release 2014.12.06

Conflicts:
	youtube_dl/extractor/audiomack.py

AUTHORS

@@ -88,3 +88,5 @@ Dao Hoang Son
 Oskar Jauch
 Matthew Rayfield
 t0mm0
+Tithen-Firion
+Zack Fernandes

README.md

@@ -30,7 +30,7 @@ Alternatively, refer to the developer instructions below for how to check out an
 # DESCRIPTION
 **youtube-dl** is a small command-line program to download videos from
 YouTube.com and a few more sites. It requires the Python interpreter, version
-2.6, 2.7, or 3.3+, and it is not platform specific. It should work on
+2.6, 2.7, or 3.2+, and it is not platform specific. It should work on
 your Unix box, on Windows or on Mac OS X. It is released to the public domain,
 which means you can modify it, redistribute it or use it however you like.
 
@@ -65,10 +65,10 @@ which means you can modify it, redistribute it or use it however you like.
                                      this is not possible instead of searching.
     --ignore-config                  Do not read configuration files. When given
                                      in the global configuration file /etc
-                                     /youtube-dl.conf: do not read the user
+                                     /youtube-dl.conf: Do not read the user
-                                     configuration in ~/.config/youtube-dl.conf
+                                     configuration in ~/.config/youtube-
-                                     (%APPDATA%/youtube-dl/config.txt on
+                                     dl/config (%APPDATA%/youtube-dl/config.txt
-                                     Windows)
+                                     on Windows)
     --flat-playlist                  Do not extract the videos of a playlist,
                                      only list them.
 
@@ -93,7 +93,8 @@ which means you can modify it, redistribute it or use it however you like.
                                      COUNT views
     --max-views COUNT                Do not download any videos with more than
                                      COUNT views
-    --no-playlist                    download only the currently playing video
+    --no-playlist                    If the URL refers to a video and a
+                                     playlist, download only the video.
     --age-limit YEARS                download only videos suitable for the given
                                      age
     --download-archive FILE          Download only videos not listed in the

devscripts/bash-completion.py

@@ -1,4 +1,6 @@
 #!/usr/bin/env python
+from __future__ import unicode_literals
+
 import os
 from os.path import dirname as dirn
 import sys

devscripts/check-porn.py

@@ -1,4 +1,5 @@
 #!/usr/bin/env python
+from __future__ import unicode_literals
 
 """
 This script employs a VERY basic heuristic ('porn' in webpage.lower()) to check

devscripts/gh-pages/add-version.py

@@ -1,4 +1,5 @@
 #!/usr/bin/env python3
+from __future__ import unicode_literals
 
 import json
 import sys

devscripts/gh-pages/generate-download.py

@@ -1,4 +1,6 @@
 #!/usr/bin/env python3
+from __future__ import unicode_literals
+
 import hashlib
 import urllib.request
 import json

devscripts/gh-pages/sign-versions.py

@@ -1,4 +1,5 @@
 #!/usr/bin/env python3
+from __future__ import unicode_literals, with_statement
 
 import rsa
 import json
@@ -29,4 +30,5 @@ signature = hexlify(rsa.pkcs1.sign(json.dumps(versions_info, sort_keys=True).enc
 print('signature: ' + signature)
 
 versions_info['signature'] = signature
-json.dump(versions_info, open('update/versions.json', 'w'), indent=4, sort_keys=True)
+with open('update/versions.json', 'w') as versionsf:
+    json.dump(versions_info, versionsf, indent=4, sort_keys=True)

devscripts/gh-pages/update-copyright.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # coding: utf-8
 
-from __future__ import with_statement
+from __future__ import with_statement, unicode_literals
 
 import datetime
 import glob
@@ -13,7 +13,7 @@ year = str(datetime.datetime.now().year)
 for fn in glob.glob('*.html*'):
     with io.open(fn, encoding='utf-8') as f:
         content = f.read()
-    newc = re.sub(u'(?P<copyright>Copyright © 2006-)(?P<year>[0-9]{4})', u'Copyright © 2006-' + year, content)
+    newc = re.sub(r'(?P<copyright>Copyright © 2006-)(?P<year>[0-9]{4})', 'Copyright © 2006-' + year, content)
     if content != newc:
         tmpFn = fn + '.part'
         with io.open(tmpFn, 'wt', encoding='utf-8') as outf:

devscripts/gh-pages/update-feed.py

@@ -1,4 +1,5 @@
 #!/usr/bin/env python3
+from __future__ import unicode_literals
 
 import datetime
 import io

devscripts/gh-pages/update-sites.py

@@ -1,4 +1,5 @@
 #!/usr/bin/env python3
+from __future__ import unicode_literals
 
 import sys
 import os

devscripts/make_readme.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import io
 import sys
 import re

devscripts/prepare_manpage.py

@@ -1,3 +1,4 @@
+from __future__ import unicode_literals
 
 import io
 import os.path

devscripts/zsh-completion.py

@@ -1,4 +1,6 @@
 #!/usr/bin/env python
+from __future__ import unicode_literals
+
 import os
 from os.path import dirname as dirn
 import sys

setup.py

@@ -102,7 +102,9 @@ setup(
         "Programming Language :: Python :: 2.6",
         "Programming Language :: Python :: 2.7",
         "Programming Language :: Python :: 3",
-        "Programming Language :: Python :: 3.3"
+        "Programming Language :: Python :: 3.2",
+        "Programming Language :: Python :: 3.3",
+        "Programming Language :: Python :: 3.4",
     ],
 
     **params

test/helper.py

@@ -141,7 +141,7 @@ def expect_info_dict(self, expected_dict, got_dict):
     if missing_keys:
         def _repr(v):
             if isinstance(v, compat_str):
-                return "'%s'" % v.replace('\\', '\\\\').replace("'", "\\'")
+                return "'%s'" % v.replace('\\', '\\\\').replace("'", "\\'").replace('\n', '\\n')
             else:
                 return repr(v)
         info_dict_str = ''.join(

test/test_download.py

@@ -97,7 +97,7 @@ def generator(test_case):
             return
         for other_ie in other_ies:
             if not other_ie.working():
-                print_skipping(u'test depends on %sIE, marked as not WORKING' % other_ie.ie_key())
+                print_skipping('test depends on %sIE, marked as not WORKING' % other_ie.ie_key())
                 return
 
         params = get_params(test_case.get('params', {}))
@@ -143,7 +143,7 @@ def generator(test_case):
                         raise
 
                     if try_num == RETRIES:
-                        report_warning(u'Failed due to network errors, skipping...')
+                        report_warning('Failed due to network errors, skipping...')
                         return
 
                     print('Retrying: {0} failed tries\n\n##########\n\n'.format(try_num))

test/test_subtitles.py

@@ -238,7 +238,7 @@ class TestVimeoSubtitles(BaseTestSubtitles):
     def test_subtitles(self):
         self.DL.params['writesubtitles'] = True
         subtitles = self.getSubtitles()
-        self.assertEqual(md5(subtitles['en']), '8062383cf4dec168fc40a088aa6d5888')
+        self.assertEqual(md5(subtitles['en']), '26399116d23ae3cf2c087cea94bc43b4')
 
     def test_subtitles_lang(self):
         self.DL.params['writesubtitles'] = True

test/test_unicode_literals.py

@@ -9,14 +9,13 @@ rootDir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
 
 IGNORED_FILES = [
     'setup.py',  # http://bugs.python.org/issue13943
+    'conf.py',
+    'buildserver.py',
 ]
 
 
 class TestUnicodeLiterals(unittest.TestCase):
     def test_all_files(self):
-        print('Skipping this test (not yet fully implemented)')
-        return
-
         for dirpath, _, filenames in os.walk(rootDir):
             for basename in filenames:
                 if not basename.endswith('.py'):
@@ -30,10 +29,10 @@ class TestUnicodeLiterals(unittest.TestCase):
 
                 if "'" not in code and '"' not in code:
                     continue
-                imps = 'from __future__ import unicode_literals'
+                self.assertRegexpMatches(
-                self.assertTrue(
+                    code,
-                    imps in code,
+                    r'(?:#.*\n*)?from __future__ import (?:[a-z_]+,\s*)*unicode_literals',
-                    ' %s  missing in %s' % (imps, fn))
+                    'unicode_literals import  missing in %s' % fn)
 
                 m = re.search(r'(?<=\s)u[\'"](?!\)|,|$)', code)
                 if m is not None:

test/test_utils.py

@@ -171,7 +171,7 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(find('media:song/url').text, 'http://server.com/download.mp3')
 
     def test_smuggle_url(self):
-        data = {u"ö": u"ö", u"abc": [3]}
+        data = {"ö": "ö", "abc": [3]}
         url = 'https://foo.bar/baz?x=y#a'
         smug_url = smuggle_url(url, data)
         unsmug_url, unsmug_data = unsmuggle_url(smug_url)
@@ -220,6 +220,9 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(parse_duration('0s'), 0)
         self.assertEqual(parse_duration('01:02:03.05'), 3723.05)
         self.assertEqual(parse_duration('T30M38S'), 1838)
+        self.assertEqual(parse_duration('5 s'), 5)
+        self.assertEqual(parse_duration('3 min'), 180)
+        self.assertEqual(parse_duration('2.5 hours'), 9000)
 
     def test_fix_xml_ampersands(self):
         self.assertEqual(
@@ -376,6 +379,7 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(parse_filesize('2 MiB'), 2097152)
         self.assertEqual(parse_filesize('5 GB'), 5000000000)
         self.assertEqual(parse_filesize('1.2Tb'), 1200000000000)
+        self.assertEqual(parse_filesize('1,24 KB'), 1240)
 
 if __name__ == '__main__':
     unittest.main()

test/test_write_annotations.py

@@ -1,5 +1,6 @@
 #!/usr/bin/env python
 # coding: utf-8
+from __future__ import unicode_literals
 
 # Allow direct execution
 import os

test/test_write_info_json.py

@@ -1,5 +1,6 @@
 #!/usr/bin/env python
 # coding: utf-8
+from __future__ import unicode_literals
 
 # Allow direct execution
 import os
@@ -32,7 +33,7 @@ params = get_params({
 TEST_ID = 'BaW_jenozKc'
 INFO_JSON_FILE = TEST_ID + '.info.json'
 DESCRIPTION_FILE = TEST_ID + '.mp4.description'
-EXPECTED_DESCRIPTION = u'''test chars:  "'/\ä↭𝕐
+EXPECTED_DESCRIPTION = '''test chars:  "'/\ä↭𝕐
 test URL: https://github.com/rg3/youtube-dl/issues/1892
 
 This is a test video for youtube-dl.
@@ -53,11 +54,11 @@ class TestInfoJSON(unittest.TestCase):
         self.assertTrue(os.path.exists(INFO_JSON_FILE))
         with io.open(INFO_JSON_FILE, 'r', encoding='utf-8') as jsonf:
             jd = json.load(jsonf)
-        self.assertEqual(jd['upload_date'], u'20121002')
+        self.assertEqual(jd['upload_date'], '20121002')
         self.assertEqual(jd['description'], EXPECTED_DESCRIPTION)
         self.assertEqual(jd['id'], TEST_ID)
         self.assertEqual(jd['extractor'], 'youtube')
-        self.assertEqual(jd['title'], u'''youtube-dl test video "'/\ä↭𝕐''')
+        self.assertEqual(jd['title'], '''youtube-dl test video "'/\ä↭𝕐''')
         self.assertEqual(jd['uploader'], 'Philipp Hagemeister')
 
         self.assertTrue(os.path.exists(DESCRIPTION_FILE))

test/test_youtube_lists.py

@@ -1,4 +1,5 @@
 #!/usr/bin/env python
+from __future__ import unicode_literals
 
 # Allow direct execution
 import os

youtube_dl/YoutubeDL.py

@@ -787,6 +787,10 @@ class YoutubeDL(object):
             info_dict['display_id'] = info_dict['id']
 
         if info_dict.get('upload_date') is None and info_dict.get('timestamp') is not None:
+            # Working around negative timestamps in Windows
+            # (see http://bugs.python.org/issue1646728)
+            if info_dict['timestamp'] < 0 and os.name == 'nt':
+                info_dict['timestamp'] = 0
             upload_date = datetime.datetime.utcfromtimestamp(
                 info_dict['timestamp'])
             info_dict['upload_date'] = upload_date.strftime('%Y%m%d')

youtube_dl/__main__.py

@@ -1,4 +1,5 @@
 #!/usr/bin/env python
+from __future__ import unicode_literals
 
 # Execute with
 # $ python youtube_dl/__main__.py (2.6+)

youtube_dl/aes.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 __all__ = ['aes_encrypt', 'key_expansion', 'aes_ctr_decrypt', 'aes_cbc_decrypt', 'aes_decrypt_text']
 
 import base64

youtube_dl/compat.py

@@ -270,7 +270,7 @@ if sys.version_info < (3, 0):
         print(s.encode(preferredencoding(), 'xmlcharrefreplace'))
 else:
     def compat_print(s):
-        assert type(s) == type(u'')
+        assert isinstance(s, compat_str)
         print(s)
 
 

youtube_dl/downloader/hls.py

@@ -28,14 +28,14 @@ class HlsFD(FileDownloader):
             if check_executable(program, ['-version']):
                 break
         else:
-            self.report_error(u'm3u8 download detected but ffmpeg or avconv could not be found. Please install one.')
+            self.report_error('m3u8 download detected but ffmpeg or avconv could not be found. Please install one.')
             return False
         cmd = [program] + args
 
         retval = subprocess.call(cmd)
         if retval == 0:
             fsize = os.path.getsize(encodeFilename(tmpfilename))
-            self.to_screen(u'\r[%s] %s bytes' % (cmd[0], fsize))
+            self.to_screen('\r[%s] %s bytes' % (cmd[0], fsize))
             self.try_rename(tmpfilename, filename)
             self._hook_progress({
                 'downloaded_bytes': fsize,
@@ -45,8 +45,8 @@ class HlsFD(FileDownloader):
             })
             return True
         else:
-            self.to_stderr(u"\n")
+            self.to_stderr('\n')
-            self.report_error(u'%s exited with code %d' % (program, retval))
+            self.report_error('%s exited with code %d' % (program, retval))
             return False
 
 

youtube_dl/downloader/http.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import os
 import time
 
@@ -106,7 +108,7 @@ class HttpFD(FileDownloader):
                 self.report_retry(count, retries)
 
         if count > retries:
-            self.report_error(u'giving up after %s retries' % retries)
+            self.report_error('giving up after %s retries' % retries)
             return False
 
         data_len = data.info().get('Content-length', None)
@@ -124,10 +126,10 @@ class HttpFD(FileDownloader):
             min_data_len = self.params.get("min_filesize", None)
             max_data_len = self.params.get("max_filesize", None)
             if min_data_len is not None and data_len < min_data_len:
-                self.to_screen(u'\r[download] File is smaller than min-filesize (%s bytes < %s bytes). Aborting.' % (data_len, min_data_len))
+                self.to_screen('\r[download] File is smaller than min-filesize (%s bytes < %s bytes). Aborting.' % (data_len, min_data_len))
                 return False
             if max_data_len is not None and data_len > max_data_len:
-                self.to_screen(u'\r[download] File is larger than max-filesize (%s bytes > %s bytes). Aborting.' % (data_len, max_data_len))
+                self.to_screen('\r[download] File is larger than max-filesize (%s bytes > %s bytes). Aborting.' % (data_len, max_data_len))
                 return False
 
         data_len_str = format_bytes(data_len)
@@ -151,13 +153,13 @@ class HttpFD(FileDownloader):
                     filename = self.undo_temp_name(tmpfilename)
                     self.report_destination(filename)
                 except (OSError, IOError) as err:
-                    self.report_error(u'unable to open for writing: %s' % str(err))
+                    self.report_error('unable to open for writing: %s' % str(err))
                     return False
             try:
                 stream.write(data_block)
             except (IOError, OSError) as err:
-                self.to_stderr(u"\n")
+                self.to_stderr('\n')
-                self.report_error(u'unable to write data: %s' % str(err))
+                self.report_error('unable to write data: %s' % str(err))
                 return False
             if not self.params.get('noresizebuffer', False):
                 block_size = self.best_block_size(after - before, len(data_block))
@@ -188,10 +190,10 @@ class HttpFD(FileDownloader):
             self.slow_down(start, byte_counter - resume_len)
 
         if stream is None:
-            self.to_stderr(u"\n")
+            self.to_stderr('\n')
-            self.report_error(u'Did not get any data blocks')
+            self.report_error('Did not get any data blocks')
             return False
-        if tmpfilename != u'-':
+        if tmpfilename != '-':
             stream.close()
         self.report_finish(data_len_str, (time.time() - start))
         if data_len is not None and byte_counter != data_len:

youtube_dl/downloader/mplayer.py

@@ -1,7 +1,10 @@
+from __future__ import unicode_literals
+
 import os
 import subprocess
 
 from .common import FileDownloader
+from ..compat import compat_subprocess_get_DEVNULL
 from ..utils import (
     encodeFilename,
 )
@@ -13,19 +16,23 @@ class MplayerFD(FileDownloader):
         self.report_destination(filename)
         tmpfilename = self.temp_name(filename)
 
-        args = ['mplayer', '-really-quiet', '-vo', 'null', '-vc', 'dummy', '-dumpstream', '-dumpfile', tmpfilename, url]
+        args = [
+            'mplayer', '-really-quiet', '-vo', 'null', '-vc', 'dummy',
+            '-dumpstream', '-dumpfile', tmpfilename, url]
         # Check for mplayer first
         try:
-            subprocess.call(['mplayer', '-h'], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
+            subprocess.call(
+                ['mplayer', '-h'],
+                stdout=compat_subprocess_get_DEVNULL(), stderr=subprocess.STDOUT)
         except (OSError, IOError):
-            self.report_error(u'MMS or RTSP download detected but "%s" could not be run' % args[0])
+            self.report_error('MMS or RTSP download detected but "%s" could not be run' % args[0])
             return False
 
