Merge branch 'master' into tvpleextractor

Conflicts:
	youtube_dl/extractor/__init__.py

.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 *2016.04.01*. 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 Issues with outdated version will be rejected.
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.04.06*. 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 Issues with outdated version will be rejected.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 **2016.04.01**
+- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2016.04.06**
 
 ### 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 2016.04.01
+[debug] youtube-dl version 2016.04.06
 [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: {}

.gitignore

@@ -13,6 +13,7 @@ README.txt
 youtube-dl.1
 youtube-dl.bash-completion
 youtube-dl.fish
+youtube_dl/extractor/lazy_extractors.py
 youtube-dl
 youtube-dl.exe
 youtube-dl.tar.gz

CONTRIBUTING.md

@@ -140,14 +140,14 @@ After you have ensured this site is distributing it's content legally, you can f
                 # TODO more properties (see youtube_dl/extractor/common.py)
             }
     ```
-5. Add an import in [`youtube_dl/extractor/__init__.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/__init__.py).
+5. Add an import in [`youtube_dl/extractor/extractors.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/extractors.py).
 6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc.
 7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/58525c94d547be1c8167d16c298bdd75506db328/youtube_dl/extractor/common.py#L68-L226). Add tests and code for as many as you want.
 8. Keep in mind that the only mandatory fields in info dict for successful extraction process are `id`, `title` and either `url` or `formats`, i.e. these are the critical data the extraction does not make any sense without. This means that [any field](https://github.com/rg3/youtube-dl/blob/58525c94d547be1c8167d16c298bdd75506db328/youtube_dl/extractor/common.py#L138-L226) apart from aforementioned mandatory ones should be treated **as optional** and extraction should be **tolerate** to situations when sources for these fields can potentially be unavailable (even if they always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields. For example, if you have some intermediate dict `meta` that is a source of metadata and it has a key `summary` that you want to extract and put into resulting info dict as `description`, you should be ready that this key may be missing from the `meta` dict, i.e. you should extract it as `meta.get('summary')` and not `meta['summary']`. Similarly, you should pass `fatal=False` when extracting data from a webpage with `_search_regex/_html_search_regex`.
 9. Check the code with [flake8](https://pypi.python.org/pypi/flake8).
 10. When the tests pass, [add](http://git-scm.com/docs/git-add) the new files and [commit](http://git-scm.com/docs/git-commit) them and [push](http://git-scm.com/docs/git-push) the result, like this:
 
-        $ git add youtube_dl/extractor/__init__.py
+        $ git add youtube_dl/extractor/extractors.py
         $ git add youtube_dl/extractor/yourextractor.py
         $ git commit -m '[yourextractor] Add new extractor'
         $ git push origin yourextractor

Makefile

@@ -1,7 +1,7 @@
-all: youtube-dl README.md CONTRIBUTING.md ISSUE_TEMPLATE.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish supportedsites
+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 *.dump *.part *.info.json *.mp4 *.flv *.mp3 *.avi 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 *.flv *.mp3 *.avi CONTRIBUTING.md.tmp ISSUE_TEMPLATE.md.tmp youtube-dl youtube-dl.exe
 	find . -name "*.pyc" -delete
 	find . -name "*.class" -delete
 
@@ -59,7 +59,7 @@ README.md: youtube_dl/*.py youtube_dl/*/*.py
 CONTRIBUTING.md: README.md
 	$(PYTHON) devscripts/make_contributing.py README.md CONTRIBUTING.md
 
-ISSUE_TEMPLATE.md:
+.github/ISSUE_TEMPLATE.md: devscripts/make_issue_template.py .github/ISSUE_TEMPLATE_tmpl.md  youtube_dl/version.py
 	$(PYTHON) devscripts/make_issue_template.py .github/ISSUE_TEMPLATE_tmpl.md .github/ISSUE_TEMPLATE.md
 
 supportedsites:
@@ -88,6 +88,12 @@ youtube-dl.fish: youtube_dl/*.py youtube_dl/*/*.py devscripts/fish-completion.in
 
 fish-completion: youtube-dl.fish
 
+lazy-extractors: youtube_dl/extractor/lazy_extractors.py
+
+_EXTRACTOR_FILES != find youtube_dl/extractor -iname '*.py' -and -not -iname 'lazy_extractors.py'
+youtube_dl/extractor/lazy_extractors.py: devscripts/make_lazy_extractors.py devscripts/lazy_load_template.py $(_EXTRACTOR_FILES)
+	$(PYTHON) devscripts/make_lazy_extractors.py $@
+
 youtube-dl.tar.gz: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish
 	@tar -czf youtube-dl.tar.gz --transform "s|^|youtube-dl/|" --owner 0 --group 0 \
 		--exclude '*.DS_Store' \

README.md

@@ -889,14 +889,14 @@ After you have ensured this site is distributing it's content legally, you can f
                 # TODO more properties (see youtube_dl/extractor/common.py)
             }
     ```
-5. Add an import in [`youtube_dl/extractor/__init__.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/__init__.py).
+5. Add an import in [`youtube_dl/extractor/extractors.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/extractors.py).
 6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc.
 7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/58525c94d547be1c8167d16c298bdd75506db328/youtube_dl/extractor/common.py#L68-L226). Add tests and code for as many as you want.
 8. Keep in mind that the only mandatory fields in info dict for successful extraction process are `id`, `title` and either `url` or `formats`, i.e. these are the critical data the extraction does not make any sense without. This means that [any field](https://github.com/rg3/youtube-dl/blob/58525c94d547be1c8167d16c298bdd75506db328/youtube_dl/extractor/common.py#L138-L226) apart from aforementioned mandatory ones should be treated **as optional** and extraction should be **tolerate** to situations when sources for these fields can potentially be unavailable (even if they always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields. For example, if you have some intermediate dict `meta` that is a source of metadata and it has a key `summary` that you want to extract and put into resulting info dict as `description`, you should be ready that this key may be missing from the `meta` dict, i.e. you should extract it as `meta.get('summary')` and not `meta['summary']`. Similarly, you should pass `fatal=False` when extracting data from a webpage with `_search_regex/_html_search_regex`.
 9. Check the code with [flake8](https://pypi.python.org/pypi/flake8).
 10. When the tests pass, [add](http://git-scm.com/docs/git-add) the new files and [commit](http://git-scm.com/docs/git-commit) them and [push](http://git-scm.com/docs/git-push) the result, like this:
 
-        $ git add youtube_dl/extractor/__init__.py
+        $ git add youtube_dl/extractor/extractors.py
         $ git add youtube_dl/extractor/yourextractor.py
         $ git commit -m '[yourextractor] Add new extractor'
         $ git push origin yourextractor

devscripts/lazy_load_template.py

@@ -0,0 +1,19 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+
+class LazyLoadExtractor(object):
+    _module = None
+
+    @classmethod
+    def ie_key(cls):
+        return cls.__name__[:-2]
+
+    def __new__(cls, *args, **kwargs):
+        mod = __import__(cls._module, fromlist=(cls.__name__,))
+        real_cls = getattr(mod, cls.__name__)
+        instance = real_cls.__new__(real_cls)
+        instance.__init__(*args, **kwargs)
+        return instance

devscripts/make_lazy_extractors.py

@@ -0,0 +1,63 @@
+from __future__ import unicode_literals, print_function
+
+from inspect import getsource
+import os
+from os.path import dirname as dirn
+import sys
+
+print('WARNING: Lazy loading extractors is an experimental feature that may not always work', file=sys.stderr)
+
+sys.path.insert(0, dirn(dirn((os.path.abspath(__file__)))))
+
+lazy_extractors_filename = sys.argv[1]
+if os.path.exists(lazy_extractors_filename):
+    os.remove(lazy_extractors_filename)
+
+from youtube_dl.extractor import _ALL_CLASSES
+from youtube_dl.extractor.common import InfoExtractor
+
+with open('devscripts/lazy_load_template.py', 'rt') as f:
+    module_template = f.read()
+
+module_contents = [module_template + '\n' + getsource(InfoExtractor.suitable)]
+
+ie_template = '''
+class {name}(LazyLoadExtractor):
+    _VALID_URL = {valid_url!r}
+    _module = '{module}'
+'''
+
+make_valid_template = '''
+    @classmethod
+    def _make_valid_url(cls):
+        return {valid_url!r}
+'''
+
+
+def build_lazy_ie(ie, name):
+    valid_url = getattr(ie, '_VALID_URL', None)
+    s = ie_template.format(
+        name=name,
+        valid_url=valid_url,
+        module=ie.__module__)
+    if ie.suitable.__func__ is not InfoExtractor.suitable.__func__:
+        s += '\n' + getsource(ie.suitable)
+    if hasattr(ie, '_make_valid_url'):
+        # search extractors
+        s += make_valid_template.format(valid_url=ie._make_valid_url())
+    return s
+
+names = []
+for ie in list(sorted(_ALL_CLASSES[:-1], key=lambda cls: cls.ie_key())) + _ALL_CLASSES[-1:]:
+    name = ie.ie_key() + 'IE'
+    src = build_lazy_ie(ie, name)
+    module_contents.append(src)
+    names.append(name)
+
+module_contents.append(
+    '_ALL_CLASSES = [{0}]'.format(', '.join(names)))
+
+module_src = '\n'.join(module_contents) + '\n'
+
+with open(lazy_extractors_filename, 'wt') as f:
+    f.write(module_src)

devscripts/release.sh

@@ -46,7 +46,7 @@ fi
 sed -i "s/__version__ = '.*'/__version__ = '$version'/" youtube_dl/version.py
 
