release 2014.11.13.2

Fix YouTube Signature Extraction

AUTHORS

@@ -79,4 +79,6 @@ Dennis Scheiba
 Damon Timm
 winwon
 Xavier Beynon
-Gabriel Schubiner
+Gabriel Schubiner
+xantares
+Jan Matějka

README.md

@@ -131,17 +131,19 @@ which means you can modify it, redistribute it or use it however you like.
                                      %(upload_date)s for the upload date
                                      (YYYYMMDD), %(extractor)s for the provider
                                      (youtube, metacafe, etc), %(id)s for the
-                                     video id, %(playlist)s for the playlist the
+                                     video id, %(playlist_title)s,
+                                     %(playlist_id)s, or %(playlist)s (=title if
+                                     present, ID otherwise) for the playlist the
                                      video is in, %(playlist_index)s for the
-                                     position in the playlist and %% for a
-                                     literal percent. %(height)s and %(width)s
-                                     for the width and height of the video
-                                     format. %(resolution)s for a textual
+                                     position in the playlist. %(height)s and
+                                     %(width)s for the width and height of the
+                                     video format. %(resolution)s for a textual
                                      description of the resolution of the video
-                                     format. Use - to output to stdout. Can also
-                                     be used to download to a different
-                                     directory, for example with -o '/my/downloa
-                                     ds/%(uploader)s/%(title)s-%(id)s.%(ext)s' .
+                                     format. %% for a literal percent. Use - to
+                                     output to stdout. Can also be used to
+                                     download to a different directory, for
+                                     example with -o '/my/downloads/%(uploader)s
+                                     /%(title)s-%(id)s.%(ext)s' .
     --autonumber-size NUMBER         Specifies the number of digits in
                                      %(autonumber)s when it is present in output
                                      filename template or --auto-number option
@@ -239,8 +241,13 @@ which means you can modify it, redistribute it or use it however you like.
                                      "worst", "worstvideo" and "worstaudio". By
                                      default, youtube-dl will pick the best
                                      quality. Use commas to download multiple
-                                     audio formats, such as  -f
-                                     136/137/mp4/bestvideo,140/m4a/bestaudio
+                                     audio formats, such as -f
+                                     136/137/mp4/bestvideo,140/m4a/bestaudio.
+                                     You can merge the video and audio of two
+                                     formats into a single file using -f <video-
+                                     format>+<audio-format> (requires ffmpeg or
+                                     avconv), for example -f
+                                     bestvideo+bestaudio.
     --all-formats                    download all available video formats
     --prefer-free-formats            prefer free video formats unless a specific
                                      one is requested
@@ -500,7 +507,7 @@ If you want to add support for a new site, you can follow this quick list (assum
 6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will be then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc.
 7. Have a look at [`youtube_dl/common/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L38). Add tests and code for as many as you want.
 8. If you can, check the code with [pyflakes](https://pypi.python.org/pypi/pyflakes) (a good idea) and [pep8](https://pypi.python.org/pypi/pep8) (optional, ignore E501).
-9. When the tests pass, [add](https://www.kernel.org/pub/software/scm/git/docs/git-add.html) the new files and [commit](https://www.kernel.org/pub/software/scm/git/docs/git-commit.html) them and [push](https://www.kernel.org/pub/software/scm/git/docs/git-push.html) the result, like this:
+9. When the tests pass, [add](http://git-scm.com/docs/git-add) the new files and [commit](http://git-scm.com/docs/git-commit) them and [push](http://git-scm.com/docs/git-push) the result, like this:
 
         $ git add youtube_dl/extractor/__init__.py
         $ git add youtube_dl/extractor/yourextractor.py

test/helper.py

@@ -57,7 +57,7 @@ class FakeYDL(YoutubeDL):
         # Different instances of the downloader can't share the same dictionary
         # some test set the "sublang" parameter, which would break the md5 checks.
         params = get_params(override=override)
-        super(FakeYDL, self).__init__(params)
+        super(FakeYDL, self).__init__(params, auto_init=False)
         self.result = []
         
     def to_screen(self, s, skip_eol=None):
@@ -145,7 +145,8 @@ def expect_info_dict(self, expected_dict, got_dict):
         info_dict_str = ''.join(
             '    %s: %s,\n' % (_repr(k), _repr(v))
             for k, v in test_info_dict.items())
-        write_string('\n"info_dict": {\n' + info_dict_str + '}\n', out=sys.stderr)
+        write_string(
+            '\n\'info_dict\': {\n' + info_dict_str + '}\n', out=sys.stderr)
         self.assertFalse(
             missing_keys,
             'Missing keys in test definition: %s' % (

test/test_compat.py

@@ -0,0 +1,44 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+from __future__ import unicode_literals
+
+# Allow direct execution
+import os
+import sys
+import unittest
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+
+from youtube_dl.utils import get_filesystem_encoding
+from youtube_dl.compat import (
+    compat_getenv,
+    compat_expanduser,
+)
+
+
+class TestCompat(unittest.TestCase):
+    def test_compat_getenv(self):
+        test_str = 'тест'
+        os.environ['YOUTUBE-DL-TEST'] = (
+            test_str if sys.version_info >= (3, 0)
+            else test_str.encode(get_filesystem_encoding()))
+        self.assertEqual(compat_getenv('YOUTUBE-DL-TEST'), test_str)
+
+    def test_compat_expanduser(self):
+        test_str = 'C:\Documents and Settings\тест\Application Data'
+        os.environ['HOME'] = (
+            test_str if sys.version_info >= (3, 0)
+            else test_str.encode(get_filesystem_encoding()))
+        self.assertEqual(compat_expanduser('~'), test_str)
+
+    def test_all_present(self):
+        import youtube_dl.compat
+        all_names = youtube_dl.compat.__all__
+        present_names = set(filter(
+            lambda c: '_' in c and not c.startswith('_'),
+            dir(youtube_dl.compat))) - set(['unicode_literals'])
+        self.assertEqual(all_names, sorted(present_names))
+
+if __name__ == '__main__':
+    unittest.main()

test/test_download.py

@@ -23,10 +23,12 @@ import json
 import socket
 
 import youtube_dl.YoutubeDL
-from youtube_dl.utils import (
+from youtube_dl.compat import (
     compat_http_client,
     compat_urllib_error,
     compat_HTTPError,
+)
+from youtube_dl.utils import (
     DownloadError,
     ExtractorError,
     format_bytes,
@@ -94,7 +96,7 @@ def generator(test_case):
             params.setdefault('extract_flat', True)
             params.setdefault('skip_download', True)
 
-        ydl = YoutubeDL(params)
+        ydl = YoutubeDL(params, auto_init=False)
         ydl.add_default_info_extractors()
         finished_hook_called = set()
         def _hook(status):

test/test_swfinterp.py

@@ -37,7 +37,9 @@ def _make_testfunc(testfile):
                 or os.path.getmtime(swf_file) < os.path.getmtime(as_file)):
             # Recompile
             try:
-                subprocess.check_call(['mxmlc', '-output', swf_file, as_file])
+                subprocess.check_call([
+                    'mxmlc', '-output', swf_file,
+                    '-static-link-runtime-shared-libraries', as_file])
             except OSError as ose:
                 if ose.errno == errno.ENOENT:
                     print('mxmlc not found! Skipping test.')

test/test_utils.py

@@ -16,11 +16,11 @@ import json
 import xml.etree.ElementTree
 
 from youtube_dl.utils import (
+    clean_html,
     DateRange,
     encodeFilename,
     find_xpath_attr,
     fix_xml_ampersands,
-    get_meta_content,
     orderedSet,
     OnDemandPagedList,
     InAdvancePagedList,
@@ -46,8 +46,7 @@ from youtube_dl.utils import (
     escape_url,
     js_to_json,
     get_filesystem_encoding,
-    compat_getenv,
-    compat_expanduser,
+    intlist_to_bytes,
 )
 
 
@@ -157,17 +156,6 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'a'), doc[1])
         self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'c'), doc[2])
 
-    def test_meta_parser(self):
-        testhtml = '''
-        <head>
-            <meta name="description" content="foo &amp; bar">
-            <meta content='Plato' name='author'/>
-        </head>
-        '''
-        get_meta = lambda name: get_meta_content(name, testhtml)
-        self.assertEqual(get_meta('description'), 'foo & bar')
-        self.assertEqual(get_meta('author'), 'Plato')
-
     def test_xpath_with_ns(self):
         testxml = '''<root xmlns:media="http://example.com/">
             <media:song>
@@ -359,17 +347,14 @@ class TestUtil(unittest.TestCase):
         on = js_to_json('{"abc": true}')
         self.assertEqual(json.loads(on), {'abc': True})
 
-    def test_compat_getenv(self):
-        test_str = 'тест'
-        os.environ['YOUTUBE-DL-TEST'] = (test_str if sys.version_info >= (3, 0)
-            else test_str.encode(get_filesystem_encoding()))
-        self.assertEqual(compat_getenv('YOUTUBE-DL-TEST'), test_str)
+    def test_clean_html(self):
+        self.assertEqual(clean_html('a:\nb'), 'a: b')
+        self.assertEqual(clean_html('a:\n   "b"'), 'a:    "b"')
 
-    def test_compat_expanduser(self):
-        test_str = 'C:\Documents and Settings\тест\Application Data'
-        os.environ['HOME'] = (test_str if sys.version_info >= (3, 0)
-            else test_str.encode(get_filesystem_encoding()))
-        self.assertEqual(compat_expanduser('~'), test_str)
+    def test_intlist_to_bytes(self):
+        self.assertEqual(
+            intlist_to_bytes([0, 1, 127, 128, 255]),
+            b'\x00\x01\x7f\x80\xff')
 
 if __name__ == '__main__':
     unittest.main()

test/test_youtube_signature.py

@@ -14,7 +14,7 @@ import re
 import string
 
 from youtube_dl.extractor import YoutubeIE
-from youtube_dl.utils import compat_str, compat_urlretrieve
+from youtube_dl.compat import compat_str, compat_urlretrieve
 
 _TESTS = [
     (

youtube_dl/YoutubeDL.py

@@ -22,13 +22,15 @@ import traceback
 if os.name == 'nt':
     import ctypes
 
-from .utils import (
+from .compat import (
     compat_cookiejar,
     compat_expanduser,
     compat_http_client,
     compat_str,
     compat_urllib_error,
     compat_urllib_request,
+)
+from .utils import (
     escape_url,
     ContentTooShortError,
     date_from_str,
@@ -62,6 +64,7 @@ from .utils import (
 from .cache import Cache
 from .extractor import get_info_extractor, gen_extractors
 from .downloader import get_suitable_downloader
+from .downloader.rtmp import rtmpdump_version
 from .postprocessor import FFmpegMergerPP, FFmpegPostProcessor
 from .version import __version__
 
@@ -655,6 +658,8 @@ class YoutubeDL(object):
                 extra = {
                     'n_entries': n_entries,
                     'playlist': playlist,
+                    'playlist_id': ie_result.get('id'),
+                    'playlist_title': ie_result.get('title'),
                     'playlist_index': i + playliststart,
                     'extractor': ie_result['extractor'],
                     'webpage_url': ie_result['webpage_url'],
@@ -833,6 +838,13 @@ class YoutubeDL(object):
                         formats_info = (self.select_format(format_1, formats),
                             self.select_format(format_2, formats))
                         if all(formats_info):
+                            # The first format must contain the video and the
+                            # second the audio
+                            if formats_info[0].get('vcodec') == 'none':
+                                self.report_error('The first format must '
+                                    'contain the video, try using '
+                                    '"-f %s+%s"' % (format_2, format_1))
+                                return
                             selected_format = {
                                 'requested_formats': formats_info,
                                 'format': rf,
@@ -1294,11 +1306,13 @@ class YoutubeDL(object):
             self.report_warning(
                 'Your Python is broken! Update to a newer and supported version')
 
+        stdout_encoding = getattr(
+            sys.stdout, 'encoding', 'missing (%s)' % type(sys.stdout).__name__)
         encoding_str = (
             '[debug] Encodings: locale %s, fs %s, out %s, pref %s\n' % (
                 locale.getpreferredencoding(),
                 sys.getfilesystemencoding(),
-                sys.stdout.encoding,
+                stdout_encoding,
                 self.get_encoding()))
         write_string(encoding_str, encoding=None)
 