         # Download using mplayer.
         retval = subprocess.call(args)
         if retval == 0:
             fsize = os.path.getsize(encodeFilename(tmpfilename))
-            self.to_screen(u'\r[%s] %s bytes' % (args[0], fsize))
+            self.to_screen('\r[%s] %s bytes' % (args[0], fsize))
             self.try_rename(tmpfilename, filename)
             self._hook_progress({
                 'downloaded_bytes': fsize,
@@ -35,6 +42,6 @@ class MplayerFD(FileDownloader):
             })
             return True
         else:
-            self.to_stderr(u"\n")
+            self.to_stderr('\n')
-            self.report_error(u'mplayer exited with code %d' % retval)
+            self.report_error('mplayer exited with code %d' % retval)
             return False

youtube_dl/extractor/__init__.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 from .abc import ABCIE
 from .academicearth import AcademicEarthCourseIE
 from .addanime import AddAnimeIE
@@ -22,6 +24,7 @@ from .arte import (
 )
 from .audiomack import AudiomackIE
 from .auengine import AUEngineIE
+from .azubu import AzubuIE
 from .bambuser import BambuserIE, BambuserChannelIE
 from .bandcamp import BandcampIE, BandcampAlbumIE
 from .bbccouk import BBCCoUkIE
@@ -36,6 +39,7 @@ from .bpb import BpbIE
 from .br import BRIE
 from .breakcom import BreakIE
 from .brightcove import BrightcoveIE
+from .buzzfeed import BuzzFeedIE
 from .byutv import BYUtvIE
 from .c56 import C56IE
 from .canal13cl import Canal13clIE
@@ -118,6 +122,8 @@ from .fktv import (
 from .flickr import FlickrIE
 from .folketinget import FolketingetIE
 from .fourtube import FourTubeIE
+from .foxgay import FoxgayIE
+from .foxnews import FoxNewsIE
 from .franceculture import FranceCultureIE
 from .franceinter import FranceInterIE
 from .francetv import (
@@ -213,6 +219,7 @@ from .mdr import MDRIE
 from .metacafe import MetacafeIE
 from .metacritic import MetacriticIE
 from .mgoon import MgoonIE
+from .minhateca import MinhatecaIE
 from .ministrygrid import MinistryGridIE
 from .mit import TechTVMITIE, MITIE, OCWMITIE
 from .mitele import MiTeleIE
@@ -239,9 +246,10 @@ from .muenchentv import MuenchenTVIE
 from .musicplayon import MusicPlayOnIE
 from .musicvault import MusicVaultIE
 from .muzu import MuzuTVIE
-from .myspace import MySpaceIE
+from .myspace import MySpaceIE, MySpaceAlbumIE
 from .myspass import MySpassIE
 from .myvideo import MyVideoIE
+from .myvidster import MyVidsterIE
 from .naver import NaverIE
 from .nba import NBAIE
 from .nbc import (
@@ -373,6 +381,7 @@ from .syfy import SyfyIE
 from .sztvhu import SztvHuIE
 from .tagesschau import TagesschauIE
 from .tapely import TapelyIE
+from .tass import TassIE
 from .teachertube import (
     TeacherTubeIE,
     TeacherTubeUserIE,
@@ -413,6 +422,7 @@ from .tutv import TutvIE
 from .tvigle import TvigleIE
 from .tvp import TvpIE
 from .tvplay import TVPlayIE
+from .twentyfourvideo import TwentyFourVideoIE
 from .twitch import TwitchIE
 from .ubu import UbuIE
 from .udemy import (

youtube_dl/extractor/academicearth.py

@@ -1,4 +1,5 @@
 from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -18,15 +19,14 @@ class AcademicEarthCourseIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        m = re.match(self._VALID_URL, url)
+        playlist_id = self._match_id(url)
-        playlist_id = m.group('id')
 
         webpage = self._download_webpage(url, playlist_id)
         title = self._html_search_regex(
-            r'<h1 class="playlist-name"[^>]*?>(.*?)</h1>', webpage, u'title')
+            r'<h1 class="playlist-name"[^>]*?>(.*?)</h1>', webpage, 'title')
         description = self._html_search_regex(
             r'<p class="excerpt"[^>]*?>(.*?)</p>',
-            webpage, u'description', fatal=False)
+            webpage, 'description', fatal=False)
         urls = re.findall(
             r'<li class="lecture-preview">\s*?<a target="_blank" href="([^"]+)">',
             webpage)

youtube_dl/extractor/addanime.py

@@ -15,8 +15,7 @@ from ..utils import (
 
 
 class AddAnimeIE(InfoExtractor):
-
+    _VALID_URL = r'^http://(?:\w+\.)?add-anime\.net/watch_video\.php\?(?:.*?)v=(?P<id>[\w_]+)(?:.*)'
-    _VALID_URL = r'^http://(?:\w+\.)?add-anime\.net/watch_video\.php\?(?:.*?)v=(?P<video_id>[\w_]+)(?:.*)'
     _TEST = {
         'url': 'http://www.add-anime.net/watch_video.php?v=24MR3YO5SAS9',
         'md5': '72954ea10bc979ab5e2eb288b21425a0',
@@ -29,9 +28,9 @@ class AddAnimeIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
+        video_id = self._match_id(url)
+
         try:
-            mobj = re.match(self._VALID_URL, url)
-            video_id = mobj.group('video_id')
             webpage = self._download_webpage(url, video_id)
         except ExtractorError as ee:
             if not isinstance(ee.cause, compat_HTTPError) or \
@@ -49,7 +48,7 @@ class AddAnimeIE(InfoExtractor):
                 r'a\.value = ([0-9]+)[+]([0-9]+)[*]([0-9]+);',
                 redir_webpage)
             if av is None:
-                raise ExtractorError(u'Cannot find redirect math task')
+                raise ExtractorError('Cannot find redirect math task')
             av_res = int(av.group(1)) + int(av.group(2)) * int(av.group(3))
 
             parsed_url = compat_urllib_parse_urlparse(url)

youtube_dl/extractor/aparat.py

@@ -1,5 +1,4 @@
 # coding: utf-8
-
 from __future__ import unicode_literals
 
 import re
@@ -26,8 +25,7 @@ class AparatIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        m = re.match(self._VALID_URL, url)
+        video_id = self._match_id(url)
-        video_id = m.group('id')
 
         # Note: There is an easier-to-parse configuration at
         # http://www.aparat.com/video/video/config/videohash/%video_id
@@ -40,15 +38,15 @@ class AparatIE(InfoExtractor):
         for i, video_url in enumerate(video_urls):
             req = HEADRequest(video_url)
             res = self._request_webpage(
-                req, video_id, note=u'Testing video URL %d' % i, errnote=False)
+                req, video_id, note='Testing video URL %d' % i, errnote=False)
             if res:
                 break
         else:
-            raise ExtractorError(u'No working video URLs found')
+            raise ExtractorError('No working video URLs found')
 
-        title = self._search_regex(r'\s+title:\s*"([^"]+)"', webpage, u'title')
+        title = self._search_regex(r'\s+title:\s*"([^"]+)"', webpage, 'title')
         thumbnail = self._search_regex(
-            r'\s+image:\s*"([^"]+)"', webpage, u'thumbnail', fatal=False)
+            r'\s+image:\s*"([^"]+)"', webpage, 'thumbnail', fatal=False)
 
         return {
             'id': video_id,

youtube_dl/extractor/appletrailers.py

@@ -80,7 +80,7 @@ class AppleTrailersIE(InfoExtractor):
             def _clean_json(m):
                 return 'iTunes.playURL(%s);' % m.group(1).replace('\'', ''')
             s = re.sub(self._JSON_RE, _clean_json, s)
-            s = '<html>' + s + u'</html>'
+            s = '<html>%s</html>' % s
             return s
         doc = self._download_xml(playlist_url, movie, transform_source=fix_html)
 

youtube_dl/extractor/audiomack.py

@@ -24,17 +24,17 @@ class AudiomackIE(InfoExtractor):
         },
         # hosted on soundcloud via audiomack
         {
+            'add_ie': ['Soundcloud'],
             'url': 'http://www.audiomack.com/song/xclusiveszone/take-kare',
-            'file': '172419696.mp3',
+            'info_dict': {
-            'info_dict':
+                'id': '172419696',
-            {
                 'ext': 'mp3',
+                'description': 'md5:1fc3272ed7a635cce5be1568c2822997',
                 'title': 'Young Thug ft Lil Wayne - Take Kare',
-                "upload_date": "20141016",
+                'uploader': 'Young Thug World',
-                "description": "New track produced by London On Da Track called “Take Kare\"\n\nhttp://instagram.com/theyoungthugworld\nhttps://www.facebook.com/ThuggerThuggerCashMoney\n",
+                'upload_date': '20141016',
-                "uploader": "Young Thug World"
-            }
             }
+        },
     ]
 
     def _real_extract(self, url):

youtube_dl/extractor/azubu.py

@@ -0,0 +1,93 @@
+from __future__ import unicode_literals
+
+import json
+
+from .common import InfoExtractor
+from ..utils import float_or_none
+
+
+class AzubuIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?azubu\.tv/[^/]+#!/play/(?P<id>\d+)'
+    _TESTS = [
+        {
+            'url': 'http://www.azubu.tv/GSL#!/play/15575/2014-hot6-cup-last-big-match-ro8-day-1',
+            'md5': 'a88b42fcf844f29ad6035054bd9ecaf4',
+            'info_dict': {
+                'id': '15575',
+                'ext': 'mp4',
+                'title': '2014 HOT6 CUP LAST BIG MATCH Ro8 Day 1',
+                'description': 'md5:d06bdea27b8cc4388a90ad35b5c66c01',
+                'thumbnail': 're:^https?://.*\.jpe?g',
+                'timestamp': 1417523507.334,
+                'upload_date': '20141202',
+                'duration': 9988.7,
+                'uploader': 'GSL',
+                'uploader_id': 414310,
+                'view_count': int,
+            },
+        },
+        {
+            'url': 'http://www.azubu.tv/FnaticTV#!/play/9344/-fnatic-at-worlds-2014:-toyz---%22i-love-rekkles,-he-has-amazing-mechanics%22-',
+            'md5': 'b72a871fe1d9f70bd7673769cdb3b925',
+            'info_dict': {
+                'id': '9344',
+                'ext': 'mp4',
+                'title': 'Fnatic at Worlds 2014: Toyz - "I love Rekkles, he has amazing mechanics"',
+                'description': 'md5:4a649737b5f6c8b5c5be543e88dc62af',
+                'thumbnail': 're:^https?://.*\.jpe?g',
+                'timestamp': 1410530893.320,
+                'upload_date': '20140912',
+                'duration': 172.385,
+                'uploader': 'FnaticTV',
+                'uploader_id': 272749,
+                'view_count': int,
+            },
+        },
+    ]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        data = self._download_json(
+            'http://www.azubu.tv/api/video/%s' % video_id, video_id)['data']
+
+        title = data['title'].strip()
+        description = data['description']
+        thumbnail = data['thumbnail']
+        view_count = data['view_count']
+        uploader = data['user']['username']
+        uploader_id = data['user']['id']
+
+        stream_params = json.loads(data['stream_params'])
+
+        timestamp = float_or_none(stream_params['creationDate'], 1000)
+        duration = float_or_none(stream_params['length'], 1000)
+
+        renditions = stream_params.get('renditions') or []
+        video = stream_params.get('FLVFullLength') or stream_params.get('videoFullLength')
+        if video:
+            renditions.append(video)
+
+        formats = [{
+            'url': fmt['url'],
+            'width': fmt['frameWidth'],
+            'height': fmt['frameHeight'],
+            'vbr': float_or_none(fmt['encodingRate'], 1000),
+            'filesize': fmt['size'],
+            'vcodec': fmt['videoCodec'],
+            'container': fmt['videoContainer'],
+        } for fmt in renditions if fmt['url']]
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'timestamp': timestamp,
+            'duration': duration,
+            'uploader': uploader,
+            'uploader_id': uploader_id,
+            'view_count': view_count,
+            'formats': formats,
+        }

youtube_dl/extractor/bambuser.py

@@ -18,7 +18,7 @@ class BambuserIE(InfoExtractor):
     _TEST = {
         'url': 'http://bambuser.com/v/4050584',
         # MD5 seems to be flaky, see https://travis-ci.org/rg3/youtube-dl/jobs/14051016#L388
-        # u'md5': 'fba8f7693e48fd4e8641b3fd5539a641',
+        # 'md5': 'fba8f7693e48fd4e8641b3fd5539a641',
         'info_dict': {
             'id': '4050584',
             'ext': 'flv',

youtube_dl/extractor/bbccouk.py

@@ -1,9 +1,10 @@
 from __future__ import unicode_literals
 
-import re
+import xml.etree.ElementTree
 
 from .subtitles import SubtitlesInfoExtractor
 from ..utils import ExtractorError
+from ..compat import compat_HTTPError
 
 
 class BBCCoUkIE(SubtitlesInfoExtractor):
@@ -55,7 +56,22 @@ class BBCCoUkIE(SubtitlesInfoExtractor):
                 'skip_download': True,
             },
             'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only',
-        }
+        },
+        {
+            'url': 'http://www.bbc.co.uk/iplayer/episode/p026c7jt/tomorrows-worlds-the-unearthly-history-of-science-fiction-2-invasion',
+            'info_dict': {
+                'id': 'b03k3pb7',
+                'ext': 'flv',
+                'title': "Tomorrow's Worlds: The Unearthly History of Science Fiction",
+                'description': '2. Invasion',
+                'duration': 3600,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+            'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only',
+        },
     ]
 
     def _extract_asx_playlist(self, connection, programme_id):
@@ -102,6 +118,10 @@ class BBCCoUkIE(SubtitlesInfoExtractor):
         return playlist.findall('./{http://bbc.co.uk/2008/emp/playlist}item')
 
     def _extract_medias(self, media_selection):
+        error = media_selection.find('./{http://bbc.co.uk/2008/mp/mediaselection}error')
+        if error is not None:
+            raise ExtractorError(
+                '%s returned error: %s' % (self.IE_NAME, error.get('id')), expected=True)
         return media_selection.findall('./{http://bbc.co.uk/2008/mp/mediaselection}media')
 
     def _extract_connections(self, media):
@@ -158,45 +178,19 @@ class BBCCoUkIE(SubtitlesInfoExtractor):
             subtitles[lang] = srt
         return subtitles
 
-    def _real_extract(self, url):
+    def _download_media_selector(self, programme_id):
-        mobj = re.match(self._VALID_URL, url)
+        try:
-        group_id = mobj.group('id')
-
-        webpage = self._download_webpage(url, group_id, 'Downloading video page')
-        if re.search(r'id="emp-error" class="notinuk">', webpage):
-            raise ExtractorError('Currently BBC iPlayer TV programmes are available to play in the UK only',
-                                 expected=True)
-
-        playlist = self._download_xml('http://www.bbc.co.uk/iplayer/playlist/%s' % group_id, group_id,
-                                      'Downloading playlist XML')
-
-        no_items = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}noItems')
-        if no_items is not None:
-            reason = no_items.get('reason')
-            if reason == 'preAvailability':
-                msg = 'Episode %s is not yet available' % group_id
-            elif reason == 'postAvailability':
-                msg = 'Episode %s is no longer available' % group_id
-            else:
-                msg = 'Episode %s is not available: %s' % (group_id, reason)
-            raise ExtractorError(msg, expected=True)
-
-        formats = []
-        subtitles = None
-
-        for item in self._extract_items(playlist):
-            kind = item.get('kind')
-            if kind != 'programme' and kind != 'radioProgramme':
-                continue
-            title = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}title').text
-            description = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}summary').text
-
-            programme_id = item.get('identifier')
-            duration = int(item.get('duration'))
-
             media_selection = self._download_xml(
                 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s' % programme_id,
                 programme_id, 'Downloading media selection XML')
+        except ExtractorError as ee:
+            if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
+                media_selection = xml.etree.ElementTree.fromstring(ee.cause.read().encode('utf-8'))
+            else:
+                raise
+
+        formats = []
+        subtitles = None
 
         for media in self._extract_medias(media_selection):
             kind = media.get('kind')
@@ -207,6 +201,51 @@ class BBCCoUkIE(SubtitlesInfoExtractor):
             elif kind == 'captions':
                 subtitles = self._extract_captions(media, programme_id)
 
+        return formats, subtitles
+
+    def _real_extract(self, url):
+        group_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, group_id, 'Downloading video page')
+
+        programme_id = self._search_regex(
+            r'"vpid"\s*:\s*"([\da-z]{8})"', webpage, 'vpid', fatal=False)
+        if programme_id:
+            player = self._download_json(
+                'http://www.bbc.co.uk/iplayer/episode/%s.json' % group_id,
+                group_id)['jsConf']['player']
+            title = player['title']
+            description = player['subtitle']
+            duration = player['duration']
+            formats, subtitles = self._download_media_selector(programme_id)
+        else:
+            playlist = self._download_xml(
+                'http://www.bbc.co.uk/iplayer/playlist/%s' % group_id,
+                group_id, 'Downloading playlist XML')
+
+            no_items = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}noItems')
+            if no_items is not None:
+                reason = no_items.get('reason')
+                if reason == 'preAvailability':
+                    msg = 'Episode %s is not yet available' % group_id
+                elif reason == 'postAvailability':
+                    msg = 'Episode %s is no longer available' % group_id
+                elif reason == 'noMedia':
+                    msg = 'Episode %s is not currently available' % group_id
+                else:
+                    msg = 'Episode %s is not available: %s' % (group_id, reason)
+                raise ExtractorError(msg, expected=True)
+
+            for item in self._extract_items(playlist):
+                kind = item.get('kind')
+                if kind != 'programme' and kind != 'radioProgramme':
+                    continue
+                title = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}title').text
+                description = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}summary').text
+                programme_id = item.get('identifier')
+                duration = int(item.get('duration'))
+                formats, subtitles = self._download_media_selector(programme_id)
+
         if self._downloader.params.get('listsubtitles', False):
             self._list_available_subtitles(programme_id, subtitles)
             return

youtube_dl/extractor/bliptv.py

@@ -64,6 +64,20 @@ class BlipTVIE(SubtitlesInfoExtractor):
                 'uploader': 'redvsblue',
                 'uploader_id': '792887',
             }
+        },
+        {
+            'url': 'http://blip.tv/play/gbk766dkj4Yn',
+            'md5': 'fe0a33f022d49399a241e84a8ea8b8e3',
+            'info_dict': {
+                'id': '1749452',
+                'ext': 'mp4',
+                'upload_date': '20090208',
+                'description': 'Witness the first appearance of the Nostalgia Critic character, as Doug reviews the movie Transformers.',
+                'title': 'Nostalgia Critic: Transformers',
+                'timestamp': 1234068723,
+                'uploader': 'NostalgiaCritic',
+                'uploader_id': '246467',
+            }
         }
     ]
 
