Merge branch 'master' of https://github.com/rg3/youtube-dl

2016-05-30 11:29:24 +02:00 · 2016-05-30 11:29:24 +02:00 · 300eac126b
commit 300eac126b
parent 91ba156b43 197a5da1d0
17 changed files with 390 additions and 122 deletions
--- a/.github/ISSUE_TEMPLATE.md
+++ b/.github/ISSUE_TEMPLATE.md
@ -6,8 +6,8 @@

 ---

-### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.05.21.2*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2016.05.21.2**
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.05.30.2*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
+- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2016.05.30.2**

 ### Before submitting an *issue* make sure you have:
 - [ ] At least skimmed through [README](https://github.com/rg3/youtube-dl/blob/master/README.md) and **most notably** [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
@ -35,7 +35,7 @@ $ youtube-dl -v <your command line>
 [debug] User config: []
 [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
 [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
-[debug] youtube-dl version 2016.05.21.2
+[debug] youtube-dl version 2016.05.30.2
 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
 [debug] Proxy map: {}
--- a/.gitignore
+++ b/.gitignore
@ -28,12 +28,16 @@ updates_key.pem
 *.mp4
 *.m4a
 *.m4v
+*.mp3
 *.part
 *.swp
 test/testdata
 test/local_parameters.json
 .tox
 youtube-dl.zsh
+
+# IntelliJ related files
 .idea
-.idea/*
+*.iml
+
 tmp/
--- a/.travis.yml
+++ b/.travis.yml
@ -14,7 +14,6 @@ script: nosetests test --verbose
 notifications:
  email:
    - filippo.valsorda@gmail.com
-    - phihag@phihag.de
    - yasoob.khld@gmail.com
 #  irc:
 #    channels:
--- a/4
+++ b/4
@ -1,7 +1,7 @@
 all: youtube-dl README.md CONTRIBUTING.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish supportedsites

 clean:
-	rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish youtube_dl/extractor/lazy_extractors.py *.dump *.part *.info.json *.mp4 *.flv *.mp3 *.avi *.mkv *.webm *.jpg *.png CONTRIBUTING.md.tmp ISSUE_TEMPLATE.md.tmp youtube-dl youtube-dl.exe
+	rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish youtube_dl/extractor/lazy_extractors.py *.dump *.part *.info.json *.mp4 *.m4a *.flv *.mp3 *.avi *.mkv *.webm *.jpg *.png CONTRIBUTING.md.tmp ISSUE_TEMPLATE.md.tmp youtube-dl youtube-dl.exe
 	find . -name "*.pyc" -delete
 	find . -name "*.class" -delete

@ -69,7 +69,7 @@ README.txt: README.md
 	pandoc -f markdown -t plain README.md -o README.txt

 youtube-dl.1: README.md
-	$(PYTHON) devscripts/prepare_manpage.py >youtube-dl.1.temp.md
+	$(PYTHON) devscripts/prepare_manpage.py youtube-dl.1.temp.md
 	pandoc -s -f markdown -t man youtube-dl.1.temp.md -o youtube-dl.1
 	rm -f youtube-dl.1.temp.md

--- a/README.md
+++ b/README.md
@ -785,9 +785,9 @@ means you're using an outdated version of Python. Please update to Python 2.6 or

 Since June 2012 ([#342](https://github.com/rg3/youtube-dl/issues/342)) youtube-dl is packed as an executable zipfile, simply unzip it (might need renaming to `youtube-dl.zip` first on some systems) or clone the git repository, as laid out above. If you modify the code, you can run it by executing the `__main__.py` file. To recompile the executable, run `make youtube-dl`.

-### The exe throws a *Runtime error from Visual C++*
+### The exe throws an error due to missing `MSVCR100.dll`

-To run the exe you need to install first the [Microsoft Visual C++ 2008 Redistributable Package](http://www.microsoft.com/en-us/download/details.aspx?id=29).
+To run the exe you need to install first the [Microsoft Visual C++ 2010 Redistributable Package (x86)](https://www.microsoft.com/en-US/download/details.aspx?id=5555).

