release 2015.03.24

Urls can also contain contain a query (for example a timestamp '?t=foo')

AUTHORS

@@ -113,3 +113,7 @@ Robin de Rooij
 Ryan Schmidt
 Leslie P. Polzer
 Duncan Keall
+Alexander Mamay
+Devin J. Pohly
+Eduardo Ferro Aldama
+Jeff Buchbinder

README.md

@@ -228,6 +228,9 @@ which means you can modify it, redistribute it or use it however you like.
     --embed-subs                     embed subtitles in the video (only for mp4 videos)
     --embed-thumbnail                embed thumbnail in the audio as cover art
     --add-metadata                   write metadata to the video file
+    --metadata-from-title FORMAT     parse additional metadata like song title / artist from the video title. The format syntax is the same as --output, the parsed
+                                     parameters replace existing values. Additional templates: %(album), %(artist). Example: --metadata-from-title "%(artist)s -
+                                     %(title)s" matches a title like "Coldplay - Paradise"
     --xattrs                         write metadata to the video file's xattrs (using dublin core and xdg standards)
     --fixup POLICY                   Automatically correct known faults of the file. One of never (do nothing), warn (only emit a warning), detect_or_warn(the default;
                                      fix file if we can, warn otherwise)
@@ -515,6 +518,7 @@ youtube-dl makes the best effort to be a good command-line program, and thus sho
 From a Python program, you can embed youtube-dl in a more powerful fashion, like this:
 
 ```python
+from __future__ import unicode_literals
 import youtube_dl
 
 ydl_opts = {}
@@ -527,6 +531,7 @@ Most likely, you'll want to use various options. For a list of what can be done,
 Here's a more complete example of a program that outputs only errors (and a short message after the download is finished), and downloads/converts the video to an mp3 file:
 
 ```python
+from __future__ import unicode_literals
 import youtube_dl
 
 

devscripts/generate_aes_testdata.py

@@ -0,0 +1,42 @@
+from __future__ import unicode_literals
+
+import codecs
+import subprocess
+
+import os
+import sys
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from youtube_dl.utils import intlist_to_bytes
+from youtube_dl.aes import aes_encrypt, key_expansion
+
+secret_msg = b'Secret message goes here'
+
+
+def hex_str(int_list):
+    return codecs.encode(intlist_to_bytes(int_list), 'hex')
+
+
+def openssl_encode(algo, key, iv):
+    cmd = ['openssl', 'enc', '-e', '-' + algo, '-K', hex_str(key), '-iv', hex_str(iv)]
+    prog = subprocess.Popen(cmd, stdin=subprocess.PIPE, stdout=subprocess.PIPE)
+    out, _ = prog.communicate(secret_msg)
+    return out
+
+iv = key = [0x20, 0x15] + 14 * [0]
+
+r = openssl_encode('aes-128-cbc', key, iv)
+print('aes_cbc_decrypt')
+print(repr(r))
+
+password = key
+new_key = aes_encrypt(password, key_expansion(password))
+r = openssl_encode('aes-128-ctr', new_key, iv)
+print('aes_decrypt_text 16')
+print(repr(r))
+
+password = key + 16 * [0]
+new_key = aes_encrypt(password, key_expansion(password)) * (32 // 16)
+r = openssl_encode('aes-256-ctr', new_key, iv)
+print('aes_decrypt_text 32')
+print(repr(r))

docs/supportedsites.md

@@ -47,6 +47,7 @@
  - **Bandcamp**
  - **Bandcamp:album**
  - **bbc.co.uk**: BBC iPlayer
+ - **BeatportPro**
  - **Beeg**
  - **BehindKink**
  - **Bet**
@@ -111,6 +112,7 @@
  - **Discovery**
  - **divxstage**: DivxStage
  - **Dotsub**
+ - **DouyuTV**
  - **DRBonanza**
  - **Dropbox**
  - **DrTuber**
@@ -145,6 +147,7 @@
  - **Firstpost**
  - **Flickr**
  - **Folketinget**: Folketinget (ft.dk; Danish parliament)
+ - **FootyRoom**
  - **Foxgay**
  - **FoxNews**
  - **france2.fr:generation-quoi**
@@ -213,6 +216,7 @@
  - **jpopsuki.tv**
  - **Jukebox**
  - **Kaltura**
+ - **KanalPlay**: Kanal 5/9/11 Play
  - **Kankan**
  - **Karaoketv**
  - **keek**
@@ -227,6 +231,7 @@
  - **Letv**
  - **LetvPlaylist**
  - **LetvTv**
+ - **Libsyn**
  - **lifenews**: LIFE | NEWS
  - **LiveLeak**
  - **livestream**
@@ -306,6 +311,7 @@
  - **npo.nl:radio**
  - **npo.nl:radio:fragment**
  - **NRK**
+ - **NRKPlaylist**
  - **NRKTV**
  - **ntv.ru**
  - **Nuvid**
@@ -339,6 +345,7 @@
  - **PornHubPlaylist**
  - **Pornotube**
  - **PornoXO**
+ - **PrimeShareTV**
  - **PromptFile**
  - **prosiebensat1**: ProSiebenSat.1 Digital
  - **Puls4**
@@ -364,6 +371,7 @@
  - **RTP**
  - **RTS**: RTS.ch
  - **rtve.es:alacarta**: RTVE a la carta
+ - **rtve.es:infantil**: RTVE infantil
  - **rtve.es:live**: RTVE.es live streams
  - **RUHD**
  - **rutube**: Rutube videos
@@ -414,6 +422,7 @@
  - **SportBox**
  - **SportDeutschland**
  - **SRMediathek**: Saarländischer Rundfunk
+ - **SSA**
  - **stanfordoc**: Stanford Open ClassRoom
  - **Steam**
  - **streamcloud.eu**
@@ -483,6 +492,7 @@
  - **Ubu**
  - **udemy**
  - **udemy:course**
+ - **Ultimedia**
  - **Unistra**
  - **Urort**: NRK P3 Urørt
  - **ustream**
@@ -510,6 +520,7 @@
  - **Vidzi**
  - **vier**
  - **vier:videos**
+ - **Viewster**
  - **viki**
  - **vimeo**
  - **vimeo:album**
@@ -556,6 +567,9 @@
  - **XXXYMovies**
  - **Yahoo**: Yahoo screen and movies
  - **Yam**
+ - **yandexmusic:album**: Яндекс.Музыка - Альбом
+ - **yandexmusic:playlist**: Яндекс.Музыка - Плейлист
+ - **yandexmusic:track**: Яндекс.Музыка - Трек
  - **YesJapan**
  - **Ynet**
  - **YouJizz**

test/test_YoutubeDL.py

@@ -14,6 +14,9 @@ from test.helper import FakeYDL, assertRegexpMatches
 from youtube_dl import YoutubeDL
 from youtube_dl.extractor import YoutubeIE
 from youtube_dl.postprocessor.common import PostProcessor
+from youtube_dl.utils import match_filter_func
+
+TEST_URL = 'http://localhost/sample.mp4'
 
 
 class YDL(FakeYDL):
@@ -46,8 +49,8 @@ class TestFormatSelection(unittest.TestCase):
         ydl = YDL()
         ydl.params['prefer_free_formats'] = True
         formats = [
-            {'ext': 'webm', 'height': 460, 'url': 'x'},
-            {'ext': 'mp4', 'height': 460, 'url': 'y'},
+            {'ext': 'webm', 'height': 460, 'url': TEST_URL},
+            {'ext': 'mp4', 'height': 460, 'url': TEST_URL},
         ]
         info_dict = _make_result(formats)
         yie = YoutubeIE(ydl)
@@ -60,8 +63,8 @@ class TestFormatSelection(unittest.TestCase):
         ydl = YDL()
         ydl.params['prefer_free_formats'] = True
         formats = [
-            {'ext': 'webm', 'height': 720, 'url': 'a'},
-            {'ext': 'mp4', 'height': 1080, 'url': 'b'},
+            {'ext': 'webm', 'height': 720, 'url': TEST_URL},
+            {'ext': 'mp4', 'height': 1080, 'url': TEST_URL},
         ]
         info_dict['formats'] = formats
         yie = YoutubeIE(ydl)
@@ -74,9 +77,9 @@ class TestFormatSelection(unittest.TestCase):
         ydl = YDL()
         ydl.params['prefer_free_formats'] = False
         formats = [
-            {'ext': 'webm', 'height': 720, 'url': '_'},
-            {'ext': 'mp4', 'height': 720, 'url': '_'},
-            {'ext': 'flv', 'height': 720, 'url': '_'},
+            {'ext': 'webm', 'height': 720, 'url': TEST_URL},
+            {'ext': 'mp4', 'height': 720, 'url': TEST_URL},
+            {'ext': 'flv', 'height': 720, 'url': TEST_URL},
         ]
         info_dict['formats'] = formats
         yie = YoutubeIE(ydl)
@@ -88,8 +91,8 @@ class TestFormatSelection(unittest.TestCase):
         ydl = YDL()
         ydl.params['prefer_free_formats'] = False
         formats = [
-            {'ext': 'flv', 'height': 720, 'url': '_'},
-            {'ext': 'webm', 'height': 720, 'url': '_'},
+            {'ext': 'flv', 'height': 720, 'url': TEST_URL},
+            {'ext': 'webm', 'height': 720, 'url': TEST_URL},
         ]
         info_dict['formats'] = formats
         yie = YoutubeIE(ydl)
@@ -133,10 +136,10 @@ class TestFormatSelection(unittest.TestCase):
 
     def test_format_selection(self):
         formats = [
-            {'format_id': '35', 'ext': 'mp4', 'preference': 1, 'url': '_'},
-            {'format_id': '45', 'ext': 'webm', 'preference': 2, 'url': '_'},
-            {'format_id': '47', 'ext': 'webm', 'preference': 3, 'url': '_'},
-            {'format_id': '2', 'ext': 'flv', 'preference': 4, 'url': '_'},
+            {'format_id': '35', 'ext': 'mp4', 'preference': 1, 'url': TEST_URL},
+            {'format_id': '45', 'ext': 'webm', 'preference': 2, 'url': TEST_URL},
+            {'format_id': '47', 'ext': 'webm', 'preference': 3, 'url': TEST_URL},
+            {'format_id': '2', 'ext': 'flv', 'preference': 4, 'url': TEST_URL},
         ]
         info_dict = _make_result(formats)
 
@@ -167,10 +170,10 @@ class TestFormatSelection(unittest.TestCase):
 
     def test_format_selection_audio(self):
         formats = [
-            {'format_id': 'audio-low', 'ext': 'webm', 'preference': 1, 'vcodec': 'none', 'url': '_'},
-            {'format_id': 'audio-mid', 'ext': 'webm', 'preference': 2, 'vcodec': 'none', 'url': '_'},
-            {'format_id': 'audio-high', 'ext': 'flv', 'preference': 3, 'vcodec': 'none', 'url': '_'},
-            {'format_id': 'vid', 'ext': 'mp4', 'preference': 4, 'url': '_'},
+            {'format_id': 'audio-low', 'ext': 'webm', 'preference': 1, 'vcodec': 'none', 'url': TEST_URL},
+            {'format_id': 'audio-mid', 'ext': 'webm', 'preference': 2, 'vcodec': 'none', 'url': TEST_URL},
+            {'format_id': 'audio-high', 'ext': 'flv', 'preference': 3, 'vcodec': 'none', 'url': TEST_URL},
+            {'format_id': 'vid', 'ext': 'mp4', 'preference': 4, 'url': TEST_URL},
         ]
         info_dict = _make_result(formats)
 
@@ -185,8 +188,8 @@ class TestFormatSelection(unittest.TestCase):
         self.assertEqual(downloaded['format_id'], 'audio-low')
 
         formats = [
-            {'format_id': 'vid-low', 'ext': 'mp4', 'preference': 1, 'url': '_'},
-            {'format_id': 'vid-high', 'ext': 'mp4', 'preference': 2, 'url': '_'},
+            {'format_id': 'vid-low', 'ext': 'mp4', 'preference': 1, 'url': TEST_URL},
+            {'format_id': 'vid-high', 'ext': 'mp4', 'preference': 2, 'url': TEST_URL},
         ]
         info_dict = _make_result(formats)
 
@@ -228,9 +231,9 @@ class TestFormatSelection(unittest.TestCase):
 
     def test_format_selection_video(self):
         formats = [
-            {'format_id': 'dash-video-low', 'ext': 'mp4', 'preference': 1, 'acodec': 'none', 'url': '_'},
-            {'format_id': 'dash-video-high', 'ext': 'mp4', 'preference': 2, 'acodec': 'none', 'url': '_'},
-            {'format_id': 'vid', 'ext': 'mp4', 'preference': 3, 'url': '_'},
+            {'format_id': 'dash-video-low', 'ext': 'mp4', 'preference': 1, 'acodec': 'none', 'url': TEST_URL},
+            {'format_id': 'dash-video-high', 'ext': 'mp4', 'preference': 2, 'acodec': 'none', 'url': TEST_URL},
+            {'format_id': 'vid', 'ext': 'mp4', 'preference': 3, 'url': TEST_URL},
         ]
         info_dict = _make_result(formats)
 
@@ -337,6 +340,8 @@ class TestFormatSelection(unittest.TestCase):
         downloaded = ydl.downloaded_info_dicts[0]
         self.assertEqual(downloaded['format_id'], 'G')
 
+
+class TestYoutubeDL(unittest.TestCase):
     def test_subtitles(self):
         def s_formats(lang, autocaption=False):
             return [{
@@ -459,6 +464,73 @@ class TestFormatSelection(unittest.TestCase):
         self.assertTrue(os.path.exists(audiofile), '%s doesn\'t exist' % audiofile)
         os.unlink(audiofile)
 
