize': 1000, 'width': 500}, | |
464 | {'format_id': 'C', 'filesize': 1000, 'width': 400}, | |
465 | {'format_id': 'D', 'filesize': 2000, 'width': 600}, | |
466 | {'format_id': 'E', 'filesize': 3000}, | |
467 | {'format_id': 'F'}, | |
468 | {'format_id': 'G', 'filesize': 1000000}, | |
469 | ] | |
470 | for f in formats: | |
471 | f['url'] = 'http://_/' | |
472 | f['ext'] = 'unknown' | |
473 | info_dict = _make_result(formats) | |
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'], 'D') | |
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'], 'E') | |
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'], 'F') | |
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'], 'B') | |
494 | ||
495 | ydl = YDL({'format': 'best [filesize = 1000] [width!=450]'}) | |
496 | ydl.process_ie_result(info_dict) | |
497 | downloaded = ydl.downloaded_info_dicts[0] | |
498 | self.assertEqual(downloaded['format_id'], 'C') | |
499 | ||
500 | ydl = YDL({'format': '[filesize>?1]'}) | |
501 | ydl.process_ie_result(info_dict) | |
502 | downloaded = ydl.downloaded_info_dicts[0] | |
503 | self.assertEqual(downloaded['format_id'], 'G') | |
504 | ||
505 | ydl = YDL({'format': '[filesize<1M]'}) | |
506 | ydl.process_ie_result(info_dict) | |
507 | downloaded = ydl.downloaded_info_dicts[0] | |
508 | self.assertEqual(downloaded['format_id'], 'E') | |
509 | ||
510 | ydl = YDL({'format': '[filesize<1MiB]'}) | |
511 | ydl.process_ie_result(info_dict) | |
512 | downloaded = ydl.downloaded_info_dicts[0] | |
513 | self.assertEqual(downloaded['format_id'], 'G') | |
514 | ||
5acfa126 JMF |
515 | ydl = YDL({'format': 'all[width>=400][width<=600]'}) |
516 | ydl.process_ie_result(info_dict) | |
517 | downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts] | |
dd2a987d | 518 | self.assertEqual(downloaded_ids, ['D', 'C', 'B']) |
5acfa126 | 519 | |
bb8e5536 JMF |
520 | ydl = YDL({'format': 'best[height<40]'}) |
521 | try: | |
522 | ydl.process_ie_result(info_dict) | |
523 | except ExtractorError: | |
524 | pass | |
525 | self.assertEqual(ydl.downloaded_info_dicts, []) | |
526 | ||
0017d9ad S |
527 | def test_default_format_spec(self): |
528 | ydl = YDL({'simulate': True}) | |
5d0c5371 | 529 | self.assertEqual(ydl._default_format_spec({}), 'bestvideo*+bestaudio/best') |
0017d9ad | 530 | |
d08dcd2d S |
531 | ydl = YDL({}) |
532 | self.assertEqual(ydl._default_format_spec({'is_live': True}), 'best/bestvideo+bestaudio') | |
af0f7428 | 533 | |
d08dcd2d | 534 | ydl = YDL({'simulate': True}) |
5d0c5371 | 535 | self.assertEqual(ydl._default_format_spec({'is_live': True}), 'bestvideo*+bestaudio/best') |
af0f7428 | 536 | |
0017d9ad | 537 | ydl = YDL({'outtmpl': '-'}) |
af0f7428 | 538 | self.assertEqual(ydl._default_format_spec({}), 'best/bestvideo+bestaudio') |
0017d9ad S |
539 | |
540 | ydl = YDL({}) | |
5d0c5371 | 541 | self.assertEqual(ydl._default_format_spec({}, download=False), 'bestvideo*+bestaudio/best') |
af0f7428 | 542 | self.assertEqual(ydl._default_format_spec({'is_live': True}), 'best/bestvideo+bestaudio') |
0017d9ad | 543 | |
f20bf146 JMF |
544 | |
545 | class TestYoutubeDL(unittest.TestCase): | |
ab84349b JMF |
546 | def test_subtitles(self): |