 ### On Windows, how should I set up ffmpeg and youtube-dl? Where should I put the exe files?

--- a/devscripts/buildserver.py
+++ b/devscripts/buildserver.py
@ -1,17 +1,42 @@
 #!/usr/bin/python3

-from http.server import HTTPServer, BaseHTTPRequestHandler
-from socketserver import ThreadingMixIn
 import argparse
 import ctypes
 import functools
+import shutil
+import subprocess
 import sys
+import tempfile
 import threading
 import traceback
 import os.path

+sys.path.insert(0, os.path.dirname(os.path.dirname((os.path.abspath(__file__)))))
+from youtube_dl.compat import (
+    compat_http_server,
+    compat_str,
+    compat_urlparse,
+)

-class BuildHTTPServer(ThreadingMixIn, HTTPServer):
+# These are not used outside of buildserver.py thus not in compat.py
+
+try:
+    import winreg as compat_winreg
+except ImportError:  # Python 2
+    import _winreg as compat_winreg
+
+try:
+    import socketserver as compat_socketserver
+except ImportError:  # Python 2
+    import SocketServer as compat_socketserver
+
+try:
+    compat_input = raw_input
+except NameError:  # Python 3
+    compat_input = input
+
+
+class BuildHTTPServer(compat_socketserver.ThreadingMixIn, compat_http_server.HTTPServer):
    allow_reuse_address = True


@ -191,7 +216,7 @@ def main(args=None):
                        action='store_const', dest='action', const='service',
                        help='Run as a Windows service')
    parser.add_argument('-b', '--bind', metavar='<host:port>',
-                        action='store', default='localhost:8142',
+                        action='store', default='0.0.0.0:8142',
                        help='Bind to host:port (default %default)')
    options = parser.parse_args(args=args)

@ -216,7 +241,7 @@ def main(args=None):
    srv = BuildHTTPServer((host, port), BuildHTTPRequestHandler)
    thr = threading.Thread(target=srv.serve_forever)
    thr.start()
-    input('Press ENTER to shut down')
+    compat_input('Press ENTER to shut down')
    srv.shutdown()
    thr.join()

@ -231,8 +256,6 @@ def rmtree(path):
            os.remove(fname)
    os.rmdir(path)

-#==============================================================================
-

 class BuildError(Exception):
    def __init__(self, output, code=500):
@ -249,15 +272,25 @@ class HTTPError(BuildError):

 class PythonBuilder(object):
    def __init__(self, **kwargs):
-        pythonVersion = kwargs.pop('python', '2.7')
-        try:
-            key = _winreg.OpenKey(_winreg.HKEY_LOCAL_MACHINE, r'SOFTWARE\Python\PythonCore\%s\InstallPath' % pythonVersion)
+        python_version = kwargs.pop('python', '3.4')
+        python_path = None
+        for node in ('Wow6432Node\\', ''):
            try:
-                self.pythonPath, _ = _winreg.QueryValueEx(key, '')
-            finally:
-                _winreg.CloseKey(key)
-        except Exception:
-            raise BuildError('No such Python version: %s' % pythonVersion)
+                key = compat_winreg.OpenKey(
+                    compat_winreg.HKEY_LOCAL_MACHINE,
+                    r'SOFTWARE\%sPython\PythonCore\%s\InstallPath' % (node, python_version))
+                try:
+                    python_path, _ = compat_winreg.QueryValueEx(key, '')
+                finally:
+                    compat_winreg.CloseKey(key)
+                break
+            except Exception:
+                pass
+
+        if not python_path:
+            raise BuildError('No such Python version: %s' % python_version)
+
+        self.pythonPath = python_path

        super(PythonBuilder, self).__init__(**kwargs)

@ -305,8 +338,10 @@ class YoutubeDLBuilder(object):

    def build(self):
        try:
-            subprocess.check_output([os.path.join(self.pythonPath, 'python.exe'), 'setup.py', 'py2exe'],
-                                    cwd=self.buildPath)
+            proc = subprocess.Popen([os.path.join(self.pythonPath, 'python.exe'), 'setup.py', 'py2exe'], stdin=subprocess.PIPE, cwd=self.buildPath)
+            proc.wait()
+            #subprocess.check_output([os.path.join(self.pythonPath, 'python.exe'), 'setup.py', 'py2exe'],
+            #                        cwd=self.buildPath)
        except subprocess.CalledProcessError as e:
            raise BuildError(e.output)