+    def test_match_filter(self):
+        class FilterYDL(YDL):
+            def __init__(self, *args, **kwargs):
+                super(FilterYDL, self).__init__(*args, **kwargs)
+                self.params['simulate'] = True
+
+            def process_info(self, info_dict):
+                super(YDL, self).process_info(info_dict)
+
+            def _match_entry(self, info_dict, incomplete):
+                res = super(FilterYDL, self)._match_entry(info_dict, incomplete)
+                if res is None:
+                    self.downloaded_info_dicts.append(info_dict)
+                return res
+
+        first = {
+            'id': '1',
+            'url': TEST_URL,
+            'title': 'one',
+            'extractor': 'TEST',
+            'duration': 30,
+            'filesize': 10 * 1024,
+        }
+        second = {
+            'id': '2',
+            'url': TEST_URL,
+            'title': 'two',
+            'extractor': 'TEST',
+            'duration': 10,
+            'description': 'foo',
+            'filesize': 5 * 1024,
+        }
+        videos = [first, second]
+
+        def get_videos(filter_=None):
+            ydl = FilterYDL({'match_filter': filter_})
+            for v in videos:
+                ydl.process_ie_result(v, download=True)
+            return [v['id'] for v in ydl.downloaded_info_dicts]
+
+        res = get_videos()
+        self.assertEqual(res, ['1', '2'])
+
+        def f(v):
+            if v['id'] == '1':
+                return None
+            else:
+                return 'Video id is not 1'
+        res = get_videos(f)
+        self.assertEqual(res, ['1'])
+
+        f = match_filter_func('duration < 30')
+        res = get_videos(f)
+        self.assertEqual(res, ['2'])
+
+        f = match_filter_func('description = foo')
+        res = get_videos(f)
+        self.assertEqual(res, ['2'])
+
+        f = match_filter_func('description =? foo')
+        res = get_videos(f)
+        self.assertEqual(res, ['1', '2'])
+
+        f = match_filter_func('filesize > 5KiB')
+        res = get_videos(f)
+        self.assertEqual(res, ['1'])
+
 
 if __name__ == '__main__':
     unittest.main()

test/test_aes.py

@@ -0,0 +1,55 @@
+#!/usr/bin/env python
+
+from __future__ import unicode_literals
+
+# Allow direct execution
+import os
+import sys
+import unittest
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from youtube_dl.aes import aes_decrypt, aes_encrypt, aes_cbc_decrypt, aes_decrypt_text
+from youtube_dl.utils import bytes_to_intlist, intlist_to_bytes
+import base64
+
+# the encrypted data can be generate with 'devscripts/generate_aes_testdata.py'
+
+
+class TestAES(unittest.TestCase):
+    def setUp(self):
+        self.key = self.iv = [0x20, 0x15] + 14 * [0]
+        self.secret_msg = b'Secret message goes here'
+
+    def test_encrypt(self):
+        msg = b'message'
+        key = list(range(16))
+        encrypted = aes_encrypt(bytes_to_intlist(msg), key)
+        decrypted = intlist_to_bytes(aes_decrypt(encrypted, key))
+        self.assertEqual(decrypted, msg)
+
+    def test_cbc_decrypt(self):
+        data = bytes_to_intlist(
+            b"\x97\x92+\xe5\x0b\xc3\x18\x91ky9m&\xb3\xb5@\xe6'\xc2\x96.\xc8u\x88\xab9-[\x9e|\xf1\xcd"
+        )
+        decrypted = intlist_to_bytes(aes_cbc_decrypt(data, self.key, self.iv))
+        self.assertEqual(decrypted.rstrip(b'\x08'), self.secret_msg)
+
+    def test_decrypt_text(self):
+        password = intlist_to_bytes(self.key).decode('utf-8')
+        encrypted = base64.b64encode(
+            intlist_to_bytes(self.iv[:8]) +
+            b'\x17\x15\x93\xab\x8d\x80V\xcdV\xe0\t\xcdo\xc2\xa5\xd8ksM\r\xe27N\xae'
+        )
+        decrypted = (aes_decrypt_text(encrypted, password, 16))
+        self.assertEqual(decrypted, self.secret_msg)
+
+        password = intlist_to_bytes(self.key).decode('utf-8')
+        encrypted = base64.b64encode(
+            intlist_to_bytes(self.iv[:8]) +
+            b'\x0b\xe6\xa4\xd9z\x0e\xb8\xb9\xd0\xd4i_\x85\x1d\x99\x98_\xe5\x80\xe7.\xbf\xa5\x83'
+        )
+        decrypted = (aes_decrypt_text(encrypted, password, 32))
+        self.assertEqual(decrypted, self.secret_msg)
+
+if __name__ == '__main__':
+    unittest.main()

test/test_all_urls.py

@@ -104,11 +104,11 @@ class TestAllURLsMatching(unittest.TestCase):
         self.assertMatch(':tds', ['ComedyCentralShows'])
 
     def test_vimeo_matching(self):
-        self.assertMatch('http://vimeo.com/channels/tributes', ['vimeo:channel'])
-        self.assertMatch('http://vimeo.com/channels/31259', ['vimeo:channel'])
-        self.assertMatch('http://vimeo.com/channels/31259/53576664', ['vimeo'])
-        self.assertMatch('http://vimeo.com/user7108434', ['vimeo:user'])
-        self.assertMatch('http://vimeo.com/user7108434/videos', ['vimeo:user'])
+        self.assertMatch('https://vimeo.com/channels/tributes', ['vimeo:channel'])
+        self.assertMatch('https://vimeo.com/channels/31259', ['vimeo:channel'])
+        self.assertMatch('https://vimeo.com/channels/31259/53576664', ['vimeo'])
+        self.assertMatch('https://vimeo.com/user7108434', ['vimeo:user'])
+        self.assertMatch('https://vimeo.com/user7108434/videos', ['vimeo:user'])
         self.assertMatch('https://vimeo.com/user21297594/review/75524534/3c257a1b5d', ['vimeo:review'])
 
     # https://github.com/rg3/youtube-dl/issues/1930

test/test_execution.py

@@ -1,4 +1,6 @@
 #!/usr/bin/env python
+# coding: utf-8
+
 from __future__ import unicode_literals
 
 import unittest
@@ -27,5 +29,12 @@ class TestExecution(unittest.TestCase):
     def test_main_exec(self):
         subprocess.check_call([sys.executable, 'youtube_dl/__main__.py', '--version'], cwd=rootDir, stdout=_DEV_NULL)
 
+    def test_cmdline_umlauts(self):
+        p = subprocess.Popen(
+            [sys.executable, 'youtube_dl/__main__.py', 'ä', '--version'],
+            cwd=rootDir, stdout=_DEV_NULL, stderr=subprocess.PIPE)
+        _, stderr = p.communicate()
+        self.assertFalse(stderr)
+
 if __name__ == '__main__':
     unittest.main()

test/test_http.py

@@ -8,7 +8,7 @@ import unittest
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 from youtube_dl import YoutubeDL
-from youtube_dl.compat import compat_http_server
+from youtube_dl.compat import compat_http_server, compat_urllib_request
 import ssl
 import threading
 
@@ -68,5 +68,52 @@ class TestHTTP(unittest.TestCase):
         r = ydl.extract_info('https://localhost:%d/video.html' % self.port)
         self.assertEqual(r['url'], 'https://localhost:%d/vid.mp4' % self.port)
 
+
+def _build_proxy_handler(name):
+    class HTTPTestRequestHandler(compat_http_server.BaseHTTPRequestHandler):
+        proxy_name = name
+
+        def log_message(self, format, *args):
+            pass
+
+        def do_GET(self):
+            self.send_response(200)
+            self.send_header('Content-Type', 'text/plain; charset=utf-8')
+            self.end_headers()
+            self.wfile.write('{self.proxy_name}: {self.path}'.format(self=self).encode('utf-8'))
+    return HTTPTestRequestHandler
+
+
+class TestProxy(unittest.TestCase):
+    def setUp(self):
+        self.proxy = compat_http_server.HTTPServer(
+            ('localhost', 0), _build_proxy_handler('normal'))
+        self.port = self.proxy.socket.getsockname()[1]
+        self.proxy_thread = threading.Thread(target=self.proxy.serve_forever)
+        self.proxy_thread.daemon = True
+        self.proxy_thread.start()
+
+        self.cn_proxy = compat_http_server.HTTPServer(
+            ('localhost', 0), _build_proxy_handler('cn'))
+        self.cn_port = self.cn_proxy.socket.getsockname()[1]
+        self.cn_proxy_thread = threading.Thread(target=self.cn_proxy.serve_forever)
+        self.cn_proxy_thread.daemon = True
+        self.cn_proxy_thread.start()
+
+    def test_proxy(self):
+        cn_proxy = 'localhost:{0}'.format(self.cn_port)
+        ydl = YoutubeDL({
+            'proxy': 'localhost:{0}'.format(self.port),
+            'cn_verification_proxy': cn_proxy,
+        })
+        url = 'http://foo.com/bar'
+        response = ydl.urlopen(url).read().decode('utf-8')
+        self.assertEqual(response, 'normal: {0}'.format(url))
+
+        req = compat_urllib_request.Request(url)
+        req.add_header('Ytdl-request-proxy', cn_proxy)
+        response = ydl.urlopen(req).read().decode('utf-8')
+        self.assertEqual(response, 'cn: {0}'.format(url))
+
 if __name__ == '__main__':
     unittest.main()

test/test_postprocessors.py

@@ -0,0 +1,17 @@
+#!/usr/bin/env python
+
+from __future__ import unicode_literals
+
+# Allow direct execution
+import os
+import sys
+import unittest
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from youtube_dl.postprocessor import MetadataFromTitlePP
+
+
+class TestMetadataFromTitle(unittest.TestCase):
+    def test_format_to_regex(self):
+        pp = MetadataFromTitlePP(None, '%(title)s - %(artist)s')
+        self.assertEqual(pp._titleregex, '(?P<title>.+)\ \-\ (?P<artist>.+)')

test/test_subtitles.py

@@ -26,6 +26,7 @@ from youtube_dl.extractor import (
     VikiIE,
     ThePlatformIE,
     RTVEALaCartaIE,
+    FunnyOrDieIE,
 )
 
 
@@ -320,5 +321,17 @@ class TestRtveSubtitles(BaseTestSubtitles):
         self.assertEqual(md5(subtitles['es']), '69e70cae2d40574fb7316f31d6eb7fca')
 
 
+class TestFunnyOrDieSubtitles(BaseTestSubtitles):
+    url = 'http://www.funnyordie.com/videos/224829ff6d/judd-apatow-will-direct-your-vine'
+    IE = FunnyOrDieIE
+
+    def test_allsubtitles(self):
+        self.DL.params['writesubtitles'] = True
+        self.DL.params['allsubtitles'] = True
+        subtitles = self.getSubtitles()
+        self.assertEqual(set(subtitles.keys()), set(['en']))
+        self.assertEqual(md5(subtitles['en']), 'c5593c193eacd353596c11c2d4f9ecc4')
+
+
 if __name__ == '__main__':
     unittest.main()

test/test_unicode_literals.py

@@ -17,13 +17,22 @@ IGNORED_FILES = [
     'buildserver.py',
 ]
 
+IGNORED_DIRS = [
+    '.git',
+    '.tox',
+]
 
 from test.helper import assertRegexpMatches
 
 
 class TestUnicodeLiterals(unittest.TestCase):
     def test_all_files(self):
-        for dirpath, _, filenames in os.walk(rootDir):
+        for dirpath, dirnames, filenames in os.walk(rootDir):
+            for ignore_dir in IGNORED_DIRS:
+                if ignore_dir in dirnames:
+                    # If we remove the directory from dirnames os.walk won't
+                    # recurse into it
+                    dirnames.remove(ignore_dir)
             for basename in filenames:
                 if not basename.endswith('.py'):
                     continue

test/test_utils.py

@@ -24,6 +24,7 @@ from youtube_dl.utils import (
     encodeFilename,
     escape_rfc3986,
     escape_url,
+    ExtractorError,
     find_xpath_attr,
     fix_xml_ampersands,
     InAdvancePagedList,
@@ -39,6 +40,7 @@ from youtube_dl.utils import (
     read_batch_urls,
     sanitize_filename,
     sanitize_path,
+    sanitize_url_path_consecutive_slashes,
     shell_quote,
     smuggle_url,
     str_to_int,
@@ -53,6 +55,7 @@ from youtube_dl.utils import (
     urlencode_postdata,
     version_tuple,
     xpath_with_ns,
+    xpath_text,
     render_table,
     match_str,
 )
@@ -163,6 +166,31 @@ class TestUtil(unittest.TestCase):
         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([]), [])
@@ -224,6 +252,17 @@ class TestUtil(unittest.TestCase):
         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'

tox.ini

@@ -1,8 +1,11 @@
 [tox]
-envlist = py26,py27,py33
+envlist = py26,py27,py33,py34
 [testenv]
 deps =
    nose
    coverage
-commands = nosetests --verbose {posargs:test}  # --with-coverage --cover-package=youtube_dl --cover-html
+defaultargs = test --exclude test_download.py --exclude test_age_restriction.py
+    --exclude test_subtitles.py --exclude test_write_annotations.py
+    --exclude test_youtube_lists.py
+commands = nosetests --verbose {posargs:{[testenv]defaultargs}}  # --with-coverage --cover-package=youtube_dl --cover-html
                                                # test.test_download:TestDownload.test_NowVideo

youtube_dl/YoutubeDL.py

@@ -323,8 +323,10 @@ class YoutubeDL(object):
                 'Set the LC_ALL environment variable to fix this.')
             self.params['restrictfilenames'] = True
 
-        if '%(stitle)s' in self.params.get('outtmpl', ''):
-            self.report_warning('%(stitle)s is deprecated. Use the %(title)s and the --restrict-filenames flag(which also secures %(uploader)s et al) instead.')
+        if isinstance(params.get('outtmpl'), bytes):
+            self.report_warning(
+                'Parameter outtmpl is bytes, but should be a unicode string. '
+                'Put  from __future__ import unicode_literals  at the top of your code file or consider switching to Python 3.x.')
 
         self._setup_opener()
 
@@ -630,7 +632,7 @@ class YoutubeDL(object):
         Returns a list with a dictionary for each video we find.
         If 'download', also downloads the videos.
         extra_info is a dict containing the extra values to add to each result
-         '''
+        '''
 
         if ie_key:
             ies = [self.get_info_extractor(ie_key)]
@@ -1086,8 +1088,7 @@ class YoutubeDL(object):
         if req_format is None:
             req_format = 'best'
         formats_to_download = []
-        # The -1 is for supporting YoutubeIE
-        if req_format in ('-1', 'all'):
+        if req_format == 'all':
             formats_to_download = formats
         else:
             for rfstr in req_format.split(','):
@@ -1214,9 +1215,6 @@ class YoutubeDL(object):
         if len(info_dict['title']) > 200:
             info_dict['title'] = info_dict['title'][:197] + '...'
 