 /bin/echo -e "\n### Committing documentation, templates and youtube_dl/version.py..."
-make README.md CONTRIBUTING.md ISSUE_TEMPLATE.md supportedsites
+make README.md CONTRIBUTING.md .github/ISSUE_TEMPLATE.md supportedsites
 git add README.md CONTRIBUTING.md .github/ISSUE_TEMPLATE.md docs/supportedsites.md youtube_dl/version.py
 git commit -m "release $version"
 

docs/supportedsites.md

@@ -57,6 +57,7 @@
  - **AudioBoom**
  - **audiomack**
  - **audiomack:album**
+ - **auroravid**: AuroraVid
  - **Azubu**
  - **AzubuLive**
  - **BaiduVideo**: 百度视频
@@ -92,12 +93,14 @@
  - **BYUtv**
  - **Camdemy**
  - **CamdemyFolder**
+ - **CamWithHer**
  - **canalc2.tv**
  - **Canalplus**: canalplus.fr, piwiplus.fr and d8.tv
  - **Canvas**
  - **CBC**
  - **CBCPlayer**
  - **CBS**
+ - **CBSInteractive**
  - **CBSNews**: CBS News
  - **CBSNewsLiveVideo**: CBS News Live Videos
  - **CBSSports**
@@ -119,7 +122,6 @@
  - **Clyp**
  - **cmt.com**
  - **CNBC**
- - **CNET**
  - **CNN**
  - **CNNArticle**
  - **CNNBlogs**
@@ -419,7 +421,6 @@
  - **Normalboots**
  - **NosVideo**
  - **Nova**: TN.cz, Prásk.tv, Nova.cz, Novaplus.cz, FANDA.tv, Krásná.cz and Doma.cz
- - **novamov**: NovaMov
  - **nowness**
  - **nowness:playlist**
  - **nowness:series**

setup.cfg

@@ -2,5 +2,5 @@
 universal = True
 
 [flake8]
-exclude = youtube_dl/extractor/__init__.py,devscripts/buildserver.py,devscripts/make_issue_template.py,setup.py,build,.git
+exclude = youtube_dl/extractor/__init__.py,devscripts/buildserver.py,devscripts/lazy_load_template.py,devscripts/make_issue_template.py,setup.py,build,.git
 ignore = E402,E501,E731

setup.py

@@ -8,11 +8,12 @@ import warnings
 import sys
 
 try:
-    from setuptools import setup
+    from setuptools import setup, Command
     setuptools_available = True
 except ImportError:
-    from distutils.core import setup
+    from distutils.core import setup, Command
     setuptools_available = False
+from distutils.spawn import spawn
 
 try:
     # This will create an exe that needs Microsoft Visual C++ 2008
@@ -70,6 +71,22 @@ else:
     else:
         params['scripts'] = ['bin/youtube-dl']
 
+class build_lazy_extractors(Command):
+    description = "Build the extractor lazy loading module"
+    user_options = []
+
+    def initialize_options(self):
+        pass
+
+    def finalize_options(self):
+        pass
+
+    def run(self):
+        spawn(
+            [sys.executable, 'devscripts/make_lazy_extractors.py', 'youtube_dl/extractor/lazy_extractors.py'],
+            dry_run=self.dry_run,
+        )
+
 # Get the version from youtube_dl/version.py without importing the package
 exec(compile(open('youtube_dl/version.py').read(),
              'youtube_dl/version.py', 'exec'))
@@ -107,5 +124,6 @@ setup(
         "Programming Language :: Python :: 3.4",
     ],
 
+    cmdclass={'build_lazy_extractors': build_lazy_extractors},
     **params
 )

test/test_compat.py

@@ -76,6 +76,10 @@ class TestCompat(unittest.TestCase):
         self.assertEqual(compat_urllib_parse_urlencode({'abc': b'def'}), 'abc=def')
         self.assertEqual(compat_urllib_parse_urlencode({b'abc': 'def'}), 'abc=def')
         self.assertEqual(compat_urllib_parse_urlencode({b'abc': b'def'}), 'abc=def')
+        self.assertEqual(compat_urllib_parse_urlencode([('abc', 'def')]), 'abc=def')
+        self.assertEqual(compat_urllib_parse_urlencode([('abc', b'def')]), 'abc=def')
+        self.assertEqual(compat_urllib_parse_urlencode([(b'abc', 'def')]), 'abc=def')
+        self.assertEqual(compat_urllib_parse_urlencode([(b'abc', b'def')]), 'abc=def')
 
     def test_compat_shlex_split(self):
         self.assertEqual(compat_shlex_split('-option "one two"'), ['-option', 'one two'])

youtube_dl/YoutubeDL.py

@@ -82,7 +82,7 @@ from .utils import (
     YoutubeDLHandler,
 )
 from .cache import Cache
-from .extractor import get_info_extractor, gen_extractors
+from .extractor import get_info_extractor, gen_extractor_classes, _LAZY_LOADER
 from .downloader import get_suitable_downloader
 from .downloader.rtmp import rtmpdump_version
 from .postprocessor import (
@@ -378,6 +378,7 @@ class YoutubeDL(object):
     def add_info_extractor(self, ie):
         """Add an InfoExtractor object to the end of the list."""
         self._ies.append(ie)
+        if not isinstance(ie, type):
             self._ies_instances[ie.ie_key()] = ie
             ie.set_downloader(self)
 
@@ -397,7 +398,7 @@ class YoutubeDL(object):
         """
         Add the InfoExtractors returned by gen_extractors to the end of the list
         """
-        for ie in gen_extractors():
+        for ie in gen_extractor_classes():
             self.add_info_extractor(ie)
 
     def add_post_processor(self, pp):
@@ -661,6 +662,7 @@ class YoutubeDL(object):
             if not ie.suitable(url):
                 continue
 
+            ie = self.get_info_extractor(ie.ie_key())
             if not ie.working():
                 self.report_warning('The program functionality for this site has been marked as broken, '
                                     'and will probably not work.')
@@ -1240,7 +1242,10 @@ class YoutubeDL(object):
             self.list_thumbnails(info_dict)
             return
 
-        if thumbnails and 'thumbnail' not in info_dict:
+        thumbnail = info_dict.get('thumbnail')
+        if thumbnail:
+            info_dict['thumbnail'] = sanitize_url(thumbnail)
+        elif thumbnails:
             info_dict['thumbnail'] = thumbnails[-1]['url']
 
         if 'display_id' not in info_dict and 'id' in info_dict:
@@ -1954,6 +1959,8 @@ class YoutubeDL(object):
         write_string(encoding_str, encoding=None)
 
         self._write_string('[debug] youtube-dl version ' + __version__ + '\n')
+        if _LAZY_LOADER:
+            self._write_string('[debug] Lazy loading extractors enabled' + '\n')
         try:
             sp = subprocess.Popen(
                 ['git', 'rev-parse', '--short', 'HEAD'],

youtube_dl/compat.py

@@ -181,7 +181,8 @@ except ImportError:  # Python 2
             if isinstance(e, dict):
                 e = encode_dict(e)
             elif isinstance(e, (list, tuple,)):
-                e = encode_list(e)
+                list_e = encode_list(e)
+                e = tuple(list_e) if isinstance(e, tuple) else list_e
             elif isinstance(e, compat_str):
                 e = e.encode(encoding)
             return e

youtube_dl/extractor/acast.py

@@ -2,10 +2,14 @@
 from __future__ import unicode_literals
 
 import re
+import functools
 
 from .common import InfoExtractor
 from ..compat import compat_str
-from ..utils import int_or_none
+from ..utils import (
+    int_or_none,
+    OnDemandPagedList,
+)
 
 
 class ACastIE(InfoExtractor):
@@ -26,13 +30,8 @@ class ACastIE(InfoExtractor):
 
     def _real_extract(self, url):
         channel, display_id = re.match(self._VALID_URL, url).groups()
-
+        cast_data = self._download_json(
-        embed_page = self._download_webpage(
+            'https://embed.acast.com/api/acasts/%s/%s' % (channel, display_id), display_id)
-            re.sub('(?:www\.)?acast\.com', 'embedcdn.acast.com', url), display_id)
-        cast_data = self._parse_json(self._search_regex(
-            r'window\[\'acast/queries\'\]\s*=\s*([^;]+);', embed_page, 'acast data'),
-            display_id)['GetAcast/%s/%s' % (channel, display_id)]
-
         return {
             'id': compat_str(cast_data['id']),
             'display_id': display_id,
@@ -58,15 +57,26 @@ class ACastChannelIE(InfoExtractor):
         'playlist_mincount': 20,
     }
     _API_BASE_URL = 'https://www.acast.com/api/'
+    _PAGE_SIZE = 10
 
     @classmethod
     def suitable(cls, url):
         return False if ACastIE.suitable(url) else super(ACastChannelIE, cls).suitable(url)
 
-    def _real_extract(self, url):
+    def _fetch_page(self, channel_slug, page):
-        display_id = self._match_id(url)
+        casts = self._download_json(
-        channel_data = self._download_json(self._API_BASE_URL + 'channels/%s' % display_id, display_id)
+            self._API_BASE_URL + 'channels/%s/acasts?page=%s' % (channel_slug, page),
-        casts = self._download_json(self._API_BASE_URL + 'channels/%s/acasts' % display_id, display_id)
+            channel_slug, note='Download page %d of channel data' % page)
-        entries = [self.url_result('https://www.acast.com/%s/%s' % (display_id, cast['url']), 'ACast') for cast in casts]
+        for cast in casts:
+            yield self.url_result(
+                'https://www.acast.com/%s/%s' % (channel_slug, cast['url']),
+                'ACast', cast['id'])
 
