release 2014.11.26.1

From now on, the line

from __future__ import unicode_literals

should be contained in every single Python file lest we run into any more 2.x/3.x issues.
Going forward, we're likely to develop on 3.x only and would likely miss subtle bugs otherwise.

AUTHORS

@@ -84,3 +84,7 @@ xantares
 Jan Matějka
 Mauroy Sébastien
 William Sewell
+Dao Hoang Son
+Oskar Jauch
+Matthew Rayfield
+t0mm0

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.
 
@@ -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)
 

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)

test/test_unicode_literals.py

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

test/test_utils.py

@@ -45,9 +45,9 @@ from youtube_dl.utils import (
     escape_rfc3986,
     escape_url,
     js_to_json,
-    get_filesystem_encoding,
     intlist_to_bytes,
     args_to_str,
+    parse_filesize,
 )
 
 
@@ -171,7 +171,7 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(find('media:song/url').text, 'http://server.com/download.mp3')
 
     def test_smuggle_url(self):
-        data = {u"ö": u"ö", u"abc": [3]}
+        data = {"ö": "ö", "abc": [3]}
         url = 'https://foo.bar/baz?x=y#a'
         smug_url = smuggle_url(url, data)
         unsmug_url, unsmug_data = unsmuggle_url(smug_url)
@@ -368,5 +368,14 @@ class TestUtil(unittest.TestCase):
             'foo ba/r -baz \'2 be\' \'\''
         )
 
+    def test_parse_filesize(self):
+        self.assertEqual(parse_filesize(None), None)
+        self.assertEqual(parse_filesize(''), None)
+        self.assertEqual(parse_filesize('91 B'), 91)
+        self.assertEqual(parse_filesize('foobar'), None)
+        self.assertEqual(parse_filesize('2 MiB'), 2097152)
+        self.assertEqual(parse_filesize('5 GB'), 5000000000)
+        self.assertEqual(parse_filesize('1.2Tb'), 1200000000000)
+
 if __name__ == '__main__':
     unittest.main()

test/test_write_annotations.py

@@ -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

@@ -29,7 +29,6 @@ from .compat import (
     compat_str,
     compat_urllib_error,
     compat_urllib_request,
-    shlex_quote,
 )
 from .utils import (
     escape_url,
@@ -700,14 +699,17 @@ class YoutubeDL(object):
             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)
@@ -1428,4 +1430,3 @@ class YoutubeDL(object):
         if encoding is None:
             encoding = preferredencoding()
         return encoding
-

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:

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

@@ -182,8 +182,10 @@ except ImportError:  # Python < 3.3
 
 
 def compat_ord(c):
-    if type(c) is int: return c
+    if type(c) is int:
-    else: return ord(c)
+        return c
+    else:
+        return ord(c)
 
 
 if sys.version_info >= (3, 0):
@@ -268,7 +270,7 @@ if sys.version_info < (3, 0):
         print(s.encode(preferredencoding(), 'xmlcharrefreplace'))
 else:
     def compat_print(s):
-        assert type(s) == type(u'')
+        assert isinstance(s, compat_str)
         print(s)
 
 

youtube_dl/downloader/__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

@@ -28,14 +28,14 @@ class HlsFD(FileDownloader):
             if check_executable(program, ['-version']):
                 break
         else:
-            self.report_error(u'm3u8 download detected but ffmpeg or avconv could not be found. Please install one.')
+            self.report_error('m3u8 download detected but ffmpeg or avconv could not be found. Please install one.')
             return False
         cmd = [program] + args
 
         retval = subprocess.call(cmd)
         if retval == 0:
             fsize = os.path.getsize(encodeFilename(tmpfilename))
-            self.to_screen(u'\r[%s] %s bytes' % (cmd[0], fsize))
+            self.to_screen('\r[%s] %s bytes' % (cmd[0], fsize))
             self.try_rename(tmpfilename, filename)
             self._hook_progress({
                 'downloaded_bytes': fsize,
@@ -45,8 +45,8 @@ class HlsFD(FileDownloader):
             })
             return True
         else:
-            self.to_stderr(u"\n")
+            self.to_stderr('\n')
-            self.report_error(u'%s exited with code %d' % (program, retval))
+            self.report_error('%s exited with code %d' % (program, retval))
             return False
 