-        # Keep for backwards compatibility
-        info_dict['stitle'] = info_dict['title']
-
         if 'format' not in info_dict:
             info_dict['format'] = info_dict['ext']
 

youtube_dl/__init__.py

@@ -213,6 +213,11 @@ def _real_main(argv=None):
     # PostProcessors
     postprocessors = []
     # Add the metadata pp first, the other pps will copy it
+    if opts.metafromtitle:
+        postprocessors.append({
+            'key': 'MetadataFromTitle',
+            'titleformat': opts.metafromtitle
+        })
     if opts.addmetadata:
         postprocessors.append({'key': 'FFmpegMetadata'})
     if opts.extractaudio:

youtube_dl/extractor/__init__.py

@@ -37,6 +37,7 @@ from .bandcamp import BandcampIE, BandcampAlbumIE
 from .bbccouk import BBCCoUkIE
 from .beeg import BeegIE
 from .behindkink import BehindKinkIE
+from .beatportpro import BeatportProIE
 from .bet import BetIE
 from .bild import BildIE
 from .bilibili import BiliBiliIE
@@ -106,6 +107,7 @@ from .dctp import DctpTvIE
 from .deezer import DeezerPlaylistIE
 from .dfb import DFBIE
 from .dotsub import DotsubIE
+from .douyutv import DouyuTVIE
 from .dreisat import DreiSatIE
 from .drbonanza import DRBonanzaIE
 from .drtuber import DrTuberIE
@@ -151,6 +153,7 @@ from .fktv import (
 )
 from .flickr import FlickrIE
 from .folketinget import FolketingetIE
+from .footyroom import FootyRoomIE
 from .fourtube import FourTubeIE
 from .foxgay import FoxgayIE
 from .foxnews import FoxNewsIE
@@ -230,6 +233,7 @@ from .jove import JoveIE
 from .jukebox import JukeboxIE
 from .jpopsukitv import JpopsukiIE
 from .kaltura import KalturaIE
+from .kanalplay import KanalPlayIE
 from .kankan import KankanIE
 from .karaoketv import KaraoketvIE
 from .keezmovies import KeezMoviesIE
@@ -246,6 +250,7 @@ from .letv import (
     LetvTvIE,
     LetvPlaylistIE
 )
+from .libsyn import LibsynIE
 from .lifenews import LifeNewsIE
 from .liveleak import LiveLeakIE
 from .livestream import (
@@ -342,6 +347,7 @@ from .npo import (
 )
 from .nrk import (
     NRKIE,
+    NRKPlaylistIE,
     NRKTVIE,
 )
 from .ntvde import NTVDeIE
@@ -377,6 +383,7 @@ from .pornhub import (
 )
 from .pornotube import PornotubeIE
 from .pornoxo import PornoXOIE
+from .primesharetv import PrimeShareTVIE
 from .promptfile import PromptFileIE
 from .prosiebensat1 import ProSiebenSat1IE
 from .puls4 import Puls4IE
@@ -402,7 +409,7 @@ from .rtlnow import RTLnowIE
 from .rtl2 import RTL2IE
 from .rtp import RTPIE
 from .rts import RTSIE
-from .rtve import RTVEALaCartaIE, RTVELiveIE
+from .rtve import RTVEALaCartaIE, RTVELiveIE, RTVEInfantilIE
 from .ruhd import RUHDIE
 from .rutube import (
     RutubeIE,
@@ -460,6 +467,7 @@ from .sport5 import Sport5IE
 from .sportbox import SportBoxIE
 from .sportdeutschland import SportDeutschlandIE
 from .srmediathek import SRMediathekIE
+from .ssa import SSAIE
 from .stanfordoc import StanfordOpenClassroomIE
 from .steam import SteamIE
 from .streamcloud import StreamcloudIE
@@ -532,6 +540,7 @@ from .udemy import (
     UdemyIE,
     UdemyCourseIE
 )
+from .ultimedia import UltimediaIE
 from .unistra import UnistraIE
 from .urort import UrortIE
 from .ustream import UstreamIE, UstreamChannelIE
@@ -555,6 +564,7 @@ from .videoweed import VideoWeedIE
 from .vidme import VidmeIE
 from .vidzi import VidziIE
 from .vier import VierIE, VierVideosIE
+from .viewster import ViewsterIE
 from .vimeo import (
     VimeoIE,
     VimeoAlbumIE,
@@ -611,6 +621,11 @@ from .yahoo import (
     YahooSearchIE,
 )
 from .yam import YamIE
+from .yandexmusic import (
+    YandexMusicTrackIE,
+    YandexMusicAlbumIE,
+    YandexMusicPlaylistIE,
+)
 from .yesjapan import YesJapanIE
 from .ynet import YnetIE
 from .youjizz import YouJizzIE

youtube_dl/extractor/aftenposten.py

@@ -14,10 +14,10 @@ from ..utils import (
 
 
 class AftenpostenIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?aftenposten\.no/webtv/([^/]+/)*(?P<id>[^/]+)-\d+\.html'
+    _VALID_URL = r'https?://(?:www\.)?aftenposten\.no/webtv/(?:#!/)?video/(?P<id>\d+)'
 
     _TEST = {
-        'url': 'http://www.aftenposten.no/webtv/serier-og-programmer/sweatshopenglish/TRAILER-SWEATSHOP---I-cant-take-any-more-7800835.html?paging=&section=webtv_serierogprogrammer_sweatshop_sweatshopenglish',
+        'url': 'http://www.aftenposten.no/webtv/#!/video/21039/trailer-sweatshop-i-can-t-take-any-more',
         'md5': 'fd828cd29774a729bf4d4425fe192972',
         'info_dict': {
             'id': '21039',
@@ -30,12 +30,7 @@ class AftenpostenIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        display_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, display_id)
-
-        video_id = self._html_search_regex(
-            r'data-xs-id="(\d+)"', webpage, 'video id')
+        video_id = self._match_id(url)
 
         data = self._download_xml(
             'http://frontend.xstream.dk/ap/feed/video/?platform=web&id=%s' % video_id, video_id)

youtube_dl/extractor/ard.py

@@ -50,6 +50,9 @@ class ARDMediathekIE(InfoExtractor):
         if '>Der gewünschte Beitrag ist nicht mehr verfügbar.<' in webpage:
             raise ExtractorError('Video %s is no longer available' % video_id, expected=True)
 
+        if 'Diese Sendung ist für Jugendliche unter 12 Jahren nicht geeignet. Der Clip ist deshalb nur von 20 bis 6 Uhr verfügbar.' in webpage:
+            raise ExtractorError('This program is only suitable for those aged 12 and older. Video %s is therefore only available between 20 pm and 6 am.' % video_id, expected=True)
+
         if re.search(r'[\?&]rss($|[=&])', url):
             doc = parse_xml(webpage)
             if doc.tag == 'rss':

youtube_dl/extractor/arte.py

@@ -146,6 +146,7 @@ class ArteTVPlus7IE(InfoExtractor):
 
             formats.append(format)
 
+        self._check_formats(formats, video_id)
         self._sort_formats(formats)
 
         info_dict['formats'] = formats

youtube_dl/extractor/beatportpro.py

@@ -0,0 +1,103 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import int_or_none
+
+
+class BeatportProIE(InfoExtractor):
+    _VALID_URL = r'https?://pro\.beatport\.com/track/(?P<display_id>[^/]+)/(?P<id>[0-9]+)'
+    _TESTS = [{
+        'url': 'https://pro.beatport.com/track/synesthesia-original-mix/5379371',
+        'md5': 'b3c34d8639a2f6a7f734382358478887',
+        'info_dict': {
+            'id': '5379371',
+            'display_id': 'synesthesia-original-mix',
+            'ext': 'mp4',
+            'title': 'Froxic - Synesthesia (Original Mix)',
+        },
+    }, {
+        'url': 'https://pro.beatport.com/track/love-and-war-original-mix/3756896',
+        'md5': 'e44c3025dfa38c6577fbaeb43da43514',
+        'info_dict': {
+            'id': '3756896',
+            'display_id': 'love-and-war-original-mix',
+            'ext': 'mp3',
+            'title': 'Wolfgang Gartner - Love & War (Original Mix)',
+        },
+    }, {
+        'url': 'https://pro.beatport.com/track/birds-original-mix/4991738',
+        'md5': 'a1fd8e8046de3950fd039304c186c05f',
+        'info_dict': {
+            'id': '4991738',
+            'display_id': 'birds-original-mix',
+            'ext': 'mp4',
+            'title': "Tos, Middle Milk, Mumblin' Johnsson - Birds (Original Mix)",
+        }
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        track_id = mobj.group('id')
+        display_id = mobj.group('display_id')
+
+        webpage = self._download_webpage(url, display_id)
+
+        playables = self._parse_json(
+            self._search_regex(
+                r'window\.Playables\s*=\s*({.+?});', webpage,
+                'playables info', flags=re.DOTALL),
+            track_id)
+
+        track = next(t for t in playables['tracks'] if t['id'] == int(track_id))
+
+        title = ', '.join((a['name'] for a in track['artists'])) + ' - ' + track['name']
+        if track['mix']:
+            title += ' (' + track['mix'] + ')'
+
+        formats = []
+        for ext, info in track['preview'].items():
+            if not info['url']:
+                continue
+            fmt = {
+                'url': info['url'],
+                'ext': ext,
+                'format_id': ext,
+                'vcodec': 'none',
+            }
+            if ext == 'mp3':
+                fmt['preference'] = 0
+                fmt['acodec'] = 'mp3'
+                fmt['abr'] = 96
+                fmt['asr'] = 44100
+            elif ext == 'mp4':
+                fmt['preference'] = 1
+                fmt['acodec'] = 'aac'
+                fmt['abr'] = 96
+                fmt['asr'] = 44100
+            formats.append(fmt)
+        self._sort_formats(formats)
+
+        images = []
+        for name, info in track['images'].items():
+            image_url = info.get('url')
+            if name == 'dynamic' or not image_url:
+                continue
+            image = {
+                'id': name,
+                'url': image_url,
+                'height': int_or_none(info.get('height')),
+                'width': int_or_none(info.get('width')),
+            }
+            images.append(image)
+
+        return {
+            'id': compat_str(track.get('id')) or track_id,
+            'display_id': track.get('slug') or display_id,
+            'title': title,
+            'formats': formats,
+            'thumbnails': images,
+        }

youtube_dl/extractor/cloudy.py

@@ -105,6 +105,7 @@ class CloudyIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         file_key = self._search_regex(
-            r'filekey\s*=\s*"([^"]+)"', webpage, 'file_key')
+            [r'key\s*:\s*"([^"]+)"', r'filekey\s*=\s*"([^"]+)"'],
+            webpage, 'file_key')
 
         return self._extract_video(video_host, video_id, file_key)

youtube_dl/extractor/common.py

@@ -1062,6 +1062,9 @@ class InfoExtractor(object):
     def _get_automatic_captions(self, *args, **kwargs):
         raise NotImplementedError("This method must be implemented by subclasses")
 
+    def _subtitles_timecode(self, seconds):
+        return '%02d:%02d:%02d.%03d' % (seconds / 3600, (seconds % 3600) / 60, seconds % 60, (seconds % 1) * 1000)
+
 
 class SearchInfoExtractor(InfoExtractor):
     """

youtube_dl/extractor/crunchyroll.py

@@ -23,7 +23,6 @@ from ..utils import (
 )
 from ..aes import (
     aes_cbc_decrypt,
-    inc,
 )
 
 
@@ -102,13 +101,6 @@ class CrunchyrollIE(InfoExtractor):
 
         key = obfuscate_key(id)
 
-        class Counter:
-            __value = iv
-
-            def next_value(self):
-                temp = self.__value
-                self.__value = inc(self.__value)
-                return temp
         decrypted_data = intlist_to_bytes(aes_cbc_decrypt(data, key, iv))
         return zlib.decompress(decrypted_data)
 

youtube_dl/extractor/douyutv.py

@@ -0,0 +1,77 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+
+class DouyuTVIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?douyutv\.com/(?P<id>[A-Za-z0-9]+)'
+    _TEST = {
+        'url': 'http://www.douyutv.com/iseven',
+        'info_dict': {
+            'id': 'iseven',
+            'ext': 'flv',
+            'title': 're:^清晨醒脑！T-ara根本停不下来！ [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+            'description': 'md5:9e525642c25a0a24302869937cf69d17',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'uploader': '7师傅',
+            'uploader_id': '431925',
+            'is_live': True,
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        config = self._download_json(
+            'http://www.douyutv.com/api/client/room/%s' % video_id, video_id)
+
+        data = config['data']
+
+        error_code = config.get('error', 0)
+        show_status = data.get('show_status')
+        if error_code is not 0:
+            raise ExtractorError(
+                'Server reported error %i' % error_code, expected=True)
+
+        # 1 = live, 2 = offline
+        if show_status == '2':
+            raise ExtractorError(
+                'Live stream is offline', expected=True)
+
+        base_url = data['rtmp_url']
+        live_path = data['rtmp_live']
+
+        title = self._live_title(data['room_name'])
+        description = data.get('show_details')
+        thumbnail = data.get('room_src')
+
+        uploader = data.get('nickname')
+        uploader_id = data.get('owner_uid')
+
+        multi_formats = data.get('rtmp_multi_bitrate')
+        if not isinstance(multi_formats, dict):
+            multi_formats = {}
+        multi_formats['live'] = live_path
+
+        formats = [{
+            'url': '%s/%s' % (base_url, format_path),
+            'format_id': format_id,
+            'preference': 1 if format_id == 'live' else 0,
+        } for format_id, format_path in multi_formats.items()]
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'uploader': uploader,
+            'uploader_id': uploader_id,
+            'formats': formats,
+            'is_live': True,
+        }

youtube_dl/extractor/eighttracks.py

@@ -3,7 +3,6 @@ from __future__ import unicode_literals
 
 import json
 import random
-import re
 
 from .common import InfoExtractor
 from ..compat import (
@@ -103,20 +102,23 @@ class EightTracksIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        playlist_id = mobj.group('id')
+        playlist_id = self._match_id(url)
 
         webpage = self._download_webpage(url, playlist_id)
 
-        json_like = self._search_regex(
-            r"(?s)PAGE.mix = (.*?);\n", webpage, 'trax information')
-        data = json.loads(json_like)
+        data = self._parse_json(
+            self._search_regex(
+                r"(?s)PAGE\.mix\s*=\s*({.+?});\n", webpage, 'trax information'),
+            playlist_id)
 
         session = str(random.randint(0, 1000000000))
         mix_id = data['id']
         track_count = data['tracks_count']
         duration = data['duration']
         avg_song_duration = float(duration) / track_count
+        # duration is sometimes negative, use predefined avg duration
+        if avg_song_duration <= 0:
+            avg_song_duration = 300
         first_url = 'http://8tracks.com/sets/%s/play?player=sm&mix_id=%s&format=jsonh' % (session, mix_id)
         next_url = first_url
         entries = []

youtube_dl/extractor/footyroom.py

@@ -0,0 +1,41 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class FootyRoomIE(InfoExtractor):
+    _VALID_URL = r'http://footyroom\.com/(?P<id>[^/]+)'
+    _TEST = {
+        'url': 'http://footyroom.com/schalke-04-0-2-real-madrid-2015-02/',
+        'info_dict': {
+            'id': 'schalke-04-0-2-real-madrid-2015-02',
+            'title': 'Schalke 04 0 – 2 Real Madrid',
+        },
+        'playlist_count': 3,
+    }
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, playlist_id)
+
+        playlist = self._parse_json(
+            self._search_regex(
+                r'VideoSelector\.load\((\[.+?\])\);', webpage, 'video selector'),
+            playlist_id)
+
+        playlist_title = self._og_search_title(webpage)
+
+        entries = []
+        for video in playlist:
+            payload = video.get('payload')
+            if not payload:
+                continue
+            playwire_url = self._search_regex(
+                r'data-config="([^"]+)"', payload,
+                'playwire url', default=None)
+            if playwire_url:
+                entries.append(self.url_result(playwire_url, 'Playwire'))
+
+        return self.playlist_result(entries, playlist_id, playlist_title)

youtube_dl/extractor/funnyordie.py

@@ -50,7 +50,6 @@ class FunnyOrDieIE(InfoExtractor):
         bitrates.sort()
 
         formats = []
-
         for bitrate in bitrates:
             for link in links:
                 formats.append({
@@ -59,6 +58,13 @@ class FunnyOrDieIE(InfoExtractor):
                     'vbr': bitrate,
                 })
 
+        subtitles = {}
+        for src, src_lang in re.findall(r'<track kind="captions" src="([^"]+)" srclang="([^"]+)"', webpage):
+            subtitles[src_lang] = [{
+                'ext': src.split('/')[-1],
+                'url': 'http://www.funnyordie.com%s' % src,
+            }]
+
         post_json = self._search_regex(
             r'fb_post\s*=\s*(\{.*?\});', webpage, 'post details')
         post = json.loads(post_json)
@@ -69,4 +75,5 @@ class FunnyOrDieIE(InfoExtractor):
             'description': post.get('description'),
             'thumbnail': post.get('picture'),
             'formats': formats,
+            'subtitles': subtitles,
         }

youtube_dl/extractor/generic.py

@@ -527,6 +527,17 @@ class GenericIE(InfoExtractor):
             },
             'add_ie': ['Viddler'],
         },
+        # Libsyn embed
+        {
+            'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
+            'info_dict': {
+                'id': '3377616',
+                'ext': 'mp3',
+                'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
+                'description': 'md5:601cb790edd05908957dae8aaa866465',
+                'upload_date': '20150220',
+            },
+        },
         # jwplayer YouTube
         {
             'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
@@ -1006,6 +1017,19 @@ class GenericIE(InfoExtractor):
         if mobj is not None:
             return self.url_result(mobj.group('url'))
 
