release 2014.11.26

Lots of sites do have this meta tag, so just add it to the example.

AUTHORS

@@ -82,3 +82,9 @@ Xavier Beynon
 Gabriel Schubiner
 xantares
 Jan Matějka
+Mauroy Sébastien
+William Sewell
+Dao Hoang Son
+Oskar Jauch
+Matthew Rayfield
+t0mm0

README.md

@@ -492,14 +492,15 @@ If you want to add support for a new site, you can follow this quick list (assum
 
         def _real_extract(self, url):
             video_id = self._match_id(url)
+            webpage = self._download_webpage(url, video_id)
 
             # TODO more code goes here, for example ...
-            webpage = self._download_webpage(url, video_id)
             title = self._html_search_regex(r'<h1>(.*?)</h1>', webpage, 'title')
 
             return {
                 'id': video_id,
                 'title': title,
+                'description': self._og_search_description(webpage),
                 # TODO more properties (see youtube_dl/extractor/common.py)
             }
     ```

devscripts/bash-completion.py

@@ -9,6 +9,7 @@ import youtube_dl
 BASH_COMPLETION_FILE = "youtube-dl.bash-completion"
 BASH_COMPLETION_TEMPLATE = "devscripts/bash-completion.in"
 
+
 def build_completion(opt_parser):
     opts_flag = []
     for group in opt_parser.option_groups:

devscripts/buildserver.py

@@ -233,6 +233,7 @@ def rmtree(path):
 
 #==============================================================================
 
+
 class BuildError(Exception):
     def __init__(self, output, code=500):
         self.output = output

devscripts/fish-completion.py

@@ -23,13 +23,13 @@ EXTRA_ARGS = {
     'batch-file': ['--require-parameter'],
 }
 
+
 def build_completion(opt_parser):
     commands = []
 
     for group in opt_parser.option_groups:
         for option in group.option_list:
             long_option = option.get_opt_string().strip('-')
-            help_msg = shell_quote([option.help])
             complete_cmd = ['complete', '--command', 'youtube-dl', '--long-option', long_option]
             if option._short_opts:
                 complete_cmd += ['--short-option', option._short_opts[0].strip('-')]

devscripts/gh-pages/generate-download.py

@@ -1,8 +1,5 @@
 #!/usr/bin/env python3
 import hashlib
-import shutil
-import subprocess
-import tempfile
 import urllib.request
 import json
 

devscripts/gh-pages/update-feed.py

@@ -73,4 +73,3 @@ atom_template = atom_template.replace('@ENTRIES@', entries_str)
 
 with io.open('update/releases.atom', 'w', encoding='utf-8') as atom_file:
     atom_file.write(atom_template)
-

devscripts/gh-pages/update-sites.py

@@ -9,6 +9,7 @@ sys.path.append(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(
 
 import youtube_dl
 
+
 def main():
     with open('supportedsites.html.in', 'r', encoding='utf-8') as tmplf:
         template = tmplf.read()
@@ -21,7 +22,7 @@ def main():
             continue
         elif ie_desc is not None:
             ie_html += ': {}'.format(ie.IE_DESC)
-        if ie.working() == False:
+        if not ie.working():
             ie_html += ' (Currently broken)'
         ie_htmls.append('<li>{}</li>'.format(ie_html))
 

devscripts/transition_helper.py

@@ -1,40 +0,0 @@
-#!/usr/bin/env python
-
-import sys, os
-
-try:
-    import urllib.request as compat_urllib_request
-except ImportError: # Python 2
-    import urllib2 as compat_urllib_request
-
-sys.stderr.write(u'Hi! We changed distribution method and now youtube-dl needs to update itself one more time.\n')
-sys.stderr.write(u'This will only happen once. Simply press enter to go on. Sorry for the trouble!\n')
-sys.stderr.write(u'The new location of the binaries is https://github.com/rg3/youtube-dl/downloads, not the git repository.\n\n')
-
-try:
-	raw_input()
-except NameError: # Python 3
-	input()
-
-filename = sys.argv[0]
-
-API_URL = "https://api.github.com/repos/rg3/youtube-dl/downloads"
-BIN_URL = "https://github.com/downloads/rg3/youtube-dl/youtube-dl"
-
-if not os.access(filename, os.W_OK):
-    sys.exit('ERROR: no write permissions on %s' % filename)
-
-try:
-    urlh = compat_urllib_request.urlopen(BIN_URL)
-    newcontent = urlh.read()
-    urlh.close()
-except (IOError, OSError) as err:
-    sys.exit('ERROR: unable to download latest version')
-
-try:
-    with open(filename, 'wb') as outf:
-        outf.write(newcontent)
-except (IOError, OSError) as err:
-    sys.exit('ERROR: unable to overwrite current version')
-
-sys.stderr.write(u'Done! Now you can run youtube-dl.\n')

devscripts/transition_helper_exe/setup.py

@@ -1,12 +0,0 @@
-from distutils.core import setup
-import py2exe
-
-py2exe_options = {
-    "bundle_files": 1,
-    "compressed": 1,
-    "optimize": 2,
-    "dist_dir": '.',
-    "dll_excludes": ['w9xpopen.exe']
-}
-
-setup(console=['youtube-dl.py'], options={ "py2exe": py2exe_options }, zipfile=None)

devscripts/transition_helper_exe/youtube-dl.py

@@ -1,102 +0,0 @@
-#!/usr/bin/env python
-
-import sys, os
-import urllib2
-import json, hashlib
-
-def rsa_verify(message, signature, key):
-    from struct import pack
-    from hashlib import sha256
-    from sys import version_info
-    def b(x):
-        if version_info[0] == 2: return x
-        else: return x.encode('latin1')
-    assert(type(message) == type(b('')))
-    block_size = 0
-    n = key[0]
-    while n:
-        block_size += 1
-        n >>= 8
-    signature = pow(int(signature, 16), key[1], key[0])
-    raw_bytes = []
-    while signature:
-        raw_bytes.insert(0, pack("B", signature & 0xFF))
-        signature >>= 8
-    signature = (block_size - len(raw_bytes)) * b('\x00') + b('').join(raw_bytes)
-    if signature[0:2] != b('\x00\x01'): return False
-    signature = signature[2:]
-    if not b('\x00') in signature: return False
-    signature = signature[signature.index(b('\x00'))+1:]
-    if not signature.startswith(b('\x30\x31\x30\x0D\x06\x09\x60\x86\x48\x01\x65\x03\x04\x02\x01\x05\x00\x04\x20')): return False
-    signature = signature[19:]
-    if signature != sha256(message).digest(): return False
-    return True
-
-sys.stderr.write(u'Hi! We changed distribution method and now youtube-dl needs to update itself one more time.\n')
-sys.stderr.write(u'This will only happen once. Simply press enter to go on. Sorry for the trouble!\n')
-sys.stderr.write(u'From now on, get the binaries from http://rg3.github.com/youtube-dl/download.html, not from the git repository.\n\n')
-
-raw_input()
-
-filename = sys.argv[0]
-
-UPDATE_URL = "http://rg3.github.io/youtube-dl/update/"
-VERSION_URL = UPDATE_URL + 'LATEST_VERSION'
-JSON_URL = UPDATE_URL + 'versions.json'
-UPDATES_RSA_KEY = (0x9d60ee4d8f805312fdb15a62f87b95bd66177b91df176765d13514a0f1754bcd2057295c5b6f1d35daa6742c3ffc9a82d3e118861c207995a8031e151d863c9927e304576bc80692bc8e094896fcf11b66f3e29e04e3a71e9a11558558acea1840aec37fc396fb6b65dc81a1c4144e03bd1c011de62e3f1357b327d08426fe93, 65537)
-
-if not os.access(filename, os.W_OK):
-    sys.exit('ERROR: no write permissions on %s' % filename)
-
-exe = os.path.abspath(filename)
-directory = os.path.dirname(exe)
-if not os.access(directory, os.W_OK):
-    sys.exit('ERROR: no write permissions on %s' % directory)
-
-try:
-    versions_info = urllib2.urlopen(JSON_URL).read().decode('utf-8')
-    versions_info = json.loads(versions_info)
-except:
-    sys.exit(u'ERROR: can\'t obtain versions info. Please try again later.')
-if not 'signature' in versions_info:
-    sys.exit(u'ERROR: the versions file is not signed or corrupted. Aborting.')
-signature = versions_info['signature']
-del versions_info['signature']
-if not rsa_verify(json.dumps(versions_info, sort_keys=True), signature, UPDATES_RSA_KEY):
-    sys.exit(u'ERROR: the versions file signature is invalid. Aborting.')
-
-version = versions_info['versions'][versions_info['latest']]
-
-try:
-    urlh = urllib2.urlopen(version['exe'][0])
-    newcontent = urlh.read()
-    urlh.close()
-except (IOError, OSError) as err:
-    sys.exit('ERROR: unable to download latest version')
-
-newcontent_hash = hashlib.sha256(newcontent).hexdigest()
-if newcontent_hash != version['exe'][1]:
-    sys.exit(u'ERROR: the downloaded file hash does not match. Aborting.')
-
-try:
-    with open(exe + '.new', 'wb') as outf:
-        outf.write(newcontent)
-except (IOError, OSError) as err:
-    sys.exit(u'ERROR: unable to write the new version')
-
-try:
-    bat = os.path.join(directory, 'youtube-dl-updater.bat')
-    b = open(bat, 'w')
-    b.write("""
-echo Updating youtube-dl...
-ping 127.0.0.1 -n 5 -w 1000 > NUL
-move /Y "%s.new" "%s"
-del "%s"
-    \n""" %(exe, exe, bat))
-    b.close()
-
-    os.startfile(bat)
-except (IOError, OSError) as err:
-    sys.exit('ERROR: unable to overwrite current version')
-
-sys.stderr.write(u'Done! Now you can run youtube-dl.\n')

setup.py

@@ -4,7 +4,6 @@
 from __future__ import print_function
 
 import os.path
-import pkg_resources
 import warnings
 import sys
 

test/helper.py

@@ -72,8 +72,10 @@ class FakeYDL(YoutubeDL):
     def expect_warning(self, regex):
         # Silence an expected warning matching a regex
         old_report_warning = self.report_warning
+
         def report_warning(self, message):
-            if re.match(regex, message): return
+            if re.match(regex, message):
+                return
             old_report_warning(message)
         self.report_warning = types.MethodType(report_warning, self)
 

test/test_YoutubeDL.py

@@ -266,6 +266,7 @@ class TestFormatSelection(unittest.TestCase):
             'ext': 'mp4',
             'width': None,
         }
+
         def fname(templ):
             ydl = YoutubeDL({'outtmpl': templ})
             return ydl.prepare_filename(info)

test/test_download.py

@@ -40,18 +40,22 @@ from youtube_dl.extractor import get_info_extractor
 
 RETRIES = 3
 
+
 class YoutubeDL(youtube_dl.YoutubeDL):
     def __init__(self, *args, **kwargs):
         self.to_stderr = self.to_screen
         self.processed_info_dicts = []
         super(YoutubeDL, self).__init__(*args, **kwargs)
+
     def report_warning(self, message):
         # Don't accept warnings during tests
         raise ExtractorError(message)
+
     def process_info(self, info_dict):
         self.processed_info_dicts.append(info_dict)
         return super(YoutubeDL, self).process_info(info_dict)
 
+
 def _file_md5(fn):
     with open(fn, 'rb') as f:
         return hashlib.md5(f.read()).hexdigest()
@@ -61,10 +65,13 @@ defs = gettestcases()
 
 class TestDownload(unittest.TestCase):
     maxDiff = None
+
     def setUp(self):
         self.defs = defs
 
-### Dynamically generate tests
+# Dynamically generate tests
+
+
 def generator(test_case):
 
     def test_template(self):
@@ -101,6 +108,7 @@ def generator(test_case):
         ydl = YoutubeDL(params, auto_init=False)
         ydl.add_default_info_extractors()
         finished_hook_called = set()
+
         def _hook(status):
             if status['status'] == 'finished':
                 finished_hook_called.add(status['filename'])
@@ -111,6 +119,7 @@ def generator(test_case):
             return tc.get('file') or ydl.prepare_filename(tc.get('info_dict', {}))
 
         res_dict = None
+
         def try_rm_tcs_files(tcs=None):
             if tcs is None:
                 tcs = test_cases
@@ -206,7 +215,7 @@ def generator(test_case):
 
     return test_template
 
-### And add them to TestDownload
+# And add them to TestDownload
 for n, test_case in enumerate(defs):
     test_method = generator(test_case)
     tname = 'test_' + str(test_case['name'])

test/test_subtitles.py

@@ -23,6 +23,7 @@ from youtube_dl.extractor import (
 class BaseTestSubtitles(unittest.TestCase):
     url = None
     IE = None
+
     def setUp(self):
         self.DL = FakeYDL()
         self.ie = self.IE(self.DL)

test/test_utils.py

@@ -45,8 +45,9 @@ from youtube_dl.utils import (
     escape_rfc3986,
     escape_url,
     js_to_json,
-    get_filesystem_encoding,
     intlist_to_bytes,
+    args_to_str,
+    parse_filesize,
 )
 
 
@@ -361,5 +362,20 @@ class TestUtil(unittest.TestCase):
             intlist_to_bytes([0, 1, 127, 128, 255]),
             b'\x00\x01\x7f\x80\xff')
 
+    def test_args_to_str(self):
+        self.assertEqual(
+            args_to_str(['foo', 'ba/r', '-baz', '2 be', '']),
+            'foo ba/r -baz \'2 be\' \'\''
+        )
+
+    def test_parse_filesize(self):
+        self.assertEqual(parse_filesize(None), None)
+        self.assertEqual(parse_filesize(''), None)
+        self.assertEqual(parse_filesize('91 B'), 91)
+        self.assertEqual(parse_filesize('foobar'), None)
+        self.assertEqual(parse_filesize('2 MiB'), 2097152)
+        self.assertEqual(parse_filesize('5 GB'), 5000000000)
+        self.assertEqual(parse_filesize('1.2Tb'), 1200000000000)
+
 if __name__ == '__main__':
     unittest.main()

test/test_write_annotations.py

@@ -31,17 +31,16 @@ params = get_params({
 })
 
 
-
 TEST_ID = 'gr51aVj-mLg'
 ANNOTATIONS_FILE = TEST_ID + '.flv.annotations.xml'
 EXPECTED_ANNOTATIONS = ['Speech bubble', 'Note', 'Title', 'Spotlight', 'Label']
 
+
 class TestAnnotations(unittest.TestCase):
     def setUp(self):
         # Clear old files
         self.tearDown()
 
-
     def test_info_json(self):
         expected = list(EXPECTED_ANNOTATIONS)  # Two annotations could have the same text.
         ie = youtube_dl.extractor.YoutubeIE()
@@ -71,7 +70,6 @@ class TestAnnotations(unittest.TestCase):
         # We should have seen (and removed) all the expected annotation texts.
         self.assertEqual(len(expected), 0, 'Not all expected annotations were found.')
 