@@ -1321,6 +1335,7 @@ class YoutubeDL(object):
             platform.python_version(), platform_name()))
 
         exe_versions = FFmpegPostProcessor.get_versions()
+        exe_versions['rtmpdump'] = rtmpdump_version()
         exe_str = ', '.join(
             '%s %s' % (exe, v)
             for exe, v in sorted(exe_versions.items())

youtube_dl/__init__.py

@@ -13,10 +13,12 @@ import sys
 from .options import (
     parseOpts,
 )
-from .utils import (
+from .compat import (
     compat_expanduser,
     compat_getpass,
     compat_print,
+)
+from .utils import (
     DateRange,
     DEFAULT_OUTTMPL,
     decodeOption,

youtube_dl/cache.py

@@ -8,10 +8,8 @@ import re
 import shutil
 import traceback
 
-from .utils import (
-    compat_expanduser,
-    write_json_file,
-)
+from .compat import compat_expanduser
+from .utils import write_json_file
 
 
 class Cache(object):

youtube_dl/compat.py

@@ -0,0 +1,317 @@
+from __future__ import unicode_literals
+
+import getpass
+import os
+import subprocess
+import sys
+
+
+try:
+    import urllib.request as compat_urllib_request
+except ImportError: # Python 2
+    import urllib2 as compat_urllib_request
+
+try:
+    import urllib.error as compat_urllib_error
+except ImportError: # Python 2
+    import urllib2 as compat_urllib_error
+
+try:
+    import urllib.parse as compat_urllib_parse
+except ImportError: # Python 2
+    import urllib as compat_urllib_parse
+
+try:
+    from urllib.parse import urlparse as compat_urllib_parse_urlparse
+except ImportError: # Python 2
+    from urlparse import urlparse as compat_urllib_parse_urlparse
+
+try:
+    import urllib.parse as compat_urlparse
+except ImportError: # Python 2
+    import urlparse as compat_urlparse
+
+try:
+    import http.cookiejar as compat_cookiejar
+except ImportError: # Python 2
+    import cookielib as compat_cookiejar
+
+try:
+    import html.entities as compat_html_entities
+except ImportError: # Python 2
+    import htmlentitydefs as compat_html_entities
+
+try:
+    import html.parser as compat_html_parser
+except ImportError: # Python 2
+    import HTMLParser as compat_html_parser
+
+try:
+    import http.client as compat_http_client
+except ImportError: # Python 2
+    import httplib as compat_http_client
+
+try:
+    from urllib.error import HTTPError as compat_HTTPError
+except ImportError:  # Python 2
+    from urllib2 import HTTPError as compat_HTTPError
+
+try:
+    from urllib.request import urlretrieve as compat_urlretrieve
+except ImportError:  # Python 2
+    from urllib import urlretrieve as compat_urlretrieve
+
+
+try:
+    from subprocess import DEVNULL
+    compat_subprocess_get_DEVNULL = lambda: DEVNULL
+except ImportError:
+    compat_subprocess_get_DEVNULL = lambda: open(os.path.devnull, 'w')
+
+try:
+    from urllib.parse import unquote as compat_urllib_parse_unquote
+except ImportError:
+    def compat_urllib_parse_unquote(string, encoding='utf-8', errors='replace'):
+        if string == '':
+            return string
+        res = string.split('%')
+        if len(res) == 1:
+            return string
+        if encoding is None:
+            encoding = 'utf-8'
+        if errors is None:
+            errors = 'replace'
+        # pct_sequence: contiguous sequence of percent-encoded bytes, decoded
+        pct_sequence = b''
+        string = res[0]
+        for item in res[1:]:
+            try:
+                if not item:
+                    raise ValueError
+                pct_sequence += item[:2].decode('hex')
+                rest = item[2:]
+                if not rest:
+                    # This segment was just a single percent-encoded character.
+                    # May be part of a sequence of code units, so delay decoding.
+                    # (Stored in pct_sequence).
+                    continue
+            except ValueError:
+                rest = '%' + item
+            # Encountered non-percent-encoded characters. Flush the current
+            # pct_sequence.
+            string += pct_sequence.decode(encoding, errors) + rest
+            pct_sequence = b''
+        if pct_sequence:
+            # Flush the final pct_sequence
+            string += pct_sequence.decode(encoding, errors)
+        return string
+
+
+try:
+    from urllib.parse import parse_qs as compat_parse_qs
+except ImportError: # Python 2
+    # HACK: The following is the correct parse_qs implementation from cpython 3's stdlib.
+    # Python 2's version is apparently totally broken
+
+    def _parse_qsl(qs, keep_blank_values=False, strict_parsing=False,
+                encoding='utf-8', errors='replace'):
+        qs, _coerce_result = qs, unicode
+        pairs = [s2 for s1 in qs.split('&') for s2 in s1.split(';')]
+        r = []
+        for name_value in pairs:
+            if not name_value and not strict_parsing:
+                continue
+            nv = name_value.split('=', 1)
+            if len(nv) != 2:
+                if strict_parsing:
+                    raise ValueError("bad query field: %r" % (name_value,))
+                # Handle case of a control-name with no equal sign
+                if keep_blank_values:
+                    nv.append('')
+                else:
+                    continue
+            if len(nv[1]) or keep_blank_values:
+                name = nv[0].replace('+', ' ')
+                name = compat_urllib_parse_unquote(
+                    name, encoding=encoding, errors=errors)
+                name = _coerce_result(name)
+                value = nv[1].replace('+', ' ')
+                value = compat_urllib_parse_unquote(
+                    value, encoding=encoding, errors=errors)
+                value = _coerce_result(value)
+                r.append((name, value))
+        return r
+
+    def compat_parse_qs(qs, keep_blank_values=False, strict_parsing=False,
+                encoding='utf-8', errors='replace'):
+        parsed_result = {}
+        pairs = _parse_qsl(qs, keep_blank_values, strict_parsing,
+                        encoding=encoding, errors=errors)
+        for name, value in pairs:
+            if name in parsed_result:
+                parsed_result[name].append(value)
+            else:
+                parsed_result[name] = [value]
+        return parsed_result
+
+try:
+    compat_str = unicode # Python 2
+except NameError:
+    compat_str = str
+
+try:
+    compat_chr = unichr # Python 2
+except NameError:
+    compat_chr = chr
+
+try:
+    from xml.etree.ElementTree import ParseError as compat_xml_parse_error
+except ImportError:  # Python 2.6
+    from xml.parsers.expat import ExpatError as compat_xml_parse_error
+
+try:
+    from shlex import quote as shlex_quote
+except ImportError:  # Python < 3.3
+    def shlex_quote(s):
+        return "'" + s.replace("'", "'\"'\"'") + "'"
+
+
+def compat_ord(c):
+    if type(c) is int: return c
+    else: return ord(c)
+
+
+if sys.version_info >= (3, 0):
+    compat_getenv = os.getenv
+    compat_expanduser = os.path.expanduser
+else:
+    # Environment variables should be decoded with filesystem encoding.
+    # Otherwise it will fail if any non-ASCII characters present (see #3854 #3217 #2918)
+
+    def compat_getenv(key, default=None):
+        from .utils import get_filesystem_encoding
+        env = os.getenv(key, default)
+        if env:
+            env = env.decode(get_filesystem_encoding())
+        return env
+
+    # HACK: The default implementations of os.path.expanduser from cpython do not decode
+    # environment variables with filesystem encoding. We will work around this by
+    # providing adjusted implementations.
+    # The following are os.path.expanduser implementations from cpython 2.7.8 stdlib
+    # for different platforms with correct environment variables decoding.
+
+    if os.name == 'posix':
+        def compat_expanduser(path):
+            """Expand ~ and ~user constructions.  If user or $HOME is unknown,
+            do nothing."""
+            if not path.startswith('~'):
+                return path
+            i = path.find('/', 1)
+            if i < 0:
+                i = len(path)
+            if i == 1:
+                if 'HOME' not in os.environ:
+                    import pwd
+                    userhome = pwd.getpwuid(os.getuid()).pw_dir
+                else:
+                    userhome = compat_getenv('HOME')
+            else:
+                import pwd
+                try:
+                    pwent = pwd.getpwnam(path[1:i])
+                except KeyError:
+                    return path
+                userhome = pwent.pw_dir
+            userhome = userhome.rstrip('/')
+            return (userhome + path[i:]) or '/'
+    elif os.name == 'nt' or os.name == 'ce':
+        def compat_expanduser(path):
+            """Expand ~ and ~user constructs.
+
+            If user or $HOME is unknown, do nothing."""
+            if path[:1] != '~':
+                return path
+            i, n = 1, len(path)
+            while i < n and path[i] not in '/\\':
+                i = i + 1
+
+            if 'HOME' in os.environ:
+                userhome = compat_getenv('HOME')
+            elif 'USERPROFILE' in os.environ:
+                userhome = compat_getenv('USERPROFILE')
+            elif not 'HOMEPATH' in os.environ:
+                return path
+            else:
+                try:
+                    drive = compat_getenv('HOMEDRIVE')
+                except KeyError:
+                    drive = ''
+                userhome = os.path.join(drive, compat_getenv('HOMEPATH'))
+
+            if i != 1: #~user
+                userhome = os.path.join(os.path.dirname(userhome), path[1:i])
+
+            return userhome + path[i:]
+    else:
+        compat_expanduser = os.path.expanduser
+
+
+if sys.version_info < (3, 0):
+    def compat_print(s):
+        from .utils import preferredencoding
+        print(s.encode(preferredencoding(), 'xmlcharrefreplace'))
+else:
+    def compat_print(s):
+        assert type(s) == type(u'')
+        print(s)
+
+
+try:
+    subprocess_check_output = subprocess.check_output
+except AttributeError:
+    def subprocess_check_output(*args, **kwargs):
+        assert 'input' not in kwargs
+        p = subprocess.Popen(*args, stdout=subprocess.PIPE, **kwargs)
+        output, _ = p.communicate()
+        ret = p.poll()
+        if ret:
+            raise subprocess.CalledProcessError(ret, p.args, output=output)
+        return output
+
+if sys.version_info < (3, 0) and sys.platform == 'win32':
+    def compat_getpass(prompt, *args, **kwargs):
+        if isinstance(prompt, compat_str):
+            from .utils import preferredencoding
+            prompt = prompt.encode(preferredencoding())
+        return getpass.getpass(prompt, *args, **kwargs)
+else:
+    compat_getpass = getpass.getpass
+
+
+__all__ = [
+    'compat_HTTPError',
+    'compat_chr',
+    'compat_cookiejar',
+    'compat_expanduser',
+    'compat_getenv',
+    'compat_getpass',
+    'compat_html_entities',
+    'compat_html_parser',
+    'compat_http_client',
+    'compat_ord',
+    'compat_parse_qs',
+    'compat_print',
+    'compat_str',
+    'compat_subprocess_get_DEVNULL',
+    'compat_urllib_error',
+    'compat_urllib_parse',
+    'compat_urllib_parse_unquote',
+    'compat_urllib_parse_urlparse',
+    'compat_urllib_request',
+    'compat_urlparse',
+    'compat_urlretrieve',
+    'compat_xml_parse_error',
+    'shlex_quote',
+    'subprocess_check_output',
+]

youtube_dl/downloader/rtmp.py

@@ -12,9 +12,15 @@ from ..utils import (
     compat_str,
     encodeFilename,
     format_bytes,
+    get_exe_version,
 )
 
 
+def rtmpdump_version():
+    return get_exe_version(
+        'rtmpdump', ['--help'], r'(?i)RTMPDump\s*v?([0-9a-zA-Z._-]+)')
+
+
 class RtmpFD(FileDownloader):
     def real_download(self, filename, info_dict):
         def run_rtmpdump(args):

youtube_dl/extractor/__init__.py

@@ -127,6 +127,7 @@ from .francetv import (
 )
 from .freesound import FreesoundIE
 from .freespeech import FreespeechIE
+from .freevideo import FreeVideoIE
 from .funnyordie import FunnyOrDieIE
 from .gamekings import GamekingsIE
 from .gameone import (
@@ -141,6 +142,7 @@ from .generic import GenericIE
 from .glide import GlideIE
 from .globo import GloboIE
 from .godtube import GodTubeIE
+from .goldenmoustache import GoldenMoustacheIE
 from .golem import GolemIE
 from .googleplus import GooglePlusIE
 from .googlesearch import GoogleSearchIE
@@ -323,6 +325,7 @@ from .sbs import SBSIE
 from .scivee import SciVeeIE
 from .screencast import ScreencastIE
 from .servingsys import ServingSysIE
+from .sexu import SexuIE
 from .sexykarma import SexyKarmaIE
 from .shared import SharedIE
 from .sharesix import ShareSixIE
@@ -421,6 +424,7 @@ from .vesti import VestiIE
 from .vevo import VevoIE
 from .vgtv import VGTVIE
 from .vh1 import VH1IE
+from .vice import ViceIE
 from .viddler import ViddlerIE
 from .videobam import VideoBamIE
 from .videodetective import VideoDetectiveIE

youtube_dl/extractor/abc.py

@@ -11,13 +11,13 @@ class ABCIE(InfoExtractor):
     _VALID_URL = r'http://www\.abc\.net\.au/news/[^/]+/[^/]+/(?P<id>\d+)'
 
