release 2014.11.13.3

Fix YouTube Signature Extraction

AUTHORS

@@ -0,0 +1,84 @@
+Ricardo Garcia Gonzalez
+Danny Colligan
+Benjamin Johnson
+Vasyl' Vavrychuk
+Witold Baryluk
+Paweł Paprota
+Gergely Imreh
+Rogério Brito
+Philipp Hagemeister
+Sören Schulze
+Kevin Ngo
+Ori Avtalion
+shizeeg
+Filippo Valsorda
+Christian Albrecht
+Dave Vasilevsky
+Jaime Marquínez Ferrándiz
+Jeff Crouse
+Osama Khalid
+Michael Walter
+M. Yasoob Ullah Khalid
+Julien Fraichard
+Johny Mo Swag
+Axel Noack
+Albert Kim
+Pierre Rudloff
+Huarong Huo
+Ismael Mejía
+Steffan 'Ruirize' James
+Andras Elso
+Jelle van der Waa
+Marcin Cieślak
+Anton Larionov
+Takuya Tsuchida
+Sergey M.
+Michael Orlitzky
+Chris Gahan
+Saimadhav Heblikar
+Mike Col
+Oleg Prutz
+pulpe
+Andreas Schmitz
+Michael Kaiser
+Niklas Laxström
+David Triendl
+Anthony Weems
+David Wagner
+Juan C. Olivares
+Mattias Harrysson
+phaer
+Sainyam Kapoor
+Nicolas Évrard
+Jason Normore
+Hoje Lee
+Adam Thalhammer
+Georg Jähnig
+Ralf Haring
+Koki Takahashi
+Ariset Llerena
+Adam Malcontenti-Wilson
+Tobias Bell
+Naglis Jonaitis
+Charles Chen
+Hassaan Ali
+Dobrosław Żybort
+David Fabijan
+Sebastian Haas
+Alexander Kirk
+Erik Johnson
+Keith Beckman
+Ole Ernst
+Aaron McDaniel (mcd1992)
+Magnus Kolstad
+Hari Padmanaban
+Carlos Ramos
+5moufl
+lenaten
+Dennis Scheiba
+Damon Timm
+winwon
+Xavier Beynon
+Gabriel Schubiner
+xantares
+Jan Matějka

Makefile

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

README.md

@@ -69,6 +69,8 @@ which means you can modify it, redistribute it or use it however you like.
                                      configuration in ~/.config/youtube-dl.conf
                                      (%APPDATA%/youtube-dl/config.txt on
                                      Windows)
+    --flat-playlist                  Do not extract the videos of a playlist,
+                                     only list them.
 
 ## Video Selection:
     --playlist-start NUMBER          playlist video to start at (default is 1)
@@ -129,17 +131,19 @@ which means you can modify it, redistribute it or use it however you like.
                                      %(upload_date)s for the upload date
                                      (YYYYMMDD), %(extractor)s for the provider
                                      (youtube, metacafe, etc), %(id)s for the
-                                     video id, %(playlist)s for the playlist the
+                                     video id, %(playlist_title)s,
+                                     %(playlist_id)s, or %(playlist)s (=title if
+                                     present, ID otherwise) for the playlist the
                                      video is in, %(playlist_index)s for the
-                                     position in the playlist and %% for a
-                                     literal percent. %(height)s and %(width)s
-                                     for the width and height of the video
-                                     format. %(resolution)s for a textual
+                                     position in the playlist. %(height)s and
+                                     %(width)s for the width and height of the
+                                     video format. %(resolution)s for a textual
                                      description of the resolution of the video
-                                     format. Use - to output to stdout. Can also
-                                     be used to download to a different
-                                     directory, for example with -o '/my/downloa
-                                     ds/%(uploader)s/%(title)s-%(id)s.%(ext)s' .
+                                     format. %% for a literal percent. Use - to
+                                     output to stdout. Can also be used to
+                                     download to a different directory, for
+                                     example with -o '/my/downloads/%(uploader)s
+                                     /%(title)s-%(id)s.%(ext)s' .
     --autonumber-size NUMBER         Specifies the number of digits in
                                      %(autonumber)s when it is present in output
                                      filename template or --auto-number option
@@ -197,6 +201,10 @@ which means you can modify it, redistribute it or use it however you like.
     -j, --dump-json                  simulate, quiet but print JSON information.
                                      See --output for a description of available
                                      keys.
+    -J, --dump-single-json           simulate, quiet but print JSON information
+                                     for each command-line argument. If the URL
+                                     refers to a playlist, dump the whole
+                                     playlist information in a single line.
     --newline                        output progress bar as new lines
     --no-progress                    do not print progress bar
     --console-title                  display progress in console titlebar
@@ -233,8 +241,13 @@ which means you can modify it, redistribute it or use it however you like.
                                      "worst", "worstvideo" and "worstaudio". By
                                      default, youtube-dl will pick the best
                                      quality. Use commas to download multiple
-                                     audio formats, such as  -f
-                                     136/137/mp4/bestvideo,140/m4a/bestaudio
+                                     audio formats, such as -f
+                                     136/137/mp4/bestvideo,140/m4a/bestaudio.
+                                     You can merge the video and audio of two
+                                     formats into a single file using -f <video-
+                                     format>+<audio-format> (requires ffmpeg or
+                                     avconv), for example -f
+                                     bestvideo+bestaudio.
     --all-formats                    download all available video formats
     --prefer-free-formats            prefer free video formats unless a specific
                                      one is requested
@@ -375,7 +388,7 @@ Again, from then on you'll be able to update with `sudo youtube-dl -U`.
 
 YouTube changed their playlist format in March 2014 and later on, so you'll need at least youtube-dl 2014.07.25 to download all YouTube videos.
 
-If you have installed youtube-dl with a package manager, pip, setup.py or a tarball, please use that to update. Note that Ubuntu packages do not seem to get updated anymore. Since we are not affiliated with Ubuntu, there is little we can do. Feel free to report bugs to the Ubuntu packaging guys - all they have to do is update the package to a somewhat recent version. See above for a way to update.
+If you have installed youtube-dl with a package manager, pip, setup.py or a tarball, please use that to update. Note that Ubuntu packages do not seem to get updated anymore. Since we are not affiliated with Ubuntu, there is little we can do. Feel free to [report bugs](https://bugs.launchpad.net/ubuntu/+source/youtube-dl/+filebug) to the [Ubuntu packaging guys](mailto:ubuntu-motu@lists.ubuntu.com?subject=outdated%20version%20of%20youtube-dl) - all they have to do is update the package to a somewhat recent version. See above for a way to update.
 
 ### Do I always have to pass in `--max-quality FORMAT`, or `-citw`?
 
@@ -494,7 +507,7 @@ If you want to add support for a new site, you can follow this quick list (assum
 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 be then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc.
 7. Have a look at [`youtube_dl/common/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 return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L38). Add tests and code for as many as you want.
 8. If you can, check the code with [pyflakes](https://pypi.python.org/pypi/pyflakes) (a good idea) and [pep8](https://pypi.python.org/pypi/pep8) (optional, ignore E501).
-9. When the tests pass, [add](https://www.kernel.org/pub/software/scm/git/docs/git-add.html) the new files and [commit](https://www.kernel.org/pub/software/scm/git/docs/git-commit.html) them and [push](https://www.kernel.org/pub/software/scm/git/docs/git-push.html) the result, like this:
+9. 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/yourextractor.py
@@ -505,6 +518,20 @@ If you want to add support for a new site, you can follow this quick list (assum
 
 In any case, thank you very much for your contributions!
 
