X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/d9d7cd0e85dc712461d9185db9df9d6c900a573b..09e2f88f88353cd91b2157a8dfb28df7799cd25b:/test/test_utils.py diff --git a/test/test_utils.py b/test/test_utils.py index f31559e..962fd8d 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -19,6 +19,7 @@ from youtube_dl.utils import ( age_restricted, args_to_str, encode_base_n, + caesar, clean_html, date_from_str, DateRange, @@ -33,15 +34,18 @@ from youtube_dl.utils import ( ExtractorError, find_xpath_attr, fix_xml_ampersands, + float_or_none, get_element_by_class, get_element_by_attribute, get_elements_by_class, get_elements_by_attribute, InAdvancePagedList, + int_or_none, intlist_to_bytes, is_html, js_to_json, limit_length, + merge_dicts, mimetype2ext, month_by_name, multipart_encode, @@ -53,20 +57,26 @@ from youtube_dl.utils import ( parse_filesize, parse_count, parse_iso8601, + parse_resolution, + parse_bitrate, pkcs1pad, read_batch_urls, sanitize_filename, sanitize_path, + sanitize_url, expand_path, prepend_extension, replace_extension, remove_start, remove_end, remove_quotes, + rot47, shell_quote, smuggle_url, str_to_int, strip_jsonp, + strip_or_none, + subtitles_filename, timeconvert, unescapeHTML, unified_strdate, @@ -75,6 +85,7 @@ from youtube_dl.utils import ( uppercase_escape, lowercase_escape, url_basename, + url_or_none, base_url, urljoin, urlencode_postdata, @@ -98,6 +109,7 @@ from youtube_dl.compat import ( compat_chr, compat_etree_fromstring, compat_getenv, + compat_os_name, compat_setenv, compat_urlparse, compat_parse_qs, @@ -175,7 +187,7 @@ class TestUtil(unittest.TestCase): self.assertEqual(sanitize_filename( 'ÂÃÄÀÁÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖŐØŒÙÚÛÜŰÝÞßàáâãäåæçèéêëìíîïðñòóôõöőøœùúûüűýþÿ', restricted=True), - 'AAAAAAAECEEEEIIIIDNOOOOOOOOEUUUUUYPssaaaaaaaeceeeeiiiionooooooooeuuuuuypy') + 'AAAAAAAECEEEEIIIIDNOOOOOOOOEUUUUUYTHssaaaaaaaeceeeeiiiionooooooooeuuuuuythy') def test_sanitize_ids(self): self.assertEqual(sanitize_filename('_n_cd26wFpw', is_id=True), '_n_cd26wFpw') @@ -218,6 +230,12 @@ class TestUtil(unittest.TestCase): self.assertEqual(sanitize_path('./abc'), 'abc') self.assertEqual(sanitize_path('./../abc'), '..\\abc') + def test_sanitize_url(self): + self.assertEqual(sanitize_url('//foo.bar'), 'http://foo.bar') + self.assertEqual(sanitize_url('httpss://foo.bar'), 'https://foo.bar') + self.assertEqual(sanitize_url('rmtps://foo.bar'), 'rtmps://foo.bar') + self.assertEqual(sanitize_url('https://foo.bar'), 'https://foo.bar') + def test_expand_path(self): def env(var): return '%{0}%'.format(var) if sys.platform == 'win32' else '${0}'.format(var) @@ -246,6 +264,11 @@ class TestUtil(unittest.TestCase): self.assertEqual(replace_extension('.abc', 'temp'), '.abc.temp') self.assertEqual(replace_extension('.abc.ext', 'temp'), '.abc.temp') + def test_subtitles_filename(self): + self.assertEqual(subtitles_filename('abc.ext', 'en', 'vtt'), 'abc.en.vtt') + self.assertEqual(subtitles_filename('abc.ext', 'en', 'vtt', 'ext'), 'abc.en.vtt') + self.assertEqual(subtitles_filename('abc.unexpected_ext', 'en', 'vtt', 'ext'), 'abc.unexpected_ext.en.vtt') + def test_remove_start(self): self.assertEqual(remove_start(None, 'A - '), None) self.assertEqual(remove_start('A - B', 'A - '), 'B') @@ -278,6 +301,7 @@ class TestUtil(unittest.TestCase): self.assertEqual(unescapeHTML('/'), '/') self.assertEqual(unescapeHTML('é'), 'é') self.assertEqual(unescapeHTML('�'), '�') + self.assertEqual(unescapeHTML('&a"'), '&a"') # HTML5 entities self.assertEqual(unescapeHTML('.''), '.