release 2014.12.12

Videos which return `is_geo_blocked' to be True can actually be downloaded from
the country to which the video is restricted

AUTHORS

@@ -82,3 +82,13 @@ Xavier Beynon
 Gabriel Schubiner
 xantares
 Jan Matějka
+Mauroy Sébastien
+William Sewell
+Dao Hoang Son
+Oskar Jauch
+Matthew Rayfield
+t0mm0
+Tithen-Firion
+Zack Fernandes
+cryptonaut
+Adrian Kretz

Makefile

@@ -1,7 +1,7 @@
 all: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish
 
 clean:
-	rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish *.dump *.part
+	rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish *.dump *.part *.info.json
 
 cleanall: clean
 	rm -f youtube-dl youtube-dl.exe

README.md

@@ -30,7 +30,7 @@ Alternatively, refer to the developer instructions below for how to check out an
 # DESCRIPTION
 **youtube-dl** is a small command-line program to download videos from
 YouTube.com and a few more sites. It requires the Python interpreter, version
-2.6, 2.7, or 3.3+, and it is not platform specific. It should work on
+2.6, 2.7, or 3.2+, and it is not platform specific. It should work on
 your Unix box, on Windows or on Mac OS X. It is released to the public domain,
 which means you can modify it, redistribute it or use it however you like.
 
@@ -65,10 +65,10 @@ which means you can modify it, redistribute it or use it however you like.
                                      this is not possible instead of searching.
     --ignore-config                  Do not read configuration files. When given
                                      in the global configuration file /etc
-                                     /youtube-dl.conf: do not read the user
-                                     configuration in ~/.config/youtube-dl.conf
-                                     (%APPDATA%/youtube-dl/config.txt on
-                                     Windows)
+                                     /youtube-dl.conf: Do not read the user
+                                     configuration in ~/.config/youtube-
+                                     dl/config (%APPDATA%/youtube-dl/config.txt
+                                     on Windows)
     --flat-playlist                  Do not extract the videos of a playlist,
                                      only list them.
 
@@ -93,7 +93,8 @@ which means you can modify it, redistribute it or use it however you like.
                                      COUNT views
     --max-views COUNT                Do not download any videos with more than
                                      COUNT views
-    --no-playlist                    download only the currently playing video
+    --no-playlist                    If the URL refers to a video and a
+                                     playlist, download only the video.
     --age-limit YEARS                download only videos suitable for the given
                                      age
     --download-archive FILE          Download only videos not listed in the
@@ -492,14 +493,15 @@ 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

@@ -1,4 +1,6 @@
 #!/usr/bin/env python
+from __future__ import unicode_literals
+
 import os
 from os.path import dirname as dirn
 import sys
@@ -9,6 +11,7 @@ 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/check-porn.py

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

devscripts/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/add-version.py

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

devscripts/gh-pages/generate-download.py

@@ -1,8 +1,7 @@
 #!/usr/bin/env python3
+from __future__ import unicode_literals
+
 import hashlib
-import shutil
-import subprocess
-import tempfile
 import urllib.request
 import json
 

devscripts/gh-pages/sign-versions.py

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

devscripts/gh-pages/update-copyright.py

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

devscripts/gh-pages/update-feed.py

@@ -1,4 +1,5 @@
 #!/usr/bin/env python3
+from __future__ import unicode_literals
 
 import datetime
 import io
@@ -73,4 +74,3 @@ 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

@@ -1,4 +1,5 @@
 #!/usr/bin/env python3
+from __future__ import unicode_literals
 
 import sys
 import os
@@ -9,6 +10,7 @@ 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 +23,7 @@ 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/make_readme.py

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

devscripts/prepare_manpage.py

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

devscripts/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')

devscripts/zsh-completion.py

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

setup.py

@@ -4,7 +4,6 @@
 from __future__ import print_function
 
 import os.path
-import pkg_resources
 import warnings
 import sys
 
@@ -103,7 +102,9 @@ setup(
         "Programming Language :: Python :: 2.6",
         "Programming Language :: Python :: 2.7",
         "Programming Language :: Python :: 3",
-        "Programming Language :: Python :: 3.3"
+        "Programming Language :: Python :: 3.2",
+        "Programming Language :: Python :: 3.3",
+        "Programming Language :: Python :: 3.4",
     ],
 
     **params

test/helper.py

@@ -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)
 
@@ -139,7 +141,7 @@ def expect_info_dict(self, expected_dict, got_dict):
     if missing_keys:
         def _repr(v):
             if isinstance(v, compat_str):
-                return "'%s'" % v.replace('\\', '\\\\').replace("'", "\\'")
+                return "'%s'" % v.replace('\\', '\\\\').replace("'", "\\'").replace('\n', '\\n')
             else:
                 return repr(v)
         info_dict_str = ''.join(

test/test_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):
@@ -90,7 +97,7 @@ def generator(test_case):
             return
         for other_ie in other_ies:
             if not other_ie.working():
-                print_skipping(u'test depends on %sIE, marked as not WORKING' % other_ie.ie_key())
+                print_skipping('test depends on %sIE, marked as not WORKING' % other_ie.ie_key())
                 return
 
         params = get_params(test_case.get('params', {}))
@@ -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
@@ -134,7 +143,7 @@ def generator(test_case):
                         raise
 
                     if try_num == RETRIES:
-                        report_warning(u'Failed due to network errors, skipping...')
+                        report_warning('Failed due to network errors, skipping...')
                         return
 
                     print('Retrying: {0} failed tries\n\n##########\n\n'.format(try_num))
@@ -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)
@@ -237,7 +238,7 @@ class TestVimeoSubtitles(BaseTestSubtitles):
     def test_subtitles(self):
         self.DL.params['writesubtitles'] = True
         subtitles = self.getSubtitles()
-        self.assertEqual(md5(subtitles['en']), '8062383cf4dec168fc40a088aa6d5888')
+        self.assertEqual(md5(subtitles['en']), '26399116d23ae3cf2c087cea94bc43b4')
 
     def test_subtitles_lang(self):
         self.DL.params['writesubtitles'] = True

test/test_unicode_literals.py

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

test/test_utils.py

@@ -45,8 +45,10 @@ from youtube_dl.utils import (
     escape_rfc3986,
     escape_url,
     js_to_json,
-    get_filesystem_encoding,
     intlist_to_bytes,
+    args_to_str,
+    parse_filesize,
+    version_tuple,
 )
 
 
@@ -142,6 +144,9 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
         self.assertEqual(unified_strdate('1968-12-10'), '19681210')
         self.assertEqual(unified_strdate('28/01/2014 21:00:00 +0100'), '20140128')
+        self.assertEqual(
+            unified_strdate('11/26/2014 11:30:00 AM PST', day_first=False),
+            '20141126')
 
     def test_find_xpath_attr(self):
         testxml = '''<root>
@@ -170,7 +175,7 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(find('media:song/url').text, 'http://server.com/download.mp3')
 
     def test_smuggle_url(self):
-        data = {u"ö": u"ö", u"abc": [3]}
+        data = {"ö": "ö", "abc": [3]}
         url = 'https://foo.bar/baz?x=y#a'
         smug_url = smuggle_url(url, data)
         unsmug_url, unsmug_data = unsmuggle_url(smug_url)
@@ -219,6 +224,9 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(parse_duration('0s'), 0)
         self.assertEqual(parse_duration('01:02:03.05'), 3723.05)
         self.assertEqual(parse_duration('T30M38S'), 1838)
+        self.assertEqual(parse_duration('5 s'), 5)
+        self.assertEqual(parse_duration('3 min'), 180)
+        self.assertEqual(parse_duration('2.5 hours'), 9000)
 
     def test_fix_xml_ampersands(self):
         self.assertEqual(
@@ -361,5 +369,26 @@ 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)
+        self.assertEqual(parse_filesize('1,24 KB'), 1240)
+
+    def test_version_tuple(self):
+        self.assertEqual(version_tuple('1'), (1,))
+        self.assertEqual(version_tuple('10.23.344'), (10, 23, 344))
+        self.assertEqual(version_tuple('10.1-6'), (10, 1, 6))  # avconv style
+
 if __name__ == '__main__':
     unittest.main()

test/test_write_annotations.py

@@ -1,5 +1,6 @@
 #!/usr/bin/env python
 # coding: utf-8
+from __future__ import unicode_literals
 