+# EMBEDDING YOUTUBE-DL
+
+youtube-dl makes the best effort to be a good command-line program, and thus should be callable from any programming language. If you encounter any problems parsing its output, feel free to [create a report](https://github.com/rg3/youtube-dl/issues/new).
+
+From a Python program, you can embed youtube-dl in a more powerful fashion, like this:
+
+    import youtube_dl
+
+    ydl_opts = {}
+    with youtube_dl.YoutubeDL(ydl_opts) as ydl:
+        ydl.download(['http://www.youtube.com/watch?v=BaW_jenozKc'])
+
+Most likely, you'll want to use various options. For a list of what can be done, have a look at [youtube_dl/YoutubeDL.py](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/YoutubeDL.py#L69). For a start, if you want to intercept youtube-dl's output, set a `logger` object.
+
 # BUGS
 
 Bugs and suggestions should be reported at: <https://github.com/rg3/youtube-dl/issues> . Unless you were prompted so or there is another pertinent reason (e.g. GitHub fails to accept the bug report), please do not send bug reports via personal email.

docs/conf.py

@@ -44,8 +44,8 @@ copyright = u'2014, Ricardo Garcia Gonzalez'
 # built documents.
 #
 # The short X.Y version.
-import youtube_dl
-version = youtube_dl.__version__
+from youtube_dl.version import __version__
+version = __version__
 # The full version, including alpha/beta/rc tags.
 release = version
 

test/helper.py

@@ -57,7 +57,7 @@ class FakeYDL(YoutubeDL):
         # Different instances of the downloader can't share the same dictionary
         # some test set the "sublang" parameter, which would break the md5 checks.
         params = get_params(override=override)
-        super(FakeYDL, self).__init__(params)
+        super(FakeYDL, self).__init__(params, auto_init=False)
         self.result = []
         
     def to_screen(self, s, skip_eol=None):
@@ -145,7 +145,8 @@ def expect_info_dict(self, expected_dict, got_dict):
         info_dict_str = ''.join(
             '    %s: %s,\n' % (_repr(k), _repr(v))
             for k, v in test_info_dict.items())
-        write_string('\n"info_dict": {' + info_dict_str + '}\n', out=sys.stderr)
+        write_string(
+            '\n\'info_dict\': {\n' + info_dict_str + '}\n', out=sys.stderr)
         self.assertFalse(
             missing_keys,
             'Missing keys in test definition: %s' % (
@@ -171,3 +172,13 @@ def assertGreaterEqual(self, got, expected, msg=None):
         if msg is None:
             msg = '%r not greater than or equal to %r' % (got, expected)
         self.assertTrue(got >= expected, msg)
+
+
+def expect_warnings(ydl, warnings_re):
+    real_warning = ydl.report_warning
+
+    def _report_warning(w):
+        if not any(re.search(w_re, w) for w_re in warnings_re):
+            real_warning(w)
+
+    ydl.report_warning = _report_warning

test/test_all_urls.py

@@ -14,7 +14,7 @@ from test.helper import gettestcases
 from youtube_dl.extractor import (
     FacebookIE,
     gen_extractors,
-    JustinTVIE,
+    TwitchIE,
     YoutubeIE,
 )
 
@@ -72,21 +72,17 @@ class TestAllURLsMatching(unittest.TestCase):
         self.assertMatch('http://www.youtube.com/results?search_query=making+mustard', ['youtube:search_url'])
         self.assertMatch('https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', ['youtube:search_url'])
 
-    def test_justin_tv_channelid_matching(self):
-        self.assertTrue(JustinTVIE.suitable('justin.tv/vanillatv'))
-        self.assertTrue(JustinTVIE.suitable('twitch.tv/vanillatv'))
-        self.assertTrue(JustinTVIE.suitable('www.justin.tv/vanillatv'))
-        self.assertTrue(JustinTVIE.suitable('www.twitch.tv/vanillatv'))
-        self.assertTrue(JustinTVIE.suitable('http://www.justin.tv/vanillatv'))
-        self.assertTrue(JustinTVIE.suitable('http://www.twitch.tv/vanillatv'))
-        self.assertTrue(JustinTVIE.suitable('http://www.justin.tv/vanillatv/'))
-        self.assertTrue(JustinTVIE.suitable('http://www.twitch.tv/vanillatv/'))
+    def test_twitch_channelid_matching(self):
+        self.assertTrue(TwitchIE.suitable('twitch.tv/vanillatv'))
+        self.assertTrue(TwitchIE.suitable('www.twitch.tv/vanillatv'))
+        self.assertTrue(TwitchIE.suitable('http://www.twitch.tv/vanillatv'))
+        self.assertTrue(TwitchIE.suitable('http://www.twitch.tv/vanillatv/'))
 
-    def test_justintv_videoid_matching(self):
-        self.assertTrue(JustinTVIE.suitable('http://www.twitch.tv/vanillatv/b/328087483'))
+    def test_twitch_videoid_matching(self):
+        self.assertTrue(TwitchIE.suitable('http://www.twitch.tv/vanillatv/b/328087483'))
 
-    def test_justin_tv_chapterid_matching(self):
-        self.assertTrue(JustinTVIE.suitable('http://www.twitch.tv/tsm_theoddone/c/2349361'))
+    def test_twitch_chapterid_matching(self):
+        self.assertTrue(TwitchIE.suitable('http://www.twitch.tv/tsm_theoddone/c/2349361'))
 
     def test_youtube_extract(self):
         assertExtractId = lambda url, id: self.assertEqual(YoutubeIE.extract_id(url), id)

test/test_compat.py

@@ -0,0 +1,44 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+from __future__ import unicode_literals
+
+# Allow direct execution
+import os
+import sys
+import unittest
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+
+from youtube_dl.utils import get_filesystem_encoding
+from youtube_dl.compat import (
+    compat_getenv,
+    compat_expanduser,
+)
+
+
+class TestCompat(unittest.TestCase):
+    def test_compat_getenv(self):
+        test_str = 'тест'
+        os.environ['YOUTUBE-DL-TEST'] = (
+            test_str if sys.version_info >= (3, 0)
+            else test_str.encode(get_filesystem_encoding()))
+        self.assertEqual(compat_getenv('YOUTUBE-DL-TEST'), test_str)
+
+    def test_compat_expanduser(self):
+        test_str = 'C:\Documents and Settings\тест\Application Data'
+        os.environ['HOME'] = (
+            test_str if sys.version_info >= (3, 0)
+            else test_str.encode(get_filesystem_encoding()))
+        self.assertEqual(compat_expanduser('~'), test_str)
+
+    def test_all_present(self):
+        import youtube_dl.compat
+        all_names = youtube_dl.compat.__all__
+        present_names = set(filter(
+            lambda c: '_' in c and not c.startswith('_'),
+            dir(youtube_dl.compat))) - set(['unicode_literals'])
+        self.assertEqual(all_names, sorted(present_names))
+
+if __name__ == '__main__':
+    unittest.main()

test/test_download.py

@@ -8,6 +8,7 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 from test.helper import (
     assertGreaterEqual,
+    expect_warnings,
     get_params,
     gettestcases,
     expect_info_dict,
@@ -22,10 +23,12 @@ import json
 import socket
 
 import youtube_dl.YoutubeDL
-from youtube_dl.utils import (
+from youtube_dl.compat import (
     compat_http_client,
     compat_urllib_error,
     compat_HTTPError,
+)
+from youtube_dl.utils import (
     DownloadError,
     ExtractorError,
     format_bytes,
@@ -93,13 +96,14 @@ def generator(test_case):
             params.setdefault('extract_flat', True)
             params.setdefault('skip_download', True)
 
