encodeFilename,
escape_rfc3986,
escape_url,
+ ExtractorError,
find_xpath_attr,
fix_xml_ampersands,
InAdvancePagedList,
parse_iso8601,
read_batch_urls,
sanitize_filename,
+ sanitize_path,
+ sanitize_url_path_consecutive_slashes,
shell_quote,
smuggle_url,
str_to_int,
urlencode_postdata,
version_tuple,
xpath_with_ns,
+ xpath_text,
+ render_table,
+ match_str,
)
sanitize_filename('New World record at 0:12:34'),
'New World record at 0_12_34')
+ self.assertEqual(sanitize_filename('--gasdgf'), '_-gasdgf')
+ self.assertEqual(sanitize_filename('--gasdgf', is_id=True), '--gasdgf')
+ self.assertEqual(sanitize_filename('.gasdgf'), 'gasdgf')
+ self.assertEqual(sanitize_filename('.gasdgf', is_id=True), '.gasdgf')
+
forbidden = '"\0\\/'
for fc in forbidden:
for fbc in forbidden:
self.assertEqual(sanitize_filename('_BD_eEpuzXw', is_id=True), '_BD_eEpuzXw')
self.assertEqual(sanitize_filename('N0Y__7-UOdI', is_id=True), 'N0Y__7-UOdI')
+ def test_sanitize_path(self):
+ if sys.platform != 'win32':
+ return
+
+ self.assertEqual(sanitize_path('abc'), 'abc')
+ self.assertEqual(sanitize_path('abc/def'), 'abc\\def')
+ self.assertEqual(sanitize_path('abc\\def'), 'abc\\def')
+ self.assertEqual(sanitize_path('abc|def'), 'abc#def')
+ self.assertEqual(sanitize_path('<>:"|?*'), '#######')
+ self.assertEqual(sanitize_path('C:/abc/def'), 'C:\\abc\\def')
+ self.assertEqual(sanitize_path('C?:/abc/def'), 'C##\\abc\\def')
+
+ self.assertEqual(sanitize_path('\\\\?\\UNC\\ComputerName\\abc'), '\\\\?\\UNC\\ComputerName\\abc')
+ self.assertEqual(sanitize_path('\\\\?\\UNC/ComputerName/abc'), '\\\\?\\UNC\\ComputerName\\abc')
+
+ self.assertEqual(sanitize_path('\\\\?\\C:\\abc'), '\\\\?\\C:\\abc')
+ self.assertEqual(sanitize_path('\\\\?\\C:/abc'), '\\\\?\\C:\\abc')
+ self.assertEqual(sanitize_path('\\\\?\\C:\\ab?c\\de:f'), '\\\\?\\C:\\ab#c\\de#f')
+ self.assertEqual(sanitize_path('\\\\?\\C:\\abc'), '\\\\?\\C:\\abc')
+
+ self.assertEqual(
+ sanitize_path('youtube/%(uploader)s/%(autonumber)s-%(title)s-%(upload_date)s.%(ext)s'),
+ 'youtube\\%(uploader)s\\%(autonumber)s-%(title)s-%(upload_date)s.%(ext)s')
+
+ self.assertEqual(
+ sanitize_path('youtube/TheWreckingYard ./00001-Not bad, Especially for Free! (1987 Yamaha 700)-20141116.mp4.part'),
+ 'youtube\\TheWreckingYard #\\00001-Not bad, Especially for Free! (1987 Yamaha 700)-20141116.mp4.part')
+ self.assertEqual(sanitize_path('abc/def...'), 'abc\\def..#')
+ self.assertEqual(sanitize_path('abc.../def'), 'abc..#\\def')
+ self.assertEqual(sanitize_path('abc.../def...'), 'abc..#\\def..#')
+
+ self.assertEqual(sanitize_path('../abc'), '..\\abc')
+ self.assertEqual(sanitize_path('../../abc'), '..\\..\\abc')
+ self.assertEqual(sanitize_path('./abc'), 'abc')
+ self.assertEqual(sanitize_path('./../abc'), '..\\abc')
+
+ def test_sanitize_url_path_consecutive_slashes(self):
+ self.assertEqual(
+ sanitize_url_path_consecutive_slashes('http://hostname/foo//bar/filename.html'),
+ 'http://hostname/foo/bar/filename.html')
+ self.assertEqual(
+ sanitize_url_path_consecutive_slashes('http://hostname//foo/bar/filename.html'),
+ 'http://hostname/foo/bar/filename.html')
+ self.assertEqual(
+ sanitize_url_path_consecutive_slashes('http://hostname//'),
+ 'http://hostname/')
+ self.assertEqual(
+ sanitize_url_path_consecutive_slashes('http://hostname/foo/bar/filename.html'),
+ 'http://hostname/foo/bar/filename.html')
+ self.assertEqual(
+ sanitize_url_path_consecutive_slashes('http://hostname/'),
+ 'http://hostname/')
+ self.assertEqual(
+ sanitize_url_path_consecutive_slashes('http://hostname/abc//'),
+ 'http://hostname/abc/')
+
def test_ordered_set(self):
self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7])
self.assertEqual(orderedSet([]), [])
self.assertEqual(
unified_strdate('11/26/2014 11:30:00 AM PST', day_first=False),
'20141126')
+ self.assertEqual(
+ unified_strdate('2/2/2015 6:47:40 PM', day_first=False),
+ '20150202')
def test_find_xpath_attr(self):
testxml = '''<root>
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_text(self):
+ testxml = '''<root>
+ <div>
+ <p>Foo</p>
+ </div>
+ </root>'''
+ doc = xml.etree.ElementTree.fromstring(testxml)
+ self.assertEqual(xpath_text(doc, 'div/p'), 'Foo')
+ self.assertTrue(xpath_text(doc, 'div/bar') is None)
+ self.assertRaises(ExtractorError, xpath_text, doc, 'div/bar', fatal=True)
+
def test_smuggle_url(self):
data = {"ö": "ö", "abc": [3]}
url = 'https://foo.bar/baz?x=y#a'
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)
def test_fix_xml_ampersands(self):
self.assertEqual(
"playlist":[{"controls":{"all":null}}]
}''')
+ 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))
+
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')
+
def test_clean_html(self):
self.assertEqual(clean_html('a:\nb'), 'a: b')
self.assertEqual(clean_html('a:\n "b"'), 'a: "b"')
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}))
+
+
if __name__ == '__main__':
unittest.main()