 # Allow direct execution
 import os
@@ -31,17 +32,16 @@ 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 +71,6 @@ 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_write_info_json.py

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

test/test_youtube_lists.py

@@ -1,4 +1,5 @@
 #!/usr/bin/env python
+from __future__ import unicode_literals
 
 # Allow direct execution
 import os
@@ -12,10 +13,6 @@ from test.helper import FakeYDL
 from youtube_dl.extractor import (
     YoutubePlaylistIE,
     YoutubeIE,
-    YoutubeChannelIE,
-    YoutubeShowIE,
-    YoutubeTopListIE,
-    YoutubeSearchURLIE,
 )
 
 

youtube_dl/YoutubeDL.py

@@ -7,6 +7,7 @@ import collections
 import datetime
 import errno
 import io
+import itertools
 import json
 import locale
 import os
@@ -60,6 +61,7 @@ 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 +255,22 @@ 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)
@@ -604,27 +622,21 @@ class YoutubeDL(object):
                 ie_result['url'], ie_key=ie_result.get('ie_key'),
                 extra_info=extra_info, download=False, process=False)
 
-            def make_result(embedded_info):
             new_result = ie_result.copy()
-                for f in ('_type', 'url', 'ext', 'player_url', 'formats',
+            for f in ('_type', 'id', 'url', 'ext', 'player_url', 'formats',
                       'entries', 'ie_key', 'duration',
                       'subtitles', 'annotations', 'format',
                       'thumbnail', 'thumbnails'):
                 if f in new_result:
                     del new_result[f]
-                    if f in embedded_info:
-                        new_result[f] = embedded_info[f]
-                return new_result
-            new_result = make_result(info)
+                if f in info:
+                    new_result[f] = info[f]
 
             assert new_result.get('_type') != 'url_transparent'
-            if new_result.get('_type') == 'compat_list':
-                new_result['entries'] = [
-                    make_result(e) for e in new_result['entries']]
 
             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)
@@ -637,21 +649,28 @@ class YoutubeDL(object):
             if playlistend == -1:
                 playlistend = None
 
-            if isinstance(ie_result['entries'], list):
-                n_all_entries = len(ie_result['entries'])
-                entries = ie_result['entries'][playliststart:playlistend]
+            ie_entries = ie_result['entries']
+            if isinstance(ie_entries, list):
+                n_all_entries = len(ie_entries)
+                entries = ie_entries[playliststart:playlistend]
                 n_entries = len(entries)
                 self.to_screen(
                     "[%s] playlist %s: Collected %d video ids (downloading %d of them)" %
                     (ie_result['extractor'], playlist, n_all_entries, n_entries))
-            else:
-                assert isinstance(ie_result['entries'], PagedList)
-                entries = ie_result['entries'].getslice(
+            elif isinstance(ie_entries, PagedList):
+                entries = ie_entries.getslice(
                     playliststart, playlistend)
                 n_entries = len(entries)
                 self.to_screen(
                     "[%s] playlist %s: Downloading %d videos" %
                     (ie_result['extractor'], playlist, n_entries))
+            else:  # iterable
+                entries = list(itertools.islice(
+                    ie_entries, playliststart, playlistend))
+                n_entries = len(entries)
+                self.to_screen(
+                    "[%s] playlist %s: Downloading %d videos" %
+                    (ie_result['extractor'], playlist, n_entries))
 
             for i, entry in enumerate(entries, 1):
                 self.to_screen('[download] Downloading video #%s of %s' % (i, n_entries))
@@ -679,14 +698,20 @@ 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)
@@ -764,6 +789,10 @@ class YoutubeDL(object):
             info_dict['display_id'] = info_dict['id']
 
         if info_dict.get('upload_date') is None and info_dict.get('timestamp') is not None:
+            # Working around negative timestamps in Windows
+            # (see http://bugs.python.org/issue1646728)
+            if info_dict['timestamp'] < 0 and os.name == 'nt':
+                info_dict['timestamp'] = 0
             upload_date = datetime.datetime.utcfromtimestamp(
                 info_dict['timestamp'])
             info_dict['upload_date'] = upload_date.strftime('%Y%m%d')
@@ -907,6 +936,10 @@ class YoutubeDL(object):
         if self.params.get('forceid', False):
             self.to_stdout(info_dict['id'])
         if self.params.get('forceurl', False):
+            if info_dict.get('requested_formats') is not None:
+                for f in info_dict['requested_formats']:
+                    self.to_stdout(f['url'] + f.get('play_path', ''))
+            else:
                 # For RTMP URLs, also include the playpath
                 self.to_stdout(info_dict['url'] + info_dict.get('play_path', ''))
         if self.params.get('forcethumbnail', False) and info_dict.get('thumbnail') is not None:

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/__main__.py

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

youtube_dl/aes.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 __all__ = ['aes_encrypt', 'key_expansion', 'aes_ctr_decrypt', 'aes_cbc_decrypt', 'aes_decrypt_text']
 
 import base64
@@ -7,6 +9,7 @@ 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 +35,7 @@ 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 +61,7 @@ def aes_cbc_decrypt(data, key, iv):
 
     return decrypted_data
 
+
 def key_expansion(data):
     """
     Generate key schedule
@@ -91,6 +96,7 @@ def key_expansion(data):
 
     return data
 
+
 def aes_encrypt(data, expanded_key):
     """
     Encrypt one block with aes
@@ -111,6 +117,7 @@ def aes_encrypt(data, expanded_key):
 
     return data
 
+
 def aes_decrypt(data, expanded_key):
     """
     Decrypt one block with aes
@@ -131,6 +138,7 @@ def aes_decrypt(data, expanded_key):
 
     return data
 
+
 def aes_decrypt_text(data, password, key_size_bytes):
     """
     Decrypt text
@@ -157,6 +165,7 @@ 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 +250,19 @@ 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 +270,17 @@ 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 +291,7 @@ 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 +299,11 @@ 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 +311,7 @@ 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 +319,7 @@ 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):
@@ -241,7 +247,7 @@ else:
                 userhome = compat_getenv('HOME')
             elif 'USERPROFILE' in os.environ:
                 userhome = compat_getenv('USERPROFILE')
-            elif not 'HOMEPATH' in os.environ:
+            elif 'HOMEPATH' not in os.environ:
                 return path
             else:
                 try:
@@ -264,7 +270,7 @@ if sys.version_info < (3, 0):
         print(s.encode(preferredencoding(), 'xmlcharrefreplace'))
 else:
     def compat_print(s):
-        assert type(s) == type(u'')
+        assert isinstance(s, compat_str)
         print(s)
 
 
@@ -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

@@ -4,6 +4,7 @@ import os
 import re
 import subprocess
 
+from ..postprocessor.ffmpeg import FFmpegPostProcessor
 from .common import FileDownloader
 from ..utils import (
     compat_urlparse,
@@ -28,14 +29,17 @@ class HlsFD(FileDownloader):
             if check_executable(program, ['-version']):
                 break
         else:
-            self.report_error(u'm3u8 download detected but ffmpeg or avconv could not be found. Please install one.')
+            self.report_error('m3u8 download detected but ffmpeg or avconv could not be found. Please install one.')
             return False
         cmd = [program] + args
 
+        ffpp = FFmpegPostProcessor(downloader=self)
+        ffpp.check_version()
+
         retval = subprocess.call(cmd)
         if retval == 0:
             fsize = os.path.getsize(encodeFilename(tmpfilename))
-            self.to_screen(u'\r[%s] %s bytes' % (cmd[0], fsize))
+            self.to_screen('\r[%s] %s bytes' % (cmd[0], fsize))
             self.try_rename(tmpfilename, filename)
             self._hook_progress({
                 'downloaded_bytes': fsize,
@@ -45,8 +49,8 @@ class HlsFD(FileDownloader):
             })
             return True
         else:
-            self.to_stderr(u"\n")
-            self.report_error(u'%s exited with code %d' % (program, retval))
+            self.to_stderr('\n')
+            self.report_error('%s exited with code %d' % (program, retval))
             return False
 