     _TEST = {
-        'url': 'http://www.abc.net.au/news/2014-07-25/bringing-asylum-seekers-to-australia-would-give/5624716',
-        'md5': 'dad6f8ad011a70d9ddf887ce6d5d0742',
+        'url': 'http://www.abc.net.au/news/2014-11-05/australia-to-staff-ebola-treatment-centre-in-sierra-leone/5868334',
+        'md5': 'cb3dd03b18455a661071ee1e28344d9f',
         'info_dict': {
-            'id': '5624716',
+            'id': '5868334',
             'ext': 'mp4',
-            'title': 'Bringing asylum seekers to Australia would give them right to asylum claims: professor',
-            'description': 'md5:ba36fa5e27e5c9251fd929d339aea4af',
+            'title': 'Australia to help staff Ebola treatment centre in Sierra Leone',
+            'description': 'md5:809ad29c67a05f54eb41f2a105693a67',
         },
     }
 

youtube_dl/extractor/addanime.py

@@ -3,12 +3,13 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_HTTPError,
     compat_str,
     compat_urllib_parse,
     compat_urllib_parse_urlparse,
-
+)
+from ..utils import (
     ExtractorError,
 )
 

youtube_dl/extractor/allocine.py

@@ -22,7 +22,7 @@ class AllocineIE(InfoExtractor):
             'id': '19546517',
             'ext': 'mp4',
             'title': 'Astérix - Le Domaine des Dieux Teaser VF',
-            'description': 'md5:4a754271d9c6f16c72629a8a993ee884',
+            'description': 'md5:abcd09ce503c6560512c14ebfdb720d2',
             'thumbnail': 're:http://.*\.jpg',
         },
     }, {

youtube_dl/extractor/bandcamp.py

@@ -110,20 +110,25 @@ class BandcampAlbumIE(InfoExtractor):
         'url': 'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1',
         'playlist': [
             {
-                'file': '1353101989.mp3',
                 'md5': '39bc1eded3476e927c724321ddf116cf',
                 'info_dict': {
+                    'id': '1353101989',
+                    'ext': 'mp3',
                     'title': 'Intro',
                 }
             },
             {
-                'file': '38097443.mp3',
                 'md5': '1a2c32e2691474643e912cc6cd4bffaa',
                 'info_dict': {
+                    'id': '38097443',
+                    'ext': 'mp3',
                     'title': 'Kero One - Keep It Alive (Blazo remix)',
                 }
             },
         ],
+        'info_dict': {
+            'title': 'Jazz Format Mixtape vol.1',
+        },
         'params': {
             'playlistend': 2
         },

youtube_dl/extractor/brightcove.py

@@ -14,6 +14,7 @@ from ..utils import (
     compat_str,
     compat_urllib_request,
     compat_parse_qs,
+    compat_urllib_parse_urlparse,
 
     determine_ext,
     ExtractorError,
@@ -23,7 +24,7 @@ from ..utils import (
 
 
 class BrightcoveIE(InfoExtractor):
-    _VALID_URL = r'https?://.*brightcove\.com/(services|viewer).*\?(?P<query>.*)'
+    _VALID_URL = r'https?://.*brightcove\.com/(services|viewer).*?\?(?P<query>.*)'
     _FEDERATED_URL_TEMPLATE = 'http://c.brightcove.com/services/viewer/htmlFederated?%s'
 
     _TESTS = [
@@ -260,11 +261,19 @@ class BrightcoveIE(InfoExtractor):
             formats = []
             for rend in renditions:
                 url = rend['defaultURL']
+                if not url:
+                    continue
                 if rend['remote']:
-                    # This type of renditions are served through 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'
+                    url_comp = compat_urllib_parse_urlparse(url)
+                    if url_comp.path.endswith('.m3u8'):
+                        formats.extend(
+                            self._extract_m3u8_formats(url, info['id'], 'mp4'))
+                        continue
+                    elif 'akamaihd.net' in url_comp.netloc:
+                        # This type of renditions are served through
+                        # 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:
                     ext = determine_ext(url)
                 size = rend.get('size')

youtube_dl/extractor/byutv.py

@@ -10,12 +10,12 @@ from ..utils import ExtractorError
 class BYUtvIE(InfoExtractor):
     _VALID_URL = r'^https?://(?:www\.)?byutv.org/watch/[0-9a-f-]+/(?P<video_id>[^/?#]+)'
     _TEST = {
-        'url': 'http://www.byutv.org/watch/44e80f7b-e3ba-43ba-8c51-b1fd96c94a79/granite-flats-talking',
+        'url': 'http://www.byutv.org/watch/6587b9a3-89d2-42a6-a7f7-fd2f81840a7d/studio-c-season-5-episode-5',
         'info_dict': {
-            'id': 'granite-flats-talking',
+            'id': 'studio-c-season-5-episode-5',
             'ext': 'mp4',
-            'description': 'md5:4e9a7ce60f209a33eca0ac65b4918e1c',
-            'title': 'Talking',
+            'description': 'md5:5438d33774b6bdc662f9485a340401cc',
+            'title': 'Season 5 Episode 5',
             'thumbnail': 're:^https?://.*promo.*'
         },
         'params': {

youtube_dl/extractor/channel9.py

@@ -27,7 +27,7 @@ class Channel9IE(InfoExtractor):
                 'title': 'Developer Kick-Off Session: Stuff We Love',
                 'description': 'md5:c08d72240b7c87fcecafe2692f80e35f',
                 'duration': 4576,
-                'thumbnail': 'http://media.ch9.ms/ch9/9d51/03902f2d-fc97-4d3c-b195-0bfe15a19d51/KOS002_220.jpg',
+                'thumbnail': 'http://video.ch9.ms/ch9/9d51/03902f2d-fc97-4d3c-b195-0bfe15a19d51/KOS002_220.jpg',
                 'session_code': 'KOS002',
                 'session_day': 'Day 1',
                 'session_room': 'Arena 1A',
@@ -43,7 +43,7 @@ class Channel9IE(InfoExtractor):
                 'title': 'Self-service BI with Power BI - nuclear testing',
                 'description': 'md5:d1e6ecaafa7fb52a2cacdf9599829f5b',
                 'duration': 1540,
-                'thumbnail': 'http://media.ch9.ms/ch9/87e1/0300391f-a455-4c72-bec3-4422f19287e1/selfservicenuk_512.jpg',
+                'thumbnail': 'http://video.ch9.ms/ch9/87e1/0300391f-a455-4c72-bec3-4422f19287e1/selfservicenuk_512.jpg',
                 'authors': [ 'Mike Wilmot' ],
             },
         }
@@ -94,7 +94,7 @@ class Channel9IE(InfoExtractor):
 
     def _extract_title(self, html):
         title = self._html_search_meta('title', html, 'title')
-        if title is None:           
+        if title is None:
             title = self._og_search_title(html)
             TITLE_SUFFIX = ' (Channel 9)'
             if title is not None and title.endswith(TITLE_SUFFIX):
@@ -115,7 +115,7 @@ class Channel9IE(InfoExtractor):
         return self._html_search_meta('description', html, 'description')
 
     def _extract_duration(self, html):
-        m = re.search(r'data-video_duration="(?P<hours>\d{2}):(?P<minutes>\d{2}):(?P<seconds>\d{2})"', html)
+        m = re.search(r'"length": *"(?P<hours>\d{2}):(?P<minutes>\d{2}):(?P<seconds>\d{2})"', html)
         return ((int(m.group('hours')) * 60 * 60) + (int(m.group('minutes')) * 60) + int(m.group('seconds'))) if m else None
 
     def _extract_slides(self, html):
@@ -167,7 +167,7 @@ class Channel9IE(InfoExtractor):
         return re.findall(r'<a href="/Events/Speakers/[^"]+">([^<]+)</a>', html)
 
     def _extract_content(self, html, content_path):
-        # Look for downloadable content        
+        # Look for downloadable content
         formats = self._formats_from_html(html)
         slides = self._extract_slides(html)
         zip_ = self._extract_zip(html)
@@ -258,16 +258,17 @@ class Channel9IE(InfoExtractor):
 
         webpage = self._download_webpage(url, content_path, 'Downloading web page')
 
-        page_type_m = re.search(r'<meta name="Search.PageType" content="(?P<pagetype>[^"]+)"/>', webpage)
-        if page_type_m is None:
-            raise ExtractorError('Search.PageType not found, don\'t know how to process this page', expected=True)
+        page_type_m = re.search(r'<meta name="WT.entryid" content="(?P<pagetype>[^:]+)[^"]+"/>', webpage)
+        if page_type_m is not None:
+            page_type = page_type_m.group('pagetype')
+            if page_type == 'Entry':      # Any 'item'-like page, may contain downloadable content
+                return self._extract_entry_item(webpage, content_path)
+            elif page_type == 'Session':  # Event session page, may contain downloadable content
+                return self._extract_session(webpage, content_path)
+            elif page_type == 'Event':
+                return self._extract_list(content_path)
+            else:
+                raise ExtractorError('Unexpected WT.entryid %s' % page_type, expected=True)
 
-        page_type = page_type_m.group('pagetype')
-        if page_type == 'List':         # List page, may contain list of 'item'-like objects
+        else: # Assuming list
             return self._extract_list(content_path)
-        elif page_type == 'Entry.Item': # Any 'item'-like page, may contain downloadable content
-            return self._extract_entry_item(webpage, content_path)
-        elif page_type == 'Session':    # Event session page, may contain downloadable content
-            return self._extract_session(webpage, content_path)
-        else:
-            raise ExtractorError('Unexpected Search.PageType %s' % page_type, expected=True)

youtube_dl/extractor/cinemassacre.py

@@ -42,11 +42,12 @@ class CinemassacreIE(InfoExtractor):
 
         webpage = self._download_webpage(url, display_id)
         video_date = mobj.group('date_Y') + mobj.group('date_m') + mobj.group('date_d')
-        mobj = re.search(r'src="(?P<embed_url>http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=(?:Cinemassacre-)?(?P<video_id>.+?))"', webpage)
+        mobj = re.search(r'src="(?P<embed_url>http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=(?P<full_video_id>(?:Cinemassacre-)?(?P<video_id>.+?)))"', webpage)
         if not mobj:
             raise ExtractorError('Can\'t extract embed url and video id')
         playerdata_url = mobj.group('embed_url')
         video_id = mobj.group('video_id')
+        full_video_id = mobj.group('full_video_id')
 
         video_title = self._html_search_regex(
             r'<title>(?P<title>.+?)\|', webpage, 'title')
@@ -60,37 +61,52 @@ class CinemassacreIE(InfoExtractor):
         vidurl = self._search_regex(
             r'\'vidurl\'\s*:\s*"([^\']+)"', playerdata, 'vidurl').replace('\\/', '/')
 
-        videolist_url = self._search_regex(
-            r"file\s*:\s*'(http.+?/jwplayer\.smil)'", playerdata, 'jwplayer.smil')
-        videolist = self._download_xml(videolist_url, video_id, 'Downloading videolist XML')
+        videolist_url = None
 
-        formats = []
-        baseurl = vidurl[:vidurl.rfind('/')+1]
-        for video in videolist.findall('.//video'):
-            src = video.get('src')
-            if not src:
-                continue
-            file_ = src.partition(':')[-1]
-            width = int_or_none(video.get('width'))
-            height = int_or_none(video.get('height'))
-            bitrate = int_or_none(video.get('system-bitrate'))
-            format = {
-                'url': baseurl + file_,
-                'format_id': src.rpartition('.')[0].rpartition('_')[-1],
-            }
-            if width or height:
-                format.update({
-                    'tbr': bitrate // 1000 if bitrate else None,
-                    'width': width,
-                    'height': height,
-                })
-            else:
-                format.update({
-                    'abr': bitrate // 1000 if bitrate else None,
-                    'vcodec': 'none',
-                })
-            formats.append(format)
-        self._sort_formats(formats)
+        mobj = re.search(r"'videoserver'\s*:\s*'(?P<videoserver>[^']+)'", playerdata)
+        if mobj:
+            videoserver = mobj.group('videoserver')
+            mobj = re.search(r'\'vidid\'\s*:\s*"(?P<vidid>[^\']+)"', playerdata)
+            vidid = mobj.group('vidid') if mobj else full_video_id
+            videolist_url = 'http://%s/vod/smil:%s.smil/jwplayer.smil' % (videoserver, vidid)
+        else:
+            mobj = re.search(r"file\s*:\s*'(?P<smil>http.+?/jwplayer\.smil)'", playerdata)
+            if mobj:
+                videolist_url = mobj.group('smil')
+
+        if videolist_url:
+            videolist = self._download_xml(videolist_url, video_id, 'Downloading videolist XML')
+            formats = []
+            baseurl = vidurl[:vidurl.rfind('/')+1]
+            for video in videolist.findall('.//video'):
+                src = video.get('src')
+                if not src:
+                    continue
+                file_ = src.partition(':')[-1]
+                width = int_or_none(video.get('width'))
+                height = int_or_none(video.get('height'))
+                bitrate = int_or_none(video.get('system-bitrate'))
+                format = {
+                    'url': baseurl + file_,
+                    'format_id': src.rpartition('.')[0].rpartition('_')[-1],
+                }
+                if width or height:
+                    format.update({
+                        'tbr': bitrate // 1000 if bitrate else None,
+                        'width': width,
+                        'height': height,
+                    })
+                else:
+                    format.update({
+                        'abr': bitrate // 1000 if bitrate else None,
+                        'vcodec': 'none',
+                    })
+                formats.append(format)
+            self._sort_formats(formats)
+        else:
+            formats = [{
+                'url': vidurl,
+            }]
 
         return {
             'id': video_id,

youtube_dl/extractor/cloudy.py

@@ -4,14 +4,16 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
+from ..compat import (
     compat_parse_qs,
     compat_urllib_parse,
-    remove_end,
-    HEADRequest,
     compat_HTTPError,
 )
+from ..utils import (
+    ExtractorError,
+    HEADRequest,
+    remove_end,
+)
 
 
 class CloudyIE(InfoExtractor):

youtube_dl/extractor/cnn.py

@@ -16,9 +16,10 @@ class CNNIE(InfoExtractor):
 