+        # Look for NYTimes player
+        mobj = re.search(
+            r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
+            webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'))
+
+        # Look for Libsyn player
+        mobj = re.search(
+            r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'))
+
         # Look for Ooyala videos
         mobj = (re.search(r'player\.ooyala\.com/[^"?]+\?[^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
                 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
@@ -1268,10 +1292,16 @@ class GenericIE(InfoExtractor):
             # HTML5 video
             found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
         if not found:
+            REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
             found = re.search(
                 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
-                r'(?:[a-z-]+="[^"]+"\s+)*?content="[0-9]{,2};url=\'?([^\'"]+)',
+                r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
                 webpage)
+            if not found:
+                # Look also in Refresh HTTP header
+                refresh_header = head_response.headers.get('Refresh')
+                if refresh_header:
+                    found = re.search(REDIRECT_REGEX, refresh_header)
             if found:
                 new_url = found.group(1)
                 self.report_following_redirect(new_url)

youtube_dl/extractor/globo.py

@@ -20,7 +20,7 @@ class GloboIE(InfoExtractor):
     _VALID_URL = 'https?://.+?\.globo\.com/(?P<id>.+)'
 
     _API_URL_TEMPLATE = 'http://api.globovideos.com/videos/%s/playlist'
-    _SECURITY_URL_TEMPLATE = 'http://security.video.globo.com/videos/%s/hash?player=flash&version=2.9.9.50&resource_id=%s'
+    _SECURITY_URL_TEMPLATE = 'http://security.video.globo.com/videos/%s/hash?player=flash&version=17.0.0.132&resource_id=%s'
 
     _VIDEOID_REGEXES = [
         r'\bdata-video-id="(\d+)"',

youtube_dl/extractor/grooveshark.py

@@ -140,9 +140,9 @@ class GroovesharkIE(InfoExtractor):
 
         if webpage is not None:
             o = GroovesharkHtmlParser.extract_object_tags(webpage)
-            return (webpage, [x for x in o if x['attrs']['id'] == 'jsPlayerEmbed'])
+            return webpage, [x for x in o if x['attrs']['id'] == 'jsPlayerEmbed']
 
-        return (webpage, None)
+        return webpage, None
 
     def _real_initialize(self):
         self.ts = int(time.time() * 1000)  # timestamp in millis
@@ -154,7 +154,7 @@ class GroovesharkIE(InfoExtractor):
         swf_referer = None
         if self.do_playerpage_request:
             (_, player_objs) = self._get_playerpage(url)
-            if player_objs is not None:
+            if player_objs:
                 swf_referer = self._build_swf_referer(url, player_objs[0])
                 self.to_screen('SWF Referer: %s' % swf_referer)
 

youtube_dl/extractor/jeuxvideo.py

@@ -2,7 +2,6 @@
 
 from __future__ import unicode_literals
 
-import json
 import re
 
 from .common import InfoExtractor
@@ -15,10 +14,10 @@ class JeuxVideoIE(InfoExtractor):
         'url': 'http://www.jeuxvideo.com/reportages-videos-jeux/0004/00046170/tearaway-playstation-vita-gc-2013-tearaway-nous-presente-ses-papiers-d-identite-00115182.htm',
         'md5': '046e491afb32a8aaac1f44dd4ddd54ee',
         'info_dict': {
-            'id': '5182',
+            'id': '114765',
             'ext': 'mp4',
-            'title': 'GC 2013 : Tearaway nous présente ses papiers d\'identité',
-            'description': 'Lorsque les développeurs de LittleBigPlanet proposent un nouveau titre, on ne peut que s\'attendre à un résultat original et fort attrayant.\n',
+            'title': 'Tearaway : GC 2013 : Tearaway nous présente ses papiers d\'identité',
+            'description': 'Lorsque les développeurs de LittleBigPlanet proposent un nouveau titre, on ne peut que s\'attendre à un résultat original et fort attrayant.',
         },
     }
 
@@ -26,26 +25,29 @@ class JeuxVideoIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         title = mobj.group(1)
         webpage = self._download_webpage(url, title)
-        xml_link = self._html_search_regex(
-            r'<param name="flashvars" value="config=(.*?)" />',
+        title = self._html_search_meta('name', webpage)
+        config_url = self._html_search_regex(
+            r'data-src="(/contenu/medias/video.php.*?)"',
             webpage, 'config URL')
+        config_url = 'http://www.jeuxvideo.com' + config_url
 
         video_id = self._search_regex(
-            r'http://www\.jeuxvideo\.com/config/\w+/\d+/(.*?)/\d+_player\.xml',
-            xml_link, 'video ID')
+            r'id=(\d+)',
+            config_url, 'video ID')
 
-        config = self._download_xml(
-            xml_link, title, 'Downloading XML config')
-        info_json = config.find('format.json').text
-        info = json.loads(info_json)['versions'][0]
+        config = self._download_json(
+            config_url, title, 'Downloading JSON config')
 
-        video_url = 'http://video720.jeuxvideo.com/' + info['file']
+        formats = [{
+            'url': source['file'],
+            'format_id': source['label'],
+            'resolution': source['label'],
+        } for source in reversed(config['sources'])]
 
         return {
             'id': video_id,
-            'title': config.find('titre_video').text,
-            'ext': 'mp4',
-            'url': video_url,
+            'title': title,
+            'formats': formats,
             'description': self._og_search_description(webpage),
-            'thumbnail': config.find('image').text,
+            'thumbnail': config.get('image'),
         }

youtube_dl/extractor/kanalplay.py

@@ -0,0 +1,96 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    float_or_none,
+)
+
+
+class KanalPlayIE(InfoExtractor):
+    IE_DESC = 'Kanal 5/9/11 Play'
+    _VALID_URL = r'https?://(?:www\.)?kanal(?P<channel_id>5|9|11)play\.se/(?:#!/)?(?:play/)?program/\d+/video/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'http://www.kanal5play.se/#!/play/program/3060212363/video/3270012277',
+        'info_dict': {
+            'id': '3270012277',
+            'ext': 'flv',
+            'title': 'Saknar både dusch och avlopp',
+            'description': 'md5:6023a95832a06059832ae93bc3c7efb7',
+            'duration': 2636.36,
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        }
+    }, {
+        'url': 'http://www.kanal9play.se/#!/play/program/335032/video/246042',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.kanal11play.se/#!/play/program/232835958/video/367135199',
+        'only_matching': True,
+    }]
+
+    def _fix_subtitles(self, subs):
+        return '\r\n\r\n'.join(
+            '%s\r\n%s --> %s\r\n%s'
+            % (
+                num,
+                self._subtitles_timecode(item['startMillis'] / 1000.0),
+                self._subtitles_timecode(item['endMillis'] / 1000.0),
+                item['text'],
+            ) for num, item in enumerate(subs, 1))
+
+    def _get_subtitles(self, channel_id, video_id):
+        subs = self._download_json(
+            'http://www.kanal%splay.se/api/subtitles/%s' % (channel_id, video_id),
+            video_id, 'Downloading subtitles JSON', fatal=False)
+        return {'se': [{'ext': 'srt', 'data': self._fix_subtitles(subs)}]} if subs else {}
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        channel_id = mobj.group('channel_id')
+
+        video = self._download_json(
+            'http://www.kanal%splay.se/api/getVideo?format=FLASH&videoId=%s' % (channel_id, video_id),
+            video_id)
+
+        reasons_for_no_streams = video.get('reasonsForNoStreams')
+        if reasons_for_no_streams:
+            raise ExtractorError(
+                '%s returned error: %s' % (self.IE_NAME, '\n'.join(reasons_for_no_streams)),
+                expected=True)
+
+        title = video['title']
+        description = video.get('description')
+        duration = float_or_none(video.get('length'), 1000)
+        thumbnail = video.get('posterUrl')
+
+        stream_base_url = video['streamBaseUrl']
+
+        formats = [{
+            'url': stream_base_url,
+            'play_path': stream['source'],
+            'ext': 'flv',
+            'tbr': float_or_none(stream.get('bitrate'), 1000),
+            'rtmp_real_time': True,
+        } for stream in video['streams']]
+        self._sort_formats(formats)
+
+        subtitles = {}
+        if video.get('hasSubtitle'):
+            subtitles = self.extract_subtitles(channel_id, video_id)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'formats': formats,
+            'subtitles': subtitles,
+        }

youtube_dl/extractor/krasview.py

@@ -40,8 +40,10 @@ class KrasViewIE(InfoExtractor):
         description = self._og_search_description(webpage, default=None)
         thumbnail = flashvars.get('image') or self._og_search_thumbnail(webpage)
         duration = int_or_none(flashvars.get('duration'))
-        width = int_or_none(self._og_search_property('video:width', webpage, 'video width'))
-        height = int_or_none(self._og_search_property('video:height', webpage, 'video height'))
+        width = int_or_none(self._og_search_property(
+            'video:width', webpage, 'video width', default=None))
+        height = int_or_none(self._og_search_property(
+            'video:height', webpage, 'video height', default=None))
 
         return {
             'id': video_id,

youtube_dl/extractor/letv.py

@@ -88,12 +88,13 @@ class LetvIE(InfoExtractor):
         play_json_req = compat_urllib_request.Request(
             'http://api.letv.com/mms/out/video/playJson?' + compat_urllib_parse.urlencode(params)
         )
-        play_json_req.add_header(
-            'Ytdl-request-proxy',
-            self._downloader.params.get('cn_verification_proxy'))
+        cn_verification_proxy = self._downloader.params.get('cn_verification_proxy')
+        if cn_verification_proxy:
+            play_json_req.add_header('Ytdl-request-proxy', cn_verification_proxy)
+
         play_json = self._download_json(
             play_json_req,
-            media_id, 'playJson data')
+            media_id, 'Downloading playJson data')
 
         # Check for errors
         playstatus = play_json['playstatus']

youtube_dl/extractor/libsyn.py

@@ -0,0 +1,59 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import unified_strdate
+
+
+class LibsynIE(InfoExtractor):
+    _VALID_URL = r'https?://html5-player\.libsyn\.com/embed/episode/id/(?P<id>[0-9]+)'
+
+    _TEST = {
+        'url': 'http://html5-player.libsyn.com/embed/episode/id/3377616/',
+        'md5': '443360ee1b58007bc3dcf09b41d093bb',
+        'info_dict': {
+            'id': '3377616',
+            'ext': 'mp3',
+            'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
+            'description': 'md5:601cb790edd05908957dae8aaa866465',
+            'upload_date': '20150220',
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        formats = [{
+            'url': media_url,
+        } for media_url in set(re.findall('var\s+mediaURL(?:Libsyn)?\s*=\s*"([^"]+)"', webpage))]
+
+        podcast_title = self._search_regex(
+            r'<h2>([^<]+)</h2>', webpage, 'title')
+        episode_title = self._search_regex(
+            r'<h3>([^<]+)</h3>', webpage, 'title', default=None)
+
+        title = '%s - %s' % (podcast_title, episode_title) if podcast_title else episode_title
+
+        description = self._html_search_regex(
+            r'<div id="info_text_body">(.+?)</div>', webpage,
+            'description', fatal=False)
+
+        thumbnail = self._search_regex(
+            r'<img[^>]+class="info-show-icon"[^>]+src="([^"]+)"',
+            webpage, 'thumbnail', fatal=False)
+
+        release_date = unified_strdate(self._search_regex(
+            r'<div class="release_date">Released: ([^<]+)<', webpage, 'release date', fatal=False))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'upload_date': release_date,
+            'formats': formats,
+        }

youtube_dl/extractor/livestream.py

@@ -2,6 +2,7 @@ from __future__ import unicode_literals
 
 import re
 import json
+import itertools
 
 from .common import InfoExtractor
 from ..compat import (
@@ -40,6 +41,13 @@ class LivestreamIE(InfoExtractor):
             'id': '2245590',
         },
         'playlist_mincount': 4,
+    }, {
+        'url': 'http://new.livestream.com/chess24/tatasteelchess',
+        'info_dict': {
+            'title': 'Tata Steel Chess',
+            'id': '3705884',
+        },
+        'playlist_mincount': 60,
     }, {
         'url': 'https://new.livestream.com/accounts/362/events/3557232/videos/67864563/player?autoPlay=false&height=360&mute=false&width=640',
         'only_matching': True,
@@ -117,6 +125,30 @@ class LivestreamIE(InfoExtractor):
             'view_count': video_data.get('views'),
         }
 
+    def _extract_event(self, info):
+        event_id = compat_str(info['id'])
+        account = compat_str(info['owner_account_id'])
+        root_url = (
+            'https://new.livestream.com/api/accounts/{account}/events/{event}/'
+            'feed.json'.format(account=account, event=event_id))
+
+        def _extract_videos():
+            last_video = None
+            for i in itertools.count(1):
+                if last_video is None:
+                    info_url = root_url
+                else:
+                    info_url = '{root}?&id={id}&newer=-1&type=video'.format(
+                        root=root_url, id=last_video)
+                videos_info = self._download_json(info_url, event_id, 'Downloading page {0}'.format(i))['data']
+                videos_info = [v['data'] for v in videos_info if v['type'] == 'video']
+                if not videos_info:
+                    break
+                for v in videos_info:
+                    yield self._extract_video_info(v)
+                last_video = videos_info[-1]['id']
+        return self.playlist_result(_extract_videos(), event_id, info['full_name'])
+
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
@@ -144,14 +176,13 @@ class LivestreamIE(InfoExtractor):
                 result = result and compat_str(vdata['data']['id']) == vid
             return result
 
-        videos = [self._extract_video_info(video_data['data'])
-                  for video_data in info['feed']['data']
-                  if is_relevant(video_data, video_id)]
         if video_id is None:
             # This is an event page:
-            return self.playlist_result(
-                videos, '%s' % info['id'], info['full_name'])
+            return self._extract_event(info)
         else:
+            videos = [self._extract_video_info(video_data['data'])
+                      for video_data in info['feed']['data']
+                      if is_relevant(video_data, video_id)]
             if not videos:
                 raise ExtractorError('Cannot find video %s' % video_id)
             return videos[0]

youtube_dl/extractor/mixcloud.py

@@ -1,6 +1,7 @@
 from __future__ import unicode_literals
 
 import re
+import itertools
 
 from .common import InfoExtractor
 from ..compat import (
@@ -10,7 +11,6 @@ from ..utils import (
     ExtractorError,
     HEADRequest,
     str_to_int,
-    parse_iso8601,
 )
 
 
@@ -27,8 +27,6 @@ class MixcloudIE(InfoExtractor):
             'description': 'After quite a long silence from myself, finally another Drum\'n\'Bass mix with my favourite current dance floor bangers.',
             'uploader': 'Daniel Holbach',
             'uploader_id': 'dholbach',
-            'upload_date': '20111115',
-            'timestamp': 1321359578,
             'thumbnail': 're:https?://.*\.jpg',
             'view_count': int,
             'like_count': int,
@@ -37,31 +35,30 @@ class MixcloudIE(InfoExtractor):
         'url': 'http://www.mixcloud.com/gillespeterson/caribou-7-inch-vinyl-mix-chat/',
         'info_dict': {
             'id': 'gillespeterson-caribou-7-inch-vinyl-mix-chat',
-            'ext': 'm4a',
-            'title': 'Electric Relaxation vol. 3',
+            'ext': 'mp3',
+            'title': 'Caribou 7 inch Vinyl Mix & Chat',
             'description': 'md5:2b8aec6adce69f9d41724647c65875e8',
-            'uploader': 'Daniel Drumz',
+            'uploader': 'Gilles Peterson Worldwide',
             'uploader_id': 'gillespeterson',
-            'thumbnail': 're:https?://.*\.jpg',
+            'thumbnail': 're:https?://.*/images/',
             'view_count': int,
             'like_count': int,
         },
     }]
 