@@ -74,10 +88,12 @@ class BlipTVIE(SubtitlesInfoExtractor):
         # See https://github.com/rg3/youtube-dl/issues/857 and
         # https://github.com/rg3/youtube-dl/issues/4197
         if lookup_id:
-            info_page = self._download_webpage(
+            urlh = self._request_webpage(
-                'http://blip.tv/play/%s.x?p=1' % lookup_id, lookup_id, 'Resolving lookup id')
+                'http://blip.tv/play/%s' % lookup_id, lookup_id, 'Resolving lookup id')
-            video_id = self._search_regex(r'config\.id\s*=\s*"([0-9]+)', info_page, 'video_id')
+            url = compat_urlparse.urlparse(urlh.geturl())
-        else:
+            qs = compat_urlparse.parse_qs(url.query)
+            mobj = re.match(self._VALID_URL, qs['file'][0])
+
         video_id = mobj.group('id')
 
         rss = self._download_xml('http://blip.tv/rss/flash/%s' % video_id, video_id, 'Downloading video RSS')
@@ -114,7 +130,7 @@ class BlipTVIE(SubtitlesInfoExtractor):
             msg = self._download_webpage(
                 url + '?showplayer=20140425131715&referrer=http://blip.tv&mask=7&skin=flashvars&view=url',
                 video_id, 'Resolving URL for %s' % role)
-            real_url = compat_urlparse.parse_qs(msg)['message'][0]
+            real_url = compat_urlparse.parse_qs(msg.strip())['message'][0]
 
             media_type = media_content.get('type')
             if media_type == 'text/srt' or url.endswith('.srt'):

youtube_dl/extractor/breakcom.py

@@ -14,7 +14,6 @@ class BreakIE(InfoExtractor):
     _VALID_URL = r'http://(?:www\.)?break\.com/video/(?:[^/]+/)*.+-(?P<id>\d+)'
     _TESTS = [{
         'url': 'http://www.break.com/video/when-girls-act-like-guys-2468056',
-        'md5': '33aa4ff477ecd124d18d7b5d23b87ce5',
         'info_dict': {
             'id': '2468056',
             'ext': 'mp4',

youtube_dl/extractor/brightcove.py

@@ -265,6 +265,7 @@ class BrightcoveIE(InfoExtractor):
                 url = rend['defaultURL']
                 if not url:
                     continue
+                ext = None
                 if rend['remote']:
                     url_comp = compat_urllib_parse_urlparse(url)
                     if url_comp.path.endswith('.m3u8'):
@@ -276,7 +277,7 @@ class BrightcoveIE(InfoExtractor):
                         # akamaihd.net, but they don't use f4m manifests
                         url = url.replace('control/', '') + '?&v=3.3.0&fp=13&r=FEEFJ&g=RTSJIMBMPFPB'
                         ext = 'flv'
-                else:
+                if ext is None:
                     ext = determine_ext(url)
                 size = rend.get('size')
                 formats.append({

youtube_dl/extractor/buzzfeed.py

@@ -0,0 +1,74 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import json
+import re
+
+from .common import InfoExtractor
+
+
+class BuzzFeedIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?buzzfeed\.com/[^?#]*?/(?P<id>[^?#]+)'
+    _TESTS = [{
+        'url': 'http://www.buzzfeed.com/abagg/this-angry-ram-destroys-a-punching-bag-like-a-boss?utm_term=4ldqpia',
+        'info_dict': {
+            'id': 'this-angry-ram-destroys-a-punching-bag-like-a-boss',
+            'title': 'This Angry Ram Destroys A Punching Bag Like A Boss',
+            'description': 'Rambro!',
+        },
+        'playlist': [{
+            'info_dict': {
+                'id': 'aVCR29aE_OQ',
+                'ext': 'mp4',
+                'upload_date': '20141024',
+                'uploader_id': 'Buddhanz1',
+                'description': 'He likes to stay in shape with his heavy bag, he wont stop until its on the ground\n\nFollow Angry Ram on Facebook for regular updates -\nhttps://www.facebook.com/pages/Angry-Ram/1436897249899558?ref=hl',
+                'uploader': 'Buddhanz',
+                'title': 'Angry Ram destroys a punching bag',
+            }
+        }]
+    }, {
+        'url': 'http://www.buzzfeed.com/sheridanwatson/look-at-this-cute-dog-omg?utm_term=4ldqpia',
+        'params': {
+            'skip_download': True,  # Got enough YouTube download tests
+        },
+        'info_dict': {
+            'description': 'Munchkin the Teddy Bear is back !',
+            'title': 'You Need To Stop What You\'re Doing And Watching This Dog Walk On A Treadmill',
+        },
+        'playlist': [{
+            'info_dict': {
+                'id': 'mVmBL8B-In0',
+                'ext': 'mp4',
+                'upload_date': '20141124',
+                'uploader_id': 'CindysMunchkin',
+                'description': '© 2014 Munchkin the Shih Tzu\nAll rights reserved\nFacebook: http://facebook.com/MunchkintheShihTzu',
+                'uploader': 'Munchkin the Shih Tzu',
+                'title': 'Munchkin the Teddy Bear gets her exercise',
+            },
+        }]
+    }]
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+        webpage = self._download_webpage(url, playlist_id)
+
+        all_buckets = re.findall(
+            r'(?s)<div class="video-embed[^"]*"..*?rel:bf_bucket_data=\'([^\']+)\'',
+            webpage)
+
+        entries = []
+        for bd_json in all_buckets:
+            bd = json.loads(bd_json)
+            video = bd.get('video') or bd.get('progload_video')
+            if not video:
+                continue
+            entries.append(self.url_result(video['url']))
+
+        return {
+            '_type': 'playlist',
+            'id': playlist_id,
+            'title': self._og_search_title(webpage),
+            'description': self._og_search_description(webpage),
+            'entries': entries,
+        }

youtube_dl/extractor/cbs.py

@@ -45,4 +45,4 @@ class CBSIE(InfoExtractor):
         real_id = self._search_regex(
             r"video\.settings\.pid\s*=\s*'([^']+)';",
             webpage, 'real video ID')
-        return self.url_result(u'theplatform:%s' % real_id)
+        return self.url_result('theplatform:%s' % real_id)

youtube_dl/extractor/clipfish.py

@@ -24,7 +24,7 @@ class ClipfishIE(InfoExtractor):
             'title': 'FIFA 14 - E3 2013 Trailer',
             'duration': 82,
         },
-        u'skip': 'Blocked in the US'
+        'skip': 'Blocked in the US'
     }
 
     def _real_extract(self, url):
@@ -34,7 +34,7 @@ class ClipfishIE(InfoExtractor):
         info_url = ('http://www.clipfish.de/devxml/videoinfo/%s?ts=%d' %
                     (video_id, int(time.time())))
         doc = self._download_xml(
-            info_url, video_id, note=u'Downloading info page')
+            info_url, video_id, note='Downloading info page')
         title = doc.find('title').text
         video_url = doc.find('filename').text
         if video_url is None:

youtube_dl/extractor/common.py

@@ -13,6 +13,7 @@ import time
 import xml.etree.ElementTree
 
 from ..compat import (
+    compat_cookiejar,
     compat_http_client,
     compat_urllib_error,
     compat_urllib_parse_urlparse,
@@ -296,9 +297,11 @@ class InfoExtractor(object):
         content = self._webpage_read_content(urlh, url_or_request, video_id, note, errnote, fatal)
         return (content, urlh)
 
-    def _webpage_read_content(self, urlh, url_or_request, video_id, note=None, errnote=None, fatal=True):
+    def _webpage_read_content(self, urlh, url_or_request, video_id, note=None, errnote=None, fatal=True, prefix=None):
         content_type = urlh.headers.get('Content-Type', '')
         webpage_bytes = urlh.read()
+        if prefix is not None:
+            webpage_bytes = prefix + webpage_bytes
         m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type)
         if m:
             encoding = m.group(1)
@@ -815,6 +818,12 @@ class InfoExtractor(object):
                 self._downloader.report_warning(msg)
         return res
 
+    def _set_cookie(self, domain, name, value, expire_time=None):
+        cookie = compat_cookiejar.Cookie(
+            0, name, value, None, None, domain, None,
+            None, '/', True, False, expire_time, '', None, None, None)
+        self._downloader.cookiejar.set_cookie(cookie)
+
 
 class SearchInfoExtractor(InfoExtractor):
     """

youtube_dl/extractor/eighttracks.py

@@ -125,7 +125,7 @@ class EightTracksIE(InfoExtractor):
             info = {
                 'id': compat_str(track_data['id']),
                 'url': track_data['track_file_stream_url'],
-                'title': track_data['performer'] + u' - ' + track_data['name'],
+                'title': track_data['performer'] + ' - ' + track_data['name'],
                 'raw_title': track_data['name'],
                 'uploader_id': data['user']['login'],
                 'ext': 'm4a',

youtube_dl/extractor/foxgay.py

@@ -0,0 +1,48 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class FoxgayIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?foxgay\.com/videos/(?:\S+-)?(?P<id>\d+)\.shtml'
+    _TEST = {
+        'url': 'http://foxgay.com/videos/fuck-turkish-style-2582.shtml',
+        'md5': '80d72beab5d04e1655a56ad37afe6841',
+        'info_dict': {
+            'id': '2582',
+            'ext': 'mp4',
+            'title': 'md5:6122f7ae0fc6b21ebdf59c5e083ce25a',
+            'description': 'md5:5e51dc4405f1fd315f7927daed2ce5cf',
+            'age_limit': 18,
+            'thumbnail': 're:https?://.*\.jpg$',
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._html_search_regex(
+            r'<title>(?P<title>.*?)</title>',
+            webpage, 'title', fatal=False)
+        description = self._html_search_regex(
+            r'<div class="ico_desc"><h2>(?P<description>.*?)</h2>',
+            webpage, 'description', fatal=False)
+
+        # Find the URL for the iFrame which contains the actual video.
+        iframe = self._download_webpage(
+            self._html_search_regex(r'iframe src="(?P<frame>.*?)"', webpage, 'video frame'),
+            video_id)
+        video_url = self._html_search_regex(
+            r"v_path = '(?P<vid>http://.*?)'", iframe, 'url')
+        thumb_url = self._html_search_regex(
+            r"t_path = '(?P<thumb>http://.*?)'", iframe, 'thumbnail', fatal=False)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'url': video_url,
+            'description': description,
+            'thumbnail': thumb_url,
+            'age_limit': 18,
+        }

youtube_dl/extractor/foxnews.py

@@ -0,0 +1,94 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    parse_iso8601,
+    int_or_none,
+)
+
+
+class FoxNewsIE(InfoExtractor):
+    _VALID_URL = r'https?://video\.foxnews\.com/v/(?:video-embed\.html\?video_id=)?(?P<id>\d+)'
+    _TESTS = [
+        {
+            'url': 'http://video.foxnews.com/v/3937480/frozen-in-time/#sp=show-clips',
+            'md5': '32aaded6ba3ef0d1c04e238d01031e5e',
+            'info_dict': {
+                'id': '3937480',
+                'ext': 'flv',
+                'title': 'Frozen in Time',
+                'description': 'Doctors baffled by 16-year-old girl that is the size of a toddler',
+                'duration': 265,
+                'timestamp': 1304411491,
+                'upload_date': '20110503',
+                'thumbnail': 're:^https?://.*\.jpg$',
+            },
+        },
+        {
+            'url': 'http://video.foxnews.com/v/3922535568001/rep-luis-gutierrez-on-if-obamas-immigration-plan-is-legal/#sp=show-clips',
+            'md5': '5846c64a1ea05ec78175421b8323e2df',
+            'info_dict': {
+                'id': '3922535568001',
+                'ext': 'mp4',
+                'title': "Rep. Luis Gutierrez on if Obama's immigration plan is legal",
+                'description': "Congressman discusses the president's executive action",
+                'duration': 292,
+                'timestamp': 1417662047,
+                'upload_date': '20141204',
+                'thumbnail': 're:^https?://.*\.jpg$',
+            },
+        },
+        {
+            'url': 'http://video.foxnews.com/v/video-embed.html?video_id=3937480&d=video.foxnews.com',
+            'only_matching': True,
+        },
+    ]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        video = self._download_json(
+            'http://video.foxnews.com/v/feed/video/%s.js?template=fox' % video_id, video_id)
+
+        item = video['channel']['item']
+        title = item['title']
+        description = item['description']
+        timestamp = parse_iso8601(item['dc-date'])
+
+        media_group = item['media-group']
+        duration = None
+        formats = []
+        for media in media_group['media-content']:
+            attributes = media['@attributes']
+            video_url = attributes['url']
+            if video_url.endswith('.f4m'):
+                formats.extend(self._extract_f4m_formats(video_url + '?hdcore=3.4.0&plugin=aasp-3.4.0.132.124', video_id))
+            elif video_url.endswith('.m3u8'):
+                formats.extend(self._extract_m3u8_formats(video_url, video_id, 'flv'))
+            elif not video_url.endswith('.smil'):
+                duration = int_or_none(attributes.get('duration'))
+                formats.append({
+                    'url': video_url,
+                    'format_id': media['media-category']['@attributes']['label'],
+                    'preference': 1,
+                    'vbr': int_or_none(attributes.get('bitrate')),
+                    'filesize': int_or_none(attributes.get('fileSize'))
+                })
+        self._sort_formats(formats)
+
+        media_thumbnail = media_group['media-thumbnail']['@attributes']
+        thumbnails = [{
+            'url': media_thumbnail['url'],
+            'width': int_or_none(media_thumbnail.get('width')),
+            'height': int_or_none(media_thumbnail.get('height')),
+        }] if media_thumbnail else []
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'duration': duration,
+            'timestamp': timestamp,
+            'formats': formats,
+            'thumbnails': thumbnails,
+        }

youtube_dl/extractor/francetv.py

@@ -40,8 +40,6 @@ class FranceTVBaseInfoExtractor(InfoExtractor):
         else:
             georestricted = False
 
-
-
         formats = []
         for video in info['videos']:
             if video['statut'] != 'ONLINE':

youtube_dl/extractor/gamekings.py

@@ -11,7 +11,7 @@ class GamekingsIE(InfoExtractor):
         'url': 'http://www.gamekings.tv/videos/phoenix-wright-ace-attorney-dual-destinies-review/',
         # MD5 is flaky, seems to change regularly
         # 'md5': '2f32b1f7b80fdc5cb616efb4f387f8a3',
-        u'info_dict': {
+        'info_dict': {
             'id': '20130811',
             'ext': 'mp4',
             'title': 'Phoenix Wright: Ace Attorney \u2013 Dual Destinies Review',

youtube_dl/extractor/generic.py

@@ -452,7 +452,23 @@ class GenericIE(InfoExtractor):
                 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
             },
             'playlist_mincount': 2,
+        },
+        # Direct link with incorrect MIME type
+        {
+            'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
+            'md5': '4ccbebe5f36706d85221f204d7eb5913',
+            'info_dict': {
+                'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
+                'id': '5_Lennart_Poettering_-_Systemd',
+                'ext': 'webm',
+                'title': '5_Lennart_Poettering_-_Systemd',
+                'upload_date': '20141120',
+            },
+            'expected_warnings': [
+                'URL could be a direct video link, returning it as such.'
+            ]
         }
+
     ]
 
     def report_following_redirect(self, new_url):
@@ -606,10 +622,28 @@ class GenericIE(InfoExtractor):
         if not self._downloader.params.get('test', False) and not is_intentional:
             self._downloader.report_warning('Falling back on generic information extractor.')
 
-        if full_response:
+        if not full_response:
-            webpage = self._webpage_read_content(full_response, url, video_id)
+            full_response = self._request_webpage(url, video_id)
-        else:
+
-            webpage = self._download_webpage(url, video_id)
+        # Maybe it's a direct link to a video?
+        # Be careful not to download the whole thing!
+        first_bytes = full_response.read(512)
+        if not re.match(r'^\s*<', first_bytes.decode('utf-8', 'replace')):
+            self._downloader.report_warning(
+                'URL could be a direct video link, returning it as such.')
+            upload_date = unified_strdate(
+                head_response.headers.get('Last-Modified'))
+            return {
+                'id': video_id,
+                'title': os.path.splitext(url_basename(url))[0],
+                'direct': True,
+                'url': url,
+                'upload_date': upload_date,
+            }
+
+        webpage = self._webpage_read_content(
+            full_response, url, video_id, prefix=first_bytes)
+
         self.report_extraction(video_id)
 
         # Is it an RSS feed?

youtube_dl/extractor/gorillavid.py

@@ -9,14 +9,15 @@ from ..utils import (
     determine_ext,
     compat_urllib_parse,
     compat_urllib_request,
+    int_or_none,
 )
 
 
 class GorillaVidIE(InfoExtractor):
-    IE_DESC = 'GorillaVid.in, daclips.in and movpod.in'
+    IE_DESC = 'GorillaVid.in, daclips.in, movpod.in and fastvideo.in'
     _VALID_URL = r'''(?x)
         https?://(?P<host>(?:www\.)?
-            (?:daclips\.in|gorillavid\.in|movpod\.in))/
+            (?:daclips\.in|gorillavid\.in|movpod\.in|fastvideo\.in))/
         (?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:-[0-9]+x[0-9]+\.html)?
     '''
 
@@ -49,6 +50,16 @@ class GorillaVidIE(InfoExtractor):
             'title': 'Micro Pig piglets ready on 16th July 2009-bG0PdrCdxUc',
             'thumbnail': 're:http://.*\.jpg',
         }
+    }, {
+        # video with countdown timeout
+        'url': 'http://fastvideo.in/1qmdn1lmsmbw',
+        'md5': '8b87ec3f6564a3108a0e8e66594842ba',
+        'info_dict': {
+            'id': '1qmdn1lmsmbw',
+            'ext': 'mp4',
+            'title': 'Man of Steel - Trailer',
+            'thumbnail': 're:http://.*\.jpg',
+        },
     }, {
         'url': 'http://movpod.in/0wguyyxi1yca',
         'only_matching': True,
@@ -71,6 +82,12 @@ class GorillaVidIE(InfoExtractor):
             ''', webpage))
 
         if fields['op'] == 'download1':
+            countdown = int_or_none(self._search_regex(
+                r'<span id="countdown_str">(?:[Ww]ait)?\s*<span id="cxc">(\d+)</span>\s*(?:seconds?)?</span>',
+                webpage, 'countdown', default=None))
+            if countdown:
+                self._sleep(countdown, video_id)
+
             post = compat_urllib_parse.urlencode(fields)
 
             req = compat_urllib_request.Request(url, post)
@@ -78,9 +95,13 @@ class GorillaVidIE(InfoExtractor):
 
             webpage = self._download_webpage(req, video_id, 'Downloading video page')
 
-        title = self._search_regex(r'style="z-index: [0-9]+;">([^<]+)</span>', webpage, 'title')
+        title = self._search_regex(
-        video_url = self._search_regex(r'file\s*:\s*\'(http[^\']+)\',', webpage, 'file url')
+            r'style="z-index: [0-9]+;">([^<]+)</span>',
-        thumbnail = self._search_regex(r'image\s*:\s*\'(http[^\']+)\',', webpage, 'thumbnail', fatal=False)
+            webpage, 'title', default=None) or self._og_search_title(webpage)
+        video_url = self._search_regex(
+            r'file\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'file url')
+        thumbnail = self._search_regex(
+            r'image\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'thumbnail', fatal=False)
 
         formats = [{
             'format_id': 'sd',

youtube_dl/extractor/hotnewhiphop.py

@@ -1,12 +1,13 @@
 from __future__ import unicode_literals
 
-import re
 import base64
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urllib_parse,
     compat_urllib_request,
+)
+from ..utils import (
     ExtractorError,
     HEADRequest,
 )
@@ -16,25 +17,24 @@ class HotNewHipHopIE(InfoExtractor):
     _VALID_URL = r'http://www\.hotnewhiphop\.com/.*\.(?P<id>.*)\.html'
     _TEST = {
         'url': 'http://www.hotnewhiphop.com/freddie-gibbs-lay-it-down-song.1435540.html',
-        'file': '1435540.mp3',
         'md5': '2c2cd2f76ef11a9b3b581e8b232f3d96',
         'info_dict': {
+            'id': '1435540',
+            'ext': 'mp3',
             'title': 'Freddie Gibbs - Lay It Down'
         }
     }
 
     def _real_extract(self, url):
-        m = re.match(self._VALID_URL, url)
+        video_id = self._match_id(url)
-        video_id = m.group('id')
+        webpage = self._download_webpage(url, video_id)
-
-        webpage_src = self._download_webpage(url, video_id)
 
         video_url_base64 = self._search_regex(
-            r'data-path="(.*?)"', webpage_src, u'video URL', fatal=False)
+            r'data-path="(.*?)"', webpage, 'video URL', default=None)
 
         if video_url_base64 is None:
             video_url = self._search_regex(
-                r'"contentUrl" content="(.*?)"', webpage_src, u'video URL')
+                r'"contentUrl" content="(.*?)"', webpage, 'content URL')
             return self.url_result(video_url, ie='Youtube')
 
         reqdata = compat_urllib_parse.urlencode([
@@ -59,11 +59,11 @@ class HotNewHipHopIE(InfoExtractor):
         if video_url.endswith('.html'):
             raise ExtractorError('Redirect failed')
 