     _TESTS = [{
         'url': 'http://edition.cnn.com/video/?/video/sports/2013/06/09/nadal-1-on-1.cnn',
-        'file': 'sports_2013_06_09_nadal-1-on-1.cnn.mp4',
         'md5': '3e6121ea48df7e2259fe73a0628605c4',
         'info_dict': {
+            'id': 'sports_2013_06_09_nadal-1-on-1.cnn',
+            'ext': 'mp4',
             'title': 'Nadal wins 8th French Open title',
             'description': 'World Sport\'s Amanda Davies chats with 2013 French Open champion Rafael Nadal.',
             'duration': 135,
@@ -27,9 +28,10 @@ class CNNIE(InfoExtractor):
     },
     {
         "url": "http://edition.cnn.com/video/?/video/us/2013/08/21/sot-student-gives-epic-speech.georgia-institute-of-technology&utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%3A+rss%2Fcnn_topstories+%28RSS%3A+Top+Stories%29",
-        "file": "us_2013_08_21_sot-student-gives-epic-speech.georgia-institute-of-technology.mp4",
         "md5": "b5cc60c60a3477d185af8f19a2a26f4e",
         "info_dict": {
+            'id': 'us/2013/08/21/sot-student-gives-epic-speech.georgia-institute-of-technology',
+            'ext': 'mp4',
             "title": "Student's epic speech stuns new freshmen",
             "description": "A Georgia Tech student welcomes the incoming freshmen with an epic speech backed by music from \"2001: A Space Odyssey.\"",
             "upload_date": "20130821",

youtube_dl/extractor/common.py

@@ -12,13 +12,14 @@ import sys
 import time
 import xml.etree.ElementTree
 
-from ..utils import (
+from ..compat import (
     compat_http_client,
     compat_urllib_error,
     compat_urllib_parse_urlparse,
     compat_urlparse,
     compat_str,
-
+)
+from ..utils import (
     clean_html,
     compiled_regex_type,
     ExtractorError,
@@ -403,7 +404,7 @@ class InfoExtractor(object):
             video_info['title'] = playlist_title
         return video_info
 
-    def _search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0):
+    def _search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0, group=None):
         """
         Perform a regex search on the given string, using a single or a list of
         patterns returning the first matching group.
@@ -424,8 +425,11 @@ class InfoExtractor(object):
             _name = name
 
         if mobj:
-            # return the first matching group
-            return next(g for g in mobj.groups() if g is not None)
+            if group is None:
+                # return the first matching group
+                return next(g for g in mobj.groups() if g is not None)
+            else:
+                return mobj.group(group)
         elif default is not _NO_DEFAULT:
             return default
         elif fatal:
@@ -435,11 +439,11 @@ class InfoExtractor(object):
                 'please report this issue on http://yt-dl.org/bug' % _name)
             return None
 
-    def _html_search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0):
+    def _html_search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0, group=None):
         """
         Like _search_regex, but strips HTML tags and unescapes entities.
         """
-        res = self._search_regex(pattern, string, name, default, fatal, flags)
+        res = self._search_regex(pattern, string, name, default, fatal, flags, group)
         if res:
             return clean_html(res).strip()
         else:
@@ -533,9 +537,9 @@ class InfoExtractor(object):
             display_name = name
         return self._html_search_regex(
             r'''(?ix)<meta
-                    (?=[^>]+(?:itemprop|name|property)=["\']?%s["\']?)
-                    [^>]+content=["\']([^"\']+)["\']''' % re.escape(name),
-            html, display_name, fatal=fatal, **kwargs)
+                    (?=[^>]+(?:itemprop|name|property)=(["\']?)%s\1)
+                    [^>]+content=(["\'])(?P<content>.*?)\1''' % re.escape(name),
+            html, display_name, fatal=fatal, group='content', **kwargs)
 
     def _dc_search_uploader(self, html):
         return self._html_search_meta('dc.creator', html, 'uploader')

youtube_dl/extractor/crunchyroll.py

@@ -17,7 +17,6 @@ from ..utils import (
     bytes_to_intlist,
     intlist_to_bytes,
     unified_strdate,
-    clean_html,
     urlencode_postdata,
 )
 from ..aes import (

youtube_dl/extractor/dailymotion.py

@@ -94,7 +94,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
 
         # It may just embed a vevo video:
         m_vevo = re.search(
-            r'<link rel="video_src" href="[^"]*?vevo.com[^"]*?videoId=(?P<id>[\w]*)',
+            r'<link rel="video_src" href="[^"]*?vevo.com[^"]*?video=(?P<id>[\w]*)',
             webpage)
         if m_vevo is not None:
             vevo_id = m_vevo.group('id')

youtube_dl/extractor/dropbox.py

@@ -5,7 +5,8 @@ import os.path
 import re
 
 from .common import InfoExtractor
-from ..utils import compat_urllib_parse_unquote, url_basename
+from ..compat import compat_urllib_parse_unquote
+from ..utils import url_basename
 
 
 class DropboxIE(InfoExtractor):

youtube_dl/extractor/facebook.py

@@ -5,12 +5,14 @@ import re
 import socket
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_http_client,
     compat_str,
     compat_urllib_error,
     compat_urllib_parse,
     compat_urllib_request,
+)
+from ..utils import (
     urlencode_postdata,
     ExtractorError,
     limit_length,

youtube_dl/extractor/freevideo.py

@@ -0,0 +1,38 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+
+class FreeVideoIE(InfoExtractor):
+    _VALID_URL = r'^http://www.freevideo.cz/vase-videa/(?P<id>[^.]+)\.html(?:$|[?#])'
+
+    _TEST = {
+        'url': 'http://www.freevideo.cz/vase-videa/vysukany-zadecek-22033.html',
+        'info_dict': {
+            'id': 'vysukany-zadecek-22033',
+            'ext': 'mp4',
+            "title": "vysukany-zadecek-22033",
+            "age_limit": 18,
+        },
+        'skip': 'Blocked outside .cz',
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage, handle = self._download_webpage_handle(url, video_id)
+        if '//www.czechav.com/' in handle.geturl():
+            raise ExtractorError(
+                'Access to freevideo is blocked from your location',
+                expected=True)
+
+        video_url = self._search_regex(
+            r'\s+url: "(http://[a-z0-9-]+.cdn.freevideo.cz/stream/.*?/video.mp4)"',
+            webpage, 'video URL')
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': video_id,
+            'age_limit': 18,
+        }

youtube_dl/extractor/funnyordie.py

@@ -21,7 +21,6 @@ class FunnyOrDieIE(InfoExtractor):
         },
     }, {
         'url': 'http://www.funnyordie.com/embed/e402820827',
-        'md5': '29f4c5e5a61ca39dfd7e8348a75d0aad',
         'info_dict': {
             'id': 'e402820827',
             'ext': 'mp4',

youtube_dl/extractor/gamespot.py

@@ -8,12 +8,11 @@ from ..utils import (
     compat_urllib_parse,
     compat_urlparse,
     unescapeHTML,
-    get_meta_content,
 )
 
 
 class GameSpotIE(InfoExtractor):
-    _VALID_URL = r'(?:http://)?(?:www\.)?gamespot\.com/.*-(?P<page_id>\d+)/?'
+    _VALID_URL = r'(?:http://)?(?:www\.)?gamespot\.com/.*-(?P<id>\d+)/?'
     _TEST = {
         'url': 'http://www.gamespot.com/videos/arma-3-community-guide-sitrep-i/2300-6410818/',
         'md5': 'b2a30deaa8654fcccd43713a6b6a4825',
@@ -26,10 +25,10 @@ class GameSpotIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        page_id = mobj.group('page_id')
+        page_id = self._match_id(url)
         webpage = self._download_webpage(url, page_id)
-        data_video_json = self._search_regex(r'data-video=["\'](.*?)["\']', webpage, 'data video')
+        data_video_json = self._search_regex(
+            r'data-video=["\'](.*?)["\']', webpage, 'data video')
         data_video = json.loads(unescapeHTML(data_video_json))
 
         # Transform the manifest url to a link to the mp4 files
@@ -41,7 +40,8 @@ class GameSpotIE(InfoExtractor):
         http_path = f4m_path[1:].split('/', 1)[1]
         http_template = re.sub(QUALITIES_RE, r'%s', http_path)
         http_template = http_template.replace('.csmil/manifest.f4m', '')
-        http_template = compat_urlparse.urljoin('http://video.gamespotcdn.com/', http_template)
+        http_template = compat_urlparse.urljoin(
+            'http://video.gamespotcdn.com/', http_template)
         formats = []
         for q in qualities:
             formats.append({
@@ -52,8 +52,9 @@ class GameSpotIE(InfoExtractor):
 
         return {
             'id': data_video['guid'],
+            'display_id': page_id,
             'title': compat_urllib_parse.unquote(data_video['title']),
             'formats': formats,
-            'description': get_meta_content('description', webpage),
+            'description': self._html_search_meta('description', webpage),
             'thumbnail': self._og_search_thumbnail(webpage),
         }

youtube_dl/extractor/generic.py

@@ -7,11 +7,12 @@ import re
 
 from .common import InfoExtractor
 from .youtube import YoutubeIE
-from ..utils import (
+from ..compat import (
     compat_urllib_parse,
     compat_urlparse,
     compat_xml_parse_error,
-
+)
+from ..utils import (
     determine_ext,
     ExtractorError,
     float_or_none,
@@ -99,6 +100,22 @@ class GenericIE(InfoExtractor):
                 'uploader': 'Championat',
             },
         },
+        {
+            # https://github.com/rg3/youtube-dl/issues/3541
+            'add_ie': ['Brightcove'],
+            'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
+            'info_dict': {
+                'id': '3866516442001',
+                'ext': 'mp4',
+                'title': 'Leer mij vrouwen kennen: Aflevering 1',
+                'description': 'Leer mij vrouwen kennen: Aflevering 1',
+                'uploader': 'SBS Broadcasting',
+            },
+            'skip': 'Restricted to Netherlands',
+            'params': {
+                'skip_download': True,  # m3u8 download
+            },
+        },
         # Direct link to a video
         {
             'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
@@ -417,7 +434,17 @@ class GenericIE(InfoExtractor):
                 'title': 'Chet Chat 171 - Oct 29, 2014',
                 'upload_date': '20141029',
             }
-        }
+        },
+        # Livestream embed
+        {
+            'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
+            'info_dict': {
+                'id': '67864563',
+                'ext': 'flv',
+                'upload_date': '20141112',
+                'title': 'Rosetta #CometLanding webcast HL 10',
+            }
+        },
     ]
 
     def report_following_redirect(self, new_url):
@@ -559,6 +586,7 @@ class GenericIE(InfoExtractor):
             return {
                 'id': video_id,
                 'title': os.path.splitext(url_basename(url))[0],
+                'direct': True,
                 'formats': [{
                     'format_id': m.group('format_id'),
                     'url': url,
@@ -898,6 +926,12 @@ class GenericIE(InfoExtractor):
         if mobj is not None:
             return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
 
+        mobj = re.search(
+            r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
+            webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'), 'Livestream')
+
         def check_video(vurl):
             vpath = compat_urlparse.urlparse(vurl).path
             vext = determine_ext(vpath)

youtube_dl/extractor/globo.py

@@ -5,13 +5,15 @@ import random
 import math
 
 from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-    float_or_none,
+from ..compat import (
     compat_str,
     compat_chr,
     compat_ord,
 )
+from ..utils import (
+    ExtractorError,
+    float_or_none,
+)
 
 
 class GloboIE(InfoExtractor):

youtube_dl/extractor/goldenmoustache.py

@@ -0,0 +1,48 @@
+from __future__ import unicode_literals
+
+import re
+from .common import InfoExtractor
+from ..utils import (
+    parse_duration,
+    int_or_none,
+)
+
+
+class GoldenMoustacheIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?goldenmoustache\.com/(?P<display_id>[\w-]+)-(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://www.goldenmoustache.com/suricate-le-poker-3700/',
+        'md5': '0f904432fa07da5054d6c8beb5efb51a',
+        'info_dict': {
+            'id': '3700',
+            'ext': 'mp4',
+            'title': 'Suricate - Le Poker',
+            'description': 'md5:3d1f242f44f8c8cb0a106f1fd08e5dc9',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'view_count': int,
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        video_url = self._html_search_regex(
+            r'data-src-type="mp4" data-src="([^"]+)"', webpage, 'video URL')
+        title = self._html_search_regex(
+            r'<title>(.*?) - Golden Moustache</title>', webpage, 'title')
+        thumbnail = self._og_search_thumbnail(webpage)
+        description = self._og_search_description(webpage)
+        view_count = int_or_none(self._html_search_regex(
+            r'<strong>([0-9]+)</strong>\s*VUES</span>',
+            webpage, 'view count', fatal=False))
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'ext': 'mp4',
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'view_count': view_count,
+        }

youtube_dl/extractor/goshgay.py

@@ -1,15 +1,11 @@
 # -*- coding: utf-8 -*-
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 from ..utils import (
     compat_urlparse,
-    str_to_int,
     ExtractorError,
 )
-import json
 
 
 class GoshgayIE(InfoExtractor):
@@ -27,36 +23,27 @@ class GoshgayIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
-        title = self._search_regex(r'class="video-title"><h1>(.+?)<', webpage, 'title')
+        title = self._og_search_title(webpage)
+        thumbnail = self._og_search_thumbnail(webpage)
+        family_friendly = self._html_search_meta(
+            'isFamilyFriendly', webpage, default='false')
+        config_url = self._search_regex(
+            r"'config'\s*:\s*'([^']+)'", webpage, 'config URL')
 
-        player_config = self._search_regex(
-            r'(?s)jwplayer\("player"\)\.setup\(({.+?})\)', webpage, 'config settings')
-        player_vars = json.loads(player_config.replace("'", '"'))
-        width = str_to_int(player_vars.get('width'))
-        height = str_to_int(player_vars.get('height'))
-        config_uri = player_vars.get('config')
+        config = self._download_xml(
+            config_url, video_id, 'Downloading player config XML')
 
