+ self.assertEqual(parse_duration('3h11m53s'), 11513)
+ self.assertEqual(parse_duration('3h 11m 53s'), 11513)
+ self.assertEqual(parse_duration('3 hours 11 minutes 53 seconds'), 11513)
+ self.assertEqual(parse_duration('3 hours 11 mins 53 secs'), 11513)
+ self.assertEqual(parse_duration('62m45s'), 3765)
+ self.assertEqual(parse_duration('6m59s'), 419)
+ self.assertEqual(parse_duration('49s'), 49)
+ self.assertEqual(parse_duration('0h0m0s'), 0)
+ self.assertEqual(parse_duration('0m0s'), 0)
+ self.assertEqual(parse_duration('0s'), 0)
+ self.assertEqual(parse_duration('01:02:03.05'), 3723.05)
+ self.assertEqual(parse_duration('T30M38S'), 1838)
+ self.assertEqual(parse_duration('5 s'), 5)
+ self.assertEqual(parse_duration('3 min'), 180)
+ self.assertEqual(parse_duration('2.5 hours'), 9000)
+ self.assertEqual(parse_duration('02:03:04'), 7384)
+ self.assertEqual(parse_duration('01:02:03:04'), 93784)
+ self.assertEqual(parse_duration('1 hour 3 minutes'), 3780)
+ 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(
+ fix_xml_ampersands('"&x=y&z=a'), '"&x=y&z=a')
+ self.assertEqual(
+ fix_xml_ampersands('"&x=y&wrong;&z=a'),
+ '"&x=y&wrong;&z=a')
+ self.assertEqual(
+ fix_xml_ampersands('&'><"'),
+ '&'><"')
+ self.assertEqual(
+ fix_xml_ampersands('Ӓ᪼'), 'Ӓ᪼')
+ self.assertEqual(fix_xml_ampersands('&#&#'), '&#&#')
+
+ def test_paged_list(self):
+ def testPL(size, pagesize, sliceargs, expected):
+ def get_page(pagenum):
+ firstid = pagenum * pagesize
+ upto = min(size, pagenum * pagesize + pagesize)
+ for i in range(firstid, upto):
+ yield i
+
+ pl = OnDemandPagedList(get_page, pagesize)
+ got = pl.getslice(*sliceargs)
+ self.assertEqual(got, expected)
+
+ iapl = InAdvancePagedList(get_page, size // pagesize + 1, pagesize)
+ got = iapl.getslice(*sliceargs)
+ self.assertEqual(got, expected)
+
+ testPL(5, 2, (), [0, 1, 2, 3, 4])
+ testPL(5, 2, (1,), [1, 2, 3, 4])
+ testPL(5, 2, (2,), [2, 3, 4])
+ testPL(5, 2, (4,), [4])
+ testPL(5, 2, (0, 3), [0, 1, 2])
+ testPL(5, 2, (1, 4), [1, 2, 3])
+ testPL(5, 2, (2, 99), [2, 3, 4])
+ testPL(5, 2, (20, 99), [])
+
+ def test_read_batch_urls(self):
+ f = io.StringIO('''\xef\xbb\xbf foo
+ bar\r
+ baz
+ # More after this line\r
+ ; or after this
+ bam''')
+ self.assertEqual(read_batch_urls(f), ['foo', 'bar', 'baz', 'bam'])
+
+ def test_urlencode_postdata(self):
+ data = urlencode_postdata({'username': 'foo@bar.com', 'password': '1234'})
+ self.assertTrue(isinstance(data, bytes))
+
+ def test_update_url_query(self):
+ def query_dict(url):
+ return compat_parse_qs(compat_urlparse.urlparse(url).query)
+ self.assertEqual(query_dict(update_url_query(
+ 'http://example.com/path', {'quality': ['HD'], 'format': ['mp4']})),
+ query_dict('http://example.com/path?quality=HD&format=mp4'))
+ self.assertEqual(query_dict(update_url_query(
+ 'http://example.com/path', {'system': ['LINUX', 'WINDOWS']})),
+ query_dict('http://example.com/path?system=LINUX&system=WINDOWS'))
+ self.assertEqual(query_dict(update_url_query(
+ 'http://example.com/path', {'fields': 'id,formats,subtitles'})),
+ query_dict('http://example.com/path?fields=id,formats,subtitles'))
+ self.assertEqual(query_dict(update_url_query(
+ 'http://example.com/path', {'fields': ('id,formats,subtitles', 'thumbnails')})),
+ query_dict('http://example.com/path?fields=id,formats,subtitles&fields=thumbnails'))
+ self.assertEqual(query_dict(update_url_query(
+ 'http://example.com/path?manifest=f4m', {'manifest': []})),
+ query_dict('http://example.com/path'))
+ self.assertEqual(query_dict(update_url_query(
+ 'http://example.com/path?system=LINUX&system=WINDOWS', {'system': 'LINUX'})),
+ query_dict('http://example.com/path?system=LINUX'))
+ self.assertEqual(query_dict(update_url_query(
+ 'http://example.com/path', {'fields': b'id,formats,subtitles'})),
+ query_dict('http://example.com/path?fields=id,formats,subtitles'))