-        video_title = self._og_search_title(webpage_src).strip()
+        video_title = self._og_search_title(webpage).strip()
 
         return {
             'id': video_id,
             'url': video_url,
             'title': video_title,
-            'thumbnail': self._og_search_thumbnail(webpage_src),
+            'thumbnail': self._og_search_thumbnail(webpage),
         }

youtube_dl/extractor/minhateca.py

@@ -0,0 +1,72 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import (
+    compat_urllib_parse,
+    compat_urllib_request,
+)
+from ..utils import (
+    int_or_none,
+    parse_duration,
+    parse_filesize,
+)
+
+
+class MinhatecaIE(InfoExtractor):
+    _VALID_URL = r'https?://minhateca\.com\.br/[^?#]+,(?P<id>[0-9]+)\.'
+    _TEST = {
+        'url': 'http://minhateca.com.br/pereba/misc/youtube-dl+test+video,125848331.mp4(video)',
+        'info_dict': {
+            'id': '125848331',
+            'ext': 'mp4',
+            'title': 'youtube-dl test video',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'filesize_approx': 1530000,
+            'duration': 9,
+            'view_count': int,
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        token = self._html_search_regex(
+            r'<input name="__RequestVerificationToken".*?value="([^"]+)"',
+            webpage, 'request token')
+        token_data = [
+            ('fileId', video_id),
+            ('__RequestVerificationToken', token),
+        ]
+        req = compat_urllib_request.Request(
+            'http://minhateca.com.br/action/License/Download',
+            data=compat_urllib_parse.urlencode(token_data))
+        req.add_header('Content-Type', 'application/x-www-form-urlencoded')
+        data = self._download_json(
+            req, video_id, note='Downloading metadata')
+
+        video_url = data['redirectUrl']
+        title_str = self._html_search_regex(
+            r'<h1.*?>(.*?)</h1>', webpage, 'title')
+        title, _, ext = title_str.rpartition('.')
+        filesize_approx = parse_filesize(self._html_search_regex(
+            r'<p class="fileSize">(.*?)</p>',
+            webpage, 'file size approximation', fatal=False))
+        duration = parse_duration(self._html_search_regex(
+            r'(?s)<p class="fileLeng[ht][th]">.*?class="bold">(.*?)<',
+            webpage, 'duration', fatal=False))
+        view_count = int_or_none(self._html_search_regex(
+            r'<p class="downloadsCounter">([0-9]+)</p>',
+            webpage, 'view count', fatal=False))
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': title,
+            'ext': ext,
+            'filesize_approx': filesize_approx,
+            'duration': duration,
+            'view_count': view_count,
+            'thumbnail': self._og_search_thumbnail(webpage),
+        }

youtube_dl/extractor/mooshare.py

@@ -49,7 +49,7 @@ class MooshareIE(InfoExtractor):
         page = self._download_webpage(url, video_id, 'Downloading page')
 
         if re.search(r'>Video Not Found or Deleted<', page) is not None:
-            raise ExtractorError(u'Video %s does not exist' % video_id, expected=True)
+            raise ExtractorError('Video %s does not exist' % video_id, expected=True)
 
         hash_key = self._html_search_regex(r'<input type="hidden" name="hash" value="([^"]+)">', page, 'hash')
         title = self._html_search_regex(r'(?m)<div class="blockTitle">\s*<h2>Watch ([^<]+)</h2>', page, 'title')

youtube_dl/extractor/mtv.py

@@ -164,7 +164,7 @@ class MTVServicesInfoExtractor(InfoExtractor):
         if mgid is None or ':' not in mgid:
             mgid = self._search_regex(
                 [r'data-mgid="(.*?)"', r'swfobject.embedSWF\(".*?(mgid:.*?)"'],
-                webpage, u'mgid')
+                webpage, 'mgid')
         return self._get_videos_info(mgid)
 
 

youtube_dl/extractor/muzu.py

@@ -1,47 +1,48 @@
-import re
+from __future__ import unicode_literals
-import json
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urllib_parse,
-    determine_ext,
 )
 
 
 class MuzuTVIE(InfoExtractor):
     _VALID_URL = r'https?://www\.muzu\.tv/(.+?)/(.+?)/(?P<id>\d+)'
-    IE_NAME = u'muzu.tv'
+    IE_NAME = 'muzu.tv'
 
     _TEST = {
-        u'url': u'http://www.muzu.tv/defected/marcashken-featuring-sos-cat-walk-original-mix-music-video/1981454/',
+        'url': 'http://www.muzu.tv/defected/marcashken-featuring-sos-cat-walk-original-mix-music-video/1981454/',
-        u'file': u'1981454.mp4',
+        'md5': '98f8b2c7bc50578d6a0364fff2bfb000',
-        u'md5': u'98f8b2c7bc50578d6a0364fff2bfb000',
+        'info_dict': {
-        u'info_dict': {
+            'id': '1981454',
-            u'title': u'Cat Walk (Original Mix)',
+            'ext': 'mp4',
-            u'description': u'md5:90e868994de201b2570e4e5854e19420',
+            'title': 'Cat Walk (Original Mix)',
-            u'uploader': u'MarcAshken featuring SOS',
+            'description': 'md5:90e868994de201b2570e4e5854e19420',
+            'uploader': 'MarcAshken featuring SOS',
         },
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
+        video_id = self._match_id(url)
-        video_id = mobj.group('id')
 
-        info_data = compat_urllib_parse.urlencode({'format': 'json',
+        info_data = compat_urllib_parse.urlencode({
+            'format': 'json',
             'url': url,
         })
-        video_info_page = self._download_webpage('http://www.muzu.tv/api/oembed/?%s' % info_data,
+        info = self._download_json(
-                                                 video_id, u'Downloading video info')
+            'http://www.muzu.tv/api/oembed/?%s' % info_data,
-        info = json.loads(video_info_page)
+            video_id, 'Downloading video info')
 
-        player_info_page = self._download_webpage('http://player.muzu.tv/player/playerInit?ai=%s' % video_id,
+        player_info = self._download_json(
-                                                  video_id, u'Downloading player info')
+            'http://player.muzu.tv/player/playerInit?ai=%s' % video_id,
-        video_info = json.loads(player_info_page)['videos'][0]
+            video_id, 'Downloading player info')
+        video_info = player_info['videos'][0]
         for quality in ['1080', '720', '480', '360']:
             if video_info.get('v%s' % quality):
                 break
 
-        data = compat_urllib_parse.urlencode({'ai': video_id,
+        data = compat_urllib_parse.urlencode({
+            'ai': video_id,
             # Even if each time you watch a video the hash changes,
             # it seems to work for different videos, and it will work
             # even if you use any non empty string as a hash
@@ -49,15 +50,15 @@ class MuzuTVIE(InfoExtractor):
             'device': 'web',
             'qv': quality,
         })
-        video_url_page = self._download_webpage('http://player.muzu.tv/player/requestVideo?%s' % data,
+        video_url_info = self._download_json(
-                                                video_id, u'Downloading video url')
+            'http://player.muzu.tv/player/requestVideo?%s' % data,
-        video_url_info = json.loads(video_url_page)
+            video_id, 'Downloading video url')
         video_url = video_url_info['url']
 
-        return {'id': video_id,
+        return {
+            'id': video_id,
             'title': info['title'],
             'url': video_url,
-                'ext': determine_ext(video_url),
             'thumbnail': info['thumbnail_url'],
             'description': info['description'],
             'uploader': info['author_name'],

youtube_dl/extractor/myspace.py

@@ -1,3 +1,4 @@
+# encoding: utf-8
 from __future__ import unicode_literals
 
 import re
@@ -7,6 +8,7 @@ from .common import InfoExtractor
 from ..compat import (
     compat_str,
 )
+from ..utils import ExtractorError
 
 
 class MySpaceIE(InfoExtractor):
@@ -14,33 +16,58 @@ class MySpaceIE(InfoExtractor):
 
     _TESTS = [
         {
-            'url': 'https://myspace.com/coldplay/video/viva-la-vida/100008689',
+            'url': 'https://myspace.com/fiveminutestothestage/video/little-big-town/109594919',
             'info_dict': {
-                'id': '100008689',
+                'id': '109594919',
                 'ext': 'flv',
-                'title': 'Viva La Vida',
+                'title': 'Little Big Town',
-                'description': 'The official Viva La Vida video, directed by Hype Williams',
+                'description': 'This country quartet was all smiles while playing a sold out show at the Pacific Amphitheatre in Orange County, California.',
-                'uploader': 'Coldplay',
+                'uploader': 'Five Minutes to the Stage',
-                'uploader_id': 'coldplay',
+                'uploader_id': 'fiveminutestothestage',
             },
             'params': {
                 # rtmp download
                 'skip_download': True,
             },
         },
-        # song
+        # songs
         {
-            'url': 'https://myspace.com/spiderbags/music/song/darkness-in-my-heart-39008454-27041242',
+            'url': 'https://myspace.com/killsorrow/music/song/of-weakened-soul...-93388656-103880681',
             'info_dict': {
-                'id': '39008454',
+                'id': '93388656',
                 'ext': 'flv',
-                'title': 'Darkness In My Heart',
+                'title': 'Of weakened soul...',
-                'uploader_id': 'spiderbags',
+                'uploader': 'Killsorrow',
+                'uploader_id': 'killsorrow',
             },
             'params': {
                 # rtmp download
                 'skip_download': True,
             },
+        }, {
+            'add_ie': ['Vevo'],
+            'url': 'https://myspace.com/threedaysgrace/music/song/animal-i-have-become-28400208-28218041',
+            'info_dict': {
+                'id': 'USZM20600099',
+                'ext': 'mp4',
+                'title': 'Animal I Have Become',
+                'uploader': 'Three Days Grace',
+                'timestamp': int,
+                'upload_date': '20060502',
+            },
+            'skip': 'VEVO is only available in some countries',
+        }, {
+            'add_ie': ['Youtube'],
+            'url': 'https://myspace.com/starset2/music/song/first-light-95799905-106964426',
+            'info_dict': {
+                'id': 'ypWvQgnJrSU',
+                'ext': 'mp4',
+                'title': 'Starset - First Light',
+                'description': 'md5:2d5db6c9d11d527683bcda818d332414',
+                'uploader': 'Jacob Soren',
+                'uploader_id': 'SorenPromotions',
+                'upload_date': '20140725',
+            }
         },
     ]
 
@@ -48,16 +75,41 @@ class MySpaceIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
         webpage = self._download_webpage(url, video_id)
+        player_url = self._search_regex(
+            r'playerSwf":"([^"?]*)', webpage, 'player URL')
 
         if mobj.group('mediatype').startswith('music/song'):
             # songs don't store any useful info in the 'context' variable
+            song_data = self._search_regex(
+                r'''<button.*data-song-id=(["\'])%s\1.*''' % video_id,
+                webpage, 'song_data', default=None, group=0)
+            if song_data is None:
+                # some songs in an album are not playable
+                self.report_warning(
+                    '%s: No downloadable song on this page' % video_id)
+                return
+
             def search_data(name):
                 return self._search_regex(
-                    r'data-%s="(.*?)"' % name, webpage, name)
+                    r'''data-%s=([\'"])(?P<data>.*?)\1''' % name,
+                    song_data, name, default='', group='data')
             streamUrl = search_data('stream-url')
+            if not streamUrl:
+                vevo_id = search_data('vevo-id')
+                youtube_id = search_data('youtube-id')
+                if vevo_id:
+                    self.to_screen('Vevo video detected: %s' % vevo_id)
+                    return self.url_result('vevo:%s' % vevo_id, ie='Vevo')
+                elif youtube_id:
+                    self.to_screen('Youtube video detected: %s' % youtube_id)
+                    return self.url_result(youtube_id, ie='Youtube')
+                else:
+                    raise ExtractorError(
+                        'Found song but don\'t know how to download it')
             info = {
                 'id': video_id,
                 'title': self._og_search_title(webpage),
+                'uploader': search_data('artist-name'),
                 'uploader_id': search_data('artist-username'),
                 'thumbnail': self._og_search_thumbnail(webpage),
             }
@@ -79,6 +131,50 @@ class MySpaceIE(InfoExtractor):
         info.update({
             'url': rtmp_url,
             'play_path': play_path,
+            'player_url': player_url,
             'ext': 'flv',
         })
         return info
+
+
+class MySpaceAlbumIE(InfoExtractor):
+    IE_NAME = 'MySpace:album'
+    _VALID_URL = r'https?://myspace\.com/([^/]+)/music/album/(?P<title>.*-)(?P<id>\d+)'
+
+    _TESTS = [{
+        'url': 'https://myspace.com/starset2/music/album/transmissions-19455773',
+        'info_dict': {
+            'title': 'Transmissions',
+            'id': '19455773',
+        },
+        'playlist_count': 14,
+        'skip': 'this album is only available in some countries',
+    }, {
+        'url': 'https://myspace.com/killsorrow/music/album/the-demo-18596029',
+        'info_dict': {
+            'title': 'The Demo',
+            'id': '18596029',
+        },
+        'playlist_count': 5,
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        playlist_id = mobj.group('id')
+        display_id = mobj.group('title') + playlist_id
+        webpage = self._download_webpage(url, display_id)
+        tracks_paths = re.findall(r'"music:song" content="(.*?)"', webpage)
+        if not tracks_paths:
+            raise ExtractorError(
+                '%s: No songs found, try using proxy' % display_id,
+                expected=True)
+        entries = [
+            self.url_result(t_path, ie=MySpaceIE.ie_key())
+            for t_path in tracks_paths]
+        return {
+            '_type': 'playlist',
+            'id': playlist_id,
+            'display_id': display_id,
+            'title': self._og_search_title(webpage),
+            'entries': entries,
+        }

youtube_dl/extractor/myvidster.py

@@ -0,0 +1,29 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class MyVidsterIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?myvidster\.com/video/(?P<id>\d+)/'
+
+    _TEST = {
+        'url': 'http://www.myvidster.com/video/32059805/Hot_chemistry_with_raw_love_making',
+        'md5': '95296d0231c1363222c3441af62dc4ca',
+        'info_dict': {
+            'id': '3685814',
+            'title': 'md5:7d8427d6d02c4fbcef50fe269980c749',
+            'upload_date': '20141027',
+            'uploader_id': 'utkualp',
+            'ext': 'mp4',
+            'age_limit': 18,
+        },
+        'add_ie': ['XHamster'],
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        return self.url_result(self._html_search_regex(
+            r'rel="videolink" href="(?P<real_url>.*)">',
+            webpage, 'real video url'))

youtube_dl/extractor/nhl.py

@@ -4,9 +4,12 @@ import re
 import json
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urlparse,
     compat_urllib_parse,
+    compat_urllib_parse_urlparse
+)
+from ..utils import (
     unified_strdate,
 )
 
@@ -22,9 +25,11 @@ class NHLBaseInfoExtractor(InfoExtractor):
 
         initial_video_url = info['publishPoint']
         if info['formats'] == '1':
+            parsed_url = compat_urllib_parse_urlparse(initial_video_url)
+            path = parsed_url.path.replace('.', '_sd.', 1)
             data = compat_urllib_parse.urlencode({
                 'type': 'fvod',
-                'path': initial_video_url.replace('.mp4', '_sd.mp4'),
+                'path': compat_urlparse.urlunparse(parsed_url[:2] + (path,) + parsed_url[3:])
             })
             path_url = 'http://video.nhl.com/videocenter/servlets/encryptvideopath?' + data
             path_doc = self._download_xml(
@@ -71,6 +76,17 @@ class NHLIE(NHLBaseInfoExtractor):
             'duration': 0,
             'upload_date': '20141011',
         },
+    }, {
+        'url': 'http://video.mapleleafs.nhl.com/videocenter/console?id=58665&catid=802',
+        'md5': 'c78fc64ea01777e426cfc202b746c825',
+        'info_dict': {
+            'id': '58665',
+            'ext': 'flv',
+            'title': 'Classic Game In Six - April 22, 1979',
+            'description': 'It was the last playoff game for the Leafs in the decade, and the last time the Leafs and Habs played in the playoffs. Great game, not a great ending.',
+            'duration': 400,
+            'upload_date': '20100129'
+        },
     }, {
         'url': 'http://video.flames.nhl.com/videocenter/console?id=630616',
         'only_matching': True,
@@ -88,7 +104,7 @@ class NHLIE(NHLBaseInfoExtractor):
 class NHLVideocenterIE(NHLBaseInfoExtractor):
     IE_NAME = 'nhl.com:videocenter'
     IE_DESC = 'NHL videocenter category'
-    _VALID_URL = r'https?://video\.(?P<team>[^.]*)\.nhl\.com/videocenter/(console\?.*?catid=(?P<catid>[0-9]+)(?![&?]id=).*?)?$'
+    _VALID_URL = r'https?://video\.(?P<team>[^.]*)\.nhl\.com/videocenter/(console\?[^(id=)]*catid=(?P<catid>[0-9]+)(?![&?]id=).*?)?$'
     _TEST = {
         'url': 'http://video.canucks.nhl.com/videocenter/console?catid=999',
         'info_dict': {
@@ -122,7 +138,7 @@ class NHLVideocenterIE(NHLBaseInfoExtractor):
         response = self._download_webpage(request_url, playlist_title)
         response = self._fix_json(response)
         if not response.strip():
-            self._downloader.report_warning(u'Got an empty reponse, trying '
+            self._downloader.report_warning('Got an empty reponse, trying '
                                             'adding the "newvideos" parameter')
             response = self._download_webpage(request_url + '&newvideos=true',
                                               playlist_title)

youtube_dl/extractor/noco.py

@@ -20,6 +20,7 @@ class NocoIE(InfoExtractor):
     _VALID_URL = r'http://(?:(?:www\.)?noco\.tv/emission/|player\.noco\.tv/\?idvideo=)(?P<id>\d+)'
     _LOGIN_URL = 'http://noco.tv/do.php'
     _API_URL_TEMPLATE = 'https://api.noco.tv/1.1/%s?ts=%s&tk=%s'
+    _SUB_LANG_TEMPLATE = '&sub_lang=%s'
     _NETRC_MACHINE = 'noco'
 
     _TEST = {
@@ -60,10 +61,12 @@ class NocoIE(InfoExtractor):
         if 'erreur' in login:
             raise ExtractorError('Unable to login: %s' % clean_html(login['erreur']), expected=True)
 
-    def _call_api(self, path, video_id, note):
+    def _call_api(self, path, video_id, note, sub_lang=None):
         ts = compat_str(int(time.time() * 1000))
         tk = hashlib.md5((hashlib.md5(ts.encode('ascii')).hexdigest() + '#8S?uCraTedap6a').encode('ascii')).hexdigest()
         url = self._API_URL_TEMPLATE % (path, ts, tk)
+        if sub_lang:
+            url += self._SUB_LANG_TEMPLATE % sub_lang
 
         resp = self._download_json(url, video_id, note)
 
@@ -91,11 +94,14 @@ class NocoIE(InfoExtractor):
 
         formats = []
 
-        for format_id, fmt in medias['fr']['video_list']['none']['quality_list'].items():
+        for lang, lang_dict in medias['fr']['video_list'].items():
+            for format_id, fmt in lang_dict['quality_list'].items():
+                format_id_extended = '%s-%s' % (lang, format_id) if lang != 'none' else format_id
 
                 video = self._call_api(
                     'shows/%s/video/%s/fr' % (video_id, format_id.lower()),
-                video_id, 'Downloading %s video JSON' % format_id)
+                    video_id, 'Downloading %s video JSON' % format_id_extended,
+                    lang if lang != 'none' else None)
 
                 file_url = video['file']
                 if not file_url:
@@ -107,7 +113,7 @@ class NocoIE(InfoExtractor):
 
                 formats.append({
                     'url': file_url,
-                'format_id': format_id,
+                    'format_id': format_id_extended,
                     'width': fmt['res_width'],
                     'height': fmt['res_lines'],
                     'abr': fmt['audiobitrate'],

youtube_dl/extractor/playvid.py

@@ -4,6 +4,8 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
+    ExtractorError,
+    clean_html,
     compat_urllib_parse,
 )
 
@@ -28,6 +30,11 @@ class PlayvidIE(InfoExtractor):
 
         webpage = self._download_webpage(url, video_id)
 
+        m_error = re.search(
+            r'<div class="block-error">\s*<div class="heading">\s*<div>(?P<msg>.+?)</div>\s*</div>', webpage)
+        if m_error:
+            raise ExtractorError(clean_html(m_error.group('msg')), expected=True)
+
         video_title = None
         duration = None
         video_thumbnail = None

youtube_dl/extractor/redtube.py

@@ -1,7 +1,5 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 
 
@@ -9,32 +7,23 @@ class RedTubeIE(InfoExtractor):
     _VALID_URL = r'http://(?:www\.)?redtube\.com/(?P<id>[0-9]+)'
     _TEST = {
         'url': 'http://www.redtube.com/66418',
-        'file': '66418.mp4',
-        # md5 varies from time to time, as in
-        # https://travis-ci.org/rg3/youtube-dl/jobs/14052463#L295
-        #'md5': u'7b8c22b5e7098a3e1c09709df1126d2d',
         'info_dict': {
+            'id': '66418',
+            'ext': 'mp4',
             "title": "Sucked on a toilet",
             "age_limit": 18,
         }
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
+        video_id = self._match_id(url)
-
-        video_id = mobj.group('id')
-        video_extension = 'mp4'
         webpage = self._download_webpage(url, video_id)
 