 
@@ -101,4 +101,3 @@ 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.to_stderr('\n')
-                self.report_error(u'unable to write data: %s' % str(err))
+                self.report_error('unable to write data: %s' % str(err))
                 return False
             if not self.params.get('noresizebuffer', False):
                 block_size = self.best_block_size(after - before, len(data_block))
@@ -188,10 +190,10 @@ class HttpFD(FileDownloader):
             self.slow_down(start, byte_counter - resume_len)
 
         if stream is None:
-            self.to_stderr(u"\n")
+            self.to_stderr('\n')
-            self.report_error(u'Did not get any data blocks')
+            self.report_error('Did not get any data blocks')
             return False
-        if tmpfilename != u'-':
+        if tmpfilename != '-':
             stream.close()
         self.report_finish(data_len_str, (time.time() - start))
         if data_len is not None and byte_counter != data_len:

youtube_dl/downloader/mplayer.py

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

youtube_dl/extractor/__init__.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 from .abc import ABCIE
 from .academicearth import AcademicEarthCourseIE
 from .addanime import AddAnimeIE
@@ -32,6 +34,7 @@ from .bilibili import BiliBiliIE
 from .blinkx import BlinkxIE
 from .bliptv import BlipTVIE, BlipTVUserIE
 from .bloomberg import BloombergIE
+from .bpb import BpbIE
 from .br import BRIE
 from .breakcom import BreakIE
 from .brightcove import BrightcoveIE
@@ -372,6 +375,7 @@ 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,
@@ -392,6 +396,7 @@ 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,
@@ -405,6 +410,7 @@ from .trutube import TruTubeIE
 from .tube8 import Tube8IE
 from .tudou import TudouIE
 from .tumblr import TumblrIE
+from .tunein import TuneInIE
 from .turbo import TurboIE
 from .tutv import TutvIE
 from .tvigle import TvigleIE
@@ -481,6 +487,7 @@ 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
@@ -511,6 +518,10 @@ from .youtube import (
     YoutubeWatchLaterIE,
 )
 from .zdf import ZDFIE
+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 = self._match_id(url)
-        playlist_id = m.group('id')
 
         webpage = self._download_webpage(url, playlist_id)
         title = self._html_search_regex(
-            r'<h1 class="playlist-name"[^>]*?>(.*?)</h1>', webpage, u'title')
+            r'<h1 class="playlist-name"[^>]*?>(.*?)</h1>', webpage, 'title')
         description = self._html_search_regex(
             r'<p class="excerpt"[^>]*?>(.*?)</p>',
-            webpage, u'description', fatal=False)
+            webpage, 'description', fatal=False)
         urls = re.findall(
             r'<li class="lecture-preview">\s*?<a target="_blank" href="([^"]+)">',
             webpage)

youtube_dl/extractor/addanime.py

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

youtube_dl/extractor/adultswim.py

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

youtube_dl/extractor/aparat.py

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

youtube_dl/extractor/appletrailers.py

@@ -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/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/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/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/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/common.py

@@ -296,9 +296,11 @@ class InfoExtractor(object):
         content = self._webpage_read_content(urlh, url_or_request, video_id, note, errnote, fatal)
         return (content, urlh)
 
-    def _webpage_read_content(self, urlh, url_or_request, video_id, note=None, errnote=None, fatal=True):
+    def _webpage_read_content(self, urlh, url_or_request, video_id, note=None, errnote=None, fatal=True, prefix=None):
         content_type = urlh.headers.get('Content-Type', '')
         webpage_bytes = urlh.read()
+        if prefix is not None:
+            webpage_bytes = prefix + webpage_bytes
         m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type)
         if m:
             encoding = m.group(1)
@@ -434,6 +436,7 @@ class InfoExtractor(object):
         if video_id is not None:
             video_info['id'] = video_id
         return video_info
+
     @staticmethod
     def playlist_result(entries, playlist_id=None, playlist_title=None):
         """Returns a playlist"""

youtube_dl/extractor/crunchyroll.py

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

youtube_dl/extractor/dailymotion.py

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

youtube_dl/extractor/dropbox.py

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

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

youtube_dl/extractor/gorillavid.py

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

youtube_dl/extractor/hotnewhiphop.py

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

youtube_dl/extractor/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'
+                'description': (
-                    ' natural beauty take our breath away.',
+                    '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,
+            return xpath_with_ns(
-                {'media': 'http://search.yahoo.com/mrss/',
+                p,
-                'jwplayer': 'http://developer.longtailvideo.com/trac/wiki/FlashFormats'})
+                {
+                    '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 '
+            'description': (
-                'life and mind of one of sports most elite athletes: Josh Grant.',
+                '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/mooshare.py