547 | def s_formats(lang, autocaption=False): | |
548 | return [{ | |
549 | 'ext': ext, | |
86e5f3ed | 550 | 'url': f'http://localhost/video.{lang}.{ext}', |
ab84349b JMF |
551 | '_auto': autocaption, |
552 | } for ext in ['vtt', 'srt', 'ass']] | |
86e5f3ed | 553 | subtitles = {l: s_formats(l) for l in ['en', 'fr', 'es']} |
554 | auto_captions = {l: s_formats(l, True) for l in ['it', 'pt', 'es']} | |
ab84349b JMF |
555 | info_dict = { |
556 | 'id': 'test', | |
557 | 'title': 'Test', | |
558 | 'url': 'http://localhost/video.mp4', | |
559 | 'subtitles': subtitles, | |
560 | 'automatic_captions': auto_captions, | |
561 | 'extractor': 'TEST', | |
732044af | 562 | 'webpage_url': 'http://example.com/watch?v=shenanigans', |
ab84349b JMF |
563 | } |
564 | ||
565 | def get_info(params={}): | |
566 | params.setdefault('simulate', True) | |
567 | ydl = YDL(params) | |
568 | ydl.report_warning = lambda *args, **kargs: None | |
569 | return ydl.process_video_result(info_dict, download=False) | |
570 | ||
571 | result = get_info() | |
572 | self.assertFalse(result.get('requested_subtitles')) | |
573 | self.assertEqual(result['subtitles'], subtitles) | |
574 | self.assertEqual(result['automatic_captions'], auto_captions) | |
575 | ||
576 | result = get_info({'writesubtitles': True}) | |
577 | subs = result['requested_subtitles'] | |
578 | self.assertTrue(subs) | |
86e5f3ed | 579 | self.assertEqual(set(subs.keys()), {'en'}) |
ab84349b JMF |
580 | self.assertTrue(subs['en'].get('data') is None) |
581 | self.assertEqual(subs['en']['ext'], 'ass') | |
582 | ||
583 | result = get_info({'writesubtitles': True, 'subtitlesformat': 'foo/srt'}) | |
584 | subs = result['requested_subtitles'] | |
585 | self.assertEqual(subs['en']['ext'], 'srt') | |
586 | ||
587 | result = get_info({'writesubtitles': True, 'subtitleslangs': ['es', 'fr', 'it']}) | |
588 | subs = result['requested_subtitles'] | |
589 | self.assertTrue(subs) | |
86e5f3ed | 590 | self.assertEqual(set(subs.keys()), {'es', 'fr'}) |
ab84349b | 591 | |
c32b0aab | 592 | result = get_info({'writesubtitles': True, 'subtitleslangs': ['all', '-en']}) |
593 | subs = result['requested_subtitles'] | |
594 | self.assertTrue(subs) | |
86e5f3ed | 595 | self.assertEqual(set(subs.keys()), {'es', 'fr'}) |
c32b0aab | 596 | |
597 | result = get_info({'writesubtitles': True, 'subtitleslangs': ['en', 'fr', '-en']}) | |
598 | subs = result['requested_subtitles'] | |
599 | self.assertTrue(subs) | |
86e5f3ed | 600 | self.assertEqual(set(subs.keys()), {'fr'}) |
c32b0aab | 601 | |
602 | result = get_info({'writesubtitles': True, 'subtitleslangs': ['-en', 'en']}) | |
603 | subs = result['requested_subtitles'] | |
604 | self.assertTrue(subs) | |
86e5f3ed | 605 | self.assertEqual(set(subs.keys()), {'en'}) |
c32b0aab | 606 | |
607 | result = get_info({'writesubtitles': True, 'subtitleslangs': ['e.+']}) | |
608 | subs = result['requested_subtitles'] | |
609 | self.assertTrue(subs) | |
86e5f3ed | 610 | self.assertEqual(set(subs.keys()), {'es', 'en'}) |
c32b0aab | 611 | |
ab84349b JMF |
612 | result = get_info({'writesubtitles': True, 'writeautomaticsub': True, 'subtitleslangs': ['es', 'pt']}) |
613 | subs = result['requested_subtitles'] | |