 
@@ -101,4 +105,3 @@ class NativeHlsFD(FileDownloader):
         })
         self.try_rename(tmpfilename, filename)
         return True
-

youtube_dl/downloader/http.py

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

youtube_dl/downloader/mplayer.py

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

youtube_dl/extractor/__init__.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 from .abc import ABCIE
 from .academicearth import AcademicEarthCourseIE
 from .addanime import AddAnimeIE
@@ -22,19 +24,23 @@ from .arte import (
 )
 from .audiomack import AudiomackIE
 from .auengine import AUEngineIE
+from .azubu import AzubuIE
 from .bambuser import BambuserIE, BambuserChannelIE
 from .bandcamp import BandcampIE, BandcampAlbumIE
 from .bbccouk import BBCCoUkIE
 from .beeg import BeegIE
 from .behindkink import BehindKinkIE
+from .bet import BetIE
 from .bild import BildIE
 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
+from .buzzfeed import BuzzFeedIE
 from .byutv import BYUtvIE
 from .c56 import C56IE
 from .canal13cl import Canal13clIE
@@ -45,7 +51,7 @@ from .cbsnews import CBSNewsIE
 from .ceskatelevize import CeskaTelevizeIE
 from .channel9 import Channel9IE
 from .chilloutzone import ChilloutzoneIE
-from .cinemassacre import CinemassacreIE
+from .cinchcast import CinchcastIE
 from .clipfish import ClipfishIE
 from .cliphunter import CliphunterIE
 from .clipsyndicate import ClipsyndicateIE
@@ -115,7 +121,10 @@ from .fktv import (
     FKTVPosteckeIE,
 )
 from .flickr import FlickrIE
+from .folketinget import FolketingetIE
 from .fourtube import FourTubeIE
+from .foxgay import FoxgayIE
+from .foxnews import FoxNewsIE
 from .franceculture import FranceCultureIE
 from .franceinter import FranceInterIE
 from .francetv import (
@@ -211,6 +220,7 @@ from .mdr import MDRIE
 from .metacafe import MetacafeIE
 from .metacritic import MetacriticIE
 from .mgoon import MgoonIE
+from .minhateca import MinhatecaIE
 from .ministrygrid import MinistryGridIE
 from .mit import TechTVMITIE, MITIE, OCWMITIE
 from .mitele import MiTeleIE
@@ -237,9 +247,10 @@ from .muenchentv import MuenchenTVIE
 from .musicplayon import MusicPlayOnIE
 from .musicvault import MusicVaultIE
 from .muzu import MuzuTVIE
-from .myspace import MySpaceIE
+from .myspace import MySpaceIE, MySpaceAlbumIE
 from .myspass import MySpassIE
 from .myvideo import MyVideoIE
+from .myvidster import MyVidsterIE
 from .naver import NaverIE
 from .nba import NBAIE
 from .nbc import (
@@ -297,6 +308,7 @@ from .promptfile import PromptFileIE
 from .prosiebensat1 import ProSiebenSat1IE
 from .pyvideo import PyvideoIE
 from .quickvid import QuickVidIE
+from .radiode import RadioDeIE
 from .radiofrance import RadioFranceIE
 from .rai import RaiIE
 from .rbmaradio import RBMARadioIE
@@ -324,6 +336,7 @@ from .savefrom import SaveFromIE
 from .sbs import SBSIE
 from .scivee import SciVeeIE
 from .screencast import ScreencastIE
+from .screenwavemedia import CinemassacreIE, ScreenwaveMediaIE, TeamFourIE
 from .servingsys import ServingSysIE
 from .sexu import SexuIE
 from .sexykarma import SexyKarmaIE
@@ -371,6 +384,7 @@ 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 +393,7 @@ 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 +405,7 @@ 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,
@@ -403,11 +419,13 @@ 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
 from .tvp import TvpIE
 from .tvplay import TVPlayIE
+from .twentyfourvideo import TwentyFourVideoIE
 from .twitch import TwitchIE
 from .ubu import UbuIE
 from .udemy import (
@@ -452,7 +470,10 @@ 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 +497,7 @@ 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
@@ -505,7 +527,11 @@ from .youtube import (
     YoutubeUserIE,
     YoutubeWatchLaterIE,
 )
-from .zdf import ZDFIE
+from .zdf import ZDFIE, ZDFChannelIE
+from .zingmp3 import (
+    ZingMp3SongIE,
+    ZingMp3AlbumIE,
+)
 
 _ALL_CLASSES = [
     klass

youtube_dl/extractor/academicearth.py

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

youtube_dl/extractor/addanime.py

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

youtube_dl/extractor/adultswim.py

@@ -2,122 +2,147 @@
 from __future__ import unicode_literals
 
 import re
+import json
 
 from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+)
+
 
 class AdultSwimIE(InfoExtractor):
-    _VALID_URL = r'https?://video\.adultswim\.com/(?P<path>.+?)(?:\.html)?(?:\?.*)?(?:#.*)?$'
-    _TEST = {
-        'url': 'http://video.adultswim.com/rick-and-morty/close-rick-counters-of-the-rick-kind.html?x=y#title',
+    _VALID_URL = r'https?://(?:www\.)?adultswim\.com/videos/(?P<is_playlist>playlists/)?(?P<show_path>[^/]+)/(?P<episode_path>[^/?#]+)/?'
+
+    _TESTS = [{
+        'url': 'http://adultswim.com/videos/rick-and-morty/pilot',
         'playlist': [
             {
-                'md5': '4da359ec73b58df4575cd01a610ba5dc',
+                'md5': '247572debc75c7652f253c8daa51a14d',
                 'info_dict': {
-                    'id': '8a250ba1450996e901453d7f02ca02f5',
+                    'id': 'rQxZvXQ4ROaSOqq-or2Mow-0',
                     'ext': 'flv',
-                    'title': 'Rick and Morty Close Rick-Counters of the Rick Kind part 1',
-                    'description': 'Rick has a run in with some old associates, resulting in a fallout with Morty. You got any chips, broh?',
-                    'uploader': 'Rick and Morty',
-                    'thumbnail': 'http://i.cdn.turner.com/asfix/repository/8a250ba13f865824013fc9db8b6b0400/thumbnail_267549017116827057.jpg'
-                }
+                    'title': 'Rick and Morty - Pilot Part 1',
+                    'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. "
+                },
             },
             {
-                'md5': 'ffbdf55af9331c509d95350bd0cc1819',
+                'md5': '77b0e037a4b20ec6b98671c4c379f48d',
                 'info_dict': {
-                    'id': '8a250ba1450996e901453d7f4bd102f6',
+                    'id': 'rQxZvXQ4ROaSOqq-or2Mow-3',
                     'ext': 'flv',
-                    'title': 'Rick and Morty Close Rick-Counters of the Rick Kind part 2',
-                    'description': 'Rick has a run in with some old associates, resulting in a fallout with Morty. You got any chips, broh?',
-                    'uploader': 'Rick and Morty',
-                    'thumbnail': 'http://i.cdn.turner.com/asfix/repository/8a250ba13f865824013fc9db8b6b0400/thumbnail_267549017116827057.jpg'
-                }
+                    'title': 'Rick and Morty - Pilot Part 4',
+                    'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. "
                 },
-            {
-                'md5': 'b92409635540304280b4b6c36bd14a0a',
-                'info_dict': {
-                    'id': '8a250ba1450996e901453d7fa73c02f7',
-                    'ext': 'flv',
-                    'title': 'Rick and Morty Close Rick-Counters of the Rick Kind part 3',
-                    'description': 'Rick has a run in with some old associates, resulting in a fallout with Morty. You got any chips, broh?',
-                    'uploader': 'Rick and Morty',
-                    'thumbnail': 'http://i.cdn.turner.com/asfix/repository/8a250ba13f865824013fc9db8b6b0400/thumbnail_267549017116827057.jpg'
-                }
             },
-            {
-                'md5': 'e8818891d60e47b29cd89d7b0278156d',
+        ],
         'info_dict': {
-                    'id': '8a250ba1450996e901453d7fc8ba02f8',
+            'title': 'Rick and Morty - Pilot',
+            'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. "
+        }
+    }, {
+        'url': 'http://www.adultswim.com/videos/playlists/american-parenting/putting-francine-out-of-business/',
+        'playlist': [
+            {
+                'md5': '2eb5c06d0f9a1539da3718d897f13ec5',
+                'info_dict': {
+                    'id': '-t8CamQlQ2aYZ49ItZCFog-0',
                     'ext': 'flv',
-                    'title': 'Rick and Morty Close Rick-Counters of the Rick Kind part 4',
-                    'description': 'Rick has a run in with some old associates, resulting in a fallout with Morty. You got any chips, broh?',
-                    'uploader': 'Rick and Morty',
-                    'thumbnail': 'http://i.cdn.turner.com/asfix/repository/8a250ba13f865824013fc9db8b6b0400/thumbnail_267549017116827057.jpg'
-                }
-            }
-        ]
+                    'title': 'American Dad - Putting Francine Out of Business',
+                    'description': 'Stan hatches a plan to get Francine out of the real estate business.Watch more American Dad on [adult swim].'
+                },
             }
+        ],
+        'info_dict': {
+            'title': 'American Dad - Putting Francine Out of Business',
+            'description': 'Stan hatches a plan to get Francine out of the real estate business.Watch more American Dad on [adult swim].'
+        },
+    }]
 