@ -369,12 +404,12 @@ class Builder(PythonBuilder, GITBuilder, YoutubeDLBuilder, DownloadBuilder, Clea
    pass


-class BuildHTTPRequestHandler(BaseHTTPRequestHandler):
+class BuildHTTPRequestHandler(compat_http_server.BaseHTTPRequestHandler):
    actionDict = {'build': Builder, 'download': Builder}  # They're the same, no more caching.

    def do_GET(self):
-        path = urlparse.urlparse(self.path)
-        paramDict = dict([(key, value[0]) for key, value in urlparse.parse_qs(path.query).items()])
+        path = compat_urlparse.urlparse(self.path)
+        paramDict = dict([(key, value[0]) for key, value in compat_urlparse.parse_qs(path.query).items()])
        action, _, path = path.path.strip('/').partition('/')
        if path:
            path = path.split('/')
@ -388,7 +423,7 @@ class BuildHTTPRequestHandler(BaseHTTPRequestHandler):
                        builder.close()
                except BuildError as e:
                    self.send_response(e.code)
-                    msg = unicode(e).encode('UTF-8')
+                    msg = compat_str(e).encode('UTF-8')
                    self.send_header('Content-Type', 'text/plain; charset=UTF-8')
                    self.send_header('Content-Length', len(msg))
                    self.end_headers()
@ -400,7 +435,5 @@ class BuildHTTPRequestHandler(BaseHTTPRequestHandler):
        else:
            self.send_response(500, 'Malformed URL')

-#==============================================================================
-
 if __name__ == '__main__':
    main()
--- a/devscripts/prepare_manpage.py
+++ b/devscripts/prepare_manpage.py
@ -1,13 +1,46 @@
 from __future__ import unicode_literals

 import io
+import optparse
 import os.path
-import sys
 import re

 ROOT_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
 README_FILE = os.path.join(ROOT_DIR, 'README.md')

+PREFIX = '''%YOUTUBE-DL(1)
+
+# NAME
+
+youtube\-dl \- download videos from youtube.com or other video platforms
+
+# SYNOPSIS
+
+**youtube-dl** \[OPTIONS\] URL [URL...]
+
+'''
+
+
+def main():
+    parser = optparse.OptionParser(usage='%prog OUTFILE.md')
+    options, args = parser.parse_args()
+    if len(args) != 1:
+        parser.error('Expected an output filename')
+
+    outfile, = args
+
+    with io.open(README_FILE, encoding='utf-8') as f:
+        readme = f.read()
+
+    readme = re.sub(r'(?s)^.*?(?=# DESCRIPTION)', '', readme)
+    readme = re.sub(r'\s+youtube-dl \[OPTIONS\] URL \[URL\.\.\.\]', '', readme)
+    readme = PREFIX + readme
+
+    readme = filter_options(readme)
+
+    with io.open(outfile, 'w', encoding='utf-8') as outf:
+        outf.write(readme)
+

 def filter_options(readme):
    ret = ''
@ -37,27 +70,5 @@ def filter_options(readme):

    return ret

-with io.open(README_FILE, encoding='utf-8') as f:
-    readme = f.read()
-
-PREFIX = '''%YOUTUBE-DL(1)
-
-# NAME
-
-youtube\-dl \- download videos from youtube.com or other video platforms
-
-# SYNOPSIS
-
-**youtube-dl** \[OPTIONS\] URL [URL...]
-
-'''
-readme = re.sub(r'(?s)^.*?(?=# DESCRIPTION)', '', readme)
-readme = re.sub(r'\s+youtube-dl \[OPTIONS\] URL \[URL\.\.\.\]', '', readme)
-readme = PREFIX + readme
-
-readme = filter_options(readme)
-
-if sys.version_info < (3, 0):
-    print(readme.encode('utf-8'))
-else:
-    print(readme)
+if __name__ == '__main__':
+    main()
--- a/devscripts/release.sh
+++ b/devscripts/release.sh
@ -6,7 +6,7 @@
 # * the git config user.signingkey is properly set