-        return self.playlist_result(entries, compat_str(channel_data['id']), channel_data['name'], channel_data.get('description'))
+    def _real_extract(self, url):
+        channel_slug = self._match_id(url)
+        channel_data = self._download_json(
+            self._API_BASE_URL + 'channels/%s' % channel_slug, channel_slug)
+        entries = OnDemandPagedList(functools.partial(
+            self._fetch_page, channel_slug), self._PAGE_SIZE)
+        return self.playlist_result(entries, compat_str(
+            channel_data['id']), channel_data['name'], channel_data.get('description'))

youtube_dl/extractor/beeg.py

@@ -33,8 +33,33 @@ class BeegIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
+        webpage = self._download_webpage(url, video_id)
+
+        cpl_url = self._search_regex(
+            r'<script[^>]+src=(["\'])(?P<url>(?:https?:)?//static\.beeg\.com/cpl/\d+\.js.*?)\1',
+            webpage, 'cpl', default=None, group='url')
+
+        beeg_version, beeg_salt = [None] * 2
+
+        if cpl_url:
+            cpl = self._download_webpage(
+                self._proto_relative_url(cpl_url), video_id,
+                'Downloading cpl JS', fatal=False)
+            if cpl:
+                beeg_version = self._search_regex(
+                    r'beeg_version\s*=\s*(\d+)', cpl,
+                    'beeg version', default=None) or self._search_regex(
+                    r'/(\d+)\.js', cpl_url, 'beeg version', default=None)
+                beeg_salt = self._search_regex(
+                    r'beeg_salt\s*=\s*(["\'])(?P<beeg_salt>.+?)\1', cpl, 'beeg beeg_salt',
+                    default=None, group='beeg_salt')
+
+        beeg_version = beeg_version or '1750'
+        beeg_salt = beeg_salt or 'MIDtGaw96f0N1kMMAM1DE46EC9pmFr'
+
         video = self._download_json(
-            'https://api.beeg.com/api/v6/1738/video/%s' % video_id, video_id)
+            'http://api.beeg.com/api/v6/%s/video/%s' % (beeg_version, video_id),
+            video_id)
 
         def split(o, e):
             def cut(s, x):
@@ -51,7 +76,7 @@ class BeegIE(InfoExtractor):
 
         def decrypt_key(key):
             # Reverse engineered from http://static.beeg.com/cpl/1738.js
-            a = 'GUuyodcfS8FW8gQp4OKLMsZBcX0T7B'
+            a = beeg_salt
             e = compat_urllib_parse_unquote(key)
             o = ''.join([
                 compat_chr(compat_ord(e[n]) - compat_ord(a[n % len(a)]) % 21)
@@ -101,5 +126,5 @@ class BeegIE(InfoExtractor):
             'duration': duration,
             'tags': tags,
             'formats': formats,
-            'age_limit': 18,
+            'age_limit': self._rta_search(webpage),
         }

youtube_dl/extractor/brightcove.py

@@ -48,7 +48,7 @@ class BrightcoveLegacyIE(InfoExtractor):
                 'description': 'md5:a950cc4285c43e44d763d036710cd9cd',
                 'timestamp': 1368213670,
                 'upload_date': '20130510',
-                'uploader_id': 1589608506001,
+                'uploader_id': '1589608506001',
             }
         },
         {
@@ -62,7 +62,7 @@ class BrightcoveLegacyIE(InfoExtractor):
                 'uploader': 'Oracle',
                 'timestamp': 1344975024,
                 'upload_date': '20120814',
-                'uploader_id': 1460825906,
+                'uploader_id': '1460825906',
             },
         },
         {
@@ -76,7 +76,7 @@ class BrightcoveLegacyIE(InfoExtractor):
                 'uploader': 'Mashable',
                 'timestamp': 1382041798,
                 'upload_date': '20131017',
-                'uploader_id': 1130468786001,
+                'uploader_id': '1130468786001',
             },
         },
         {
@@ -104,7 +104,7 @@ class BrightcoveLegacyIE(InfoExtractor):
                 'description': 'UCI MTB World Cup 2014: Fort William, UK - Downhill Finals',
                 'timestamp': 1409122195,
                 'upload_date': '20140827',
-                'uploader_id': 710858724001,
+                'uploader_id': '710858724001',
             },
         },
         {
@@ -307,13 +307,14 @@ class BrightcoveLegacyIE(InfoExtractor):
                                     playlist_title=playlist_info['mediaCollectionDTO']['displayName'])
 
     def _extract_video_info(self, video_info):
+        publisher_id = video_info.get('publisherId')
         info = {
             'id': compat_str(video_info['id']),
             'title': video_info['displayName'].strip(),
             'description': video_info.get('shortDescription'),
             'thumbnail': video_info.get('videoStillURL') or video_info.get('thumbnailURL'),
             'uploader': video_info.get('publisherName'),
-            'uploader_id': video_info.get('publisherId'),
+            'uploader_id': compat_str(publisher_id) if publisher_id else None,
             'duration': float_or_none(video_info.get('length'), 1000),
             'timestamp': int_or_none(video_info.get('creationDate'), 1000),
         }

youtube_dl/extractor/common.py

@@ -232,6 +232,24 @@ class InfoExtractor(object):
     episode_number: Number of the video episode within a season, as an integer.
     episode_id:     Id of the video episode, as a unicode string.
 
+    The following fields should only be used when the media is a track or a part of
+    a music album:
+
+    track:          Title of the track.
+    track_number:   Number of the track within an album or a disc, as an integer.
+    track_id:       Id of the track (useful in case of custom indexing, e.g. 6.iii),
+                    as a unicode string.
+    artist:         Artist(s) of the track.
+    genre:          Genre(s) of the track.
+    album:          Title of the album the track belongs to.
+    album_type:     Type of the album (e.g. "Demo", "Full-length", "Split", "Compilation", etc).
+    album_artist:   List of all artists appeared on the album (e.g.
+                    "Ash Borer / Fell Voices" or "Various Artists", useful for splits
+                    and compilations).
+    disc_number:    Number of the disc or other physical medium the track belongs to,
+                    as an integer.
+    release_year:   Year (YYYY) when the album was released.
+
     Unless mentioned otherwise, the fields should be Unicode strings.
 
     Unless mentioned otherwise, None is equivalent to absence of information.
@@ -825,7 +843,7 @@ class InfoExtractor(object):
         for input in re.findall(r'(?i)<input([^>]+)>', html):
             if not re.search(r'type=(["\'])(?:hidden|submit)\1', input):
                 continue
-            name = re.search(r'name=(["\'])(?P<value>.+?)\1', input)
+            name = re.search(r'(?:name|id)=(["\'])(?P<value>.+?)\1', input)
             if not name:
                 continue
             value = re.search(r'value=(["\'])(?P<value>.*?)\1', input)
@@ -1516,7 +1534,7 @@ class InfoExtractor(object):
                             media_template = representation_ms_info['media_template']
                             media_template = media_template.replace('$RepresentationID$', representation_id)
                             media_template = re.sub(r'\$(Number|Bandwidth)\$', r'%(\1)d', media_template)
-                            media_template = re.sub(r'\$(Number|Bandwidth)%(\d+)\$', r'%(\1)\2d', media_template)
+                            media_template = re.sub(r'\$(Number|Bandwidth)%([^$]+)\$', r'%(\1)\2', media_template)
                             media_template.replace('$$', '$')
                             representation_ms_info['segment_urls'] = [
                                 media_template % {

youtube_dl/extractor/deezer.py

@@ -41,7 +41,9 @@ class DeezerPlaylistIE(InfoExtractor):
                 'Deezer said: %s' % geoblocking_msg, expected=True)
 
         data_json = self._search_regex(
-            r'naboo\.display\(\'[^\']+\',\s*(.*?)\);\n', webpage, 'data JSON')
+            (r'__DZR_APP_STATE__\s*=\s*({.+?})\s*</script>',
+             r'naboo\.display\(\'[^\']+\',\s*(.*?)\);\n'),
+            webpage, 'data JSON')
         data = json.loads(data_json)
 
         playlist_title = data.get('DATA', {}).get('TITLE')

youtube_dl/extractor/democracynow.py

@@ -17,37 +17,53 @@ class DemocracynowIE(InfoExtractor):
     IE_NAME = 'democracynow'
     _TESTS = [{
         'url': 'http://www.democracynow.org/shows/2015/7/3',
-        'md5': 'fbb8fe3d7a56a5e12431ce2f9b2fab0d',
+        'md5': '3757c182d3d84da68f5c8f506c18c196',
         'info_dict': {
             'id': '2015-0703-001',
             'ext': 'mp4',
-            'title': 'July 03, 2015 - Democracy Now!',
+            'title': 'Daily Show',
-            'description': 'A daily independent global news hour with Amy Goodman & Juan González "What to the Slave is 4th of July?": James Earl Jones Reads Frederick Douglass\u2019 Historic Speech : "This Flag Comes Down Today": Bree Newsome Scales SC Capitol Flagpole, Takes Down Confederate Flag : "We Shall Overcome": Remembering Folk Icon, Activist Pete Seeger in His Own Words & Songs',
         },
     }, {
         'url': 'http://www.democracynow.org/2015/7/3/this_flag_comes_down_today_bree',
-        'md5': 'fbb8fe3d7a56a5e12431ce2f9b2fab0d',
         'info_dict': {
             'id': '2015-0703-001',
             'ext': 'mp4',
             'title': '"This Flag Comes Down Today": Bree Newsome Scales SC Capitol Flagpole, Takes Down Confederate Flag',
             'description': 'md5:4d2bc4f0d29f5553c2210a4bc7761a21',
         },
+        'params': {
+            'skip_download': True,
+        },
     }]
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
+
         webpage = self._download_webpage(url, display_id)
-        description = self._og_search_description(webpage)
 
         json_data = self._parse_json(self._search_regex(
             r'<script[^>]+type="text/json"[^>]*>\s*({[^>]+})', webpage, 'json'),
             display_id)
-        video_id = None
+
+        title = json_data['title']
         formats = []
 
-        default_lang = 'en'
+        video_id = None
 
+        for key in ('file', 'audio', 'video', 'high_res_video'):
+            media_url = json_data.get(key, '')
+            if not media_url:
+                continue
+            media_url = re.sub(r'\?.*', '', compat_urlparse.urljoin(url, media_url))
+            video_id = video_id or remove_start(os.path.splitext(url_basename(media_url))[0], 'dn')
+            formats.append({
+                'url': media_url,
+                'vcodec': 'none' if key == 'audio' else None,
+            })
+
+        self._sort_formats(formats)
+
+        default_lang = 'en'
         subtitles = {}
 
         def add_subtitle_item(lang, info_dict):
@@ -67,22 +83,13 @@ class DemocracynowIE(InfoExtractor):
                 'url': compat_urlparse.urljoin(url, subtitle_item['url']),
             })
 