+ self.assertEqual(query_dict(update_url_query(
+ 'http://example.com/path', {'width': 1080, 'height': 720})),
+ query_dict('http://example.com/path?width=1080&height=720'))
+ self.assertEqual(query_dict(update_url_query(
+ 'http://example.com/path', {'bitrate': 5020.43})),
+ query_dict('http://example.com/path?bitrate=5020.43'))
+ self.assertEqual(query_dict(update_url_query(
+ 'http://example.com/path', {'test': '第二行тест'})),
+ query_dict('http://example.com/path?test=%E7%AC%AC%E4%BA%8C%E8%A1%8C%D1%82%D0%B5%D1%81%D1%82'))
+
+ def test_multipart_encode(self):
+ self.assertEqual(
+ multipart_encode({b'field': b'value'}, boundary='AAAAAA')[0],
+ b'--AAAAAA\r\nContent-Disposition: form-data; name="field"\r\n\r\nvalue\r\n--AAAAAA--\r\n')
+ self.assertEqual(
+ multipart_encode({'欄位'.encode('utf-8'): '值'.encode('utf-8')}, boundary='AAAAAA')[0],
+ b'--AAAAAA\r\nContent-Disposition: form-data; name="\xe6\xac\x84\xe4\xbd\x8d"\r\n\r\n\xe5\x80\xbc\r\n--AAAAAA--\r\n')
+ self.assertRaises(
+ ValueError, multipart_encode, {b'field': b'value'}, boundary='value')
+
+ def test_dict_get(self):
+ FALSE_VALUES = {
+ 'none': None,
+ 'false': False,
+ 'zero': 0,
+ 'empty_string': '',
+ 'empty_list': [],
+ }
+ d = FALSE_VALUES.copy()
+ d['a'] = 42
+ self.assertEqual(dict_get(d, 'a'), 42)
+ self.assertEqual(dict_get(d, 'b'), None)
+ self.assertEqual(dict_get(d, 'b', 42), 42)
+ self.assertEqual(dict_get(d, ('a', )), 42)
+ self.assertEqual(dict_get(d, ('b', 'a', )), 42)
+ self.assertEqual(dict_get(d, ('b', 'c', 'a', 'd', )), 42)
+ self.assertEqual(dict_get(d, ('b', 'c', )), None)
+ self.assertEqual(dict_get(d, ('b', 'c', ), 42), 42)
+ for key, false_value in FALSE_VALUES.items():
+ 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')
+
+ def test_parse_iso8601(self):
+ self.assertEqual(parse_iso8601('2014-03-23T23:04:26+0100'), 1395612266)
+ self.assertEqual(parse_iso8601('2014-03-23T22:04:26+0000'), 1395612266)
+ self.assertEqual(parse_iso8601('2014-03-23T22:04:26Z'), 1395612266)
+ self.assertEqual(parse_iso8601('2014-03-23T22:04:26.1234Z'), 1395612266)
+ self.assertEqual(parse_iso8601('2015-09-29T08:27:31.727'), 1443515251)
+ self.assertEqual(parse_iso8601('2015-09-29T08-27-31.727'), None)
+
+ def test_strip_jsonp(self):
+ stripped = strip_jsonp('cb ([ {"id":"532cb",\n\n\n"x":\n3}\n]\n);')
+ d = json.loads(stripped)
+ self.assertEqual(d, [{"id": "532cb", "x": 3}])
+
+ stripped = strip_jsonp('parseMetadata({"STATUS":"OK"})\n\n\n//epc')
+ d = json.loads(stripped)
+ self.assertEqual(d, {'STATUS': 'OK'})
+
+ stripped = strip_jsonp('ps.embedHandler({"status": "success"});')
+ 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_uppercase_escape(self):
+ self.assertEqual(uppercase_escape('aä'), 'aä')
+ self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐')
+
+ def test_lowercase_escape(self):
+ self.assertEqual(lowercase_escape('aä'), 'aä')
+ self.assertEqual(lowercase_escape('\\u0026'), '&')
+
+ def test_limit_length(self):
+ self.assertEqual(limit_length(None, 12), None)
+ self.assertEqual(limit_length('foo', 12), 'foo')
+ self.assertTrue(
+ limit_length('foo bar baz asd', 12).startswith('foo bar'))
+ self.assertTrue('...' in limit_length('foo bar baz asd', 12))
+
+ def test_mimetype2ext(self):
+ self.assertEqual(mimetype2ext(None), None)
+ self.assertEqual(mimetype2ext('video/x-flv'), 'flv')
+ self.assertEqual(mimetype2ext('application/x-mpegURL'), 'm3u8')
+ self.assertEqual(mimetype2ext('text/vtt'), 'vtt')
+ self.assertEqual(mimetype2ext('text/vtt;charset=utf-8'), 'vtt')
+ self.assertEqual(mimetype2ext('text/html; charset=utf-8'), 'html')
+
+ def test_month_by_name(self):
+ self.assertEqual(month_by_name(None), None)
+ self.assertEqual(month_by_name('December', 'en'), 12)
+ self.assertEqual(month_by_name('décembre', 'fr'), 12)