 # You will need
-# pip install coverage nose rsa
+# pip install coverage nose rsa wheel

 # TODO
 # release notes
@ -15,10 +15,28 @@
 set -e

 skip_tests=true
-if [ "$1" = '--run-tests' ]; then
-    skip_tests=false
-    shift
-fi
+buildserver='localhost:8142'
+
+while true
+do
+case "$1" in
+    --run-tests)
+        skip_tests=false
+        shift
+    ;;
+    --buildserver)
+        buildserver="$2"
+        shift 2
+    ;;
+    --*)
+        echo "ERROR: unknown option $1"
+        exit 1
+    ;;
+    *)
+        break
+    ;;
+esac
+done

 if [ -z "$1" ]; then echo "ERROR: specify version number like this: $0 1994.09.06"; exit 1; fi
 version="$1"
@ -35,6 +53,7 @@ if [ ! -z "$useless_files" ]; then echo "ERROR: Non-.py files in youtube_dl: $us
 if [ ! -f "updates_key.pem" ]; then echo 'ERROR: updates_key.pem missing'; exit 1; fi
 if ! type pandoc >/dev/null 2>/dev/null; then echo 'ERROR: pandoc is missing'; exit 1; fi
 if ! python3 -c 'import rsa' 2>/dev/null; then echo 'ERROR: python3-rsa is missing'; exit 1; fi
+if ! python3 -c 'import wheel' 2>/dev/null; then echo 'ERROR: wheel is missing'; exit 1; fi

 /bin/echo -e "\n### First of all, testing..."
 make clean
@ -66,7 +85,7 @@ git push origin "$version"
 REV=$(git rev-parse HEAD)
 make youtube-dl youtube-dl.tar.gz
 read -p "VM running? (y/n) " -n 1
-wget "http://localhost:8142/build/rg3/youtube-dl/youtube-dl.exe?rev=$REV" -O youtube-dl.exe
+wget "http://$buildserver/build/rg3/youtube-dl/youtube-dl.exe?rev=$REV" -O youtube-dl.exe
 mkdir -p "build/$version"
 mv youtube-dl youtube-dl.exe "build/$version"
 mv youtube-dl.tar.gz "build/$version/youtube-dl-$version.tar.gz"
--- a/docs/supportedsites.md
+++ b/docs/supportedsites.md
@ -43,8 +43,8 @@
 - **appletrailers:section**
 - **archive.org**: archive.org videos
 - **ARD**
- - **ARD:mediathek**: Saarländischer Rundfunk
 - **ARD:mediathek**
+ - **ARD:mediathek**: Saarländischer Rundfunk
 - **arte.tv**
 - **arte.tv:+7**
 - **arte.tv:cinema**
@ -136,6 +136,7 @@
 - **ComedyCentral**
 - **ComedyCentralShows**: The Daily Show / The Colbert Report
 - **CondeNast**: Condé Nast media group: Allure, Architectural Digest, Ars Technica, Bon Appétit, Brides, Condé Nast, Condé Nast Traveler, Details, Epicurious, GQ, Glamour, Golf Digest, SELF, Teen Vogue, The New Yorker, Vanity Fair, Vogue, W Magazine, WIRED
+ - **Coub**
 - **Cracked**
 - **Crackle**
 - **Criterion**
@ -205,6 +206,7 @@
 - **exfm**: ex.fm
 - **ExpoTV**
 - **ExtremeTube**
+ - **EyedoTV**
 - **facebook**
 - **faz.net**
 - **fc2**
@ -326,8 +328,8 @@
 - **LePlaylist**
 - **LetvCloud**: 乐视云
 - **Libsyn**
+ - **life**: Life.ru
 - **life:embed**
- - **lifenews**: LIFE | NEWS
 - **limelight**
 - **limelight:channel**
 - **limelight:channel_list**
@ -512,6 +514,8 @@
 - **R7**
 - **radio.de**
 - **radiobremen**
+ - **radiocanada**
+ - **RadioCanadaAudioVideo**
 - **radiofrance**
 - **RadioJavan**
 - **Rai**
@ -521,6 +525,7 @@
 - **RedTube**
 - **RegioTV**
 - **Restudy**
+ - **Reuters**
 - **ReverbNation**
 - **Revision3**
 - **RICE**
@ -682,8 +687,8 @@
 - **TVCArticle**
 - **tvigle**: Интернет-телевидение Tvigle.ru
 - **tvland.com**
- - **tvp.pl**
- - **tvp.pl:Series**
+ - **tvp**: Telewizja Polska
+ - **tvp:series**
 - **TVPlay**: TV3Play and related services
 - **Tweakers**
 - **twitch:chapter**
@ -766,7 +771,8 @@
 - **VuClip**
 - **vulture.com**
 - **Walla**
- - **WashingtonPost**
+ - **washingtonpost**
+ - **washingtonpost:article**
 - **wat.tv**
 - **WatchIndianPorn**: Watch Indian Porn
 - **WDR**
--- a/youtube_dl/extractor/bilibili.py
+++ b/youtube_dl/extractor/bilibili.py
@ -1,34 +1,42 @@
 # coding: utf-8
 from __future__ import unicode_literals