-        for key in ('file', 'audio', 'video'):
+        description = self._og_search_description(webpage, default=None)
-            media_url = json_data.get(key, '')
-            if not media_url:
-                continue
-            media_url = re.sub(r'\?.*', '', compat_urlparse.urljoin(url, media_url))
-            video_id = video_id or remove_start(os.path.splitext(url_basename(media_url))[0], 'dn')
-            formats.append({
-                'url': media_url,
-            })
-
-        self._sort_formats(formats)
 
         return {
             'id': video_id or display_id,
-            'title': json_data['title'],
+            'title': title,
             'description': description,
+            'thumbnail': json_data.get('image'),
             'subtitles': subtitles,
             'formats': formats,
         }

youtube_dl/extractor/extractors.py

@@ -0,0 +1,991 @@
+# flake8: noqa
+from __future__ import unicode_literals
+
+from .abc import ABCIE
+from .abc7news import Abc7NewsIE
+from .academicearth import AcademicEarthCourseIE
+from .acast import (
+    ACastIE,
+    ACastChannelIE,
+)
+from .addanime import AddAnimeIE
+from .adobetv import (
+    AdobeTVIE,
+    AdobeTVShowIE,
+    AdobeTVChannelIE,
+    AdobeTVVideoIE,
+)
+from .adultswim import AdultSwimIE
+from .aenetworks import AENetworksIE
+from .aftonbladet import AftonbladetIE
+from .airmozilla import AirMozillaIE
+from .aljazeera import AlJazeeraIE
+from .alphaporno import AlphaPornoIE
+from .animeondemand import AnimeOnDemandIE
+from .anitube import AnitubeIE
+from .anysex import AnySexIE
+from .aol import (
+    AolIE,
+    AolFeaturesIE,
+)
+from .allocine import AllocineIE
+from .aparat import AparatIE
+from .appleconnect import AppleConnectIE
+from .appletrailers import (
+    AppleTrailersIE,
+    AppleTrailersSectionIE,
+)
+from .archiveorg import ArchiveOrgIE
+from .ard import (
+    ARDIE,
+    ARDMediathekIE,
+    SportschauIE,
+)
+from .arte import (
+    ArteTvIE,
+    ArteTVPlus7IE,
+    ArteTVCreativeIE,
+    ArteTVConcertIE,
+    ArteTVFutureIE,
+    ArteTVCinemaIE,
+    ArteTVDDCIE,
+    ArteTVMagazineIE,
+    ArteTVEmbedIE,
+)
+from .atresplayer import AtresPlayerIE
+from .atttechchannel import ATTTechChannelIE
+from .audimedia import AudiMediaIE
+from .audioboom import AudioBoomIE
+from .audiomack import AudiomackIE, AudiomackAlbumIE
+from .azubu import AzubuIE, AzubuLiveIE
+from .baidu import BaiduVideoIE
+from .bambuser import BambuserIE, BambuserChannelIE
+from .bandcamp import BandcampIE, BandcampAlbumIE
+from .bbc import (
+    BBCCoUkIE,
+    BBCCoUkArticleIE,
+    BBCIE,
+)
+from .beeg import BeegIE
+from .behindkink import BehindKinkIE
+from .beatportpro import BeatportProIE
+from .bet import BetIE
+from .bigflix import BigflixIE
+from .bild import BildIE
+from .bilibili import BiliBiliIE
+from .biobiochiletv import BioBioChileTVIE
+from .bleacherreport import (
+    BleacherReportIE,
+    BleacherReportCMSIE,
+)
+from .blinkx import BlinkxIE
+from .bloomberg import BloombergIE
+from .bokecc import BokeCCIE
+from .bpb import BpbIE
+from .br import BRIE
+from .bravotv import BravoTVIE
+from .breakcom import BreakIE
+from .brightcove import (
+    BrightcoveLegacyIE,
+    BrightcoveNewIE,
+)
+from .buzzfeed import BuzzFeedIE
+from .byutv import BYUtvIE
+from .c56 import C56IE
+from .camdemy import (
+    CamdemyIE,
+    CamdemyFolderIE
+)
+from .camwithher import CamWithHerIE
+from .canalplus import CanalplusIE
+from .canalc2 import Canalc2IE
+from .canvas import CanvasIE
+from .cbc import (
+    CBCIE,
+    CBCPlayerIE,
+)
+from .cbs import CBSIE
+from .cbsinteractive import CBSInteractiveIE
+from .cbsnews import (
+    CBSNewsIE,
+    CBSNewsLiveVideoIE,
+)
+from .cbssports import CBSSportsIE
+from .ccc import CCCIE
+from .cda import CDAIE
+from .ceskatelevize import CeskaTelevizeIE
+from .channel9 import Channel9IE
+from .chaturbate import ChaturbateIE
+from .chilloutzone import ChilloutzoneIE
+from .chirbit import (
+    ChirbitIE,
+    ChirbitProfileIE,
+)
+from .cinchcast import CinchcastIE
+from .cinemassacre import CinemassacreIE
+from .clipfish import ClipfishIE
+from .cliphunter import CliphunterIE
+from .clipsyndicate import ClipsyndicateIE
+from .cloudy import CloudyIE
+from .clubic import ClubicIE
+from .clyp import ClypIE
+from .cmt import CMTIE
+from .cnbc import CNBCIE
+from .cnn import (
+    CNNIE,
+    CNNBlogsIE,
+    CNNArticleIE,
+)
+from .collegehumor import CollegeHumorIE
+from .collegerama import CollegeRamaIE
+from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE
+from .comcarcoff import ComCarCoffIE
+from .commonmistakes import CommonMistakesIE, UnicodeBOMIE
+from .commonprotocols import RtmpIE
+from .condenast import CondeNastIE
+from .cracked import CrackedIE
+from .crackle import CrackleIE
+from .criterion import CriterionIE
+from .crooksandliars import CrooksAndLiarsIE
+from .crunchyroll import (
+    CrunchyrollIE,
+    CrunchyrollShowPlaylistIE
+)
+from .cspan import CSpanIE
+from .ctsnews import CtsNewsIE
+from .cultureunplugged import CultureUnpluggedIE
+from .cwtv import CWTVIE
+from .dailymotion import (
+    DailymotionIE,
+    DailymotionPlaylistIE,
+    DailymotionUserIE,
+    DailymotionCloudIE,
+)
+from .daum import (
+    DaumIE,
+    DaumClipIE,
+    DaumPlaylistIE,
+    DaumUserIE,
+)
+from .dbtv import DBTVIE
+from .dcn import (
+    DCNIE,
+    DCNVideoIE,
+    DCNLiveIE,
+    DCNSeasonIE,
+)
+from .dctp import DctpTvIE
+from .deezer import DeezerPlaylistIE
+from .democracynow import DemocracynowIE
+from .dfb import DFBIE
+from .dhm import DHMIE
+from .dotsub import DotsubIE
+from .douyutv import DouyuTVIE
+from .dplay import DPlayIE
+from .dramafever import (
+    DramaFeverIE,
+    DramaFeverSeriesIE,
+)
+from .dreisat import DreiSatIE
+from .drbonanza import DRBonanzaIE
+from .drtuber import DrTuberIE
+from .drtv import DRTVIE
+from .dvtv import DVTVIE
+from .dump import DumpIE
+from .dumpert import DumpertIE
+from .defense import DefenseGouvFrIE
+from .discovery import DiscoveryIE
+from .dropbox import DropboxIE
+from .dw import (
+    DWIE,
+    DWArticleIE,
+)
+from .eagleplatform import EaglePlatformIE
+from .ebaumsworld import EbaumsWorldIE
+from .echomsk import EchoMskIE
+from .ehow import EHowIE
+from .eighttracks import EightTracksIE
+from .einthusan import EinthusanIE
+from .eitb import EitbIE
+from .ellentv import (
+    EllenTVIE,
+    EllenTVClipsIE,
+)
+from .elpais import ElPaisIE
+from .embedly import EmbedlyIE
+from .engadget import EngadgetIE
+from .eporner import EpornerIE
+from .eroprofile import EroProfileIE
+from .escapist import EscapistIE
+from .espn import ESPNIE
+from .esri import EsriVideoIE
+from .europa import EuropaIE
+from .everyonesmixtape import EveryonesMixtapeIE
+from .exfm import ExfmIE
+from .expotv import ExpoTVIE
+from .extremetube import ExtremeTubeIE
+from .facebook import FacebookIE
+from .faz import FazIE
+from .fc2 import FC2IE
+from .fczenit import FczenitIE
+from .firstpost import FirstpostIE
+from .firsttv import FirstTVIE
+from .fivemin import FiveMinIE
+from .fivetv import FiveTVIE
+from .fktv import FKTVIE
+from .flickr import FlickrIE
+from .folketinget import FolketingetIE
+from .footyroom import FootyRoomIE
+from .fourtube import FourTubeIE
+from .fox import FOXIE
+from .foxgay import FoxgayIE
+from .foxnews import FoxNewsIE
+from .foxsports import FoxSportsIE
+from .franceculture import (
+    FranceCultureIE,
+    FranceCultureEmissionIE,
+)
+from .franceinter import FranceInterIE
+from .francetv import (
+    PluzzIE,
+    FranceTvInfoIE,
+    FranceTVIE,
+    GenerationQuoiIE,
+    CultureboxIE,
+)
+from .freesound import FreesoundIE
+from .freespeech import FreespeechIE
+from .freevideo import FreeVideoIE
+from .funimation import FunimationIE
+from .funnyordie import FunnyOrDieIE
+from .gameinformer import GameInformerIE
+from .gamekings import GamekingsIE
+from .gameone import (
+    GameOneIE,
+    GameOnePlaylistIE,
+)
+from .gamersyde import GamersydeIE
+from .gamespot import GameSpotIE
+from .gamestar import GameStarIE
+from .gametrailers import GametrailersIE
+from .gazeta import GazetaIE
+from .gdcvault import GDCVaultIE
+from .generic import GenericIE
+from .gfycat import GfycatIE
+from .giantbomb import GiantBombIE
+from .giga import GigaIE
+from .glide import GlideIE
+from .globo import (
+    GloboIE,
+    GloboArticleIE,
+)
+from .godtube import GodTubeIE
+from .goldenmoustache import GoldenMoustacheIE
+from .golem import GolemIE
+from .googledrive import GoogleDriveIE
+from .googleplus import GooglePlusIE
+from .googlesearch import GoogleSearchIE
+from .goshgay import GoshgayIE
+from .gputechconf import GPUTechConfIE