+ self.assertEqual(month_by_name('December'), 12)
+ self.assertEqual(month_by_name('décembre'), None)
+ self.assertEqual(month_by_name('Unknown', 'unknown'), None)
+
+ def test_parse_codecs(self):
+ self.assertEqual(parse_codecs(''), {})
+ self.assertEqual(parse_codecs('avc1.77.30, mp4a.40.2'), {
+ 'vcodec': 'avc1.77.30',
+ 'acodec': 'mp4a.40.2',
+ })
+ self.assertEqual(parse_codecs('mp4a.40.2'), {
+ 'vcodec': 'none',
+ 'acodec': 'mp4a.40.2',
+ })
+ self.assertEqual(parse_codecs('mp4a.40.5,avc1.42001e'), {
+ 'vcodec': 'avc1.42001e',
+ 'acodec': 'mp4a.40.5',
+ })
+ self.assertEqual(parse_codecs('avc3.640028'), {
+ 'vcodec': 'avc3.640028',
+ 'acodec': 'none',
+ })
+ self.assertEqual(parse_codecs(', h264,,newcodec,aac'), {
+ 'vcodec': 'h264',
+ 'acodec': 'aac',
+ })
+ self.assertEqual(parse_codecs('av01.0.05M.08'), {
+ 'vcodec': 'av01.0.05M.08',
+ 'acodec': 'none',
+ })
+
+ def test_escape_rfc3986(self):
+ reserved = "!*'();:@&=+$,/?#[]"
+ unreserved = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_.~'
+ self.assertEqual(escape_rfc3986(reserved), reserved)
+ self.assertEqual(escape_rfc3986(unreserved), unreserved)
+ self.assertEqual(escape_rfc3986('тест'), '%D1%82%D0%B5%D1%81%D1%82')
+ self.assertEqual(escape_rfc3986('%D1%82%D0%B5%D1%81%D1%82'), '%D1%82%D0%B5%D1%81%D1%82')
+ self.assertEqual(escape_rfc3986('foo bar'), 'foo%20bar')
+ self.assertEqual(escape_rfc3986('foo%20bar'), 'foo%20bar')
+
+ def test_escape_url(self):
+ self.assertEqual(
+ escape_url('http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavré_FD.mp4'),
+ 'http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavre%CC%81_FD.mp4'
+ )
+ self.assertEqual(
+ escape_url('http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erklärt/Das-Erste/Video?documentId=22673108&bcastId=5290'),
+ 'http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erkl%C3%A4rt/Das-Erste/Video?documentId=22673108&bcastId=5290'
+ )
+ self.assertEqual(
+ escape_url('http://тест.рф/фрагмент'),
+ 'http://xn--e1aybc.xn--p1ai/%D1%84%D1%80%D0%B0%D0%B3%D0%BC%D0%B5%D0%BD%D1%82'
+ )
+ self.assertEqual(
+ escape_url('http://тест.рф/абв?абв=абв#абв'),
+ 'http://xn--e1aybc.xn--p1ai/%D0%B0%D0%B1%D0%B2?%D0%B0%D0%B1%D0%B2=%D0%B0%D0%B1%D0%B2#%D0%B0%D0%B1%D0%B2'
+ )
+ self.assertEqual(escape_url('http://vimeo.com/56015672#at=0'), 'http://vimeo.com/56015672#at=0')
+
+ def test_js_to_json_realworld(self):
+ inp = '''{
+ 'clip':{'provider':'pseudo'}
+ }'''
+ self.assertEqual(js_to_json(inp), '''{
+ "clip":{"provider":"pseudo"}
+ }''')
+ json.loads(js_to_json(inp))
+
+ inp = '''{
+ 'playlist':[{'controls':{'all':null}}]
+ }'''
+ self.assertEqual(js_to_json(inp), '''{
+ "playlist":[{"controls":{"all":null}}]
+ }''')
+
+ inp = '''"The CW\\'s \\'Crazy Ex-Girlfriend\\'"'''
+ self.assertEqual(js_to_json(inp), '''"The CW's 'Crazy Ex-Girlfriend'"''')
+
+ inp = '"SAND Number: SAND 2013-7800P\\nPresenter: Tom Russo\\nHabanero Software Training - Xyce Software\\nXyce, Sandia\\u0027s"'
+ json_code = js_to_json(inp)
+ self.assertEqual(json.loads(json_code), json.loads(inp))
+
+ inp = '''{
+ 0:{src:'skipped', type: 'application/dash+xml'},
+ 1:{src:'skipped', type: 'application/vnd.apple.mpegURL'},
+ }'''
+ self.assertEqual(js_to_json(inp), '''{
+ "0":{"src":"skipped", "type": "application/dash+xml"},
+ "1":{"src":"skipped", "type": "application/vnd.apple.mpegURL"}
+ }''')
+
+ inp = '''{"foo":101}'''
+ self.assertEqual(js_to_json(inp), '''{"foo":101}''')
+
+ 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"})
+
+ on = js_to_json('{"abc": true}')
+ self.assertEqual(json.loads(on), {'abc': True})
+
+ # Ignore JavaScript code as well
+ on = js_to_json('''{
+ "x": 1,
+ y: "a",
+ z: some.code
+ }''')
+ d = json.loads(on)
+ self.assertEqual(d['x'], 1)
+ self.assertEqual(d['y'], 'a')
+
+ on = js_to_json('["abc", "def",]')
+ self.assertEqual(json.loads(on), ['abc', 'def'])