-        ydl = YoutubeDL(params)
+        ydl = YoutubeDL(params, auto_init=False)
         ydl.add_default_info_extractors()
         finished_hook_called = set()
         def _hook(status):
             if status['status'] == 'finished':
                 finished_hook_called.add(status['filename'])
         ydl.add_progress_hook(_hook)
+        expect_warnings(ydl, test_case.get('expected_warnings', []))
 
         def get_tc_filename(tc):
             return tc.get('file') or ydl.prepare_filename(tc.get('info_dict', {}))
@@ -183,7 +187,9 @@ def generator(test_case):
                         md5_for_file = _file_md5(tc_filename)
                         self.assertEqual(md5_for_file, tc['md5'])
                 info_json_fn = os.path.splitext(tc_filename)[0] + '.info.json'
-                self.assertTrue(os.path.exists(info_json_fn))
+                self.assertTrue(
+                    os.path.exists(info_json_fn),
+                    'Missing info file %s' % info_json_fn)
                 with io.open(info_json_fn, encoding='utf-8') as infof:
                     info_dict = json.load(infof)
 

test/test_swfinterp.py

@@ -37,7 +37,9 @@ def _make_testfunc(testfile):
                 or os.path.getmtime(swf_file) < os.path.getmtime(as_file)):
             # Recompile
             try:
-                subprocess.check_call(['mxmlc', '-output', swf_file, as_file])
+                subprocess.check_call([
+                    'mxmlc', '-output', swf_file,
+                    '-static-link-runtime-shared-libraries', as_file])
             except OSError as ose:
                 if ose.errno == errno.ENOENT:
                     print('mxmlc not found! Skipping test.')

test/test_utils.py

@@ -16,11 +16,11 @@ import json
 import xml.etree.ElementTree
 
 from youtube_dl.utils import (
+    clean_html,
     DateRange,
     encodeFilename,
     find_xpath_attr,
     fix_xml_ampersands,
-    get_meta_content,
     orderedSet,
     OnDemandPagedList,
     InAdvancePagedList,
@@ -45,6 +45,8 @@ from youtube_dl.utils import (
     escape_rfc3986,
     escape_url,
     js_to_json,
+    get_filesystem_encoding,
+    intlist_to_bytes,
 )
 
 
@@ -154,17 +156,6 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'a'), doc[1])
         self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'c'), doc[2])
 
-    def test_meta_parser(self):
-        testhtml = '''
-        <head>
-            <meta name="description" content="foo &amp; bar">
-            <meta content='Plato' name='author'/>
-        </head>
-        '''
-        get_meta = lambda name: get_meta_content(name, testhtml)
-        self.assertEqual(get_meta('description'), 'foo & bar')
-        self.assertEqual(get_meta('author'), 'Plato')
-
     def test_xpath_with_ns(self):
         testxml = '''<root xmlns:media="http://example.com/">
             <media:song>
@@ -286,12 +277,17 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(parse_iso8601('2014-03-23T23:04:26+0100'), 1395612266)
         self.assertEqual(parse_iso8601('2014-03-23T22:04:26+0000'), 1395612266)
         self.assertEqual(parse_iso8601('2014-03-23T22:04:26Z'), 1395612266)
+        self.assertEqual(parse_iso8601('2014-03-23T22:04:26.1234Z'), 1395612266)
 
     def test_strip_jsonp(self):
         stripped = strip_jsonp('cb ([ {"id":"532cb",\n\n\n"x":\n3}\n]\n);')
         d = json.loads(stripped)
         self.assertEqual(d, [{"id": "532cb", "x": 3}])
 
+        stripped = strip_jsonp('parseMetadata({"STATUS":"OK"})\n\n\n//epc')
+        d = json.loads(stripped)
+        self.assertEqual(d, {'STATUS': 'OK'})
+
     def test_uppercase_escape(self):
         self.assertEqual(uppercase_escape('aä'), 'aä')
         self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐')
@@ -355,5 +351,14 @@ class TestUtil(unittest.TestCase):
         on = js_to_json('{"abc": true}')
         self.assertEqual(json.loads(on), {'abc': True})
 
+    def test_clean_html(self):
+        self.assertEqual(clean_html('a:\nb'), 'a: b')
+        self.assertEqual(clean_html('a:\n   "b"'), 'a:    "b"')
+
+    def test_intlist_to_bytes(self):
+        self.assertEqual(
+            intlist_to_bytes([0, 1, 127, 128, 255]),
+            b'\x00\x01\x7f\x80\xff')
+
 if __name__ == '__main__':
     unittest.main()

test/test_youtube_signature.py

@@ -14,7 +14,7 @@ import re
 import string
 
 from youtube_dl.extractor import YoutubeIE
-from youtube_dl.utils import compat_str, compat_urlretrieve
+from youtube_dl.compat import compat_str, compat_urlretrieve
 
 _TESTS = [
     (

youtube_dl/YoutubeDL.py

@@ -22,12 +22,15 @@ import traceback
 if os.name == 'nt':
     import ctypes
 
-from .utils import (
+from .compat import (
     compat_cookiejar,
+    compat_expanduser,
     compat_http_client,
     compat_str,
     compat_urllib_error,
     compat_urllib_request,
+)
+from .utils import (
     escape_url,
     ContentTooShortError,
     date_from_str,
@@ -61,7 +64,8 @@ from .utils import (
 from .cache import Cache
 from .extractor import get_info_extractor, gen_extractors
 from .downloader import get_suitable_downloader
-from .postprocessor import FFmpegMergerPP
+from .downloader.rtmp import rtmpdump_version
+from .postprocessor import FFmpegMergerPP, FFmpegPostProcessor
 from .version import __version__
 
 
@@ -107,6 +111,8 @@ class YoutubeDL(object):
     forcefilename:     Force printing final filename.
     forceduration:     Force printing duration.
     forcejson:         Force printing info_dict as JSON.
+    dump_single_json:  Force printing the info_dict of the whole playlist
+                       (or video) as a single JSON line.
     simulate:          Do not download the video files.
     format:            Video format code.
     format_limit:      Highest quality format to try.
@@ -165,6 +171,8 @@ class YoutubeDL(object):
                        'auto' for elaborate guessing
     encoding:          Use this encoding instead of the system-specified.
     extract_flat:      Do not resolve URLs, return the immediate result.
+                       Pass in 'in_playlist' to only show this behavior for
+                       playlist items.
 