+from .groupon import GrouponIE
+from .hark import HarkIE
+from .hbo import HBOIE
+from .hearthisat import HearThisAtIE
+from .heise import HeiseIE
+from .hellporno import HellPornoIE
+from .helsinki import HelsinkiIE
+from .hentaistigma import HentaiStigmaIE
+from .historicfilms import HistoricFilmsIE
+from .hitbox import HitboxIE, HitboxLiveIE
+from .hornbunny import HornBunnyIE
+from .hotnewhiphop import HotNewHipHopIE
+from .hotstar import HotStarIE
+from .howcast import HowcastIE
+from .howstuffworks import HowStuffWorksIE
+from .huffpost import HuffPostIE
+from .hypem import HypemIE
+from .iconosquare import IconosquareIE
+from .ign import (
+    IGNIE,
+    OneUPIE,
+    PCMagIE,
+)
+from .imdb import (
+    ImdbIE,
+    ImdbListIE
+)
+from .imgur import (
+    ImgurIE,
+    ImgurAlbumIE,
+)
+from .ina import InaIE
+from .indavideo import (
+    IndavideoIE,
+    IndavideoEmbedIE,
+)
+from .infoq import InfoQIE
+from .instagram import InstagramIE, InstagramUserIE
+from .internetvideoarchive import InternetVideoArchiveIE
+from .iprima import IPrimaIE
+from .iqiyi import IqiyiIE
+from .ir90tv import Ir90TvIE
+from .ivi import (
+    IviIE,
+    IviCompilationIE
+)
+from .ivideon import IvideonIE
+from .izlesene import IzleseneIE
+from .jadorecettepub import JadoreCettePubIE
+from .jeuxvideo import JeuxVideoIE
+from .jove import JoveIE
+from .jwplatform import JWPlatformIE
+from .jpopsukitv import JpopsukiIE
+from .kaltura import KalturaIE
+from .kanalplay import KanalPlayIE
+from .kankan import KankanIE
+from .karaoketv import KaraoketvIE
+from .karrierevideos import KarriereVideosIE
+from .keezmovies import KeezMoviesIE
+from .khanacademy import KhanAcademyIE
+from .kickstarter import KickStarterIE
+from .keek import KeekIE
+from .konserthusetplay import KonserthusetPlayIE
+from .kontrtube import KontrTubeIE
+from .krasview import KrasViewIE
+from .ku6 import Ku6IE
+from .kusi import KUSIIE
+from .kuwo import (
+    KuwoIE,
+    KuwoAlbumIE,
+    KuwoChartIE,
+    KuwoSingerIE,
+    KuwoCategoryIE,
+    KuwoMvIE,
+)
+from .la7 import LA7IE
+from .laola1tv import Laola1TvIE
+from .lecture2go import Lecture2GoIE
+from .lemonde import LemondeIE
+from .leeco import (
+    LeIE,
+    LePlaylistIE,
+    LetvCloudIE,
+)
+from .libsyn import LibsynIE
+from .lifenews import (
+    LifeNewsIE,
+    LifeEmbedIE,
+)
+from .limelight import (
+    LimelightMediaIE,
+    LimelightChannelIE,
+    LimelightChannelListIE,
+)
+from .liveleak import LiveLeakIE
+from .livestream import (
+    LivestreamIE,
+    LivestreamOriginalIE,
+    LivestreamShortenerIE,
+)
+from .lnkgo import LnkGoIE
+from .lovehomeporn import LoveHomePornIE
+from .lrt import LRTIE
+from .lynda import (
+    LyndaIE,
+    LyndaCourseIE
+)
+from .m6 import M6IE
+from .macgamestore import MacGameStoreIE
+from .mailru import MailRuIE
+from .makerschannel import MakersChannelIE
+from .makertv import MakerTVIE
+from .malemotion import MalemotionIE
+from .matchtv import MatchTVIE
+from .mdr import MDRIE
+from .metacafe import MetacafeIE
+from .metacritic import MetacriticIE
+from .mgoon import MgoonIE
+from .minhateca import MinhatecaIE
+from .ministrygrid import MinistryGridIE
+from .minoto import MinotoIE
+from .miomio import MioMioIE
+from .mit import TechTVMITIE, MITIE, OCWMITIE
+from .mitele import MiTeleIE
+from .mixcloud import MixcloudIE
+from .mlb import MLBIE
+from .mnet import MnetIE
+from .mpora import MporaIE
+from .moevideo import MoeVideoIE
+from .mofosex import MofosexIE
+from .mojvideo import MojvideoIE
+from .moniker import MonikerIE
+from .mooshare import MooshareIE
+from .morningstar import MorningstarIE
+from .motherless import MotherlessIE
+from .motorsport import MotorsportIE
+from .movieclips import MovieClipsIE
+from .moviezine import MoviezineIE
+from .mtv import (
+    MTVIE,
+    MTVServicesEmbeddedIE,
+    MTVIggyIE,
+    MTVDEIE,
+)
+from .muenchentv import MuenchenTVIE
+from .musicplayon import MusicPlayOnIE
+from .muzu import MuzuTVIE
+from .mwave import MwaveIE
+from .myspace import MySpaceIE, MySpaceAlbumIE
+from .myspass import MySpassIE
+from .myvi import MyviIE
+from .myvideo import MyVideoIE
+from .myvidster import MyVidsterIE
+from .nationalgeographic import (
+    NationalGeographicIE,
+    NationalGeographicChannelIE,
+)
+from .naver import NaverIE
+from .nba import NBAIE
+from .nbc import (
+    CSNNEIE,
+    NBCIE,
+    NBCNewsIE,
+    NBCSportsIE,
+    NBCSportsVPlayerIE,
+    MSNBCIE,
+)
+from .ndr import (
+    NDRIE,
+    NJoyIE,
+    NDREmbedBaseIE,
+    NDREmbedIE,
+    NJoyEmbedIE,
+)
+from .ndtv import NDTVIE
+from .netzkino import NetzkinoIE
+from .nerdcubed import NerdCubedFeedIE
+from .nerdist import NerdistIE
+from .neteasemusic import (
+    NetEaseMusicIE,
+    NetEaseMusicAlbumIE,
+    NetEaseMusicSingerIE,
+    NetEaseMusicListIE,
+    NetEaseMusicMvIE,
+    NetEaseMusicProgramIE,
+    NetEaseMusicDjRadioIE,
+)
+from .newgrounds import NewgroundsIE
+from .newstube import NewstubeIE
+from .nextmedia import (
+    NextMediaIE,
+    NextMediaActionNewsIE,
+    AppleDailyIE,
+)
+from .nextmovie import NextMovieIE
+from .nfb import NFBIE
+from .nfl import NFLIE
+from .nhl import (
+    NHLIE,
+    NHLNewsIE,
+    NHLVideocenterIE,
+)
+from .nick import NickIE
+from .niconico import NiconicoIE, NiconicoPlaylistIE
+from .ninegag import NineGagIE
+from .noco import NocoIE
+from .normalboots import NormalbootsIE
+from .nosvideo import NosVideoIE
+from .nova import NovaIE
+from .novamov import (
+    AuroraVidIE,
+    CloudTimeIE,
+    NowVideoIE,
+    VideoWeedIE,
+    WholeCloudIE,
+)
+from .nowness import (
+    NownessIE,
+    NownessPlaylistIE,
+    NownessSeriesIE,
+)
+from .nowtv import (
+    NowTVIE,
+    NowTVListIE,
+)
+from .noz import NozIE
+from .npo import (
+    NPOIE,
+    NPOLiveIE,
+    NPORadioIE,
+    NPORadioFragmentIE,
+    SchoolTVIE,
+    VPROIE,
+    WNLIE
+)
+from .npr import NprIE
+from .nrk import (
+    NRKIE,
+    NRKPlaylistIE,
+    NRKSkoleIE,
+    NRKTVIE,
+)
+from .ntvde import NTVDeIE
+from .ntvru import NTVRuIE
+from .nytimes import (
+    NYTimesIE,
+    NYTimesArticleIE,
+)
+from .nuvid import NuvidIE
+from .odnoklassniki import OdnoklassnikiIE
+from .oktoberfesttv import OktoberfestTVIE
+from .onionstudios import OnionStudiosIE
+from .ooyala import (
+    OoyalaIE,
+    OoyalaExternalIE,
+)
+from .openload import OpenloadIE
+from .ora import OraTVIE
+from .orf import (
+    ORFTVthekIE,
+    ORFOE1IE,
+    ORFFM4IE,
+    ORFIPTVIE,
+)
+from .pandoratv import PandoraTVIE
+from .parliamentliveuk import ParliamentLiveUKIE
+from .patreon import PatreonIE
+from .pbs import PBSIE
+from .periscope import PeriscopeIE
+from .philharmoniedeparis import PhilharmonieDeParisIE
+from .phoenix import PhoenixIE
+from .photobucket import PhotobucketIE
+from .pinkbike import PinkbikeIE
+from .planetaplay import PlanetaPlayIE
+from .pladform import PladformIE
+from .played import PlayedIE
+from .playfm import PlayFMIE
+from .plays import PlaysTVIE
+from .playtvak import PlaytvakIE
+from .playvid import PlayvidIE
+from .playwire import PlaywireIE
+from .pluralsight import (
+    PluralsightIE,
+    PluralsightCourseIE,
+)
+from .podomatic import PodomaticIE
+from .porn91 import Porn91IE
+from .pornhd import PornHdIE
+from .pornhub import (
+    PornHubIE,
+    PornHubPlaylistIE,
+    PornHubUserVideosIE,
+)
+from .pornotube import PornotubeIE
+from .pornovoisines import PornoVoisinesIE
+from .pornoxo import PornoXOIE
+from .primesharetv import PrimeShareTVIE
+from .promptfile import PromptFileIE
+from .prosiebensat1 import ProSiebenSat1IE
+from .puls4 import Puls4IE
+from .pyvideo import PyvideoIE
+from .qqmusic import (
+    QQMusicIE,
+    QQMusicSingerIE,
+    QQMusicAlbumIE,
+    QQMusicToplistIE,
+    QQMusicPlaylistIE,
+)
+from .quickvid import QuickVidIE
+from .r7 import R7IE
+from .radiode import RadioDeIE
+from .radiojavan import RadioJavanIE
+from .radiobremen import RadioBremenIE
+from .radiofrance import RadioFranceIE
+from .rai import (
+    RaiTVIE,
+    RaiIE,
+)
+from .rbmaradio import RBMARadioIE
+from .rds import RDSIE
+from .redtube import RedTubeIE
+from .regiotv import RegioTVIE
+from .restudy import RestudyIE
+from .reverbnation import ReverbNationIE
+from .revision3 import Revision3IE
+from .rice import RICEIE
+from .ringtv import RingTVIE
+from .ro220 import Ro220IE
+from .rottentomatoes import RottenTomatoesIE
+from .roxwel import RoxwelIE
+from .rtbf import RTBFIE
+from .rte import RteIE, RteRadioIE
+from .rtlnl import RtlNlIE
+from .rtl2 import RTL2IE
+from .rtp import RTPIE
+from .rts import RTSIE
+from .rtve import RTVEALaCartaIE, RTVELiveIE, RTVEInfantilIE
+from .rtvnh import RTVNHIE
