+ self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'd'), doc[3])
+ self.assertEqual(find_xpath_attr(doc, './/node', 'x', ''), doc[4])
+
+ def test_xpath_with_ns(self):
+ testxml = '''<root xmlns:media="http://example.com/">
+ <media:song>
+ <media:author>The Author</media:author>
+ <url>http://server.com/download.mp3</url>
+ </media:song>
+ </root>'''
+ doc = compat_etree_fromstring(testxml)
+ find = lambda p: doc.find(xpath_with_ns(p, {'media': 'http://example.com/'}))
+ self.assertTrue(find('media:song') is not None)
+ self.assertEqual(find('media:song/media:author').text, 'The Author')
+ self.assertEqual(find('media:song/url').text, 'http://server.com/download.mp3')
+
+ def test_xpath_element(self):
+ doc = xml.etree.ElementTree.Element('root')
+ div = xml.etree.ElementTree.SubElement(doc, 'div')
+ p = xml.etree.ElementTree.SubElement(div, 'p')
+ p.text = 'Foo'
+ self.assertEqual(xpath_element(doc, 'div/p'), p)
+ self.assertEqual(xpath_element(doc, ['div/p']), p)
+ self.assertEqual(xpath_element(doc, ['div/bar', 'div/p']), p)
+ self.assertEqual(xpath_element(doc, 'div/bar', default='default'), 'default')
+ self.assertEqual(xpath_element(doc, ['div/bar'], default='default'), 'default')
+ self.assertTrue(xpath_element(doc, 'div/bar') is None)
+ self.assertTrue(xpath_element(doc, ['div/bar']) is None)
+ self.assertTrue(xpath_element(doc, ['div/bar'], 'div/baz') is None)
+ self.assertRaises(ExtractorError, xpath_element, doc, 'div/bar', fatal=True)
+ self.assertRaises(ExtractorError, xpath_element, doc, ['div/bar'], fatal=True)
+ self.assertRaises(ExtractorError, xpath_element, doc, ['div/bar', 'div/baz'], fatal=True)
+
+ def test_xpath_text(self):
+ testxml = '''<root>
+ <div>
+ <p>Foo</p>
+ </div>
+ </root>'''
+ doc = compat_etree_fromstring(testxml)
+ self.assertEqual(xpath_text(doc, 'div/p'), 'Foo')
+ self.assertEqual(xpath_text(doc, 'div/bar', default='default'), 'default')
+ self.assertTrue(xpath_text(doc, 'div/bar') is None)
+ self.assertRaises(ExtractorError, xpath_text, doc, 'div/bar', fatal=True)
+
+ def test_xpath_attr(self):
+ testxml = '''<root>
+ <div>
+ <p x="a">Foo</p>
+ </div>
+ </root>'''
+ doc = compat_etree_fromstring(testxml)
+ self.assertEqual(xpath_attr(doc, 'div/p', 'x'), 'a')
+ self.assertEqual(xpath_attr(doc, 'div/bar', 'x'), None)
+ self.assertEqual(xpath_attr(doc, 'div/p', 'y'), None)
+ self.assertEqual(xpath_attr(doc, 'div/bar', 'x', default='default'), 'default')
+ self.assertEqual(xpath_attr(doc, 'div/p', 'y', default='default'), 'default')
+ self.assertRaises(ExtractorError, xpath_attr, doc, 'div/bar', 'x', fatal=True)
+ self.assertRaises(ExtractorError, xpath_attr, doc, 'div/p', 'y', fatal=True)
+
+ def test_smuggle_url(self):
+ data = {"ö": "ö", "abc": [3]}
+ url = 'https://foo.bar/baz?x=y#a'
+ smug_url = smuggle_url(url, data)
+ unsmug_url, unsmug_data = unsmuggle_url(smug_url)
+ self.assertEqual(url, unsmug_url)
+ self.assertEqual(data, unsmug_data)
+
+ res_url, res_data = unsmuggle_url(url)
+ self.assertEqual(res_url, url)
+ self.assertEqual(res_data, None)
+
+ smug_url = smuggle_url(url, {'a': 'b'})
+ smug_smug_url = smuggle_url(smug_url, {'c': 'd'})
+ res_url, res_data = unsmuggle_url(smug_smug_url)
+ self.assertEqual(res_url, url)
+ self.assertEqual(res_data, {'a': 'b', 'c': 'd'})
+
+ def test_shell_quote(self):
+ args = ['ffmpeg', '-i', encodeFilename('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_str_to_int(self):
+ self.assertEqual(str_to_int('123,456'), 123456)
+ self.assertEqual(str_to_int('123.456'), 123456)
+
+ def test_url_basename(self):