     The following parameters are not used by YoutubeDL itself, they are used by
     the FileDownloader:
@@ -184,7 +192,7 @@ class YoutubeDL(object):
     _num_downloads = None
     _screen_file = None
 
-    def __init__(self, params=None):
+    def __init__(self, params=None, auto_init=True):
         """Create a FileDownloader object with the given options."""
         if params is None:
             params = {}
@@ -241,6 +249,10 @@ class YoutubeDL(object):
 
         self._setup_opener()
 
+        if auto_init:
+            self.print_debug_header()
+            self.add_default_info_extractors()
+
     def add_info_extractor(self, ie):
         """Add an InfoExtractor object to the end of the list."""
         self._ies.append(ie)
@@ -447,7 +459,7 @@ class YoutubeDL(object):
             template_dict = collections.defaultdict(lambda: 'NA', template_dict)
 
             outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL)
-            tmpl = os.path.expanduser(outtmpl)
+            tmpl = compat_expanduser(outtmpl)
             filename = tmpl % template_dict
             return filename
         except ValueError as err:
@@ -568,8 +580,12 @@ class YoutubeDL(object):
 
         result_type = ie_result.get('_type', 'video')
 
-        if self.params.get('extract_flat', False):
-            if result_type in ('url', 'url_transparent'):
+        if result_type in ('url', 'url_transparent'):
+            extract_flat = self.params.get('extract_flat', False)
+            if ((extract_flat == 'in_playlist' and 'playlist' in extra_info) or
+                    extract_flat is True):
+                if self.params.get('forcejson', False):
+                    self.to_stdout(json.dumps(ie_result))
                 return ie_result
 
         if result_type == 'video':
@@ -642,6 +658,8 @@ class YoutubeDL(object):
                 extra = {
                     'n_entries': n_entries,
                     'playlist': playlist,
+                    'playlist_id': ie_result.get('id'),
+                    'playlist_title': ie_result.get('title'),
                     'playlist_index': i + playliststart,
                     'extractor': ie_result['extractor'],
                     'webpage_url': ie_result['webpage_url'],
@@ -820,6 +838,13 @@ class YoutubeDL(object):
                         formats_info = (self.select_format(format_1, formats),
                             self.select_format(format_2, formats))
                         if all(formats_info):
+                            # The first format must contain the video and the
+                            # second the audio
+                            if formats_info[0].get('vcodec') == 'none':
+                                self.report_error('The first format must '
+                                    'contain the video, try using '
+                                    '"-f %s+%s"' % (format_2, format_1))
+                                return
                             selected_format = {
                                 'requested_formats': formats_info,
                                 'format': rf,
@@ -897,6 +922,8 @@ class YoutubeDL(object):
         if self.params.get('forcejson', False):
             info_dict['_filename'] = filename
             self.to_stdout(json.dumps(info_dict))
+        if self.params.get('dump_single_json', False):
+            info_dict['_filename'] = filename
 
         # Do nothing else if in simulate mode
         if self.params.get('simulate', False):
@@ -1015,7 +1042,7 @@ class YoutubeDL(object):
                         downloaded = []
                         success = True
                         merger = FFmpegMergerPP(self, not self.params.get('keepvideo'))
-                        if not merger._get_executable():
+                        if not merger._executable:
                             postprocessors = []
                             self.report_warning('You have requested multiple '
                                 'formats but ffmpeg or avconv are not installed.'
@@ -1064,12 +1091,15 @@ class YoutubeDL(object):
         for url in url_list:
             try:
                 #It also downloads the videos
-                self.extract_info(url)
+                res = self.extract_info(url)
             except UnavailableVideoError:
                 self.report_error('unable to download video')
             except MaxDownloadsReached:
                 self.to_screen('[info] Maximum number of downloaded files reached.')
                 raise
+            else:
+                if self.params.get('dump_single_json', False):
+                    self.to_stdout(json.dumps(res))
 
         return self._download_retcode
 
@@ -1193,6 +1223,8 @@ class YoutubeDL(object):
             res += 'video@'
         if fdict.get('vbr') is not None:
             res += '%4dk' % fdict['vbr']
+        if fdict.get('fps') is not None:
+            res += ', %sfps' % fdict['fps']
         if fdict.get('acodec') is not None:
             if res:
                 res += ', '
@@ -1274,11 +1306,13 @@ class YoutubeDL(object):
             self.report_warning(
                 'Your Python is broken! Update to a newer and supported version')
 
+        stdout_encoding = getattr(
+            sys.stdout, 'encoding', 'missing (%s)' % type(sys.stdout).__name__)
         encoding_str = (
             '[debug] Encodings: locale %s, fs %s, out %s, pref %s\n' % (
                 locale.getpreferredencoding(),
                 sys.getfilesystemencoding(),
-                sys.stdout.encoding,
+                stdout_encoding,
                 self.get_encoding()))
         write_string(encoding_str, encoding=None)
 
@@ -1297,8 +1331,19 @@ class YoutubeDL(object):
                 sys.exc_clear()
             except:
                 pass
-        self._write_string('[debug] Python version %s - %s' %
-                     (platform.python_version(), platform_name()) + '\n')
+        self._write_string('[debug] Python version %s - %s\n' % (
+            platform.python_version(), platform_name()))
+
+        exe_versions = FFmpegPostProcessor.get_versions()
+        exe_versions['rtmpdump'] = rtmpdump_version()
+        exe_str = ', '.join(
+            '%s %s' % (exe, v)
+            for exe, v in sorted(exe_versions.items())
+            if v
+        )
+        if not exe_str:
+            exe_str = 'none'
+        self._write_string('[debug] exe versions: %s\n' % exe_str)
 
         proxy_map = {}
         for handler in self._opener.handlers:

youtube_dl/__init__.py

@@ -1,86 +1,6 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 
-__authors__  = (
-    'Ricardo Garcia Gonzalez',
-    'Danny Colligan',
-    'Benjamin Johnson',
-    'Vasyl\' Vavrychuk',
-    'Witold Baryluk',
-    'Paweł Paprota',
-    'Gergely Imreh',
-    'Rogério Brito',
-    'Philipp Hagemeister',
-    'Sören Schulze',
-    'Kevin Ngo',
-    'Ori Avtalion',
-    'shizeeg',
-    'Filippo Valsorda',
-    'Christian Albrecht',
-    'Dave Vasilevsky',
-    'Jaime Marquínez Ferrándiz',
-    'Jeff Crouse',
-    'Osama Khalid',
-    'Michael Walter',
-    'M. Yasoob Ullah Khalid',
-    'Julien Fraichard',
-    'Johny Mo Swag',
-    'Axel Noack',
-    'Albert Kim',
-    'Pierre Rudloff',
-    'Huarong Huo',
-    'Ismael Mejía',
-    'Steffan \'Ruirize\' James',
-    'Andras Elso',
-    'Jelle van der Waa',
-    'Marcin Cieślak',
-    'Anton Larionov',
-    'Takuya Tsuchida',
-    'Sergey M.',
-    'Michael Orlitzky',
-    'Chris Gahan',
-    'Saimadhav Heblikar',
-    'Mike Col',
-    'Oleg Prutz',
-    'pulpe',
-    'Andreas Schmitz',
-    'Michael Kaiser',
-    'Niklas Laxström',
-    'David Triendl',
-    'Anthony Weems',
-    'David Wagner',
-    'Juan C. Olivares',
-    'Mattias Harrysson',
-    'phaer',
-    'Sainyam Kapoor',
-    'Nicolas Évrard',
-    'Jason Normore',
-    'Hoje Lee',
-    'Adam Thalhammer',
-    'Georg Jähnig',
-    'Ralf Haring',
-    'Koki Takahashi',
-    'Ariset Llerena',
-    'Adam Malcontenti-Wilson',
-    'Tobias Bell',
-    'Naglis Jonaitis',
-    'Charles Chen',
-    'Hassaan Ali',
-    'Dobrosław Żybort',
-    'David Fabijan',
-    'Sebastian Haas',
-    'Alexander Kirk',
-    'Erik Johnson',
-    'Keith Beckman',
-    'Ole Ernst',
-    'Aaron McDaniel (mcd1992)',
-    'Magnus Kolstad',
-    'Hari Padmanaban',
-    'Carlos Ramos',
-    '5moufl',
-    'lenaten',
-)
-
 __license__ = 'Public Domain'
 