-    _video_extensions = {
-        '3500': 'flv',
-        '640': 'mp4',
-        '150': 'mp4',
-        'ipad': 'm3u8',
-        'iphone': 'm3u8'
-    }
-    _video_dimensions = {
-        '3500': (1280, 720),
-        '640': (480, 270),
-        '150': (320, 180)
-    }
+    @staticmethod
+    def find_video_info(collection, slug):
+        for video in collection.get('videos'):
+            if video.get('slug') == slug:
+                return video
+
+    @staticmethod
+    def find_collection_by_linkURL(collections, linkURL):
+        for collection in collections:
+            if collection.get('linkURL') == linkURL:
+                return collection
+
+    @staticmethod
+    def find_collection_containing_video(collections, slug):
+        for collection in collections:
+            for video in collection.get('videos'):
+                if video.get('slug') == slug:
+                    return collection, video
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        video_path = mobj.group('path')
+        show_path = mobj.group('show_path')
+        episode_path = mobj.group('episode_path')
+        is_playlist = True if mobj.group('is_playlist') else False
 
-        webpage = self._download_webpage(url, video_path)
-        episode_id = self._html_search_regex(
-            r'<link rel="video_src" href="http://i\.adultswim\.com/adultswim/adultswimtv/tools/swf/viralplayer.swf\?id=([0-9a-f]+?)"\s*/?\s*>',
-            webpage, 'episode_id')
-        title = self._og_search_title(webpage)
+        webpage = self._download_webpage(url, episode_path)
 
-        index_url = 'http://asfix.adultswim.com/asfix-svc/episodeSearch/getEpisodesByIDs?networkName=AS&ids=%s' % episode_id
-        idoc = self._download_xml(index_url, title, 'Downloading episode index', 'Unable to download episode index')
+        # Extract the value of `bootstrappedData` from the Javascript in the page.
+        bootstrappedDataJS = self._search_regex(r'var bootstrappedData = ({.*});', webpage, episode_path)
 
-        episode_el = idoc.find('.//episode')
-        show_title = episode_el.attrib.get('collectionTitle')
-        episode_title = episode_el.attrib.get('title')
-        thumbnail = episode_el.attrib.get('thumbnailUrl')
-        description = episode_el.find('./description').text.strip()
+        try:
+            bootstrappedData = json.loads(bootstrappedDataJS)
+        except ValueError as ve:
+            errmsg = '%s: Failed to parse JSON ' % episode_path
+            raise ExtractorError(errmsg, cause=ve)
+
+        # Downloading videos from a /videos/playlist/ URL needs to be handled differently.
+        # NOTE: We are only downloading one video (the current one) not the playlist
+        if is_playlist:
+            collections = bootstrappedData['playlists']['collections']
+            collection = self.find_collection_by_linkURL(collections, show_path)
+            video_info = self.find_video_info(collection, episode_path)
+
+            show_title = video_info['showTitle']
+            segment_ids = [video_info['videoPlaybackID']]
+        else:
+            collections = bootstrappedData['show']['collections']
+            collection, video_info = self.find_collection_containing_video(collections, episode_path)
+
+            show = bootstrappedData['show']
+            show_title = show['title']
+            segment_ids = [clip['videoPlaybackID'] for clip in video_info['clips']]
+
+        episode_id = video_info['id']
+        episode_title = video_info['title']
+        episode_description = video_info['description']
+        episode_duration = video_info.get('duration')
 
         entries = []
-        segment_els = episode_el.findall('./segments/segment')
+        for part_num, segment_id in enumerate(segment_ids):
+            segment_url = 'http://www.adultswim.com/videos/api/v0/assets?id=%s&platform=mobile' % segment_id
 
-        for part_num, segment_el in enumerate(segment_els):
-            segment_id = segment_el.attrib.get('id')
-            segment_title = '%s %s part %d' % (show_title, episode_title, part_num + 1)
-            thumbnail = segment_el.attrib.get('thumbnailUrl')
-            duration = segment_el.attrib.get('duration')
+            segment_title = '%s - %s' % (show_title, episode_title)
+            if len(segment_ids) > 1:
+                segment_title += ' Part %d' % (part_num + 1)
 
-            segment_url = 'http://asfix.adultswim.com/asfix-svc/episodeservices/getCvpPlaylist?networkName=AS&id=%s' % segment_id
             idoc = self._download_xml(
                 segment_url, segment_title,
                 'Downloading segment information', 'Unable to download segment information')
 
+            segment_duration = idoc.find('.//trt').text.strip()
+
             formats = []
             file_els = idoc.findall('.//files/file')
 
             for file_el in file_els:
                 bitrate = file_el.attrib.get('bitrate')
-                type = file_el.attrib.get('type')
-                width, height = self._video_dimensions.get(bitrate, (None, None))
+                ftype = file_el.attrib.get('type')
+
                 formats.append({
-                    'format_id': '%s-%s' % (bitrate, type),
-                    'url': file_el.text,
-                    'ext': self._video_extensions.get(bitrate, 'mp4'),
+                    'format_id': '%s_%s' % (bitrate, ftype),
+                    'url': file_el.text.strip(),
                     # The bitrate may not be a number (for example: 'iphone')
                     'tbr': int(bitrate) if bitrate.isdigit() else None,
-                    'height': height,
-                    'width': width
+                    'quality': 1 if ftype == 'hd' else -1
                 })
 
             self._sort_formats(formats)
@@ -126,18 +151,16 @@ class AdultSwimIE(InfoExtractor):
                 'id': segment_id,
                 'title': segment_title,
                 'formats': formats,
-                'uploader': show_title,
-                'thumbnail': thumbnail,
-                'duration': duration,
-                'description': description
+                'duration': segment_duration,
+                'description': episode_description
             })
 
         return {
             '_type': 'playlist',
             'id': episode_id,
-            'display_id': video_path,
+            'display_id': episode_path,
             'entries': entries,
-            'title': '%s %s' % (show_title, episode_title),
-            'description': description,
-            'thumbnail': thumbnail
+            'title': '%s - %s' % (show_title, episode_title),
+            'description': episode_description,
+            'duration': episode_duration
         }

youtube_dl/extractor/aparat.py

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

youtube_dl/extractor/appletrailers.py

@@ -70,15 +70,17 @@ 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)
-            s = '<html>' + s + u'</html>'
+            s = '<html>%s</html>' % s
             return s
         doc = self._download_xml(playlist_url, movie, transform_source=fix_html)
 

youtube_dl/extractor/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/audiomack.py