+import calendar
+import datetime
 import re

 from .common import InfoExtractor
-from ..compat import compat_str
+from ..compat import (
+    compat_etree_fromstring,
+    compat_str,
+    compat_parse_qs,
+    compat_xml_parse_error,
+)
 from ..utils import (
-    int_or_none,
-    unescapeHTML,
    ExtractorError,
+    int_or_none,
+    float_or_none,
    xpath_text,
 )


 class BiliBiliIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.bilibili\.(?:tv|com)/video/av(?P<id>\d+)(?:/index_(?P<page_num>\d+).html)?'
+    _VALID_URL = r'https?://www\.bilibili\.(?:tv|com)/video/av(?P<id>\d+)'

    _TESTS = [{
        'url': 'http://www.bilibili.tv/video/av1074402/',
-        'md5': '2c301e4dab317596e837c3e7633e7d86',
+        'md5': '5f7d29e1a2872f3df0cf76b1f87d3788',
        'info_dict': {
            'id': '1554319',
            'ext': 'flv',
            'title': '【金坷垃】金泡沫',
-            'duration': 308313,
+            'description': 'md5:ce18c2a2d2193f0df2917d270f2e5923',
+            'duration': 308.067,
+            'timestamp': 1398012660,
            'upload_date': '20140420',
            'thumbnail': 're:^https?://.+\.jpg',
-            'description': 'md5:ce18c2a2d2193f0df2917d270f2e5923',
-            'timestamp': 1397983878,
            'uploader': '菊子桑',
+            'uploader_id': '156160',
        },
    }, {
        'url': 'http://www.bilibili.com/video/av1041170/',
@ -36,75 +44,110 @@ class BiliBiliIE(InfoExtractor):
            'id': '1041170',
            'title': '【BD1080P】刀语【诸神&异域】',
            'description': '这是个神奇的故事~每个人不留弹幕不给走哦~切利哦！~',
-            'uploader': '枫叶逝去',
-            'timestamp': 1396501299,
        },
        'playlist_count': 9,
    }]

+    # BiliBili blocks keys from time to time. The current key is extracted from
+    # the Android client
+    # TODO: find the sign algorithm used in the flash player
+    _APP_KEY = '86385cdc024c0f6c'
+
    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        video_id = mobj.group('id')
-        page_num = mobj.group('page_num') or '1'

-        view_data = self._download_json(
-            'http://api.bilibili.com/view?type=json&appkey=8e9fc618fbd41e28&id=%s&page=%s' % (video_id, page_num),
-            video_id)
-        if 'error' in view_data:
-            raise ExtractorError('%s said: %s' % (self.IE_NAME, view_data['error']), expected=True)
+        webpage = self._download_webpage(url, video_id)

-        cid = view_data['cid']
-        title = unescapeHTML(view_data['title'])
+        params = compat_parse_qs(self._search_regex(
+            [r'EmbedPlayer\([^)]+,\s*"([^"]+)"\)',
+             r'<iframe[^>]+src="https://secure\.bilibili\.com/secure,([^"]+)"'],
+            webpage, 'player parameters'))
+        cid = params['cid'][0]