 import codecs
@@ -93,9 +13,12 @@ import sys
 from .options import (
     parseOpts,
 )
-from .utils import (
+from .compat import (
+    compat_expanduser,
     compat_getpass,
     compat_print,
+)
+from .utils import (
     DateRange,
     DEFAULT_OUTTMPL,
     decodeOption,
@@ -255,8 +178,6 @@ def _real_main(argv=None):
         date = DateRange.day(opts.date)
     else:
         date = DateRange(opts.dateafter, opts.datebefore)
-    if opts.default_search not in ('auto', 'auto_warning', 'error', 'fixup_error', None) and ':' not in opts.default_search:
-        parser.error(u'--default-search invalid; did you forget a colon (:) at the end?')
 
     # Do not download videos when there are audio-only formats
     if opts.extractaudio and not opts.keepvideo and opts.format is None:
@@ -284,8 +205,8 @@ def _real_main(argv=None):
                      u' file! Use "{0}.%(ext)s" instead of "{0}" as the output'
                      u' template'.format(outtmpl))
 
-    any_printing = opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat or opts.getduration or opts.dumpjson
-    download_archive_fn = os.path.expanduser(opts.download_archive) if opts.download_archive is not None else opts.download_archive
+    any_printing = opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat or opts.getduration or opts.dumpjson or opts.dump_single_json
+    download_archive_fn = compat_expanduser(opts.download_archive) if opts.download_archive is not None else opts.download_archive
 
     ydl_opts = {
         'usenetrc': opts.usenetrc,
@@ -304,8 +225,9 @@ def _real_main(argv=None):
         'forcefilename': opts.getfilename,
         'forceformat': opts.getformat,
         'forcejson': opts.dumpjson,
-        'simulate': opts.simulate,
-        'skip_download': (opts.skip_download or opts.simulate or any_printing),
+        'dump_single_json': opts.dump_single_json,
+        'simulate': opts.simulate or any_printing,
+        'skip_download': opts.skip_download,
         'format': opts.format,
         'format_limit': opts.format_limit,
         'listformats': opts.listformats,
@@ -369,12 +291,10 @@ def _real_main(argv=None):
         'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
         'encoding': opts.encoding,
         'exec_cmd': opts.exec_cmd,
+        'extract_flat': opts.extract_flat,
     }
 
     with YoutubeDL(ydl_opts) as ydl:
-        ydl.print_debug_header()
-        ydl.add_default_info_extractors()
-
         # PostProcessors
         # Add the metadata pp first, the other pps will copy it
         if opts.addmetadata:

youtube_dl/cache.py

@@ -8,9 +8,8 @@ import re
 import shutil
 import traceback
 
-from .utils import (
-    write_json_file,
-)
+from .compat import compat_expanduser
+from .utils import write_json_file
 
 
 class Cache(object):
@@ -22,7 +21,7 @@ class Cache(object):
         if res is None:
             cache_root = os.environ.get('XDG_CACHE_HOME', '~/.cache')
             res = os.path.join(cache_root, 'youtube-dl')
-        return os.path.expanduser(res)
+        return compat_expanduser(res)
 
     def _get_cache_fn(self, section, key, dtype):
         assert re.match(r'^[a-zA-Z0-9_.-]+$', section), \