-
     def tearDown(self):
         try_rm(ANNOTATIONS_FILE)
 

test/test_youtube_lists.py

@@ -12,10 +12,6 @@ from test.helper import FakeYDL
 from youtube_dl.extractor import (
     YoutubePlaylistIE,
     YoutubeIE,
-    YoutubeChannelIE,
-    YoutubeShowIE,
-    YoutubeTopListIE,
-    YoutubeSearchURLIE,
 )
 
 

youtube_dl/YoutubeDL.py

@@ -60,6 +60,7 @@ from .utils import (
     write_string,
     YoutubeDLHandler,
     prepend_extension,
+    args_to_str,
 )
 from .cache import Cache
 from .extractor import get_info_extractor, gen_extractors
@@ -253,6 +254,22 @@ class YoutubeDL(object):
             self.print_debug_header()
             self.add_default_info_extractors()
 
+    def warn_if_short_id(self, argv):
+        # short YouTube ID starting with dash?
+        idxs = [
+            i for i, a in enumerate(argv)
+            if re.match(r'^-[0-9A-Za-z_-]{10}$', a)]
+        if idxs:
+            correct_argv = (
+                ['youtube-dl'] +
+                [a for i, a in enumerate(argv) if i not in idxs] +
+                ['--'] + [argv[i] for i in idxs]
+            )
+            self.report_warning(
+                'Long argument string detected. '
+                'Use -- to separate parameters and URLs, like this:\n%s\n' %
+                args_to_str(correct_argv))
+
     def add_info_extractor(self, ie):
         """Add an InfoExtractor object to the end of the list."""
         self._ies.append(ie)
@@ -624,7 +641,7 @@ class YoutubeDL(object):
 
             return self.process_ie_result(
                 new_result, download=download, extra_info=extra_info)
-        elif result_type == 'playlist':
+        elif result_type == 'playlist' or result_type == 'multi_video':
             # We process each entry in the playlist
             playlist = ie_result.get('title', None) or ie_result.get('id', None)
             self.to_screen('[download] Downloading playlist: %s' % playlist)
@@ -679,14 +696,20 @@ class YoutubeDL(object):
             ie_result['entries'] = playlist_results
             return ie_result
         elif result_type == 'compat_list':
+            self.report_warning(
+                'Extractor %s returned a compat_list result. '
+                'It needs to be updated.' % ie_result.get('extractor'))
+
             def _fixup(r):
-                self.add_extra_info(r,
+                self.add_extra_info(
+                    r,
                     {
                         'extractor': ie_result['extractor'],
                         'webpage_url': ie_result['webpage_url'],
                         'webpage_url_basename': url_basename(ie_result['webpage_url']),
                         'extractor_key': ie_result['extractor_key'],
-                    })
+                    }
+                )
                 return r
             ie_result['entries'] = [
                 self.process_ie_result(_fixup(r), download, extra_info)

youtube_dl/__init__.py

@@ -128,7 +128,6 @@ def _real_main(argv=None):
             compat_print(desc)
         sys.exit(0)
 
-
     # Conflicting, missing and erroneous options
     if opts.usenetrc and (opts.username is not None or opts.password is not None):
         parser.error('using .netrc conflicts with giving username/password')
@@ -190,7 +189,7 @@ def _real_main(argv=None):
 
     # --all-sub automatically sets --write-sub if --write-auto-sub is not given
     # this was the old behaviour if only --all-sub was given.
-    if opts.allsubtitles and (opts.writeautomaticsub == False):
+    if opts.allsubtitles and not opts.writeautomaticsub:
         opts.writesubtitles = True
 
     if sys.version_info < (3,):
@@ -317,7 +316,6 @@ def _real_main(argv=None):
                 ydl.add_post_processor(FFmpegAudioFixPP())
             ydl.add_post_processor(AtomicParsleyPP())
 
-
         # Please keep ExecAfterDownload towards the bottom as it allows the user to modify the final file in any way.
         # So if the user is able to remove the file before your postprocessor runs it might cause a few problems.
         if opts.exec_cmd:
@@ -334,11 +332,12 @@ def _real_main(argv=None):
 
         # Maybe do nothing
         if (len(all_urls) < 1) and (opts.load_info_filename is None):
-            if not (opts.update_self or opts.rm_cachedir):
-                parser.error('you must provide at least one URL')
-            else:
+            if opts.update_self or opts.rm_cachedir:
                 sys.exit()
 
+            ydl.warn_if_short_id(sys.argv[1:] if argv is None else argv)
+            parser.error('you must provide at least one URL')
+
         try:
             if opts.load_info_filename is not None:
                 retcode = ydl.download_with_info_file(opts.load_info_filename)

youtube_dl/aes.py

@@ -7,6 +7,7 @@ from .utils import bytes_to_intlist, intlist_to_bytes
 
 BLOCK_SIZE_BYTES = 16
 
+
 def aes_ctr_decrypt(data, key, counter):
     """
     Decrypt with aes in counter mode
@@ -32,6 +33,7 @@ def aes_ctr_decrypt(data, key, counter):
 
     return decrypted_data
 
+
 def aes_cbc_decrypt(data, key, iv):
     """
     Decrypt with aes in CBC mode
@@ -57,6 +59,7 @@ def aes_cbc_decrypt(data, key, iv):
 
     return decrypted_data
 
+
 def key_expansion(data):
     """
     Generate key schedule
@@ -91,6 +94,7 @@ def key_expansion(data):
 
     return data
 
+
 def aes_encrypt(data, expanded_key):
     """
     Encrypt one block with aes
@@ -111,6 +115,7 @@ def aes_encrypt(data, expanded_key):
 
     return data
 
+
 def aes_decrypt(data, expanded_key):
     """
     Decrypt one block with aes
@@ -131,6 +136,7 @@ def aes_decrypt(data, expanded_key):
 
     return data
 
+
 def aes_decrypt_text(data, password, key_size_bytes):
     """
     Decrypt text
@@ -157,6 +163,7 @@ def aes_decrypt_text(data, password, key_size_bytes):
 
     class Counter:
         __value = nonce + [0] * (BLOCK_SIZE_BYTES - NONCE_LENGTH_BYTES)
+
         def next_value(self):
             temp = self.__value
             self.__value = inc(self.__value)
@@ -241,15 +248,19 @@ RIJNDAEL_LOG_TABLE = (0x00, 0x00, 0x19, 0x01, 0x32, 0x02, 0x1a, 0xc6, 0x4b, 0xc7
                       0x44, 0x11, 0x92, 0xd9, 0x23, 0x20, 0x2e, 0x89, 0xb4, 0x7c, 0xb8, 0x26, 0x77, 0x99, 0xe3, 0xa5,
                       0x67, 0x4a, 0xed, 0xde, 0xc5, 0x31, 0xfe, 0x18, 0x0d, 0x63, 0x8c, 0x80, 0xc0, 0xf7, 0x70, 0x07)
 
+
 def sub_bytes(data):
     return [SBOX[x] for x in data]
 
+
 def sub_bytes_inv(data):
     return [SBOX_INV[x] for x in data]
 
+
 def rotate(data):
     return data[1:] + [data[0]]
 
+
 def key_schedule_core(data, rcon_iteration):
     data = rotate(data)
     data = sub_bytes(data)
@@ -257,14 +268,17 @@ def key_schedule_core(data, rcon_iteration):
 
     return data
 
+
 def xor(data1, data2):
     return [x ^ y for x, y in zip(data1, data2)]
 
+
 def rijndael_mul(a, b):
     if(a == 0 or b == 0):
         return 0
     return RIJNDAEL_EXP_TABLE[(RIJNDAEL_LOG_TABLE[a] + RIJNDAEL_LOG_TABLE[b]) % 0xFF]
 
+
 def mix_column(data, matrix):
     data_mixed = []
     for row in range(4):
@@ -275,6 +289,7 @@ def mix_column(data, matrix):
         data_mixed.append(mixed)
     return data_mixed
 
+
 def mix_columns(data, matrix=MIX_COLUMN_MATRIX):
     data_mixed = []
     for i in range(4):
@@ -282,9 +297,11 @@ def mix_columns(data, matrix=MIX_COLUMN_MATRIX):
         data_mixed += mix_column(column, matrix)
     return data_mixed
 
+
 def mix_columns_inv(data):
     return mix_columns(data, MIX_COLUMN_MATRIX_INV)
 
+
 def shift_rows(data):
     data_shifted = []
     for column in range(4):
@@ -292,6 +309,7 @@ def shift_rows(data):
             data_shifted.append(data[((column + row) & 0b11) * 4 + row])
     return data_shifted
 
+
 def shift_rows_inv(data):
     data_shifted = []
     for column in range(4):
@@ -299,6 +317,7 @@ def shift_rows_inv(data):
             data_shifted.append(data[((column - row) & 0b11) * 4 + row])
     return data_shifted
 
+
 def inc(data):
     data = data[:]  # copy
     for i in range(len(data) - 1, -1, -1):

youtube_dl/compat.py

@@ -3,6 +3,7 @@ from __future__ import unicode_literals
 import getpass
 import optparse
 import os
+import re
 import subprocess
 import sys
 
@@ -174,12 +175,17 @@ try:
     from shlex import quote as shlex_quote
 except ImportError:  # Python < 3.3
     def shlex_quote(s):
+        if re.match(r'^[-_\w./]+$', s):
+            return s
+        else:
             return "'" + s.replace("'", "'\"'\"'") + "'"
 
 
 def compat_ord(c):
-    if type(c) is int: return c
-    else: return ord(c)
+    if type(c) is int:
+        return c
+    else:
+        return ord(c)
 
 
 if sys.version_info >= (3, 0):
@@ -306,7 +312,7 @@ def workaround_optparse_bug9161():
     og = optparse.OptionGroup(op, 'foo')
     try:
         og.add_option('-t')
-    except TypeError as te:
+    except TypeError:
         real_add_option = optparse.OptionGroup.add_option
 
         def _compat_add_option(self, *args, **kwargs):

youtube_dl/downloader/__init__.py

@@ -30,3 +30,8 @@ def get_suitable_downloader(info_dict):
         return F4mFD
     else:
         return HttpFD
+
+__all__ = [
+    'get_suitable_downloader',
+    'FileDownloader',
+]

youtube_dl/downloader/f4m.py

@@ -225,13 +225,15 @@ class F4mFD(FileDownloader):
         self.to_screen('[download] Downloading f4m manifest')
         manifest = self.ydl.urlopen(man_url).read()
         self.report_destination(filename)
-        http_dl = HttpQuietDownloader(self.ydl,
+        http_dl = HttpQuietDownloader(
+            self.ydl,
             {
                 'continuedl': True,
                 'quiet': True,
                 'noprogress': True,
                 'test': self.params.get('test', False),
-            })
+            }
+        )
 
         doc = etree.fromstring(manifest)
         formats = [(int(f.attrib.get('bitrate', -1)), f) for f in doc.findall(_add_ns('media'))]

youtube_dl/downloader/hls.py

@@ -101,4 +101,3 @@ class NativeHlsFD(FileDownloader):
         })
         self.try_rename(tmpfilename, filename)
         return True
-

youtube_dl/extractor/__init__.py

@@ -32,6 +32,7 @@ from .bilibili import BiliBiliIE
 from .blinkx import BlinkxIE
 from .bliptv import BlipTVIE, BlipTVUserIE
 from .bloomberg import BloombergIE
+from .bpb import BpbIE
 from .br import BRIE
 from .breakcom import BreakIE
 from .brightcove import BrightcoveIE
@@ -115,6 +116,7 @@ from .fktv import (
     FKTVPosteckeIE,
 )
 from .flickr import FlickrIE
+from .folketinget import FolketingetIE
 from .fourtube import FourTubeIE
 from .franceculture import FranceCultureIE
 from .franceinter import FranceInterIE
@@ -371,6 +373,7 @@ from .syfy import SyfyIE
 from .sztvhu import SztvHuIE
 from .tagesschau import TagesschauIE
 from .tapely import TapelyIE
+from .tass import TassIE
 from .teachertube import (
     TeacherTubeIE,
     TeacherTubeUserIE,
@@ -379,6 +382,7 @@ from .teachingchannel import TeachingChannelIE
 from .teamcoco import TeamcocoIE
 from .techtalks import TechTalksIE
 from .ted import TEDIE
+from .telebruxelles import TeleBruxellesIE
 from .telecinco import TelecincoIE
 from .telemb import TeleMBIE
 from .tenplay import TenPlayIE
@@ -390,6 +394,7 @@ from .thesixtyone import TheSixtyOneIE
 from .thisav import ThisAVIE
 from .tinypic import TinyPicIE
 from .tlc import TlcIE, TlcDeIE
+from .tmz import TMZIE
 from .tnaflix import TNAFlixIE
 from .thvideo import (
     THVideoIE,
@@ -403,6 +408,7 @@ from .trutube import TruTubeIE
 from .tube8 import Tube8IE
 from .tudou import TudouIE
 from .tumblr import TumblrIE
+from .tunein import TuneInIE
 from .turbo import TurboIE
 from .tutv import TutvIE
 from .tvigle import TvigleIE
@@ -452,7 +458,10 @@ from .vine import (
     VineUserIE,
 )
 from .viki import VikiIE
-from .vk import VKIE
+from .vk import (
+    VKIE,
+    VKUserVideosIE,
+)
 from .vodlocker import VodlockerIE
 from .vporn import VpornIE
 from .vrt import VRTIE
@@ -476,6 +485,7 @@ from .wrzuta import WrzutaIE
 from .xbef import XBefIE
 from .xboxclips import XboxClipsIE
 from .xhamster import XHamsterIE
+from .xminus import XMinusIE
 from .xnxx import XNXXIE
 from .xvideos import XVideosIE
 from .xtube import XTubeUserIE, XTubeIE
@@ -506,6 +516,10 @@ from .youtube import (
     YoutubeWatchLaterIE,
 )
 from .zdf import ZDFIE
+from .zingmp3 import (
+    ZingMp3SongIE,
+    ZingMp3AlbumIE,
+)
 