614 | self.assertTrue(subs) | |
86e5f3ed | 615 | self.assertEqual(set(subs.keys()), {'es', 'pt'}) |
ab84349b JMF |
616 | self.assertFalse(subs['es']['_auto']) |
617 | self.assertTrue(subs['pt']['_auto']) | |
618 | ||
98c70d6f JMF |
619 | result = get_info({'writeautomaticsub': True, 'subtitleslangs': ['es', 'pt']}) |
620 | subs = result['requested_subtitles'] | |
621 | self.assertTrue(subs) | |
86e5f3ed | 622 | self.assertEqual(set(subs.keys()), {'es', 'pt'}) |
98c70d6f JMF |
623 | self.assertTrue(subs['es']['_auto']) |
624 | self.assertTrue(subs['pt']['_auto']) | |
625 | ||
b6c45014 JMF |
626 | def test_add_extra_info(self): |
627 | test_dict = { | |
628 | 'extractor': 'Foo', | |
629 | } | |
630 | extra_info = { | |
631 | 'extractor': 'Bar', | |
632 | 'playlist': 'funny videos', | |
633 | } | |
634 | YDL.add_extra_info(test_dict, extra_info) | |
635 | self.assertEqual(test_dict['extractor'], 'Foo') | |
636 | self.assertEqual(test_dict['playlist'], 'funny videos') | |
637 | ||
752cda38 | 638 | outtmpl_info = { |
639 | 'id': '1234', | |
640 | 'ext': 'mp4', | |
641 | 'width': None, | |
642 | 'height': 1080, | |
abbeeebc | 643 | 'filesize': 1024, |
752cda38 | 644 | 'title1': '$PATH', |
645 | 'title2': '%PATH%', | |
87ea7dfc | 646 | 'title3': 'foo/bar\\test', |
7d1eb38a | 647 | 'title4': 'foo "bar" test', |
524e2e4f | 648 | 'title5': 'áéí 𝐀', |
752cda38 | 649 | 'timestamp': 1618488000, |
650 | 'duration': 100000, | |
651 | 'playlist_index': 1, | |
e6f21b3d | 652 | 'playlist_autonumber': 2, |
752cda38 | 653 | '_last_playlist_index': 100, |
654 | 'n_entries': 10, | |
4476d2c7 | 655 | 'formats': [{'id': 'id 1'}, {'id': 'id 2'}, {'id': 'id 3'}] |
752cda38 | 656 | } |
657 | ||
5c6542ce | 658 | def test_prepare_outtmpl_and_filename(self): |
9fea350f | 659 | def test(tmpl, expected, *, info=None, **params): |
752cda38 | 660 | params['outtmpl'] = tmpl |
661 | ydl = YoutubeDL(params) | |
662 | ydl._num_downloads = 1 | |
5c6542ce | 663 | self.assertEqual(ydl.validate_outtmpl(tmpl), None) |
752cda38 | 664 | |
819e0531 | 665 | out = ydl.evaluate_outtmpl(tmpl, info or self.outtmpl_info) |
9fea350f | 666 | fname = ydl.prepare_filename(info or self.outtmpl_info) |
5c6542ce | 667 | |
2b8a2973 | 668 | if not isinstance(expected, (list, tuple)): |
669 | expected = (expected, expected) | |
670 | for (name, got), expect in zip((('outtmpl', out), ('filename', fname)), expected): | |
671 | if callable(expect): | |
672 | self.assertTrue(expect(got), f'Wrong {name} from {tmpl}') | |
673 | else: | |
674 | self.assertEqual(got, expect, f'Wrong {name} from {tmpl}') | |
5c6542ce | 675 | |
6e84b215 | 676 | # Side-effects |
677 | original_infodict = dict(self.outtmpl_info) | |
678 | test('foo.bar', 'foo.bar') | |
679 | original_infodict['epoch'] = self.outtmpl_info.get('epoch') | |
680 | self.assertTrue(isinstance(original_infodict['epoch'], int)) | |
681 | test('%(epoch)d', int_or_none) | |
682 | self.assertEqual(original_infodict, self.outtmpl_info) | |
683 | ||
5c6542ce | 684 | # Auto-generated fields |
685 | test('%(id)s.%(ext)s', '1234.mp4') | |
686 | test('%(duration_string)s', ('27:46:40', '27-46-40')) | |