-    def _get_url(self, track_id, template_url):
-        server_count = 30
-        for i in range(server_count):
-            url = template_url % i
+    def _get_url(self, track_id, template_url, server_number):
+        boundaries = (1, 30)
+        for nr in server_numbers(server_number, boundaries):
+            url = template_url % nr
             try:
                 # We only want to know if the request succeed
                 # don't download the whole file
                 self._request_webpage(
                     HEADRequest(url), track_id,
-                    'Checking URL %d/%d ...' % (i + 1, server_count + 1))
+                    'Checking URL %d/%d ...' % (nr, boundaries[-1]))
                 return url
             except ExtractorError:
                 pass
-
         return None
 
     def _real_extract(self, url):
@@ -75,17 +72,18 @@ class MixcloudIE(InfoExtractor):
         preview_url = self._search_regex(
             r'\s(?:data-preview-url|m-preview)="([^"]+)"', webpage, 'preview url')
         song_url = preview_url.replace('/previews/', '/c/originals/')
+        server_number = int(self._search_regex(r'stream(\d+)', song_url, 'server number'))
         template_url = re.sub(r'(stream\d*)', 'stream%d', song_url)
-        final_song_url = self._get_url(track_id, template_url)
+        final_song_url = self._get_url(track_id, template_url, server_number)
         if final_song_url is None:
             self.to_screen('Trying with m4a extension')
             template_url = template_url.replace('.mp3', '.m4a').replace('originals/', 'm4a/64/')
-            final_song_url = self._get_url(track_id, template_url)
+            final_song_url = self._get_url(track_id, template_url, server_number)
         if final_song_url is None:
             raise ExtractorError('Unable to extract track url')
 
         PREFIX = (
-            r'<span class="play-button[^"]*?"'
+            r'm-play-on-spacebar[^>]+'
             r'(?:\s+[a-zA-Z0-9-]+(?:="[^"]+")?)*?\s+')
         title = self._html_search_regex(
             PREFIX + r'm-title="([^"]+)"', webpage, 'title')
@@ -99,16 +97,12 @@ class MixcloudIE(InfoExtractor):
             r'\s+"profile": "([^"]+)",', webpage, 'uploader id', fatal=False)
         description = self._og_search_description(webpage)
         like_count = str_to_int(self._search_regex(
-            [r'<meta itemprop="interactionCount" content="UserLikes:([0-9]+)"',
-             r'/favorites/?">([0-9]+)<'],
+            r'\bbutton-favorite\b.+m-ajax-toggle-count="([^"]+)"',
             webpage, 'like count', fatal=False))
         view_count = str_to_int(self._search_regex(
             [r'<meta itemprop="interactionCount" content="UserPlays:([0-9]+)"',
              r'/listeners/?">([0-9,.]+)</a>'],
             webpage, 'play count', fatal=False))
-        timestamp = parse_iso8601(self._search_regex(
-            r'<time itemprop="dateCreated" datetime="([^"]+)">',
-            webpage, 'upload date', default=None))
 
         return {
             'id': track_id,
@@ -118,7 +112,38 @@ class MixcloudIE(InfoExtractor):
             'thumbnail': thumbnail,
             'uploader': uploader,
             'uploader_id': uploader_id,
-            'timestamp': timestamp,
             'view_count': view_count,
             'like_count': like_count,
         }
+
+
+def server_numbers(first, boundaries):
+    """ Server numbers to try in descending order of probable availability.
+    Starting from first (i.e. the number of the server hosting the preview file)
+    and going further and further up to the higher boundary and down to the
+    lower one in an alternating fashion. Namely:
+
+        server_numbers(2, (1, 5))
+
+        # Where the preview server is 2, min number is 1 and max is 5.
+        # Yields: 2, 3, 1, 4, 5
+
+    Why not random numbers or increasing sequences? Since from what I've seen,
+    full length files seem to be hosted on servers whose number is closer to
+    that of the preview; to be confirmed.
+    """
+    zip_longest = getattr(itertools, 'zip_longest', None)
+    if zip_longest is None:
+        # python 2.x
+        zip_longest = itertools.izip_longest
+
+    if len(boundaries) != 2:
+        raise ValueError("boundaries should be a two-element tuple")
+    min, max = boundaries
+    highs = range(first + 1, max + 1)
+    lows = range(first - 1, min - 1, -1)
+    rest = filter(
+        None, itertools.chain.from_iterable(zip_longest(highs, lows)))
+    yield first
+    for n in rest:
+        yield n

youtube_dl/extractor/mlb.py

@@ -10,7 +10,7 @@ from ..utils import (
 
 
 class MLBIE(InfoExtractor):
-    _VALID_URL = r'https?://m(?:lb)?\.mlb\.com/(?:(?:.*?/)?video/(?:topic/[\da-z_-]+/)?v|(?:shared/video/embed/embed\.html|[^/]+/video/play\.jsp)\?.*?\bcontent_id=)(?P<id>n?\d+)'
+    _VALID_URL = r'https?://m(?:lb)?\.(?:[\da-z_-]+\.)?mlb\.com/(?:(?:.*?/)?video/(?:topic/[\da-z_-]+/)?v|(?:shared/video/embed/embed\.html|[^/]+/video/play\.jsp)\?.*?\bcontent_id=)(?P<id>n?\d+)'
     _TESTS = [
         {
             'url': 'http://m.mlb.com/sea/video/topic/51231442/v34698933/nymsea-ackley-robs-a-home-run-with-an-amazing-catch/?c_id=sea',
@@ -80,6 +80,10 @@ class MLBIE(InfoExtractor):
             'url': 'http://mlb.mlb.com/es/video/play.jsp?content_id=36599553',
             'only_matching': True,
         },
+        {
+            'url': 'http://m.cardinals.mlb.com/stl/video/v51175783/atlstl-piscotty-makes-great-sliding-catch-on-line/?partnerId=as_mlb_20150321_42500876&adbid=579409712979910656&adbpl=tw&adbpr=52847728',
+            'only_matching': True,
+        }
     ]
 
     def _real_extract(self, url):

youtube_dl/extractor/niconico.py

@@ -22,7 +22,7 @@ class NiconicoIE(InfoExtractor):
     IE_NAME = 'niconico'
     IE_DESC = 'ニコニコ動画'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.nicovideo.jp/watch/sm22312215',
         'md5': 'd1a75c0823e2f629128c43e1212760f9',
         'info_dict': {
@@ -39,9 +39,26 @@ class NiconicoIE(InfoExtractor):
             'username': 'ydl.niconico@gmail.com',
             'password': 'youtube-dl',
         },
-    }
+    }, {
+        'url': 'http://www.nicovideo.jp/watch/nm14296458',
+        'md5': '8db08e0158457cf852a31519fceea5bc',
+        'info_dict': {
+            'id': 'nm14296458',
+            'ext': 'swf',
+            'title': '【鏡音リン】Dance on media【オリジナル】take2!',
+            'description': 'md5:',
+            'uploader': 'りょうた',
+            'uploader_id': '18822557',
+            'upload_date': '20110429',
+            'duration': 209,
+        },
+        'params': {
+            'username': 'ydl.niconico@gmail.com',
+            'password': 'youtube-dl',
+        },
+    }]
 
-    _VALID_URL = r'https?://(?:www\.|secure\.)?nicovideo\.jp/watch/((?:[a-z]{2})?[0-9]+)'
+    _VALID_URL = r'https?://(?:www\.|secure\.)?nicovideo\.jp/watch/(?P<id>(?:[a-z]{2})?[0-9]+)'
     _NETRC_MACHINE = 'niconico'
     # Determine whether the downloader used authentication to download video
     _AUTHENTICATED = False
@@ -76,8 +93,7 @@ class NiconicoIE(InfoExtractor):
         return True
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group(1)
+        video_id = self._match_id(url)
 
         # Get video webpage. We are not actually interested in it, but need
         # the cookies in order to be able to download the info webpage
@@ -90,7 +106,7 @@ class NiconicoIE(InfoExtractor):
         if self._AUTHENTICATED:
             # Get flv info
             flv_info_webpage = self._download_webpage(
-                'http://flapi.nicovideo.jp/api/getflv?v=' + video_id,
+                'http://flapi.nicovideo.jp/api/getflv/' + video_id + '?as3=1',
                 video_id, 'Downloading flv info')
         else:
             # Get external player info

youtube_dl/extractor/npo.py

@@ -219,7 +219,8 @@ class NPOLiveIE(NPOBaseIE):
         if streams:
             for stream in streams:
                 stream_type = stream.get('type').lower()
-                if stream_type == 'ss':
+                # smooth streaming is not supported
+                if stream_type in ['ss', 'ms']:
                     continue
                 stream_info = self._download_json(
                     'http://ida.omroep.nl/aapi/?stream=%s&token=%s&type=jsonp'
@@ -230,7 +231,10 @@ class NPOLiveIE(NPOBaseIE):
                 stream_url = self._download_json(
                     stream_info['stream'], display_id,
                     'Downloading %s URL' % stream_type,
-                    transform_source=strip_jsonp)
+                    'Unable to download %s URL' % stream_type,
+                    transform_source=strip_jsonp, fatal=False)
+                if not stream_url:
+                    continue
                 if stream_type == 'hds':
                     f4m_formats = self._extract_f4m_formats(stream_url, display_id)
                     # f4m downloader downloads only piece of live stream
@@ -242,6 +246,7 @@ class NPOLiveIE(NPOBaseIE):
                 else:
                     formats.append({
                         'url': stream_url,
+                        'preference': -10,
                     })
 
         self._sort_formats(formats)

youtube_dl/extractor/nrk.py

@@ -14,46 +14,48 @@ from ..utils import (
 
 
 class NRKIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?nrk\.no/(?:video|lyd)/[^/]+/(?P<id>[\dA-F]{16})'
+    _VALID_URL = r'(?:nrk:|http://(?:www\.)?nrk\.no/video/PS\*)(?P<id>\d+)'
 
     _TESTS = [
         {
-            'url': 'http://www.nrk.no/video/dompap_og_andre_fugler_i_piip_show/D0FA54B5C8B6CE59/emne/piipshow/',
-            'md5': 'a6eac35052f3b242bb6bb7f43aed5886',
+            'url': 'http://www.nrk.no/video/PS*150533',
+            'md5': 'bccd850baebefe23b56d708a113229c2',
             'info_dict': {
                 'id': '150533',
                 'ext': 'flv',
                 'title': 'Dompap og andre fugler i Piip-Show',
-                'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f'
+                'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f',
+                'duration': 263,
             }
         },
         {
-            'url': 'http://www.nrk.no/lyd/lyd_av_oppleser_for_blinde/AEFDDD5473BA0198/',
-            'md5': '3471f2a51718195164e88f46bf427668',
+            'url': 'http://www.nrk.no/video/PS*154915',
+            'md5': '0b1493ba1aae7d9579a5ad5531bc395a',
             'info_dict': {
                 'id': '154915',
                 'ext': 'flv',
                 'title': 'Slik høres internett ut når du er blind',
                 'description': 'md5:a621f5cc1bd75c8d5104cb048c6b8568',
+                'duration': 20,
             }
         },
     ]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-
-        page = self._download_webpage(url, video_id)
-
-        video_id = self._html_search_regex(r'<div class="nrk-video" data-nrk-id="(\d+)">', page, 'video id')
+        video_id = self._match_id(url)
 
         data = self._download_json(
-            'http://v7.psapi.nrk.no/mediaelement/%s' % video_id, video_id, 'Downloading media JSON')
+            'http://v8.psapi.nrk.no/mediaelement/%s' % video_id,
+            video_id, 'Downloading media JSON')
 
         if data['usageRights']['isGeoBlocked']:
-            raise ExtractorError('NRK har ikke rettig-heter til å vise dette programmet utenfor Norge', expected=True)
+            raise ExtractorError(
+                'NRK har ikke rettig-heter til å vise dette programmet utenfor Norge',
+                expected=True)
 
-        video_url = data['mediaUrl'] + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124'
+        video_url = data['mediaUrl'] + '?hdcore=3.5.0&plugin=aasp-3.5.0.151.81'
+
+        duration = parse_duration(data.get('duration'))
 
         images = data.get('images')
         if images:
@@ -69,10 +71,51 @@ class NRKIE(InfoExtractor):
             'ext': 'flv',
             'title': data['title'],
             'description': data['description'],
+            'duration': duration,
             'thumbnail': thumbnail,
         }
 
 
+class NRKPlaylistIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?nrk\.no/(?!video)(?:[^/]+/)+(?P<id>[^/]+)'
+
+    _TESTS = [{
+        'url': 'http://www.nrk.no/troms/gjenopplev-den-historiske-solformorkelsen-1.12270763',
+        'info_dict': {
+            'id': 'gjenopplev-den-historiske-solformorkelsen-1.12270763',
+            'title': 'Gjenopplev den historiske solformørkelsen',
+            'description': 'md5:c2df8ea3bac5654a26fc2834a542feed',
+        },
+        'playlist_count': 2,
+    }, {
+        'url': 'http://www.nrk.no/kultur/bok/rivertonprisen-til-karin-fossum-1.12266449',
+        'info_dict': {
+            'id': 'rivertonprisen-til-karin-fossum-1.12266449',
+            'title': 'Rivertonprisen til Karin Fossum',
+            'description': 'Første kvinne på 15 år til å vinne krimlitteraturprisen.',
+        },
+        'playlist_count': 5,
+    }]
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, playlist_id)
+
+        entries = [
+            self.url_result('nrk:%s' % video_id, 'NRK')
+            for video_id in re.findall(
+                r'class="[^"]*\brich\b[^"]*"[^>]+data-video-id="([^"]+)"',
+                webpage)
+        ]
+
+        playlist_title = self._og_search_title(webpage)
+        playlist_description = self._og_search_description(webpage)
+
+        return self.playlist_result(
+            entries, playlist_id, playlist_title, playlist_description)
+
+
 class NRKTVIE(InfoExtractor):
     _VALID_URL = r'(?P<baseurl>http://tv\.nrk(?:super)?\.no/)(?:serie/[^/]+|program)/(?P<id>[a-zA-Z]{4}\d{8})(?:/\d{2}-\d{2}-\d{4})?(?:#del=(?P<part_id>\d+))?'
 