 _ALL_CLASSES = [
     klass

youtube_dl/extractor/adultswim.py

@@ -5,6 +5,7 @@ import re
 
 from .common import InfoExtractor
 
+
 class AdultSwimIE(InfoExtractor):
     _VALID_URL = r'https?://video\.adultswim\.com/(?P<path>.+?)(?:\.html)?(?:\?.*)?(?:#.*)?$'
     _TEST = {

youtube_dl/extractor/appletrailers.py

@@ -70,11 +70,13 @@ class AppleTrailersIE(InfoExtractor):
         uploader_id = mobj.group('company')
 
         playlist_url = compat_urlparse.urljoin(url, 'includes/playlists/itunes.inc')
+
         def fix_html(s):
             s = re.sub(r'(?s)<script[^<]*?>.*?</script>', '', s)
             s = re.sub(r'<img ([^<]*?)>', r'<img \1/>', s)
             # The ' in the onClick attributes are not escaped, it couldn't be parsed
             # like: http://trailers.apple.com/trailers/wb/gravity/
+
             def _clean_json(m):
                 return 'iTunes.playURL(%s);' % m.group(1).replace('\'', '&#39;')
             s = re.sub(self._JSON_RE, _clean_json, s)

youtube_dl/extractor/ard.py

@@ -192,4 +192,3 @@ class ARDIE(InfoExtractor):
             'upload_date': upload_date,
             'thumbnail': thumbnail,
         }
-

youtube_dl/extractor/arte.py

@@ -5,7 +5,6 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
-    ExtractorError,
     find_xpath_attr,
     unified_strdate,
     get_element_by_id,

youtube_dl/extractor/bambuser.py

@@ -73,7 +73,8 @@ class BambuserChannelIE(InfoExtractor):
         urls = []
         last_id = ''
         for i in itertools.count(1):
-            req_url = ('http://bambuser.com/xhr-api/index.php?username={user}'
+            req_url = (
+                'http://bambuser.com/xhr-api/index.php?username={user}'
                 '&sort=created&access_mode=0%2C1%2C2&limit={count}'
                 '&method=broadcast&format=json&vid_older_than={last}'
             ).format(user=user, count=self._STEP, last=last_id)

youtube_dl/extractor/bliptv.py

@@ -166,9 +166,17 @@ class BlipTVIE(SubtitlesInfoExtractor):
 
 
 class BlipTVUserIE(InfoExtractor):
-    _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?blip\.tv/)|bliptvuser:)(?!api\.swf)([^/]+)/*$'
+    _VALID_URL = r'(?:(?:https?://(?:\w+\.)?blip\.tv/)|bliptvuser:)(?!api\.swf)([^/]+)/*$'
     _PAGE_SIZE = 12
     IE_NAME = 'blip.tv:user'
+    _TEST = {
+        'url': 'http://blip.tv/actone',
+        'info_dict': {
+            'id': 'actone',
+            'title': 'Act One: The Series',
+        },
+        'playlist_count': 5,
+    }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -179,6 +187,7 @@ class BlipTVUserIE(InfoExtractor):
         page = self._download_webpage(url, username, 'Downloading user page')
         mobj = re.search(r'data-users-id="([^"]+)"', page)
         page_base = page_base % mobj.group(1)
+        title = self._og_search_title(page)
 
         # Download video ids using BlipTV Ajax calls. Result size per
         # query is limited (currently to 12 videos) so we need to query
@@ -215,4 +224,5 @@ class BlipTVUserIE(InfoExtractor):
 
         urls = ['http://blip.tv/%s' % video_id for video_id in video_ids]
         url_entries = [self.url_result(vurl, 'BlipTV') for vurl in urls]
-        return [self.playlist_result(url_entries, playlist_title=username)]
+        return self.playlist_result(
+            url_entries, playlist_title=title, playlist_id=username)

youtube_dl/extractor/bpb.py

@@ -0,0 +1,37 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class BpbIE(InfoExtractor):
+    IE_DESC = 'Bundeszentrale für politische Bildung'
+    _VALID_URL = r'http://www\.bpb\.de/mediathek/(?P<id>[0-9]+)/'
+
+    _TEST = {
+        'url': 'http://www.bpb.de/mediathek/297/joachim-gauck-zu-1989-und-die-erinnerung-an-die-ddr',
+        'md5': '0792086e8e2bfbac9cdf27835d5f2093',
+        'info_dict': {
+            'id': '297',
+            'ext': 'mp4',
+            'title': 'Joachim Gauck zu 1989 und die Erinnerung an die DDR',
+            'description': 'Joachim Gauck, erster Beauftragter für die Stasi-Unterlagen, spricht auf dem Geschichtsforum über die friedliche Revolution 1989 und eine "gewisse Traurigkeit" im Umgang mit der DDR-Vergangenheit.'
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._html_search_regex(
+            r'<h2 class="white">(.*?)</h2>', webpage, 'title')
+        video_url = self._html_search_regex(
+            r'(http://film\.bpb\.de/player/dokument_[0-9]+\.mp4)',
+            webpage, 'video URL')
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': title,
+            'description': self._og_search_description(webpage),
+        }

youtube_dl/extractor/brightcove.py

@@ -111,6 +111,8 @@ class BrightcoveIE(InfoExtractor):
                             lambda m: m.group(1) + '/>', object_str)
         # Fix up some stupid XML, see https://github.com/rg3/youtube-dl/issues/1608
         object_str = object_str.replace('<--', '<!--')
+        # remove namespace to simplify extraction
+        object_str = re.sub(r'(<object[^>]*)(xmlns=".*?")', r'\1', object_str)
         object_str = fix_xml_ampersands(object_str)
 
         object_doc = xml.etree.ElementTree.fromstring(object_str.encode('utf-8'))
@@ -219,7 +221,7 @@ class BrightcoveIE(InfoExtractor):
         webpage = self._download_webpage(req, video_id)
 
         error_msg = self._html_search_regex(
-            r"<h1>We're sorry.</h1>\s*<p>(.*?)</p>", webpage,
+            r"<h1>We're sorry.</h1>([\s\n]*<p>.*?</p>)+", webpage,
             'error message', default=None)
         if error_msg is not None:
             raise ExtractorError(

youtube_dl/extractor/channel9.py

@@ -5,6 +5,7 @@ import re
 from .common import InfoExtractor
 from ..utils import ExtractorError
 
+
 class Channel9IE(InfoExtractor):
     '''
     Common extractor for channel9.msdn.com.
@@ -187,7 +188,8 @@ class Channel9IE(InfoExtractor):
         view_count = self._extract_view_count(html)
         comment_count = self._extract_comment_count(html)
 
-        common = {'_type': 'video',
+        common = {
+            '_type': 'video',
             'id': content_path,
             'description': description,
             'thumbnail': thumbnail,

youtube_dl/extractor/clipsyndicate.py

@@ -39,6 +39,7 @@ class ClipsyndicateIE(InfoExtractor):
             transform_source=fix_xml_ampersands)
 
         track_doc = pdoc.find('trackList/track')
+
         def find_param(name):
             node = find_xpath_attr(track_doc, './/param', 'name', name)
             if node is not None:

youtube_dl/extractor/cnn.py

@@ -25,8 +25,7 @@ class CNNIE(InfoExtractor):
             'duration': 135,
             'upload_date': '20130609',
         },
-    },
-    {
+    }, {
         "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",
         "md5": "b5cc60c60a3477d185af8f19a2a26f4e",
         "info_dict": {

youtube_dl/extractor/collegehumor.py

@@ -10,7 +10,8 @@ from ..utils import int_or_none
 class CollegeHumorIE(InfoExtractor):
     _VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/(video|embed|e)/(?P<videoid>[0-9]+)/?(?P<shorttitle>.*)$'
 
-    _TESTS = [{
+    _TESTS = [
+        {
             'url': 'http://www.collegehumor.com/video/6902724/comic-con-cosplay-catastrophe',
             'md5': 'dcc0f5c1c8be98dc33889a191f4c26bd',
             'info_dict': {
@@ -21,8 +22,7 @@ class CollegeHumorIE(InfoExtractor):
                 'age_limit': 13,
                 'duration': 187,
             },
-    },
-    {
+        }, {
             'url': 'http://www.collegehumor.com/video/3505939/font-conference',
             'md5': '72fa701d8ef38664a4dbb9e2ab721816',
             'info_dict': {
@@ -33,9 +33,8 @@ class CollegeHumorIE(InfoExtractor):
                 'age_limit': 10,
                 'duration': 179,
             },
-    },
+        }, {
             # embedded youtube video
-    {
             'url': 'http://www.collegehumor.com/embed/6950306',
             'info_dict': {
                 'id': 'Z-bao9fg6Yc',

youtube_dl/extractor/comedycentral.py

@@ -2,7 +2,6 @@ from __future__ import unicode_literals
 
 import re
 
-from .common import InfoExtractor
 from .mtv import MTVServicesInfoExtractor
 from ..utils import (
     compat_str,
@@ -110,9 +109,7 @@ class ComedyCentralShowsIE(MTVServicesInfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url, re.VERBOSE)
-        if mobj is None:
-            raise ExtractorError('Invalid URL: %s' % url)
+        mobj = re.match(self._VALID_URL, url)
 
         if mobj.group('shortname'):
             if mobj.group('shortname') in ('tds', 'thedailyshow'):

youtube_dl/extractor/common.py

@@ -43,7 +43,11 @@ class InfoExtractor(object):
     information possibly downloading the video to the file system, among
     other possible outcomes.
 
-    The dictionaries must include the following fields:
+    The type field determines the the type of the result.
+    By far the most common value (and the default if _type is missing) is
+    "video", which indicates a single video.
+
+    For a video, the dictionaries must include the following fields:
 
     id:             Video identifier.
     title:          Video title, unescaped.
@@ -151,6 +155,38 @@ class InfoExtractor(object):
 
     Unless mentioned otherwise, None is equivalent to absence of information.
 
+
+    _type "playlist" indicates multiple videos.
+    There must be a key "entries", which is a list or a PagedList object, each
+    element of which is a valid dictionary under this specfication.
+
+    Additionally, playlists can have "title" and "id" attributes with the same
+    semantics as videos (see above).
+
+
+    _type "multi_video" indicates that there are multiple videos that
+    form a single show, for examples multiple acts of an opera or TV episode.
+    It must have an entries key like a playlist and contain all the keys
+    required for a video at the same time.
+
+
+    _type "url" indicates that the video must be extracted from another
+    location, possibly by a different extractor. Its only required key is:
+    "url" - the next URL to extract.
+
+    Additionally, it may have properties believed to be identical to the
+    resolved entity, for example "title" if the title of the referred video is
+    known ahead of time.
+
+
+    _type "url_transparent" entities have the same specification as "url", but
+    indicate that the given additional information is more precise than the one
+    associated with the resolved URL.
+    This is useful when a site employs a video service that hosts the video and
+    its technical metadata, but that video service does not embed a useful
+    title, description etc.
+
+
     Subclasses of this one should re-define the _real_initialize() and
     _real_extract() methods and define a _VALID_URL regexp.
     Probably, they should also be added to the list of extractors.
@@ -260,9 +296,11 @@ class InfoExtractor(object):
         content = self._webpage_read_content(urlh, url_or_request, video_id, note, errnote, fatal)
         return (content, urlh)
 
-    def _webpage_read_content(self, urlh, url_or_request, video_id, note=None, errnote=None, fatal=True):
+    def _webpage_read_content(self, urlh, url_or_request, video_id, note=None, errnote=None, fatal=True, prefix=None):
         content_type = urlh.headers.get('Content-Type', '')
         webpage_bytes = urlh.read()
+        if prefix is not None:
+            webpage_bytes = prefix + webpage_bytes
         m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type)
         if m:
             encoding = m.group(1)
@@ -398,6 +436,7 @@ class InfoExtractor(object):
         if video_id is not None:
             video_info['id'] = video_id
         return video_info
+
     @staticmethod
     def playlist_result(entries, playlist_id=None, playlist_title=None):
         """Returns a playlist"""

youtube_dl/extractor/crunchyroll.py

@@ -69,11 +69,9 @@ class CrunchyrollIE(SubtitlesInfoExtractor):
         login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
         self._download_webpage(login_request, None, False, 'Wrong login info')
 
-
     def _real_initialize(self):
         self._login()
 
-
     def _decrypt_subtitles(self, data, iv, id):
         data = bytes_to_intlist(data)
         iv = bytes_to_intlist(iv)
@@ -99,8 +97,10 @@ class CrunchyrollIE(SubtitlesInfoExtractor):
             return shaHash + [0] * 12
 
         key = obfuscate_key(id)
+
         class Counter:
             __value = iv
+
             def next_value(self):
                 temp = self.__value
                 self.__value = inc(self.__value)
@@ -248,7 +248,8 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
         subtitles = {}
         sub_format = self._downloader.params.get('subtitlesformat', 'srt')
         for sub_id, sub_name in re.findall(r'\?ssid=([0-9]+)" title="([^"]+)', webpage):
-            sub_page = self._download_webpage('http://www.crunchyroll.com/xml/?req=RpcApiSubtitle_GetXml&subtitle_script_id='+sub_id,\
+            sub_page = self._download_webpage(
+                'http://www.crunchyroll.com/xml/?req=RpcApiSubtitle_GetXml&subtitle_script_id=' + sub_id,
                 video_id, note='Downloading subtitles for ' + sub_name)
             id = self._search_regex(r'id=\'([0-9]+)', sub_page, 'subtitle_id', fatal=False)
             iv = self._search_regex(r'<iv>([^<]+)', sub_page, 'subtitle_iv', fatal=False)

youtube_dl/extractor/dailymotion.py

@@ -18,6 +18,7 @@ from ..utils import (
     unescapeHTML,
 )
 
+
 class DailymotionBaseInfoExtractor(InfoExtractor):
     @staticmethod
     def _build_request(url):
@@ -27,6 +28,7 @@ class DailymotionBaseInfoExtractor(InfoExtractor):
         request.add_header('Cookie', 'ff=off')
         return request
 
+
 class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
     """Information Extractor for Dailymotion"""
 

youtube_dl/extractor/dropbox.py

@@ -11,15 +11,15 @@ from ..utils import url_basename
 
 class DropboxIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?dropbox[.]com/sh?/(?P<id>[a-zA-Z0-9]{15})/.*'
-    _TESTS = [{
+    _TESTS = [
+        {
             'url': 'https://www.dropbox.com/s/nelirfsxnmcfbfh/youtube-dl%20test%20video%20%27%C3%A4%22BaW_jenozKc.mp4?dl=0',
             'info_dict': {
                 'id': 'nelirfsxnmcfbfh',
                 'ext': 'mp4',
                 'title': 'youtube-dl test video \'ä"BaW_jenozKc'
             }
-    },
-    {
+        }, {
             'url': 'https://www.dropbox.com/sh/662glsejgzoj9sr/AAByil3FGH9KFNZ13e08eSa1a/Pregame%20Ceremony%20Program%20PA%2020140518.m4v',
             'only_matching': True,
         },

youtube_dl/extractor/folketinget.py

@@ -0,0 +1,75 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import compat_parse_qs
+from ..utils import (
+    int_or_none,
+    parse_duration,
+    parse_iso8601,
+    xpath_text,
+)
+
+
+class FolketingetIE(InfoExtractor):
+    IE_DESC = 'Folketinget (ft.dk; Danish parliament)'
+    _VALID_URL = r'https?://(?:www\.)?ft\.dk/webtv/video/[^?#]*?\.(?P<id>[0-9]+)\.aspx'
+    _TEST = {
+        'url': 'http://www.ft.dk/webtv/video/20141/eru/td.1165642.aspx?as=1#player',
+        'info_dict': {
+            'id': '1165642',
+            'ext': 'mp4',
+            'title': 'Åbent samråd i Erhvervsudvalget',
+            'description': 'Åbent samråd med erhvervs- og vækstministeren om regeringens politik på teleområdet',
+            'view_count': int,
+            'width': 768,
+            'height': 432,
+            'tbr': 928000,
+            'timestamp': 1416493800,
+            'upload_date': '20141120',
+            'duration': 3960,
+        },
+        'params': {
+            'skip_download': 'rtmpdump required',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._og_search_title(webpage)
+        description = self._html_search_regex(
+            r'(?s)<div class="video-item-agenda"[^>]*>(.*?)<',
+            webpage, 'description', fatal=False)
+
+        player_params = compat_parse_qs(self._search_regex(
+            r'<embed src="http://ft\.arkena\.tv/flash/ftplayer\.swf\?([^"]+)"',
+            webpage, 'player params'))
+        xml_url = player_params['xml'][0]
+        doc = self._download_xml(xml_url, video_id)
+
+        timestamp = parse_iso8601(xpath_text(doc, './/date'))
+        duration = parse_duration(xpath_text(doc, './/duration'))
+        width = int_or_none(xpath_text(doc, './/width'))
+        height = int_or_none(xpath_text(doc, './/height'))
+        view_count = int_or_none(xpath_text(doc, './/views'))
+
+        formats = [{
+            'format_id': n.attrib['bitrate'],
+            'url': xpath_text(n, './url', fatal=True),
+            'tbr': int_or_none(n.attrib['bitrate']),
+        } for n in doc.findall('.//streams/stream')]
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'description': description,
+            'timestamp': timestamp,
+            'width': width,
+            'height': height,
+            'duration': duration,
+            'view_count': view_count,
+        }