+from .ruhd import RUHDIE
+from .ruleporn import RulePornIE
+from .rutube import (
+    RutubeIE,
+    RutubeChannelIE,
+    RutubeEmbedIE,
+    RutubeMovieIE,
+    RutubePersonIE,
+)
+from .rutv import RUTVIE
+from .ruutu import RuutuIE
+from .sandia import SandiaIE
+from .safari import (
+    SafariIE,
+    SafariApiIE,
+    SafariCourseIE,
+)
+from .sapo import SapoIE
+from .savefrom import SaveFromIE
+from .sbs import SBSIE
+from .scivee import SciVeeIE
+from .screencast import ScreencastIE
+from .screencastomatic import ScreencastOMaticIE
+from .screenjunkies import ScreenJunkiesIE
+from .screenwavemedia import ScreenwaveMediaIE, TeamFourIE
+from .senateisvp import SenateISVPIE
+from .servingsys import ServingSysIE
+from .sexu import SexuIE
+from .sexykarma import SexyKarmaIE
+from .shahid import ShahidIE
+from .shared import SharedIE
+from .sharesix import ShareSixIE
+from .sina import SinaIE
+from .skynewsarabia import (
+    SkyNewsArabiaIE,
+    SkyNewsArabiaArticleIE,
+)
+from .slideshare import SlideshareIE
+from .slutload import SlutloadIE
+from .smotri import (
+    SmotriIE,
+    SmotriCommunityIE,
+    SmotriUserIE,
+    SmotriBroadcastIE,
+)
+from .snagfilms import (
+    SnagFilmsIE,
+    SnagFilmsEmbedIE,
+)
+from .snotr import SnotrIE
+from .sohu import SohuIE
+from .soundcloud import (
+    SoundcloudIE,
+    SoundcloudSetIE,
+    SoundcloudUserIE,
+    SoundcloudPlaylistIE,
+    SoundcloudSearchIE
+)
+from .soundgasm import (
+    SoundgasmIE,
+    SoundgasmProfileIE
+)
+from .southpark import (
+    SouthParkIE,
+    SouthParkDeIE,
+    SouthParkDkIE,
+    SouthParkEsIE,
+    SouthParkNlIE
+)
+from .spankbang import SpankBangIE
+from .spankwire import SpankwireIE
+from .spiegel import SpiegelIE, SpiegelArticleIE
+from .spiegeltv import SpiegeltvIE
+from .spike import SpikeIE
+from .stitcher import StitcherIE
+from .sport5 import Sport5IE
+from .sportbox import (
+    SportBoxIE,
+    SportBoxEmbedIE,
+)
+from .sportdeutschland import SportDeutschlandIE
+from .srgssr import (
+    SRGSSRIE,
+    SRGSSRPlayIE,
+)
+from .srmediathek import SRMediathekIE
+from .ssa import SSAIE
+from .stanfordoc import StanfordOpenClassroomIE
+from .steam import SteamIE
+from .streamcloud import StreamcloudIE
+from .streamcz import StreamCZIE
+from .streetvoice import StreetVoiceIE
+from .sunporno import SunPornoIE
+from .svt import (
+    SVTIE,
+    SVTPlayIE,
+)
+from .swrmediathek import SWRMediathekIE
+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,
+)
+from .teachingchannel import TeachingChannelIE
+from .teamcoco import TeamcocoIE
+from .techtalks import TechTalksIE
+from .ted import TEDIE
+from .tele13 import Tele13IE
+from .telebruxelles import TeleBruxellesIE
+from .telecinco import TelecincoIE
+from .telegraaf import TelegraafIE
+from .telemb import TeleMBIE
+from .teletask import TeleTaskIE
+from .testurl import TestURLIE
+from .tf1 import TF1IE
+from .theintercept import TheInterceptIE
+from .theonion import TheOnionIE
+from .theplatform import (
+    ThePlatformIE,
+    ThePlatformFeedIE,
+)
+from .thescene import TheSceneIE
+from .thesixtyone import TheSixtyOneIE
+from .thestar import TheStarIE
+from .thisamericanlife import ThisAmericanLifeIE
+from .thisav import ThisAVIE
+from .tinypic import TinyPicIE
+from .tlc import TlcDeIE
+from .tmz import (
+    TMZIE,
+    TMZArticleIE,
+)
+from .tnaflix import (
+    TNAFlixNetworkEmbedIE,
+    TNAFlixIE,
+    EMPFlixIE,
+    MovieFapIE,
+)
+from .toggle import ToggleIE
+from .thvideo import (
+    THVideoIE,
+    THVideoPlaylistIE
+)
+from .toutv import TouTvIE
+from .toypics import ToypicsUserIE, ToypicsIE
+from .traileraddict import TrailerAddictIE
+from .trilulilu import TriluliluIE
+from .trollvids import TrollvidsIE
+from .trutube import TruTubeIE
+from .tube8 import Tube8IE
+from .tubitv import TubiTvIE
+from .tudou import (
+    TudouIE,
+    TudouPlaylistIE,
+    TudouAlbumIE,
+)
+from .tumblr import TumblrIE
+from .tunein import (
+    TuneInClipIE,
+    TuneInStationIE,
+    TuneInProgramIE,
+    TuneInTopicIE,
+    TuneInShortenerIE,
+)
+from .turbo import TurboIE
+from .tutv import TutvIE
+from .tv2 import (
+    TV2IE,
+    TV2ArticleIE,
+)
+from .tv3 import TV3IE
+from .tv4 import TV4IE
+from .tvc import (
+    TVCIE,
+    TVCArticleIE,
+)
+from .tvigle import TvigleIE
+from .tvland import TVLandIE
+from .tvp import TvpIE, TvpSeriesIE
+from .tvplay import TVPlayIE
+from .tweakers import TweakersIE
+from .twentyfourvideo import TwentyFourVideoIE
+from .twentymin import TwentyMinutenIE
+from .twentytwotracks import (
+    TwentyTwoTracksIE,
+    TwentyTwoTracksGenreIE
+)
+from .twitch import (
+    TwitchVideoIE,
+    TwitchChapterIE,
+    TwitchVodIE,
+    TwitchProfileIE,
+    TwitchPastBroadcastsIE,
+    TwitchBookmarksIE,
+    TwitchStreamIE,
+)
+from .twitter import (
+    TwitterCardIE,
+    TwitterIE,
+    TwitterAmplifyIE,
+)
+from .ubu import UbuIE
+from .udemy import (
+    UdemyIE,
+    UdemyCourseIE
+)
+from .udn import UDNEmbedIE
+from .digiteka import DigitekaIE
+from .unistra import UnistraIE
+from .urort import UrortIE
+from .usatoday import USATodayIE
+from .ustream import UstreamIE, UstreamChannelIE
+from .ustudio import UstudioIE
+from .varzesh3 import Varzesh3IE
+from .vbox7 import Vbox7IE
+from .veehd import VeeHDIE
+from .veoh import VeohIE
+from .vessel import VesselIE
+from .vesti import VestiIE
+from .vevo import VevoIE
+from .vgtv import (
+    BTArticleIE,
+    BTVestlendingenIE,
+    VGTVIE,
+)
+from .vh1 import VH1IE
+from .vice import (
+    ViceIE,
+    ViceShowIE,
+)
+from .viddler import ViddlerIE
+from .videodetective import VideoDetectiveIE
+from .videofyme import VideofyMeIE
+from .videomega import VideoMegaIE
+from .videomore import (
+    VideomoreIE,
+    VideomoreVideoIE,
+    VideomoreSeasonIE,
+)
+from .videopremium import VideoPremiumIE
+from .videott import VideoTtIE
+from .vidme import (
+    VidmeIE,
+    VidmeUserIE,
+    VidmeUserLikesIE,
+)
+from .vidzi import VidziIE
+from .vier import VierIE, VierVideosIE
+from .viewster import ViewsterIE
+from .viidea import ViideaIE
+from .vimeo import (
+    VimeoIE,
+    VimeoAlbumIE,
+    VimeoChannelIE,
+    VimeoGroupsIE,
+    VimeoLikesIE,
+    VimeoOndemandIE,
+    VimeoReviewIE,
+    VimeoUserIE,
+    VimeoWatchLaterIE,
+)
+from .vimple import VimpleIE
+from .vine import (
+    VineIE,
+    VineUserIE,
+)
+from .viki import (
+    VikiIE,
+    VikiChannelIE,
+)
+from .vk import (
+    VKIE,
+    VKUserVideosIE,
+)
+from .vlive import VLiveIE
+from .vodlocker import VodlockerIE
+from .voicerepublic import VoiceRepublicIE
+from .voxmedia import VoxMediaIE
+from .vporn import VpornIE
+from .vrt import VRTIE
+from .vube import VubeIE
+from .vuclip import VuClipIE
+from .vulture import VultureIE
+from .walla import WallaIE
+from .washingtonpost import WashingtonPostIE
+from .wat import WatIE
+from .wayofthemaster import WayOfTheMasterIE
+from .wdr import (
+    WDRIE,
+    WDRMobileIE,
+    WDRMausIE,
+)
+from .webofstories import (
+    WebOfStoriesIE,
+    WebOfStoriesPlaylistIE,
+)
+from .weibo import WeiboIE
+from .weiqitv import WeiqiTVIE
+from .wimp import WimpIE
+from .wistia import WistiaIE
+from .worldstarhiphop import WorldStarHipHopIE
+from .wrzuta import WrzutaIE
+from .wsj import WSJIE
+from .xbef import XBefIE
+from .xboxclips import XboxClipsIE
+from .xfileshare import XFileShareIE
+from .xhamster import (
+    XHamsterIE,
+    XHamsterEmbedIE,
+)
+from .xminus import XMinusIE
+from .xnxx import XNXXIE
+from .xstream import XstreamIE
+from .xtube import XTubeUserIE, XTubeIE
+from .xuite import XuiteIE
+from .xvideos import XVideosIE
+from .xxxymovies import XXXYMoviesIE
+from .yahoo import (
+    YahooIE,
+    YahooSearchIE,
+)
+from .yam import YamIE
+from .yandexmusic import (
+    YandexMusicTrackIE,
+    YandexMusicAlbumIE,
+    YandexMusicPlaylistIE,
+)
+from .yesjapan import YesJapanIE
+from .yinyuetai import YinYueTaiIE
+from .ynet import YnetIE
+from .youjizz import YouJizzIE
+from .youku import YoukuIE
+from .youporn import YouPornIE
+from .yourupload import YourUploadIE
+from .youtube import (
+    YoutubeIE,
+    YoutubeChannelIE,
+    YoutubeFavouritesIE,
+    YoutubeHistoryIE,
+    YoutubeLiveIE,
+    YoutubePlaylistIE,
+    YoutubePlaylistsIE,
+    YoutubeRecommendedIE,
+    YoutubeSearchDateIE,
+    YoutubeSearchIE,
+    YoutubeSearchURLIE,
+    YoutubeShowIE,
+    YoutubeSubscriptionsIE,
+    YoutubeTruncatedIDIE,
+    YoutubeTruncatedURLIE,
+    YoutubeUserIE,
+    YoutubeWatchLaterIE,
+)
+from .zapiks import ZapiksIE
+from .zdf import ZDFIE, ZDFChannelIE
+from .zingmp3 import (
+    ZingMp3SongIE,
+    ZingMp3AlbumIE,
+)
+from .zippcast import ZippCastIE