+ self.assertEqual(url_basename('http://foo.de/'), '')
+ self.assertEqual(url_basename('http://foo.de/bar/baz'), 'baz')
+ self.assertEqual(url_basename('http://foo.de/bar/baz?x=y'), 'baz')
+ self.assertEqual(url_basename('http://foo.de/bar/baz#x=y'), 'baz')
+ self.assertEqual(url_basename('http://foo.de/bar/baz/'), 'baz')
+ self.assertEqual(
+ url_basename('http://media.w3.org/2010/05/sintel/trailer.mp4'),
+ 'trailer.mp4')
+
+ def test_base_url(self):
+ self.assertEqual(base_url('http://foo.de/'), 'http://foo.de/')
+ self.assertEqual(base_url('http://foo.de/bar'), 'http://foo.de/')
+ self.assertEqual(base_url('http://foo.de/bar/'), 'http://foo.de/bar/')
+ self.assertEqual(base_url('http://foo.de/bar/baz'), 'http://foo.de/bar/')
+ self.assertEqual(base_url('http://foo.de/bar/baz?x=z/x/c'), 'http://foo.de/bar/')
+
+ def test_urljoin(self):
+ self.assertEqual(urljoin('http://foo.de/', '/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
+ self.assertEqual(urljoin(b'http://foo.de/', '/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
+ self.assertEqual(urljoin('http://foo.de/', b'/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
+ self.assertEqual(urljoin(b'http://foo.de/', b'/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
+ self.assertEqual(urljoin('//foo.de/', '/a/b/c.txt'), '//foo.de/a/b/c.txt')
+ self.assertEqual(urljoin('http://foo.de/', 'a/b/c.txt'), 'http://foo.de/a/b/c.txt')
+ self.assertEqual(urljoin('http://foo.de', '/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
+ self.assertEqual(urljoin('http://foo.de', 'a/b/c.txt'), 'http://foo.de/a/b/c.txt')
+ self.assertEqual(urljoin('http://foo.de/', 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
+ self.assertEqual(urljoin('http://foo.de/', '//foo.de/a/b/c.txt'), '//foo.de/a/b/c.txt')
+ self.assertEqual(urljoin(None, 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
+ self.assertEqual(urljoin(None, '//foo.de/a/b/c.txt'), '//foo.de/a/b/c.txt')
+ self.assertEqual(urljoin('', 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
+ self.assertEqual(urljoin(['foobar'], 'http://foo.de/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
+ self.assertEqual(urljoin('http://foo.de/', None), None)
+ 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')
+
+ def test_parse_age_limit(self):
+ self.assertEqual(parse_age_limit(None), None)
+ self.assertEqual(parse_age_limit(False), None)
+ self.assertEqual(parse_age_limit('invalid'), None)
+ self.assertEqual(parse_age_limit(0), 0)
+ self.assertEqual(parse_age_limit(18), 18)
+ self.assertEqual(parse_age_limit(21), 21)
+ self.assertEqual(parse_age_limit(22), None)
+ self.assertEqual(parse_age_limit('18'), 18)
+ self.assertEqual(parse_age_limit('18+'), 18)
+ self.assertEqual(parse_age_limit('PG-13'), 13)
+ self.assertEqual(parse_age_limit('TV-14'), 14)
+ self.assertEqual(parse_age_limit('TV-MA'), 17)
+
+ def test_parse_duration(self):
+ self.assertEqual(parse_duration(None), None)
+ self.assertEqual(parse_duration(False), None)
+ self.assertEqual(parse_duration('invalid'), None)
+ self.assertEqual(parse_duration('1'), 1)
+ self.assertEqual(parse_duration('1337:12'), 80232)
+ self.assertEqual(parse_duration('9:12:43'), 33163)
+ self.assertEqual(parse_duration('12:00'), 720)
+ self.assertEqual(parse_duration('00:01:01'), 61)
+ self.assertEqual(parse_duration('x:y'), None)
+ 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_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'})
+
+ 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',
+ })
+
+ 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))
Rapsys Git / youtubedl / blobdiff