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

youtube_dl/extractor/mtv.py

@@ -164,7 +164,7 @@ class MTVServicesInfoExtractor(InfoExtractor):
         if mgid is None or ':' not in mgid:
             mgid = self._search_regex(
                 [r'data-mgid="(.*?)"', r'swfobject.embedSWF\(".*?(mgid:.*?)"'],
-                webpage, u'mgid')
+                webpage, 'mgid')
         return self._get_videos_info(mgid)
 
 
@@ -245,7 +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
+from __future__ import unicode_literals
-import json
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urllib_parse,
-    determine_ext,
 )
 
 
 class MuzuTVIE(InfoExtractor):
     _VALID_URL = r'https?://www\.muzu\.tv/(.+?)/(.+?)/(?P<id>\d+)'
-    IE_NAME = u'muzu.tv'
+    IE_NAME = 'muzu.tv'
 
     _TEST = {
-        u'url': u'http://www.muzu.tv/defected/marcashken-featuring-sos-cat-walk-original-mix-music-video/1981454/',
+        'url': 'http://www.muzu.tv/defected/marcashken-featuring-sos-cat-walk-original-mix-music-video/1981454/',
-        u'file': u'1981454.mp4',
+        'md5': '98f8b2c7bc50578d6a0364fff2bfb000',
-        u'md5': u'98f8b2c7bc50578d6a0364fff2bfb000',
+        'info_dict': {
-        u'info_dict': {
+            'id': '1981454',
-            u'title': u'Cat Walk (Original Mix)',
+            'ext': 'mp4',
-            u'description': u'md5:90e868994de201b2570e4e5854e19420',
+            'title': 'Cat Walk (Original Mix)',
-            u'uploader': u'MarcAshken featuring SOS',
+            'description': 'md5:90e868994de201b2570e4e5854e19420',
+            'uploader': 'MarcAshken featuring SOS',
         },
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
+        video_id = self._match_id(url)
-        video_id = mobj.group('id')
 
-        info_data = compat_urllib_parse.urlencode({'format': 'json',
+        info_data = compat_urllib_parse.urlencode({
+            'format': 'json',
             'url': url,
         })
-        video_info_page = self._download_webpage('http://www.muzu.tv/api/oembed/?%s' % info_data,
+        info = self._download_json(
-                                                 video_id, u'Downloading video info')
+            'http://www.muzu.tv/api/oembed/?%s' % info_data,
-        info = json.loads(video_info_page)
+            video_id, 'Downloading video info')
 
-        player_info_page = self._download_webpage('http://player.muzu.tv/player/playerInit?ai=%s' % video_id,
+        player_info = self._download_json(
-                                                  video_id, u'Downloading player info')
+            'http://player.muzu.tv/player/playerInit?ai=%s' % video_id,
-        video_info = json.loads(player_info_page)['videos'][0]
+            video_id, 'Downloading player info')
+        video_info = player_info['videos'][0]
         for quality in ['1080', '720', '480', '360']:
             if video_info.get('v%s' % quality):
                 break
 
-        data = compat_urllib_parse.urlencode({'ai': video_id,
+        data = compat_urllib_parse.urlencode({
+            'ai': video_id,
             # Even if each time you watch a video the hash changes,
             # it seems to work for different videos, and it will work
             # even if you use any non empty string as a hash
@@ -49,15 +50,15 @@ class MuzuTVIE(InfoExtractor):
             'device': 'web',
             'qv': quality,
         })
-        video_url_page = self._download_webpage('http://player.muzu.tv/player/requestVideo?%s' % data,
+        video_url_info = self._download_json(
-                                                video_id, u'Downloading video url')
+            'http://player.muzu.tv/player/requestVideo?%s' % data,
-        video_url_info = json.loads(video_url_page)
+            video_id, 'Downloading video url')
         video_url = video_url_info['url']
 