-        doc = self._download_xml(
-            'http://interface.bilibili.com/v_cdn_play?appkey=8e9fc618fbd41e28&cid=%s' % cid,
-            cid,
-            'Downloading page %s/%s' % (page_num, view_data['pages'])
-        )
+        info_xml_str = self._download_webpage(
+            'http://interface.bilibili.com/v_cdn_play',
+            cid, query={'appkey': self._APP_KEY, 'cid': cid},
+            note='Downloading video info page')

-        if xpath_text(doc, './result') == 'error':
-            raise ExtractorError('%s said: %s' % (self.IE_NAME, xpath_text(doc, './message')), expected=True)
+        err_msg = None
+        durls = None
+        info_xml = None
+        try:
+            info_xml = compat_etree_fromstring(info_xml_str.encode('utf-8'))
+        except compat_xml_parse_error:
+            info_json = self._parse_json(info_xml_str, video_id, fatal=False)
+            err_msg = (info_json or {}).get('error_text')
+        else:
+            err_msg = xpath_text(info_xml, './message')
+
+        if info_xml is not None:
+            durls = info_xml.findall('./durl')
+        if not durls:
+            if err_msg:
+                raise ExtractorError('%s said: %s' % (self.IE_NAME, err_msg), expected=True)
+            else:
+                raise ExtractorError('No videos found!')

        entries = []

-        for durl in doc.findall('./durl'):
+        for durl in durls:
            size = xpath_text(durl, ['./filesize', './size'])
            formats = [{
                'url': durl.find('./url').text,
                'filesize': int_or_none(size),
-                'ext': 'flv',
            }]
-            backup_urls = durl.find('./backup_url')
-            if backup_urls is not None:
-                for backup_url in backup_urls.findall('./url'):
-                    formats.append({'url': backup_url.text})
-            formats.reverse()
+            for backup_url in durl.findall('./backup_url/url'):
+                formats.append({
+                    'url': backup_url.text,
+                    # backup URLs have lower priorities
+                    'preference': -2 if 'hd.mp4' in backup_url.text else -3,
+                })
+
+            self._sort_formats(formats)

            entries.append({
                'id': '%s_part%s' % (cid, xpath_text(durl, './order')),
-                'title': title,
                'duration': int_or_none(xpath_text(durl, './length'), 1000),
                'formats': formats,
            })

+        title = self._html_search_regex('<h1[^>]+title="([^"]+)">', webpage, 'title')
+        description = self._html_search_meta('description', webpage)
+        datetime_str = self._html_search_regex(
+            r'<time[^>]+datetime="([^"]+)"', webpage, 'upload time', fatal=False)
+        if datetime_str:
+            timestamp = calendar.timegm(datetime.datetime.strptime(datetime_str, '%Y-%m-%dT%H:%M').timetuple())
+
+        # TODO 'view_count' requires deobfuscating Javascript
        info = {
            'id': compat_str(cid),
            'title': title,
-            'description': view_data.get('description'),
-            'thumbnail': view_data.get('pic'),
-            'uploader': view_data.get('author'),
-            'timestamp': int_or_none(view_data.get('created')),
-            'view_count': int_or_none(view_data.get('play')),
-            'duration': int_or_none(xpath_text(doc, './timelength')),
+            'description': description,
+            'timestamp': timestamp,
+            'thumbnail': self._html_search_meta('thumbnailUrl', webpage),
+            'duration': float_or_none(xpath_text(info_xml, './timelength'), scale=1000),
        }