youtube_dl/extractor/francetv.py

@@ -26,6 +26,21 @@ class FranceTVBaseInfoExtractor(InfoExtractor):
         if info.get('status') == 'NOK':
             raise ExtractorError(
                 '%s returned error: %s' % (self.IE_NAME, info['message']), expected=True)
+        allowed_countries = info['videos'][0].get('geoblocage')
+        if allowed_countries:
+            georestricted = True
+            geo_info = self._download_json(
+                'http://geo.francetv.fr/ws/edgescape.json', video_id,
+                'Downloading geo restriction info')
+            country = geo_info['reponse']['geo_info']['country_code']
+            if country not in allowed_countries:
+                raise ExtractorError(
+                    'The video is not available from your location',
+                    expected=True)
+        else:
+            georestricted = False
+
+
 
         formats = []
         for video in info['videos']:
@@ -36,6 +51,10 @@ class FranceTVBaseInfoExtractor(InfoExtractor):
                 continue
             format_id = video['format']
             if video_url.endswith('.f4m'):
+                if georestricted:
+                    # See https://github.com/rg3/youtube-dl/issues/3963
+                    # m3u8 urls work fine
+                    continue
                 video_url_parsed = compat_urllib_parse_urlparse(video_url)
                 f4m_url = self._download_webpage(
                     'http://hdfauth.francetv.fr/esi/urltokengen2.html?url=%s' % video_url_parsed.path,

youtube_dl/extractor/generic.py

@@ -445,6 +445,30 @@ class GenericIE(InfoExtractor):
                 'title': 'Rosetta #CometLanding webcast HL 10',
             }
         },
+        # LazyYT
+        {
+            'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
+            'info_dict': {
+                'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
+            },
+            'playlist_mincount': 2,
+        },
+        # Direct link with incorrect MIME type
+        {
+            'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
+            'md5': '4ccbebe5f36706d85221f204d7eb5913',
+            'info_dict': {
+                'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
+                'id': '5_Lennart_Poettering_-_Systemd',
+                'ext': 'webm',
+                'title': '5_Lennart_Poettering_-_Systemd',
+                'upload_date': '20141120',
+            },
+            'expected_warnings': [
+                'URL could be a direct video link, returning it as such.'
+            ]
+        }
+
     ]
 
     def report_following_redirect(self, new_url):
@@ -537,9 +561,9 @@ class GenericIE(InfoExtractor):
 
             if default_search in ('error', 'fixup_error'):
                 raise ExtractorError(
-                    ('%r is not a valid URL. '
+                    '%r is not a valid URL. '
                     'Set --default-search "ytsearch" (or run  youtube-dl "ytsearch:%s" ) to search YouTube'
-                    ) % (url, url), expected=True)
+                    % (url, url), expected=True)
             else:
                 if ':' not in default_search:
                     default_search += ':'
@@ -598,10 +622,28 @@ class GenericIE(InfoExtractor):
         if not self._downloader.params.get('test', False) and not is_intentional:
             self._downloader.report_warning('Falling back on generic information extractor.')
 
-        if full_response:
-            webpage = self._webpage_read_content(full_response, url, video_id)
-        else:
-            webpage = self._download_webpage(url, video_id)
+        if not full_response:
+            full_response = self._request_webpage(url, video_id)
+
+        # Maybe it's a direct link to a video?
+        # Be careful not to download the whole thing!
+        first_bytes = full_response.read(512)
+        if not re.match(r'^\s*<', first_bytes.decode('utf-8', 'replace')):
+            self._downloader.report_warning(
+                'URL could be a direct video link, returning it as such.')
+            upload_date = unified_strdate(
+                head_response.headers.get('Last-Modified'))
+            return {
+                'id': video_id,
+                'title': os.path.splitext(url_basename(url))[0],
+                'direct': True,
+                'url': url,
+                'upload_date': upload_date,
+            }
+
+        webpage = self._webpage_read_content(
+            full_response, url, video_id, prefix=first_bytes)
+
         self.report_extraction(video_id)
 
         # Is it an RSS feed?
@@ -702,6 +744,12 @@ class GenericIE(InfoExtractor):
             return _playlist_from_matches(
                 matches, lambda m: unescapeHTML(m[1]))
 
+        # Look for lazyYT YouTube embed
+        matches = re.findall(
+            r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
+        if matches:
+            return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
+
         # Look for embedded Dailymotion player
         matches = re.findall(
             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
@@ -979,7 +1027,7 @@ class GenericIE(InfoExtractor):
                 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
         if not found:
             # HTML5 video
-            found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]*)?\s+src="([^"]+)"', webpage)
+            found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
         if not found:
             found = re.search(
                 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
@@ -1025,4 +1073,3 @@ class GenericIE(InfoExtractor):
                 '_type': 'playlist',
                 'entries': entries,
             }
-

youtube_dl/extractor/goldenmoustache.py

@@ -1,9 +1,7 @@
 from __future__ import unicode_literals
 
-import re
 from .common import InfoExtractor
 from ..utils import (
-    parse_duration,
     int_or_none,
 )
 

youtube_dl/extractor/ign.py

@@ -63,8 +63,10 @@ class IGNIE(InfoExtractor):
                 'id': '078fdd005f6d3c02f63d795faa1b984f',
                 'ext': 'mp4',
                 'title': 'Rewind Theater - Wild Trailer Gamescom 2014',
-                'description': 'Giant skeletons, bloody hunts, and captivating'
-                    ' natural beauty take our breath away.',
+                'description': (
+                    'Giant skeletons, bloody hunts, and captivating'
+                    ' natural beauty take our breath away.'
+                ),
             },
         },
     ]

youtube_dl/extractor/internetvideoarchive.py

@@ -58,9 +58,13 @@ class InternetVideoArchiveIE(InfoExtractor):
         item = info.find('channel/item')
 
         def _bp(p):
-            return xpath_with_ns(p,
-                {'media': 'http://search.yahoo.com/mrss/',
-                'jwplayer': 'http://developer.longtailvideo.com/trac/wiki/FlashFormats'})
+            return xpath_with_ns(
+                p,
+                {
+                    'media': 'http://search.yahoo.com/mrss/',
+                    'jwplayer': 'http://developer.longtailvideo.com/trac/wiki/FlashFormats',
+                }
+            )
         formats = []
         for content in item.findall(_bp('media:group/media:content')):
             attr = content.attrib

youtube_dl/extractor/jadorecettepub.py

@@ -45,4 +45,3 @@ class JadoreCettePubIE(InfoExtractor):
             'title': title,
             'description': description,
         }
-

youtube_dl/extractor/kickstarter.py

@@ -13,8 +13,10 @@ class KickStarterIE(InfoExtractor):
             'id': '1404461844',
             'ext': 'mp4',
             'title': 'Intersection: The Story of Josh Grant by Kyle Cowling',
-            'description': 'A unique motocross documentary that examines the '
-                'life and mind of one of sports most elite athletes: Josh Grant.',
+            'description': (
+                'A unique motocross documentary that examines the '
+                'life and mind of one of sports most elite athletes: Josh Grant.'
+            ),
         },
     }, {
         'note': 'Embedded video (not using the native kickstarter video service)',

youtube_dl/extractor/ku6.py

@@ -30,4 +30,3 @@ class Ku6IE(InfoExtractor):
             'title': title,
             'url': downloadUrl
         }
-

youtube_dl/extractor/laola1tv.py

@@ -75,4 +75,3 @@ class Laola1TvIE(InfoExtractor):
             'categories': categories,
             'ext': 'mp4',
         }
-

youtube_dl/extractor/liveleak.py

@@ -19,8 +19,7 @@ class LiveLeakIE(InfoExtractor):
             'uploader': 'ljfriel2',
             'title': 'Most unlucky car accident'
         }
-    },
-    {
+    }, {
         'url': 'http://www.liveleak.com/view?i=f93_1390833151',
         'md5': 'd3f1367d14cc3c15bf24fbfbe04b9abf',
         'info_dict': {
@@ -30,8 +29,7 @@ class LiveLeakIE(InfoExtractor):
             'uploader': 'ARD_Stinkt',
             'title': 'German Television does first Edward Snowden Interview (ENGLISH)',
         }
-    },
-    {
+    }, {
         'url': 'http://www.liveleak.com/view?i=4f7_1392687779',
         'md5': '42c6d97d54f1db107958760788c5f48f',
         'info_dict': {

youtube_dl/extractor/malemotion.py

@@ -7,6 +7,7 @@ from ..utils import (
     compat_urllib_parse,
 )
 
+
 class MalemotionIE(InfoExtractor):
     _VALID_URL = r'^(?:https?://)?malemotion\.com/video/(.+?)\.(?P<id>.+?)(#|$)'
     _TEST = {

youtube_dl/extractor/mtv.py

@@ -145,7 +145,8 @@ class MTVServicesInfoExtractor(InfoExtractor):
         idoc = self._download_xml(
             feed_url + '?' + data, video_id,
             'Downloading info', transform_source=fix_xml_ampersands)
-        return [self._get_video_info(item) for item in idoc.findall('.//item')]
+        return self.playlist_result(
+            [self._get_video_info(item) for item in idoc.findall('.//item')])
 
     def _real_extract(self, url):
         title = url_basename(url)
@@ -244,7 +245,7 @@ class MTVIE(MTVServicesInfoExtractor):
             m_vevo = re.search(r'isVevoVideo = true;.*?vevoVideoId = "(.*?)";',
                                webpage, re.DOTALL)
             if m_vevo:
-                vevo_id = m_vevo.group(1);
+                vevo_id = m_vevo.group(1)
                 self.to_screen('Vevo video detected: %s' % vevo_id)
                 return self.url_result('vevo:%s' % vevo_id, ie='Vevo')
 

youtube_dl/extractor/muenchentv.py

@@ -73,4 +73,3 @@ class MuenchenTVIE(InfoExtractor):
             'is_live': True,
             'thumbnail': thumbnail,
         }
-

youtube_dl/extractor/myspace.py

@@ -4,7 +4,7 @@ import re
 import json
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_str,
 )
 
@@ -52,8 +52,8 @@ class MySpaceIE(InfoExtractor):
         if mobj.group('mediatype').startswith('music/song'):
             # songs don't store any useful info in the 'context' variable
             def search_data(name):
-                return self._search_regex(r'data-%s="(.*?)"' % name, webpage,
-                    name)
+                return self._search_regex(
+                    r'data-%s="(.*?)"' % name, webpage, name)
             streamUrl = search_data('stream-url')
             info = {
                 'id': video_id,
@@ -62,8 +62,8 @@ class MySpaceIE(InfoExtractor):
                 'thumbnail': self._og_search_thumbnail(webpage),
             }
         else:
-            context = json.loads(self._search_regex(r'context = ({.*?});', webpage,
-                u'context'))
+            context = json.loads(self._search_regex(
+                r'context = ({.*?});', webpage, 'context'))
             video = context['video']
             streamUrl = video['streamUrl']
             info = {

youtube_dl/extractor/myvideo.py

@@ -173,4 +173,3 @@ class MyVideoIE(InfoExtractor):
             'play_path': video_playpath,
             'player_url': video_swfobj,
         }
-

youtube_dl/extractor/nba.py

@@ -39,7 +39,6 @@ class NBAIE(InfoExtractor):
         duration = parse_duration(
             self._html_search_meta('duration', webpage, 'duration', fatal=False))
 
-
         return {
             'id': shortened_video_id,
             'url': video_url,

youtube_dl/extractor/ninegag.py

@@ -27,8 +27,7 @@ class NineGagIE(InfoExtractor):
             "thumbnail": "re:^https?://",
         },
         'add_ie': ['Youtube']
-    },
-    {
+    }, {
         'url': 'http://9gag.tv/p/KklwM/alternate-banned-opening-scene-of-gravity?ref=fsidebar',
         'info_dict': {
             'id': 'KklwM',

youtube_dl/extractor/ooyala.py

@@ -97,4 +97,3 @@ class OoyalaIE(InfoExtractor):
             }
         else:
             return self._extract_result(videos_info[0], videos_more_info)
-        

youtube_dl/extractor/podomatic.py

@@ -6,6 +6,7 @@ import re
 from .common import InfoExtractor
 from ..utils import int_or_none
 
+
 class PodomaticIE(InfoExtractor):
     IE_NAME = 'podomatic'
     _VALID_URL = r'^(?P<proto>https?)://(?P<channel>[^.]+)\.podomatic\.com/entry/(?P<id>[^?]+)'

youtube_dl/extractor/ringtv.py

@@ -41,4 +41,3 @@ class RingTVIE(InfoExtractor):
             'thumbnail': thumbnail_url,
             'description': description,
         }
-

youtube_dl/extractor/rtlnl.py

@@ -28,9 +28,8 @@ class RtlXlIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         uuid = mobj.group('uuid')
 
-        # Use m3u8 streams (see https://github.com/rg3/youtube-dl/issues/4118)
         info = self._download_json(
-            'http://www.rtl.nl/system/s4m/vfd/version=2/uuid=%s/d=pc/fmt=adaptive/' % uuid,
+            'http://www.rtl.nl/system/s4m/vfd/version=2/uuid=%s/fmt=flash/' % uuid,
             uuid)
 
         material = info['material'][0]
@@ -39,12 +38,13 @@ class RtlXlIE(InfoExtractor):
         progname = info['abstracts'][0]['name']
         subtitle = material['title'] or info['episodes'][0]['name']
 
-        videopath = material['videopath']
+        # Use unencrypted m3u8 streams (See https://github.com/rg3/youtube-dl/issues/4118)
+        videopath = material['videopath'].replace('.f4m', '.m3u8')
         m3u8_url = 'http://manifest.us.rtl.nl' + videopath
 
         formats = self._extract_m3u8_formats(m3u8_url, uuid, ext='mp4')
 