\'') @@ -318,6 +342,8 @@ class TestUtil(unittest.TestCase): self.assertEqual(unified_strdate('July 15th, 2013'), '20130715') self.assertEqual(unified_strdate('September 1st, 2013'), '20130901') self.assertEqual(unified_strdate('Sep 2nd, 2013'), '20130902') + self.assertEqual(unified_strdate('November 3rd, 2019'), '20191103') + self.assertEqual(unified_strdate('October 23rd, 2005'), '20051023') def test_unified_timestamps(self): self.assertEqual(unified_timestamp('December 21, 2010'), 1292889600) @@ -340,6 +366,9 @@ class TestUtil(unittest.TestCase): self.assertEqual(unified_timestamp('May 16, 2016 11:15 PM'), 1463440500) self.assertEqual(unified_timestamp('Feb 7, 2016 at 6:35 pm'), 1454870100) self.assertEqual(unified_timestamp('2017-03-30T17:52:41Q'), 1490896361) + self.assertEqual(unified_timestamp('Sep 11, 2013 | 5:49 AM'), 1378878540) + self.assertEqual(unified_timestamp('December 15, 2017 at 7:49 am'), 1513324140) + self.assertEqual(unified_timestamp('2018-03-14T08:32:43.1493874+00:00'), 1521016363) def test_determine_ext(self): self.assertEqual(determine_ext('http://example.com/foo/bar.mp4/?download'), 'mp4') @@ -347,6 +376,7 @@ class TestUtil(unittest.TestCase): self.assertEqual(determine_ext('http://example.com/foo/bar.nonext/?download', None), None) self.assertEqual(determine_ext('http://example.com/foo/bar/mp4?download', None), None) self.assertEqual(determine_ext('http://example.com/foo/bar.m3u8//?download'), 'm3u8') + self.assertEqual(determine_ext('foobar', None), None) def test_find_xpath_attr(self): testxml = ''' @@ -447,11 +477,34 @@ class TestUtil(unittest.TestCase): def test_shell_quote(self): args = ['ffmpeg', '-i', encodeFilename('ñ€ß\'.mp4')] - self.assertEqual(shell_quote(args), """ffmpeg -i 'ñ€ß'"'"'.mp4'""") + self.assertEqual( + shell_quote(args), + """ffmpeg -i 'ñ€ß'"'"'.mp4'""" if compat_os_name != 'nt' else '''ffmpeg -i "ñ€ß'.mp4"''') + + def test_float_or_none(self): + self.assertEqual(float_or_none('42.42'), 42.42) + self.assertEqual(float_or_none('42'), 42.0) + self.assertEqual(float_or_none(''), None) + self.assertEqual(float_or_none(None), None) + self.assertEqual(float_or_none([]), None) + self.assertEqual(float_or_none(set()), None) + + def test_int_or_none(self): + self.assertEqual(int_or_none('42'), 42) + self.assertEqual(int_or_none(''), None) + self.assertEqual(int_or_none(None), None) + self.assertEqual(int_or_none([]), None) + self.assertEqual(int_or_none(set()), None) def test_str_to_int(self): self.assertEqual(str_to_int('123,456'), 123456) self.assertEqual(str_to_int('123.456'), 123456) + self.assertEqual(str_to_int(523), 523) + # Python 3 has no long + if sys.version_info < (3, 0): + eval('self.assertEqual(str_to_int(123456L), 123456)') + self.assertEqual(str_to_int('noninteger'), None) + self.assertEqual(str_to_int([]), None) def test_url_basename(self): self.assertEqual(url_basename('http://foo.de/'), '') @@ -489,6 +542,18 @@ class TestUtil(unittest.TestCase): self.assertEqual(urljoin('http://foo.de/', ''), None) self.assertEqual(urljoin('http://foo.de/', ['foobar']), None) self.assertEqual(urljoin('http://foo.de/a/b/c.txt', '.././../d.txt'), 'http://foo.de/d.txt') + self.assertEqual(urljoin('http://foo.de/a/b/c.txt', 'rtmp://foo.de'), 'rtmp://foo.de') + self.assertEqual(urljoin(None, 'rtmp://foo.de'), 'rtmp://foo.de') + + def test_url_or_none(self): + self.assertEqual(url_or_none(None), None) + self.assertEqual(url_or_none(''), None) + self.assertEqual(url_or_none('foo'), None) + self.assertEqual(url_or_none('http://foo.de'), 'http://foo.de') + self.assertEqual(url_or_none('https://foo.de'), 