-        self.report_extraction(video_id)
-
         video_url = self._html_search_regex(
-            r'<source src="(.+?)" type="video/mp4">', webpage, u'video URL')
+            r'<source src="(.+?)" type="video/mp4">', webpage, 'video URL')
-
         video_title = self._html_search_regex(
             r'<h1 class="videoTitle[^"]*">(.+?)</h1>',
-            webpage, u'title')
+            webpage, 'title')
-
         video_thumbnail = self._og_search_thumbnail(webpage)
 
         # No self-labeling, but they describe themselves as
@@ -44,7 +33,7 @@ class RedTubeIE(InfoExtractor):
         return {
             'id': video_id,
             'url': video_url,
-            'ext': video_extension,
+            'ext': 'mp4',
             'title': video_title,
             'thumbnail': video_thumbnail,
             'age_limit': age_limit,

youtube_dl/extractor/rts.py

@@ -15,7 +15,7 @@ from ..utils import (
 
 class RTSIE(InfoExtractor):
     IE_DESC = 'RTS.ch'
-    _VALID_URL = r'^https?://(?:www\.)?rts\.ch/(?:[^/]+/){2,}(?P<id>[0-9]+)-.*?\.html'
+    _VALID_URL = r'https?://(?:www\.)?rts\.ch/(?:(?:[^/]+/){2,}(?P<id>[0-9]+)-(?P<display_id>.+?)\.html|play/tv/[^/]+/video/(?P<display_id_new>.+?)\?id=(?P<id_new>[0-9]+))'
 
     _TESTS = [
         {
@@ -23,6 +23,7 @@ class RTSIE(InfoExtractor):
             'md5': '753b877968ad8afaeddccc374d4256a5',
             'info_dict': {
                 'id': '3449373',
+                'display_id': 'les-enfants-terribles',
                 'ext': 'mp4',
                 'duration': 1488,
                 'title': 'Les Enfants Terribles',
@@ -30,7 +31,8 @@ class RTSIE(InfoExtractor):
                 'uploader': 'Divers',
                 'upload_date': '19680921',
                 'timestamp': -40280400,
-                'thumbnail': 're:^https?://.*\.image'
+                'thumbnail': 're:^https?://.*\.image',
+                'view_count': int,
             },
         },
         {
@@ -38,6 +40,7 @@ class RTSIE(InfoExtractor):
             'md5': 'c148457a27bdc9e5b1ffe081a7a8337b',
             'info_dict': {
                 'id': '5624067',
+                'display_id': 'entre-ciel-et-mer',
                 'ext': 'mp4',
                 'duration': 3720,
                 'title': 'Les yeux dans les cieux - Mon homard au Canada',
@@ -45,7 +48,8 @@ class RTSIE(InfoExtractor):
                 'uploader': 'Passe-moi les jumelles',
                 'upload_date': '20140404',
                 'timestamp': 1396635300,
-                'thumbnail': 're:^https?://.*\.image'
+                'thumbnail': 're:^https?://.*\.image',
+                'view_count': int,
             },
         },
         {
@@ -53,6 +57,7 @@ class RTSIE(InfoExtractor):
             'md5': 'b4326fecd3eb64a458ba73c73e91299d',
             'info_dict': {
                 'id': '5745975',
+                'display_id': '1-2-kloten-fribourg-5-2-second-but-pour-gotteron-par-kwiatowski',
                 'ext': 'mp4',
                 'duration': 48,
                 'title': '1/2, Kloten - Fribourg (5-2): second but pour Gottéron par Kwiatowski',
@@ -60,7 +65,8 @@ class RTSIE(InfoExtractor):
                 'uploader': 'Hockey',
                 'upload_date': '20140403',
                 'timestamp': 1396556882,
-                'thumbnail': 're:^https?://.*\.image'
+                'thumbnail': 're:^https?://.*\.image',
+                'view_count': int,
             },
             'skip': 'Blocked outside Switzerland',
         },
@@ -69,6 +75,7 @@ class RTSIE(InfoExtractor):
             'md5': '9bb06503773c07ce83d3cbd793cebb91',
             'info_dict': {
                 'id': '5745356',
+                'display_id': 'londres-cachee-par-un-epais-smog',
                 'ext': 'mp4',
                 'duration': 33,
                 'title': 'Londres cachée par un épais smog',
@@ -76,7 +83,8 @@ class RTSIE(InfoExtractor):
                 'uploader': 'Le Journal en continu',
                 'upload_date': '20140403',
                 'timestamp': 1396537322,
-                'thumbnail': 're:^https?://.*\.image'
+                'thumbnail': 're:^https?://.*\.image',
+                'view_count': int,
             },
         },
         {
@@ -84,6 +92,7 @@ class RTSIE(InfoExtractor):
             'md5': 'dd8ef6a22dff163d063e2a52bc8adcae',
             'info_dict': {
                 'id': '5706148',
+                'display_id': 'urban-hippie-de-damien-krisl-03-04-2014',
                 'ext': 'mp3',
                 'duration': 123,
                 'title': '"Urban Hippie", de Damien Krisl',
@@ -92,22 +101,44 @@ class RTSIE(InfoExtractor):
                 'timestamp': 1396551600,
             },
         },
+        {
+            'url': 'http://www.rts.ch/play/tv/-/video/le-19h30?id=6348260',
+            'md5': '968777c8779e5aa2434be96c54e19743',
+            'info_dict': {
+                'id': '6348260',
+                'display_id': 'le-19h30',
+                'ext': 'mp4',
+                'duration': 1796,
+                'title': 'Le 19h30',
+                'description': '',
+                'uploader': 'Le 19h30',
+                'upload_date': '20141201',
+                'timestamp': 1417458600,
+                'thumbnail': 're:^https?://.*\.image',
+                'view_count': int,
+            },
+        },
+        {
+            'url': 'http://www.rts.ch/play/tv/le-19h30/video/le-chantier-du-nouveau-parlement-vaudois-a-permis-une-trouvaille-historique?id=6348280',
+            'only_matching': True,
+        }
     ]
 
     def _real_extract(self, url):
         m = re.match(self._VALID_URL, url)
-        video_id = m.group('id')
+        video_id = m.group('id') or m.group('id_new')
+        display_id = m.group('display_id') or m.group('display_id_new')
 
         def download_json(internal_id):
             return self._download_json(
                 'http://www.rts.ch/a/%s.html?f=json/article' % internal_id,
-                video_id)
+                display_id)
 
         all_info = download_json(video_id)
 
         # video_id extracted out of URL is not always a real id
         if 'video' not in all_info and 'audio' not in all_info:
-            page = self._download_webpage(url, video_id)
+            page = self._download_webpage(url, display_id)
             internal_id = self._html_search_regex(
                 r'<(?:video|audio) data-id="([0-9]+)"', page,
                 'internal video id')
@@ -143,6 +174,7 @@ class RTSIE(InfoExtractor):
 
         return {
             'id': video_id,
+            'display_id': display_id,
             'formats': formats,
             'title': info['title'],
             'description': info.get('intro'),

youtube_dl/extractor/rutube.py

@@ -53,6 +53,7 @@ class RutubeIE(InfoExtractor):
         m3u8_url = options['video_balancer'].get('m3u8')
         if m3u8_url is None:
             raise ExtractorError('Couldn\'t find m3u8 manifest url')
+        formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4')
 
         return {
             'id': video['id'],
@@ -60,8 +61,7 @@ class RutubeIE(InfoExtractor):
             'description': video['description'],
             'duration': video['duration'],
             'view_count': video['hits'],
-            'url': m3u8_url,
+            'formats': formats,
-            'ext': 'mp4',
             'thumbnail': video['thumbnail_url'],
             'uploader': author.get('name'),
             'uploader_id': compat_str(author['id']) if author else None,

youtube_dl/extractor/slideshare.py

@@ -39,7 +39,7 @@ class SlideshareIE(InfoExtractor):
         ext = info['jsplayer']['video_extension']
         video_url = compat_urlparse.urljoin(bucket, doc + '-SD.' + ext)
         description = self._html_search_regex(
-            r'<p\s+(?:style="[^"]*"\s+)?class="description.*?"[^>]*>(.*?)</p>', webpage,
+            r'<p\s+(?:style="[^"]*"\s+)?class=".*?description.*?"[^>]*>(.*?)</p>', webpage,
             'description', fatal=False)
 
         return {

youtube_dl/extractor/sohu.py

@@ -1,4 +1,5 @@
 # encoding: utf-8
+from __future__ import unicode_literals
 
 import json
 import re
@@ -11,13 +12,14 @@ class SohuIE(InfoExtractor):
     _VALID_URL = r'https?://(?P<mytv>my\.)?tv\.sohu\.com/.+?/(?(mytv)|n)(?P<id>\d+)\.shtml.*?'
 
     _TEST = {
-        u'url': u'http://tv.sohu.com/20130724/n382479172.shtml#super',
+        'url': 'http://tv.sohu.com/20130724/n382479172.shtml#super',
-        u'file': u'382479172.mp4',
+        'md5': 'bde8d9a6ffd82c63a1eefaef4eeefec7',
-        u'md5': u'bde8d9a6ffd82c63a1eefaef4eeefec7',
+        'info_dict': {
-        u'info_dict': {
+            'id': '382479172',
-            u'title': u'MV：Far East Movement《The Illest》',
+            'ext': 'mp4',
+            'title': 'MV：Far East Movement《The Illest》',
         },
-        u'skip': u'Only available from China',
+        'skip': 'Only available from China',
     }
 
     def _real_extract(self, url):
@@ -26,11 +28,11 @@ class SohuIE(InfoExtractor):
             if mytv:
                 base_data_url = 'http://my.tv.sohu.com/play/videonew.do?vid='
             else:
-                base_data_url = u'http://hot.vrs.sohu.com/vrs_flash.action?vid='
+                base_data_url = 'http://hot.vrs.sohu.com/vrs_flash.action?vid='
             data_url = base_data_url + str(vid_id)
             data_json = self._download_webpage(
                 data_url, video_id,
-                note=u'Downloading JSON data for ' + str(vid_id))
+                note='Downloading JSON data for ' + str(vid_id))
             return json.loads(data_json)
 
         mobj = re.match(self._VALID_URL, url)
@@ -39,11 +41,11 @@ class SohuIE(InfoExtractor):
 
         webpage = self._download_webpage(url, video_id)
         raw_title = self._html_search_regex(r'(?s)<title>(.+?)</title>',
-                                            webpage, u'video title')
+                                            webpage, 'video title')
         title = raw_title.partition('-')[0].strip()
 
         vid = self._html_search_regex(r'var vid ?= ?["\'](\d+)["\']', webpage,
-                                      u'video path')
+                                      'video path')
         data = _fetch_data(vid, mytv)
 
         QUALITIES = ('ori', 'super', 'high', 'nor')
@@ -51,7 +53,7 @@ class SohuIE(InfoExtractor):
                    for q in QUALITIES
                    if data['data'][q + 'Vid'] != 0]
         if not vid_ids:
-            raise ExtractorError(u'No formats available for this video')
+            raise ExtractorError('No formats available for this video')
 
         # For now, we just pick the highest available quality
         vid_id = vid_ids[-1]
@@ -69,7 +71,7 @@ class SohuIE(InfoExtractor):
                         (allot, prot, clipsURL[i], su[i]))
             part_str = self._download_webpage(
                 part_url, video_id,
-                note=u'Downloading part %d of %d' % (i + 1, part_count))
+                note='Downloading part %d of %d' % (i + 1, part_count))
 
             part_info = part_str.split('|')
             video_url = '%s%s?key=%s' % (part_info[0], su[i], part_info[3])

youtube_dl/extractor/soundcloud.py

@@ -32,7 +32,7 @@ class SoundcloudIE(InfoExtractor):
                             (?P<title>[\w\d-]+)/?
                             (?P<token>[^?]+?)?(?:[?].*)?$)
                        |(?:api\.soundcloud\.com/tracks/(?P<track_id>\d+)
-                          (?:/?\?secret_token=(?P<secret_token>[^&]+?))?$)
+                          (?:/?\?secret_token=(?P<secret_token>[^&]+))?)
                        |(?P<player>(?:w|player|p.)\.soundcloud\.com/player/?.*?url=.*)
                     )
                     '''

youtube_dl/extractor/space.py

@@ -33,5 +33,6 @@ class SpaceIE(InfoExtractor):
             # Other videos works fine with the info from the object
             brightcove_url = BrightcoveIE._extract_brightcove_url(webpage)
         if brightcove_url is None:
-            raise ExtractorError(u'The webpage does not contain a video', expected=True)
+            raise ExtractorError(
+                'The webpage does not contain a video', expected=True)
         return self.url_result(brightcove_url, BrightcoveIE.ie_key())

youtube_dl/extractor/subtitles.py

@@ -1,7 +1,8 @@
+from __future__ import unicode_literals
 from .common import InfoExtractor
 
+from ..compat import compat_str
 from ..utils import (
-    compat_str,
     ExtractorError,
 )
 
@@ -17,10 +18,10 @@ class SubtitlesInfoExtractor(InfoExtractor):
         sub_lang_list = self._get_available_subtitles(video_id, webpage)
         auto_captions_list = self._get_available_automatic_caption(video_id, webpage)
         sub_lang = ",".join(list(sub_lang_list.keys()))
-        self.to_screen(u'%s: Available subtitles for video: %s' %
+        self.to_screen('%s: Available subtitles for video: %s' %
                        (video_id, sub_lang))
         auto_lang = ",".join(auto_captions_list.keys())
-        self.to_screen(u'%s: Available automatic captions for video: %s' %
+        self.to_screen('%s: Available automatic captions for video: %s' %
                        (video_id, auto_lang))
 
     def extract_subtitles(self, video_id, webpage):
@@ -51,7 +52,7 @@ class SubtitlesInfoExtractor(InfoExtractor):
             sub_lang_list = {}
             for sub_lang in requested_langs:
                 if sub_lang not in available_subs_list:
-                    self._downloader.report_warning(u'no closed captions found in the specified language "%s"' % sub_lang)
+                    self._downloader.report_warning('no closed captions found in the specified language "%s"' % sub_lang)
                     continue
                 sub_lang_list[sub_lang] = available_subs_list[sub_lang]
 
@@ -70,10 +71,10 @@ class SubtitlesInfoExtractor(InfoExtractor):
         try:
             sub = self._download_subtitle_url(sub_lang, url)
         except ExtractorError as err:
-            self._downloader.report_warning(u'unable to download video subtitles for %s: %s' % (sub_lang, compat_str(err)))
+            self._downloader.report_warning('unable to download video subtitles for %s: %s' % (sub_lang, compat_str(err)))
             return
         if not sub:
-            self._downloader.report_warning(u'Did not fetch video subtitles')
+            self._downloader.report_warning('Did not fetch video subtitles')
             return
         return sub
 
@@ -94,5 +95,5 @@ class SubtitlesInfoExtractor(InfoExtractor):
         Must be redefined by the subclasses that support automatic captions,
         otherwise it will return {}
         """
-        self._downloader.report_warning(u'Automatic Captions not supported by this server')
+        self._downloader.report_warning('Automatic Captions not supported by this server')
         return {}

youtube_dl/extractor/tagesschau.py

@@ -4,10 +4,11 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..utils import parse_filesize
 
 
 class TagesschauIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?tagesschau\.de/multimedia/video/video(?P<id>-?[0-9]+)\.html'
+    _VALID_URL = r'https?://(?:www\.)?tagesschau\.de/multimedia/(?:sendung/ts|video/video)(?P<id>-?[0-9]+)\.html'
 
     _TESTS = [{
         'url': 'http://www.tagesschau.de/multimedia/video/video1399128.html',
@@ -19,6 +20,16 @@ class TagesschauIE(InfoExtractor):
             'description': 'md5:69da3c61275b426426d711bde96463ab',
             'thumbnail': 're:^http:.*\.jpg$',
         },
+    }, {
+        'url': 'http://www.tagesschau.de/multimedia/sendung/ts-5727.html',
+        'md5': '3c54c1f6243d279b706bde660ceec633',
+        'info_dict': {
+            'id': '5727',
+            'ext': 'mp4',
+            'description': 'md5:695c01bfd98b7e313c501386327aea59',
+            'title': 'Sendung: tagesschau \t04.12.2014 20:00 Uhr',
+            'thumbnail': 're:^http:.*\.jpg$',
+        }
     }]
 
     _FORMATS = {
@@ -28,24 +39,19 @@ class TagesschauIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
+        video_id = self._match_id(url)
-        video_id = mobj.group('id')
+        display_id = video_id.lstrip('-')
-
-        if video_id.startswith('-'):
-            display_id = video_id.strip('-')
-        else:
-            display_id = video_id
-
         webpage = self._download_webpage(url, display_id)
 