youtube_dl/compat.py

@@ -0,0 +1,317 @@
+from __future__ import unicode_literals
+
+import getpass
+import os
+import subprocess
+import sys
+
+
+try:
+    import urllib.request as compat_urllib_request
+except ImportError: # Python 2
+    import urllib2 as compat_urllib_request
+
+try:
+    import urllib.error as compat_urllib_error
+except ImportError: # Python 2
+    import urllib2 as compat_urllib_error
+
+try:
+    import urllib.parse as compat_urllib_parse
+except ImportError: # Python 2
+    import urllib as compat_urllib_parse
+
+try:
+    from urllib.parse import urlparse as compat_urllib_parse_urlparse
+except ImportError: # Python 2
+    from urlparse import urlparse as compat_urllib_parse_urlparse
+
+try:
+    import urllib.parse as compat_urlparse
+except ImportError: # Python 2
+    import urlparse as compat_urlparse
+
+try:
+    import http.cookiejar as compat_cookiejar
+except ImportError: # Python 2
+    import cookielib as compat_cookiejar
+
+try:
+    import html.entities as compat_html_entities
+except ImportError: # Python 2
+    import htmlentitydefs as compat_html_entities
+
+try:
+    import html.parser as compat_html_parser
+except ImportError: # Python 2
+    import HTMLParser as compat_html_parser
+
+try:
+    import http.client as compat_http_client
+except ImportError: # Python 2
+    import httplib as compat_http_client
+
+try:
+    from urllib.error import HTTPError as compat_HTTPError
+except ImportError:  # Python 2
+    from urllib2 import HTTPError as compat_HTTPError
+
+try:
+    from urllib.request import urlretrieve as compat_urlretrieve
+except ImportError:  # Python 2
+    from urllib import urlretrieve as compat_urlretrieve
+
+
+try:
+    from subprocess import DEVNULL
+    compat_subprocess_get_DEVNULL = lambda: DEVNULL
+except ImportError:
+    compat_subprocess_get_DEVNULL = lambda: open(os.path.devnull, 'w')
+
+try:
+    from urllib.parse import unquote as compat_urllib_parse_unquote
+except ImportError:
+    def compat_urllib_parse_unquote(string, encoding='utf-8', errors='replace'):
+        if string == '':
+            return string
+        res = string.split('%')
+        if len(res) == 1:
+            return string
+        if encoding is None:
+            encoding = 'utf-8'
+        if errors is None:
+            errors = 'replace'
+        # pct_sequence: contiguous sequence of percent-encoded bytes, decoded
+        pct_sequence = b''
+        string = res[0]
+        for item in res[1:]:
+            try:
+                if not item:
+                    raise ValueError
+                pct_sequence += item[:2].decode('hex')
+                rest = item[2:]
+                if not rest:
+                    # This segment was just a single percent-encoded character.
+                    # May be part of a sequence of code units, so delay decoding.
+                    # (Stored in pct_sequence).
+                    continue
+            except ValueError:
+                rest = '%' + item
+            # Encountered non-percent-encoded characters. Flush the current
+            # pct_sequence.
+            string += pct_sequence.decode(encoding, errors) + rest
+            pct_sequence = b''
+        if pct_sequence:
+            # Flush the final pct_sequence
+            string += pct_sequence.decode(encoding, errors)
+        return string
+
+
+try:
+    from urllib.parse import parse_qs as compat_parse_qs
+except ImportError: # Python 2
+    # HACK: The following is the correct parse_qs implementation from cpython 3's stdlib.
+    # Python 2's version is apparently totally broken
+
+    def _parse_qsl(qs, keep_blank_values=False, strict_parsing=False,
+                encoding='utf-8', errors='replace'):
+        qs, _coerce_result = qs, unicode
+        pairs = [s2 for s1 in qs.split('&') for s2 in s1.split(';')]
+        r = []
+        for name_value in pairs:
+            if not name_value and not strict_parsing:
+                continue
+            nv = name_value.split('=', 1)
+            if len(nv) != 2:
+                if strict_parsing:
+                    raise ValueError("bad query field: %r" % (name_value,))
+                # Handle case of a control-name with no equal sign
+                if keep_blank_values:
+                    nv.append('')
+                else:
+                    continue
+            if len(nv[1]) or keep_blank_values:
+                name = nv[0].replace('+', ' ')
+                name = compat_urllib_parse_unquote(
+                    name, encoding=encoding, errors=errors)
+                name = _coerce_result(name)
+                value = nv[1].replace('+', ' ')
+                value = compat_urllib_parse_unquote(
+                    value, encoding=encoding, errors=errors)
+                value = _coerce_result(value)
+                r.append((name, value))
+        return r
+
+    def compat_parse_qs(qs, keep_blank_values=False, strict_parsing=False,
+                encoding='utf-8', errors='replace'):
+        parsed_result = {}
+        pairs = _parse_qsl(qs, keep_blank_values, strict_parsing,
+                        encoding=encoding, errors=errors)
+        for name, value in pairs:
+            if name in parsed_result:
+                parsed_result[name].append(value)
+            else:
+                parsed_result[name] = [value]
+        return parsed_result
+
+try:
+    compat_str = unicode # Python 2
+except NameError:
+    compat_str = str
+
+try:
+    compat_chr = unichr # Python 2
+except NameError:
+    compat_chr = chr
+
+try:
+    from xml.etree.ElementTree import ParseError as compat_xml_parse_error
+except ImportError:  # Python 2.6
+    from xml.parsers.expat import ExpatError as compat_xml_parse_error
+
+try:
+    from shlex import quote as shlex_quote
+except ImportError:  # Python < 3.3
+    def shlex_quote(s):
+        return "'" + s.replace("'", "'\"'\"'") + "'"
+
+
+def compat_ord(c):
+    if type(c) is int: return c
+    else: return ord(c)
+
+
+if sys.version_info >= (3, 0):
+    compat_getenv = os.getenv
+    compat_expanduser = os.path.expanduser
+else:
+    # Environment variables should be decoded with filesystem encoding.
+    # Otherwise it will fail if any non-ASCII characters present (see #3854 #3217 #2918)
+
+    def compat_getenv(key, default=None):
+        from .utils import get_filesystem_encoding
+        env = os.getenv(key, default)
+        if env:
+            env = env.decode(get_filesystem_encoding())
+        return env
+
+    # HACK: The default implementations of os.path.expanduser from cpython do not decode
+    # environment variables with filesystem encoding. We will work around this by
+    # providing adjusted implementations.
+    # The following are os.path.expanduser implementations from cpython 2.7.8 stdlib
+    # for different platforms with correct environment variables decoding.
+
+    if os.name == 'posix':
+        def compat_expanduser(path):
+            """Expand ~ and ~user constructions.  If user or $HOME is unknown,
+            do nothing."""
+            if not path.startswith('~'):
+                return path
+            i = path.find('/', 1)
+            if i < 0:
+                i = len(path)
+            if i == 1:
+                if 'HOME' not in os.environ:
+                    import pwd
+                    userhome = pwd.getpwuid(os.getuid()).pw_dir
+                else:
+                    userhome = compat_getenv('HOME')
+            else:
+                import pwd
+                try:
+                    pwent = pwd.getpwnam(path[1:i])
+                except KeyError:
+                    return path
+                userhome = pwent.pw_dir
+            userhome = userhome.rstrip('/')
+            return (userhome + path[i:]) or '/'
+    elif os.name == 'nt' or os.name == 'ce':
+        def compat_expanduser(path):
+            """Expand ~ and ~user constructs.
+
+            If user or $HOME is unknown, do nothing."""
+            if path[:1] != '~':
+                return path
+            i, n = 1, len(path)
+            while i < n and path[i] not in '/\\':
+                i = i + 1
+
+            if 'HOME' in os.environ:
+                userhome = compat_getenv('HOME')
+            elif 'USERPROFILE' in os.environ:
+                userhome = compat_getenv('USERPROFILE')
+            elif not 'HOMEPATH' in os.environ:
+                return path
+            else:
+                try:
+                    drive = compat_getenv('HOMEDRIVE')
+                except KeyError:
+                    drive = ''
+                userhome = os.path.join(drive, compat_getenv('HOMEPATH'))
+
+            if i != 1: #~user
+                userhome = os.path.join(os.path.dirname(userhome), path[1:i])
+
+            return userhome + path[i:]
+    else:
+        compat_expanduser = os.path.expanduser
+
+
+if sys.version_info < (3, 0):
+    def compat_print(s):
+        from .utils import preferredencoding
+        print(s.encode(preferredencoding(), 'xmlcharrefreplace'))
+else:
+    def compat_print(s):
+        assert type(s) == type(u'')
+        print(s)
+
+
+try:
+    subprocess_check_output = subprocess.check_output
+except AttributeError:
+    def subprocess_check_output(*args, **kwargs):
+        assert 'input' not in kwargs
+        p = subprocess.Popen(*args, stdout=subprocess.PIPE, **kwargs)
+        output, _ = p.communicate()
+        ret = p.poll()
+        if ret:
+            raise subprocess.CalledProcessError(ret, p.args, output=output)
+        return output
+
+if sys.version_info < (3, 0) and sys.platform == 'win32':
+    def compat_getpass(prompt, *args, **kwargs):
+        if isinstance(prompt, compat_str):
+            from .utils import preferredencoding
+            prompt = prompt.encode(preferredencoding())
+        return getpass.getpass(prompt, *args, **kwargs)
+else:
+    compat_getpass = getpass.getpass
+
+
+__all__ = [
+    'compat_HTTPError',
+    'compat_chr',
+    'compat_cookiejar',
+    'compat_expanduser',
+    'compat_getenv',
+    'compat_getpass',
+    'compat_html_entities',
+    'compat_html_parser',
+    'compat_http_client',
+    'compat_ord',
+    'compat_parse_qs',
+    'compat_print',
+    'compat_str',
+    'compat_subprocess_get_DEVNULL',
+    'compat_urllib_error',
+    'compat_urllib_parse',
+    'compat_urllib_parse_unquote',
+    'compat_urllib_parse_urlparse',
+    'compat_urllib_request',
+    'compat_urlparse',
+    'compat_urlretrieve',
+    'compat_xml_parse_error',
+    'shlex_quote',
+    'subprocess_check_output',
+]