-        video_urlpart = videopath.split('/adaptive/')[1][:-4]
+        video_urlpart = videopath.split('/flash/')[1][:-5]
         PG_URL_TEMPLATE = 'http://pg.us.rtl.nl/rtlxl/network/%s/progressive/%s.mp4'
 
         formats.extend([

youtube_dl/extractor/rtve.py

@@ -54,7 +54,6 @@ def _decrypt_url(png):
     return url
 
 
-
 class RTVEALaCartaIE(InfoExtractor):
     IE_NAME = 'rtve.es:alacarta'
     IE_DESC = 'RTVE a la carta'

youtube_dl/extractor/sbs.py

@@ -27,8 +27,7 @@ class SBSIE(InfoExtractor):
             'thumbnail': 're:http://.*\.jpg',
         },
         'add_ies': ['generic'],
-    },
-    {
+    }, {
         'url': 'http://www.sbs.com.au/ondemand/video/320403011771/Dingo-Conservation-The-Feed',
         'only_matching': True,
     }]

youtube_dl/extractor/servingsys.py

@@ -67,5 +67,3 @@ class ServingSysIE(InfoExtractor):
             'title': title,
             'entries': entries,
         }
-
- 

youtube_dl/extractor/smotri.py

@@ -1,7 +1,6 @@
 # encoding: utf-8
 from __future__ import unicode_literals
 
-import os.path
 import re
 import json
 import hashlib
@@ -12,15 +11,15 @@ from ..utils import (
     compat_urllib_parse,
     compat_urllib_request,
     ExtractorError,
-    url_basename,
     int_or_none,
+    unified_strdate,
 )
 
 
 class SmotriIE(InfoExtractor):
     IE_DESC = 'Smotri.com'
     IE_NAME = 'smotri'
-    _VALID_URL = r'^https?://(?:www\.)?(?:smotri\.com/video/view/\?id=|pics\.smotri\.com/(?:player|scrubber_custom8)\.swf\?file=)(?P<videoid>v(?P<realvideoid>[0-9]+)[a-z0-9]{4})'
+    _VALID_URL = r'^https?://(?:www\.)?(?:smotri\.com/video/view/\?id=|pics\.smotri\.com/(?:player|scrubber_custom8)\.swf\?file=)(?P<id>v(?P<realvideoid>[0-9]+)[a-z0-9]{4})'
     _NETRC_MACHINE = 'smotri'
 
     _TESTS = [
@@ -35,7 +34,6 @@ class SmotriIE(InfoExtractor):
                 'uploader': 'rbc2008',
                 'uploader_id': 'rbc08',
                 'upload_date': '20131118',
-                'description': 'катастрофа с камер видеонаблюдения, видео катастрофа с камер видеонаблюдения',
                 'thumbnail': 'http://frame6.loadup.ru/8b/a9/2610366.3.3.jpg',
             },
         },
@@ -50,7 +48,6 @@ class SmotriIE(InfoExtractor):
                 'uploader': 'Support Photofile@photofile',
                 'uploader_id': 'support-photofile',
                 'upload_date': '20070704',
-                'description': 'test, видео test',
                 'thumbnail': 'http://frame4.loadup.ru/03/ed/57591.2.3.jpg',
             },
         },
@@ -66,7 +63,6 @@ class SmotriIE(InfoExtractor):
                 'uploader_id': 'timoxa40',
                 'upload_date': '20100404',
                 'thumbnail': 'http://frame7.loadup.ru/af/3f/1390466.3.3.jpg',
-                'description': 'TOCCA_A_NOI_-_LE_COSE_NON_VANNO_CAMBIAMOLE_ORA-1, видео TOCCA_A_NOI_-_LE_COSE_NON_VANNO_CAMBIAMOLE_ORA-1',
             },
             'params': {
                 'videopassword': 'qwerty',
@@ -85,7 +81,6 @@ class SmotriIE(InfoExtractor):
                 'upload_date': '20101001',
                 'thumbnail': 'http://frame3.loadup.ru/75/75/1540889.1.3.jpg',
                 'age_limit': 18,
-                'description': 'этот ролик не покажут по ТВ, видео этот ролик не покажут по ТВ',
             },
             'params': {
                 'videopassword': '333'
@@ -102,17 +97,11 @@ class SmotriIE(InfoExtractor):
                 'uploader': 'HannahL',
                 'uploader_id': 'lisaha95',
                 'upload_date': '20090331',
-                'description': 'Shakira - Don\'t Bother, видео Shakira - Don\'t Bother',
                 'thumbnail': 'http://frame8.loadup.ru/44/0b/918809.7.3.jpg',
             },
         },
     ]
 
-    _SUCCESS = 0
-    _PASSWORD_NOT_VERIFIED = 1
-    _PASSWORD_DETECTED = 2
-    _VIDEO_NOT_FOUND = 3
-
     @classmethod
     def _extract_url(cls, webpage):
         mobj = re.search(
@@ -137,44 +126,44 @@ class SmotriIE(InfoExtractor):
         return self._html_search_meta(name, html, display_name)
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('videoid')
-        real_video_id = mobj.group('realvideoid')
+        video_id = self._match_id(url)
 
-        # Download video JSON data
-        video_json_url = 'http://smotri.com/vt.php?id=%s' % real_video_id
-        video_json_page = self._download_webpage(video_json_url, video_id, 'Downloading video JSON')
-        video_json = json.loads(video_json_page)
+        video_form = {
+            'ticket': video_id,
+            'video_url': '1',
+            'frame_url': '1',
+            'devid': 'LoadupFlashPlayer',
+            'getvideoinfo': '1',
+        }
 
-        status = video_json['status']
-        if status == self._VIDEO_NOT_FOUND:
+        request = compat_urllib_request.Request(
+            'http://smotri.com/video/view/url/bot/', compat_urllib_parse.urlencode(video_form))
+        request.add_header('Content-Type', 'application/x-www-form-urlencoded')
+
+        video = self._download_json(request, video_id, 'Downloading video JSON')
+
+        if video.get('_moderate_no') or not video.get('moderated'):
+            raise ExtractorError('Video %s has not been approved by moderator' % video_id, expected=True)
+
+        if video.get('error'):
             raise ExtractorError('Video %s does not exist' % video_id, expected=True)
-        elif status == self._PASSWORD_DETECTED: # The video is protected by a password, retry with
-                                                # video-password set
-            video_password = self._downloader.params.get('videopassword', None)
-            if not video_password:
-                raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True)
-            video_json_url += '&md5pass=%s' % hashlib.md5(video_password.encode('utf-8')).hexdigest()
-            video_json_page = self._download_webpage(video_json_url, video_id, 'Downloading video JSON (video-password set)')
-            video_json = json.loads(video_json_page)
-            status = video_json['status']
-            if status == self._PASSWORD_NOT_VERIFIED:
-                raise ExtractorError('Video password is invalid', expected=True)
 
-        if status != self._SUCCESS:
-            raise ExtractorError('Unexpected status value %s' % status)
-
-        # Extract the URL of the video
-        video_url = video_json['file_data']
+        video_url = video.get('_vidURL') or video.get('_vidURL_mp4')
+        title = video['title']
+        thumbnail = video['_imgURL']
+        upload_date = unified_strdate(video['added'])
+        uploader = video['userNick']
+        uploader_id = video['userLogin']
+        duration = int_or_none(video['duration'])
 
         # Video JSON does not provide enough meta data
         # We will extract some from the video web page instead
-        video_page_url = 'http://smotri.com/video/view/?id=%s' % video_id
-        video_page = self._download_webpage(video_page_url, video_id, 'Downloading video page')
+        webpage_url = 'http://smotri.com/video/view/?id=%s' % video_id
+        webpage = self._download_webpage(webpage_url, video_id, 'Downloading video page')
 
         # Warning if video is unavailable
         warning = self._html_search_regex(
-            r'<div class="videoUnModer">(.*?)</div>', video_page,
+            r'<div class="videoUnModer">(.*?)</div>', webpage,
             'warning message', default=None)
         if warning is not None:
             self._downloader.report_warning(
@@ -182,84 +171,32 @@ class SmotriIE(InfoExtractor):
                 (video_id, warning))
 
         # Adult content
-        if re.search('EroConfirmText">', video_page) is not None:
+        if re.search('EroConfirmText">', webpage) is not None:
             self.report_age_confirmation()
             confirm_string = self._html_search_regex(
                 r'<a href="/video/view/\?id=%s&confirm=([^"]+)" title="[^"]+">' % video_id,
-                video_page, 'confirm string')
-            confirm_url = video_page_url + '&confirm=%s' % confirm_string
-            video_page = self._download_webpage(confirm_url, video_id, 'Downloading video page (age confirmed)')
+                webpage, 'confirm string')
+            confirm_url = webpage_url + '&confirm=%s' % confirm_string
+            webpage = self._download_webpage(confirm_url, video_id, 'Downloading video page (age confirmed)')
             adult_content = True
         else:
             adult_content = False
 
-        # Extract the rest of meta data
-        video_title = self._search_meta('name', video_page, 'title')
-        if not video_title:
-            video_title = os.path.splitext(url_basename(video_url))[0]
-
-        video_description = self._search_meta('description', video_page)
-        END_TEXT = ' на сайте Smotri.com'
-        if video_description and video_description.endswith(END_TEXT):
-            video_description = video_description[:-len(END_TEXT)]
-        START_TEXT = 'Смотреть онлайн ролик '
-        if video_description and video_description.startswith(START_TEXT):
-            video_description = video_description[len(START_TEXT):]
-        video_thumbnail = self._search_meta('thumbnail', video_page)
-
-        upload_date_str = self._search_meta('uploadDate', video_page, 'upload date')
-        if upload_date_str:
-            upload_date_m = re.search(r'(?P<year>\d{4})\.(?P<month>\d{2})\.(?P<day>\d{2})T', upload_date_str)
-            video_upload_date = (
-                (
-                    upload_date_m.group('year') +
-                    upload_date_m.group('month') +
-                    upload_date_m.group('day')
-                )
-                if upload_date_m else None
-            )
-        else:
-            video_upload_date = None
-
-        duration_str = self._search_meta('duration', video_page)
-        if duration_str:
-            duration_m = re.search(r'T(?P<hours>[0-9]{2})H(?P<minutes>[0-9]{2})M(?P<seconds>[0-9]{2})S', duration_str)
-            video_duration = (
-                (
-                    (int(duration_m.group('hours')) * 60 * 60) +
-                    (int(duration_m.group('minutes')) * 60) +
-                    int(duration_m.group('seconds'))
-                )
-                if duration_m else None
-            )
-        else:
-            video_duration = None
-
-        video_uploader = self._html_search_regex(
-            '<div class="DescrUser"><div>Автор.*?onmouseover="popup_user_info[^"]+">(.*?)</a>',
-            video_page, 'uploader', fatal=False, flags=re.MULTILINE|re.DOTALL)
-
-        video_uploader_id = self._html_search_regex(
-            '<div class="DescrUser"><div>Автор.*?onmouseover="popup_user_info\\(.*?\'([^\']+)\'\\);">',
-            video_page, 'uploader id', fatal=False, flags=re.MULTILINE|re.DOTALL)
-
-        video_view_count = self._html_search_regex(
+        view_count = self._html_search_regex(
             'Общее количество просмотров.*?<span class="Number">(\\d+)</span>',
-            video_page, 'view count', fatal=False, flags=re.MULTILINE|re.DOTALL)
+            webpage, 'view count', fatal=False, flags=re.MULTILINE | re.DOTALL)
 
         return {
             'id': video_id,
             'url': video_url,
-            'title': video_title,
-            'thumbnail': video_thumbnail,
-            'description': video_description,
-            'uploader': video_uploader,
-            'upload_date': video_upload_date,
-            'uploader_id': video_uploader_id,
-            'duration': video_duration,
-            'view_count': int_or_none(video_view_count),
+            'title': title,
+            'thumbnail': thumbnail,
+            'uploader': uploader,
+            'upload_date': upload_date,
+            'uploader_id': uploader_id,
+            'duration': duration,
+            'view_count': int_or_none(view_count),
             'age_limit': 18 if adult_content else 0,
-            'video_page_url': video_page_url
         }
 
 

youtube_dl/extractor/sportdeutschland.py

@@ -93,4 +93,3 @@ class SportDeutschlandIE(InfoExtractor):
             'rtmp_live': asset.get('live'),
             'timestamp': parse_iso8601(asset.get('date')),
         }
-

youtube_dl/extractor/stanfordoc.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -9,22 +11,21 @@ from ..utils import (
 
 
 class StanfordOpenClassroomIE(InfoExtractor):
-    IE_NAME = u'stanfordoc'
-    IE_DESC = u'Stanford Open ClassRoom'
-    _VALID_URL = r'^(?:https?://)?openclassroom\.stanford\.edu(?P<path>/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P<course>[^&]+)(&video=(?P<video>[^&]+))?(&.*)?)?))$'
+    IE_NAME = 'stanfordoc'
+    IE_DESC = 'Stanford Open ClassRoom'
+    _VALID_URL = r'https?://openclassroom\.stanford\.edu(?P<path>/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P<course>[^&]+)(&video=(?P<video>[^&]+))?(&.*)?)?))$'
     _TEST = {
-        u'url': u'http://openclassroom.stanford.edu/MainFolder/VideoPage.php?course=PracticalUnix&video=intro-environment&speed=100',
-        u'file': u'PracticalUnix_intro-environment.mp4',
-        u'md5': u'544a9468546059d4e80d76265b0443b8',
-        u'info_dict': {
-            u"title": u"Intro Environment"
+        'url': 'http://openclassroom.stanford.edu/MainFolder/VideoPage.php?course=PracticalUnix&video=intro-environment&speed=100',
+        'md5': '544a9468546059d4e80d76265b0443b8',
+        'info_dict': {
+            'id': 'PracticalUnix_intro-environment',
+            'ext': 'mp4',
+            'title': 'Intro Environment',
         }
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError(u'Invalid URL: %s' % url)
 
         if mobj.group('course') and mobj.group('video'):  # A specific video
             course = mobj.group('course')
@@ -35,7 +36,6 @@ class StanfordOpenClassroomIE(InfoExtractor):
                 'upload_date': None,
             }
 
-            self.report_extraction(info['id'])
             baseUrl = 'http://openclassroom.stanford.edu/MainFolder/courses/' + course + '/videos/'
             xmlUrl = baseUrl + video + '.xml'
             mdoc = self._download_xml(xmlUrl, info['id'])
@@ -43,63 +43,49 @@ class StanfordOpenClassroomIE(InfoExtractor):
                 info['title'] = mdoc.findall('./title')[0].text
                 info['url'] = baseUrl + mdoc.findall('./videoFile')[0].text
             except IndexError:
-                raise ExtractorError(u'Invalid metadata XML file')
-            info['ext'] = info['url'].rpartition('.')[2]
-            return [info]
+                raise ExtractorError('Invalid metadata XML file')
+            return info
         elif mobj.group('course'):  # A course page
             course = mobj.group('course')
             info = {
                 'id': course,
-                'type': 'playlist',
+                '_type': 'playlist',
                 'uploader': None,
                 'upload_date': None,
             }
 
-            coursepage = self._download_webpage(url, info['id'],
+            coursepage = self._download_webpage(
+                url, info['id'],
                 note='Downloading course info page',
                 errnote='Unable to download course info page')
 
-            info['title'] = self._html_search_regex('<h1>([^<]+)</h1>', coursepage, 'title', default=info['id'])
+            info['title'] = self._html_search_regex(
+                r'<h1>([^<]+)</h1>', coursepage, 'title', default=info['id'])
 