+        player_url = self._html_search_meta(
+            'twitter:player', webpage, 'player URL', default=None)
+        if player_url:
             playerpage = self._download_webpage(
-            'http://www.tagesschau.de/multimedia/video/video%s~player_autoplay-true.html' % video_id,
+                player_url, display_id, 'Downloading player page')
-            display_id, 'Downloading player page')
 
             medias = re.findall(
                 r'"(http://media.+?)", type:"video/(.+?)", quality:"(.+?)"',
                 playerpage)
-
             formats = []
             for url, ext, res in medias:
                 f = {
@@ -55,15 +61,60 @@ class TagesschauIE(InfoExtractor):
                 }
                 f.update(self._FORMATS.get(res, {}))
                 formats.append(f)
+            thumbnail_fn = re.findall(r'"(/multimedia/.+?\.jpg)"', playerpage)[-1]
+            title = self._og_search_title(webpage).strip()
+            description = self._og_search_description(webpage).strip()
+        else:
+            download_text = self._search_regex(
+                r'(?s)<p>Wir bieten dieses Video in folgenden Formaten zum Download an:</p>\s*<div class="controls">(.*?)</div>\s*<p>',
+                webpage, 'download links')
+            links = re.finditer(
+                r'<div class="button" title="(?P<title>[^"]*)"><a href="(?P<url>[^"]+)">(?P<name>.+?)</a></div>',
+                webpage)
+            formats = []
+            for l in links:
+                format_id = self._search_regex(
+                    r'.*/[^/.]+\.([^/]+)\.[^/.]+', l.group('url'), 'format ID')
+                format = {
+                    'format_id': format_id,
+                    'url': l.group('url'),
+                    'format_name': l.group('name'),
+                }
+                m = re.match(
+                    r'''(?x)
+                        Video:\s*(?P<vcodec>[a-zA-Z0-9/._-]+)\s*&\#10;
+                        (?P<width>[0-9]+)x(?P<height>[0-9]+)px&\#10;
+                        (?P<vbr>[0-9]+)kbps&\#10;
+                        Audio:\s*(?P<abr>[0-9]+)kbps,\s*(?P<audio_desc>[A-Za-z\.0-9]+)&\#10;
+                        Gr&ouml;&szlig;e:\s*(?P<filesize_approx>[0-9.,]+\s+[a-zA-Z]*B)''',
+                    l.group('title'))
+                if m:
+                    format.update({
+                        'format_note': m.group('audio_desc'),
+                        'vcodec': m.group('vcodec'),
+                        'width': int(m.group('width')),
+                        'height': int(m.group('height')),
+                        'abr': int(m.group('abr')),
+                        'vbr': int(m.group('vbr')),
+                        'filesize_approx': parse_filesize(m.group('filesize_approx')),
+                    })
+                formats.append(format)
+            thumbnail_fn = self._search_regex(
+                r'(?s)<img alt="Sendungsbild".*?src="([^"]+)"',
+                webpage, 'thumbnail', fatal=False)
+            description = self._html_search_regex(
+                r'(?s)<p class="teasertext">(.*?)</p>',
+                webpage, 'description', fatal=False)
+            title = self._html_search_regex(
+                r'<span class="headline".*?>(.*?)</span>', webpage, 'title')
 
         self._sort_formats(formats)
-
+        thumbnail = 'http://www.tagesschau.de' + thumbnail_fn
-        thumbnail = re.findall(r'"(/multimedia/.+?\.jpg)"', playerpage)[-1]
 
         return {
             'id': display_id,
-            'title': self._og_search_title(webpage).strip(),
+            'title': title,
-            'thumbnail': 'http://www.tagesschau.de' + thumbnail,
+            'thumbnail': thumbnail,
             'formats': formats,
-            'description': self._og_search_description(webpage).strip(),
+            'description': description,
         }

youtube_dl/extractor/tass.py

@@ -0,0 +1,62 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    js_to_json,
+    qualities,
+)
+
+
+class TassIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:tass\.ru|itar-tass\.com)/[^/]+/(?P<id>\d+)'
+    _TESTS = [
+        {
+            'url': 'http://tass.ru/obschestvo/1586870',
+            'md5': '3b4cdd011bc59174596b6145cda474a4',
+            'info_dict': {
+                'id': '1586870',
+                'ext': 'mp4',
+                'title': 'Посетителям московского зоопарка показали красную панду',
+                'description': 'Приехавшую из Дублина Зейну можно увидеть в павильоне "Кошки тропиков"',
+                'thumbnail': 're:^https?://.*\.jpg$',
+            },
+        },
+        {
+            'url': 'http://itar-tass.com/obschestvo/1600009',
+            'only_matching': True,
+        },
+    ]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        sources = json.loads(js_to_json(self._search_regex(
+            r'(?s)sources\s*:\s*(\[.+?\])', webpage, 'sources')))
+
+        quality = qualities(['sd', 'hd'])
+
+        formats = []
+        for source in sources:
+            video_url = source.get('file')
+            if not video_url or not video_url.startswith('http') or not video_url.endswith('.mp4'):
+                continue
+            label = source.get('label')
+            formats.append({
+                'url': video_url,
+                'format_id': label,
+                'quality': quality(label),
+            })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': self._og_search_title(webpage),
+            'description': self._og_search_description(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'formats': formats,
+        }

youtube_dl/extractor/ted.py

@@ -199,8 +199,9 @@ class TEDIE(SubtitlesInfoExtractor):
         webpage = self._download_webpage(url, name)
 
         config_json = self._html_search_regex(
-            r"data-config='([^']+)", webpage, 'config')
+            r'"pages\.jwplayer"\s*,\s*({.+?})\s*\)\s*</script>',
-        config = json.loads(config_json)
+            webpage, 'config')
+        config = json.loads(config_json)['config']
         video_url = config['video']['url']
         thumbnail = config.get('image', {}).get('url')
 

youtube_dl/extractor/trilulilu.py

@@ -1,28 +1,28 @@
+from __future__ import unicode_literals
+
 import json
-import re
 
 from .common import InfoExtractor
 
 
 class TriluliluIE(InfoExtractor):
-    _VALID_URL = r'(?x)(?:https?://)?(?:www\.)?trilulilu\.ro/video-(?P<category>[^/]+)/(?P<video_id>[^/]+)'
+    _VALID_URL = r'https?://(?:www\.)?trilulilu\.ro/video-[^/]+/(?P<id>[^/]+)'
     _TEST = {
-        u"url": u"http://www.trilulilu.ro/video-animatie/big-buck-bunny-1",
+        'url': 'http://www.trilulilu.ro/video-animatie/big-buck-bunny-1',
-        u'file': u"big-buck-bunny-1.mp4",
+        'info_dict': {
-        u'info_dict': {
+            'id': 'big-buck-bunny-1',
-            u"title": u"Big Buck Bunny",
+            'ext': 'mp4',
-            u"description": u":) pentru copilul din noi",
+            'title': 'Big Buck Bunny',
+            'description': ':) pentru copilul din noi',
         },
         # Server ignores Range headers (--test)
-        u"params": {
+        'params': {
-            u"skip_download": True
+            'skip_download': True
         }
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
+        video_id = self._match_id(url)
-        video_id = mobj.group('video_id')
-
         webpage = self._download_webpage(url, video_id)
 
         title = self._og_search_title(webpage)
@@ -30,20 +30,20 @@ class TriluliluIE(InfoExtractor):
         description = self._og_search_description(webpage)
 
         log_str = self._search_regex(
-            r'block_flash_vars[ ]=[ ]({[^}]+})', webpage, u'log info')
+            r'block_flash_vars[ ]=[ ]({[^}]+})', webpage, 'log info')
         log = json.loads(log_str)
 
-        format_url = (u'http://fs%(server)s.trilulilu.ro/%(hash)s/'
+        format_url = ('http://fs%(server)s.trilulilu.ro/%(hash)s/'
-                      u'video-formats2' % log)
+                      'video-formats2' % log)
         format_doc = self._download_xml(
             format_url, video_id,
-            note=u'Downloading formats',
+            note='Downloading formats',
-            errnote=u'Error while downloading formats')
+            errnote='Error while downloading formats')
 
         video_url_template = (
-            u'http://fs%(server)s.trilulilu.ro/stream.php?type=video'
+            'http://fs%(server)s.trilulilu.ro/stream.php?type=video'
-            u'&source=site&hash=%(hash)s&username=%(userid)s&'
+            '&source=site&hash=%(hash)s&username=%(userid)s&'
-            u'key=ministhebest&format=%%s&sig=&exp=' %
+            'key=ministhebest&format=%%s&sig=&exp=' %
             log)
         formats = [
             {

youtube_dl/extractor/tudou.py

@@ -73,7 +73,7 @@ class TudouIE(InfoExtractor):
         result = []
         len_parts = len(parts)
         if len_parts > 1:
-            self.to_screen(u'%s: found %s parts' % (video_id, len_parts))
+            self.to_screen('%s: found %s parts' % (video_id, len_parts))
         for part in parts:
             part_id = part['k']
             final_url = self._url_for_id(part_id, quality)

youtube_dl/extractor/tunein.py

@@ -19,6 +19,7 @@ class TuneInIE(InfoExtractor):
         |tun\.in/(?P<redirect_id>[A-Za-z0-9]+)
     )
     '''
+    _API_URL_TEMPLATE = 'http://tunein.com/tuner/tune/?stationId={0:}&tuneType=Station'
 
     _INFO_DICT = {
         'id': '34682',
@@ -56,13 +57,10 @@ class TuneInIE(InfoExtractor):
             mobj = re.match(self._VALID_URL, url)
         station_id = mobj.group('id')
 
-        webpage = self._download_webpage(
+        station_info = self._download_json(
-            url, station_id, note='Downloading station webpage')
+            self._API_URL_TEMPLATE.format(station_id),
+            station_id, note='Downloading station JSON')
 
-        payload = self._html_search_regex(
-            r'(?m)TuneIn\.payload\s*=\s*(\{[^$]+?)$', webpage, 'JSON data')
-        json_data = json.loads(payload)
-        station_info = json_data['Station']['broadcast']
         title = station_info['Title']
         thumbnail = station_info.get('Logo')
         location = station_info.get('Location')

youtube_dl/extractor/tvp.py

@@ -1,40 +1,35 @@
-import json
+from __future__ import unicode_literals
-import re
 
 from .common import InfoExtractor
 
 
 class TvpIE(InfoExtractor):
-    IE_NAME = u'tvp.pl'
+    IE_NAME = 'tvp.pl'
     _VALID_URL = r'https?://www\.tvp\.pl/.*?wideo/(?P<date>\d+)/(?P<id>\d+)'
 
     _TEST = {
-        u'url': u'http://www.tvp.pl/warszawa/magazyny/campusnews/wideo/31102013/12878238',
+        'url': 'http://www.tvp.pl/warszawa/magazyny/campusnews/wideo/31102013/12878238',
-        u'md5': u'148408967a6a468953c0a75cbdaf0d7a',
+        'md5': '148408967a6a468953c0a75cbdaf0d7a',
-        u'file': u'12878238.wmv',
+        'info_dict': {
-        u'info_dict': {
+            'id': '12878238',
-            u'title': u'31.10.2013 - Odcinek 2',
+            'ext': 'wmv',
-            u'description': u'31.10.2013 - Odcinek 2',
+            'title': '31.10.2013 - Odcinek 2',
+            'description': '31.10.2013 - Odcinek 2',
         },
-        u'skip': u'Download has to use same server IP as extraction. Therefore, a good (load-balancing) DNS resolver will make the download fail.'
+        'skip': 'Download has to use same server IP as extraction. Therefore, a good (load-balancing) DNS resolver will make the download fail.'
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
+        video_id = self._match_id(url)
-        video_id = mobj.group('id')
         webpage = self._download_webpage(url, video_id)
         json_url = 'http://www.tvp.pl/pub/stat/videofileinfo?video_id=%s' % video_id
-        json_params = self._download_webpage(
+        params = self._download_json(
-            json_url, video_id, u"Downloading video metadata")
+            json_url, video_id, "Downloading video metadata")
-
-        params = json.loads(json_params)
-        self.report_extraction(video_id)
         video_url = params['video_url']
 
-        title = self._og_search_title(webpage, fatal=True)
         return {
             'id': video_id,
-            'title': title,
+            'title': self._og_search_title(webpage),
             'ext': 'wmv',
             'url': video_url,
             'description': self._og_search_description(webpage),

youtube_dl/extractor/twentyfourvideo.py

@@ -0,0 +1,109 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    parse_iso8601,
+    int_or_none,
+)
+
+
+class TwentyFourVideoIE(InfoExtractor):
+    IE_NAME = '24video'
+    _VALID_URL = r'https?://(?:www\.)?24video\.net/(?:video/(?:view|xml)/|player/new24_play\.swf\?id=)(?P<id>\d+)'
+
+    _TESTS = [
+        {
+            'url': 'http://www.24video.net/video/view/1044982',
+            'md5': '48dd7646775690a80447a8dca6a2df76',
+            'info_dict': {
+                'id': '1044982',
+                'ext': 'mp4',
+                'title': 'Эротика каменного века',
+                'description': 'Как смотрели порно в каменном веке.',
+                'thumbnail': 're:^https?://.*\.jpg$',
+                'uploader': 'SUPERTELO',
+                'duration': 31,
+                'timestamp': 1275937857,
+                'upload_date': '20100607',
+                'age_limit': 18,
+                'like_count': int,
+                'dislike_count': int,
+            },
+        },
+        {
+            'url': 'http://www.24video.net/player/new24_play.swf?id=1044982',
+            'only_matching': True,
+        }
+    ]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(
+            'http://www.24video.net/video/view/%s' % video_id, video_id)
+
+        title = self._og_search_title(webpage)
+        description = self._html_search_regex(
+            r'<span itemprop="description">([^<]+)</span>', webpage, 'description', fatal=False)
+        thumbnail = self._og_search_thumbnail(webpage)
+        duration = int_or_none(self._og_search_property(
+            'duration', webpage, 'duration', fatal=False))
+        timestamp = parse_iso8601(self._search_regex(
+            r'<time id="video-timeago" datetime="([^"]+)" itemprop="uploadDate">',
+            webpage, 'upload date'))
+
+        uploader = self._html_search_regex(
+            r'Загрузил\s*<a href="/jsecUser/movies/[^"]+" class="link">([^<]+)</a>',
+            webpage, 'uploader', fatal=False)
+
+        view_count = int_or_none(self._html_search_regex(
+            r'<span class="video-views">(\d+) просмотр',
+            webpage, 'view count', fatal=False))
+        comment_count = int_or_none(self._html_search_regex(
+            r'<div class="comments-title" id="comments-count">(\d+) комментари',
+            webpage, 'comment count', fatal=False))
+
+        formats = []
+
+        pc_video = self._download_xml(
+            'http://www.24video.net/video/xml/%s?mode=play' % video_id,
+            video_id, 'Downloading PC video URL').find('.//video')
+
+        formats.append({
+            'url': pc_video.attrib['url'],
+            'format_id': 'pc',
+            'quality': 1,
+        })
+
+        like_count = int_or_none(pc_video.get('ratingPlus'))
+        dislike_count = int_or_none(pc_video.get('ratingMinus'))
+        age_limit = 18 if pc_video.get('adult') == 'true' else 0
+
+        mobile_video = self._download_xml(
+            'http://www.24video.net/video/xml/%s' % video_id,
+            video_id, 'Downloading mobile video URL').find('.//video')
+
+        formats.append({
+            'url': mobile_video.attrib['url'],
+            'format_id': 'mobile',
+            'quality': 0,
+        })
+
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'uploader': uploader,
+            'duration': duration,
+            'timestamp': timestamp,
+            'view_count': view_count,
+            'comment_count': comment_count,
+            'like_count': like_count,
+            'dislike_count': dislike_count,
+            'age_limit': age_limit,
+            'formats': formats,
+        }

youtube_dl/extractor/udemy.py

@@ -40,8 +40,24 @@ class UdemyIE(InfoExtractor):
                 error_str += ' - %s' % error_data.get('formErrors')
             raise ExtractorError(error_str, expected=True)
 
-    def _download_json(self, url, video_id, note='Downloading JSON metadata'):
+    def _download_json(self, url_or_request, video_id, note='Downloading JSON metadata'):
-        response = super(UdemyIE, self)._download_json(url, video_id, note)
+        headers = {
+            'X-Udemy-Snail-Case': 'true',
+            'X-Requested-With': 'XMLHttpRequest',
+        }
+        for cookie in self._downloader.cookiejar:
+            if cookie.name == 'client_id':
+                headers['X-Udemy-Client-Id'] = cookie.value
+            elif cookie.name == 'access_token':
+                headers['X-Udemy-Bearer-Token'] = cookie.value
+
+        if isinstance(url_or_request, compat_urllib_request.Request):
+            for header, value in headers.items():
+                url_or_request.add_header(header, value)
+        else:
+            url_or_request = compat_urllib_request.Request(url_or_request, headers=headers)
+
+        response = super(UdemyIE, self)._download_json(url_or_request, video_id, note)
         self._handle_error(response)
         return response
 
@@ -62,7 +78,9 @@ class UdemyIE(InfoExtractor):
         if login_popup == '<div class="run-command close-popup redirect" data-url="https://www.udemy.com/"></div>':
             return
 
-        csrf = self._html_search_regex(r'<input type="hidden" name="csrf" value="(.+?)"', login_popup, 'csrf token')
+        csrf = self._html_search_regex(
+            r'<input type="hidden" name="csrf" value="(.+?)"',
+            login_popup, 'csrf token')
 
         login_form = {
             'email': username,
@@ -71,42 +89,49 @@ class UdemyIE(InfoExtractor):
             'displayType': 'json',
             'isSubmitted': '1',
         }
-        request = compat_urllib_request.Request(self._LOGIN_URL, compat_urllib_parse.urlencode(login_form))
+        request = compat_urllib_request.Request(
-        response = self._download_json(request, None, 'Logging in as %s' % username)
+            self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
+        response = self._download_json(
+            request, None, 'Logging in as %s' % username)
 
         if 'returnUrl' not in response:
             raise ExtractorError('Unable to log in')
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
+        lecture_id = self._match_id(url)
-        lecture_id = mobj.group('id')
 
         lecture = self._download_json(
-            'https://www.udemy.com/api-1.1/lectures/%s' % lecture_id, lecture_id, 'Downloading lecture JSON')
+            'https://www.udemy.com/api-1.1/lectures/%s' % lecture_id,
+            lecture_id, 'Downloading lecture JSON')
 
-        if lecture['assetType'] != 'Video':
+        asset_type = lecture.get('assetType') or lecture.get('asset_type')
-            raise ExtractorError('Lecture %s is not a video' % lecture_id, expected=True)
+        if asset_type != 'Video':
+            raise ExtractorError(
+                'Lecture %s is not a video' % lecture_id, expected=True)
 
         asset = lecture['asset']
 
-        stream_url = asset['streamUrl']
+        stream_url = asset.get('streamUrl') or asset.get('stream_url')
         mobj = re.search(r'(https?://www\.youtube\.com/watch\?v=.*)', stream_url)
         if mobj:
             return self.url_result(mobj.group(1), 'Youtube')
 
         video_id = asset['id']
-        thumbnail = asset['thumbnailUrl']
+        thumbnail = asset.get('thumbnailUrl') or asset.get('thumbnail_url')
         duration = asset['data']['duration']
 
-        download_url = asset['downloadUrl']
+        download_url = asset.get('downloadUrl') or asset.get('download_url')
+
+        video = download_url.get('Video') or download_url.get('video')
+        video_480p = download_url.get('Video480p') or download_url.get('video_480p')
 
         formats = [
             {
-                'url': download_url['Video480p'][0],
+                'url': video_480p[0],
                 'format_id': '360p',
             },
             {
-                'url': download_url['Video'][0],
+                'url': video[0],
                 'format_id': '720p',
             },
         ]
@@ -140,25 +165,29 @@ class UdemyCourseIE(UdemyIE):
         course_path = mobj.group('coursepath')
 
         response = self._download_json(
-            'https://www.udemy.com/api-1.1/courses/%s' % course_path, course_path, 'Downloading course JSON')
+            'https://www.udemy.com/api-1.1/courses/%s' % course_path,
+            course_path, 'Downloading course JSON')
 
         course_id = int(response['id'])
         course_title = response['title']
 
         webpage = self._download_webpage(
-            'https://www.udemy.com/course/subscribe/?courseId=%s' % course_id, course_id, 'Enrolling in the course')
+            'https://www.udemy.com/course/subscribe/?courseId=%s' % course_id,
+            course_id, 'Enrolling in the course')
 
         if self._SUCCESSFULLY_ENROLLED in webpage:
             self.to_screen('%s: Successfully enrolled in' % course_id)
         elif self._ALREADY_ENROLLED in webpage:
             self.to_screen('%s: Already enrolled in' % course_id)
 
-        response = self._download_json('https://www.udemy.com/api-1.1/courses/%s/curriculum' % course_id,
+        response = self._download_json(
+            'https://www.udemy.com/api-1.1/courses/%s/curriculum' % course_id,
             course_id, 'Downloading course curriculum')
 
         entries = [
-            self.url_result('https://www.udemy.com/%s/#/lecture/%s' % (course_path, asset['id']), 'Udemy')
+            self.url_result(
-            for asset in response if asset.get('assetType') == 'Video'
+                'https://www.udemy.com/%s/#/lecture/%s' % (course_path, asset['id']), 'Udemy')
+            for asset in response if asset.get('assetType') or asset.get('asset_type') == 'Video'
         ]
 
         return self.playlist_result(entries, course_id, course_title)

youtube_dl/extractor/vevo.py

@@ -13,7 +13,7 @@ from ..utils import (
 class VevoIE(InfoExtractor):
     """
     Accepts urls from vevo.com or in the format 'vevo:{id}'
-    (currently used by MTVIE)
+    (currently used by MTVIE and MySpaceIE)
     """
     _VALID_URL = r'''(?x)
         (?:https?://www\.vevo\.com/watch/(?:[^/]+/(?:[^/]+/)?)?|

youtube_dl/extractor/vgtv.py

@@ -17,7 +17,7 @@ class VGTVIE(InfoExtractor):
             'info_dict': {
                 'id': '84196',
                 'ext': 'mp4',
-                'title': 'Hevnen er søt episode 1:10 - Abu',
+                'title': 'Hevnen er søt: Episode 10 - Abu',
                 'description': 'md5:e25e4badb5f544b04341e14abdc72234',
                 'thumbnail': 're:^https?://.*\.jpg',
                 'duration': 648.000,
@@ -35,7 +35,7 @@ class VGTVIE(InfoExtractor):
                 'title': 'OPPTAK: VGTV følger EM-kvalifiseringen',
                 'description': 'md5:3772d9c0dc2dff92a886b60039a7d4d3',
                 'thumbnail': 're:^https?://.*\.jpg',
-                'duration': 9056.000,
+                'duration': 9103.0,
                 'timestamp': 1410113864,
                 'upload_date': '20140907',
                 'view_count': int,

youtube_dl/extractor/videofyme.py

@@ -1,32 +1,33 @@
-import re
+from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from ..utils import (
     find_xpath_attr,
-    determine_ext,
+    int_or_none,
 )
 
 
 class VideofyMeIE(InfoExtractor):
-    _VALID_URL = r'https?://(www\.videofy\.me/.+?|p\.videofy\.me/v)/(?P<id>\d+)(&|#|$)'
+    _VALID_URL = r'https?://(?:www\.videofy\.me/.+?|p\.videofy\.me/v)/(?P<id>\d+)(&|#|$)'
-    IE_NAME = u'videofy.me'
+    IE_NAME = 'videofy.me'
 