5c6542ce | 687 | test('%(resolution)s', '1080p') |
688 | test('%(playlist_index)s', '001') | |
e6f21b3d | 689 | test('%(playlist_autonumber)s', '02') |
5c6542ce | 690 | test('%(autonumber)s', '00001') |
691 | test('%(autonumber+2)03d', '005', autonumber_start=3) | |
692 | test('%(autonumber)s', '001', autonumber_size=3) | |
693 | ||
694 | # Escaping % | |
901130bb | 695 | test('%', '%') |
5c6542ce | 696 | test('%%', '%') |
697 | test('%%%%', '%%') | |
901130bb | 698 | test('%s', '%s') |
699 | test('%%%s', '%%s') | |
700 | test('%d', '%d') | |
701 | test('%abc%', '%abc%') | |
5c6542ce | 702 | test('%%(width)06d.%(ext)s', '%(width)06d.mp4') |
901130bb | 703 | test('%%%(height)s', '%1080') |
5c6542ce | 704 | test('%(width)06d.%(ext)s', 'NA.mp4') |
705 | test('%(width)06d.%%(ext)s', 'NA.%(ext)s') | |
706 | test('%%(width)06d.%(ext)s', '%(width)06d.mp4') | |
707 | ||
9fea350f | 708 | # ID sanitization |
709 | test('%(id)s', '_abcd', info={'id': '_abcd'}) | |
710 | test('%(some_id)s', '_abcd', info={'some_id': '_abcd'}) | |
711 | test('%(formats.0.id)s', '_abcd', info={'formats': [{'id': '_abcd'}]}) | |
712 | test('%(id)s', '-abcd', info={'id': '-abcd'}) | |
713 | test('%(id)s', '.abcd', info={'id': '.abcd'}) | |
714 | test('%(id)s', 'ab__cd', info={'id': 'ab__cd'}) | |
715 | test('%(id)s', ('ab:cd', 'ab -cd'), info={'id': 'ab:cd'}) | |
e0fd9573 | 716 | test('%(id.0)s', '-', info={'id': '--'}) |
9fea350f | 717 | |
5c6542ce | 718 | # Invalid templates |
5c6542ce | 719 | self.assertTrue(isinstance(YoutubeDL.validate_outtmpl('%(title)'), ValueError)) |
720 | test('%(invalid@tmpl|def)s', 'none', outtmpl_na_placeholder='none') | |
2b8a2973 | 721 | test('%(..)s', 'NA') |
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'] |
4476d2c7 | 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') |
781 | test('%(title4).10S', ('foo \'bar\' ', 'foo \'bar\'' + ('#' if compat_os_name == 'nt' else ' '))) | |
7d1eb38a | 782 | if compat_os_name == 'nt': |
783 | test('%(title4)q', ('"foo \\"bar\\" test"', "'foo _'bar_' test'")) | |
4476d2c7 | 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: |
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') |
5c6542ce | 806 | |
7c37ff97 | 807 | # Alternates |
808 | test('%(title,id)s', '1234') | |
809 | test('%(width-100,height+20|def)d', '1100') | |
810 | test('%(width-100,height+width|def)s', 'def') | |
811 | test('%(timestamp-x>%H\\,%M\\,%S,timestamp>%H\\,%M\\,%S)s', '12,00,00') | |
812 | ||
e0fd9573 | 813 | # Replacement |
814 | test('%(id&foo)s.bar', 'foo.bar') | |
815 | test('%(title&foo)s.bar', 'NA.bar') | |
816 | test('%(title&foo|baz)s.bar', 'baz.bar') | |
34baa9fd | 817 | test('%(x,id&foo|baz)s.bar', 'foo.bar') |
818 | test('%(x,title&foo|baz)s.bar', 'baz.bar') | |
e0fd9573 | 819 | |
6e84b215 | 820 | # Laziness |
821 | def gen(): | |
822 | yield from range(5) | |
823 | raise self.assertTrue(False, 'LazyList should not be evaluated till here') | |
824 | test('%(key.4)s', '4', info={'key': LazyList(gen())}) | |
825 | ||
5c6542ce | 826 | # Empty filename |
827 | test('%(foo|)s-%(bar|)s.%(ext)s', '-.mp4') | |
828 | # test('%(foo|)s.%(ext)s', ('.mp4', '_.mp4')) # fixme | |
829 | # test('%(foo|)s', ('', '_')) # fixme | |