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

youtube_dl/extractor/azubu.py

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

youtube_dl/extractor/bambuser.py

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

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

youtube_dl/extractor/behindkink.py

@@ -10,15 +10,15 @@ from ..utils import url_basename
 class BehindKinkIE(InfoExtractor):
     _VALID_URL = r'http://(?:www\.)?behindkink\.com/(?P<year>[0-9]{4})/(?P<month>[0-9]{2})/(?P<day>[0-9]{2})/(?P<id>[^/#?_]+)'
     _TEST = {
-        'url': 'http://www.behindkink.com/2014/08/14/ab1576-performers-voice-finally-heard-the-bill-is-killed/',
-        'md5': '41ad01222b8442089a55528fec43ec01',
+        'url': 'http://www.behindkink.com/2014/12/05/what-are-you-passionate-about-marley-blaze/',
+        'md5': '507b57d8fdcd75a41a9a7bdb7989c762',
         'info_dict': {
-            'id': '36370',
+            'id': '37127',
             'ext': 'mp4',
-            'title': 'AB1576 - PERFORMERS VOICE FINALLY HEARD - THE BILL IS KILLED!',
-            'description': 'The adult industry voice was finally heard as Assembly Bill 1576 remained\xa0 in suspense today at the Senate Appropriations Hearing. AB1576 was, among other industry damaging issues, a condom mandate...',
-            'upload_date': '20140814',
-            'thumbnail': 'http://www.behindkink.com/wp-content/uploads/2014/08/36370_AB1576_Win.jpg',
+            'title': 'What are you passionate about – Marley Blaze',
+            'description': 'md5:aee8e9611b4ff70186f752975d9b94b4',
+            'upload_date': '20141205',
+            'thumbnail': 'http://www.behindkink.com/wp-content/uploads/2014/12/blaze-1.jpg',
             'age_limit': 18,
         }
     }
@@ -26,26 +26,19 @@ class BehindKinkIE(InfoExtractor):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         display_id = mobj.group('id')
-        year = mobj.group('year')
-        month = mobj.group('month')
-        day = mobj.group('day')
-        upload_date = year + month + day
 
         webpage = self._download_webpage(url, display_id)
 
         video_url = self._search_regex(
-            r"'file':\s*'([^']+)'",
-            webpage, 'URL base')
-
-        video_id = url_basename(video_url)
-        video_id = video_id.split('_')[0]
+            r'<source src="([^"]+)"', webpage, 'video URL')
+        video_id = url_basename(video_url).split('_')[0]
+        upload_date = mobj.group('year') + mobj.group('month') + mobj.group('day')
 
         return {
             'id': video_id,
-            'url': video_url,
-            'ext': 'mp4',
-            'title': self._og_search_title(webpage),
             'display_id': display_id,
+            'url': video_url,
+            'title': self._og_search_title(webpage),
             'thumbnail': self._og_search_thumbnail(webpage),
             'description': self._og_search_description(webpage),
             'upload_date': upload_date,

youtube_dl/extractor/bet.py

@@ -0,0 +1,108 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_parse,
+    xpath_text,
+    xpath_with_ns,
+    int_or_none,
+    parse_iso8601,
+)
+
+
+class BetIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?bet\.com/(?:[^/]+/)+(?P<id>.+?)\.html'
+    _TESTS = [
+        {
+            'url': 'http://www.bet.com/news/politics/2014/12/08/in-bet-exclusive-obama-talks-race-and-racism.html',
+            'info_dict': {
+                'id': '417cd61c-c793-4e8e-b006-e445ecc45add',
+                'display_id': 'in-bet-exclusive-obama-talks-race-and-racism',
+                'ext': 'flv',
+                'title': 'BET News Presents: A Conversation With President Obama',
+                'description': 'md5:5a88d8ae912c1b33e090290af7ec33c6',
+                'duration': 1534,
+                'timestamp': 1418075340,
+                'upload_date': '20141208',
+                'uploader': 'admin',
+                'thumbnail': 're:(?i)^https?://.*\.jpg$',
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+        },
+        {
+            'url': 'http://www.bet.com/video/news/national/2014/justice-for-ferguson-a-community-reacts.html',
+            'info_dict': {
+                'id': '4160e53b-ad41-43b1-980f-8d85f63121f4',
+                'display_id': 'justice-for-ferguson-a-community-reacts',
+                'ext': 'flv',
+                'title': 'Justice for Ferguson: A Community Reacts',
+                'description': 'A BET News special.',
+                'duration': 1696,
+                'timestamp': 1416942360,
+                'upload_date': '20141125',
+                'uploader': 'admin',
+                'thumbnail': 're:(?i)^https?://.*\.jpg$',
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+        }
+    ]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        media_url = compat_urllib_parse.unquote(self._search_regex(
+            [r'mediaURL\s*:\s*"([^"]+)"', r"var\s+mrssMediaUrl\s*=\s*'([^']+)'"],
+            webpage, 'media URL'))
+
+        mrss = self._download_xml(media_url, display_id)
+
+        item = mrss.find('./channel/item')
+
+        NS_MAP = {
+            'dc': 'http://purl.org/dc/elements/1.1/',
+            'media': 'http://search.yahoo.com/mrss/',
+            'ka': 'http://kickapps.com/karss',
+        }
+
+        title = xpath_text(item, './title', 'title')
+        description = xpath_text(
+            item, './description', 'description', fatal=False)
+
+        video_id = xpath_text(item, './guid', 'video id', fatal=False)
+
+        timestamp = parse_iso8601(xpath_text(
+            item, xpath_with_ns('./dc:date', NS_MAP),
+            'upload date', fatal=False))
+        uploader = xpath_text(
+            item, xpath_with_ns('./dc:creator', NS_MAP),
+            'uploader', fatal=False)
+
+        media_content = item.find(
+            xpath_with_ns('./media:content', NS_MAP))
+        duration = int_or_none(media_content.get('duration'))
+        smil_url = media_content.get('url')
+
+        thumbnail = media_content.find(
+            xpath_with_ns('./media:thumbnail', NS_MAP)).get('url')
+
+        formats = self._extract_smil_formats(smil_url, display_id)
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'timestamp': timestamp,
+            'uploader': uploader,
+            'duration': duration,
+            'formats': formats,
+        }

youtube_dl/extractor/bliptv.py

@@ -4,13 +4,17 @@ import re
 
 from .common import InfoExtractor
 from .subtitles import SubtitlesInfoExtractor
-from ..utils import (
-    compat_urllib_request,
-    unescapeHTML,
-    parse_iso8601,
-    compat_urlparse,
-    clean_html,
+
+from ..compat import (
     compat_str,
+    compat_urllib_request,
+    compat_urlparse,
+)
+from ..utils import (
+    clean_html,
+    int_or_none,
+    parse_iso8601,
+    unescapeHTML,
 )
 