+        uploader_mobj = re.search(
+            r'<a[^>]+href="https?://space\.bilibili\.com/(?P<id>\d+)"[^>]+title="(?P<name>[^"]+)"',
+            webpage)
+        if uploader_mobj:
+            info.update({
+                'uploader': uploader_mobj.group('name'),
+                'uploader_id': uploader_mobj.group('id'),
+            })
+
+        for entry in entries:
+            entry.update(info)
+
        if len(entries) == 1:
-            entries[0].update(info)
            return entries[0]
        else:
-            info.update({
+            return {
                '_type': 'multi_video',
                'id': video_id,
+                'title': title,
+                'description': description,
                'entries': entries,
-            })
-            return info
+            }
--- a/youtube_dl/extractor/coub.py
+++ b/youtube_dl/extractor/coub.py
@ -0,0 +1,143 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    float_or_none,
+    int_or_none,
+    parse_iso8601,
+    qualities,
+)
+
+
+class CoubIE(InfoExtractor):
+    _VALID_URL = r'(?:coub:|https?://(?:coub\.com/(?:view|embed|coubs)/|c-cdn\.coub\.com/fb-player\.swf\?.*\bcoub(?:ID|id)=))(?P<id>[\da-z]+)'
+
+    _TESTS = [{
+        'url': 'http://coub.com/view/5u5n1',
+        'info_dict': {
+            'id': '5u5n1',
+            'ext': 'mp4',
+            'title': 'The Matrix Moonwalk',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 4.6,
+            'timestamp': 1428527772,
+            'upload_date': '20150408',
+            'uploader': 'Артём Лоскутников',
+            'uploader_id': 'artyom.loskutnikov',
+            'view_count': int,
+            'like_count': int,
+            'repost_count': int,
+            'comment_count': int,
+            'age_limit': 0,
+        },
+    }, {
+        'url': 'http://c-cdn.coub.com/fb-player.swf?bot_type=vk&coubID=7w5a4',
+        'only_matching': True,
+    }, {
+        'url': 'coub:5u5n1',
+        'only_matching': True,
+    }, {
+        # longer video id
+        'url': 'http://coub.com/view/237d5l5h',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        coub = self._download_json(
+            'http://coub.com/api/v2/coubs/%s.json' % video_id, video_id)
+
+        if coub.get('error'):
+            raise ExtractorError(
+                '%s said: %s' % (self.IE_NAME, coub['error']), expected=True)
+
+        title = coub['title']
+
+        file_versions = coub['file_versions']
+
+        QUALITIES = ('low', 'med', 'high')
+
+        MOBILE = 'mobile'
+        IPHONE = 'iphone'
+        HTML5 = 'html5'
+
+        SOURCE_PREFERENCE = (MOBILE, IPHONE, HTML5)
+
+        quality_key = qualities(QUALITIES)
+        preference_key = qualities(SOURCE_PREFERENCE)
+
+        formats = []
+
+        for kind, items in file_versions.get(HTML5, {}).items():
+            if kind not in ('video', 'audio'):
+                continue
+            if not isinstance(items, dict):
+                continue
+            for quality, item in items.items():
+                if not isinstance(item, dict):
+                    continue
+                item_url = item.get('url')
+                if not item_url:
+                    continue
+                formats.append({
+                    'url': item_url,
+                    'format_id': '%s-%s-%s' % (HTML5, kind, quality),
+                    'filesize': int_or_none(item.get('size')),
+                    'vcodec': 'none' if kind == 'audio' else None,
+                    'quality': quality_key(quality),
+                    'preference': preference_key(HTML5),
+                })
+
+        iphone_url = file_versions.get(IPHONE, {}).get('url')
+        if iphone_url:
+            formats.append({
+                'url': iphone_url,
+                'format_id': IPHONE,
+                'preference': preference_key(IPHONE),
+            })
+
+        mobile_url = file_versions.get(MOBILE, {}).get('audio_url')
+        if mobile_url:
+            formats.append({
+                'url': mobile_url,
+                'format_id': '%s-audio' % MOBILE,
+                'preference': preference_key(MOBILE),
+            })
+
+        self._sort_formats(formats)
+
+        thumbnail = coub.get('picture')
+        duration = float_or_none(coub.get('duration'))
+        timestamp = parse_iso8601(coub.get('published_at') or coub.get('created_at'))
+        uploader = coub.get('channel', {}).get('title')
+        uploader_id = coub.get('channel', {}).get('permalink')
+
+        view_count = int_or_none(coub.get('views_count') or coub.get('views_increase_count'))
+        like_count = int_or_none(coub.get('likes_count'))
+        repost_count = int_or_none(coub.get('recoubs_count'))
+        comment_count = int_or_none(coub.get('comments_count'))
+
+        age_restricted = coub.get('age_restricted', coub.get('age_restricted_by_admin'))
+        if age_restricted is not None:
+            age_limit = 18 if age_restricted is True else 0
+        else:
+            age_limit = None
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'timestamp': timestamp,
+            'uploader': uploader,
+            'uploader_id': uploader_id,
+            'view_count': view_count,
+            'like_count': like_count,
+            'repost_count': repost_count,
+            'comment_count': comment_count,
+            'age_limit': age_limit,
+            'formats': formats,
+        }
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@ -143,6 +143,7 @@ from .cnn import (
    CNNBlogsIE,
    CNNArticleIE,
 )
+from .coub import CoubIE
 from .collegerama import CollegeRamaIE
 from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE
 from .comcarcoff import ComCarCoffIE
--- a/youtube_dl/extractor/udemy.py
+++ b/youtube_dl/extractor/udemy.py
@ -142,7 +142,9 @@ class UdemyIE(InfoExtractor):
            self._LOGIN_URL, None, 'Downloading login popup')