830 | ||
901130bb | 831 | # Environment variable expansion for prepare_filename |
832 | compat_setenv('__yt_dlp_var', 'expanded') | |
833 | envvar = '%__yt_dlp_var%' if compat_os_name == 'nt' else '$__yt_dlp_var' | |
834 | test(envvar, (envvar, 'expanded')) | |
b836dc94 | 835 | if compat_os_name == 'nt': |
836 | test('%s%', ('%s%', '%s%')) | |
837 | compat_setenv('s', 'expanded') | |
838 | test('%s%', ('%s%', 'expanded')) # %s% should be expanded before escaping %s | |
839 | compat_setenv('(test)s', 'expanded') | |
840 | test('%(test)s%', ('NA%', 'expanded')) # Environment should take priority over template | |
901130bb | 841 | |
5c6542ce | 842 | # Path expansion and escaping |
843 | test('Hello %(title1)s', 'Hello $PATH') | |
844 | test('Hello %(title2)s', 'Hello %PATH%') | |
845 | test('%(title3)s', ('foo/bar\\test', 'foo_bar_test')) | |
846 | test('folder/%(title3)s', ('folder/foo/bar\\test', 'folder%sfoo_bar_test' % os.path.sep)) | |
26e63931 | 847 | |
c57f7757 PH |
848 | def test_format_note(self): |
849 | ydl = YoutubeDL() | |
850 | self.assertEqual(ydl._format_note({}), '') | |
851 | assertRegexpMatches(self, ydl._format_note({ | |
852 | 'vbr': 10, | |
398dea32 | 853 | }), r'^\s*10k$') |
5d583bdf S |
854 | assertRegexpMatches(self, ydl._format_note({ |
855 | 'fps': 30, | |
398dea32 | 856 | }), r'^30fps$') |
5d583bdf | 857 | |
2b4ecde2 JMF |
858 | def test_postprocessors(self): |
859 | filename = 'post-processor-testfile.mp4' | |
860 | audiofile = filename + '.mp3' | |
861 | ||
862 | class SimplePP(PostProcessor): | |
863 | def run(self, info): | |
2b4ecde2 JMF |
864 | with open(audiofile, 'wt') as f: |
865 | f.write('EXAMPLE') | |
592e97e8 | 866 | return [info['filepath']], info |
2b4ecde2 | 867 | |
592e97e8 | 868 | def run_pp(params, PP): |
2b4ecde2 JMF |
869 | with open(filename, 'wt') as f: |
870 | f.write('EXAMPLE') | |
871 | ydl = YoutubeDL(params) | |
592e97e8 | 872 | ydl.add_post_processor(PP()) |
2b4ecde2 JMF |
873 | ydl.post_process(filename, {'filepath': filename}) |
874 | ||
592e97e8 | 875 | run_pp({'keepvideo': True}, SimplePP) |
2b4ecde2 JMF |
876 | self.assertTrue(os.path.exists(filename), '%s doesn\'t exist' % filename) |
877 | self.assertTrue(os.path.exists(audiofile), '%s doesn\'t exist' % audiofile) | |
878 | os.unlink(filename) | |
879 | os.unlink(audiofile) | |
880 | ||
592e97e8 | 881 | run_pp({'keepvideo': False}, SimplePP) |
2b4ecde2 JMF |
882 | self.assertFalse(os.path.exists(filename), '%s exists' % filename) |
883 | self.assertTrue(os.path.exists(audiofile), '%s doesn\'t exist' % audiofile) | |
884 | os.unlink(audiofile) | |
885 | ||
592e97e8 JMF |
886 | class ModifierPP(PostProcessor): |
887 | def run(self, info): | |
888 | with open(info['filepath'], 'wt') as f: | |
889 | f.write('MODIFIED') | |
890 | return [], info | |
891 | ||
892 | run_pp({'keepvideo': False}, ModifierPP) | |
893 | self.assertTrue(os.path.exists(filename), '%s doesn\'t exist' % filename) | |
894 | os.unlink(filename) | |
895 | ||
531980d8 | 896 | def test_match_filter(self): |
531980d8 JMF |
897 | first = { |
898 | 'id': '1', | |
899 | 'url': TEST_URL, | |
900 | 'title': 'one', | |
901 | 'extractor': 'TEST', | |