-        return {'id': video_id,
+        return {
+            'id': video_id,
             'title': info['title'],
             'url': video_url,
-                'ext': determine_ext(video_url),
             'thumbnail': info['thumbnail_url'],
             'description': info['description'],
             'uploader': info['author_name'],

youtube_dl/extractor/myspace.py

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

youtube_dl/extractor/myvideo.py

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

youtube_dl/extractor/nba.py

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

youtube_dl/extractor/nhl.py

@@ -4,9 +4,11 @@ import re
 import json
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urlparse,
     compat_urllib_parse,
+)
+from ..utils import (
     unified_strdate,
 )
 
@@ -122,7 +124,7 @@ class NHLVideocenterIE(NHLBaseInfoExtractor):
         response = self._download_webpage(request_url, playlist_title)
         response = self._fix_json(response)
         if not response.strip():
-            self._downloader.report_warning(u'Got an empty reponse, trying '
+            self._downloader.report_warning('Got an empty reponse, trying '
                                             'adding the "newvideos" parameter')
             response = self._download_webpage(request_url + '&newvideos=true',
                                               playlist_title)

youtube_dl/extractor/ninegag.py

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

youtube_dl/extractor/ooyala.py

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

youtube_dl/extractor/podomatic.py

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

youtube_dl/extractor/redtube.py

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

youtube_dl/extractor/ringtv.py

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

youtube_dl/extractor/rtlnl.py

@@ -44,7 +44,7 @@ class RtlXlIE(InfoExtractor):
 
         formats = self._extract_m3u8_formats(m3u8_url, uuid, ext='mp4')
 
-        video_urlpart = videopath.split('/flash/')[1][:-4]
+        video_urlpart = videopath.split('/flash/')[1][:-5]
         PG_URL_TEMPLATE = 'http://pg.us.rtl.nl/rtlxl/network/%s/progressive/%s.mp4'
 
         formats.extend([

youtube_dl/extractor/rtve.py

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

youtube_dl/extractor/sbs.py

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

youtube_dl/extractor/servingsys.py

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

youtube_dl/extractor/smotri.py

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

youtube_dl/extractor/sohu.py

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

youtube_dl/extractor/space.py

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

youtube_dl/extractor/sportdeutschland.py

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

youtube_dl/extractor/subtitles.py

@@ -1,7 +1,8 @@
+from __future__ import unicode_literals
 from .common import InfoExtractor
 
+from ..compat import compat_str
 from ..utils import (
-    compat_str,
     ExtractorError,
 )
 
@@ -17,10 +18,10 @@ class SubtitlesInfoExtractor(InfoExtractor):
         sub_lang_list = self._get_available_subtitles(video_id, webpage)
         auto_captions_list = self._get_available_automatic_caption(video_id, webpage)
         sub_lang = ",".join(list(sub_lang_list.keys()))
-        self.to_screen(u'%s: Available subtitles for video: %s' %
+        self.to_screen('%s: Available subtitles for video: %s' %
                        (video_id, sub_lang))
         auto_lang = ",".join(auto_captions_list.keys())
-        self.to_screen(u'%s: Available automatic captions for video: %s' %
+        self.to_screen('%s: Available automatic captions for video: %s' %
                        (video_id, auto_lang))
 
     def extract_subtitles(self, video_id, webpage):
@@ -50,8 +51,8 @@ class SubtitlesInfoExtractor(InfoExtractor):
 
             sub_lang_list = {}
             for sub_lang in requested_langs:
-                if not sub_lang in available_subs_list:
+                if sub_lang not in available_subs_list:
-                    self._downloader.report_warning(u'no closed captions found in the specified language "%s"' % sub_lang)
+                    self._downloader.report_warning('no closed captions found in the specified language "%s"' % sub_lang)
                     continue
                 sub_lang_list[sub_lang] = available_subs_list[sub_lang]
 