+
+ on = js_to_json('[/*comment\n*/"abc"/*comment\n*/,/*comment\n*/"def",/*comment\n*/]')
+ self.assertEqual(json.loads(on), ['abc', 'def'])
+
+ on = js_to_json('[//comment\n"abc" //comment\n,//comment\n"def",//comment\n]')
+ self.assertEqual(json.loads(on), ['abc', 'def'])
+
+ on = js_to_json('{"abc": "def",}')
+ self.assertEqual(json.loads(on), {'abc': 'def'})
+
+ on = js_to_json('{/*comment\n*/"abc"/*comment\n*/:/*comment\n*/"def"/*comment\n*/,/*comment\n*/}')
+ self.assertEqual(json.loads(on), {'abc': 'def'})
+
+ on = js_to_json('{ 0: /* " \n */ ",]" , }')
+ self.assertEqual(json.loads(on), {'0': ',]'})
+
+ on = js_to_json('{ /*comment\n*/0/*comment\n*/: /* " \n */ ",]" , }')
+ self.assertEqual(json.loads(on), {'0': ',]'})
+
+ on = js_to_json('{ 0: // comment\n1 }')
+ self.assertEqual(json.loads(on), {'0': 1})
+
+ on = js_to_json(r'["<p>x<\/p>"]')
+ self.assertEqual(json.loads(on), ['<p>x</p>'])
+
+ on = js_to_json(r'["\xaa"]')
+ self.assertEqual(json.loads(on), ['\u00aa'])
+
+ on = js_to_json("['a\\\nb']")
+ self.assertEqual(json.loads(on), ['ab'])
+
+ on = js_to_json("/*comment\n*/[/*comment\n*/'a\\\nb'/*comment\n*/]/*comment\n*/")
+ self.assertEqual(json.loads(on), ['ab'])
+
+ on = js_to_json('{0xff:0xff}')
+ self.assertEqual(json.loads(on), {'255': 255})
+
+ on = js_to_json('{/*comment\n*/0xff/*comment\n*/:/*comment\n*/0xff/*comment\n*/}')
+ self.assertEqual(json.loads(on), {'255': 255})
+
+ on = js_to_json('{077:077}')
+ self.assertEqual(json.loads(on), {'63': 63})
+
+ on = js_to_json('{/*comment\n*/077/*comment\n*/:/*comment\n*/077/*comment\n*/}')
+ self.assertEqual(json.loads(on), {'63': 63})
+
+ on = js_to_json('{42:42}')
+ self.assertEqual(json.loads(on), {'42': 42})
+
+ 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('<e x="y">'), {'x': 'y'})
+ self.assertEqual(extract_attributes("<e x='y'>"), {'x': 'y'})
+ self.assertEqual(extract_attributes('<e x=y>'), {'x': 'y'})
+ self.assertEqual(extract_attributes('<e x="a \'b\' c">'), {'x': "a 'b' c"})
+ self.assertEqual(extract_attributes('<e x=\'a "b" c\'>'), {'x': 'a "b" c'})
+ self.assertEqual(extract_attributes('<e x="y">'), {'x': 'y'})
+ self.assertEqual(extract_attributes('<e x="y">'), {'x': 'y'})
+ self.assertEqual(extract_attributes('<e x="&">'), {'x': '&'}) # XML
+ self.assertEqual(extract_attributes('<e x=""">'), {'x': '"'})
+ self.assertEqual(extract_attributes('<e x="£">'), {'x': '£'}) # HTML 3.2
+ self.assertEqual(extract_attributes('<e x="λ">'), {'x': 'λ'}) # HTML 4.0
+ self.assertEqual(extract_attributes('<e x="&foo">'), {'x': '&foo'})
+ self.assertEqual(extract_attributes('<e x="\'">'), {'x': "'"})
+ self.assertEqual(extract_attributes('<e x=\'"\'>'), {'x': '"'})
+ self.assertEqual(extract_attributes('<e x >'), {'x': None})
+ self.assertEqual(extract_attributes('<e x=y a>'), {'x': 'y', 'a': None})
+ self.assertEqual(extract_attributes('<e x= y>'), {'x': 'y'})
+ self.assertEqual(extract_attributes('<e x=1 y=2 x=3>'), {'y': '2', 'x': '3'})
+ self.assertEqual(extract_attributes('<e \nx=\ny\n>'), {'x': 'y'})
+ self.assertEqual(extract_attributes('<e \nx=\n"y"\n>'), {'x': 'y'})
+ self.assertEqual(extract_attributes("<e \nx=\n'y'\n>"), {'x': 'y'})
+ self.assertEqual(extract_attributes('<e \nx="\ny\n">'), {'x': '\ny\n'})
+ self.assertEqual(extract_attributes('<e CAPS=x>'), {'caps': 'x'}) # Names lowercased
+ self.assertEqual(extract_attributes('<e x=1 X=2>'), {'x': '2'})
+ self.assertEqual(extract_attributes('<e X=1 x=2>'), {'x': '2'})
+ self.assertEqual(extract_attributes('<e _:funny-name1=1>'), {'_:funny-name1': '1'})
+ self.assertEqual(extract_attributes('<e x="Fáilte 世界 \U0001f600">'), {'x': 'Fáilte 世界 \U0001f600'})
+ self.assertEqual(extract_attributes('<e x="décomposé">'), {'x': 'décompose\u0301'})
+ # "Narrow" Python builds don't support unicode code points outside BMP.