902 | 'duration': 30, | |
903 | 'filesize': 10 * 1024, | |
e5a088dc | 904 | 'playlist_id': '42', |
db13c16e S |
905 | 'uploader': "變態妍字幕版 太妍 тест", |
906 | 'creator': "тест ' 123 ' тест--", | |
732044af | 907 | 'webpage_url': 'http://example.com/watch?v=shenanigans', |
531980d8 JMF |
908 | } |
909 | second = { | |
910 | 'id': '2', | |
911 | 'url': TEST_URL, | |
912 | 'title': 'two', | |
913 | 'extractor': 'TEST', | |
914 | 'duration': 10, | |
915 | 'description': 'foo', | |
916 | 'filesize': 5 * 1024, | |
e5a088dc | 917 | 'playlist_id': '43', |
db13c16e | 918 | 'uploader': "тест 123", |
732044af | 919 | 'webpage_url': 'http://example.com/watch?v=SHENANIGANS', |
531980d8 JMF |
920 | } |
921 | videos = [first, second] | |
922 | ||
923 | def get_videos(filter_=None): | |
09b49e1f | 924 | ydl = YDL({'match_filter': filter_, 'simulate': True}) |
531980d8 JMF |
925 | for v in videos: |
926 | ydl.process_ie_result(v, download=True) | |
927 | return [v['id'] for v in ydl.downloaded_info_dicts] | |
928 | ||
929 | res = get_videos() | |
930 | self.assertEqual(res, ['1', '2']) | |
931 | ||
6db9c4d5 | 932 | def f(v, incomplete): |
531980d8 JMF |
933 | if v['id'] == '1': |
934 | return None | |
935 | else: | |
936 | return 'Video id is not 1' | |
937 | res = get_videos(f) | |
938 | self.assertEqual(res, ['1']) | |
939 | ||
940 | f = match_filter_func('duration < 30') | |
941 | res = get_videos(f) | |
942 | self.assertEqual(res, ['2']) | |
943 | ||
944 | f = match_filter_func('description = foo') | |
945 | res = get_videos(f) | |
946 | self.assertEqual(res, ['2']) | |
947 | ||
948 | f = match_filter_func('description =? foo') | |
949 | res = get_videos(f) | |
950 | self.assertEqual(res, ['1', '2']) | |
951 | ||
952 | f = match_filter_func('filesize > 5KiB') | |
953 | res = get_videos(f) | |
954 | self.assertEqual(res, ['1']) | |
955 | ||
e5a088dc S |
956 | f = match_filter_func('playlist_id = 42') |
957 | res = get_videos(f) | |
958 | self.assertEqual(res, ['1']) | |
959 | ||
db13c16e S |
960 | f = match_filter_func('uploader = "變態妍字幕版 太妍 тест"') |
961 | res = get_videos(f) | |
962 | self.assertEqual(res, ['1']) | |
963 | ||
964 | f = match_filter_func('uploader != "變態妍字幕版 太妍 тест"') | |
965 | res = get_videos(f) | |
966 | self.assertEqual(res, ['2']) | |
967 | ||
968 | f = match_filter_func('creator = "тест \' 123 \' тест--"') | |
969 | res = get_videos(f) | |
970 | self.assertEqual(res, ['1']) | |
971 | ||
972 | f = match_filter_func("creator = 'тест \\' 123 \\' тест--'") | |
973 | res = get_videos(f) | |
974 | self.assertEqual(res, ['1']) | |
975 | ||
976 | f = match_filter_func(r"creator = 'тест \' 123 \' тест--' & duration > 30") | |
977 | res = get_videos(f) | |
978 | self.assertEqual(res, []) | |
979 | ||
e9eaf3fb JMF |
980 | def test_playlist_items_selection(self): |
981 | entries = [{ | |
982 | 'id': compat_str(i), | |
983 | 'title': compat_str(i), | |
984 | 'url': TEST_URL, | |
985 | } for i in range(1, 5)] | |
986 | playlist = { | |
987 | '_type': 'playlist', | |
988 | 'id': 'test', | |
989 | 'entries': entries, | |
990 | 'extractor': 'test:playlist', | |
991 | 'extractor_key': 'test:playlist', | |