 
@@ -64,7 +68,39 @@ class BlipTVIE(SubtitlesInfoExtractor):
                 'uploader': 'redvsblue',
                 'uploader_id': '792887',
             }
+        },
+        {
+            'url': 'http://blip.tv/play/gbk766dkj4Yn',
+            'md5': 'fe0a33f022d49399a241e84a8ea8b8e3',
+            'info_dict': {
+                'id': '1749452',
+                'ext': 'mp4',
+                'upload_date': '20090208',
+                'description': 'Witness the first appearance of the Nostalgia Critic character, as Doug reviews the movie Transformers.',
+                'title': 'Nostalgia Critic: Transformers',
+                'timestamp': 1234068723,
+                'uploader': 'NostalgiaCritic',
+                'uploader_id': '246467',
             }
+        },
+        {
+            # https://github.com/rg3/youtube-dl/pull/4404
+            'note': 'Audio only',
+            'url': 'http://blip.tv/hilarios-productions/weekly-manga-recap-kingdom-7119982',
+            'md5': '76c0a56f24e769ceaab21fbb6416a351',
+            'info_dict': {
+                'id': '7103299',
+                'ext': 'flv',
+                'title': 'Weekly Manga Recap: Kingdom',
+                'description': 'And then Shin breaks the enemy line, and he's all like HWAH! And then he slices a guy and it's all like FWASHING! And... it's really hard to describe the best parts of this series without breaking down into sound effects, okay?',
+                'timestamp': 1417660321,
+                'upload_date': '20141204',
+                'uploader': 'The Rollo T',
+                'uploader_id': '407429',
+                'duration': 7251,
+                'vcodec': 'none',
+            }
+        },
     ]
 
     def _real_extract(self, url):
@@ -74,10 +110,12 @@ class BlipTVIE(SubtitlesInfoExtractor):
         # See https://github.com/rg3/youtube-dl/issues/857 and
         # https://github.com/rg3/youtube-dl/issues/4197
         if lookup_id:
-            info_page = self._download_webpage(
-                'http://blip.tv/play/%s.x?p=1' % lookup_id, lookup_id, 'Resolving lookup id')
-            video_id = self._search_regex(r'config\.id\s*=\s*"([0-9]+)', info_page, 'video_id')
-        else:
+            urlh = self._request_webpage(
+                'http://blip.tv/play/%s' % lookup_id, lookup_id, 'Resolving lookup id')
+            url = compat_urlparse.urlparse(urlh.geturl())
+            qs = compat_urlparse.parse_qs(url.query)
+            mobj = re.match(self._VALID_URL, qs['file'][0])
+
         video_id = mobj.group('id')
 
         rss = self._download_xml('http://blip.tv/rss/flash/%s' % video_id, video_id, 'Downloading video RSS')
@@ -114,7 +152,7 @@ class BlipTVIE(SubtitlesInfoExtractor):
             msg = self._download_webpage(
                 url + '?showplayer=20140425131715&referrer=http://blip.tv&mask=7&skin=flashvars&view=url',
                 video_id, 'Resolving URL for %s' % role)
-            real_url = compat_urlparse.parse_qs(msg)['message'][0]
+            real_url = compat_urlparse.parse_qs(msg.strip())['message'][0]
 
             media_type = media_content.get('type')
             if media_type == 'text/srt' or url.endswith('.srt'):
@@ -129,11 +167,11 @@ class BlipTVIE(SubtitlesInfoExtractor):
                     'url': real_url,
                     'format_id': role,
                     'format_note': media_type,
-                    'vcodec': media_content.get(blip('vcodec')),
+                    'vcodec': media_content.get(blip('vcodec')) or 'none',
                     'acodec': media_content.get(blip('acodec')),
                     'filesize': media_content.get('filesize'),
-                    'width': int(media_content.get('width')),
-                    'height': int(media_content.get('height')),
+                    'width': int_or_none(media_content.get('width')),
+                    'height': int_or_none(media_content.get('height')),
                 })
         self._sort_formats(formats)
 
@@ -166,9 +204,17 @@ 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 +225,7 @@ 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 +262,5 @@ 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/breakcom.py

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

youtube_dl/extractor/brightcove.py

@@ -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(
@@ -263,6 +265,7 @@ class BrightcoveIE(InfoExtractor):
                 url = rend['defaultURL']
                 if not url:
                     continue
+                ext = None
                 if rend['remote']:
                     url_comp = compat_urllib_parse_urlparse(url)
                     if url_comp.path.endswith('.m3u8'):
@@ -274,7 +277,7 @@ class BrightcoveIE(InfoExtractor):
                         # akamaihd.net, but they don't use f4m manifests
                         url = url.replace('control/', '') + '?&v=3.3.0&fp=13&r=FEEFJ&g=RTSJIMBMPFPB'
                         ext = 'flv'
-                else:
+                if ext is None:
                     ext = determine_ext(url)
                 size = rend.get('size')
                 formats.append({

youtube_dl/extractor/buzzfeed.py

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

youtube_dl/extractor/cbs.py

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

youtube_dl/extractor/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/cinchcast.py

@@ -0,0 +1,53 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    unified_strdate,
+    xpath_text,
+)
+
+
+class CinchcastIE(InfoExtractor):
+    _VALID_URL = r'https?://player\.cinchcast\.com/.*?assetId=(?P<id>[0-9]+)'
+    _TEST = {
+        # Actual test is run in generic, look for undergroundwellness
+        'url': 'http://player.cinchcast.com/?platformId=1&#038;assetType=single&#038;assetId=7141703',
+        'only_matching': True,
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        doc = self._download_xml(
+            'http://www.blogtalkradio.com/playerasset/mrss?assetType=single&assetId=%s' % video_id,
+            video_id)
+
+        item = doc.find('.//item')
+        title = xpath_text(item, './title', fatal=True)
+        date_str = xpath_text(
+            item, './{http://developer.longtailvideo.com/trac/}date')
+        upload_date = unified_strdate(date_str, day_first=False)
+        # duration is present but wrong
+        formats = []
+        formats.append({
+            'format_id': 'main',
+            'url': item.find(
+                './{http://search.yahoo.com/mrss/}content').attrib['url'],
+        })
+        backup_url = xpath_text(
+            item, './{http://developer.longtailvideo.com/trac/}backupContent')
+        if backup_url:
+            formats.append({
+                'preference': 2,  # seems to be more reliable
+                'format_id': 'backup',
+                'url': backup_url,
+            })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'upload_date': upload_date,
+            'formats': formats,
+        }

youtube_dl/extractor/clipfish.py

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

youtube_dl/extractor/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

@@ -13,6 +13,7 @@ import time
 import xml.etree.ElementTree
 
 from ..compat import (
+    compat_cookiejar,
     compat_http_client,
     compat_urllib_error,
     compat_urllib_parse_urlparse,
@@ -43,7 +44,11 @@ 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 +156,39 @@ 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, an iterable, or a PagedList
+    object, each element of which is a valid dictionary by this specification.
+
+    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.
+    The key "ie_key" can be set to the class name (minus the trailing "IE",
+    e.g. "Youtube") if the extractor class is known in advance.
+    Additionally, the dictionary may have any properties of the resolved entity
+    known in advance, 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 +298,11 @@ 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)
@@ -398,8 +438,9 @@ 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):
+    def playlist_result(entries, playlist_id=None, playlist_title=None, playlist_description=None):
         """Returns a playlist"""
         video_info = {'_type': 'playlist',
                       'entries': entries}
@@ -407,6 +448,8 @@ class InfoExtractor(object):
             video_info['id'] = playlist_id
         if playlist_title:
             video_info['title'] = playlist_title
+        if playlist_description:
+            video_info['description'] = playlist_description
         return video_info
 
     def _search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0, group=None):
@@ -750,6 +793,49 @@ class InfoExtractor(object):
         self._sort_formats(formats)
         return formats
 
+    # TODO: improve extraction
+    def _extract_smil_formats(self, smil_url, video_id):
+        smil = self._download_xml(
+            smil_url, video_id, 'Downloading SMIL file',
+            'Unable to download SMIL file')
+
+        base = smil.find('./head/meta').get('base')
+
+        formats = []
+        rtmp_count = 0
+        for video in smil.findall('./body/switch/video'):
+            src = video.get('src')
+            if not src:
+                continue
+            bitrate = int_or_none(video.get('system-bitrate') or video.get('systemBitrate'), 1000)
+            width = int_or_none(video.get('width'))
+            height = int_or_none(video.get('height'))
+            proto = video.get('proto')
+            if not proto:
+                if base:
+                    if base.startswith('rtmp'):
+                        proto = 'rtmp'
+                    elif base.startswith('http'):
+                        proto = 'http'
+            ext = video.get('ext')
+            if proto == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(src, video_id, ext))
+            elif proto == 'rtmp':
+                rtmp_count += 1
+                streamer = video.get('streamer') or base
+                formats.append({
+                    'url': streamer,
+                    'play_path': src,
+                    'ext': 'flv',
+                    'format_id': 'rtmp-%d' % (rtmp_count if bitrate is None else bitrate),
+                    'tbr': bitrate,
+                    'width': width,
+                    'height': height,
+                })
+        self._sort_formats(formats)
+
+        return formats
+
     def _live_title(self, name):
         """ Generate the title for a live video """
         now = datetime.datetime.now()
@@ -778,6 +864,12 @@ class InfoExtractor(object):
                 self._downloader.report_warning(msg)
         return res
 