-        if config_uri is None:
-            raise ExtractorError('Missing config URI')
-        node = self._download_xml(config_uri, video_id, 'Downloading player config XML',
-                                  errnote='Unable to download XML')
-        if node is None:
+        if config is None:
             raise ExtractorError('Missing config XML')
-        if node.tag != 'config':
+        if config.tag != 'config':
             raise ExtractorError('Missing config attribute')
-        fns = node.findall('file')
-        imgs = node.findall('image')
-        if len(fns) != 1:
+        fns = config.findall('file')
+        if len(fns) < 1:
             raise ExtractorError('Missing media URI')
         video_url = fns[0].text
-        if len(imgs) < 1:
-            thumbnail = None
-        else:
-            thumbnail = imgs[0].text
 
         url_comp = compat_urlparse.urlparse(url)
         ref = "%s://%s%s" % (url_comp[0], url_comp[1], url_comp[2])
@@ -65,9 +52,7 @@ class GoshgayIE(InfoExtractor):
             'id': video_id,
             'url': video_url,
             'title': title,
-            'width': width,
-            'height': height,
             'thumbnail': thumbnail,
             'http_referer': ref,
-            'age_limit': 18,
+            'age_limit': 0 if family_friendly == 'true' else 18,
         }

youtube_dl/extractor/grooveshark.py

@@ -8,12 +8,13 @@ import re
 
 
 from .common import InfoExtractor
-from ..utils import ExtractorError, compat_urllib_request, compat_html_parser
-
-from ..utils import (
+from ..compat import (
+    compat_html_parser,
     compat_urllib_parse,
+    compat_urllib_request,
     compat_urlparse,
 )
+from ..utils import ExtractorError
 
 
 class GroovesharkHtmlParser(compat_html_parser.HTMLParser):

youtube_dl/extractor/heise.py

@@ -3,7 +3,7 @@ from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from ..utils import (
-    get_meta_content,
+    determine_ext,
     int_or_none,
     parse_iso8601,
 )
@@ -25,11 +25,11 @@ class HeiseIE(InfoExtractor):
             'title': (
                 "Podcast: c't uplink 3.3 – Owncloud / Tastaturen / Peilsender Smartphone"
             ),
-            'format_id': 'mp4_720',
+            'format_id': 'mp4_720p',
             'timestamp': 1411812600,
             'upload_date': '20140927',
             'description': 'In uplink-Episode 3.3 geht es darum, wie man sich von Cloud-Anbietern emanzipieren kann, worauf man beim Kauf einer Tastatur achten sollte und was Smartphones über uns verraten.',
-            'thumbnail': 're:https?://.*\.jpg$',
+            'thumbnail': 're:^https?://.*\.jpe?g$',
         }
     }
 
@@ -49,11 +49,12 @@ class HeiseIE(InfoExtractor):
         info = {
             'id': video_id,
             'thumbnail': self._og_search_thumbnail(webpage),
-            'timestamp': parse_iso8601(get_meta_content('date', webpage)),
+            'timestamp': parse_iso8601(
+                self._html_search_meta('date', webpage)),
             'description': self._og_search_description(webpage),
         }
 
-        title = get_meta_content('fulltitle', webpage)
+        title = self._html_search_meta('fulltitle', webpage)
         if title:
             info['title'] = title
         else:
@@ -64,9 +65,12 @@ class HeiseIE(InfoExtractor):
             label = source_node.attrib['label']
             height = int_or_none(self._search_regex(
                 r'^(.*?_)?([0-9]+)p$', label, 'height', default=None))
+            video_url = source_node.attrib['file']
+            ext = determine_ext(video_url, '')
             formats.append({
-                'url': source_node.attrib['file'],
+                'url': video_url,
                 'format_note': label,
+                'format_id': '%s_%s' % (ext, label),
                 'height': height,
             })
         self._sort_formats(formats)

youtube_dl/extractor/imdb.py

@@ -6,7 +6,6 @@ import json
 from .common import InfoExtractor
 from ..utils import (
     compat_urlparse,
-    get_element_by_attribute,
 )
 
 
@@ -27,10 +26,11 @@ class ImdbIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
         webpage = self._download_webpage('http://www.imdb.com/video/imdb/vi%s' % video_id, video_id)
-        descr = get_element_by_attribute('itemprop', 'description', webpage)
+        descr = self._html_search_regex(
+            r'(?s)<span itemprop="description">(.*?)</span>',
+            webpage, 'description', fatal=False)
         available_formats = re.findall(
             r'case \'(?P<f_id>.*?)\' :$\s+url = \'(?P<path>.*?)\'', webpage,
             flags=re.MULTILINE)
@@ -73,9 +73,7 @@ class ImdbListIE(InfoExtractor):
     }
     
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        list_id = mobj.group('id')
-
+        list_id = self._match_id(url)
         webpage = self._download_webpage(url, list_id)
         entries = [
             self.url_result('http://www.imdb.com' + m, 'Imdb')

youtube_dl/extractor/izlesene.py

@@ -5,11 +5,11 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
-    get_element_by_id,
-    parse_iso8601,
     determine_ext,
-    int_or_none,
     float_or_none,
+    get_element_by_id,
+    int_or_none,
+    parse_iso8601,
     str_to_int,
 )
 
@@ -30,7 +30,7 @@ class IzleseneIE(InfoExtractor):
                 'description': 'md5:253753e2655dde93f59f74b572454f6d',
                 'thumbnail': 're:^http://.*\.jpg',
                 'uploader_id': 'pelikzzle',
-                'timestamp': 1404298698,
+                'timestamp': 1404302298,
                 'upload_date': '20140702',
                 'duration': 95.395,
                 'age_limit': 0,
@@ -46,7 +46,7 @@ class IzleseneIE(InfoExtractor):
                 'description': 'Tarkan Dortmund 2006 Konseri',
                 'thumbnail': 're:^http://.*\.jpg',
                 'uploader_id': 'parlayankiz',
-                'timestamp': 1163318593,
+                'timestamp': 1163322193,
                 'upload_date': '20061112',
                 'duration': 253.666,
                 'age_limit': 0,
@@ -55,10 +55,9 @@ class IzleseneIE(InfoExtractor):
     ]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        url = 'http://www.izlesene.com/video/%s' % video_id
+        video_id = self._match_id(url)
 
+        url = 'http://www.izlesene.com/video/%s' % video_id
         webpage = self._download_webpage(url, video_id)
 
         title = self._og_search_title(webpage)

youtube_dl/extractor/laola1tv.py

@@ -4,6 +4,7 @@ import random
 import re
 
 from .common import InfoExtractor
+from ..utils import ExtractorError
 
 
 class Laola1TvIE(InfoExtractor):

youtube_dl/extractor/livestream.py

@@ -18,7 +18,7 @@ from ..utils import (
 
 class LivestreamIE(InfoExtractor):
     IE_NAME = 'livestream'
-    _VALID_URL = r'http://new\.livestream\.com/.*?/(?P<event_name>.*?)(/videos/(?P<id>\d+))?/?$'
+    _VALID_URL = r'https?://new\.livestream\.com/.*?/(?P<event_name>.*?)(/videos/(?P<id>[0-9]+)(?:/player)?)?/?(?:$|[?#])'
     _TESTS = [{
         'url': 'http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370',
         'md5': '53274c76ba7754fb0e8d072716f2292b',
@@ -37,6 +37,9 @@ class LivestreamIE(InfoExtractor):
             'title': 'TEDCity2.0 (English)',
         },
         'playlist_mincount': 4,
+    }, {
+        'url': 'https://new.livestream.com/accounts/362/events/3557232/videos/67864563/player?autoPlay=false&height=360&mute=false&width=640',
+        'only_matching': True,
     }]
 
     def _parse_smil(self, video_id, smil_url):

youtube_dl/extractor/mtv.py

@@ -33,7 +33,7 @@ class MTVServicesInfoExtractor(InfoExtractor):
         m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp\..+?/.*)$', rtmp_video_url)
         if not m:
             return rtmp_video_url
-        base = 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=1+_pxI0=Ripod-h264+_pxL0=undefined+_pxM0=+_pxK=18639+_pxE=mp4/44620/mtvnorigin/'
+        base = 'http://viacommtvstrmfs.fplive.net/'
         return base + m.group('finalid')
 
     def _get_feed_url(self, uri):

youtube_dl/extractor/myspass.py

@@ -13,9 +13,10 @@ class MySpassIE(InfoExtractor):
     _VALID_URL = r'http://www\.myspass\.de/.*'
     _TEST = {
         'url': 'http://www.myspass.de/myspass/shows/tvshows/absolute-mehrheit/Absolute-Mehrheit-vom-17022013-Die-Highlights-Teil-2--/11741/',
-        'file': '11741.mp4',
         'md5': '0b49f4844a068f8b33f4b7c88405862b',
         'info_dict': {
+            'id': '11741',
+            'ext': 'mp4',
             "description": "Wer kann in die Fu\u00dfstapfen von Wolfgang Kubicki treten und die Mehrheit der Zuschauer hinter sich versammeln? Wird vielleicht sogar die Absolute Mehrheit geknackt und der Jackpot von 200.000 Euro mit nach Hause genommen?",
             "title": "Absolute Mehrheit vom 17.02.2013 - Die Highlights, Teil 2",
         },

youtube_dl/extractor/myvideo.py

@@ -7,11 +7,12 @@ import re
 import json
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_ord,
     compat_urllib_parse,
     compat_urllib_request,
-
+)
+from ..utils import (
     ExtractorError,
 )
 

youtube_dl/extractor/ndr.py

@@ -67,7 +67,7 @@ class NDRIE(InfoExtractor):
 
         thumbnail = None
 
-        video_url = re.search(r'''3: \{src:'(?P<video>.+?)\.hi\.mp4', type:"video/mp4"},''', page)
+        video_url = re.search(r'''3: \{src:'(?P<video>.+?)\.(lo|hi|hq)\.mp4', type:"video/mp4"},''', page)
         if video_url:
             thumbnails = re.findall(r'''\d+: \{src: "([^"]+)"(?: \|\| '[^']+')?, quality: '([^']+)'}''', page)
             if thumbnails:

youtube_dl/extractor/niconico.py

@@ -12,6 +12,7 @@ from ..utils import (
     unified_strdate,
     parse_duration,
     int_or_none,
+    ExtractorError,
 )
 
 
@@ -108,6 +109,9 @@ class NiconicoIE(InfoExtractor):
                 flv_info_request, video_id,
                 note='Downloading flv info', errnote='Unable to download flv info')
 
+        if 'deleted=' in flv_info_webpage:
+            raise ExtractorError('The video has been deleted.',
+                expected=True)
         video_real_url = compat_urlparse.parse_qs(flv_info_webpage)['url'][0]
 
         # Start extracting information
@@ -171,7 +175,8 @@ class NiconicoPlaylistIE(InfoExtractor):
         entries = [{
             '_type': 'url',
             'ie_key': NiconicoIE.ie_key(),
-            'url': 'http://www.nicovideo.jp/watch/%s' % entry['item_id'],
+            'url': ('http://www.nicovideo.jp/watch/%s' %
+                entry['item_data']['video_id']),
         } for entry in entries]
 
         return {

youtube_dl/extractor/played.py

@@ -6,6 +6,7 @@ import os.path
 
 from .common import InfoExtractor
 from ..utils import (
+    ExtractorError,
     compat_urllib_parse,
     compat_urllib_request,
 )
@@ -29,6 +30,12 @@ class PlayedIE(InfoExtractor):
         video_id = self._match_id(url)
 
         orig_webpage = self._download_webpage(url, video_id)
+
+        m_error = re.search(
+            r'(?s)Reason for deletion:.*?<b class="err"[^>]*>(?P<msg>[^<]+)</b>', orig_webpage)
+        if m_error:
+            raise ExtractorError(m_error.group('msg'), expected=True)
+
         fields = re.findall(
             r'type="hidden" name="([^"]+)"\s+value="([^"]+)">', orig_webpage)
         data = dict(fields)

youtube_dl/extractor/ro220.py

@@ -1,7 +1,7 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import compat_urllib_parse_unquote
+from ..compat import compat_urllib_parse_unquote
 
 
 class Ro220IE(InfoExtractor):

youtube_dl/extractor/sexu.py

@@ -0,0 +1,61 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class SexuIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?sexu\.com/(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://sexu.com/961791/',
+        'md5': 'ff615aca9691053c94f8f10d96cd7884',
+        'info_dict': {
+            'id': '961791',
+            'ext': 'mp4',
+            'title': 'md5:4d05a19a5fc049a63dbbaf05fb71d91b',
+            'description': 'md5:c5ed8625eb386855d5a7967bd7b77a54',
+            'categories': list,  # NSFW
+            'thumbnail': 're:https?://.*\.jpg$',
+            'age_limit': 18,
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        quality_arr = self._search_regex(
+            r'sources:\s*\[([^\]]+)\]', webpage, 'forrmat string')
+        formats = [{
+            'url': fmt[0].replace('\\', ''),
+            'format_id': fmt[1],
+            'height': int(fmt[1][:3]),
+        } for fmt in re.findall(r'"file":"([^"]+)","label":"([^"]+)"', quality_arr)]
+        self._sort_formats(formats)
+
+        title = self._html_search_regex(
+            r'<title>([^<]+)\s*-\s*Sexu\.Com</title>', webpage, 'title')
+
+        description = self._html_search_meta(
+            'description', webpage, 'description')
+
+        thumbnail = self._html_search_regex(
+            r'image:\s*"([^"]+)"',
+            webpage, 'thumbnail', fatal=False)
+
+        categories_str = self._html_search_meta(
+            'keywords', webpage, 'categories')
+        categories = (
+            None if categories_str is None
+            else categories_str.split(','))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'categories': categories,
+            'formats': formats,
+            'age_limit': 18,
+        }