     _TEST = {
-        u'url': u'http://www.videofy.me/thisisvideofyme/1100701',
+        'url': 'http://www.videofy.me/thisisvideofyme/1100701',
-        u'file': u'1100701.mp4',
+        'md5': 'c77d700bdc16ae2e9f3c26019bd96143',
-        u'md5': u'c77d700bdc16ae2e9f3c26019bd96143',
+        'info_dict': {
-        u'info_dict': {
+            'id': '1100701',
-            u'title': u'This is VideofyMe',
+            'ext': 'mp4',
-            u'description': None,
+            'title': 'This is VideofyMe',
-            u'uploader': u'VideofyMe',
+            'description': None,
-            u'uploader_id': u'thisisvideofyme',
+            'uploader': 'VideofyMe',
+            'uploader_id': 'thisisvideofyme',
+            'view_count': int,
         },
 
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
+        video_id = self._match_id(url)
-        video_id = mobj.group('id')
         config = self._download_xml('http://sunshine.videofy.me/?videoId=%s' % video_id,
                                     video_id)
         video = config.find('video')
@@ -34,14 +35,16 @@ class VideofyMeIE(InfoExtractor):
         url_node = next(node for node in [find_xpath_attr(sources, 'source', 'id', 'HQ %s' % key)
                                           for key in ['on', 'av', 'off']] if node is not None)
         video_url = url_node.find('url').text
+        view_count = int_or_none(self._search_regex(
+            r'([0-9]+)', video.find('views').text, 'view count', fatal=False))
 
-        return {'id': video_id,
+        return {
+            'id': video_id,
             'title': video.find('title').text,
             'url': video_url,
-                'ext': determine_ext(video_url),
             'thumbnail': video.find('thumb').text,
             'description': video.find('description').text,
             'uploader': config.find('blog/name').text,
             'uploader_id': video.find('identifier').text,
-                'view_count': re.search(r'\d+', video.find('views').text).group(),
+            'view_count': view_count,
         }

youtube_dl/extractor/videopremium.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import re
 import random
 
@@ -5,23 +7,22 @@ from .common import InfoExtractor
 
 
 class VideoPremiumIE(InfoExtractor):
-    _VALID_URL = r'(?:https?://)?(?:www\.)?videopremium\.(?:tv|me)/(?P<id>\w+)(?:/.*)?'
+    _VALID_URL = r'https?://(?:www\.)?videopremium\.(?:tv|me)/(?P<id>\w+)(?:/.*)?'
     _TEST = {
-        u'url': u'http://videopremium.tv/4w7oadjsf156',
+        'url': 'http://videopremium.tv/4w7oadjsf156',
-        u'file': u'4w7oadjsf156.f4v',
+        'info_dict': {
-        u'info_dict': {
+            'id': '4w7oadjsf156',
-            u"title": u"youtube-dl_test_video____a_________-BaW_jenozKc.mp4.mp4"
+            'ext': 'f4v',
+            'title': 'youtube-dl_test_video____a_________-BaW_jenozKc.mp4.mp4'
         },
-        u'params': {
+        'params': {
-            u'skip_download': True,
+            'skip_download': True,
         },
-        u'skip': u'Test file has been deleted.',
+        'skip': 'Test file has been deleted.',
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
+        video_id = self._match_id(url)
-
-        video_id = mobj.group('id')
         webpage_url = 'http://videopremium.tv/' + video_id
         webpage = self._download_webpage(webpage_url, video_id)
 
@@ -29,10 +30,10 @@ class VideoPremiumIE(InfoExtractor):
             # Download again, we need a cookie
             webpage = self._download_webpage(
                 webpage_url, video_id,
-                note=u'Downloading webpage again (with cookie)')
+                note='Downloading webpage again (with cookie)')
 
         video_title = self._html_search_regex(
-            r'<h2(?:.*?)>\s*(.+?)\s*<', webpage, u'video title')
+            r'<h2(?:.*?)>\s*(.+?)\s*<', webpage, 'video title')
 
         return {
             'id': video_id,

youtube_dl/extractor/vine.py

@@ -63,29 +63,36 @@ class VineIE(InfoExtractor):
 
 class VineUserIE(InfoExtractor):
     IE_NAME = 'vine:user'
-    _VALID_URL = r'(?:https?://)?vine\.co/(?P<user>[^/]+)/?(\?.*)?$'
+    _VALID_URL = r'(?:https?://)?vine\.co/(?P<u>u/)?(?P<user>[^/]+)/?(\?.*)?$'
     _VINE_BASE_URL = "https://vine.co/"
-    _TEST = {
+    _TESTS = [
+        {
             'url': 'https://vine.co/Visa',
             'info_dict': {
                 'id': 'Visa',
             },
             'playlist_mincount': 46,
-    }
+        },
+        {
+            'url': 'https://vine.co/u/941705360593584128',
+            'only_matching': True,
+        },
+    ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         user = mobj.group('user')
+        u = mobj.group('u')
 
-        profile_url = "%sapi/users/profiles/vanity/%s" % (
+        profile_url = "%sapi/users/profiles/%s%s" % (
-            self._VINE_BASE_URL, user)
+            self._VINE_BASE_URL, 'vanity/' if not u else '', user)
         profile_data = self._download_json(
             profile_url, user, note='Downloading user profile data')
 
         user_id = profile_data['data']['userId']
         timeline_data = []
         for pagenum in itertools.count(1):
-            timeline_url = "%sapi/timelines/users/%s?page=%s" % (
+            timeline_url = "%sapi/timelines/users/%s?page=%s&size=100" % (
                 self._VINE_BASE_URL, user_id, pagenum)
             timeline_page = self._download_json(
                 timeline_url, user, note='Downloading page %d' % pagenum)

youtube_dl/extractor/xminus.py

@@ -1,6 +1,8 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..compat import (
     compat_chr,
@@ -25,6 +27,7 @@ class XMinusIE(InfoExtractor):
             'tbr': 320,
             'filesize_approx': 5900000,
             'view_count': int,
+            'description': 'md5:03238c5b663810bc79cf42ef3c03e371',
         }
     }
 
@@ -48,9 +51,14 @@ class XMinusIE(InfoExtractor):
         view_count = int_or_none(self._html_search_regex(
             r'<div class="quality.*?► ([0-9]+)',
             webpage, 'view count', fatal=False))
+        description = self._html_search_regex(
+            r'(?s)<div id="song_texts">(.*?)</div><br',
+            webpage, 'song lyrics', fatal=False)
+        if description:
+            description = re.sub(' *\r *', '\n', description)
 
         enc_token = self._html_search_regex(
-            r'data-mt="(.*?)"', webpage, 'enc_token')
+            r'minus_track\.tkn="(.+?)"', webpage, 'enc_token')
         token = ''.join(
             c if pos == 3 else compat_chr(compat_ord(c) - 1)
             for pos, c in enumerate(reversed(enc_token)))
@@ -64,4 +72,5 @@ class XMinusIE(InfoExtractor):
             'filesize_approx': filesize_approx,
             'tbr': tbr,
             'view_count': view_count,
+            'description': description,
         }

youtube_dl/extractor/youporn.py

@@ -49,7 +49,7 @@ class YouPornIE(InfoExtractor):
         try:
             params = json.loads(json_params)
         except:
-            raise ExtractorError(u'Invalid JSON')
+            raise ExtractorError('Invalid JSON')
 
         self.report_extraction(video_id)
         try:
@@ -103,7 +103,7 @@ class YouPornIE(InfoExtractor):
         self._sort_formats(formats)
 
         if not formats:
-            raise ExtractorError(u'ERROR: no known formats available for video')
+            raise ExtractorError('ERROR: no known formats available for video')
 
         return {
             'id': video_id,

youtube_dl/extractor/youtube.py

@@ -7,6 +7,7 @@ import itertools
 import json
 import os.path
 import re
+import time
 import traceback
 
 from .common import InfoExtractor, SearchInfoExtractor
@@ -38,17 +39,15 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
     """Provide base functions for Youtube extractors"""
     _LOGIN_URL = 'https://accounts.google.com/ServiceLogin'
     _TWOFACTOR_URL = 'https://accounts.google.com/SecondFactor'
-    _LANG_URL = r'https://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
-    _AGE_URL = 'https://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
     _NETRC_MACHINE = 'youtube'
     # If True it will raise an error if no login info is provided
     _LOGIN_REQUIRED = False
 
     def _set_language(self):
-        return bool(self._download_webpage(
+        self._set_cookie(
-            self._LANG_URL, None,
+            '.youtube.com', 'PREF', 'f1=50000000&hl=en',
-            note='Setting language', errnote='unable to set language',
+            # YouTube sets the expire time to about two months
-            fatal=False))
+            expire_time=time.time() + 2 * 30 * 24 * 3600)
 
     def _login(self):
         """
@@ -176,30 +175,12 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
             return False
         return True
 
-    def _confirm_age(self):
-        age_form = {
-            'next_url': '/',
-            'action_confirm': 'Confirm',
-        }
-        req = compat_urllib_request.Request(
-            self._AGE_URL,
-            compat_urllib_parse.urlencode(age_form).encode('ascii')
-        )
-
-        self._download_webpage(
-            req, None,
-            note='Confirming age', errnote='Unable to confirm age',
-            fatal=False)
-
     def _real_initialize(self):
         if self._downloader is None:
             return
-        if self._get_login_info()[0] is not None:
+        self._set_language()
-            if not self._set_language():
-                return
         if not self._login():
             return
-        self._confirm_age()
 
 
 class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
@@ -305,6 +286,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
         '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
         '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'},
         '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'},
+        '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'vcodec': 'VP9'},
 
         # Dash webm audio
         '171': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'abr': 128, 'preference': -50},
@@ -398,8 +380,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
             'info_dict': {
                 'id': 'IB3lcPjvWLA',
                 'ext': 'm4a',
-                'title': 'Afrojack - The Spark ft. Spree Wilson',
+                'title': 'Afrojack, Spree Wilson - The Spark ft. Spree Wilson',
-                'description': 'md5:9717375db5a9a3992be4668bbf3bc0a8',
+                'description': 'md5:12e7067fa6735a77bdcbb58cb1187d2d',
                 'uploader': 'AfrojackVEVO',
                 'uploader_id': 'AfrojackVEVO',
                 'upload_date': '20131011',
@@ -421,7 +403,20 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
                 'title': 'Burning Everyone\'s Koran',
                 'description': 'SUBSCRIBE: http://www.youtube.com/saturninefilms\n\nEven Obama has taken a stand against freedom on this issue: http://www.huffingtonpost.com/2010/09/09/obama-gma-interview-quran_n_710282.html',
             }
-        }
+        },
+        # Normal age-gate video (No vevo, embed allowed)
+        {
+            'url': 'http://youtube.com/watch?v=HtVdAasjOgU',
+            'info_dict': {
+                'id': 'HtVdAasjOgU',
+                'ext': 'mp4',
+                'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
+                'description': 'md5:eca57043abae25130f58f655ad9a7771',
+                'uploader': 'The Witcher',
+                'uploader_id': 'WitcherGame',
+                'upload_date': '20140605',
+            },
+        },
     ]
 
     def __init__(self, *args, **kwargs):
@@ -609,9 +604,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
             return {}
         player_config = json.loads(mobj.group(1))
         try:
-            args = player_config[u'args']
+            args = player_config['args']
-            caption_url = args[u'ttsurl']
+            caption_url = args['ttsurl']
-            timestamp = args[u'timestamp']
+            timestamp = args['timestamp']
             # We get the available subtitles
             list_params = compat_urllib_parse.urlencode({
                 'type': 'list',
@@ -684,16 +679,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
 
         # Get video webpage
         url = proto + '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1&bpctr=9999999999' % video_id
-        pref_cookies = [
-            c for c in self._downloader.cookiejar
-            if c.domain == '.youtube.com' and c.name == 'PREF']
-        for pc in pref_cookies:
-            if 'hl=' in pc.value:
-                pc.value = re.sub(r'hl=[^&]+', 'hl=en', pc.value)
-            else:
-                if pc.value:
-                    pc.value += '&'
-                pc.value += 'hl=en'
         video_webpage = self._download_webpage(url, video_id)
 
         # Attempt to extract SWF player URL
@@ -704,7 +689,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
             player_url = None
 
         # Get video info
-        self.report_video_info_webpage_download(video_id)
         if re.search(r'player-age-gate-content">', video_webpage) is not None:
             age_gate = True
             # We simulate the access to the video from www.youtube.com/v/{video_id}
@@ -723,11 +707,28 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
             video_info = compat_parse_qs(video_info_webpage)
         else:
             age_gate = False
+            try:
+                # Try looking directly into the video webpage
+                mobj = re.search(r';ytplayer\.config\s*=\s*({.*?});', video_webpage)
+                if not mobj:
+                    raise ValueError('Could not find ytplayer.config')  # caught below
+                json_code = uppercase_escape(mobj.group(1))
+                ytplayer_config = json.loads(json_code)
+                args = ytplayer_config['args']
+                # Convert to the same format returned by compat_parse_qs
+                video_info = dict((k, [v]) for k, v in args.items())
+                if 'url_encoded_fmt_stream_map' not in args:
+                    raise ValueError('No stream_map present')  # caught below
+            except ValueError:
+                # We fallback to the get_video_info pages (used by the embed page)
+                self.report_video_info_webpage_download(video_id)
                 for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']:
-                video_info_url = (proto + '://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
+                    video_info_url = (
-                                  % (video_id, el_type))
+                        '%s://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
-                video_info_webpage = self._download_webpage(video_info_url, video_id,
+                        % (proto, video_id, el_type))
-                                                            note=False,
+                    video_info_webpage = self._download_webpage(
+                        video_info_url,
+                        video_id, note=False,
                         errnote='unable to download video info webpage')
                     video_info = compat_parse_qs(video_info_webpage)
                     if 'token' in video_info:
@@ -856,32 +857,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
         if self._downloader.params.get('writeannotations', False):
             video_annotations = self._extract_annotations(video_id)
 
-        # Decide which formats to download
-        try:
-            mobj = re.search(r';ytplayer\.config\s*=\s*({.*?});', video_webpage)
-            if not mobj:
-                raise ValueError('Could not find vevo ID')
-            json_code = uppercase_escape(mobj.group(1))
-            ytplayer_config = json.loads(json_code)
-            args = ytplayer_config['args']
-            # Easy way to know if the 's' value is in url_encoded_fmt_stream_map
-            # this signatures are encrypted
-            if 'url_encoded_fmt_stream_map' not in args:
-                raise ValueError('No stream_map present')  # caught below
-            re_signature = re.compile(r'[&,]s=')
-            m_s = re_signature.search(args['url_encoded_fmt_stream_map'])
-            if m_s is not None:
-                self.to_screen('%s: Encrypted signatures detected.' % video_id)
-                video_info['url_encoded_fmt_stream_map'] = [args['url_encoded_fmt_stream_map']]
-            m_s = re_signature.search(args.get('adaptive_fmts', ''))
-            if m_s is not None:
-                if 'adaptive_fmts' in video_info:
-                    video_info['adaptive_fmts'][0] += ',' + args['adaptive_fmts']
-                else:
-                    video_info['adaptive_fmts'] = [args['adaptive_fmts']]
-        except ValueError:
-            pass
-
         def _map_to_format_list(urlmap):
             formats = []
             for itag, video_real_url in urlmap.items():
@@ -974,10 +949,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
                 # However, in the case of an age restriction there won't be any embedded dashmpd in the video_webpage.
                 # Luckily, it seems, this case uses some kind of default signature (len == 86), so the
                 # combination of get_video_info and the _static_decrypt_signature() decryption fallback will work here.
-                if age_gate:
                 dash_manifest_url = video_info.get('dashmpd')[0]
-                else:
-                    dash_manifest_url = ytplayer_config['args']['dashmpd']
 
                 def decrypt_sig(mobj):
                     s = mobj.group(1)
@@ -1002,6 +974,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
                         'tbr': int_or_none(r.attrib.get('bandwidth'), 1000),
                         'asr': int_or_none(r.attrib.get('audioSamplingRate')),
                         'filesize': filesize,
+                        'fps': int_or_none(r.attrib.get('frameRate')),
                     }
                     try:
                         existing_format = next(

youtube_dl/options.py

@@ -163,7 +163,10 @@ def parseOpts(overrideArguments=None):
     general.add_option(
         '--ignore-config',
         action='store_true',
-        help='Do not read configuration files. When given in the global configuration file /etc/youtube-dl.conf: do not read the user configuration in ~/.config/youtube-dl.conf (%APPDATA%/youtube-dl/config.txt on Windows)')
+        help='Do not read configuration files. '
+        'When given in the global configuration file /etc/youtube-dl.conf: '
+        'Do not read the user configuration in ~/.config/youtube-dl/config '
+        '(%APPDATA%/youtube-dl/config.txt on Windows)')
     general.add_option(
         '--flat-playlist',
         action='store_const', dest='extract_flat', const='in_playlist',
@@ -222,7 +225,7 @@ def parseOpts(overrideArguments=None):
     selection.add_option(
         '--no-playlist',
         action='store_true', dest='noplaylist', default=False,
-        help='download only the currently playing video')
+        help='If the URL refers to a video and a playlist, download only the video.')
     selection.add_option(
         '--age-limit',
         metavar='YEARS', dest='age_limit', default=None, type=int,

youtube_dl/postprocessor/__init__.py

@@ -1,3 +1,4 @@
+from __future__ import unicode_literals
 
 from .atomicparsley import AtomicParsleyPP
 from .ffmpeg import (

youtube_dl/postprocessor/common.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 from ..utils import PostProcessingError
 
 

youtube_dl/postprocessor/ffmpeg.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import os
 import subprocess
 import sys
@@ -33,12 +35,12 @@ class FFmpegPostProcessor(PostProcessor):
 
     def check_version(self):
         if not self._executable:
-            raise FFmpegPostProcessorError(u'ffmpeg or avconv not found. Please install one.')
+            raise FFmpegPostProcessorError('ffmpeg or avconv not found. Please install one.')
 