+    def _set_cookie(self, domain, name, value, expire_time=None):
+        cookie = compat_cookiejar.Cookie(
+            0, name, value, None, None, domain, None,
+            None, '/', True, False, expire_time, '', None, None, None)
+        self._downloader.cookiejar.set_cookie(cookie)
+
 
 class SearchInfoExtractor(InfoExtractor):
     """

youtube_dl/extractor/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/eighttracks.py

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

youtube_dl/extractor/facebook.py

@@ -13,9 +13,10 @@ from ..compat import (
     compat_urllib_request,
 )
 from ..utils import (
-    urlencode_postdata,
     ExtractorError,
+    int_or_none,
     limit_length,
+    urlencode_postdata,
 )
 
 
@@ -36,7 +37,6 @@ class FacebookIE(InfoExtractor):
         'info_dict': {
             'id': '637842556329505',
             'ext': 'mp4',
-            'duration': 38,
             'title': 're:Did you know Kei Nishikori is the first Asian man to ever reach a Grand Slam',
         }
     }, {
@@ -107,9 +107,7 @@ class FacebookIE(InfoExtractor):
         self._login()
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-
+        video_id = self._match_id(url)
         url = 'https://www.facebook.com/video/video.php?v=%s' % video_id
         webpage = self._download_webpage(url, video_id)
 
@@ -149,6 +147,6 @@ class FacebookIE(InfoExtractor):
             'id': video_id,
             'title': video_title,
             'url': video_url,
-            'duration': int(video_data['video_duration']),
-            'thumbnail': video_data['thumbnail_src'],
+            'duration': int_or_none(video_data.get('video_duration')),
+            'thumbnail': video_data.get('thumbnail_src'),
         }

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/foxgay.py

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

youtube_dl/extractor/foxnews.py

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

youtube_dl/extractor/francetv.py

@@ -26,6 +26,19 @@ 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 +49,10 @@ 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/gamekings.py

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

youtube_dl/extractor/generic.py

@@ -445,6 +445,39 @@ 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.'
+            ]
+        },
+        # Cinchcast embed
+        {
+            'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
+            'info_dict': {
+                'id': '7141703',
+                'ext': 'mp3',
+                'upload_date': '20141126',
+                'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
+            }
+        },
     ]
 
     def report_following_redirect(self, new_url):
@@ -537,9 +570,9 @@ 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 +631,28 @@ 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 +753,12 @@ 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)
@@ -914,6 +971,13 @@ class GenericIE(InfoExtractor):
         if mobj is not None:
             return self.url_result(mobj.group('url'), 'SBS')
 
+        # Look for embedded Cinchcast player
+        mobj = re.search(
+            r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
+            webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'), 'Cinchcast')
+
         mobj = re.search(
             r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
             webpage)
@@ -979,7 +1043,7 @@ 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 +1089,3 @@ 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/gorillavid.py

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

youtube_dl/extractor/hotnewhiphop.py

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

youtube_dl/extractor/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/minhateca.py

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

youtube_dl/extractor/mixcloud.py

@@ -70,7 +70,7 @@ class MixcloudIE(InfoExtractor):
             raise ExtractorError('Unable to extract track url')
 
         PREFIX = (
-            r'<div class="cloudcast-play-button-container[^"]*?"'
+            r'<span class="play-button[^"]*?"'
             r'(?:\s+[a-zA-Z0-9-]+(?:="[^"]+")?)*?\s+')
         title = self._html_search_regex(
             PREFIX + r'm-title="([^"]+)"', webpage, 'title')

youtube_dl/extractor/mooshare.py

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

youtube_dl/extractor/mtv.py

@@ -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)
@@ -163,7 +164,7 @@ class MTVServicesInfoExtractor(InfoExtractor):
         if mgid is None or ':' not in mgid:
             mgid = self._search_regex(
                 [r'data-mgid="(.*?)"', r'swfobject.embedSWF\(".*?(mgid:.*?)"'],
-                webpage, u'mgid')
+                webpage, 'mgid')
         return self._get_videos_info(mgid)
 
 
@@ -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/muzu.py

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

youtube_dl/extractor/myspace.py

@@ -1,12 +1,14 @@
+# encoding: utf-8
 from __future__ import unicode_literals
 
 import re
 import json
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_str,
 )
+from ..utils import ExtractorError
 
 
 class MySpaceIE(InfoExtractor):
@@ -14,33 +16,58 @@ class MySpaceIE(InfoExtractor):
 
     _TESTS = [
         {
-            'url': 'https://myspace.com/coldplay/video/viva-la-vida/100008689',
+            'url': 'https://myspace.com/fiveminutestothestage/video/little-big-town/109594919',
             'info_dict': {
-                'id': '100008689',
+                'id': '109594919',
                 'ext': 'flv',
-                'title': 'Viva La Vida',
-                'description': 'The official Viva La Vida video, directed by Hype Williams',
-                'uploader': 'Coldplay',
-                'uploader_id': 'coldplay',
+                'title': 'Little Big Town',
+                'description': 'This country quartet was all smiles while playing a sold out show at the Pacific Amphitheatre in Orange County, California.',
+                'uploader': 'Five Minutes to the Stage',
+                'uploader_id': 'fiveminutestothestage',
             },
             'params': {
                 # rtmp download
                 'skip_download': True,
             },
         },
-        # song
+        # songs
         {
-            'url': 'https://myspace.com/spiderbags/music/song/darkness-in-my-heart-39008454-27041242',
+            'url': 'https://myspace.com/killsorrow/music/song/of-weakened-soul...-93388656-103880681',
             'info_dict': {
-                'id': '39008454',
+                'id': '93388656',
                 'ext': 'flv',
-                'title': 'Darkness In My Heart',
-                'uploader_id': 'spiderbags',
+                'title': 'Of weakened soul...',
+                'uploader': 'Killsorrow',
+                'uploader_id': 'killsorrow',
             },
             'params': {
                 # rtmp download
                 'skip_download': True,
             },
+        }, {
+            'add_ie': ['Vevo'],
+            'url': 'https://myspace.com/threedaysgrace/music/song/animal-i-have-become-28400208-28218041',
+            'info_dict': {
+                'id': 'USZM20600099',
+                'ext': 'mp4',
+                'title': 'Animal I Have Become',
+                'uploader': 'Three Days Grace',
+                'timestamp': int,
+                'upload_date': '20060502',
+            },
+            'skip': 'VEVO is only available in some countries',
+        }, {
+            'add_ie': ['Youtube'],
+            'url': 'https://myspace.com/starset2/music/song/first-light-95799905-106964426',
+            'info_dict': {
+                'id': 'ypWvQgnJrSU',
+                'ext': 'mp4',
+                'title': 'Starset - First Light',
+                'description': 'md5:2d5db6c9d11d527683bcda818d332414',
+                'uploader': 'Jacob Soren',
+                'uploader_id': 'SorenPromotions',
+                'upload_date': '20140725',
+            }
         },
     ]
 