@@ -149,9 +192,6 @@ class NRKTVIE(InfoExtractor):
         }
     ]
 
-    def _seconds2str(self, s):
-        return '%02d:%02d:%02d.%03d' % (s / 3600, (s % 3600) / 60, s % 60, (s % 1) * 1000)
-
     def _debug_print(self, txt):
         if self._downloader.params.get('verbose', False):
             self.to_screen('[debug] %s' % txt)
@@ -168,8 +208,8 @@ class NRKTVIE(InfoExtractor):
         for pos, p in enumerate(ps):
             begin = parse_duration(p.get('begin'))
             duration = parse_duration(p.get('dur'))
-            starttime = self._seconds2str(begin)
-            endtime = self._seconds2str(begin + duration)
+            starttime = self._subtitles_timecode(begin)
+            endtime = self._subtitles_timecode(begin + duration)
             srt += '%s\r\n%s --> %s\r\n%s\r\n\r\n' % (compat_str(pos), starttime, endtime, p.text)
         return {lang: [
             {'ext': 'ttml', 'url': url},

youtube_dl/extractor/nytimes.py

@@ -1,15 +1,17 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
-from ..utils import parse_iso8601
+from ..utils import (
+    float_or_none,
+    int_or_none,
+    parse_iso8601,
+)
 
 
 class NYTimesIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?nytimes\.com/video/(?:[^/]+/)+(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:(?:www\.)?nytimes\.com/video/(?:[^/]+/)+?|graphics8\.nytimes\.com/bcvideo/\d+(?:\.\d+)?/iframe/embed\.html\?videoId=)(?P<id>\d+)'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.nytimes.com/video/opinion/100000002847155/verbatim-what-is-a-photocopier.html?playlistId=100000001150263',
         'md5': '18a525a510f942ada2720db5f31644c0',
         'info_dict': {
@@ -22,18 +24,21 @@ class NYTimesIE(InfoExtractor):
             'uploader': 'Brett Weiner',
             'duration': 419,
         }
-    }
+    }, {
+        'url': 'http://www.nytimes.com/video/travel/100000003550828/36-hours-in-dubai.html',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
 
         video_data = self._download_json(
-            'http://www.nytimes.com/svc/video/api/v2/video/%s' % video_id, video_id, 'Downloading video JSON')
+            'http://www.nytimes.com/svc/video/api/v2/video/%s' % video_id,
+            video_id, 'Downloading video JSON')
 
         title = video_data['headline']
-        description = video_data['summary']
-        duration = video_data['duration'] / 1000.0
+        description = video_data.get('summary')
+        duration = float_or_none(video_data.get('duration'), 1000)
 
         uploader = video_data['byline']
         timestamp = parse_iso8601(video_data['publication_date'][:-8])
@@ -49,11 +54,11 @@ class NYTimesIE(InfoExtractor):
         formats = [
             {
                 'url': video['url'],
-                'format_id': video['type'],
-                'vcodec': video['video_codec'],
-                'width': video['width'],
-                'height': video['height'],
-                'filesize': get_file_size(video['fileSize']),
+                'format_id': video.get('type'),
+                'vcodec': video.get('video_codec'),
+                'width': int_or_none(video.get('width')),
+                'height': int_or_none(video.get('height')),
+                'filesize': get_file_size(video.get('fileSize')),
             } for video in video_data['renditions']
         ]
         self._sort_formats(formats)
@@ -61,7 +66,8 @@ class NYTimesIE(InfoExtractor):
         thumbnails = [
             {
                 'url': 'http://www.nytimes.com/%s' % image['url'],
-                'resolution': '%dx%d' % (image['width'], image['height']),
+                'width': int_or_none(image.get('width')),
+                'height': int_or_none(image.get('height')),
             } for image in video_data['images']
         ]
 

youtube_dl/extractor/primesharetv.py

@@ -0,0 +1,69 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import (
+    compat_urllib_parse,
+    compat_urllib_request,
+)
+from ..utils import ExtractorError
+
+
+class PrimeShareTVIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?primeshare\.tv/download/(?P<id>[\da-zA-Z]+)'
+
+    _TEST = {
+        'url': 'http://primeshare.tv/download/238790B611',
+        'md5': 'b92d9bf5461137c36228009f31533fbc',
+        'info_dict': {
+            'id': '238790B611',
+            'ext': 'mp4',
+            'title': 'Public Domain - 1960s Commercial - Crest Toothpaste-YKsuFona',
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        if '>File not exist<' in webpage:
+            raise ExtractorError('Video %s does not exist' % video_id, expected=True)
+
+        fields = dict(re.findall(r'''(?x)<input\s+
+            type="hidden"\s+
+            name="([^"]+)"\s+
+            (?:id="[^"]+"\s+)?
+            value="([^"]*)"
+            ''', webpage))
+
+        headers = {
+            'Referer': url,
+            'Content-Type': 'application/x-www-form-urlencoded',
+        }
+
+        wait_time = int(self._search_regex(
+            r'var\s+cWaitTime\s*=\s*(\d+)',
+            webpage, 'wait time', default=7)) + 1
+        self._sleep(wait_time, video_id)
+
+        req = compat_urllib_request.Request(
+            url, compat_urllib_parse.urlencode(fields), headers)
+        video_page = self._download_webpage(
+            req, video_id, 'Downloading video page')
+
+        video_url = self._search_regex(
+            r"url\s*:\s*'([^']+\.primeshare\.tv(?::443)?/file/[^']+)'",
+            video_page, 'video url')
+
+        title = self._html_search_regex(
+            r'<h1>Watch\s*(?:&nbsp;)?\s*\((.+?)(?:\s*\[\.\.\.\])?\)\s*(?:&nbsp;)?\s*<strong>',
+            video_page, 'title')
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': title,
+            'ext': 'mp4',
+        }

youtube_dl/extractor/rtve.py

@@ -127,6 +127,47 @@ class RTVEALaCartaIE(InfoExtractor):
             for s in subs)
 
 
+class RTVEInfantilIE(InfoExtractor):
+    IE_NAME = 'rtve.es:infantil'
+    IE_DESC = 'RTVE infantil'
+    _VALID_URL = r'https?://(?:www\.)?rtve\.es/infantil/serie/(?P<show>[^/]*)/video/(?P<short_title>[^/]*)/(?P<id>[0-9]+)/'
+
+    _TESTS = [{
+        'url': 'http://www.rtve.es/infantil/serie/cleo/video/maneras-vivir/3040283/',
+        'md5': '915319587b33720b8e0357caaa6617e6',
+        'info_dict': {
+            'id': '3040283',
+            'ext': 'mp4',
+            'title': 'Maneras de vivir',
+            'thumbnail': 'http://www.rtve.es/resources/jpg/6/5/1426182947956.JPG',
+            'duration': 357.958,
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        info = self._download_json(
+            'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id,
+            video_id)['page']['items'][0]
+
+        webpage = self._download_webpage(url, video_id)
+        vidplayer_id = self._search_regex(
+            r' id="vidplayer([0-9]+)"', webpage, 'internal video ID')
+
+        png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/default/videos/%s.png' % vidplayer_id
+        png = self._download_webpage(png_url, video_id, 'Downloading url information')
+        video_url = _decrypt_url(png)
+
+        return {
+            'id': video_id,
+            'ext': 'mp4',
+            'title': info['title'],
+            'url': video_url,
+            'thumbnail': info.get('image'),
+            'duration': float_or_none(info.get('duration'), scale=1000),
+        }
+
+
 class RTVELiveIE(InfoExtractor):
     IE_NAME = 'rtve.es:live'
     IE_DESC = 'RTVE.es live streams'

youtube_dl/extractor/sohu.py

@@ -4,22 +4,87 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from .common import compat_str
+from ..compat import (
+    compat_str,
+    compat_urllib_request
+)
+from ..utils import sanitize_url_path_consecutive_slashes
 
 
 class SohuIE(InfoExtractor):
     _VALID_URL = r'https?://(?P<mytv>my\.)?tv\.sohu\.com/.+?/(?(mytv)|n)(?P<id>\d+)\.shtml.*?'
 
-    _TEST = {
+    _TESTS = [{
+        'note': 'This video is available only in Mainland China',
         'url': 'http://tv.sohu.com/20130724/n382479172.shtml#super',
-        'md5': 'bde8d9a6ffd82c63a1eefaef4eeefec7',
+        'md5': '29175c8cadd8b5cc4055001e85d6b372',
         'info_dict': {
             'id': '382479172',
             'ext': 'mp4',
             'title': 'MV：Far East Movement《The Illest》',
         },
-        'skip': 'Only available from China',
-    }
+        'params': {
+            'cn_verification_proxy': 'proxy.uku.im:8888'
+        }
+    }, {
+        'url': 'http://tv.sohu.com/20150305/n409385080.shtml',
+        'md5': '699060e75cf58858dd47fb9c03c42cfb',
+        'info_dict': {
+            'id': '409385080',
+            'ext': 'mp4',
+            'title': '《2015湖南卫视羊年元宵晚会》唐嫣《花好月圆》',
+        }
+    }, {
+        'url': 'http://my.tv.sohu.com/us/232799889/78693464.shtml',
+        'md5': '9bf34be48f2f4dadcb226c74127e203c',
+        'info_dict': {
+            'id': '78693464',
+            'ext': 'mp4',
+            'title': '【爱范品】第31期：MWC见不到的奇葩手机',
+        }
+    }, {
+        'note': 'Multipart video',
+        'url': 'http://my.tv.sohu.com/pl/8384802/78910339.shtml',
+        'info_dict': {
+            'id': '78910339',
+        },
+        'playlist': [{
+            'md5': 'bdbfb8f39924725e6589c146bc1883ad',
+            'info_dict': {
+                'id': '78910339_part1',
+                'ext': 'mp4',
+                'duration': 294,
+                'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
+            }
+        }, {
+            'md5': '3e1f46aaeb95354fd10e7fca9fc1804e',
+            'info_dict': {
+                'id': '78910339_part2',
+                'ext': 'mp4',
+                'duration': 300,
+                'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
+            }
+        }, {
+            'md5': '8407e634175fdac706766481b9443450',
+            'info_dict': {
+                'id': '78910339_part3',
+                'ext': 'mp4',
+                'duration': 150,
+                'title': '【神探苍实战秘籍】第13期 战争之影 赫卡里姆',
+            }
+        }]
+    }, {
+        'note': 'Video with title containing dash',
+        'url': 'http://my.tv.sohu.com/us/249884221/78932792.shtml',
+        'info_dict': {
+            'id': '78932792',
+            'ext': 'mp4',
+            'title': 'youtube-dl testing video',
+        },
+        'params': {
+            'skip_download': True
+        }
+    }]
 
     def _real_extract(self, url):
 
@@ -29,8 +94,14 @@ class SohuIE(InfoExtractor):
             else:
                 base_data_url = 'http://hot.vrs.sohu.com/vrs_flash.action?vid='
 
+            req = compat_urllib_request.Request(base_data_url + vid_id)
+
+            cn_verification_proxy = self._downloader.params.get('cn_verification_proxy')
+            if cn_verification_proxy:
+                req.add_header('Ytdl-request-proxy', cn_verification_proxy)
+
             return self._download_json(
-                base_data_url + vid_id, video_id,
+                req, video_id,
                 'Downloading JSON data for %s' % vid_id)
 
         mobj = re.match(self._VALID_URL, url)
@@ -38,10 +109,8 @@ class SohuIE(InfoExtractor):
         mytv = mobj.group('mytv') is not None
 
         webpage = self._download_webpage(url, video_id)
-        raw_title = self._html_search_regex(
-            r'(?s)<title>(.+?)</title>',
-            webpage, 'video title')
-        title = raw_title.partition('-')[0].strip()
+
+        title = self._og_search_title(webpage)
 
         vid = self._html_search_regex(
             r'var vid ?= ?["\'](\d+)["\']',
@@ -77,7 +146,9 @@ class SohuIE(InfoExtractor):
                     % (format_id, i + 1, part_count))
 
                 part_info = part_str.split('|')
-                video_url = '%s%s?key=%s' % (part_info[0], su[i], part_info[3])
+
+                video_url = sanitize_url_path_consecutive_slashes(
+                    '%s%s?key=%s' % (part_info[0], su[i], part_info[3]))
 
                 formats.append({
                     'url': video_url,

youtube_dl/extractor/ssa.py

@@ -0,0 +1,58 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    unescapeHTML,
+    parse_duration,
+)
+
+
+class SSAIE(InfoExtractor):
+    _VALID_URL = r'http://ssa\.nls\.uk/film/(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://ssa.nls.uk/film/3561',
+        'info_dict': {
+            'id': '3561',
+            'ext': 'flv',
+            'title': 'SHETLAND WOOL',
+            'description': 'md5:c5afca6871ad59b4271e7704fe50ab04',
+            'duration': 900,
+            'thumbnail': 're:^https?://.*\.jpg$',
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        streamer = self._search_regex(
+            r"'streamer'\s*,\S*'(rtmp[^']+)'", webpage, 'streamer')
+        play_path = self._search_regex(
+            r"'file'\s*,\s*'([^']+)'", webpage, 'file').rpartition('.')[0]
+
+        def search_field(field_name, fatal=False):
+            return self._search_regex(
+                r'<span\s+class="field_title">%s:</span>\s*<span\s+class="field_content">([^<]+)</span>' % field_name,
+                webpage, 'title', fatal=fatal)
+
+        title = unescapeHTML(search_field('Title', fatal=True)).strip('()[]')
+        description = unescapeHTML(search_field('Description'))
+        duration = parse_duration(search_field('Running time'))
+        thumbnail = self._search_regex(
+            r"'image'\s*,\s*'([^']+)'", webpage, 'thumbnails', fatal=False)
+
+        return {
+            'id': video_id,
+            'url': streamer,
+            'play_path': play_path,
+            'ext': 'flv',
+            'title': title,
+            'description': description,
+            'duration': duration,
+            'thumbnail': thumbnail,
+        }

youtube_dl/extractor/twitch.py

@@ -23,6 +23,7 @@ class TwitchBaseIE(InfoExtractor):
     _API_BASE = 'https://api.twitch.tv'
     _USHER_BASE = 'http://usher.twitch.tv'
     _LOGIN_URL = 'https://secure.twitch.tv/user/login'
+    _LOGIN_POST_URL = 'https://secure-login.twitch.tv/login'
     _NETRC_MACHINE = 'twitch'
 
     def _handle_error(self, response):
@@ -67,14 +68,14 @@ class TwitchBaseIE(InfoExtractor):
             'authenticity_token': authenticity_token,
             'redirect_on_login': '',
             'embed_form': 'false',
-            'mp_source_action': '',
+            'mp_source_action': 'login-button',
             'follow': '',
-            'user[login]': username,
-            'user[password]': password,
+            'login': username,
+            'password': password,
         }
 
         request = compat_urllib_request.Request(
-            self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
+            self._LOGIN_POST_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
         request.add_header('Referer', self._LOGIN_URL)
         response = self._download_webpage(
             request, None, 'Logging in as %s' % username)
@@ -148,7 +149,7 @@ class TwitchItemBaseIE(TwitchBaseIE):
 
 class TwitchVideoIE(TwitchItemBaseIE):
     IE_NAME = 'twitch:video'
-    _VALID_URL = r'%s/[^/]+/b/(?P<id>[^/]+)' % TwitchBaseIE._VALID_URL_BASE
+    _VALID_URL = r'%s/[^/]+/b/(?P<id>\d+)' % TwitchBaseIE._VALID_URL_BASE
     _ITEM_TYPE = 'video'
     _ITEM_SHORTCUT = 'a'
 
@@ -164,7 +165,7 @@ class TwitchVideoIE(TwitchItemBaseIE):
 
 class TwitchChapterIE(TwitchItemBaseIE):
     IE_NAME = 'twitch:chapter'
-    _VALID_URL = r'%s/[^/]+/c/(?P<id>[^/]+)' % TwitchBaseIE._VALID_URL_BASE
+    _VALID_URL = r'%s/[^/]+/c/(?P<id>\d+)' % TwitchBaseIE._VALID_URL_BASE
     _ITEM_TYPE = 'chapter'
     _ITEM_SHORTCUT = 'c'
 