youtube_dl/downloader/f4m.py

@@ -244,9 +244,16 @@ class F4mFD(FileDownloader):
                 lambda f: int(f[0]) == requested_bitrate, formats))[0]
 
         base_url = compat_urlparse.urljoin(man_url, media.attrib['url'])
-        bootstrap = base64.b64decode(doc.find(_add_ns('bootstrapInfo')).text)
+        bootstrap_node = doc.find(_add_ns('bootstrapInfo'))
+        if bootstrap_node.text is None:
+            bootstrap_url = compat_urlparse.urljoin(
+                base_url, bootstrap_node.attrib['url'])
+            bootstrap = self.ydl.urlopen(bootstrap_url).read()
+        else:
+            bootstrap = base64.b64decode(bootstrap_node.text)
         metadata = base64.b64decode(media.find(_add_ns('metadata')).text)
         boot_info = read_bootstrap_info(bootstrap)
+
         fragments_list = build_fragments_list(boot_info)
         if self.params.get('test', False):
             # We only download the first fragment

youtube_dl/downloader/rtmp.py

@@ -12,9 +12,15 @@ from ..utils import (
     compat_str,
     encodeFilename,
     format_bytes,
+    get_exe_version,
 )
 
 
+def rtmpdump_version():
+    return get_exe_version(
+        'rtmpdump', ['--help'], r'(?i)RTMPDump\s*v?([0-9a-zA-Z._-]+)')
+
+
 class RtmpFD(FileDownloader):
     def real_download(self, filename, info_dict):
         def run_rtmpdump(args):

youtube_dl/extractor/__init__.py

@@ -20,12 +20,14 @@ from .arte import (
     ArteTVDDCIE,
     ArteTVEmbedIE,
 )
+from .audiomack import AudiomackIE
 from .auengine import AUEngineIE
 from .bambuser import BambuserIE, BambuserChannelIE
 from .bandcamp import BandcampIE, BandcampAlbumIE
 from .bbccouk import BBCCoUkIE
 from .beeg import BeegIE
 from .behindkink import BehindKinkIE
+from .bild import BildIE
 from .bilibili import BiliBiliIE
 from .blinkx import BlinkxIE
 from .bliptv import BlipTVIE, BlipTVUserIE
@@ -60,9 +62,11 @@ from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE
 from .condenast import CondeNastIE
 from .cracked import CrackedIE
 from .criterion import CriterionIE
-from .crunchyroll import CrunchyrollIE
+from .crunchyroll import (
+    CrunchyrollIE,
+    CrunchyrollShowPlaylistIE
+)
 from .cspan import CSpanIE
-from .d8 import D8IE
 from .dailymotion import (
     DailymotionIE,
     DailymotionPlaylistIE,
@@ -123,6 +127,7 @@ from .francetv import (
 )
 from .freesound import FreesoundIE
 from .freespeech import FreespeechIE
+from .freevideo import FreeVideoIE
 from .funnyordie import FunnyOrDieIE
 from .gamekings import GamekingsIE
 from .gameone import (
@@ -134,8 +139,10 @@ from .gamestar import GameStarIE
 from .gametrailers import GametrailersIE
 from .gdcvault import GDCVaultIE
 from .generic import GenericIE
+from .glide import GlideIE
 from .globo import GloboIE
 from .godtube import GodTubeIE
+from .goldenmoustache import GoldenMoustacheIE
 from .golem import GolemIE
 from .googleplus import GooglePlusIE
 from .googlesearch import GoogleSearchIE
@@ -173,7 +180,6 @@ from .jadorecettepub import JadoreCettePubIE
 from .jeuxvideo import JeuxVideoIE
 from .jove import JoveIE
 from .jukebox import JukeboxIE
-from .justintv import JustinTVIE
 from .jpopsukitv import JpopsukiIE
 from .kankan import KankanIE
 from .keezmovies import KeezMoviesIE
@@ -184,6 +190,7 @@ from .kontrtube import KontrTubeIE
 from .krasview import KrasViewIE
 from .ku6 import Ku6IE
 from .la7 import LA7IE
+from .laola1tv import Laola1TvIE
 from .lifenews import LifeNewsIE
 from .liveleak import LiveLeakIE
 from .livestream import (
@@ -246,7 +253,7 @@ from .newstube import NewstubeIE
 from .nfb import NFBIE
 from .nfl import NFLIE
 from .nhl import NHLIE, NHLVideocenterIE
-from .niconico import NiconicoIE
+from .niconico import NiconicoIE, NiconicoPlaylistIE
 from .ninegag import NineGagIE
 from .noco import NocoIE
 from .normalboots import NormalbootsIE
@@ -275,6 +282,7 @@ from .orf import (
 from .parliamentliveuk import ParliamentLiveUKIE
 from .patreon import PatreonIE
 from .pbs import PBSIE
+from .phoenix import PhoenixIE
 from .photobucket import PhotobucketIE
 from .planetaplay import PlanetaPlayIE
 from .played import PlayedIE
@@ -288,6 +296,7 @@ from .pornoxo import PornoXOIE
 from .promptfile import PromptFileIE
 from .prosiebensat1 import ProSiebenSat1IE
 from .pyvideo import PyvideoIE
+from .quickvid import QuickVidIE
 from .radiofrance import RadioFranceIE
 from .rai import RaiIE
 from .rbmaradio import RBMARadioIE
@@ -316,6 +325,8 @@ from .sbs import SBSIE
 from .scivee import SciVeeIE
 from .screencast import ScreencastIE
 from .servingsys import ServingSysIE
+from .sexu import SexuIE
+from .sexykarma import SexyKarmaIE
 from .shared import SharedIE
 from .sharesix import ShareSixIE
 from .sina import SinaIE
@@ -349,6 +360,7 @@ from .spike import SpikeIE
 from .sport5 import Sport5IE
 from .sportbox import SportBoxIE
 from .sportdeutschland import SportDeutschlandIE
+from .srmediathek import SRMediathekIE
 from .stanfordoc import StanfordOpenClassroomIE
 from .steam import SteamIE
 from .streamcloud import StreamcloudIE
@@ -367,6 +379,7 @@ from .teachingchannel import TeachingChannelIE
 from .teamcoco import TeamcocoIE
 from .techtalks import TechTalksIE
 from .ted import TEDIE
+from .telecinco import TelecincoIE
 from .telemb import TeleMBIE
 from .tenplay import TenPlayIE
 from .testurl import TestURLIE
@@ -395,6 +408,7 @@ from .tutv import TutvIE
 from .tvigle import TvigleIE
 from .tvp import TvpIE
 from .tvplay import TVPlayIE
+from .twitch import TwitchIE
 from .ubu import UbuIE
 from .udemy import (
     UdemyIE,
@@ -410,6 +424,7 @@ from .vesti import VestiIE
 from .vevo import VevoIE
 from .vgtv import VGTVIE
 from .vh1 import VH1IE
+from .vice import ViceIE
 from .viddler import ViddlerIE
 from .videobam import VideoBamIE
 from .videodetective import VideoDetectiveIE
@@ -420,6 +435,7 @@ from .videopremium import VideoPremiumIE
 from .videott import VideoTtIE
 from .videoweed import VideoWeedIE
 from .vidme import VidmeIE
+from .vidzi import VidziIE
 from .vimeo import (
     VimeoIE,
     VimeoAlbumIE,
@@ -439,6 +455,7 @@ from .viki import VikiIE
 from .vk import VKIE
 from .vodlocker import VodlockerIE
 from .vporn import VpornIE
+from .vrt import VRTIE
 from .vube import VubeIE
 from .vuclip import VuClipIE
 from .vulture import VultureIE
@@ -488,10 +505,8 @@ from .youtube import (
     YoutubeUserIE,
     YoutubeWatchLaterIE,
 )
-
 from .zdf import ZDFIE
 