-            info['description'] = self._html_search_regex('<description>([^<]+)</description>',
-                coursepage, u'description', fatal=False)
+            info['description'] = self._html_search_regex(
+                r'(?s)<description>([^<]+)</description>',
+                coursepage, 'description', fatal=False)
 
             links = orderedSet(re.findall('<a href="(VideoPage.php\?[^"]+)">', coursepage))
-            info['list'] = [
-                {
-                    'type': 'reference',
-                    'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(vpage),
-                }
-                    for vpage in links]
-            results = []
-            for entry in info['list']:
-                assert entry['type'] == 'reference'
-                results += self.extract(entry['url'])
-            return results
+            info['entries'] = [self.url_result(
+                'http://openclassroom.stanford.edu/MainFolder/%s' % unescapeHTML(l)
+            ) for l in links]
+            return info
         else:  # Root page
             info = {
                 'id': 'Stanford OpenClassroom',
-                'type': 'playlist',
+                '_type': 'playlist',
                 'uploader': None,
                 'upload_date': None,
             }
+            info['title'] = info['id']
 
             rootURL = 'http://openclassroom.stanford.edu/MainFolder/HomePage.php'
             rootpage = self._download_webpage(rootURL, info['id'],
-                errnote=u'Unable to download course info page')
-
-            info['title'] = info['id']
+                                              errnote='Unable to download course info page')
 
             links = orderedSet(re.findall('<a href="(CoursePage.php\?[^"]+)">', rootpage))
-            info['list'] = [
-                {
-                    'type': 'reference',
-                    'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(cpage),
-                }
-                    for cpage in links]
-
-            results = []
-            for entry in info['list']:
-                assert entry['type'] == 'reference'
-                results += self.extract(entry['url'])
-            return results
+            info['entries'] = [self.url_result(
+                'http://openclassroom.stanford.edu/MainFolder/%s' % unescapeHTML(l)
+            ) for l in links]
+            return info

youtube_dl/extractor/subtitles.py

@@ -50,7 +50,7 @@ class SubtitlesInfoExtractor(InfoExtractor):
 
             sub_lang_list = {}
             for sub_lang in requested_langs:
-                if not sub_lang in available_subs_list:
+                if sub_lang not in available_subs_list:
                     self._downloader.report_warning(u'no closed captions found in the specified language "%s"' % sub_lang)
                     continue
                 sub_lang_list[sub_lang] = available_subs_list[sub_lang]

youtube_dl/extractor/sztvhu.py

@@ -1,27 +1,24 @@
 # -*- coding: utf-8 -*-
-
-import re
+from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import determine_ext
 
 
 class SztvHuIE(InfoExtractor):
-    _VALID_URL = r'(?:http://)?(?:(?:www\.)?sztv\.hu|www\.tvszombathely\.hu)/(?:[^/]+)/.+-(?P<id>[0-9]+)'
+    _VALID_URL = r'http://(?:(?:www\.)?sztv\.hu|www\.tvszombathely\.hu)/(?:[^/]+)/.+-(?P<id>[0-9]+)'
     _TEST = {
-        u'url': u'http://sztv.hu/hirek/cserkeszek-nepszerusitettek-a-kornyezettudatos-eletmodot-a-savaria-teren-20130909',
-        u'file': u'20130909.mp4',
-        u'md5': u'a6df607b11fb07d0e9f2ad94613375cb',
-        u'info_dict': {
-            u"title": u"Cserkészek népszerűsítették a környezettudatos életmódot a Savaria téren",
-            u"description": u'A zöld nap játékos ismeretterjesztő programjait a Magyar Cserkész Szövetség szervezte, akik az ország nyolc városában adják át tudásukat az érdeklődőknek. A PET...',
+        'url': 'http://sztv.hu/hirek/cserkeszek-nepszerusitettek-a-kornyezettudatos-eletmodot-a-savaria-teren-20130909',
+        'md5': 'a6df607b11fb07d0e9f2ad94613375cb',
+        'info_dict': {
+            'id': '20130909',
+            'ext': 'mp4',
+            'title': 'Cserkészek népszerűsítették a környezettudatos életmódot a Savaria téren',
+            'description': 'A zöld nap játékos ismeretterjesztő programjait a Magyar Cserkész Szövetség szervezte, akik az ország nyolc városában adják át tudásukat az érdeklődőknek. A PET...',
         },
-        u'skip': u'Service temporarily disabled as of 2013-11-20'
     }
 
     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)
         video_file = self._search_regex(
             r'file: "...:(.*?)",', webpage, 'video file')
@@ -39,7 +36,6 @@ class SztvHuIE(InfoExtractor):
             'id': video_id,
             'url': video_url,
             'title': title,
-            'ext': determine_ext(video_url),
             'description': description,
             'thumbnail': thumbnail,
         }

youtube_dl/extractor/tass.py

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

youtube_dl/extractor/teamcoco.py

@@ -16,8 +16,7 @@ class TeamcocoIE(InfoExtractor):
                 'title': 'Conan Becomes A Mary Kay Beauty Consultant',
                 'description': 'Mary Kay is perhaps the most trusted name in female beauty, so of course Conan is a natural choice to sell their products.'
             }
-    },
-    {
+        }, {
             'url': 'http://teamcoco.com/video/louis-ck-interview-george-w-bush',
             'file': '19705.mp4',
             'md5': 'cde9ba0fa3506f5f017ce11ead928f9a',

youtube_dl/extractor/telebruxelles.py

@@ -0,0 +1,60 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class TeleBruxellesIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?telebruxelles\.be/(news|sport|dernier-jt)/?(?P<id>[^/#?]+)'
+    _TESTS = [{
+        'url': 'http://www.telebruxelles.be/news/auditions-devant-parlement-francken-galant-tres-attendus/',
+        'md5': '59439e568c9ee42fb77588b2096b214f',
+        'info_dict': {
+            'id': '11942',
+            'display_id': 'auditions-devant-parlement-francken-galant-tres-attendus',
+            'ext': 'flv',
+            'title': 'Parlement : Francken et Galant répondent aux interpellations de l’opposition',
+            'description': 're:Les auditions des ministres se poursuivent*'
+        },
+        'params': {
+            'skip_download': 'requires rtmpdump'
+        },
+    }, {
+        'url': 'http://www.telebruxelles.be/sport/basket-brussels-bat-mons-80-74/',
+        'md5': '181d3fbdcf20b909309e5aef5c6c6047',
+        'info_dict': {
+            'id': '10091',
+            'display_id': 'basket-brussels-bat-mons-80-74',
+            'ext': 'flv',
+            'title': 'Basket : le Brussels bat Mons 80-74',
+            'description': 're:^Ils l\u2019on fait ! En basket, le B*',
+        },
+        'params': {
+            'skip_download': 'requires rtmpdump'
+        },
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        article_id = self._html_search_regex(
+            r"<article id=\"post-(\d+)\"", webpage, 'article ID')
+        title = self._html_search_regex(
+            r'<h1 class=\"entry-title\">(.*?)</h1>', webpage, 'title')
+        description = self._og_search_description(webpage)
+
+        rtmp_url = self._html_search_regex(
+            r"file: \"(rtmp://\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}:\d{1,5}/vod/mp4:\" \+ \"\w+\" \+ \".mp4)\"",
+            webpage, 'RTMP url')
+        rtmp_url = rtmp_url.replace("\" + \"", "")
+
+        return {
+            'id': article_id,
+            'display_id': display_id,
+            'title': title,
+            'description': description,
+            'url': rtmp_url,
+            'ext': 'flv',
+            'rtmp_live': True  # if rtmpdump is not called with "--live" argument, the download is blocked and can be completed
+        }

youtube_dl/extractor/theplatform.py

@@ -35,6 +35,7 @@ class ThePlatformIE(InfoExtractor):
             'skip_download': True,
         },
     }
+
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
@@ -48,7 +49,6 @@ class ThePlatformIE(InfoExtractor):
             smil_url = ('http://link.theplatform.com/s/dJ5BDC/{0}/meta.smil?'
                         'format=smil&mbr=true'.format(video_id))
 
-
         meta = self._download_xml(smil_url, video_id)
         try:
             error_msg = next(

youtube_dl/extractor/tlc.py

@@ -36,9 +36,10 @@ class TlcDeIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Breaking Amish: Die Welt da draußen',
             'uploader': 'Discovery Networks - Germany',
-            'description': 'Vier Amische und eine Mennonitin wagen in New York'
+            'description': (
+                'Vier Amische und eine Mennonitin wagen in New York'
                 '  den Sprung in ein komplett anderes Leben. Begleitet sie auf'
-                ' ihrem spannenden Weg.',
+                ' ihrem spannenden Weg.'),
         },
     }
 

youtube_dl/extractor/tmz.py

@@ -0,0 +1,32 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class TMZIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?tmz\.com/videos/(?P<id>[^/]+)/?'
+    _TEST = {
+        'url': 'http://www.tmz.com/videos/0_okj015ty/',
+        'md5': '791204e3bf790b1426cb2db0706184c0',
+        'info_dict': {
+            'id': '0_okj015ty',
+            'url': 'http://tmz.vo.llnwd.net/o28/2014-03/13/0_okj015ty_0_rt8ro3si_2.mp4',
+            'ext': 'mp4',
+            'title': 'Kim Kardashian\'s Boobs Unlock a Mystery!',
+            'description': 'Did Kim Kardasain try to one-up Khloe by one-upping Kylie???  Or is she just showing off her amazing boobs?',
+            'thumbnail': 'http://cdnbakmi.kaltura.com/p/591531/sp/59153100/thumbnail/entry_id/0_okj015ty/version/100002/acv/182/width/640',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        return {
+            'id': video_id,
+            'url': self._html_search_meta('VideoURL', webpage, fatal=True),
+            'title': self._og_search_title(webpage),
+            'description': self._og_search_description(webpage),
+            'thumbnail': self._html_search_meta('ThumbURL', webpage),
+        }

youtube_dl/extractor/trilulilu.py

@@ -63,4 +63,3 @@ class TriluliluIE(InfoExtractor):
             'description': description,
             'thumbnail': thumbnail,
         }
-

youtube_dl/extractor/tunein.py

@@ -0,0 +1,101 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+
+class TuneInIE(InfoExtractor):
+    _VALID_URL = r'''(?x)https?://(?:www\.)?
+    (?:
+        tunein\.com/
+        (?:
+            radio/.*?-s|
+            station/.*?StationId\=
+        )(?P<id>[0-9]+)
+        |tun\.in/(?P<redirect_id>[A-Za-z0-9]+)
+    )
+    '''
+
+    _INFO_DICT = {
+        'id': '34682',
+        'title': 'Jazz 24 on 88.5 Jazz24 - KPLU-HD2',
+        'ext': 'AAC',
+        'thumbnail': 're:^https?://.*\.png$',
+        'location': 'Tacoma, WA',
+    }
+    _TESTS = [
+        {
+            'url': 'http://tunein.com/radio/Jazz24-885-s34682/',
+            'info_dict': _INFO_DICT,
+            'params': {
+                'skip_download': True,  # live stream
+            },
+        },
+        {  # test redirection
+            'url': 'http://tun.in/ser7s',
+            'info_dict': _INFO_DICT,
+            'params': {
+                'skip_download': True,  # live stream
+            },
+        },
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        redirect_id = mobj.group('redirect_id')
+        if redirect_id:
+            # The server doesn't support HEAD requests
+            urlh = self._request_webpage(
+                url, redirect_id, note='Downloading redirect page')
+            url = urlh.geturl()
+            self.to_screen('Following redirect: %s' % url)
+            mobj = re.match(self._VALID_URL, url)
+        station_id = mobj.group('id')
+
+        webpage = self._download_webpage(
+            url, station_id, note='Downloading station webpage')
+
+        payload = self._html_search_regex(
+            r'(?m)TuneIn\.payload\s*=\s*(\{[^$]+?)$', webpage, 'JSON data')
+        json_data = json.loads(payload)
+        station_info = json_data['Station']['broadcast']
+        title = station_info['Title']
+        thumbnail = station_info.get('Logo')
+        location = station_info.get('Location')
+        streams_url = station_info.get('StreamUrl')
+        if not streams_url:
+            raise ExtractorError('No downloadable streams found',
+                                 expected=True)
+        stream_data = self._download_webpage(
+            streams_url, station_id, note='Downloading stream data')
+        streams = json.loads(self._search_regex(
+            r'\((.*)\);', stream_data, 'stream info'))['Streams']
+
+        is_live = None
+        formats = []
+        for stream in streams:
+            if stream.get('Type') == 'Live':
+                is_live = True
+            formats.append({
+                'abr': stream.get('Bandwidth'),
+                'ext': stream.get('MediaType'),
+                'acodec': stream.get('MediaType'),
+                'vcodec': 'none',
+                'url': stream.get('Url'),
+                # Sometimes streams with the highest quality do not exist
+                'preference': stream.get('Reliability'),
+            })
+        self._sort_formats(formats)
+
+        return {
+            'id': station_id,
+            'title': title,
+            'formats': formats,
+            'thumbnail': thumbnail,
+            'location': location,
+            'is_live': is_live,
+        }

youtube_dl/extractor/vh1.py

@@ -121,4 +121,7 @@ class VH1IE(MTVIE):
         idoc = self._download_xml(
             doc_url, video_id,
             'Downloading info', transform_source=fix_xml_ampersands)
-        return [self._get_video_info(item) for item in idoc.findall('.//item')]
+        return self.playlist_result(
+            [self._get_video_info(item) for item in idoc.findall('.//item')],
+            playlist_id=video_id,
+        )

youtube_dl/extractor/vice.py

@@ -35,4 +35,3 @@ class ViceIE(InfoExtractor):
         except ExtractorError:
             raise ExtractorError('The page doesn\'t contain a video', expected=True)
         return self.url_result(ooyala_url, ie='Ooyala')
-

youtube_dl/extractor/videofyme.py

@@ -6,6 +6,7 @@ from ..utils import (
     determine_ext,
 )
 
+
 class VideofyMeIE(InfoExtractor):
     _VALID_URL = r'https?://(www\.videofy\.me/.+?|p\.videofy\.me/v)/(?P<id>\d+)(&|#|$)'
     IE_NAME = u'videofy.me'

youtube_dl/extractor/vidzi.py

@@ -30,4 +30,3 @@ class VidziIE(InfoExtractor):
             'title': title,
             'url': video_url,
         }
-        

youtube_dl/extractor/vk.py

@@ -11,12 +11,13 @@ from ..utils import (
     compat_urllib_parse,
     compat_str,
     unescapeHTML,
-)
+    unified_strdate,
+    orderedSet)
 
 
 class VKIE(InfoExtractor):
     IE_NAME = 'vk.com'
-    _VALID_URL = r'https?://(?:m\.)?vk\.com/(?:video_ext\.php\?.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+)|(?:.+?\?.*?z=)?video(?P<videoid>.*?)(?:\?|%2F|$))'
+    _VALID_URL = r'https?://(?:m\.)?vk\.com/(?:video_ext\.php\?.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+)|(?:.+?\?.*?z=)?video(?P<videoid>[^s].*?)(?:\?|%2F|$))'
     _NETRC_MACHINE = 'vk'
 