youtube_dl/extractor/spiegel.py

@@ -4,11 +4,11 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import compat_urlparse
+from ..compat import compat_urlparse
 
 
 class SpiegelIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<videoID>[0-9]+)(?:\.html)?(?:#.*)?$'
+    _VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<id>[0-9]+)(?:-embed)?(?:\.html)?(?:#.*)?$'
     _TESTS = [{
         'url': 'http://www.spiegel.de/video/vulkan-tungurahua-in-ecuador-ist-wieder-aktiv-video-1259285.html',
         'md5': '2c2754212136f35fb4b19767d242f66e',
@@ -29,16 +29,24 @@ class SpiegelIE(InfoExtractor):
             'description': 'md5:c2322b65e58f385a820c10fa03b2d088',
             'duration': 983,
         },
+    }, {
+        'url': 'http://www.spiegel.de/video/astronaut-alexander-gerst-von-der-iss-station-beantwortet-fragen-video-1519126-embed.html',
+        'md5': 'd8eeca6bfc8f1cd6f490eb1f44695d51',
+        'info_dict': {
+            'id': '1519126',
+            'ext': 'mp4',
+            'description': 'SPIEGEL ONLINE-Nutzer durften den deutschen Astronauten Alexander Gerst über sein Leben auf der ISS-Station befragen. Hier kommen seine Antworten auf die besten sechs Fragen.',
+            'title': 'Fragen an Astronaut Alexander Gerst: "Bekommen Sie die Tageszeiten mit?"',
+        }
     }]
 
     def _real_extract(self, url):
-        m = re.match(self._VALID_URL, url)
-        video_id = m.group('videoID')
-
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
-        title = self._html_search_regex(
-            r'<div class="module-title">(.*?)</div>', webpage, 'title')
+        title = re.sub(r'\s+', ' ', self._html_search_regex(
+            r'(?s)<(?:h1|div) class="module-title"[^>]*>(.*?)</(?:h1|div)>',
+            webpage, 'title'))
         description = self._html_search_meta('description', webpage, 'description')
 
         base_url = self._search_regex(
@@ -79,7 +87,7 @@ class SpiegelArticleIE(InfoExtractor):
     _VALID_URL = 'https?://www\.spiegel\.de/(?!video/)[^?#]*?-(?P<id>[0-9]+)\.html'
     IE_NAME = 'Spiegel:Article'
     IE_DESC = 'Articles on spiegel.de'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.spiegel.de/sport/sonst/badminton-wm-die-randsportart-soll-populaerer-werden-a-987092.html',
         'info_dict': {
             'id': '1516455',
@@ -87,20 +95,34 @@ class SpiegelArticleIE(InfoExtractor):
             'title': 'Faszination Badminton: Nennt es bloß nicht Federball',
             'description': 're:^Patrick Kämnitz gehört.{100,}',
         },
-    }
+    }, {
+        'url': 'http://www.spiegel.de/wissenschaft/weltall/astronaut-alexander-gerst-antwortet-spiegel-online-lesern-a-989876.html',
+        'info_dict': {
+
+        },
+        'playlist_count': 6,
+    }]
 
     def _real_extract(self, url):
-        m = re.match(self._VALID_URL, url)
-        video_id = m.group('id')
-
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
+
+        # Single video on top of the page
         video_link = self._search_regex(
             r'<a href="([^"]+)" onclick="return spOpenVideo\(this,', webpage,
-            'video page URL')
-        video_url = compat_urlparse.urljoin(
-            self.http_scheme() + '//spiegel.de/', video_link)
+            'video page URL', default=None)
+        if video_link:
+            video_url = compat_urlparse.urljoin(
+                self.http_scheme() + '//spiegel.de/', video_link)
+            return self.url_result(video_url)
 
-        return {
-            '_type': 'url',
-            'url': video_url,
-        }
+        # Multiple embedded videos
+        embeds = re.findall(
+            r'<div class="vid_holder[0-9]+.*?</div>\s*.*?url\s*=\s*"([^"]+)"',
+            webpage)
+        entries = [
+            self.url_result(compat_urlparse.urljoin(
+                self.http_scheme() + '//spiegel.de/', embed_path))
+            for embed_path in embeds
+        ]
+        return self.playlist_result(entries)

youtube_dl/extractor/streamcloud.py

@@ -13,7 +13,7 @@ from ..utils import (
 
 class StreamcloudIE(InfoExtractor):
     IE_NAME = 'streamcloud.eu'
-    _VALID_URL = r'https?://streamcloud\.eu/(?P<id>[a-zA-Z0-9_-]+)/(?P<fname>[^#?]*)\.html'
+    _VALID_URL = r'https?://streamcloud\.eu/(?P<id>[a-zA-Z0-9_-]+)(?:/(?P<fname>[^#?]*)\.html)?'
 
     _TEST = {
         'url': 'http://streamcloud.eu/skp9j99s4bpz/youtube-dl_test_video_____________-BaW_jenozKc.mp4.html',
@@ -27,8 +27,8 @@ class StreamcloudIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
+        url = 'http://streamcloud.eu/%s' % video_id
 
         orig_webpage = self._download_webpage(url, video_id)
 

youtube_dl/extractor/swrmediathek.py

@@ -80,7 +80,7 @@ class SWRMediathekIE(InfoExtractor):
 
             if media_type == 'Video':
                 fmt.update({
-                    'format_note': ['144p', '288p', '544p'][quality-1],
+                    'format_note': ['144p', '288p', '544p', '720p'][quality-1],
                     'vcodec': codec,
                 })
             elif media_type == 'Audio':
@@ -101,4 +101,4 @@ class SWRMediathekIE(InfoExtractor):
             'uploader': attr['channel_title'],
             'uploader_id': attr['channel_idkey'],
             'formats': formats,
-        }
+        }

youtube_dl/extractor/tapely.py

@@ -50,6 +50,7 @@ class TapelyIE(InfoExtractor):
         request = compat_urllib_request.Request(playlist_url)
         request.add_header('X-Requested-With', 'XMLHttpRequest')
         request.add_header('Accept', 'application/json')
+        request.add_header('Referer', url)
 
         playlist = self._download_json(request, display_id)
 

youtube_dl/extractor/ted.py

@@ -38,6 +38,7 @@ class TEDIE(SubtitlesInfoExtractor):
                 'actively fooling us.'),
             'uploader': 'Dan Dennett',
             'width': 854,
+            'duration': 1308,
         }
     }, {
         'url': 'http://www.ted.com/watch/ted-institute/ted-bcg/vishal-sikka-the-beauty-and-power-of-algorithms',
@@ -57,6 +58,7 @@ class TEDIE(SubtitlesInfoExtractor):
             'title': 'Be passionate. Be courageous. Be your best.',
             'uploader': 'Gabby Giffords and Mark Kelly',
             'description': 'md5:5174aed4d0f16021b704120360f72b92',
+            'duration': 1128,
         },
     }, {
         'url': 'http://www.ted.com/playlists/who_are_the_hackers',
@@ -178,6 +180,7 @@ class TEDIE(SubtitlesInfoExtractor):
             'description': self._og_search_description(webpage),
             'subtitles': video_subtitles,
             'formats': formats,
+            'duration': talk_info.get('duration'),
         }
 
     def _get_available_subtitles(self, video_id, talk_info):

youtube_dl/extractor/trutube.py

@@ -29,7 +29,7 @@ class TruTubeIE(InfoExtractor):
 
         # filehd is always 404
         video_url = xpath_text(config, './file', 'video URL', fatal=True)
-        title = xpath_text(config, './title', 'title')
+        title = xpath_text(config, './title', 'title').strip()
         thumbnail = xpath_text(config, './image', ' thumbnail')
 
         return {

youtube_dl/extractor/tvplay.py

@@ -4,9 +4,9 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_str
 from ..utils import (
     ExtractorError,
-    compat_str,
     parse_iso8601,
     qualities,
 )
@@ -176,8 +176,7 @@ class TVPlayIE(InfoExtractor):
     ]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
 
         video = self._download_json(
             'http://playapi.mtgx.tv/v1/videos/%s' % video_id, video_id, 'Downloading video JSON')
@@ -208,6 +207,10 @@ class TVPlayIE(InfoExtractor):
                     'app': m.group('app'),
                     'play_path': m.group('playpath'),
                 })
+            elif video_url.endswith('.f4m'):
+                formats.extend(self._extract_f4m_formats(
+                    video_url + '?hdcore=3.5.0&plugin=aasp-3.5.0.151.81', video_id))
+                continue
             else:
                 fmt.update({
                     'url': video_url,

youtube_dl/extractor/ustream.py

@@ -5,7 +5,6 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     compat_urlparse,
-    get_meta_content,
 )
 
 
@@ -79,7 +78,7 @@ class UstreamChannelIE(InfoExtractor):
         m = re.match(self._VALID_URL, url)
         display_id = m.group('slug')
         webpage = self._download_webpage(url, display_id)
-        channel_id = get_meta_content('ustream:channel_id', webpage)
+        channel_id = self._html_search_meta('ustream:channel_id', webpage)
 
         BASE = 'http://www.ustream.tv'
         next_url = '/ajax/socialstream/videos/%s/1.json' % channel_id

youtube_dl/extractor/vice.py

@@ -0,0 +1,38 @@
+from __future__ import unicode_literals
+import re
+
+from .common import InfoExtractor
+from .ooyala import OoyalaIE
+from ..utils import ExtractorError
+
+
+class ViceIE(InfoExtractor):
+    _VALID_URL = r'http://www\.vice\.com/.*?/(?P<name>.+)'
+
+    _TEST = {
+        'url': 'http://www.vice.com/Fringes/cowboy-capitalists-part-1',
+        'info_dict': {
+            'id': '43cW1mYzpia9IlestBjVpd23Yu3afAfp',
+            'ext': 'mp4',
+            'title': 'VICE_COWBOYCAPITALISTS_PART01_v1_VICE_WM_1080p.mov',
+        },
+        'params': {
+            # Requires ffmpeg (m3u8 manifest)
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        name = mobj.group('name')
+        webpage = self._download_webpage(url, name)
+        try:
+            embed_code = self._search_regex(
+                r'embedCode=([^&\'"]+)', webpage,
+                'ooyala embed code')
+            ooyala_url = OoyalaIE._url_for_embed_code(embed_code)
+            print(ooyala_url)
+        except ExtractorError:
+            raise ExtractorError('The page doesn\'t contain a video', expected=True)
+        return self.url_result(ooyala_url, ie='Ooyala')
+

youtube_dl/extractor/vimeo.py

@@ -7,11 +7,13 @@ import itertools
 
 from .common import InfoExtractor
 from .subtitles import SubtitlesInfoExtractor
-from ..utils import (
+from ..compat import (
     compat_HTTPError,
     compat_urllib_parse,
     compat_urllib_request,
     compat_urlparse,
+)
+from ..utils import (
     ExtractorError,
     InAdvancePagedList,
     int_or_none,

youtube_dl/extractor/wimp.py

@@ -37,7 +37,7 @@ class WimpIE(InfoExtractor):
         video_id = mobj.group(1)
         webpage = self._download_webpage(url, video_id)
         video_url = self._search_regex(
-            r"'file'\s*:\s*'([^']+)'", webpage, 'video URL')
+            r"[\"']file[\"']\s*[:,]\s*[\"'](.+?)[\"']", webpage, 'video URL')
         if YoutubeIE.suitable(video_url):
             self.to_screen('Found YouTube video')
             return {

youtube_dl/extractor/wrzuta.py

@@ -27,15 +27,15 @@ class WrzutaIE(InfoExtractor):
             'description': 'md5:7fb5ef3c21c5893375fda51d9b15d9cd',
         },
     }, {
-        'url': 'http://w729.wrzuta.pl/audio/9oXJqdcndqv/david_guetta_amp_showtek_ft._vassy_-_bad',
-        'md5': '1e546a18e1c22ac6e9adce17b8961ff5',
+        'url': 'http://jolka85.wrzuta.pl/audio/063jOPX5ue2/liber_natalia_szroeder_-_teraz_ty',
+        'md5': 'bc78077859bea7bcfe4295d7d7fc9025',
         'info_dict': {
-            'id': '9oXJqdcndqv',
+            'id': '063jOPX5ue2',
             'ext': 'ogg',
-            'title': 'David Guetta & Showtek ft. Vassy - Bad',
-            'duration': 270,
-            'uploader_id': 'w729',
-            'description': 'md5:4628f01c666bbaaecefa83476cfa794a',
+            'title': 'Liber & Natalia Szroeder - Teraz Ty',
+            'duration': 203,
+            'uploader_id': 'jolka85',
+            'description': 'md5:2d2b6340f9188c8c4cd891580e481096',
         },
     }]
 
@@ -49,16 +49,17 @@ class WrzutaIE(InfoExtractor):
 
         quality = qualities(['SD', 'MQ', 'HQ', 'HD'])
 