+ try:
+ compat_chr(0x10000)
+ supports_outside_bmp = True
+ except ValueError:
+ supports_outside_bmp = False
+ if supports_outside_bmp:
+ self.assertEqual(extract_attributes('<e x="Smile 😀!">'), {'x': 'Smile \U0001f600!'})
+ # Malformed HTML should not break attributes extraction on older Python
+ self.assertEqual(extract_attributes('<mal"formed/>'), {})
+
+ def test_clean_html(self):
+ self.assertEqual(clean_html('a:\nb'), 'a: b')
+ self.assertEqual(clean_html('a:\n "b"'), 'a: "b"')
+ self.assertEqual(clean_html('a<br>\xa0b'), 'a\nb')
+
+ def test_intlist_to_bytes(self):
+ self.assertEqual(
+ intlist_to_bytes([0, 1, 127, 128, 255]),
+ b'\x00\x01\x7f\x80\xff')
+
+ def test_args_to_str(self):
+ self.assertEqual(
+ args_to_str(['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):
+ self.assertEqual(parse_filesize(None), None)
+ self.assertEqual(parse_filesize(''), None)
+ self.assertEqual(parse_filesize('91 B'), 91)
+ self.assertEqual(parse_filesize('foobar'), None)
+ self.assertEqual(parse_filesize('2 MiB'), 2097152)
+ self.assertEqual(parse_filesize('5 GB'), 5000000000)
+ self.assertEqual(parse_filesize('1.2Tb'), 1200000000000)
+ self.assertEqual(parse_filesize('1.2tb'), 1200000000000)
+ self.assertEqual(parse_filesize('1,24 KB'), 1240)
+ self.assertEqual(parse_filesize('1,24 kb'), 1240)
+ self.assertEqual(parse_filesize('8.5 megabytes'), 8500000)
+
+ def test_parse_count(self):
+ self.assertEqual(parse_count(None), None)
+ self.assertEqual(parse_count(''), None)
+ self.assertEqual(parse_count('0'), 0)
+ self.assertEqual(parse_count('1000'), 1000)
+ self.assertEqual(parse_count('1.000'), 1000)
+ self.assertEqual(parse_count('1.1k'), 1100)
+ self.assertEqual(parse_count('1.1kk'), 1100000)
+ 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_version_tuple(self):
+ self.assertEqual(version_tuple('1'), (1,))
+ self.assertEqual(version_tuple('10.23.344'), (10, 23, 344))
+ self.assertEqual(version_tuple('10.1-6'), (10, 1, 6)) # avconv style
+
+ def test_detect_exe_version(self):
+ self.assertEqual(detect_exe_version('''ffmpeg version 1.2.1
+built on May 27 2013 08:37:26 with gcc 4.7 (Debian 4.7.3-4)
+configuration: --prefix=/usr --extra-'''), '1.2.1')
+ self.assertEqual(detect_exe_version('''ffmpeg version N-63176-g1fb4685
+built on May 15 2014 22:09:06 with gcc 4.8.2 (GCC)'''), 'N-63176-g1fb4685')
+ self.assertEqual(detect_exe_version('''X server found. dri2 connection failed!
+Trying to open render node...
+Success at /dev/dri/renderD128.
+ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')
+
+ def test_age_restricted(self):
+ self.assertFalse(age_restricted(None, 10)) # unrestricted content
+ self.assertFalse(age_restricted(1, None)) # unrestricted policy
+ self.assertFalse(age_restricted(8, 10))
+ self.assertTrue(age_restricted(18, 14))
+ self.assertFalse(age_restricted(18, 18))
+
+ def test_is_html(self):
+ self.assertFalse(is_html(b'\x49\x44\x43<html'))
+ self.assertTrue(is_html(b'<!DOCTYPE foo>\xaaa'))
+ self.assertTrue(is_html( # UTF-8 with BOM
+ b'\xef\xbb\xbf<!DOCTYPE foo>\xaaa'))
+ self.assertTrue(is_html( # UTF-16-LE
+ b'\xff\xfe<\x00h\x00t\x00m\x00l\x00>\x00\xe4\x00'
+ ))
+ self.assertTrue(is_html( # UTF-16-BE
+ b'\xfe\xff\x00<\x00h\x00t\x00m\x00l\x00>\x00\xe4'
+ ))
+ self.assertTrue(is_html( # UTF-32-BE
+ b'\x00\x00\xFE\xFF\x00\x00\x00<\x00\x00\x00h\x00\x00\x00t\x00\x00\x00m\x00\x00\x00l\x00\x00\x00>\x00\x00\x00\xe4'))
+ self.assertTrue(is_html( # UTF-32-LE
+ b'\xFF\xFE\x00\x00<\x00\x00\x00h\x00\x00\x00t\x00\x00\x00m\x00\x00\x00l\x00\x00\x00>\x00\x00\x00\xe4\x00\x00\x00'))
+
+ def test_render_table(self):
+ self.assertEqual(
+ render_table(
+ ['a', 'bcd'],
+ [[123, 4], [9999, 51]]),
+ 'a bcd\n'
+ '123 4\n'
+ '9999 51')
+
+ def test_match_str(self):
+ self.assertRaises(ValueError, match_str, 'xy>foobar', {})
+ self.assertFalse(match_str('xy', {'x': 1200}))
+ self.assertTrue(match_str('!xy', {'x': 1200}))
+ self.assertTrue(match_str('x', {'x': 1200}))
+ self.assertFalse(match_str('!x', {'x': 1200}))
+ self.assertTrue(match_str('x', {'x': 0}))
+ self.assertFalse(match_str('x>0', {'x': 0}))
+ self.assertFalse(match_str('x>0', {}))
+ self.assertTrue(match_str('x>?0', {}))
+ self.assertTrue(match_str('x>1K', {'x': 1200}))
+ self.assertFalse(match_str('x>2K', {'x': 1200}))
+ self.assertTrue(match_str('x>=1200 & x < 1300', {'x': 1200}))
+ self.assertFalse(match_str('x>=1100 & x < 1200', {'x': 1200}))
+ self.assertFalse(match_str('y=a212', {'y': 'foobar42'}))
+ self.assertTrue(match_str('y=foobar42', {'y': 'foobar42'}))
+ self.assertFalse(match_str('y!=foobar42', {'y': 'foobar42'}))
+ self.assertTrue(match_str('y!=foobar2', {'y': 'foobar42'}))
+ self.assertFalse(match_str(
+ 'like_count > 100 & dislike_count <? 50 & description',
+ {'like_count': 90, 'description': 'foo'}))
+ self.assertTrue(match_str(
+ 'like_count > 100 & dislike_count <? 50 & description',
+ {'like_count': 190, 'description': 'foo'}))
+ self.assertFalse(match_str(
+ 'like_count > 100 & dislike_count <? 50 & description',
+ {'like_count': 190, 'dislike_count': 60, 'description': 'foo'}))
+ self.assertFalse(match_str(
+ 'like_count > 100 & dislike_count <? 50 & description',
+ {'like_count': 190, 'dislike_count': 10}))
+ self.assertTrue(match_str('is_live', {'is_live': True}))
+ self.assertFalse(match_str('is_live', {'is_live': False}))
+ self.assertFalse(match_str('is_live', {'is_live': None}))
+ self.assertFalse(match_str('is_live', {}))
+ self.assertFalse(match_str('!is_live', {'is_live': True}))
+ self.assertTrue(match_str('!is_live', {'is_live': False}))
+ self.assertTrue(match_str('!is_live', {'is_live': None}))
+ self.assertTrue(match_str('!is_live', {}))
+ self.assertTrue(match_str('title', {'title': 'abc'}))
+ self.assertTrue(match_str('title', {'title': ''}))
+ self.assertFalse(match_str('!title', {'title': 'abc'}))
+ self.assertFalse(match_str('!title', {'title': ''}))
+
+ def test_parse_dfxp_time_expr(self):
+ self.assertEqual(parse_dfxp_time_expr(None), None)
+ self.assertEqual(parse_dfxp_time_expr(''), None)
+ self.assertEqual(parse_dfxp_time_expr('0.1'), 0.1)
+ self.assertEqual(parse_dfxp_time_expr('0.1s'), 0.1)
+ self.assertEqual(parse_dfxp_time_expr('00:00:01'), 1.0)
+ self.assertEqual(parse_dfxp_time_expr('00:00:01.100'), 1.1)
+ self.assertEqual(parse_dfxp_time_expr('00:00:01:100'), 1.1)
+
+ def test_dfxp2srt(self):
+ dfxp_data = '''<?xml version="1.0" encoding="UTF-8"?>