'https://foo.de') + self.assertEqual(url_or_none('http$://foo.de'), None) + self.assertEqual(url_or_none('http://foo.de'), 'http://foo.de') + self.assertEqual(url_or_none('//foo.de'), '//foo.de') def test_parse_age_limit(self): self.assertEqual(parse_age_limit(None), None) @@ -503,6 +568,8 @@ class TestUtil(unittest.TestCase): self.assertEqual(parse_age_limit('PG-13'), 13) self.assertEqual(parse_age_limit('TV-14'), 14) self.assertEqual(parse_age_limit('TV-MA'), 17) + self.assertEqual(parse_age_limit('TV14'), 14) + self.assertEqual(parse_age_limit('TV_G'), 0) def test_parse_duration(self): self.assertEqual(parse_duration(None), None) @@ -535,6 +602,7 @@ class TestUtil(unittest.TestCase): self.assertEqual(parse_duration('87 Min.'), 5220) self.assertEqual(parse_duration('PT1H0.040S'), 3600.04) self.assertEqual(parse_duration('PT00H03M30SZ'), 210) + self.assertEqual(parse_duration('P0Y0M0DT0H4M20.880S'), 260.88) def test_fix_xml_ampersands(self): self.assertEqual( @@ -653,6 +721,17 @@ class TestUtil(unittest.TestCase): self.assertEqual(dict_get(d, ('b', 'c', key, )), None) self.assertEqual(dict_get(d, ('b', 'c', key, ), skip_false_values=False), false_value) + def test_merge_dicts(self): + self.assertEqual(merge_dicts({'a': 1}, {'b': 2}), {'a': 1, 'b': 2}) + self.assertEqual(merge_dicts({'a': 1}, {'a': 2}), {'a': 1}) + self.assertEqual(merge_dicts({'a': 1}, {'a': None}), {'a': 1}) + self.assertEqual(merge_dicts({'a': 1}, {'a': ''}), {'a': 1}) + self.assertEqual(merge_dicts({'a': 1}, {}), {'a': 1}) + self.assertEqual(merge_dicts({'a': None}, {'a': 1}), {'a': 1}) + self.assertEqual(merge_dicts({'a': ''}, {'a': 1}), {'a': ''}) + self.assertEqual(merge_dicts({'a': ''}, {'a': 'abc'}), {'a': 'abc'}) + self.assertEqual(merge_dicts({'a': None}, {'a': ''}, {'a': 'abc'}), {'a': 'abc'}) + def test_encode_compat_str(self): self.assertEqual(encode_compat_str(b'\xd1\x82\xd0\xb5\xd1\x81\xd1\x82', 'utf-8'), 'тест') self.assertEqual(encode_compat_str('тест', 'utf-8'), 'тест') @@ -678,6 +757,30 @@ class TestUtil(unittest.TestCase): d = json.loads(stripped) self.assertEqual(d, {'status': 'success'}) + stripped = strip_jsonp('window.cb && window.cb({"status": "success"});') + d = json.loads(stripped) + self.assertEqual(d, {'status': 'success'}) + + stripped = strip_jsonp('window.cb && cb({"status": "success"});') + d = json.loads(stripped) + self.assertEqual(d, {'status': 'success'}) + + stripped = strip_jsonp('({"status": "success"});') + d = json.loads(stripped) + self.assertEqual(d, {'status': 'success'}) + + def test_strip_or_none(self): + self.assertEqual(strip_or_none(' abc'), 'abc') + self.assertEqual(strip_or_none('abc '), 'abc') + self.assertEqual(strip_or_none(' abc '), 'abc') + self.assertEqual(strip_or_none('\tabc\t'), 'abc') + self.assertEqual(strip_or_none('\n\tabc\n\t'), 'abc') + self.assertEqual(strip_or_none('abc'), 'abc') + self.assertEqual(strip_or_none(''), '') + self.assertEqual(strip_or_none(None), None) + self.assertEqual(strip_or_none(42), None) + self.assertEqual(strip_or_none([]), None) + def test_uppercase_escape(self): self.assertEqual(uppercase_escape('aä'), 'aä') self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐') @@ -700,6 +803,8 @@ class TestUtil(unittest.TestCase): self.assertEqual(mimetype2ext('text/vtt'), 'vtt') self.assertEqual(mimetype2ext('text/vtt;charset=utf-8'), 'vtt') self.assertEqual(mimetype2ext('text/html; charset=utf-8'), 'html') + self.assertEqual(mimetype2ext('audio/x-wav'), 'wav') + self.assertEqual(mimetype2ext('audio/x-wav;codec=pcm'), 'wav') def test_month_by_name(self): self.assertEqual(month_by_name(None), None) @@ -731,6 +836,19 @@ class TestUtil(unittest.TestCase): 'vcodec': 'h264', 'acodec': 'aac', }) + self.assertEqual(parse_codecs('av01.0.05M.08'), { + 'vcodec': 'av01.0.05M.08', + 'acodec': 'none', + }) + self.assertEqual(parse_codecs('theora, vorbis'), { + 'vcodec': 'theora', + 'acodec': 'vorbis', + }) + self.assertEqual(parse_codecs('unknownvcodec, unknownacodec'), { + 'vcodec': 'unknownvcodec', + 'acodec': 'unknownacodec', + }) + self.assertEqual(parse_codecs('unknown'), {}) def test_escape_rfc3986(self): reserved = "!