-        audio_table = {'flv': 'mp3', 'webm': 'ogg'}
+        audio_table = {'flv': 'mp3', 'webm': 'ogg', '???': 'mp3'}
 
         embedpage = self._download_json('http://www.wrzuta.pl/npp/embed/%s/%s' % (uploader, video_id), video_id)
 
         formats = []
         for media in embedpage['url']:
+            fmt = media['type'].split('@')[0]
             if typ == 'audio':
-                ext = audio_table[media['type'].split('@')[0]]
+                ext = audio_table.get(fmt, fmt)
             else:
-                ext = media['type'].split('@')[0]
+                ext = fmt
 
             formats.append({
                 'format_id': '%s_%s' % (ext, media['quality'].lower()),

youtube_dl/extractor/youjizz.py

@@ -9,40 +9,30 @@ from ..utils import (
 
 
 class YouJizzIE(InfoExtractor):
-    _VALID_URL = r'^https?://(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+)\.html$'
+    _VALID_URL = r'https?://(?:\w+\.)?youjizz\.com/videos/[^/#?]+-(?P<id>[0-9]+)\.html(?:$|[?#])'
     _TEST = {
         'url': 'http://www.youjizz.com/videos/zeichentrick-1-2189178.html',
-        'file': '2189178.flv',
         'md5': '07e15fa469ba384c7693fd246905547c',
         'info_dict': {
+            'id': '2189178',
+            'ext': 'flv',
             "title": "Zeichentrick 1",
             "age_limit": 18,
         }
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-
-        video_id = mobj.group('videoid')
-
-        # Get webpage content
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
-
         age_limit = self._rta_search(webpage)
+        video_title = self._html_search_regex(
+            r'<title>\s*(.*)\s*</title>', webpage, 'title')
 
-        # Get the video title
-        video_title = self._html_search_regex(r'<title>(?P<title>.*)</title>',
-            webpage, 'title').strip()
-
-        # Get the embed page
-        result = re.search(r'https?://www.youjizz.com/videos/embed/(?P<videoid>[0-9]+)', webpage)
-        if result is None:
-            raise ExtractorError('ERROR: unable to extract embed page')
-
-        embed_page_url = result.group(0).strip()
-        video_id = result.group('videoid')
-
-        webpage = self._download_webpage(embed_page_url, video_id)
+        embed_page_url = self._search_regex(
+            r'(https?://www.youjizz.com/videos/embed/[0-9]+)',
+            webpage, 'embed page')
+        webpage = self._download_webpage(
+            embed_page_url, video_id, note='downloading embed page')
 
         # Get the video URL
         m_playlist = re.search(r'so.addVariable\("playlist", ?"(?P<playlist>.+?)"\);', webpage)

youtube_dl/extractor/youtube.py

@@ -510,7 +510,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
 
     def _parse_sig_js(self, jscode):
         funcname = self._search_regex(
-            r'signature=([$a-zA-Z]+)', jscode,
+            r'\.sig\|\|([a-zA-Z0-9]+)\(', jscode,
              'Initial JS player signature function name')
 
         jsi = JSInterpreter(jscode)
@@ -684,7 +684,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
         # Get video info
         self.report_video_info_webpage_download(video_id)
         if re.search(r'player-age-gate-content">', video_webpage) is not None:
-            self.report_age_confirmation()
             age_gate = True
             # We simulate the access to the video from www.youtube.com/v/{video_id}
             # this can be viewed without login into Youtube
@@ -692,12 +691,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
                 'video_id': video_id,
                 'eurl': 'https://youtube.googleapis.com/v/' + video_id,
                 'sts': self._search_regex(
-                    r'"sts"\s*:\s*(\d+)', video_webpage, 'sts'),
+                    r'"sts"\s*:\s*(\d+)', video_webpage, 'sts', default=''),
             })
             video_info_url = proto + '://www.youtube.com/get_video_info?' + data
-            video_info_webpage = self._download_webpage(video_info_url, video_id,
-                                    note=False,
-                                    errnote='unable to download video info webpage')
+            video_info_webpage = self._download_webpage(
+                video_info_url, video_id,
+                note='Refetching age-gated info webpage',
+                errnote='unable to download video info webpage')
             video_info = compat_parse_qs(video_info_webpage)
         else:
             age_gate = False
@@ -1043,6 +1043,7 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
         'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
         'info_dict': {
             'title': 'ytdl test PL',
+            'id': 'PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
         },
         'playlist_count': 3,
     }, {

youtube_dl/options.py

@@ -5,9 +5,11 @@ import optparse
 import shlex
 import sys
 
-from .utils import (
+from .compat import (
     compat_expanduser,
     compat_getenv,
+)
+from .utils import (
     get_term_width,
     write_string,
 )
@@ -259,7 +261,16 @@ def parseOpts(overrideArguments=None):
     video_format.add_option(
         '-f', '--format',
         action='store', dest='format', metavar='FORMAT', default=None,
-        help='video format code, specify the order of preference using slashes: -f 22/17/18 .  -f mp4 , -f m4a and  -f flv  are also supported. You can also use the special names "best", "bestvideo", "bestaudio", "worst", "worstvideo" and "worstaudio". By default, youtube-dl will pick the best quality. Use commas to download multiple audio formats, such as  -f  136/137/mp4/bestvideo,140/m4a/bestaudio')
+        help='video format code, specify the order of preference using'
+            ' slashes: -f 22/17/18 .  -f mp4 , -f m4a and  -f flv  are also'
+            ' supported. You can also use the special names "best",'
+            ' "bestvideo", "bestaudio", "worst", "worstvideo" and'
+            ' "worstaudio". By default, youtube-dl will pick the best quality.'
+            ' Use commas to download multiple audio formats, such as'
+            ' -f  136/137/mp4/bestvideo,140/m4a/bestaudio.'
+            ' You can merge the video and audio of two formats into a single'
+            ' file using -f <video-format>+<audio-format> (requires ffmpeg or'
+            ' avconv), for example -f bestvideo+bestaudio.')
     video_format.add_option(
         '--all-formats',
         action='store_const', dest='format', const='all',
@@ -479,10 +490,12 @@ def parseOpts(overrideArguments=None):
               '%(format_id)s for the unique id of the format (like Youtube\'s itags: "137"), '
               '%(upload_date)s for the upload date (YYYYMMDD), '
               '%(extractor)s for the provider (youtube, metacafe, etc), '
-              '%(id)s for the video id, %(playlist)s for the playlist the video is in, '
-              '%(playlist_index)s for the position in the playlist and %% for a literal percent. '
+              '%(id)s for the video id, '
+              '%(playlist_title)s, %(playlist_id)s, or %(playlist)s (=title if present, ID otherwise) for the playlist the video is in, '
+              '%(playlist_index)s for the position in the playlist. '
               '%(height)s and %(width)s for the width and height of the video format. '
               '%(resolution)s for a textual description of the resolution of the video format. '
+              '%% for a literal percent. '
               'Use - to output to stdout. Can also be used to download to a different directory, '
               'for example with -o \'/my/downloads/%(uploader)s/%(title)s-%(id)s.%(ext)s\' .'))
     filesystem.add_option(

youtube_dl/postprocessor/atomicparsley.py

@@ -6,10 +6,11 @@ import os
 import subprocess
 
 from .common import PostProcessor
-
+from ..compat import (
+    compat_urlretrieve,
+)
 from ..utils import (
     check_executable,
-    compat_urlretrieve,
     encodeFilename,
     PostProcessingError,
     prepend_extension,

youtube_dl/postprocessor/execafterdownload.py

@@ -3,10 +3,8 @@ from __future__ import unicode_literals
 import subprocess
 
 from .common import PostProcessor
-from ..utils import (
-    shlex_quote,
-    PostProcessingError,
-)
+from ..compat import shlex_quote
+from ..utils import PostProcessingError
 
 
 class ExecAfterDownloadPP(PostProcessor):

youtube_dl/postprocessor/ffmpeg.py

@@ -1,5 +1,4 @@
 import os
-import re
 import subprocess
 import sys
 import time
@@ -7,10 +6,13 @@ import time
 
 from .common import AudioConversionError, PostProcessor
 
-from ..utils import (
+from ..compat import (
     compat_subprocess_get_DEVNULL,
+)
+from ..utils import (
     encodeArgument,
     encodeFilename,
+    get_exe_version,
     is_outdated_version,
     PostProcessingError,
     prepend_extension,
@@ -19,23 +21,6 @@ from ..utils import (
 )
 
 
-def get_version(executable):
-    """ Returns the version of the specified executable,
-    or False if the executable is not present """
-    try:
-        out, err = subprocess.Popen(
-            [executable, '-version'],
-            stdout=subprocess.PIPE, stderr=subprocess.STDOUT).communicate()
-    except OSError:
-        return False
-    firstline = out.partition(b'\n')[0].decode('ascii', 'ignore')
-    m = re.search(r'version\s+([0-9._-a-zA-Z]+)', firstline)
-    if not m:
-        return u'present'
-    else:
-        return m.group(1)
-
-
 class FFmpegPostProcessorError(PostProcessingError):
     pass
 
@@ -61,7 +46,7 @@ class FFmpegPostProcessor(PostProcessor):
     @staticmethod
     def get_versions():
         programs = ['avprobe', 'avconv', 'ffmpeg', 'ffprobe']
-        return dict((program, get_version(program)) for program in programs)
+        return dict((p, get_exe_version(p, args=['-version'])) for p in programs)
 
     @property
     def _executable(self):

youtube_dl/postprocessor/xattrpp.py

@@ -3,10 +3,12 @@ import subprocess
 import sys
 
 from .common import PostProcessor
+from ..compat import (
+    subprocess_check_output
+)
 from ..utils import (
     check_executable,
     hyphenate_date,
-    subprocess_check_output
 )
 
 

youtube_dl/utils.py

@@ -1,6 +1,8 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 
+from __future__ import unicode_literals
+
 import calendar
 import codecs
 import contextlib
@@ -8,7 +10,6 @@ import ctypes
 import datetime
 import email.utils
 import errno
-import getpass
 import gzip
 import itertools
 import io
@@ -29,254 +30,18 @@ import traceback
 import xml.etree.ElementTree
 import zlib
 