@@ -183,7 +184,7 @@ class TwitchChapterIE(TwitchItemBaseIE):
 
 class TwitchVodIE(TwitchItemBaseIE):
     IE_NAME = 'twitch:vod'
-    _VALID_URL = r'%s/[^/]+/v/(?P<id>[^/]+)' % TwitchBaseIE._VALID_URL_BASE
+    _VALID_URL = r'%s/[^/]+/v/(?P<id>\d+)' % TwitchBaseIE._VALID_URL_BASE
     _ITEM_TYPE = 'vod'
     _ITEM_SHORTCUT = 'v'
 

youtube_dl/extractor/ultimedia.py

@@ -0,0 +1,104 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    qualities,
+    unified_strdate,
+    clean_html,
+)
+
+
+class UltimediaIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?ultimedia\.com/default/index/video[^/]+/id/(?P<id>[\d+a-z]+)'
+    _TESTS = [{
+        # news
+        'url': 'https://www.ultimedia.com/default/index/videogeneric/id/s8uk0r',
+        'md5': '276a0e49de58c7e85d32b057837952a2',
+        'info_dict': {
+            'id': 's8uk0r',
+            'ext': 'mp4',
+            'title': 'Loi sur la fin de vie: le texte prévoit un renforcement des directives anticipées',
+            'description': 'md5:3e5c8fd65791487333dda5db8aed32af',
+            'thumbnail': 're:^https?://.*\.jpg',
+            'upload_date': '20150317',
+        },
+    }, {
+        # music
+        'url': 'https://www.ultimedia.com/default/index/videomusic/id/xvpfp8',
+        'md5': '2ea3513813cf230605c7e2ffe7eca61c',
+        'info_dict': {
+            'id': 'xvpfp8',
+            'ext': 'mp4',
+            'title': "Two - C'est la vie (Clip)",
+            'description': 'Two',
+            'thumbnail': 're:^https?://.*\.jpg',
+            'upload_date': '20150224',
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        deliver_url = self._search_regex(
+            r'<iframe[^>]+src="(https?://(?:www\.)?ultimedia\.com/deliver/[^"]+)"',
+            webpage, 'deliver URL')
+
+        deliver_page = self._download_webpage(
+            deliver_url, video_id, 'Downloading iframe page')
+
+        if '>This video is currently not available' in deliver_page:
+            raise ExtractorError(
+                'Video %s is currently not available' % video_id, expected=True)
+
+        player = self._parse_json(
+            self._search_regex(
+                r"jwplayer\('player(?:_temp)?'\)\.setup\(({.+?})\)\.on", deliver_page, 'player'),
+            video_id)
+
+        quality = qualities(['flash', 'html5'])
+        formats = []
+        for mode in player['modes']:
+            video_url = mode.get('config', {}).get('file')
+            if not video_url:
+                continue
+            if re.match(r'https?://www\.youtube\.com/.+?', video_url):
+                return self.url_result(video_url, 'Youtube')
+            formats.append({
+                'url': video_url,
+                'format_id': mode.get('type'),
+                'quality': quality(mode.get('type')),
+            })
+        self._sort_formats(formats)
+
+        thumbnail = player.get('image')
+
+        title = clean_html((
+            self._html_search_regex(
+                r'(?s)<div\s+id="catArticle">.+?</div>(.+?)</h1>',
+                webpage, 'title', default=None)
+            or self._search_regex(
+                r"var\s+nameVideo\s*=\s*'([^']+)'",
+                deliver_page, 'title')))
+
+        description = clean_html(self._html_search_regex(
+            r'(?s)<span>Description</span>(.+?)</p>', webpage,
+            'description', fatal=False))
+
+        upload_date = unified_strdate(self._search_regex(
+            r'Ajouté le\s*<span>([^<]+)', webpage,
+            'upload date', fatal=False))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'upload_date': upload_date,
+            'formats': formats,
+        }

youtube_dl/extractor/videomega.py

@@ -4,28 +4,21 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import (
-    compat_urllib_parse,
-    compat_urllib_request,
-)
-from ..utils import (
-    ExtractorError,
-    remove_start,
-)
+from ..compat import compat_urllib_request
 
 
 class VideoMegaIE(InfoExtractor):
     _VALID_URL = r'''(?x)https?://
         (?:www\.)?videomega\.tv/
-        (?:iframe\.php)?\?ref=(?P<id>[A-Za-z0-9]+)
+        (?:iframe\.php|cdn\.php)?\?ref=(?P<id>[A-Za-z0-9]+)
         '''
     _TEST = {
-        'url': 'http://videomega.tv/?ref=QR0HCUHI1661IHUCH0RQ',
+        'url': 'http://videomega.tv/?ref=4GNA688SU99US886ANG4',
         'md5': 'bf5c2f95c4c917536e80936af7bc51e1',
         'info_dict': {
-            'id': 'QR0HCUHI1661IHUCH0RQ',
+            'id': '4GNA688SU99US886ANG4',
             'ext': 'mp4',
-            'title': 'Big Buck Bunny',
+            'title': 'BigBuckBunny_320x180',
             'thumbnail': 're:^https?://.*\.jpg$',
         }
     }
@@ -33,34 +26,24 @@ class VideoMegaIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        iframe_url = 'http://videomega.tv/iframe.php?ref={0:}'.format(video_id)
+        iframe_url = 'http://videomega.tv/cdn.php?ref=%s' % video_id
         req = compat_urllib_request.Request(iframe_url)
         req.add_header('Referer', url)
         webpage = self._download_webpage(req, video_id)
 
-        try:
-            escaped_data = re.findall(r'unescape\("([^"]+)"\)', webpage)[-1]
-        except IndexError:
-            raise ExtractorError('Unable to extract escaped data')
-
-        playlist = compat_urllib_parse.unquote(escaped_data)
-
+        title = self._html_search_regex(
+            r'<title>(.*?)</title>', webpage, 'title')
+        title = re.sub(
+            r'(?:^[Vv]ideo[Mm]ega\.tv\s-\s?|\s?-\svideomega\.tv$)', '', title)
         thumbnail = self._search_regex(
-            r'image:\s*"([^"]+)"', playlist, 'thumbnail', fatal=False)
-        video_url = self._search_regex(r'file:\s*"([^"]+)"', playlist, 'URL')
-        title = remove_start(self._html_search_regex(
-            r'<title>(.*?)</title>', webpage, 'title'), 'VideoMega.tv - ')
-
-        formats = [{
-            'format_id': 'sd',
-            'url': video_url,
-        }]
-        self._sort_formats(formats)
+            r'<video[^>]+?poster="([^"]+)"', webpage, 'thumbnail', fatal=False)
+        video_url = self._search_regex(
+            r'<source[^>]+?src="([^"]+)"', webpage, 'video URL')
 
         return {
             'id': video_id,
             'title': title,
-            'formats': formats,
+            'url': video_url,
             'thumbnail': thumbnail,
             'http_headers': {
                 'Referer': iframe_url,

youtube_dl/extractor/viewster.py

@@ -0,0 +1,129 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import compat_urllib_request
+
+
+class ViewsterIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?viewster\.com/movie/(?P<id>\d+-\d+-\d+)'
+    _TESTS = [{
+        # movielink, paymethod=fre
+        'url': 'http://www.viewster.com/movie/1293-19341-000/hout-wood/',
+        'playlist': [{
+            'md5': '8f9d94b282d80c42b378dffdbb11caf3',
+            'info_dict': {
+                'id': '1293-19341-000-movie',
+                'ext': 'flv',
+                'title': "'Hout' (Wood) - Movie",
+            },
+        }],
+        'info_dict': {
+            'id': '1293-19341-000',
+            'title': "'Hout' (Wood)",
+            'description': 'md5:925733185a9242ef96f436937683f33b',
+        }
+    }, {
+        # movielink, paymethod=adv
+        'url': 'http://www.viewster.com/movie/1140-11855-000/the-listening-project/',
+        'playlist': [{
+            'md5': '77a005453ca7396cbe3d35c9bea30aef',
+            'info_dict': {
+                'id': '1140-11855-000-movie',
+                'ext': 'flv',
+                'title': "THE LISTENING PROJECT - Movie",
+            },
+        }],
+        'info_dict': {
+            'id': '1140-11855-000',
+            'title': "THE LISTENING PROJECT",
+            'description': 'md5:714421ae9957e112e672551094bf3b08',
+        }
+    }, {
+        # direct links, no movielink
+        'url': 'http://www.viewster.com/movie/1198-56411-000/sinister/',
+        'playlist': [{
+            'md5': '0307b7eac6bfb21ab0577a71f6eebd8f',
+            'info_dict': {
+                'id': '1198-56411-000-trailer',
+                'ext': 'mp4',
+                'title': "Sinister - Trailer",
+            },
+        }, {
+            'md5': '80b9ee3ad69fb368f104cb5d9732ae95',
+            'info_dict': {
+                'id': '1198-56411-000-behind-scenes',
+                'ext': 'mp4',
+                'title': "Sinister - Behind Scenes",
+            },
+        }, {
+            'md5': '3b3ea897ecaa91fca57a8a94ac1b15c5',
+            'info_dict': {
+                'id': '1198-56411-000-scene-from-movie',
+                'ext': 'mp4',
+                'title': "Sinister - Scene from movie",
+            },
+        }],
+        'info_dict': {
+            'id': '1198-56411-000',
+            'title': "Sinister",
+            'description': 'md5:014c40b0488848de9683566a42e33372',
+        }
+    }]
+
+    _ACCEPT_HEADER = 'application/json, text/javascript, */*; q=0.01'
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        request = compat_urllib_request.Request(
+            'http://api.live.viewster.com/api/v1/movie/%s' % video_id)
+        request.add_header('Accept', self._ACCEPT_HEADER)
+
+        movie = self._download_json(
+            request, video_id, 'Downloading movie metadata JSON')
+
+        title = movie.get('title') or movie['original_title']
+        description = movie.get('synopsis')
+        thumbnail = movie.get('large_artwork') or movie.get('artwork')
+
+        entries = []
+        for clip in movie['play_list']:
+            entry = None
+
+            # movielink api
+            link_request = clip.get('link_request')
+            if link_request:
+                request = compat_urllib_request.Request(
+                    'http://api.live.viewster.com/api/v1/movielink?movieid=%(movieid)s&action=%(action)s&paymethod=%(paymethod)s&price=%(price)s&currency=%(currency)s&language=%(language)s&subtitlelanguage=%(subtitlelanguage)s&ischromecast=%(ischromecast)s'
+                    % link_request)
+                request.add_header('Accept', self._ACCEPT_HEADER)
+
+                movie_link = self._download_json(
+                    request, video_id, 'Downloading movie link JSON', fatal=False)
+
+                if movie_link:
+                    formats = self._extract_f4m_formats(
+                        movie_link['url'] + '&hdcore=3.2.0&plugin=flowplayer-3.2.0.1', video_id)
+                    self._sort_formats(formats)
+                    entry = {
+                        'formats': formats,
+                    }
+
+            # direct link
+            clip_url = clip.get('clip_data', {}).get('url')
+            if clip_url:
+                entry = {
+                    'url': clip_url,
+                    'ext': 'mp4',
+                }
+
+            if entry:
+                entry.update({
+                    'id': '%s-%s' % (video_id, clip['canonical_title']),
+                    'title': '%s - %s' % (title, clip['title']),
+                })
+                entries.append(entry)
+
+        playlist = self.playlist_result(entries, video_id, title, description)
+        playlist['thumbnail'] = thumbnail
+        return playlist

youtube_dl/extractor/vimeo.py

@@ -38,7 +38,7 @@ class VimeoBaseInfoExtractor(InfoExtractor):
         self.report_login()
         login_url = 'https://vimeo.com/log_in'
         webpage = self._download_webpage(login_url, None, False)
-        token = self._search_regex(r'xsrft: \'(.*?)\'', webpage, 'login token')
+        token = self._search_regex(r'xsrft = \'(.*?)\'', webpage, 'login token')
         data = urlencode_postdata({
             'email': username,
             'password': password,
@@ -373,7 +373,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
             for tt in text_tracks:
                 subtitles[tt['lang']] = [{
                     'ext': 'vtt',
-                    'url': 'http://vimeo.com' + tt['url'],
+                    'url': 'https://vimeo.com' + tt['url'],
                 }]
 
         return {
@@ -396,11 +396,11 @@ class VimeoIE(VimeoBaseInfoExtractor):
 
 class VimeoChannelIE(InfoExtractor):
     IE_NAME = 'vimeo:channel'
-    _VALID_URL = r'https?://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
+    _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
     _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
     _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
     _TESTS = [{
-        'url': 'http://vimeo.com/channels/tributes',
+        'url': 'https://vimeo.com/channels/tributes',
         'info_dict': {
             'id': 'tributes',
             'title': 'Vimeo Tributes',
@@ -459,7 +459,7 @@ class VimeoChannelIE(InfoExtractor):
             if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
                 break
 
-        entries = [self.url_result('http://vimeo.com/%s' % video_id, 'Vimeo')
+        entries = [self.url_result('https://vimeo.com/%s' % video_id, 'Vimeo')
                    for video_id in video_ids]
         return {'_type': 'playlist',
                 'id': list_id,
@@ -470,15 +470,15 @@ class VimeoChannelIE(InfoExtractor):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         channel_id = mobj.group('id')
-        return self._extract_videos(channel_id, 'http://vimeo.com/channels/%s' % channel_id)
+        return self._extract_videos(channel_id, 'https://vimeo.com/channels/%s' % channel_id)
 
 
 class VimeoUserIE(VimeoChannelIE):
     IE_NAME = 'vimeo:user'
-    _VALID_URL = r'https?://vimeo\.com/(?![0-9]+(?:$|[?#/]))(?P<name>[^/]+)(?:/videos|[#?]|$)'
+    _VALID_URL = r'https://vimeo\.com/(?![0-9]+(?:$|[?#/]))(?P<name>[^/]+)(?:/videos|[#?]|$)'
     _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
     _TESTS = [{
-        'url': 'http://vimeo.com/nkistudio/videos',
+        'url': 'https://vimeo.com/nkistudio/videos',
         'info_dict': {
             'title': 'Nki',
             'id': 'nkistudio',
@@ -489,7 +489,7 @@ class VimeoUserIE(VimeoChannelIE):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         name = mobj.group('name')
-        return self._extract_videos(name, 'http://vimeo.com/%s' % name)
+        return self._extract_videos(name, 'https://vimeo.com/%s' % name)
 
 
 class VimeoAlbumIE(VimeoChannelIE):
@@ -526,9 +526,9 @@ class VimeoAlbumIE(VimeoChannelIE):
 
 class VimeoGroupsIE(VimeoAlbumIE):
     IE_NAME = 'vimeo:group'
-    _VALID_URL = r'(?:https?://)?vimeo\.com/groups/(?P<name>[^/]+)'
+    _VALID_URL = r'https://vimeo\.com/groups/(?P<name>[^/]+)'
     _TESTS = [{
-        'url': 'http://vimeo.com/groups/rolexawards',
+        'url': 'https://vimeo.com/groups/rolexawards',
         'info_dict': {
             'id': 'rolexawards',
             'title': 'Rolex Awards for Enterprise',
@@ -542,13 +542,13 @@ class VimeoGroupsIE(VimeoAlbumIE):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         name = mobj.group('name')
-        return self._extract_videos(name, 'http://vimeo.com/groups/%s' % name)
+        return self._extract_videos(name, 'https://vimeo.com/groups/%s' % name)
 
 
 class VimeoReviewIE(InfoExtractor):
     IE_NAME = 'vimeo:review'
     IE_DESC = 'Review pages on vimeo'
-    _VALID_URL = r'https?://vimeo\.com/[^/]+/review/(?P<id>[^/]+)'
+    _VALID_URL = r'https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)'
     _TESTS = [{
         'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
         'md5': 'c507a72f780cacc12b2248bb4006d253',
@@ -560,7 +560,7 @@ class VimeoReviewIE(InfoExtractor):
         }
     }, {
         'note': 'video player needs Referer',
-        'url': 'http://vimeo.com/user22258446/review/91613211/13f927e053',
+        'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',
         'md5': '6295fdab8f4bf6a002d058b2c6dce276',
         'info_dict': {
             'id': '91613211',
@@ -582,11 +582,11 @@ class VimeoReviewIE(InfoExtractor):
 class VimeoWatchLaterIE(VimeoBaseInfoExtractor, VimeoChannelIE):
     IE_NAME = 'vimeo:watchlater'
     IE_DESC = 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)'
-    _VALID_URL = r'https?://vimeo\.com/home/watchlater|:vimeowatchlater'
+    _VALID_URL = r'https://vimeo\.com/home/watchlater|:vimeowatchlater'
     _LOGIN_REQUIRED = True
     _TITLE_RE = r'href="/home/watchlater".*?>(.*?)<'
     _TESTS = [{
-        'url': 'http://vimeo.com/home/watchlater',
+        'url': 'https://vimeo.com/home/watchlater',
         'only_matching': True,
     }]
 