+ <tt xmlns="http://www.w3.org/ns/ttml" xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter">
+ <body>
+ <div xml:lang="en">
+ <p begin="0" end="1">The following line contains Chinese characters and special symbols</p>
+ <p begin="1" end="2">第二行<br/>♪♪</p>
+ <p begin="2" dur="1"><span>Third<br/>Line</span></p>
+ <p begin="3" end="-1">Lines with invalid timestamps are ignored</p>
+ <p begin="-1" end="-1">Ignore, two</p>
+ <p begin="3" dur="-1">Ignored, three</p>
+ </div>
+ </body>
+ </tt>'''.encode('utf-8')
+ srt_data = '''1
+00:00:00,000 --> 00:00:01,000
+The following line contains Chinese characters and special symbols
+
+2
+00:00:01,000 --> 00:00:02,000
+第二行
+♪♪
+
+3
+00:00:02,000 --> 00:00:03,000
+Third
+Line
+
+'''
+ self.assertEqual(dfxp2srt(dfxp_data), srt_data)
+
+ dfxp_data_no_default_namespace = '''<?xml version="1.0" encoding="UTF-8"?>
+ <tt xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter">
+ <body>
+ <div xml:lang="en">
+ <p begin="0" end="1">The first line</p>
+ </div>
+ </body>
+ </tt>'''.encode('utf-8')
+ srt_data = '''1
+00:00:00,000 --> 00:00:01,000
+The first line
+
+'''
+ self.assertEqual(dfxp2srt(dfxp_data_no_default_namespace), srt_data)
+
+ dfxp_data_with_style = '''<?xml version="1.0" encoding="utf-8"?>
+<tt xmlns="http://www.w3.org/2006/10/ttaf1" xmlns:ttp="http://www.w3.org/2006/10/ttaf1#parameter" ttp:timeBase="media" xmlns:tts="http://www.w3.org/2006/10/ttaf1#style" xml:lang="en" xmlns:ttm="http://www.w3.org/2006/10/ttaf1#metadata">
+ <head>
+ <styling>
+ <style id="s2" style="s0" tts:color="cyan" tts:fontWeight="bold" />
+ <style id="s1" style="s0" tts:color="yellow" tts:fontStyle="italic" />
+ <style id="s3" style="s0" tts:color="lime" tts:textDecoration="underline" />
+ <style id="s0" tts:backgroundColor="black" tts:fontStyle="normal" tts:fontSize="16" tts:fontFamily="sansSerif" tts:color="white" />
+ </styling>
+ </head>
+ <body tts:textAlign="center" style="s0">
+ <div>
+ <p begin="00:00:02.08" id="p0" end="00:00:05.84">default style<span tts:color="red">custom style</span></p>
+ <p style="s2" begin="00:00:02.08" id="p0" end="00:00:05.84"><span tts:color="lime">part 1<br /></span><span tts:color="cyan">part 2</span></p>
+ <p style="s3" begin="00:00:05.84" id="p1" end="00:00:09.56">line 3<br />part 3</p>
+ <p style="s1" tts:textDecoration="underline" begin="00:00:09.56" id="p2" end="00:00:12.36"><span style="s2" tts:color="lime">inner<br /> </span>style</p>
+ </div>
+ </body>
+</tt>'''.encode('utf-8')
+ srt_data = '''1
+00:00:02,080 --> 00:00:05,839
+<font color="white" face="sansSerif" size="16">default style<font color="red">custom style</font></font>
+
+2
+00:00:02,080 --> 00:00:05,839
+<b><font color="cyan" face="sansSerif" size="16"><font color="lime">part 1
+</font>part 2</font></b>
+
+3
+00:00:05,839 --> 00:00:09,560
+<u><font color="lime">line 3
+part 3</font></u>
+
+4
+00:00:09,560 --> 00:00:12,359
+<i><u><font color="yellow"><font color="lime">inner
+ </font>style</font></u></i>
+
+'''
+ self.assertEqual(dfxp2srt(dfxp_data_with_style), srt_data)
+
+ dfxp_data_non_utf8 = '''<?xml version="1.0" encoding="UTF-16"?>
+ <tt xmlns="http://www.w3.org/ns/ttml" xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter">
+ <body>
+ <div xml:lang="en">
+ <p begin="0" end="1">Line 1</p>
+ <p begin="1" end="2">第二行</p>
+ </div>
+ </body>
+ </tt>'''.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'), [])
+ self.assertEqual(cli_option({}, '--proxy', 'proxy'), [])
+ self.assertEqual(cli_option({'retries': 10}, '--retries', 'retries'), ['--retries', '10'])
+
+ def test_cli_valueless_option(self):
+ self.assertEqual(cli_valueless_option(
+ {'downloader': 'external'}, '--external-downloader', 'downloader', 'external'), ['--external-downloader'])
+ self.assertEqual(cli_valueless_option(
+ {'downloader': 'internal'}, '--external-downloader', 'downloader', 'external'), [])