-try:
-    import urllib.request as compat_urllib_request
-except ImportError: # Python 2
-    import urllib2 as compat_urllib_request
-
-try:
-    import urllib.error as compat_urllib_error
-except ImportError: # Python 2
-    import urllib2 as compat_urllib_error
-
-try:
-    import urllib.parse as compat_urllib_parse
-except ImportError: # Python 2
-    import urllib as compat_urllib_parse
-
-try:
-    from urllib.parse import urlparse as compat_urllib_parse_urlparse
-except ImportError: # Python 2
-    from urlparse import urlparse as compat_urllib_parse_urlparse
-
-try:
-    import urllib.parse as compat_urlparse
-except ImportError: # Python 2
-    import urlparse as compat_urlparse
-
-try:
-    import http.cookiejar as compat_cookiejar
-except ImportError: # Python 2
-    import cookielib as compat_cookiejar
-
-try:
-    import html.entities as compat_html_entities
-except ImportError: # Python 2
-    import htmlentitydefs as compat_html_entities
-
-try:
-    import html.parser as compat_html_parser
-except ImportError: # Python 2
-    import HTMLParser as compat_html_parser
-
-try:
-    import http.client as compat_http_client
-except ImportError: # Python 2
-    import httplib as compat_http_client
-
-try:
-    from urllib.error import HTTPError as compat_HTTPError
-except ImportError:  # Python 2
-    from urllib2 import HTTPError as compat_HTTPError
-
-try:
-    from urllib.request import urlretrieve as compat_urlretrieve
-except ImportError:  # Python 2
-    from urllib import urlretrieve as compat_urlretrieve
-
-
-try:
-    from subprocess import DEVNULL
-    compat_subprocess_get_DEVNULL = lambda: DEVNULL
-except ImportError:
-    compat_subprocess_get_DEVNULL = lambda: open(os.path.devnull, 'w')
-
-try:
-    from urllib.parse import unquote as compat_urllib_parse_unquote
-except ImportError:
-    def compat_urllib_parse_unquote(string, encoding='utf-8', errors='replace'):
-        if string == '':
-            return string
-        res = string.split('%')
-        if len(res) == 1:
-            return string
-        if encoding is None:
-            encoding = 'utf-8'
-        if errors is None:
-            errors = 'replace'
-        # pct_sequence: contiguous sequence of percent-encoded bytes, decoded
-        pct_sequence = b''
-        string = res[0]
-        for item in res[1:]:
-            try:
-                if not item:
-                    raise ValueError
-                pct_sequence += item[:2].decode('hex')
-                rest = item[2:]
-                if not rest:
-                    # This segment was just a single percent-encoded character.
-                    # May be part of a sequence of code units, so delay decoding.
-                    # (Stored in pct_sequence).
-                    continue
-            except ValueError:
-                rest = '%' + item
-            # Encountered non-percent-encoded characters. Flush the current
-            # pct_sequence.
-            string += pct_sequence.decode(encoding, errors) + rest
-            pct_sequence = b''
-        if pct_sequence:
-            # Flush the final pct_sequence
-            string += pct_sequence.decode(encoding, errors)
-        return string
-
-
-try:
-    from urllib.parse import parse_qs as compat_parse_qs
-except ImportError: # Python 2
-    # HACK: The following is the correct parse_qs implementation from cpython 3's stdlib.
-    # Python 2's version is apparently totally broken
-
-    def _parse_qsl(qs, keep_blank_values=False, strict_parsing=False,
-                encoding='utf-8', errors='replace'):
-        qs, _coerce_result = qs, unicode
-        pairs = [s2 for s1 in qs.split('&') for s2 in s1.split(';')]
-        r = []
-        for name_value in pairs:
-            if not name_value and not strict_parsing:
-                continue
-            nv = name_value.split('=', 1)
-            if len(nv) != 2:
-                if strict_parsing:
-                    raise ValueError("bad query field: %r" % (name_value,))
-                # Handle case of a control-name with no equal sign
-                if keep_blank_values:
-                    nv.append('')
-                else:
-                    continue
-            if len(nv[1]) or keep_blank_values:
-                name = nv[0].replace('+', ' ')
-                name = compat_urllib_parse_unquote(
-                    name, encoding=encoding, errors=errors)
-                name = _coerce_result(name)
-                value = nv[1].replace('+', ' ')
-                value = compat_urllib_parse_unquote(
-                    value, encoding=encoding, errors=errors)
-                value = _coerce_result(value)
-                r.append((name, value))
-        return r
-
-    def compat_parse_qs(qs, keep_blank_values=False, strict_parsing=False,
-                encoding='utf-8', errors='replace'):
-        parsed_result = {}
-        pairs = _parse_qsl(qs, keep_blank_values, strict_parsing,
-                        encoding=encoding, errors=errors)
-        for name, value in pairs:
-            if name in parsed_result:
-                parsed_result[name].append(value)
-            else:
-                parsed_result[name] = [value]
-        return parsed_result
-
-try:
-    compat_str = unicode # Python 2
-except NameError:
-    compat_str = str
-
-try:
-    compat_chr = unichr # Python 2
-except NameError:
-    compat_chr = chr
-
-try:
-    from xml.etree.ElementTree import ParseError as compat_xml_parse_error
-except ImportError:  # Python 2.6
-    from xml.parsers.expat import ExpatError as compat_xml_parse_error
-
-try:
-    from shlex import quote as shlex_quote
-except ImportError:  # Python < 3.3
-    def shlex_quote(s):
-        return "'" + s.replace("'", "'\"'\"'") + "'"
-
-
-def compat_ord(c):
-    if type(c) is int: return c
-    else: return ord(c)
-
-
-if sys.version_info >= (3, 0):
-    compat_getenv = os.getenv
-    compat_expanduser = os.path.expanduser
-else:
-    # Environment variables should be decoded with filesystem encoding.
-    # Otherwise it will fail if any non-ASCII characters present (see #3854 #3217 #2918)
-
-    def compat_getenv(key, default=None):
-        env = os.getenv(key, default)
-        if env:
-            env = env.decode(get_filesystem_encoding())
-        return env
-
-    # HACK: The default implementations of os.path.expanduser from cpython do not decode
-    # environment variables with filesystem encoding. We will work around this by
-    # providing adjusted implementations.
-    # The following are os.path.expanduser implementations from cpython 2.7.8 stdlib
-    # for different platforms with correct environment variables decoding.
-
-    if os.name == 'posix':
-        def compat_expanduser(path):
-            """Expand ~ and ~user constructions.  If user or $HOME is unknown,
-            do nothing."""
-            if not path.startswith('~'):
-                return path
-            i = path.find('/', 1)
-            if i < 0:
-                i = len(path)
-            if i == 1:
-                if 'HOME' not in os.environ:
-                    import pwd
-                    userhome = pwd.getpwuid(os.getuid()).pw_dir
-                else:
-                    userhome = compat_getenv('HOME')
-            else:
-                import pwd
-                try:
-                    pwent = pwd.getpwnam(path[1:i])
-                except KeyError:
-                    return path
-                userhome = pwent.pw_dir
-            userhome = userhome.rstrip('/')
-            return (userhome + path[i:]) or '/'
-    elif os.name == 'nt' or os.name == 'ce':
-        def compat_expanduser(path):
-            """Expand ~ and ~user constructs.
-
-            If user or $HOME is unknown, do nothing."""
-            if path[:1] != '~':
-                return path
-            i, n = 1, len(path)
-            while i < n and path[i] not in '/\\':
-                i = i + 1
-
-            if 'HOME' in os.environ:
-                userhome = compat_getenv('HOME')
-            elif 'USERPROFILE' in os.environ:
-                userhome = compat_getenv('USERPROFILE')
-            elif not 'HOMEPATH' in os.environ:
-                return path
-            else:
-                try:
-                    drive = compat_getenv('HOMEDRIVE')
-                except KeyError:
-                    drive = ''
-                userhome = os.path.join(drive, compat_getenv('HOMEPATH'))
-
-            if i != 1: #~user
-                userhome = os.path.join(os.path.dirname(userhome), path[1:i])
-
-            return userhome + path[i:]
-    else:
-        compat_expanduser = os.path.expanduser
+from .compat import (
+    compat_chr,
+    compat_getenv,
+    compat_html_entities,
+    compat_parse_qs,
+    compat_str,
+    compat_urllib_error,
+    compat_urllib_parse,
+    compat_urllib_parse_urlparse,
+    compat_urllib_request,
+    compat_urlparse,
+)
 
 
 # This is not clearly defined otherwise
@@ -304,14 +69,6 @@ def preferredencoding():
 
     return pref
 
-if sys.version_info < (3,0):
-    def compat_print(s):
-        print(s.encode(preferredencoding(), 'xmlcharrefreplace'))
-else:
-    def compat_print(s):
-        assert type(s) == type(u'')
-        print(s)
-
 
 def write_json_file(obj, fn):
     """ Encode obj as JSON and write it to fn, atomically """
@@ -394,127 +151,32 @@ def xpath_text(node, xpath, name=None, fatal=False):
     return n.text
 
 
-compat_html_parser.locatestarttagend = re.compile(r"""<[a-zA-Z][-.a-zA-Z0-9:_]*(?:\s+(?:(?<=['"\s])[^\s/>][^\s/=>]*(?:\s*=+\s*(?:'[^']*'|"[^"]*"|(?!['"])[^>\s]*))?\s*)*)?\s*""", re.VERBOSE) # backport bugfix
-class BaseHTMLParser(compat_html_parser.HTMLParser):
-    def __init(self):
-        compat_html_parser.HTMLParser.__init__(self)
-        self.html = None
-
-    def loads(self, html):
-        self.html = html
-        self.feed(html)
-        self.close()
-
-class AttrParser(BaseHTMLParser):
-    """Modified HTMLParser that isolates a tag with the specified attribute"""
-    def __init__(self, attribute, value):
-        self.attribute = attribute
-        self.value = value
-        self.result = None
-        self.started = False
-        self.depth = {}
-        self.watch_startpos = False
-        self.error_count = 0
-        BaseHTMLParser.__init__(self)
-
-    def error(self, message):
-        if self.error_count > 10 or self.started:
-            raise compat_html_parser.HTMLParseError(message, self.getpos())
-        self.rawdata = '\n'.join(self.html.split('\n')[self.getpos()[0]:]) # skip one line
-        self.error_count += 1
-        self.goahead(1)
-
-    def handle_starttag(self, tag, attrs):
-        attrs = dict(attrs)
-        if self.started:
-            self.find_startpos(None)
-        if self.attribute in attrs and attrs[self.attribute] == self.value:
-            self.result = [tag]
-            self.started = True
-            self.watch_startpos = True
-        if self.started:
-            if not tag in self.depth: self.depth[tag] = 0
-            self.depth[tag] += 1
-
-    def handle_endtag(self, tag):
-        if self.started:
-            if tag in self.depth: self.depth[tag] -= 1
-            if self.depth[self.result[0]] == 0:
-                self.started = False
-                self.result.append(self.getpos())
-
-    def find_startpos(self, x):
-        """Needed to put the start position of the result (self.result[1])
-        after the opening tag with the requested id"""
-        if self.watch_startpos:
-            self.watch_startpos = False
-            self.result.append(self.getpos())
-    handle_entityref = handle_charref = handle_data = handle_comment = \
-    handle_decl = handle_pi = unknown_decl = find_startpos
-
-    def get_result(self):
-        if self.result is None:
-            return None
-        if len(self.result) != 3:
-            return None
-        lines = self.html.split('\n')
-        lines = lines[self.result[1][0]-1:self.result[2][0]]
-        lines[0] = lines[0][self.result[1][1]:]
-        if len(lines) == 1:
-            lines[-1] = lines[-1][:self.result[2][1]-self.result[1][1]]
-        lines[-1] = lines[-1][:self.result[2][1]]
-        return '\n'.join(lines).strip()
-# Hack for https://github.com/rg3/youtube-dl/issues/662
-if sys.version_info < (2, 7, 3):
-    AttrParser.parse_endtag = (lambda self, i:
-        i + len("</scr'+'ipt>")
-        if self.rawdata[i:].startswith("</scr'+'ipt>")
-        else compat_html_parser.HTMLParser.parse_endtag(self, i))
-
 def get_element_by_id(id, html):
     """Return the content of the tag with the specified ID in the passed HTML document"""
     return get_element_by_attribute("id", id, html)
 
+
 def get_element_by_attribute(attribute, value, html):
     """Return the content of the tag with the specified attribute in the passed HTML document"""
-    parser = AttrParser(attribute, value)
-    try:
-        parser.loads(html)
-    except compat_html_parser.HTMLParseError:
-        pass
-    return parser.get_result()
 
-class MetaParser(BaseHTMLParser):
-    """
-    Modified HTMLParser that isolates a meta tag with the specified name 
-    attribute.
-    """
-    def __init__(self, name):
-        BaseHTMLParser.__init__(self)
-        self.name = name
-        self.content = None
-        self.result = None
+    m = re.search(r'''(?xs)
+        <([a-zA-Z0-9:._-]+)
+         (?:\s+[a-zA-Z0-9:._-]+(?:=[a-zA-Z0-9:._-]+|="[^"]+"|='[^']+'))*?
+         \s+%s=['"]?%s['"]?
+         (?:\s+[a-zA-Z0-9:._-]+(?:=[a-zA-Z0-9:._-]+|="[^"]+"|='[^']+'))*?
+        \s*>
+        (?P<content>.*?)
+        </\1>
+    ''' % (re.escape(attribute), re.escape(value)), html)
 
-    def handle_starttag(self, tag, attrs):
-        if tag != 'meta':
-            return
-        attrs = dict(attrs)
-        if attrs.get('name') == self.name:
-            self.result = attrs.get('content')
+    if not m:
+        return None
+    res = m.group('content')
 
-    def get_result(self):
-        return self.result
+    if res.startswith('"') or res.startswith("'"):
+        res = res[1:-1]
 
-def get_meta_content(name, html):
-    """
-    Return the content attribute from the meta tag with the given name attribute.
-    """
-    parser = MetaParser(name)
-    try:
-        parser.loads(html)
-    except compat_html_parser.HTMLParseError:
-        pass
-    return parser.get_result()
+    return unescapeHTML(res)
 
 
 def clean_html(html):
@@ -1181,10 +843,7 @@ def bytes_to_intlist(bs):
 def intlist_to_bytes(xs):
     if not xs:
         return b''
-    if isinstance(chr(0), bytes):  # Python 2
-        return ''.join([chr(x) for x in xs])
-    else:
-        return bytes(xs)
+    return struct.pack('%dB' % len(xs), *xs)
 
 
 # Cross-platform file locking
@@ -1472,6 +1131,25 @@ def check_executable(exe, args=[]):
     return exe
 
 
+def get_exe_version(exe, args=['--version'],
+                    version_re=r'version\s+([0-9._-a-zA-Z]+)',
+                    unrecognized=u'present'):
+    """ Returns the version of the specified executable,
+    or False if the executable is not present """
+    try:
+        out, err = subprocess.Popen(
+            [exe] + args,
+            stdout=subprocess.PIPE, stderr=subprocess.STDOUT).communicate()
+    except OSError:
+        return False
+    firstline = out.partition(b'\n')[0].decode('ascii', 'ignore')
+    m = re.search(version_re, firstline)
+    if m:
+        return m.group(1)
+    else:
+        return unrecognized
+
+
 class PagedList(object):
     def __len__(self):
         # This is only useful for tests
@@ -1562,7 +1240,7 @@ def escape_rfc3986(s):
     """Escape non-ASCII characters as suggested by RFC 3986"""
     if sys.version_info < (3, 0) and isinstance(s, unicode):
         s = s.encode('utf-8')
-    return compat_urllib_parse.quote(s, "%/;:@&=+$,!~*'()?#[]")
+    return compat_urllib_parse.quote(s, b"%/;:@&=+$,!~*'()?#[]")
 
 
 def escape_url(url):
@@ -1636,15 +1314,6 @@ def parse_xml(s):
     return tree
 
 
-if sys.version_info < (3, 0) and sys.platform == 'win32':
-    def compat_getpass(prompt, *args, **kwargs):
-        if isinstance(prompt, compat_str):
-            prompt = prompt.encode(preferredencoding())
-        return getpass.getpass(prompt, *args, **kwargs)
-else:
-    compat_getpass = getpass.getpass
-
-
 US_RATINGS = {
     'G': 0,
     'PG': 10,
@@ -1702,18 +1371,6 @@ def qualities(quality_ids):
 
 DEFAULT_OUTTMPL = '%(title)s-%(id)s.%(ext)s'
 
-try:
-    subprocess_check_output = subprocess.check_output
-except AttributeError:
-    def subprocess_check_output(*args, **kwargs):
-        assert 'input' not in kwargs
-        p = subprocess.Popen(*args, stdout=subprocess.PIPE, **kwargs)
-        output, _ = p.communicate()
-        ret = p.poll()
-        if ret:
-            raise subprocess.CalledProcessError(ret, p.args, output=output)
-        return output
-
 
 def limit_length(s, length):
     """ Add ellipses to overly long strings """

youtube_dl/version.py

@@ -1,2 +1,2 @@
 
-__version__ = '2014.11.02.1'
+__version__ = '2014.11.13.2'