@@ -48,22 +75,47 @@ class MySpaceIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
         webpage = self._download_webpage(url, video_id)
+        player_url = self._search_regex(
+            r'playerSwf":"([^"?]*)', webpage, 'player URL')
 
         if mobj.group('mediatype').startswith('music/song'):
             # songs don't store any useful info in the 'context' variable
+            song_data = self._search_regex(
+                r'''<button.*data-song-id=(["\'])%s\1.*''' % video_id,
+                webpage, 'song_data', default=None, group=0)
+            if song_data is None:
+                # some songs in an album are not playable
+                self.report_warning(
+                    '%s: No downloadable song on this page' % video_id)
+                return
+
             def search_data(name):
-                return self._search_regex(r'data-%s="(.*?)"' % name, webpage,
-                    name)
+                return self._search_regex(
+                    r'''data-%s=([\'"])(?P<data>.*?)\1''' % name,
+                    song_data, name, default='', group='data')
             streamUrl = search_data('stream-url')
+            if not streamUrl:
+                vevo_id = search_data('vevo-id')
+                youtube_id = search_data('youtube-id')
+                if vevo_id:
+                    self.to_screen('Vevo video detected: %s' % vevo_id)
+                    return self.url_result('vevo:%s' % vevo_id, ie='Vevo')
+                elif youtube_id:
+                    self.to_screen('Youtube video detected: %s' % youtube_id)
+                    return self.url_result(youtube_id, ie='Youtube')
+                else:
+                    raise ExtractorError(
+                        'Found song but don\'t know how to download it')
             info = {
                 'id': video_id,
                 'title': self._og_search_title(webpage),
+                'uploader': search_data('artist-name'),
                 'uploader_id': search_data('artist-username'),
                 'thumbnail': self._og_search_thumbnail(webpage),
             }
         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 = {
@@ -79,6 +131,50 @@ class MySpaceIE(InfoExtractor):
         info.update({
             'url': rtmp_url,
             'play_path': play_path,
+            'player_url': player_url,
             'ext': 'flv',
         })
         return info
+
+
+class MySpaceAlbumIE(InfoExtractor):
+    IE_NAME = 'MySpace:album'
+    _VALID_URL = r'https?://myspace\.com/([^/]+)/music/album/(?P<title>.*-)(?P<id>\d+)'
+
+    _TESTS = [{
+        'url': 'https://myspace.com/starset2/music/album/transmissions-19455773',
+        'info_dict': {
+            'title': 'Transmissions',
+            'id': '19455773',
+        },
+        'playlist_count': 14,
+        'skip': 'this album is only available in some countries',
+    }, {
+        'url': 'https://myspace.com/killsorrow/music/album/the-demo-18596029',
+        'info_dict': {
+            'title': 'The Demo',
+            'id': '18596029',
+        },
+        'playlist_count': 5,
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        playlist_id = mobj.group('id')
+        display_id = mobj.group('title') + playlist_id
+        webpage = self._download_webpage(url, display_id)
+        tracks_paths = re.findall(r'"music:song" content="(.*?)"', webpage)
+        if not tracks_paths:
+            raise ExtractorError(
+                '%s: No songs found, try using proxy' % display_id,
+                expected=True)
+        entries = [
+            self.url_result(t_path, ie=MySpaceIE.ie_key())
+            for t_path in tracks_paths]
+        return {
+            '_type': 'playlist',
+            'id': playlist_id,
+            'display_id': display_id,
+            'title': self._og_search_title(webpage),
+            'entries': entries,
+        }

youtube_dl/extractor/myvideo.py

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

youtube_dl/extractor/myvidster.py

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

youtube_dl/extractor/nba.py

@@ -1,7 +1,5 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 from ..utils import (
     remove_end,
@@ -10,8 +8,8 @@ from ..utils import (
 
 
 class NBAIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:watch\.|www\.)?nba\.com/(?:nba/)?video(?P<id>/[^?]*?)(?:/index\.html)?(?:\?.*)?$'
-    _TEST = {
+    _VALID_URL = r'https?://(?:watch\.|www\.)?nba\.com/(?:nba/)?video(?P<id>/[^?]*?)/?(?:/index\.html)?(?:\?.*)?$'
+    _TESTS = [{
         'url': 'http://www.nba.com/video/games/nets/2012/12/04/0021200253-okc-bkn-recap.nba/index.html',
         'md5': 'c0edcfc37607344e2ff8f13c378c88a4',
         'info_dict': {
@@ -21,12 +19,13 @@ class NBAIE(InfoExtractor):
             'description': 'Kevin Durant scores 32 points and dishes out six assists as the Thunder beat the Nets in Brooklyn.',
             'duration': 181,
         },
-    }
+    }, {
+        'url': 'http://www.nba.com/video/games/hornets/2014/12/05/0021400276-nyk-cha-play5.nba/',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
         video_url = 'http://ht-mobile.cdn.turner.com/nba/big' + video_id + '_nba_1280x720.mp4'
@@ -37,8 +36,7 @@ class NBAIE(InfoExtractor):
 
         description = self._og_search_description(webpage)
         duration = parse_duration(
-            self._html_search_meta('duration', webpage, 'duration', fatal=False))
-
+            self._html_search_meta('duration', webpage, 'duration'))
 
         return {
             'id': shortened_video_id,

youtube_dl/extractor/nhl.py

@@ -2,11 +2,15 @@ from __future__ import unicode_literals
 
 import re
 import json
+import os
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urlparse,
     compat_urllib_parse,
+    compat_urllib_parse_urlparse
+)
+from ..utils import (
     unified_strdate,
 )
 
@@ -22,9 +26,12 @@ class NHLBaseInfoExtractor(InfoExtractor):
 
         initial_video_url = info['publishPoint']
         if info['formats'] == '1':
+            parsed_url = compat_urllib_parse_urlparse(initial_video_url)
+            filename, ext = os.path.splitext(parsed_url.path)
+            path = '%s_sd%s' % (filename, ext)
             data = compat_urllib_parse.urlencode({
                 'type': 'fvod',
-                'path': initial_video_url.replace('.mp4', '_sd.mp4'),
+                'path': compat_urlparse.urlunparse(parsed_url[:2] + (path,) + parsed_url[3:])
             })
             path_url = 'http://video.nhl.com/videocenter/servlets/encryptvideopath?' + data
             path_doc = self._download_xml(
@@ -71,6 +78,17 @@ class NHLIE(NHLBaseInfoExtractor):
             'duration': 0,
             'upload_date': '20141011',
         },
+    }, {
+        'url': 'http://video.mapleleafs.nhl.com/videocenter/console?id=58665&catid=802',
+        'md5': 'c78fc64ea01777e426cfc202b746c825',
+        'info_dict': {
+            'id': '58665',
+            'ext': 'flv',
+            'title': 'Classic Game In Six - April 22, 1979',
+            'description': 'It was the last playoff game for the Leafs in the decade, and the last time the Leafs and Habs played in the playoffs. Great game, not a great ending.',
+            'duration': 400,
+            'upload_date': '20100129'
+        },
     }, {
         'url': 'http://video.flames.nhl.com/videocenter/console?id=630616',
         'only_matching': True,
@@ -88,7 +106,7 @@ class NHLIE(NHLBaseInfoExtractor):
 class NHLVideocenterIE(NHLBaseInfoExtractor):
     IE_NAME = 'nhl.com:videocenter'
     IE_DESC = 'NHL videocenter category'
-    _VALID_URL = r'https?://video\.(?P<team>[^.]*)\.nhl\.com/videocenter/(console\?.*?catid=(?P<catid>[0-9]+)(?![&?]id=).*?)?$'
+    _VALID_URL = r'https?://video\.(?P<team>[^.]*)\.nhl\.com/videocenter/(console\?[^(id=)]*catid=(?P<catid>[0-9]+)(?![&?]id=).*?)?$'
     _TEST = {
         'url': 'http://video.canucks.nhl.com/videocenter/console?catid=999',
         'info_dict': {
@@ -122,7 +140,7 @@ class NHLVideocenterIE(NHLBaseInfoExtractor):
         response = self._download_webpage(request_url, playlist_title)
         response = self._fix_json(response)
         if not response.strip():
-            self._downloader.report_warning(u'Got an empty reponse, trying '
+            self._downloader.report_warning('Got an empty reponse, trying '
                                             'adding the "newvideos" parameter')
             response = self._download_webpage(request_url + '&newvideos=true',
                                               playlist_title)