import json
import xml.etree.ElementTree
-from youtube_dl.utils import (
+from yt_dlp.utils import (
age_restricted,
args_to_str,
encode_base_n,
+ caesar,
clean_html,
+ clean_podcast_url,
date_from_str,
DateRange,
detect_exe_version,
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,
parse_count,
parse_iso8601,
parse_resolution,
+ parse_bitrate,
pkcs1pad,
read_batch_urls,
sanitize_filename,
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,
uppercase_escape,
lowercase_escape,
url_basename,
+ url_or_none,
base_url,
urljoin,
urlencode_postdata,
cli_valueless_option,
cli_bool_option,
parse_codecs,
+ iri_to_uri,
)
-from youtube_dl.compat import (
+from yt_dlp.compat import (
compat_chr,
compat_etree_fromstring,
compat_getenv,
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')
def env(var):
return '%{0}%'.format(var) if sys.platform == 'win32' else '${0}'.format(var)
- compat_setenv('YOUTUBE_DL_EXPATH_PATH', 'expanded')
- self.assertEqual(expand_path(env('YOUTUBE_DL_EXPATH_PATH')), 'expanded')
+ compat_setenv('yt_dlp_EXPATH_PATH', 'expanded')
+ self.assertEqual(expand_path(env('yt_dlp_EXPATH_PATH')), 'expanded')
self.assertEqual(expand_path(env('HOME')), compat_getenv('HOME'))
self.assertEqual(expand_path('~'), compat_getenv('HOME'))
self.assertEqual(
- expand_path('~/%s' % env('YOUTUBE_DL_EXPATH_PATH')),
+ expand_path('~/%s' % env('yt_dlp_EXPATH_PATH')),
'%s/expanded' % compat_getenv('HOME'))
def test_prepend_extension(self):
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')
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)
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/'), '')
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')
+ self.assertEqual(url_or_none('s3://foo.de'), None)
+ self.assertEqual(url_or_none('rtmpte://foo.de'), 'rtmpte://foo.de')
+ self.assertEqual(url_or_none('mms://foo.de'), 'mms://foo.de')
+ self.assertEqual(url_or_none('rtspu://foo.de'), 'rtspu://foo.de')
+ self.assertEqual(url_or_none('ftps://foo.de'), 'ftps://foo.de')
def test_parse_age_limit(self):
self.assertEqual(parse_age_limit(None), None)
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')
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)
'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 = "!*'();:@&=+$,/?#[]"
self.assertEqual(d['x'], 1)
self.assertEqual(d['y'], 'a')
+ # Just drop ! prefix for now though this results in a wrong value
+ on = js_to_json('''{
+ a: !0,
+ b: !1,
+ c: !!0,
+ d: !!42.42,
+ e: !!![],
+ f: !"abc",
+ g: !"",
+ !42: 42
+ }''')
+ self.assertEqual(json.loads(on), {
+ 'a': 0,
+ 'b': 1,
+ 'c': 0,
+ 'd': 42.42,
+ 'e': [],
+ 'f': "abc",
+ 'g': "",
+ '42': 42
+ })
+
on = js_to_json('["abc", "def",]')
self.assertEqual(json.loads(on), ['abc', 'def'])
on = js_to_json('{42:4.2e1}')
self.assertEqual(json.loads(on), {'42': 42.0})
+ on = js_to_json('{ "0x40": "0x40" }')
+ self.assertEqual(json.loads(on), {'0x40': '0x40'})
+
+ on = js_to_json('{ "040": "040" }')
+ self.assertEqual(json.loads(on), {'040': '040'})
+
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')
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))
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('yt-dlp'), r'JE\5=A')
+ self.assertEqual(rot47('YT-DLP'), r'*%\s{!')
+
def test_urshift(self):
self.assertEqual(urshift(3, 1), 1)
self.assertEqual(urshift(-3, 1), 2147483646)
self.assertEqual(get_elements_by_attribute('class', 'foo', html), [])
self.assertEqual(get_elements_by_attribute('class', 'no-such-foo', html), [])
+ def test_iri_to_uri(self):
+ self.assertEqual(
+ iri_to_uri('https://www.google.com/search?q=foo&ie=utf-8&oe=utf-8&client=firefox-b'),
+ 'https://www.google.com/search?q=foo&ie=utf-8&oe=utf-8&client=firefox-b') # Same
+ self.assertEqual(
+ iri_to_uri('https://www.google.com/search?q=Käsesoßenrührlöffel'), # German for cheese sauce stirring spoon
+ 'https://www.google.com/search?q=K%C3%A4seso%C3%9Fenr%C3%BChrl%C3%B6ffel')
+ self.assertEqual(
+ iri_to_uri('https://www.google.com/search?q=lt<+gt>+eq%3D+amp%26+percent%25+hash%23+colon%3A+tilde~#trash=?&garbage=#'),
+ 'https://www.google.com/search?q=lt%3C+gt%3E+eq%3D+amp%26+percent%25+hash%23+colon%3A+tilde~#trash=?&garbage=#')
+ self.assertEqual(
+ iri_to_uri('http://правозащита38.рф/category/news/'),
+ 'http://xn--38-6kcaak9aj5chl4a3g.xn--p1ai/category/news/')
+ self.assertEqual(
+ iri_to_uri('http://www.правозащита38.рф/category/news/'),
+ 'http://www.xn--38-6kcaak9aj5chl4a3g.xn--p1ai/category/news/')
+ self.assertEqual(
+ iri_to_uri('https://i❤.ws/emojidomain/👍👏🤝💪'),
+ 'https://xn--i-7iq.ws/emojidomain/%F0%9F%91%8D%F0%9F%91%8F%F0%9F%A4%9D%F0%9F%92%AA')
+ self.assertEqual(
+ iri_to_uri('http://日本語.jp/'),
+ 'http://xn--wgv71a119e.jp/')
+ self.assertEqual(
+ iri_to_uri('http://导航.中国/'),
+ 'http://xn--fet810g.xn--fiqs8s/')
+
+ def test_clean_podcast_url(self):
+ self.assertEqual(clean_podcast_url('https://www.podtrac.com/pts/redirect.mp3/chtbl.com/track/5899E/traffic.megaphone.fm/HSW7835899191.mp3'), 'https://traffic.megaphone.fm/HSW7835899191.mp3')
+ self.assertEqual(clean_podcast_url('https://play.podtrac.com/npr-344098539/edge1.pod.npr.org/anon.npr-podcasts/podcast/npr/waitwait/2020/10/20201003_waitwait_wwdtmpodcast201003-015621a5-f035-4eca-a9a1-7c118d90bc3c.mp3'), 'https://edge1.pod.npr.org/anon.npr-podcasts/podcast/npr/waitwait/2020/10/20201003_waitwait_wwdtmpodcast201003-015621a5-f035-4eca-a9a1-7c118d90bc3c.mp3')
+
if __name__ == '__main__':
unittest.main()
projects / yt-dlp.git / blobdiff