youtube_dl/extractor/gdcvault.py

@@ -159,9 +159,10 @@ class GDCVaultIE(InfoExtractor):
                 'title': title,
             }
 
+        PLAYER_REGEX = r'<iframe src="(?P<xml_root>.+?)/player.*?\.html.*?".*?</iframe>'
+
         xml_root = self._html_search_regex(
-            r'<iframe src="(?P<xml_root>.*?)player.html.*?".*?</iframe>',
+            PLAYER_REGEX, start_page, 'xml root', default=None)
-            start_page, 'xml root', default=None)
         if xml_root is None:
             # Probably need to authenticate
             login_res = self._login(webpage_url, display_id)
@@ -171,18 +172,19 @@ class GDCVaultIE(InfoExtractor):
                 start_page = login_res
                 # Grab the url from the authenticated page
                 xml_root = self._html_search_regex(
-                    r'<iframe src="(.*?)player.html.*?".*?</iframe>',
+                    PLAYER_REGEX, start_page, 'xml root')
-                    start_page, 'xml root')
 
         xml_name = self._html_search_regex(
             r'<iframe src=".*?\?xml=(.+?\.xml).*?".*?</iframe>',
             start_page, 'xml filename', default=None)
         if xml_name is None:
             # Fallback to the older format
-            xml_name = self._html_search_regex(r'<iframe src=".*?\?xmlURL=xml/(?P<xml_file>.+?\.xml).*?".*?</iframe>', start_page, 'xml filename')
+            xml_name = self._html_search_regex(
+                r'<iframe src=".*?\?xmlURL=xml/(?P<xml_file>.+?\.xml).*?".*?</iframe>',
+                start_page, 'xml filename')
 
-        xml_description_url = xml_root + 'xml/' + xml_name
+        xml_description = self._download_xml(
-        xml_description = self._download_xml(xml_description_url, display_id)
+            '%s/xml/%s' % (xml_root, xml_name), display_id)
 
         video_title = xml_description.find('./metadata/title').text
         video_formats = self._parse_mp4(xml_description)

youtube_dl/extractor/iqiyi.py

@@ -368,7 +368,10 @@ class IqiyiIE(InfoExtractor):
             auth_req, video_id,
             note='Downloading video authentication JSON',
             errnote='Unable to download video authentication JSON')
-        if auth_result['code'] == 'Q00506':  # requires a VIP account
+
+        if auth_result['code'] == 'Q00505':  # No preview available (不允许试看鉴权失败)
+            raise ExtractorError('This video requires a VIP account', expected=True)
+        if auth_result['code'] == 'Q00506':  # End of preview time (试看结束鉴权失败)
             if do_report_warning:
                 self.report_warning('Needs a VIP account for full video')
             return False

youtube_dl/extractor/novamov.py

@@ -16,7 +16,14 @@ class NovaMovIE(InfoExtractor):
     IE_NAME = 'novamov'
     IE_DESC = 'NovaMov'
 
-    _VALID_URL_TEMPLATE = r'http://(?:(?:www\.)?%(host)s/(?:file|video|mobile/#/videos)/|(?:(?:embed|www)\.)%(host)s/embed\.php\?(?:.*?&)?v=)(?P<id>[a-z\d]{13})'
+    _VALID_URL_TEMPLATE = r'''(?x)
+                            http://
+                                (?:
+                                    (?:www\.)?%(host)s/(?:file|video|mobile/\#/videos)/|
+                                    (?:(?:embed|www)\.)%(host)s/embed(?:\.php|/)?\?(?:.*?&)?\bv=
+                                )
+                                (?P<id>[a-z\d]{13})
+                            '''
     _VALID_URL = _VALID_URL_TEMPLATE % {'host': 'novamov\.com'}
 
     _HOST = 'www.novamov.com'
@@ -27,17 +34,7 @@ class NovaMovIE(InfoExtractor):
     _DESCRIPTION_REGEX = r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>[^<]+</h3><p>([^<]+)</p>'
     _URL_TEMPLATE = 'http://%s/video/%s'
 
-    _TEST = {
+    _TEST = None
-        'url': 'http://www.novamov.com/video/4rurhn9x446jj',
-        'md5': '7205f346a52bbeba427603ba10d4b935',
-        'info_dict': {
-            'id': '4rurhn9x446jj',
-            'ext': 'flv',
-            'title': 'search engine optimization',
-            'description': 'search engine optimization is used to rank the web page in the google search engine'
-        },
-        'skip': '"Invalid token" errors abound (in web interface as well as youtube-dl, there is nothing we can do about it.)'
-    }
 
     def _check_existence(self, webpage, video_id):
         if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
@@ -81,7 +78,7 @@ class NovaMovIE(InfoExtractor):
 
         filekey = extract_filekey()
 
-        title = self._html_search_regex(self._TITLE_REGEX, webpage, 'title', fatal=False)
+        title = self._html_search_regex(self._TITLE_REGEX, webpage, 'title')
         description = self._html_search_regex(self._DESCRIPTION_REGEX, webpage, 'description', default='', fatal=False)
 
         api_response = self._download_webpage(
@@ -187,3 +184,29 @@ class CloudTimeIE(NovaMovIE):
     _TITLE_REGEX = r'<div[^>]+class=["\']video_det["\'][^>]*>\s*<strong>([^<]+)</strong>'
 
     _TEST = None
+
+
+class AuroraVidIE(NovaMovIE):
+    IE_NAME = 'auroravid'
+    IE_DESC = 'AuroraVid'
+
+    _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'auroravid\.to'}
+
+    _HOST = 'www.auroravid.to'
+
+    _FILE_DELETED_REGEX = r'This file no longer exists on our servers!<'
+
+    _TESTS = [{
+        'url': 'http://www.auroravid.to/video/4rurhn9x446jj',
+        'md5': '7205f346a52bbeba427603ba10d4b935',
+        'info_dict': {
+            'id': '4rurhn9x446jj',
+            'ext': 'flv',
+            'title': 'search engine optimization',
+            'description': 'search engine optimization is used to rank the web page in the google search engine'
+        },
+        'skip': '"Invalid token" errors abound (in web interface as well as youtube-dl, there is nothing we can do about it.)'
+    }, {
+        'url': 'http://www.auroravid.to/embed/?v=4rurhn9x446jj',
+        'only_matching': True,
+    }]

youtube_dl/extractor/rte.py

@@ -39,9 +39,14 @@ class RteIE(InfoExtractor):
         duration = float_or_none(self._html_search_meta(
             'duration', webpage, 'duration', fatal=False), 1000)
 
+        thumbnail = None
+        thumbnail_meta = self._html_search_meta('thumbnail', webpage)
+        if thumbnail_meta:
             thumbnail_id = self._search_regex(
-            r'<meta name="thumbnail" content="uri:irus:(.*?)" />', webpage, 'thumbnail')
+                r'uri:irus:(.+)', thumbnail_meta,
-        thumbnail = 'http://img.rasset.ie/' + thumbnail_id + '.jpg'
+                'thumbnail id', fatal=False)
+            if thumbnail_id:
+                thumbnail = 'http://img.rasset.ie/%s.jpg' % thumbnail_id
 
         feeds_url = self._html_search_meta('feeds-prefix', webpage, 'feeds url') + video_id
         json_string = self._download_json(feeds_url, video_id)

youtube_dl/extractor/tnaflix.py

@@ -76,7 +76,11 @@ class TNAFlixNetworkBaseIE(InfoExtractor):
         webpage = self._download_webpage(url, display_id)
 
         cfg_url = self._proto_relative_url(self._html_search_regex(
-            self._CONFIG_REGEX, webpage, 'flashvars.config'), 'http:')
+            self._CONFIG_REGEX, webpage, 'flashvars.config', default=None), 'http:')
+
+        if not cfg_url:
+            inputs = self._hidden_inputs(webpage)
+            cfg_url = 'https://cdn-fck.tnaflix.com/tnaflix/%s.fid?key=%s' % (inputs['vkey'], inputs['nkey'])
 
         cfg_xml = self._download_xml(
             cfg_url, display_id, 'Downloading metadata',
@@ -132,7 +136,7 @@ class TNAFlixNetworkBaseIE(InfoExtractor):
         average_rating = float_or_none(extract_field(self._AVERAGE_RATING_REGEX, 'average rating'))
 
         categories_str = extract_field(self._CATEGORIES_REGEX, 'categories')
-        categories = categories_str.split(', ') if categories_str is not None else []
+        categories = [c.strip() for c in categories_str.split(',')] if categories_str is not None else []
 
         return {
             'id': video_id,
@@ -186,13 +190,14 @@ class TNAFlixIE(TNAFlixNetworkBaseIE):
     _VALID_URL = r'https?://(?:www\.)?tnaflix\.com/[^/]+/(?P<display_id>[^/]+)/video(?P<id>\d+)'
 