992 | 'webpage_url': 'http://example.com', | |
993 | } | |
994 | ||
4e9e1e24 | 995 | def get_downloaded_info_dicts(params): |
e9eaf3fb | 996 | ydl = YDL(params) |
e0abaab2 S |
997 | # make a deep copy because the dictionary and nested entries |
998 | # can be modified | |
999 | ydl.process_ie_result(copy.deepcopy(playlist)) | |
4e9e1e24 S |
1000 | return ydl.downloaded_info_dicts |
1001 | ||
9e598870 | 1002 | def test_selection(params, expected_ids): |
1003 | results = [ | |
1004 | (v['playlist_autonumber'] - 1, (int(v['id']), v['playlist_index'])) | |
1005 | for v in get_downloaded_info_dicts(params)] | |
1006 | self.assertEqual(results, list(enumerate(zip(expected_ids, expected_ids)))) | |
1007 | ||
1008 | test_selection({}, [1, 2, 3, 4]) | |
1009 | test_selection({'playlistend': 10}, [1, 2, 3, 4]) | |
1010 | test_selection({'playlistend': 2}, [1, 2]) | |
1011 | test_selection({'playliststart': 10}, []) | |
1012 | test_selection({'playliststart': 2}, [2, 3, 4]) | |
1013 | test_selection({'playlist_items': '2-4'}, [2, 3, 4]) | |
1014 | test_selection({'playlist_items': '2,4'}, [2, 4]) | |
1015 | test_selection({'playlist_items': '10'}, []) | |
ff1c7fc9 | 1016 | test_selection({'playlist_items': '0'}, []) |
cd6fc19e | 1017 | |
4e9e1e24 | 1018 | # Tests for https://github.com/ytdl-org/youtube-dl/issues/10591 |
9e598870 | 1019 | test_selection({'playlist_items': '2-4,3-4,3'}, [2, 3, 4]) |
1020 | test_selection({'playlist_items': '4,2'}, [4, 2]) | |
1021 | ||
1022 | # Tests for https://github.com/yt-dlp/yt-dlp/issues/720 | |
1023 | # https://github.com/yt-dlp/yt-dlp/issues/302 | |
1024 | test_selection({'playlistreverse': True}, [4, 3, 2, 1]) | |
1025 | test_selection({'playliststart': 2, 'playlistreverse': True}, [4, 3, 2]) | |
1026 | test_selection({'playlist_items': '2,4', 'playlistreverse': True}, [4, 2]) | |
1027 | test_selection({'playlist_items': '4,2'}, [4, 2]) | |
4e9e1e24 | 1028 | |
e37afbe0 | 1029 | def test_urlopen_no_file_protocol(self): |
067aa17e | 1030 | # see https://github.com/ytdl-org/youtube-dl/issues/8227 |
e37afbe0 JMF |
1031 | ydl = YDL() |
1032 | self.assertRaises(compat_urllib_error.URLError, ydl.urlopen, 'file:///etc/passwd') | |
1033 | ||
b286f201 YCH |
1034 | def test_do_not_override_ie_key_in_url_transparent(self): |
1035 | ydl = YDL() | |
1036 | ||
1037 | class Foo1IE(InfoExtractor): | |
1038 | _VALID_URL = r'foo1:' | |
1039 | ||
1040 | def _real_extract(self, url): | |
1041 | return { | |
1042 | '_type': 'url_transparent', | |
1043 | 'url': 'foo2:', | |
1044 | 'ie_key': 'Foo2', | |
0396806f S |
1045 | 'title': 'foo1 title', |
1046 | 'id': 'foo1_id', | |
b286f201 YCH |
1047 | } |
1048 | ||
1049 | class Foo2IE(InfoExtractor): | |
1050 | _VALID_URL = r'foo2:' | |
1051 | ||
1052 | def _real_extract(self, url): | |
1053 | return { | |
1054 | '_type': 'url', | |
1055 | 'url': 'foo3:', | |
1056 | 'ie_key': 'Foo3', | |
1057 | } | |
1058 | ||
1059 | class Foo3IE(InfoExtractor): | |
1060 | _VALID_URL = r'foo3:' | |
1061 | ||
1062 | def _real_extract(self, url): | |
51350db5 | 1063 | return _make_result([{'url': TEST_URL}], title='foo3 title') |
b286f201 YCH |
1064 | |
1065 | ydl.add_info_extractor(Foo1IE(ydl)) | |