*'();:@&=+$,/?#[]" @@ -799,6 +917,9 @@ class TestUtil(unittest.TestCase): inp = '''{"duration": "00:01:07"}''' self.assertEqual(js_to_json(inp), '''{"duration": "00:01:07"}''') + inp = '''{segments: [{"offset":-3.885780586188048e-16,"duration":39.75000000000001}]}''' + self.assertEqual(js_to_json(inp), '''{"segments": [{"offset":-3.885780586188048e-16,"duration":39.75000000000001}]}''') + def test_js_to_json_edgecases(self): on = js_to_json("{abc_def:'1\\'\\\\2\\\\\\'3\"4'}") self.assertEqual(json.loads(on), {"abc_def": "1'\\2\\'3\"4"}) @@ -870,6 +991,13 @@ class TestUtil(unittest.TestCase): on = js_to_json('{/*comment\n*/42/*comment\n*/:/*comment\n*/42/*comment\n*/}') self.assertEqual(json.loads(on), {'42': 42}) + on = js_to_json('{42:4.2e1}') + self.assertEqual(json.loads(on), {'42': 42.0}) + + def test_js_to_json_malformed(self): + self.assertEqual(js_to_json('42a1'), '42"a1"') + self.assertEqual(js_to_json('42a-1'), '42"a"-1') + def test_extract_attributes(self): self.assertEqual(extract_attributes(''), {'x': 'y'}) self.assertEqual(extract_attributes(""), {'x': 'y'}) @@ -907,6 +1035,8 @@ class TestUtil(unittest.TestCase): supports_outside_bmp = False if supports_outside_bmp: self.assertEqual(extract_attributes(''), {'x': 'Smile \U0001f600!'}) + # Malformed HTML should not break attributes extraction on older Python + self.assertEqual(extract_attributes(''), {}) def test_clean_html(self): self.assertEqual(clean_html('a:\nb'), 'a: b') @@ -921,7 +1051,7 @@ class TestUtil(unittest.TestCase): def test_args_to_str(self): self.assertEqual( args_to_str(['foo', 'ba/r', '-baz', '2 be', '']), - 'foo ba/r -baz \'2 be\' \'\'' + 'foo ba/r -baz \'2 be\' \'\'' if compat_os_name != 'nt' else 'foo ba/r -baz "2 be" ""' ) def test_parse_filesize(self): @@ -948,6 +1078,23 @@ class TestUtil(unittest.TestCase): self.assertEqual(parse_count('1.1kk '), 1100000) self.assertEqual(parse_count('1.1kk views'), 1100000) + def test_parse_resolution(self): + self.assertEqual(parse_resolution(None), {}) + self.assertEqual(parse_resolution(''), {}) + self.assertEqual(parse_resolution('1920x1080'), {'width': 1920, 'height': 1080}) + self.assertEqual(parse_resolution('1920×1080'), {'width': 1920, 'height': 1080}) + self.assertEqual(parse_resolution('1920 x 1080'), {'width': 1920, 'height': 1080}) + self.assertEqual(parse_resolution('720p'), {'height': 720}) + self.assertEqual(parse_resolution('4k'), {'height': 2160}) + self.assertEqual(parse_resolution('8K'), {'height': 4320}) + + def test_parse_bitrate(self): + self.assertEqual(parse_bitrate(None), None) + self.assertEqual(parse_bitrate(''), None) + self.assertEqual(parse_bitrate('300kbps'), 300) + self.assertEqual(parse_bitrate('1500kbps'), 1500) + self.assertEqual(parse_bitrate('300 kbps'), 300) + def test_version_tuple(self): self.assertEqual(version_tuple('1'), (1,)) self.assertEqual(version_tuple('10.23.344'), (10, 23, 344)) @@ -1026,6 +1173,18 @@ ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4') self.assertFalse(match_str( 'like_count > 100 & dislike_count Ignored, three