     _TITLE_REGEX = r'<title>(.+?) - TNAFlix Porn Videos</title>'
-    _DESCRIPTION_REGEX = r'<h3 itemprop="description">([^<]+)</h3>'
+    _DESCRIPTION_REGEX = r'<meta[^>]+name="description"[^>]+content="([^"]+)"'
-    _UPLOADER_REGEX = r'(?s)<span[^>]+class="infoTitle"[^>]*>Uploaded By:</span>(.+?)<div'
+    _UPLOADER_REGEX = r'<i>\s*Verified Member\s*</i>\s*<h1>(.+?)</h1>'
+    _CATEGORIES_REGEX = r'(?s)<span[^>]*>Categories:</span>(.+?)</div>'
 
     _TESTS = [{
         # anonymous uploader, no categories
         'url': 'http://www.tnaflix.com/porn-stars/Carmella-Decesare-striptease/video553878',
-        'md5': 'ecf3498417d09216374fc5907f9c6ec0',
+        'md5': '7e569419fe6d69543d01e6be22f5f7c4',
         'info_dict': {
             'id': '553878',
             'display_id': 'Carmella-Decesare-striptease',
@@ -201,17 +206,16 @@ class TNAFlixIE(TNAFlixNetworkBaseIE):
             'thumbnail': 're:https?://.*\.jpg$',
             'duration': 91,
             'age_limit': 18,
-            'uploader': 'Anonymous',
+            'categories': ['Porn Stars'],
-            'categories': [],
         }
     }, {
         # non-anonymous uploader, categories
         'url': 'https://www.tnaflix.com/teen-porn/Educational-xxx-video/video6538',
-        'md5': '0f5d4d490dbfd117b8607054248a07c0',
+        'md5': 'fcba2636572895aba116171a899a5658',
         'info_dict': {
             'id': '6538',
             'display_id': 'Educational-xxx-video',
-            'ext': 'mp4',
+            'ext': 'flv',
             'title': 'Educational xxx video',
             'description': 'md5:b4fab8f88a8621c8fabd361a173fe5b8',
             'thumbnail': 're:https?://.*\.jpg$',

youtube_dl/extractor/vrt.py

@@ -4,7 +4,10 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import float_or_none
+from ..utils import (
+    determine_ext,
+    float_or_none,
+)
 
 
 class VRTIE(InfoExtractor):
@@ -52,6 +55,11 @@ class VRTIE(InfoExtractor):
                 'duration': 661,
             }
         },
+        {
+            # YouTube video
+            'url': 'http://deredactie.be/cm/vrtnieuws/videozone/nieuws/cultuurenmedia/1.2622957',
+            'only_matching': True,
+        },
         {
             'url': 'http://cobra.canvas.be/cm/cobra/videozone/rubriek/film-videozone/1.2377055',
             'only_matching': True,
@@ -66,7 +74,17 @@ class VRTIE(InfoExtractor):
         video_id = self._search_regex(
             r'data-video-id="([^"]+)_[^"]+"', webpage, 'video id', fatal=False)
 
+        src = self._search_regex(
+            r'data-video-src="([^"]+)"', webpage, 'video src', default=None)
+
+        video_type = self._search_regex(
+            r'data-video-type="([^"]+)"', webpage, 'video type', default=None)
+
+        if video_type == 'YouTubeVideo':
+            return self.url_result(src, 'Youtube')
+
         formats = []
+
         mobj = re.search(
             r'data-video-iphone-server="(?P<server>[^"]+)"\s+data-video-iphone-path="(?P<path>[^"]+)"',
             webpage)
@@ -74,11 +92,15 @@ class VRTIE(InfoExtractor):
             formats.extend(self._extract_m3u8_formats(
                 '%s/%s' % (mobj.group('server'), mobj.group('path')),
                 video_id, 'mp4', m3u8_id='hls', fatal=False))
-        mobj = re.search(r'data-video-src="(?P<src>[^"]+)"', webpage)
+
-        if mobj:
+        if src:
+            if determine_ext(src) == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    src, video_id, 'mp4', entry_protocol='m3u8_native',
+                    m3u8_id='hls', fatal=False))
+            else:
                 formats.extend(self._extract_f4m_formats(
-                '%s/manifest.f4m' % mobj.group('src'),
+                    '%s/manifest.f4m' % src, video_id, f4m_id='hds', fatal=False))
-                video_id, f4m_id='hds', fatal=False))
 
         if not formats and 'data-video-geoblocking="true"' in webpage:
             self.raise_geo_restricted('This video is only available in Belgium')

youtube_dl/extractor/yandexmusic.py

@@ -39,9 +39,14 @@ class YandexMusicTrackIE(YandexMusicBaseIE):
         'info_dict': {
             'id': '4878838',
             'ext': 'mp3',
-            'title': 'Carlo Ambrosio - Gypsy Eyes 1',
+            'title': 'Carlo Ambrosio & Fabio Di Bari, Carlo Ambrosio - Gypsy Eyes 1',
             'filesize': 4628061,
             'duration': 193.04,
+            'track': 'Gypsy Eyes 1',
+            'album': 'Gypsy Soul',
+            'album_artist': 'Carlo Ambrosio',
+            'artist': 'Carlo Ambrosio & Fabio Di Bari, Carlo Ambrosio',
+            'release_year': '2009',
         }
     }
 
@@ -64,16 +69,45 @@ class YandexMusicTrackIE(YandexMusicBaseIE):
             thumbnail = cover_uri.replace('%%', 'orig')
             if not thumbnail.startswith('http'):
                 thumbnail = 'http://' + thumbnail
-        return {
+
+        track_title = track['title']
+        track_info = {
             'id': track['id'],
             'ext': 'mp3',
             'url': self._get_track_url(track['storageDir'], track['id']),
-            'title': '%s - %s' % (track['artists'][0]['name'], track['title']),
             'filesize': int_or_none(track.get('fileSize')),
             'duration': float_or_none(track.get('durationMs'), 1000),
             'thumbnail': thumbnail,
+            'track': track_title,
         }
 
+        def extract_artist(artist_list):
+            if artist_list and isinstance(artist_list, list):
+                artists_names = [a['name'] for a in artist_list if a.get('name')]
+                if artists_names:
+                    return ', '.join(artists_names)
+
+        albums = track.get('albums')
+        if albums and isinstance(albums, list):
+            album = albums[0]
+            if isinstance(album, dict):
+                year = album.get('year')
+                track_info.update({
+                    'album': album.get('title'),
+                    'album_artist': extract_artist(album.get('artists')),
+                    'release_year': compat_str(year) if year else None,
+                })
+
+        track_artist = extract_artist(track.get('artists'))
+        if track_artist:
+            track_info.update({
+                'artist': track_artist,
+                'title': '%s - %s' % (track_artist, track_title),
+            })
+        else:
+            track_info['title'] = track_title
+        return track_info
+
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         album_id, track_id = mobj.group('album_id'), mobj.group('id')

youtube_dl/extractor/youtube.py

@@ -270,7 +270,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                          ))
                          |(?:
                             youtu\.be|                                        # just youtu.be/xxxx
-                            vid\.plus                                         # or vid.plus/xxxx
+                            vid\.plus|                                        # or vid.plus/xxxx
+                            zwearz\.com/watch|                                # or zwearz.com/watch/xxxx
                          )/
                          |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
                          )
@@ -758,6 +759,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             'url': 'http://vid.plus/FlRa-iH7PGw',
             'only_matching': True,
         },
+        {
+            'url': 'http://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
+            'only_matching': True,
+        },
         {
             # Title with JS-like syntax "};" (see https://github.com/rg3/youtube-dl/issues/7468)
             # Also tests cut-off URL expansion in video description (see

youtube_dl/extractor/zdf.py

@@ -85,6 +85,13 @@ class ZDFIE(InfoExtractor):
         uploader = xpath_text(doc, './/details/originChannelTitle', 'uploader')
         uploader_id = xpath_text(doc, './/details/originChannelId', 'uploader id')
         upload_date = unified_strdate(xpath_text(doc, './/details/airtime', 'upload date'))
+        subtitles = {}
+        captions_url = doc.find('.//caption/url')
+        if captions_url is not None:
+            subtitles['de'] = [{
+                'url': captions_url.text,
+                'ext': 'ttml',
+            }]
 
         def xml_to_thumbnails(fnode):
             thumbnails = []
@@ -190,6 +197,7 @@ class ZDFIE(InfoExtractor):
             'uploader_id': uploader_id,
             'upload_date': upload_date,
             'formats': formats,
+            'subtitles': subtitles,
         }
 
     def _real_extract(self, url):

youtube_dl/utils.py

@@ -2131,6 +2131,7 @@ def dfxp2srt(dfxp_data):
     _x = functools.partial(xpath_with_ns, ns_map={
         'ttml': 'http://www.w3.org/ns/ttml',
         'ttaf1': 'http://www.w3.org/2006/10/ttaf1',
+        'ttaf1_0604': 'http://www.w3.org/2006/04/ttaf1',
     })
 
     class TTMLPElementParser(object):
@@ -2157,7 +2158,7 @@ def dfxp2srt(dfxp_data):
 
     dfxp = compat_etree_fromstring(dfxp_data.encode('utf-8'))
     out = []
-    paras = dfxp.findall(_x('.//ttml:p')) or dfxp.findall(_x('.//ttaf1:p')) or dfxp.findall('.//p')
+    paras = dfxp.findall(_x('.//ttml:p')) or dfxp.findall(_x('.//ttaf1:p')) or dfxp.findall(_x('.//ttaf1_0604:p')) or dfxp.findall('.//p')
 
     if not paras:
         raise ValueError('Invalid dfxp/TTML subtitle')

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2016.04.01'
+__version__ = '2016.04.06'