@@ -606,7 +606,7 @@ class VimeoWatchLaterIE(VimeoBaseInfoExtractor, VimeoChannelIE):
 
 
 class VimeoLikesIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?vimeo\.com/user(?P<id>[0-9]+)/likes/?(?:$|[?#]|sort:)'
+    _VALID_URL = r'https://(?:www\.)?vimeo\.com/user(?P<id>[0-9]+)/likes/?(?:$|[?#]|sort:)'
     IE_NAME = 'vimeo:likes'
     IE_DESC = 'Vimeo user likes'
     _TEST = {
@@ -634,8 +634,8 @@ class VimeoLikesIE(InfoExtractor):
         description = self._html_search_meta('description', webpage)
 
         def _get_page(idx):
-            page_url = '%s//vimeo.com/user%s/likes/page:%d/sort:date' % (
-                self.http_scheme(), user_id, idx + 1)
+            page_url = 'https://vimeo.com/user%s/likes/page:%d/sort:date' % (
+                user_id, idx + 1)
             webpage = self._download_webpage(
                 page_url, user_id,
                 note='Downloading page %d/%d' % (idx + 1, page_count))

youtube_dl/extractor/vine.py

@@ -33,14 +33,13 @@ class VineIE(InfoExtractor):
             r'window\.POST_DATA = { %s: ({.+?}) }' % video_id, webpage, 'vine data'))
 
         formats = [{
-            'url': data['videoLowURL'],
-            'ext': 'mp4',
-            'format_id': 'low',
-        }, {
-            'url': data['videoUrl'],
-            'ext': 'mp4',
-            'format_id': 'standard',
-        }]
+            'format_id': '%(format)s-%(rate)s' % f,
+            'vcodec': f['format'],
+            'quality': f['rate'],
+            'url': f['videoUrl'],
+        } for f in data['videoUrls'] if f.get('rate')]
+
+        self._sort_formats(formats)
 
         return {
             'id': video_id,

youtube_dl/extractor/yam.py

@@ -8,6 +8,7 @@ from ..compat import compat_urlparse
 from ..utils import (
     float_or_none,
     month_by_abbreviation,
+    ExtractorError,
 )
 
 
@@ -28,23 +29,45 @@ class YamIE(InfoExtractor):
         }
     }, {
         # An external video hosted on YouTube
-        'url': 'http://mymedia.yam.com/m/3598173',
-        'md5': '0238ceec479c654e8c2f1223755bf3e9',
+        'url': 'http://mymedia.yam.com/m/3599430',
+        'md5': '03127cf10d8f35d120a9e8e52e3b17c6',
         'info_dict': {
-            'id': 'pJ2Deys283c',
+            'id': 'CNpEoQlrIgA',
             'ext': 'mp4',
-            'upload_date': '20150202',
+            'upload_date': '20150306',
             'uploader': '新莊社大瑜伽社',
-            'description': 'md5:f5cc72f0baf259a70fb731654b0d2eff',
+            'description': 'md5:11e2e405311633ace874f2e6226c8b17',
             'uploader_id': '2323agoy',
-            'title': '外婆的澎湖灣KTV-潘安邦',
-        }
+            'title': '20090412陽明山二子坪-1',
+        },
+        'skip': 'Video does not exist',
+    }, {
+        'url': 'http://mymedia.yam.com/m/3598173',
+        'info_dict': {
+            'id': '3598173',
+            'ext': 'mp4',
+        },
+        'skip': 'cause Yam system error',
+    }, {
+        'url': 'http://mymedia.yam.com/m/3599437',
+        'info_dict': {
+            'id': '3599437',
+            'ext': 'mp4',
+        },
+        'skip': 'invalid YouTube URL',
     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
         page = self._download_webpage(url, video_id)
 
+        # Check for errors
+        system_msg = self._html_search_regex(
+            r'系統訊息(?:<br>|\n|\r)*([^<>]+)<br>', page, 'system message',
+            default=None)
+        if system_msg:
+            raise ExtractorError(system_msg, expected=True)
+
         # Is it hosted externally on YouTube?
         youtube_url = self._html_search_regex(
             r'<embed src="(http://www.youtube.com/[^"]+)"',

youtube_dl/extractor/yandexmusic.py

@@ -0,0 +1,127 @@
+# coding=utf-8
+from __future__ import unicode_literals
+
+import re
+import hashlib
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    int_or_none,
+    float_or_none,
+)
+
+
+class YandexMusicBaseIE(InfoExtractor):
+    def _get_track_url(self, storage_dir, track_id):
+        data = self._download_json(
+            'http://music.yandex.ru/api/v1.5/handlers/api-jsonp.jsx?action=getTrackSrc&p=download-info/%s'
+            % storage_dir,
+            track_id, 'Downloading track location JSON')
+
+        key = hashlib.md5(('XGRlBW9FXlekgbPrRHuSiA' + data['path'][1:] + data['s']).encode('utf-8')).hexdigest()
+        storage = storage_dir.split('.')
+
+        return ('http://%s/get-mp3/%s/%s?track-id=%s&from=service-10-track&similarities-experiment=default'
+                % (data['host'], key, data['ts'] + data['path'], storage[1]))
+
+    def _get_track_info(self, track):
+        return {
+            'id': track['id'],
+            'ext': 'mp3',
+            'url': self._get_track_url(track['storageDir'], track['id']),
+            'title': '%s - %s' % (track['artists'][0]['name'], track['title']),
+            'filesize': int_or_none(track.get('fileSize')),
+            'duration': float_or_none(track.get('durationMs'), 1000),
+        }
+
+
+class YandexMusicTrackIE(YandexMusicBaseIE):
+    IE_NAME = 'yandexmusic:track'
+    IE_DESC = 'Яндекс.Музыка - Трек'
+    _VALID_URL = r'https?://music\.yandex\.(?:ru|kz|ua|by)/album/(?P<album_id>\d+)/track/(?P<id>\d+)'
+
+    _TEST = {
+        'url': 'http://music.yandex.ru/album/540508/track/4878838',
+        'md5': 'f496818aa2f60b6c0062980d2e00dc20',
+        'info_dict': {
+            'id': '4878838',
+            'ext': 'mp3',
+            'title': 'Carlo Ambrosio - Gypsy Eyes 1',
+            'filesize': 4628061,
+            'duration': 193.04,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        album_id, track_id = mobj.group('album_id'), mobj.group('id')
+
+        track = self._download_json(
+            'http://music.yandex.ru/handlers/track.jsx?track=%s:%s' % (track_id, album_id),
+            track_id, 'Downloading track JSON')['track']
+
+        return self._get_track_info(track)
+
+
+class YandexMusicAlbumIE(YandexMusicBaseIE):
+    IE_NAME = 'yandexmusic:album'
+    IE_DESC = 'Яндекс.Музыка - Альбом'
+    _VALID_URL = r'https?://music\.yandex\.(?:ru|kz|ua|by)/album/(?P<id>\d+)/?(\?|$)'
+
+    _TEST = {
+        'url': 'http://music.yandex.ru/album/540508',
+        'info_dict': {
+            'id': '540508',
+            'title': 'Carlo Ambrosio - Gypsy Soul (2009)',
+        },
+        'playlist_count': 50,
+    }
+
+    def _real_extract(self, url):
+        album_id = self._match_id(url)
+
+        album = self._download_json(
+            'http://music.yandex.ru/handlers/album.jsx?album=%s' % album_id,
+            album_id, 'Downloading album JSON')
+
+        entries = [self._get_track_info(track) for track in album['volumes'][0]]
+
+        title = '%s - %s' % (album['artists'][0]['name'], album['title'])
+        year = album.get('year')
+        if year:
+            title += ' (%s)' % year
+
+        return self.playlist_result(entries, compat_str(album['id']), title)
+
+
+class YandexMusicPlaylistIE(YandexMusicBaseIE):
+    IE_NAME = 'yandexmusic:playlist'
+    IE_DESC = 'Яндекс.Музыка - Плейлист'
+    _VALID_URL = r'https?://music\.yandex\.(?:ru|kz|ua|by)/users/[^/]+/playlists/(?P<id>\d+)'
+
+    _TEST = {
+        'url': 'http://music.yandex.ru/users/music.partners/playlists/1245',
+        'info_dict': {
+            'id': '1245',
+            'title': 'Что слушают Enter Shikari',
+            'description': 'md5:3b9f27b0efbe53f2ee1e844d07155cc9',
+        },
+        'playlist_count': 6,
+    }
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, playlist_id)
+
+        playlist = self._parse_json(
+            self._search_regex(
+                r'var\s+Mu\s*=\s*({.+?});\s*</script>', webpage, 'player'),
+            playlist_id)['pageData']['playlist']
+
+        entries = [self._get_track_info(track) for track in playlist['tracks']]
+
+        return self.playlist_result(
+            entries, compat_str(playlist_id),
+            playlist['title'], playlist.get('description'))

youtube_dl/options.py

@@ -735,6 +735,15 @@ def parseOpts(overrideArguments=None):
         '--add-metadata',
         action='store_true', dest='addmetadata', default=False,
         help='write metadata to the video file')
+    postproc.add_option(
+        '--metadata-from-title',
+        metavar='FORMAT', dest='metafromtitle',
+        help='parse additional metadata like song title / artist from the video title. '
+             'The format syntax is the same as --output, '
+             'the parsed parameters replace existing values. '
+             'Additional templates: %(album), %(artist). '
+             'Example: --metadata-from-title "%(artist)s - %(title)s" matches a title like '
+             '"Coldplay - Paradise"')
     postproc.add_option(
         '--xattrs',
         action='store_true', dest='xattrs', default=False,
@@ -785,6 +794,11 @@ def parseOpts(overrideArguments=None):
             write_string('[debug] Override config: ' + repr(overrideArguments) + '\n')
     else:
         command_line_conf = sys.argv[1:]
+        # Workaround for Python 2.x, where argv is a byte list
+        if sys.version_info < (3,):
+            command_line_conf = [
+                a.decode('utf-8', 'replace') for a in command_line_conf]
+
         if '--ignore-config' in command_line_conf:
             system_conf = []
             user_conf = []

youtube_dl/postprocessor/__init__.py

@@ -15,6 +15,7 @@ from .ffmpeg import (
 )
 from .xattrpp import XAttrMetadataPP
 from .execafterdownload import ExecAfterDownloadPP
+from .metadatafromtitle import MetadataFromTitlePP
 
 
 def get_postprocessor(key):
@@ -34,5 +35,6 @@ __all__ = [
     'FFmpegPostProcessor',
     'FFmpegSubtitlesConvertorPP',
     'FFmpegVideoConvertorPP',
+    'MetadataFromTitlePP',
     'XAttrMetadataPP',
 ]

youtube_dl/postprocessor/ffmpeg.py

@@ -545,7 +545,9 @@ class FFmpegMetadataPP(FFmpegPostProcessor):
             metadata['title'] = info['title']
         if info.get('upload_date') is not None:
             metadata['date'] = info['upload_date']
-        if info.get('uploader') is not None:
+        if info.get('artist') is not None:
+            metadata['artist'] = info['artist']
+        elif info.get('uploader') is not None:
             metadata['artist'] = info['uploader']
         elif info.get('uploader_id') is not None:
             metadata['artist'] = info['uploader_id']
@@ -554,6 +556,8 @@ class FFmpegMetadataPP(FFmpegPostProcessor):
             metadata['comment'] = info['description']
         if info.get('webpage_url') is not None:
             metadata['purl'] = info['webpage_url']
+        if info.get('album') is not None:
+            metadata['album'] = info['album']
 
         if not metadata:
             self._downloader.to_screen('[ffmpeg] There isn\'t any metadata to add')

youtube_dl/postprocessor/metadatafromtitle.py

@@ -0,0 +1,47 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import PostProcessor
+from ..utils import PostProcessingError
+
+
+class MetadataFromTitlePPError(PostProcessingError):
+    pass
+
+
+class MetadataFromTitlePP(PostProcessor):
+    def __init__(self, downloader, titleformat):
+        super(MetadataFromTitlePP, self).__init__(downloader)
+        self._titleformat = titleformat
+        self._titleregex = self.format_to_regex(titleformat)
+
+    def format_to_regex(self, fmt):
+        """
+        Converts a string like
+           '%(title)s - %(artist)s'
+        to a regex like
+           '(?P<title>.+)\ \-\ (?P<artist>.+)'
+        """
+        lastpos = 0
+        regex = ""
+        # replace %(..)s with regex group and escape other string parts
+        for match in re.finditer(r'%\((\w+)\)s', fmt):
+            regex += re.escape(fmt[lastpos:match.start()])
+            regex += r'(?P<' + match.group(1) + '>.+)'
+            lastpos = match.end()
+        if lastpos < len(fmt):
+            regex += re.escape(fmt[lastpos:len(fmt)])
+        return regex
+
+    def run(self, info):
+        title = info['title']
+        match = re.match(self._titleregex, title)
+        if match is None:
+            raise MetadataFromTitlePPError('Could not interpret title of video as "%s"' % self._titleformat)
+        for attribute, value in match.groupdict().items():
+            value = match.group(attribute)
+            info[attribute] = value
+            self._downloader.to_screen('[fromtitle] parsed ' + attribute + ': ' + value)
+
+        return True, info

youtube_dl/utils.py

@@ -319,13 +319,20 @@ def sanitize_path(s):
     if unc_or_drive:
         norm_path.pop(0)
     sanitized_path = [
-        re.sub('(?:[/<>:"\\|\\\\?\\*]|\.$)', '#', path_part)
+        path_part if path_part in ['.', '..'] else re.sub('(?:[/<>:"\\|\\\\?\\*]|\.$)', '#', path_part)
         for path_part in norm_path]
     if unc_or_drive:
         sanitized_path.insert(0, unc_or_drive + os.path.sep)
     return os.path.join(*sanitized_path)
 
 
+def sanitize_url_path_consecutive_slashes(url):
+    """Collapses consecutive slashes in URLs' path"""
+    parsed_url = list(compat_urlparse.urlparse(url))
+    parsed_url[2] = re.sub(r'/{2,}', '/', parsed_url[2])
+    return compat_urlparse.urlunparse(parsed_url)
+
+
 def orderedSet(iterable):
     """ Remove all duplicates from the input iterable """
     res = []

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2015.03.09'
+__version__ = '2015.03.24'