- ''' + '''.encode('utf-8') srt_data = '''1 00:00:00,000 --> 00:00:01,000 The following line contains Chinese characters and special symbols @@ -1074,7 +1233,7 @@ Line

The first line

- ''' + '''.encode('utf-8') srt_data = '''1 00:00:00,000 --> 00:00:01,000 The first line @@ -1100,7 +1259,7 @@ The first line

inner
style

-''' +'''.encode('utf-8') srt_data = '''1 00:00:02,080 --> 00:00:05,839 default stylecustom style @@ -1123,6 +1282,26 @@ part 3 ''' self.assertEqual(dfxp2srt(dfxp_data_with_style), srt_data) + dfxp_data_non_utf8 = ''' + + +
+

Line 1

+

第二行

+
+ + '''.encode('utf-16') + srt_data = '''1 +00:00:00,000 --> 00:00:01,000 +Line 1 + +2 +00:00:01,000 --> 00:00:02,000 +第二行 + +''' + self.assertEqual(dfxp2srt(dfxp_data_non_utf8), srt_data) + def test_cli_option(self): self.assertEqual(cli_option({'proxy': '127.0.0.1:3128'}, '--proxy', 'proxy'), ['--proxy', '127.0.0.1:3128']) self.assertEqual(cli_option({'proxy': None}, '--proxy', 'proxy'), []) @@ -1168,6 +1347,10 @@ part 3 cli_bool_option( {'nocheckcertificate': False}, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='), ['--check-certificate=true']) + self.assertEqual( + cli_bool_option( + {}, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='), + []) def test_ohdave_rsa_encrypt(self): N = 0xab86b6371b5318aaa1d3c9e612a9f1264f372323c8c0f19875b5fc3b3fd3afcc1e5bec527aa94bfa85bffc157e4245aebda05389a5357b75115ac94f074aefcd @@ -1196,6 +1379,20 @@ part 3 self.assertRaises(ValueError, encode_base_n, 0, 70) self.assertRaises(ValueError, encode_base_n, 0, 60, custom_table) + def test_caesar(self): + self.assertEqual(caesar('ace', 'abcdef', 2), 'cea') + self.assertEqual(caesar('cea', 'abcdef', -2), 'ace') + self.assertEqual(caesar('ace', 'abcdef', -2), 'eac') + self.assertEqual(caesar('eac', 'abcdef', 2), 'ace') + self.assertEqual(caesar('ace', 'abcdef', 0), 'ace') + self.assertEqual(caesar('xyz', 'abcdef', 2), 'xyz') + self.assertEqual(caesar('abc', 'acegik', 2), 'ebg') + self.assertEqual(caesar('ebg', 'acegik', -2), 'abc') + + def test_rot47(self): + self.assertEqual(rot47('youtube-dl'), r'J@FEF36\5=') + self.assertEqual(rot47('YOUTUBE-DL'), r'*~&%&qt\s{') + def test_urshift(self): self.assertEqual(urshift(3, 1), 1) self.assertEqual(urshift(-3, 1), 2147483646) @@ -1217,6 +1414,12 @@ part 3 self.assertEqual(get_element_by_attribute('class', 'foo', html), None) self.assertEqual(get_element_by_attribute('class', 'no-such-foo', html), None) + html = ''' + + ''' + + self.assertEqual(get_element_by_attribute('itemprop', 'author', html), 'foo') + def test_get_elements_by_class(self): html = ''' nicealso nice