         REQUIRED_VERSION = '1.0'
         if is_outdated_version(
                 self._versions[self._executable], REQUIRED_VERSION):
-            warning = u'Your copy of %s is outdated, update %s to version %s or newer if you encounter any errors.' % (
+            warning = 'Your copy of %s is outdated, update %s to version %s or newer if you encounter any errors.' % (
                 self._executable, self._executable, REQUIRED_VERSION)
             if self._downloader:
                 self._downloader.report_warning(warning)
@@ -84,7 +86,7 @@ class FFmpegPostProcessor(PostProcessor):
                [encodeFilename(self._ffmpeg_filename_argument(out_path), True)])
 
         if self._downloader.params.get('verbose', False):
-            self._downloader.to_screen(u'[debug] ffmpeg command line: %s' % shell_quote(cmd))
+            self._downloader.to_screen('[debug] ffmpeg command line: %s' % shell_quote(cmd))
         p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
         stdout, stderr = p.communicate()
         if p.returncode != 0:
@@ -100,8 +102,8 @@ class FFmpegPostProcessor(PostProcessor):
 
     def _ffmpeg_filename_argument(self, fn):
         # ffmpeg broke --, see https://ffmpeg.org/trac/ffmpeg/ticket/2127 for details
-        if fn.startswith(u'-'):
+        if fn.startswith('-'):
-            return u'./' + fn
+            return './' + fn
         return fn
 
 
@@ -117,7 +119,7 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor):
     def get_audio_codec(self, path):
 
         if not self._probe_executable:
-            raise PostProcessingError(u'ffprobe or avprobe not found. Please install one.')
+            raise PostProcessingError('ffprobe or avprobe not found. Please install one.')
         try:
             cmd = [
                 self._probe_executable,
@@ -153,7 +155,7 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor):
 
         filecodec = self.get_audio_codec(path)
         if filecodec is None:
-            raise PostProcessingError(u'WARNING: unable to obtain file audio codec with ffprobe')
+            raise PostProcessingError('WARNING: unable to obtain file audio codec with ffprobe')
 
         uses_avconv = self._uses_avconv()
         more_opts = []
@@ -202,7 +204,7 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor):
                 extension = 'wav'
                 more_opts += ['-f', 'wav']
 
-        prefix, sep, ext = path.rpartition(u'.')  # not os.path.splitext, since the latter does not work on unicode in all setups
+        prefix, sep, ext = path.rpartition('.')  # not os.path.splitext, since the latter does not work on unicode in all setups
         new_path = prefix + sep + extension
 
         # If we download foo.mp3 and convert it to... foo.mp3, then don't delete foo.mp3, silly.
@@ -211,16 +213,16 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor):
 
         try:
             if self._nopostoverwrites and os.path.exists(encodeFilename(new_path)):
-                self._downloader.to_screen(u'[youtube] Post-process file %s exists, skipping' % new_path)
+                self._downloader.to_screen('[youtube] Post-process file %s exists, skipping' % new_path)
             else:
-                self._downloader.to_screen(u'[' + self._executable + '] Destination: ' + new_path)
+                self._downloader.to_screen('[' + self._executable + '] Destination: ' + new_path)
                 self.run_ffmpeg(path, new_path, acodec, more_opts)
         except:
             etype, e, tb = sys.exc_info()
             if isinstance(e, AudioConversionError):
-                msg = u'audio conversion failed: ' + e.msg
+                msg = 'audio conversion failed: ' + e.msg
             else:
-                msg = u'error running ' + self._executable
+                msg = 'error running ' + self._executable
             raise PostProcessingError(msg)
 
         # Try to update the date time for extracted audio file.
@@ -228,7 +230,7 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor):
             try:
                 os.utime(encodeFilename(new_path), (time.time(), information['filetime']))
             except:
-                self._downloader.report_warning(u'Cannot update utime of audio file')
+                self._downloader.report_warning('Cannot update utime of audio file')
 
         information['filepath'] = new_path
         return self._nopostoverwrites, information
@@ -241,12 +243,12 @@ class FFmpegVideoConvertor(FFmpegPostProcessor):
 
     def run(self, information):
         path = information['filepath']
-        prefix, sep, ext = path.rpartition(u'.')
+        prefix, sep, ext = path.rpartition('.')
         outpath = prefix + sep + self._preferedformat
         if information['ext'] == self._preferedformat:
-            self._downloader.to_screen(u'[ffmpeg] Not converting video file %s - already is in target format %s' % (path, self._preferedformat))
+            self._downloader.to_screen('[ffmpeg] Not converting video file %s - already is in target format %s' % (path, self._preferedformat))
             return True, information
-        self._downloader.to_screen(u'[' + 'ffmpeg' + '] Converting video from %s to %s, Destination: ' % (information['ext'], self._preferedformat) + outpath)
+        self._downloader.to_screen('[' + 'ffmpeg' + '] Converting video from %s to %s, Destination: ' % (information['ext'], self._preferedformat) + outpath)
         self.run_ffmpeg(path, outpath, [])
         information['filepath'] = outpath
         information['format'] = self._preferedformat
@@ -453,11 +455,11 @@ class FFmpegEmbedSubtitlePP(FFmpegPostProcessor):
         return cls._lang_map.get(code[:2])
 
     def run(self, information):
-        if information['ext'] != u'mp4':
+        if information['ext'] != 'mp4':
-            self._downloader.to_screen(u'[ffmpeg] Subtitles can only be embedded in mp4 files')
+            self._downloader.to_screen('[ffmpeg] Subtitles can only be embedded in mp4 files')
             return True, information
         if not information.get('subtitles'):
-            self._downloader.to_screen(u'[ffmpeg] There aren\'t any subtitles to embed')
+            self._downloader.to_screen('[ffmpeg] There aren\'t any subtitles to embed')
             return True, information
 
         sub_langs = [key for key in information['subtitles']]
@@ -472,8 +474,8 @@ class FFmpegEmbedSubtitlePP(FFmpegPostProcessor):
                 opts.extend(['-metadata:s:s:%d' % i, 'language=%s' % lang_code])
         opts.extend(['-f', 'mp4'])
 
-        temp_filename = filename + u'.temp'
+        temp_filename = filename + '.temp'
-        self._downloader.to_screen(u'[ffmpeg] Embedding subtitles in \'%s\'' % filename)
+        self._downloader.to_screen('[ffmpeg] Embedding subtitles in \'%s\'' % filename)
         self.run_ffmpeg_multiple_files(input_files, temp_filename, opts)
         os.remove(encodeFilename(filename))
         os.rename(encodeFilename(temp_filename), encodeFilename(filename))
@@ -494,13 +496,13 @@ class FFmpegMetadataPP(FFmpegPostProcessor):
             metadata['artist'] = info['uploader_id']
 
         if not metadata:
-            self._downloader.to_screen(u'[ffmpeg] There isn\'t any metadata to add')
+            self._downloader.to_screen('[ffmpeg] There isn\'t any metadata to add')
             return True, info
 
         filename = info['filepath']
         temp_filename = prepend_extension(filename, 'temp')
 
-        if info['ext'] == u'm4a':
+        if info['ext'] == 'm4a':
             options = ['-vn', '-acodec', 'copy']
         else:
             options = ['-c', 'copy']
@@ -508,7 +510,7 @@ class FFmpegMetadataPP(FFmpegPostProcessor):
         for (name, value) in metadata.items():
             options.extend(['-metadata', '%s=%s' % (name, value)])
 
-        self._downloader.to_screen(u'[ffmpeg] Adding metadata to \'%s\'' % filename)
+        self._downloader.to_screen('[ffmpeg] Adding metadata to \'%s\'' % filename)
         self.run_ffmpeg(filename, temp_filename, options)
         os.remove(encodeFilename(filename))
         os.rename(encodeFilename(temp_filename), encodeFilename(filename))
@@ -519,7 +521,7 @@ class FFmpegMergerPP(FFmpegPostProcessor):
     def run(self, info):
         filename = info['filepath']
         args = ['-c', 'copy', '-map', '0:v:0', '-map', '1:a:0', '-shortest']
-        self._downloader.to_screen(u'[ffmpeg] Merging formats into "%s"' % filename)
+        self._downloader.to_screen('[ffmpeg] Merging formats into "%s"' % filename)
         self.run_ffmpeg_multiple_files(info['__files_to_merge'], filename, args)
         return True, info
 
@@ -530,7 +532,7 @@ class FFmpegAudioFixPP(FFmpegPostProcessor):
         temp_filename = prepend_extension(filename, 'temp')
 
         options = ['-vn', '-acodec', 'copy']
-        self._downloader.to_screen(u'[ffmpeg] Fixing audio file "%s"' % filename)
+        self._downloader.to_screen('[ffmpeg] Fixing audio file "%s"' % filename)
         self.run_ffmpeg(filename, temp_filename, options)
 
         os.remove(encodeFilename(filename))

youtube_dl/postprocessor/xattrpp.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import os
 import subprocess
 import sys

youtube_dl/update.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import io
 import json
 import traceback
@@ -7,7 +9,7 @@ import subprocess
 import sys
 from zipimport import zipimporter
 
-from .utils import (
+from .compat import (
     compat_str,
     compat_urllib_request,
 )
@@ -17,14 +19,8 @@ from .version import __version__
 def rsa_verify(message, signature, key):
     from struct import pack
     from hashlib import sha256
-    from sys import version_info
 
-    def b(x):
+    assert isinstance(message, bytes)
-        if version_info[0] == 2:
-            return x
-        else:
-            return x.encode('latin1')
-    assert(type(message) == type(b('')))
     block_size = 0
     n = key[0]
     while n:
@@ -35,14 +31,14 @@ def rsa_verify(message, signature, key):
     while signature:
         raw_bytes.insert(0, pack("B", signature & 0xFF))
         signature >>= 8
-    signature = (block_size - len(raw_bytes)) * b('\x00') + b('').join(raw_bytes)
+    signature = (block_size - len(raw_bytes)) * b'\x00' + b''.join(raw_bytes)
-    if signature[0:2] != b('\x00\x01'):
+    if signature[0:2] != b'\x00\x01':
         return False
     signature = signature[2:]
-    if not b('\x00') in signature:
+    if b'\x00' not in signature:
         return False
-    signature = signature[signature.index(b('\x00')) + 1:]
+    signature = signature[signature.index(b'\x00') + 1:]
-    if not signature.startswith(b('\x30\x31\x30\x0D\x06\x09\x60\x86\x48\x01\x65\x03\x04\x02\x01\x05\x00\x04\x20')):
+    if not signature.startswith(b'\x30\x31\x30\x0D\x06\x09\x60\x86\x48\x01\x65\x03\x04\x02\x01\x05\x00\x04\x20'):
         return False
     signature = signature[19:]
     if signature != sha256(message).digest():
@@ -59,7 +55,7 @@ def update_self(to_screen, verbose):
     UPDATES_RSA_KEY = (0x9d60ee4d8f805312fdb15a62f87b95bd66177b91df176765d13514a0f1754bcd2057295c5b6f1d35daa6742c3ffc9a82d3e118861c207995a8031e151d863c9927e304576bc80692bc8e094896fcf11b66f3e29e04e3a71e9a11558558acea1840aec37fc396fb6b65dc81a1c4144e03bd1c011de62e3f1357b327d08426fe93, 65537)
 
     if not isinstance(globals().get('__loader__'), zipimporter) and not hasattr(sys, "frozen"):
-        to_screen(u'It looks like you installed youtube-dl with a package manager, pip, setup.py or a tarball. Please use that to update.')
+        to_screen('It looks like you installed youtube-dl with a package manager, pip, setup.py or a tarball. Please use that to update.')
         return
 
     # Check if there is a new version
@@ -68,10 +64,10 @@ def update_self(to_screen, verbose):
     except:
         if verbose:
             to_screen(compat_str(traceback.format_exc()))
-        to_screen(u'ERROR: can\'t find the current version. Please try again later.')
+        to_screen('ERROR: can\'t find the current version. Please try again later.')
         return
     if newversion == __version__:
-        to_screen(u'youtube-dl is up-to-date (' + __version__ + ')')
+        to_screen('youtube-dl is up-to-date (' + __version__ + ')')
         return
 
     # Download and check versions info
@@ -81,15 +77,15 @@ def update_self(to_screen, verbose):
     except:
         if verbose:
             to_screen(compat_str(traceback.format_exc()))
-        to_screen(u'ERROR: can\'t obtain versions info. Please try again later.')
+        to_screen('ERROR: can\'t obtain versions info. Please try again later.')
         return
     if not 'signature' in versions_info:
-        to_screen(u'ERROR: the versions file is not signed or corrupted. Aborting.')
+        to_screen('ERROR: the versions file is not signed or corrupted. Aborting.')
         return
     signature = versions_info['signature']
     del versions_info['signature']
     if not rsa_verify(json.dumps(versions_info, sort_keys=True).encode('utf-8'), signature, UPDATES_RSA_KEY):
-        to_screen(u'ERROR: the versions file signature is invalid. Aborting.')
+        to_screen('ERROR: the versions file signature is invalid. Aborting.')
         return
 
     version_id = versions_info['latest']
@@ -97,10 +93,10 @@ def update_self(to_screen, verbose):
     def version_tuple(version_str):
         return tuple(map(int, version_str.split('.')))
     if version_tuple(__version__) >= version_tuple(version_id):
-        to_screen(u'youtube-dl is up to date (%s)' % __version__)
+        to_screen('youtube-dl is up to date (%s)' % __version__)
         return
 
-    to_screen(u'Updating to version ' + version_id + ' ...')
+    to_screen('Updating to version ' + version_id + ' ...')
     version = versions_info['versions'][version_id]
 
     print_notes(to_screen, versions_info['versions'])
@@ -108,11 +104,11 @@ def update_self(to_screen, verbose):
     filename = sys.argv[0]
     # Py2EXE: Filename could be different
     if hasattr(sys, "frozen") and not os.path.isfile(filename):
-        if os.path.isfile(filename + u'.exe'):
+        if os.path.isfile(filename + '.exe'):
-            filename += u'.exe'
+            filename += '.exe'
 
     if not os.access(filename, os.W_OK):
-        to_screen(u'ERROR: no write permissions on %s' % filename)
+        to_screen('ERROR: no write permissions on %s' % filename)
         return
 
     # Py2EXE
@@ -120,7 +116,7 @@ def update_self(to_screen, verbose):
         exe = os.path.abspath(filename)
         directory = os.path.dirname(exe)
         if not os.access(directory, os.W_OK):
-            to_screen(u'ERROR: no write permissions on %s' % directory)
+            to_screen('ERROR: no write permissions on %s' % directory)
             return
 
         try:
@@ -130,12 +126,12 @@ def update_self(to_screen, verbose):
         except (IOError, OSError):
             if verbose:
                 to_screen(compat_str(traceback.format_exc()))
-            to_screen(u'ERROR: unable to download latest version')
+            to_screen('ERROR: unable to download latest version')
             return
 
         newcontent_hash = hashlib.sha256(newcontent).hexdigest()
         if newcontent_hash != version['exe'][1]:
-            to_screen(u'ERROR: the downloaded file hash does not match. Aborting.')
+            to_screen('ERROR: the downloaded file hash does not match. Aborting.')
             return
 
         try:
@@ -144,27 +140,27 @@ def update_self(to_screen, verbose):
         except (IOError, OSError):
             if verbose:
                 to_screen(compat_str(traceback.format_exc()))
-            to_screen(u'ERROR: unable to write the new version')
+            to_screen('ERROR: unable to write the new version')
             return
 
         try:
             bat = os.path.join(directory, 'youtube-dl-updater.bat')
             with io.open(bat, 'w') as batfile:
-                batfile.write(u"""
+                batfile.write('''
 @echo off
 echo Waiting for file handle to be closed ...
 ping 127.0.0.1 -n 5 -w 1000 > NUL
 move /Y "%s.new" "%s" > NUL
 echo Updated youtube-dl to version %s.
 start /b "" cmd /c del "%%~f0"&exit /b"
-                \n""" % (exe, exe, version_id))
+                \n''' % (exe, exe, version_id))
 
             subprocess.Popen([bat])  # Continues to run in the background
             return  # Do not show premature success messages
         except (IOError, OSError):
             if verbose:
                 to_screen(compat_str(traceback.format_exc()))
-            to_screen(u'ERROR: unable to overwrite current version')
+            to_screen('ERROR: unable to overwrite current version')
             return
 
     # Zip unix package
@@ -176,12 +172,12 @@ start /b "" cmd /c del "%%~f0"&exit /b"
         except (IOError, OSError):
             if verbose:
                 to_screen(compat_str(traceback.format_exc()))
-            to_screen(u'ERROR: unable to download latest version')
+            to_screen('ERROR: unable to download latest version')
             return
 
         newcontent_hash = hashlib.sha256(newcontent).hexdigest()
         if newcontent_hash != version['bin'][1]:
-            to_screen(u'ERROR: the downloaded file hash does not match. Aborting.')
+            to_screen('ERROR: the downloaded file hash does not match. Aborting.')
             return
 
         try:
@@ -190,10 +186,10 @@ start /b "" cmd /c del "%%~f0"&exit /b"
         except (IOError, OSError):
             if verbose:
                 to_screen(compat_str(traceback.format_exc()))
-            to_screen(u'ERROR: unable to overwrite current version')
+            to_screen('ERROR: unable to overwrite current version')
             return
 
-    to_screen(u'Updated youtube-dl. Restart youtube-dl to use the new version.')
+    to_screen('Updated youtube-dl. Restart youtube-dl to use the new version.')
 
 
 def get_notes(versions, fromVersion):
@@ -207,6 +203,6 @@ def get_notes(versions, fromVersion):
 def print_notes(to_screen, versions, fromVersion=__version__):
     notes = get_notes(versions, fromVersion)
     if notes:
-        to_screen(u'PLEASE NOTE:')
+        to_screen('PLEASE NOTE:')
         for note in notes:
             to_screen(note)

youtube_dl/utils.py

@@ -131,7 +131,7 @@ if sys.version_info >= (2, 7):
         """ Find the xpath xpath[@key=val] """
         assert re.match(r'^[a-zA-Z-]+$', key)
         assert re.match(r'^[a-zA-Z0-9@\s:._-]*$', val)
-        expr = xpath + u"[@%s='%s']" % (key, val)
+        expr = xpath + "[@%s='%s']" % (key, val)
         return node.find(expr)
 else:
     def find_xpath_attr(node, xpath, key, val):
@@ -1090,11 +1090,14 @@ def parse_filesize(s):
     }
 
     units_re = '|'.join(re.escape(u) for u in _UNIT_TABLE)
-    m = re.match(r'(?P<num>[0-9]+(?:\.[0-9]*)?)\s*(?P<unit>%s)' % units_re, s)
+    m = re.match(
+        r'(?P<num>[0-9]+(?:[,.][0-9]*)?)\s*(?P<unit>%s)' % units_re, s)
     if not m:
         return None
 
-    return int(float(m.group('num')) * _UNIT_TABLE[m.group('unit')])
+    num_str = m.group('num').replace(',', '.')
+    mult = _UNIT_TABLE[m.group('unit')]
+    return int(float(num_str) * mult)
 
 
 def get_term_width():
@@ -1203,14 +1206,25 @@ def parse_duration(s):
 
     m = re.match(
         r'''(?ix)T?
+        (?:
+            (?P<only_mins>[0-9.]+)\s*(?:mins?|minutes?)\s*|
+            (?P<only_hours>[0-9.]+)\s*(?:hours?)|
+
             (?:
                 (?:(?P<hours>[0-9]+)\s*(?:[:h]|hours?)\s*)?
                 (?P<mins>[0-9]+)\s*(?:[:m]|mins?|minutes?)\s*
             )?
-            (?P<secs>[0-9]+)(?P<ms>\.[0-9]+)?\s*(?:s|secs?|seconds?)?$''', s)
+            (?P<secs>[0-9]+)(?P<ms>\.[0-9]+)?\s*(?:s|secs?|seconds?)?
+        )$''', s)
     if not m:
         return None
-    res = int(m.group('secs'))
+    res = 0
+    if m.group('only_mins'):
+        return float_or_none(m.group('only_mins'), invscale=60)
+    if m.group('only_hours'):
+        return float_or_none(m.group('only_hours'), invscale=60 * 60)
+    if m.group('secs'):
+        res += int(m.group('secs'))
     if m.group('mins'):
         res += int(m.group('mins')) * 60
     if m.group('hours'):

youtube_dl/version.py

@@ -1,2 +1,3 @@
+from __future__ import unicode_literals
 
-__version__ = '2014.11.25.1'
+__version__ = '2014.12.06'