     _TESTS = [
@@ -29,17 +30,19 @@ class VKIE(InfoExtractor):
                 'title': 'ProtivoGunz - Хуёвая песня',
                 'uploader': 're:Noize MC.*',
                 'duration': 195,
+                'upload_date': '20120212',
             },
         },
         {
-            'url': 'http://vk.com/video4643923_163339118',
-            'md5': 'f79bccb5cd182b1f43502ca5685b2b36',
+            'url': 'http://vk.com/video205387401_165548505',
+            'md5': '6c0aeb2e90396ba97035b9cbde548700',
             'info_dict': {
-                'id': '163339118',
+                'id': '165548505',
                 'ext': 'mp4',
-                'uploader': 'Elya Iskhakova',
-                'title': 'Dream Theater - Hollow Years Live at Budokan 720*',
-                'duration': 558,
+                'uploader': 'Tom Cruise',
+                'title': 'No name',
+                'duration': 9,
+                'upload_date': '20130721'
             }
         },
         {
@@ -52,9 +55,12 @@ class VKIE(InfoExtractor):
                 'uploader': 'Vladimir Gavrin',
                 'title': 'Lin Dan',
                 'duration': 101,
+                'upload_date': '20120730',
             }
         },
         {
+            # VIDEO NOW REMOVED
+            # please update if you find a video whose URL follows the same pattern
             'url': 'http://vk.com/video-8871596_164049491',
             'md5': 'a590bcaf3d543576c9bd162812387666',
             'note': 'Only available for registered users',
@@ -64,18 +70,7 @@ class VKIE(InfoExtractor):
                 'uploader': 'Триллеры',
                 'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]',
                 'duration': 8352,
-            },
-            'skip': 'Requires vk account credentials',
-        },
-        {
-            'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a',
-            'md5': 'd82c22e449f036282d1d3f7f4d276869',
-            'info_dict': {
-                'id': '166094326',
-                'ext': 'mp4',
-                'uploader': 'Киномания - лучшее из мира кино',
-                'title': 'Запах женщины (1992)',
-                'duration': 9392,
+                'upload_date': '20121218'
             },
             'skip': 'Requires vk account credentials',
         },
@@ -88,6 +83,7 @@ class VKIE(InfoExtractor):
                 'uploader': 'Киномания - лучшее из мира кино',
                 'title': ' ',
                 'duration': 7291,
+                'upload_date': '20140328',
             },
             'skip': 'Requires vk account credentials',
         },
@@ -100,9 +96,15 @@ class VKIE(InfoExtractor):
                 'ext': 'mp4',
                 'title': 'Книга Илая',
                 'duration': 6771,
+                'upload_date': '20140626',
             },
             'skip': 'Only works from Russia',
         },
+        {
+            # removed video, just testing that we match the pattern
+            'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a',
+            'only_matching': True,
+        },
     ]
 
     def _login(self):
@@ -141,10 +143,12 @@ class VKIE(InfoExtractor):
         ERRORS = {
             r'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<':
             'Video %s has been removed from public access due to rightholder complaint.',
+
             r'<!>Please log in or <':
             'Video %s is only available for registered users, '
             'use --username and --password options to provide account credentials.',
-            '<!>Unknown error':
+
+            r'<!>Unknown error':
             'Video %s does not exist.'
         }
 
@@ -169,6 +173,13 @@ class VKIE(InfoExtractor):
         data_json = self._search_regex(r'var vars = ({.*?});', info_page, 'vars')
         data = json.loads(data_json)
 
+        # Extract upload date
+        upload_date = None
+        mobj = re.search(r'id="mv_date_wrap".*?Added ([a-zA-Z]+ [0-9]+), ([0-9]+) at', info_page)
+        if mobj is not None:
+            mobj.group(1) + ' ' + mobj.group(2)
+            upload_date = unified_strdate(mobj.group(1) + ' ' + mobj.group(2))
+
         formats = [{
             'format_id': k,
             'url': v,
@@ -183,5 +194,28 @@ class VKIE(InfoExtractor):
             'title': unescapeHTML(data['md_title']),
             'thumbnail': data.get('jpg'),
             'uploader': data.get('md_author'),
-            'duration': data.get('duration')
+            'duration': data.get('duration'),
+            'upload_date': upload_date,
         }
+
+
+class VKUserVideosIE(InfoExtractor):
+    IE_NAME = 'vk.com:user-videos'
+    IE_DESC = 'vk.com:All of a user\'s videos'
+    _VALID_URL = r'https?://vk\.com/videos(?P<id>[0-9]+)(?:m\?.*)?'
+    _TEMPLATE_URL = 'https://vk.com/videos'
+    _TEST = {
+        'url': 'http://vk.com/videos205387401',
+        'playlist_mincount': 4,
+    }
+
+    def _real_extract(self, url):
+        page_id = self._match_id(url)
+        page = self._download_webpage(url, page_id)
+        video_ids = orderedSet(
+            m.group(1) for m in re.finditer(r'href="/video([0-9_]+)"', page))
+        url_entries = [
+            self.url_result(
+                'http://vk.com/video' + video_id, 'VK', video_id=video_id)
+            for video_id in video_ids]
+        return self.playlist_result(url_entries, page_id)

youtube_dl/extractor/worldstarhiphop.py

@@ -51,4 +51,3 @@ class WorldStarHipHopIE(InfoExtractor):
             'title': video_title,
             'thumbnail': thumbnail,
         }
-

youtube_dl/extractor/xbef.py

@@ -47,4 +47,3 @@ class XBefIE(InfoExtractor):
             'thumbnail': thumbnail,
             'age_limit': 18,
         }
-

youtube_dl/extractor/xminus.py

@@ -0,0 +1,67 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import (
+    compat_chr,
+    compat_ord,
+)
+from ..utils import (
+    int_or_none,
+    parse_filesize,
+)
+
+
+class XMinusIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?x-minus\.org/track/(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://x-minus.org/track/4542/%D0%BF%D0%B5%D1%81%D0%B5%D0%BD%D0%BA%D0%B0-%D1%88%D0%BE%D1%84%D0%B5%D1%80%D0%B0.html',
+        'md5': '401a15f2d2dcf6d592cb95528d72a2a8',
+        'info_dict': {
+            'id': '4542',
+            'ext': 'mp3',
+            'title': 'Леонид Агутин-Песенка шофера',
+            'duration': 156,
+            'tbr': 320,
+            'filesize_approx': 5900000,
+            'view_count': int,
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        artist = self._html_search_regex(
+            r'minus_track\.artist="(.+?)"', webpage, 'artist')
+        title = artist + '-' + self._html_search_regex(
+            r'minus_track\.title="(.+?)"', webpage, 'title')
+        duration = int_or_none(self._html_search_regex(
+            r'minus_track\.dur_sec=\'([0-9]*?)\'',
+            webpage, 'duration', fatal=False))
+        filesize_approx = parse_filesize(self._html_search_regex(
+            r'<div class="filesize[^"]*"></div>\s*([0-9.]+\s*[a-zA-Z][bB])',
+            webpage, 'approximate filesize', fatal=False))
+        tbr = int_or_none(self._html_search_regex(
+            r'<div class="quality[^"]*"></div>\s*([0-9]+)\s*kbps',
+            webpage, 'bitrate', fatal=False))
+        view_count = int_or_none(self._html_search_regex(
+            r'<div class="quality.*?► ([0-9]+)',
+            webpage, 'view count', fatal=False))
+
+        enc_token = self._html_search_regex(
+            r'data-mt="(.*?)"', webpage, 'enc_token')
+        token = ''.join(
+            c if pos == 3 else compat_chr(compat_ord(c) - 1)
+            for pos, c in enumerate(reversed(enc_token)))
+        video_url = 'http://x-minus.org/dwlf/%s/%s.mp3' % (video_id, token)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'url': video_url,
+            'duration': duration,
+            'filesize_approx': filesize_approx,
+            'tbr': tbr,
+            'view_count': view_count,
+        }

youtube_dl/extractor/youtube.py

@@ -33,6 +33,7 @@ from ..utils import (
     uppercase_escape,
 )
 
+
 class YoutubeBaseInfoExtractor(InfoExtractor):
     """Provide base functions for Youtube extractors"""
     _LOGIN_URL = 'https://accounts.google.com/ServiceLogin'
@@ -180,8 +181,10 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
             'next_url': '/',
             'action_confirm': 'Confirm',
         }
-        req = compat_urllib_request.Request(self._AGE_URL,
-            compat_urllib_parse.urlencode(age_form).encode('ascii'))
+        req = compat_urllib_request.Request(
+            self._AGE_URL,
+            compat_urllib_parse.urlencode(age_form).encode('ascii')
+        )
 
         self._download_webpage(
             req, None,
@@ -406,6 +409,19 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
                 'format': '141',
             },
         },
+        # Controversy video
+        {
+            'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8',
+            'info_dict': {
+                'id': 'T4XJQO3qol8',
+                'ext': 'mp4',
+                'upload_date': '20100909',
+                'uploader': 'The Amazing Atheist',
+                'uploader_id': 'TheAmazingAtheist',
+                'title': 'Burning Everyone\'s Koran',
+                'description': 'SUBSCRIBE: http://www.youtube.com/saturninefilms\n\nEven Obama has taken a stand against freedom on this issue: http://www.huffingtonpost.com/2010/09/09/obama-gma-interview-quran_n_710282.html',
+            }
+        }
     ]
 
     def __init__(self, *args, **kwargs):
@@ -638,6 +654,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
 
     def _extract_from_m3u8(self, manifest_url, video_id):
         url_map = {}
+
         def _get_urls(_manifest):
             lines = _manifest.split('\n')
             urls = filter(lambda l: l and not l.startswith('#'),
@@ -666,7 +683,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
         video_id = self.extract_id(url)
 
         # Get video webpage
-        url = proto + '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id
+        url = proto + '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1&bpctr=9999999999' % video_id
         pref_cookies = [
             c for c in self._downloader.cookiejar
             if c.domain == '.youtube.com' and c.name == 'PREF']
@@ -961,6 +978,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
                     dash_manifest_url = video_info.get('dashmpd')[0]
                 else:
                     dash_manifest_url = ytplayer_config['args']['dashmpd']
+
                 def decrypt_sig(mobj):
                     s = mobj.group(1)
                     dec_s = self._decrypt_signature(s, video_id, player_url, age_gate)
@@ -1020,6 +1038,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
             'formats': formats,
         }
 
+
 class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
     IE_DESC = 'YouTube.com playlists'
     _VALID_URL = r"""(?x)(?:
@@ -1320,8 +1339,10 @@ class YoutubeUserIE(InfoExtractor):
         # Don't return True if the url can be extracted with other youtube
         # extractor, the regex would is too permissive and it would match.
         other_ies = iter(klass for (name, klass) in globals().items() if name.endswith('IE') and klass is not cls)
-        if any(ie.suitable(url) for ie in other_ies): return False
-        else: return super(YoutubeUserIE, cls).suitable(url)
+        if any(ie.suitable(url) for ie in other_ies):
+            return False
+        else:
+            return super(YoutubeUserIE, cls).suitable(url)
 
     def _real_extract(self, url):
         # Extract username
@@ -1544,29 +1565,33 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
             paging = mobj.group('paging')
         return self.playlist_result(feed_entries, playlist_title=self._PLAYLIST_TITLE)
 
+
 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
-    IE_DESC = 'YouTube.com recommended videos, "ytrec" keyword (requires authentication)'
+    IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)'
     _VALID_URL = r'https?://www\.youtube\.com/feed/recommended|:ytrec(?:ommended)?'
     _FEED_NAME = 'recommended'
     _PLAYLIST_TITLE = 'Youtube Recommended videos'
 
+
 class YoutubeWatchLaterIE(YoutubeFeedsInfoExtractor):
-    IE_DESC = 'Youtube watch later list, "ytwatchlater" keyword (requires authentication)'
+    IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)'
     _VALID_URL = r'https?://www\.youtube\.com/feed/watch_later|:ytwatchlater'
     _FEED_NAME = 'watch_later'
     _PLAYLIST_TITLE = 'Youtube Watch Later'
     _PERSONAL_FEED = True
 
+
 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
-    IE_DESC = 'Youtube watch history, "ythistory" keyword (requires authentication)'
+    IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)'
     _VALID_URL = 'https?://www\.youtube\.com/feed/history|:ythistory'
     _FEED_NAME = 'history'
     _PERSONAL_FEED = True
     _PLAYLIST_TITLE = 'Youtube Watch History'
 
+
 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
     IE_NAME = 'youtube:favorites'
-    IE_DESC = 'YouTube.com favourite videos, "ytfav" keyword (requires authentication)'
+    IE_DESC = 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)'
     _VALID_URL = r'https?://www\.youtube\.com/my_favorites|:ytfav(?:ou?rites)?'
     _LOGIN_REQUIRED = True
 

youtube_dl/extractor/zingmp3.py

@@ -0,0 +1,107 @@
+# coding=utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class ZingMp3BaseInfoExtractor(InfoExtractor):
+
+    @staticmethod
+    def _extract_item(item):
+        title = item.find('./title').text.strip()
+        source = item.find('./source').text
+        extension = item.attrib['type']
+        thumbnail = item.find('./backimage').text
+
+        return {
+            'title': title,
+            'url': source,
+            'ext': extension,
+            'thumbnail': thumbnail,
+        }
+
+    def _extract_player_xml(self, player_xml_url, id, playlist_title=None):
+        player_xml = self._download_xml(player_xml_url, id, 'Downloading Player XML')
+        items = player_xml.findall('./item')
+
+        if len(items) == 1:
+            # one single song
+            data = self._extract_item(items[0])
+            data['id'] = id
+
+            return data
+        else:
+            # playlist of songs
+            entries = []
+
+            for i, item in enumerate(items, 1):
+                entry = self._extract_item(item)
+                entry['id'] = '%s-%d' % (id, i)
+                entries.append(entry)
+
+            return {
+                '_type': 'playlist',
+                'id': id,
+                'title': playlist_title,
+                'entries': entries,
+            }
+
+
+class ZingMp3SongIE(ZingMp3BaseInfoExtractor):
+    _VALID_URL = r'https?://mp3\.zing\.vn/bai-hat/(?P<slug>[^/]+)/(?P<song_id>\w+)\.html'
+    _TESTS = [{
+        'url': 'http://mp3.zing.vn/bai-hat/Xa-Mai-Xa-Bao-Thy/ZWZB9WAB.html',
+        'md5': 'ead7ae13693b3205cbc89536a077daed',
+        'info_dict': {
+            'id': 'ZWZB9WAB',
+            'title': 'Xa Mãi Xa',
+            'ext': 'mp3',
+            'thumbnail': 're:^https?://.*\.jpg$',
+        },
+    }]
+    IE_NAME = 'zingmp3:song'
+    IE_DESC = 'mp3.zing.vn songs'
+
+    def _real_extract(self, url):
+        matched = re.match(self._VALID_URL, url)
+        slug = matched.group('slug')
+        song_id = matched.group('song_id')
+
+        webpage = self._download_webpage(
+            'http://mp3.zing.vn/bai-hat/%s/%s.html' % (slug, song_id), song_id)
+
+        player_xml_url = self._search_regex(
+            r'&amp;xmlURL=(?P<xml_url>[^&]+)&', webpage, 'player xml url')
+
+        return self._extract_player_xml(player_xml_url, song_id)
+
+
+class ZingMp3AlbumIE(ZingMp3BaseInfoExtractor):
+    _VALID_URL = r'https?://mp3\.zing\.vn/album/(?P<slug>[^/]+)/(?P<album_id>\w+)\.html'
+    _TESTS = [{
+        'url': 'http://mp3.zing.vn/album/Lau-Dai-Tinh-Ai-Bang-Kieu-Minh-Tuyet/ZWZBWDAF.html',
+        'info_dict': {
+            '_type': 'playlist',
+            'id': 'ZWZBWDAF',
+            'title': 'Lâu Đài Tình Ái - Bằng Kiều ft. Minh Tuyết | Album 320 lossless',
+        },
+        'playlist_count': 10,
+    }]
+    IE_NAME = 'zingmp3:album'
+    IE_DESC = 'mp3.zing.vn albums'
+
+    def _real_extract(self, url):
+        matched = re.match(self._VALID_URL, url)
+        slug = matched.group('slug')
+        album_id = matched.group('album_id')
+
+        webpage = self._download_webpage(
+            'http://mp3.zing.vn/album/%s/%s.html' % (slug, album_id), album_id)
+        player_xml_url = self._search_regex(
+            r'&amp;xmlURL=(?P<xml_url>[^&]+)&', webpage, 'player xml url')
+
+        return self._extract_player_xml(
+            player_xml_url, album_id,
+            playlist_title=self._og_search_title(webpage))