1066 | ydl.add_info_extractor(Foo2IE(ydl)) | |
1067 | ydl.add_info_extractor(Foo3IE(ydl)) | |
1068 | ydl.extract_info('foo1:') | |
1069 | downloaded = ydl.downloaded_info_dicts[0] | |
1070 | self.assertEqual(downloaded['url'], TEST_URL) | |
51350db5 | 1071 | self.assertEqual(downloaded['title'], 'foo1 title') |
0396806f S |
1072 | self.assertEqual(downloaded['id'], 'testid') |
1073 | self.assertEqual(downloaded['extractor'], 'testex') | |
1074 | self.assertEqual(downloaded['extractor_key'], 'TestEx') | |
b286f201 | 1075 | |
a0566bbf | 1076 | # Test case for https://github.com/ytdl-org/youtube-dl/issues/27064 |
1077 | def test_ignoreerrors_for_playlist_with_url_transparent_iterable_entries(self): | |
1078 | ||
1079 | class _YDL(YDL): | |
1080 | def __init__(self, *args, **kwargs): | |
86e5f3ed | 1081 | super().__init__(*args, **kwargs) |
a0566bbf | 1082 | |
1083 | def trouble(self, s, tb=None): | |
1084 | pass | |
1085 | ||
1086 | ydl = _YDL({ | |
1087 | 'format': 'extra', | |
1088 | 'ignoreerrors': True, | |
1089 | }) | |
1090 | ||
1091 | class VideoIE(InfoExtractor): | |
1092 | _VALID_URL = r'video:(?P<id>\d+)' | |
1093 | ||
1094 | def _real_extract(self, url): | |
1095 | video_id = self._match_id(url) | |
1096 | formats = [{ | |
1097 | 'format_id': 'default', | |
1098 | 'url': 'url:', | |
1099 | }] | |
1100 | if video_id == '0': | |
1101 | raise ExtractorError('foo') | |
1102 | if video_id == '2': | |
1103 | formats.append({ | |
1104 | 'format_id': 'extra', | |
1105 | 'url': TEST_URL, | |
1106 | }) | |
1107 | return { | |
1108 | 'id': video_id, | |
1109 | 'title': 'Video %s' % video_id, | |
1110 | 'formats': formats, | |
1111 | } | |
1112 | ||
1113 | class PlaylistIE(InfoExtractor): | |
1114 | _VALID_URL = r'playlist:' | |
1115 | ||
1116 | def _entries(self): | |
1117 | for n in range(3): | |
1118 | video_id = compat_str(n) | |
1119 | yield { | |
1120 | '_type': 'url_transparent', | |
1121 | 'ie_key': VideoIE.ie_key(), | |
1122 | 'id': video_id, | |
1123 | 'url': 'video:%s' % video_id, | |
1124 | 'title': 'Video Transparent %s' % video_id, | |
1125 | } | |
1126 | ||
1127 | def _real_extract(self, url): | |
1128 | return self.playlist_result(self._entries()) | |
1129 | ||
1130 | ydl.add_info_extractor(VideoIE(ydl)) | |
1131 | ydl.add_info_extractor(PlaylistIE(ydl)) | |
1132 | info = ydl.extract_info('playlist:') | |
1133 | entries = info['entries'] | |
1134 | self.assertEqual(len(entries), 3) | |
1135 | self.assertTrue(entries[0] is None) | |
1136 | self.assertTrue(entries[1] is None) | |
1137 | self.assertEqual(len(ydl.downloaded_info_dicts), 1) | |
1138 | downloaded = ydl.downloaded_info_dicts[0] | |
9e907ebd | 1139 | entries[2].pop('requested_downloads', None) |
a0566bbf | 1140 | self.assertEqual(entries[2], downloaded) |
1141 | self.assertEqual(downloaded['url'], TEST_URL) | |
1142 | self.assertEqual(downloaded['title'], 'Video Transparent 2') | |
1143 | self.assertEqual(downloaded['id'], '2') | |
1144 | self.assertEqual(downloaded['extractor'], 'Video') | |
1145 | self.assertEqual(downloaded['extractor_key'], 'Video') | |
1146 | ||
2b4ecde2 | 1147 | |
e028d0d1 JMF |
1148 | if __name__ == '__main__': |
1149 | unittest.main() |