@@ -70,10 +71,10 @@ class SubtitlesInfoExtractor(InfoExtractor):
         try:
             sub = self._download_subtitle_url(sub_lang, url)
         except ExtractorError as err:
-            self._downloader.report_warning(u'unable to download video subtitles for %s: %s' % (sub_lang, compat_str(err)))
+            self._downloader.report_warning('unable to download video subtitles for %s: %s' % (sub_lang, compat_str(err)))
             return
         if not sub:
-            self._downloader.report_warning(u'Did not fetch video subtitles')
+            self._downloader.report_warning('Did not fetch video subtitles')
             return
         return sub
 
@@ -94,5 +95,5 @@ class SubtitlesInfoExtractor(InfoExtractor):
         Must be redefined by the subclasses that support automatic captions,
         otherwise it will return {}
         """
-        self._downloader.report_warning(u'Automatic Captions not supported by this server')
+        self._downloader.report_warning('Automatic Captions not supported by this server')
         return {}

youtube_dl/extractor/tass.py

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

youtube_dl/extractor/teamcoco.py

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

youtube_dl/extractor/theplatform.py

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

youtube_dl/extractor/tlc.py

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

youtube_dl/extractor/tmz.py

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

youtube_dl/extractor/trilulilu.py

@@ -1,28 +1,28 @@
+from __future__ import unicode_literals
+
 import json
-import re
 
 from .common import InfoExtractor
 
 
 class TriluliluIE(InfoExtractor):
-    _VALID_URL = r'(?x)(?:https?://)?(?:www\.)?trilulilu\.ro/video-(?P<category>[^/]+)/(?P<video_id>[^/]+)'
+    _VALID_URL = r'https?://(?:www\.)?trilulilu\.ro/video-[^/]+/(?P<id>[^/]+)'
     _TEST = {
-        u"url": u"http://www.trilulilu.ro/video-animatie/big-buck-bunny-1",
+        'url': 'http://www.trilulilu.ro/video-animatie/big-buck-bunny-1',
-        u'file': u"big-buck-bunny-1.mp4",
+        'info_dict': {
-        u'info_dict': {
+            'id': 'big-buck-bunny-1',
-            u"title": u"Big Buck Bunny",
+            'ext': 'mp4',
-            u"description": u":) pentru copilul din noi",
+            'title': 'Big Buck Bunny',
+            'description': ':) pentru copilul din noi',
         },
         # Server ignores Range headers (--test)
-        u"params": {
+        'params': {
-            u"skip_download": True
+            'skip_download': True
         }
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
+        video_id = self._match_id(url)
-        video_id = mobj.group('video_id')
-
         webpage = self._download_webpage(url, video_id)
 
         title = self._og_search_title(webpage)
@@ -30,20 +30,20 @@ class TriluliluIE(InfoExtractor):
         description = self._og_search_description(webpage)
 
         log_str = self._search_regex(
-            r'block_flash_vars[ ]=[ ]({[^}]+})', webpage, u'log info')
+            r'block_flash_vars[ ]=[ ]({[^}]+})', webpage, 'log info')
         log = json.loads(log_str)
 
-        format_url = (u'http://fs%(server)s.trilulilu.ro/%(hash)s/'
+        format_url = ('http://fs%(server)s.trilulilu.ro/%(hash)s/'
-                      u'video-formats2' % log)
+                      'video-formats2' % log)
         format_doc = self._download_xml(
             format_url, video_id,
-            note=u'Downloading formats',
+            note='Downloading formats',
-            errnote=u'Error while downloading formats')
+            errnote='Error while downloading formats')
 
         video_url_template = (
-            u'http://fs%(server)s.trilulilu.ro/stream.php?type=video'
+            'http://fs%(server)s.trilulilu.ro/stream.php?type=video'
-            u'&source=site&hash=%(hash)s&username=%(userid)s&'
+            '&source=site&hash=%(hash)s&username=%(userid)s&'
-            u'key=ministhebest&format=%%s&sig=&exp=' %
+            'key=ministhebest&format=%%s&sig=&exp=' %
             log)
         formats = [
             {
@@ -63,4 +63,3 @@ class TriluliluIE(InfoExtractor):
             'description': description,
             'thumbnail': thumbnail,
         }
-

youtube_dl/extractor/tudou.py

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