youtube_dl/jsinterp.py

@@ -61,7 +61,7 @@ class JSInterpreter(object):
             pass
 
         m = re.match(
-            r'^(?P<var>[a-zA-Z0-9_]+)\.(?P<member>[^(]+)(?:\(+(?P<args>[^()]*)\))?$',
+            r'^(?P<var>[$a-zA-Z0-9_]+)\.(?P<member>[^(]+)(?:\(+(?P<args>[^()]*)\))?$',
             expr)
         if m:
             variable = m.group('var')

youtube_dl/options.py

@@ -262,7 +262,8 @@ 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'
+        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'
@@ -271,7 +272,7 @@ def parseOpts(overrideArguments=None):
             ' -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.')
+            ' avconv), for example -f bestvideo+bestaudio.'))
     video_format.add_option(
         '--all-formats',
         action='store_const', dest='format', const='all',

youtube_dl/postprocessor/execafterdownload.py

@@ -26,4 +26,3 @@ class ExecAfterDownloadPP(PostProcessor):
                 'Command returned error code %d' % retCode)
 
         return None, information  # by default, keep file and do nothing
-

youtube_dl/postprocessor/xattrpp.py

@@ -108,4 +108,3 @@ class XAttrMetadataPP(PostProcessor):
         except (subprocess.CalledProcessError, OSError):
             self._downloader.report_error("This filesystem doesn't support extended attributes. (You may have to enable them in your /etc/fstab)")
             return False, info
-

youtube_dl/swfinterp.py

@@ -827,4 +827,3 @@ class SWFInterpreter(object):
 
         avm_class.method_pyfunctions[func_name] = resfunc
         return resfunc
-

youtube_dl/update.py

@@ -13,13 +13,17 @@ from .utils import (
 )
 from .version import __version__
 
+
 def rsa_verify(message, signature, key):
     from struct import pack
     from hashlib import sha256
     from sys import version_info
+
     def b(x):
-        if version_info[0] == 2: return x
-        else: return x.encode('latin1')
+        if version_info[0] == 2:
+            return x
+        else:
+            return x.encode('latin1')
     assert(type(message) == type(b('')))
     block_size = 0
     n = key[0]
@@ -32,13 +36,17 @@ def rsa_verify(message, signature, key):
         raw_bytes.insert(0, pack("B", signature & 0xFF))
         signature >>= 8
     signature = (block_size - len(raw_bytes)) * b('\x00') + b('').join(raw_bytes)
-    if signature[0:2] != b('\x00\x01'): return False
+    if signature[0:2] != b('\x00\x01'):
+        return False
     signature = signature[2:]
-    if not b('\x00') in signature: return False
+    if not b('\x00') in signature:
+        return False
     signature = signature[signature.index(b('\x00')) + 1:]
-    if not signature.startswith(b('\x30\x31\x30\x0D\x06\x09\x60\x86\x48\x01\x65\x03\x04\x02\x01\x05\x00\x04\x20')): return False
+    if not signature.startswith(b('\x30\x31\x30\x0D\x06\x09\x60\x86\x48\x01\x65\x03\x04\x02\x01\x05\x00\x04\x20')):
+        return False
     signature = signature[19:]
-    if signature != sha256(message).digest(): return False
+    if signature != sha256(message).digest():
+        return False
     return True
 
 
@@ -58,7 +66,8 @@ def update_self(to_screen, verbose):
     try:
         newversion = compat_urllib_request.urlopen(VERSION_URL).read().decode('utf-8').strip()
     except:
-        if verbose: to_screen(compat_str(traceback.format_exc()))
+        if verbose:
+            to_screen(compat_str(traceback.format_exc()))
         to_screen(u'ERROR: can\'t find the current version. Please try again later.')
         return
     if newversion == __version__:
@@ -70,7 +79,8 @@ def update_self(to_screen, verbose):
         versions_info = compat_urllib_request.urlopen(JSON_URL).read().decode('utf-8')
         versions_info = json.loads(versions_info)
     except:
-        if verbose: to_screen(compat_str(traceback.format_exc()))
+        if verbose:
+            to_screen(compat_str(traceback.format_exc()))
         to_screen(u'ERROR: can\'t obtain versions info. Please try again later.')
         return
     if not 'signature' in versions_info:
@@ -118,7 +128,8 @@ def update_self(to_screen, verbose):
             newcontent = urlh.read()
             urlh.close()
         except (IOError, OSError):
-            if verbose: to_screen(compat_str(traceback.format_exc()))
+            if verbose:
+                to_screen(compat_str(traceback.format_exc()))
             to_screen(u'ERROR: unable to download latest version')
             return
 
@@ -131,7 +142,8 @@ def update_self(to_screen, verbose):
             with open(exe + '.new', 'wb') as outf:
                 outf.write(newcontent)
         except (IOError, OSError):
-            if verbose: to_screen(compat_str(traceback.format_exc()))
+            if verbose:
+                to_screen(compat_str(traceback.format_exc()))
             to_screen(u'ERROR: unable to write the new version')
             return
 
@@ -150,7 +162,8 @@ start /b "" cmd /c del "%%~f0"&exit /b"
             subprocess.Popen([bat])  # Continues to run in the background
             return  # Do not show premature success messages
         except (IOError, OSError):
-            if verbose: to_screen(compat_str(traceback.format_exc()))
+            if verbose:
+                to_screen(compat_str(traceback.format_exc()))
             to_screen(u'ERROR: unable to overwrite current version')
             return
 
@@ -161,7 +174,8 @@ start /b "" cmd /c del "%%~f0"&exit /b"
             newcontent = urlh.read()
             urlh.close()
         except (IOError, OSError):
-            if verbose: to_screen(compat_str(traceback.format_exc()))
+            if verbose:
+                to_screen(compat_str(traceback.format_exc()))
             to_screen(u'ERROR: unable to download latest version')
             return
 
@@ -174,12 +188,14 @@ start /b "" cmd /c del "%%~f0"&exit /b"
             with open(filename, 'wb') as outf:
                 outf.write(newcontent)
         except (IOError, OSError):
-            if verbose: to_screen(compat_str(traceback.format_exc()))
+            if verbose:
+                to_screen(compat_str(traceback.format_exc()))
             to_screen(u'ERROR: unable to overwrite current version')
             return
 
     to_screen(u'Updated youtube-dl. Restart youtube-dl to use the new version.')
 
+
 def get_notes(versions, fromVersion):
     notes = []
     for v, vdata in sorted(versions.items()):
@@ -187,6 +203,7 @@ def get_notes(versions, fromVersion):
             notes.extend(vdata.get('notes', []))
     return notes
 
+
 def print_notes(to_screen, versions, fromVersion=__version__):
     notes = get_notes(versions, fromVersion)
     if notes:

youtube_dl/utils.py

@@ -41,6 +41,7 @@ from .compat import (
     compat_urllib_parse_urlparse,
     compat_urllib_request,
     compat_urlparse,
+    shlex_quote,
 )
 
 
@@ -55,6 +56,7 @@ std_headers = {
     'Accept-Language': 'en-us,en;q=0.5',
 }
 
+
 def preferredencoding():
     """Get preferred encoding.
 
@@ -145,6 +147,8 @@ else:
 
 # On python2.6 the xml.etree.ElementTree.Element methods don't support
 # the namespace parameter
+
+
 def xpath_with_ns(path, ns_map):
     components = [c.split(':') for c in path.split('/')]
     replaced = []
@@ -255,6 +259,7 @@ def timeconvert(timestr):
         timestamp = email.utils.mktime_tz(timetuple)
     return timestamp
 
+
 def sanitize_filename(s, restricted=False, is_id=False):
     """Sanitizes a string so it could be used as part of a filename.
     If restricted is set, use a stricter subset of allowed characters.
@@ -287,6 +292,7 @@ def sanitize_filename(s, restricted=False, is_id=False):
             result = '_'
     return result
 
+
 def orderedSet(iterable):
     """ Remove all duplicates from the input iterable """
     res = []
@@ -371,6 +377,7 @@ def decodeOption(optval):
     assert isinstance(optval, compat_str)
     return optval
 
+
 def formatSeconds(secs):
     if secs > 3600:
         return '%d:%02d:%02d' % (secs // 3600, (secs % 3600) // 60, secs % 60)
@@ -423,6 +430,7 @@ def make_HTTPS_handler(opts_no_check_certificate, **kwargs):
 
 class ExtractorError(Exception):
     """Error during info extraction."""
+
     def __init__(self, msg, tb=None, expected=False, cause=None, video_id=None):
         """ tb, if given, is the original traceback (so that it can be printed out).
         If expected is set, this is a normal error message and most likely not a bug in youtube-dl.
@@ -467,6 +475,7 @@ class DownloadError(Exception):
     configured to continue on errors. They will contain the appropriate
     error message.
     """
+
     def __init__(self, msg, exc_info=None):
         """ exc_info, if given, is the original exception that caused the trouble (as returned by sys.exc_info()). """
         super(DownloadError, self).__init__(msg)
@@ -488,9 +497,11 @@ class PostProcessingError(Exception):
     This exception may be raised by PostProcessor's .run() method to
     indicate an error in the postprocessing task.
     """
+
     def __init__(self, msg):
         self.msg = msg
 
+
 class MaxDownloadsReached(Exception):
     """ --max-downloads limit has been reached. """
     pass
@@ -520,6 +531,7 @@ class ContentTooShortError(Exception):
         self.downloaded = downloaded
         self.expected = expected
 
+
 class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
     """Handler for HTTP requests and responses.
 
@@ -680,6 +692,7 @@ def unified_strdate(date_str):
             upload_date = datetime.datetime(*timetuple[:6]).strftime('%Y%m%d')
     return upload_date
 
+
 def determine_ext(url, default_ext='unknown_video'):
     if url is None:
         return default_ext
@@ -689,9 +702,11 @@ def determine_ext(url, default_ext='unknown_video'):
     else:
         return default_ext
 
+
 def subtitles_filename(filename, sub_lang, sub_format):
     return filename.rsplit('.', 1)[0] + '.' + sub_lang + '.' + sub_format
 
+
 def date_from_str(date_str):
     """
     Return a datetime object from a string in the format YYYYMMDD or
@@ -718,6 +733,7 @@ def date_from_str(date_str):
         return today + delta
     return datetime.datetime.strptime(date_str, "%Y%m%d").date()
 
+
 def hyphenate_date(date_str):
     """
     Convert a date in 'YYYYMMDD' format to 'YYYY-MM-DD' format"""
@@ -727,8 +743,10 @@ def hyphenate_date(date_str):
     else:
         return date_str
 
+
 class DateRange(object):
     """Represents a time interval between two dates"""
+
     def __init__(self, start=None, end=None):
         """start and end must be strings in the format accepted by date"""
         if start is not None:
@@ -741,15 +759,18 @@ class DateRange(object):
             self.end = datetime.datetime.max.date()
         if self.start > self.end:
             raise ValueError('Date range: "%s" , the start date must be before the end date' % self)
+
     @classmethod
     def day(cls, day):
         """Returns a range that only contains the given day"""
         return cls(day, day)
+
     def __contains__(self, date):
         """Check if the date is in the range"""
         if not isinstance(date, datetime.date):
             date = date_from_str(date)
         return self.start <= date <= self.end
+
     def __str__(self):
         return '%s - %s' % (self.start.isoformat(), self.end.isoformat())
 
@@ -1025,6 +1046,57 @@ def format_bytes(bytes):
     return '%.2f%s' % (converted, suffix)
 
 
+def parse_filesize(s):
+    if s is None:
+        return None
+
+    # The lower-case forms are of course incorrect and inofficial,
+    # but we support those too
+    _UNIT_TABLE = {
+        'B': 1,
+        'b': 1,
+        'KiB': 1024,
+        'KB': 1000,
+        'kB': 1024,
+        'Kb': 1000,
+        'MiB': 1024 ** 2,
+        'MB': 1000 ** 2,
+        'mB': 1024 ** 2,
+        'Mb': 1000 ** 2,
+        'GiB': 1024 ** 3,
+        'GB': 1000 ** 3,
+        'gB': 1024 ** 3,
+        'Gb': 1000 ** 3,
+        'TiB': 1024 ** 4,
+        'TB': 1000 ** 4,
+        'tB': 1024 ** 4,
+        'Tb': 1000 ** 4,
+        'PiB': 1024 ** 5,
+        'PB': 1000 ** 5,
+        'pB': 1024 ** 5,
+        'Pb': 1000 ** 5,
+        'EiB': 1024 ** 6,
+        'EB': 1000 ** 6,
+        'eB': 1024 ** 6,
+        'Eb': 1000 ** 6,
+        'ZiB': 1024 ** 7,
+        'ZB': 1000 ** 7,
+        'zB': 1024 ** 7,
+        'Zb': 1000 ** 7,
+        'YiB': 1024 ** 8,
+        'YB': 1000 ** 8,
+        'yB': 1024 ** 8,
+        'Yb': 1000 ** 8,
+    }
+
+    units_re = '|'.join(re.escape(u) for u in _UNIT_TABLE)
+    m = re.match(r'(?P<num>[0-9]+(?:\.[0-9]*)?)\s*(?P<unit>%s)' % units_re, s)
+    if not m:
+        return None
+
+    return int(float(m.group('num')) * _UNIT_TABLE[m.group('unit')])
+
+
 def get_term_width():
     columns = compat_getenv('COLUMNS', None)
     if columns:
@@ -1433,3 +1505,8 @@ def ytdl_is_updateable():
     from zipimport import zipimporter
 
     return isinstance(globals().get('__loader__'), zipimporter) or hasattr(sys, 'frozen')
+
+
+def args_to_str(args):
+    # Get a short string representation for a subprocess command
+    return ' '.join(shlex_quote(a) for a in args)

youtube_dl/version.py

@@ -1,2 +1,2 @@
 
-__version__ = '2014.11.20.1'
+__version__ = '2014.11.26'