        def is_logged(webpage):
-            return any(p in webpage for p in ['href="https://www.udemy.com/user/logout/', '>Logout<'])
+            return any(re.search(p, webpage) for p in (
+                r'href=["\'](?:https://www\.udemy\.com)?/user/logout/',
+                r'>Logout<'))

        # already logged in
        if is_logged(login_popup):
--- a/youtube_dl/extractor/vk.py
+++ b/youtube_dl/extractor/vk.py
@ -217,7 +217,6 @@ class VKIE(InfoExtractor):
        mobj = re.match(self._VALID_URL, url)
        video_id = mobj.group('videoid')

-        info_url = url
        if video_id:
            info_url = 'https://vk.com/al_video.php?act=show&al=1&module=video&video=%s' % video_id
            # Some videos (removed?) can only be downloaded with list id specified
--- a/youtube_dl/extractor/yandexmusic.py
+++ b/youtube_dl/extractor/yandexmusic.py
@ -20,18 +20,24 @@ class YandexMusicBaseIE(InfoExtractor):
            error = response.get('error')
            if error:
                raise ExtractorError(error, expected=True)
+            if response.get('type') == 'captcha' or 'captcha' in response:
+                YandexMusicBaseIE._raise_captcha()
+
+    @staticmethod
+    def _raise_captcha():
+        raise ExtractorError(
+            'YandexMusic has considered youtube-dl requests automated and '
+            'asks you to solve a CAPTCHA. You can either wait for some '
+            'time until unblocked and optionally use --sleep-interval '
+            'in future or alternatively you can go to https://music.yandex.ru/ '
+            'solve CAPTCHA, then export cookies and pass cookie file to '
+            'youtube-dl with --cookies',
+            expected=True)

    def _download_webpage(self, *args, **kwargs):
        webpage = super(YandexMusicBaseIE, self)._download_webpage(*args, **kwargs)
        if 'Нам очень жаль, но&nbsp;запросы, поступившие с&nbsp;вашего IP-адреса, похожи на&nbsp;автоматические.' in webpage:
-            raise ExtractorError(
-                'YandexMusic has considered youtube-dl requests automated and '
-                'asks you to solve a CAPTCHA. You can either wait for some '
-                'time until unblocked and optionally use --sleep-interval '
-                'in future or alternatively you can go to https://music.yandex.ru/ '
-                'solve CAPTCHA, then export cookies and pass cookie file to '
-                'youtube-dl with --cookies',
-                expected=True)
+            self._raise_captcha()
        return webpage

    def _download_json(self, *args, **kwargs):
--- a/youtube_dl/extractor/youku.py
+++ b/youtube_dl/extractor/youku.py
@ -275,6 +275,8 @@ class YoukuIE(InfoExtractor):
                    'format_id': self.get_format_name(fm),
                    'ext': self.parse_ext_l(fm),
                    'filesize': int(seg['size']),
+                    'width': stream.get('width'),
+                    'height': stream.get('height'),
                })

        return {
--- a/youtube_dl/version.py
+++ b/youtube_dl/version.py
@ -1,3 +1,3 @@
 from __future__ import unicode_literals

-__version__ = '2016.05.21.2'
+__version__ = '2016.05.30.2'