+ self.assertEqual(cli_valueless_option(
+ {'nocheckcertificate': True}, '--no-check-certificate', 'nocheckcertificate'), ['--no-check-certificate'])
+ self.assertEqual(cli_valueless_option(
+ {'nocheckcertificate': False}, '--no-check-certificate', 'nocheckcertificate'), [])
+ self.assertEqual(cli_valueless_option(
+ {'checkcertificate': True}, '--no-check-certificate', 'checkcertificate', False), [])
+ self.assertEqual(cli_valueless_option(
+ {'checkcertificate': False}, '--no-check-certificate', 'checkcertificate', False), ['--no-check-certificate'])
+
+ def test_cli_bool_option(self):
+ self.assertEqual(
+ cli_bool_option(
+ {'nocheckcertificate': True}, '--no-check-certificate', 'nocheckcertificate'),
+ ['--no-check-certificate', 'true'])
+ self.assertEqual(
+ cli_bool_option(
+ {'nocheckcertificate': True}, '--no-check-certificate', 'nocheckcertificate', separator='='),
+ ['--no-check-certificate=true'])
+ self.assertEqual(
+ cli_bool_option(
+ {'nocheckcertificate': True}, '--check-certificate', 'nocheckcertificate', 'false', 'true'),
+ ['--check-certificate', 'false'])
+ self.assertEqual(
+ cli_bool_option(
+ {'nocheckcertificate': True}, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='),
+ ['--check-certificate=false'])
+ self.assertEqual(
+ cli_bool_option(
+ {'nocheckcertificate': False}, '--check-certificate', 'nocheckcertificate', 'false', 'true'),
+ ['--check-certificate', 'true'])
+ self.assertEqual(
+ 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
+ e = 65537
+
+ self.assertEqual(
+ ohdave_rsa_encrypt(b'aa111222', e, N),
+ '726664bd9a23fd0c70f9f1b84aab5e3905ce1e45a584e9cbcf9bcc7510338fc1986d6c599ff990d923aa43c51c0d9013cd572e13bc58f4ae48f2ed8c0b0ba881')
+
+ def test_pkcs1pad(self):
+ data = [1, 2, 3]
+ padded_data = pkcs1pad(data, 32)
+ self.assertEqual(padded_data[:2], [0, 2])
+ self.assertEqual(padded_data[28:], [0, 1, 2, 3])
+
+ self.assertRaises(ValueError, pkcs1pad, data, 8)
+
+ def test_encode_base_n(self):
+ self.assertEqual(encode_base_n(0, 30), '0')
+ self.assertEqual(encode_base_n(80, 30), '2k')
+
+ custom_table = '9876543210ZYXWVUTSRQPONMLKJIHGFEDCBA'
+ self.assertEqual(encode_base_n(0, 30, custom_table), '9')
+ self.assertEqual(encode_base_n(80, 30, custom_table), '7P')
+
+ self.assertRaises(ValueError, encode_base_n, 0, 70)
+ self.assertRaises(ValueError, encode_base_n, 0, 60, custom_table)
+
+ def test_urshift(self):
+ self.assertEqual(urshift(3, 1), 1)
+ self.assertEqual(urshift(-3, 1), 2147483646)
+
+ def test_get_element_by_class(self):
+ html = '''
+ <span class="foo bar">nice</span>
+ '''
+
+ self.assertEqual(get_element_by_class('foo', html), 'nice')
+ self.assertEqual(get_element_by_class('no-such-class', html), None)
+
+ def test_get_element_by_attribute(self):
+ html = '''
+ <span class="foo bar">nice</span>
+ '''
+
+ self.assertEqual(get_element_by_attribute('class', 'foo bar', html), 'nice')
+ self.assertEqual(get_element_by_attribute('class', 'foo', html), None)
+ self.assertEqual(get_element_by_attribute('class', 'no-such-foo', html), None)
+
+ html = '''
+ <div itemprop="author" itemscope>foo</div>
+ '''
+
+ self.assertEqual(get_element_by_attribute('itemprop', 'author', html), 'foo')
+
+ def test_get_elements_by_class(self):
+ html = '''
+ <span class="foo bar">nice</span><span class="foo bar">also nice</span>
+ '''
+
+ self.assertEqual(get_elements_by_class('foo', html), ['nice', 'also nice'])
+ self.assertEqual(get_elements_by_class('no-such-class', html), [])
+
+ def test_get_elements_by_attribute(self):
+ html = '''
+ <span class="foo bar">nice</span><span class="foo bar">also nice</span>
+ '''
+
+ self.assertEqual(get_elements_by_attribute('class', 'foo bar', html), ['nice', 'also nice'])
+ self.assertEqual(get_elements_by_attribute('class', 'foo', html), [])
+ self.assertEqual(get_elements_by_attribute('class', 'no-such-foo', html), [])
+
Rapsys Git / youtubedl / blobdiff