-
 _ALL_CLASSES = [
     klass
     for name, klass in globals().items()

youtube_dl/extractor/abc.py

@@ -11,13 +11,13 @@ class ABCIE(InfoExtractor):
     _VALID_URL = r'http://www\.abc\.net\.au/news/[^/]+/[^/]+/(?P<id>\d+)'
 
     _TEST = {
-        'url': 'http://www.abc.net.au/news/2014-07-25/bringing-asylum-seekers-to-australia-would-give/5624716',
-        'md5': 'dad6f8ad011a70d9ddf887ce6d5d0742',
+        'url': 'http://www.abc.net.au/news/2014-11-05/australia-to-staff-ebola-treatment-centre-in-sierra-leone/5868334',
+        'md5': 'cb3dd03b18455a661071ee1e28344d9f',
         'info_dict': {
-            'id': '5624716',
+            'id': '5868334',
             'ext': 'mp4',
-            'title': 'Bringing asylum seekers to Australia would give them right to asylum claims: professor',
-            'description': 'md5:ba36fa5e27e5c9251fd929d339aea4af',
+            'title': 'Australia to help staff Ebola treatment centre in Sierra Leone',
+            'description': 'md5:809ad29c67a05f54eb41f2a105693a67',
         },
     }
 

youtube_dl/extractor/addanime.py

@@ -3,12 +3,13 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_HTTPError,
     compat_str,
     compat_urllib_parse,
     compat_urllib_parse_urlparse,
-
+)
+from ..utils import (
     ExtractorError,
 )
 

youtube_dl/extractor/allocine.py

@@ -22,7 +22,7 @@ class AllocineIE(InfoExtractor):
             'id': '19546517',
             'ext': 'mp4',
             'title': 'Astérix - Le Domaine des Dieux Teaser VF',
-            'description': 'md5:4a754271d9c6f16c72629a8a993ee884',
+            'description': 'md5:abcd09ce503c6560512c14ebfdb720d2',
             'thumbnail': 're:http://.*\.jpg',
         },
     }, {

youtube_dl/extractor/ard.py

@@ -4,6 +4,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from .generic import GenericIE
 from ..utils import (
     determine_ext,
     ExtractorError,
@@ -12,6 +13,7 @@ from ..utils import (
     parse_duration,
     unified_strdate,
     xpath_text,
+    parse_xml,
 )
 
 
@@ -54,6 +56,11 @@ class ARDMediathekIE(InfoExtractor):
         if '>Der gewünschte Beitrag ist nicht mehr verfügbar.<' in webpage:
             raise ExtractorError('Video %s is no longer available' % video_id, expected=True)
 
+        if re.search(r'[\?&]rss($|[=&])', url):
+            doc = parse_xml(webpage)
+            if doc.tag == 'rss':
+                return GenericIE()._extract_rss(url, video_id, doc)
+
         title = self._html_search_regex(
             [r'<h1(?:\s+class="boxTopHeadline")?>(.*?)</h1>',
              r'<meta name="dcterms.title" content="(.*?)"/>',

youtube_dl/extractor/arte.py

@@ -10,8 +10,8 @@ from ..utils import (
     unified_strdate,
     determine_ext,
     get_element_by_id,
-    compat_str,
     get_element_by_attribute,
+    int_or_none,
 )
 
 # There are different sources of video in arte.tv, the extraction process 
@@ -90,15 +90,24 @@ class ArteTVPlus7IE(InfoExtractor):
         if not upload_date_str:
             upload_date_str = player_info.get('VDA', '').split(' ')[0]
 
+        title = player_info['VTI'].strip()
+        subtitle = player_info.get('VSU', '').strip()
+        if subtitle:
+            title += ' - %s' % subtitle
+
         info_dict = {
             'id': player_info['VID'],
-            'title': player_info['VTI'],
+            'title': title,
             'description': player_info.get('VDE'),
             'upload_date': unified_strdate(upload_date_str),
             'thumbnail': player_info.get('programImage') or player_info.get('VTU', {}).get('IUR'),
         }
 
-        all_formats = player_info['VSR'].values()
+        all_formats = []
+        for format_id, format_dict in player_info['VSR'].items():
+            fmt = dict(format_dict)
+            fmt['format_id'] = format_id
+            all_formats.append(fmt)
         # Some formats use the m3u8 protocol
         all_formats = list(filter(lambda f: f.get('videoFormat') != 'M3U8', all_formats))
         def _match_lang(f):
@@ -149,22 +158,12 @@ class ArteTVPlus7IE(InfoExtractor):
                 )
         formats = sorted(formats, key=sort_key)
         def _format(format_info):
-            quality = ''
-            height = format_info.get('height')
-            if height is not None:
-                quality = compat_str(height)
-            bitrate = format_info.get('bitrate')
-            if bitrate is not None:
-                quality += '-%d' % bitrate
-            if format_info.get('versionCode') is not None:
-                format_id = '%s-%s' % (quality, format_info['versionCode'])
-            else:
-                format_id = quality
             info = {
-                'format_id': format_id,
-                'format_note': format_info.get('versionLibelle'),
-                'width': format_info.get('width'),
-                'height': height,
+                'format_id': format_info['format_id'],
+                'format_note': '%s, %s' % (format_info.get('versionCode'), format_info.get('versionLibelle')),
+                'width': int_or_none(format_info.get('width')),
+                'height': int_or_none(format_info.get('height')),
+                'tbr': int_or_none(format_info.get('bitrate')),
             }
             if format_info['mediaType'] == 'rtmp':
                 info['url'] = format_info['streamer']

youtube_dl/extractor/audiomack.py

@@ -0,0 +1,69 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from .soundcloud import SoundcloudIE
+from ..utils import ExtractorError
+
+import time
+
+
+class AudiomackIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?audiomack\.com/song/(?P<id>[\w/-]+)'
+    IE_NAME = 'audiomack'
+    _TESTS = [
+        #hosted on audiomack
+        {
+            'url': 'http://www.audiomack.com/song/roosh-williams/extraordinary',
+            'info_dict':
+            {
+                'id' : 'roosh-williams/extraordinary',
+                'ext': 'mp3',
+                'title': 'Roosh Williams - Extraordinary'
+            }
+        },
+        #hosted on soundcloud via audiomack
+        {
+            'url': 'http://www.audiomack.com/song/xclusiveszone/take-kare',
+            'file': '172419696.mp3',
+            'info_dict':
+            {
+                'ext': 'mp3',
+                'title': 'Young Thug ft Lil Wayne - Take Kare',
+                "upload_date": "20141016",
+                "description": "New track produced by London On Da Track called “Take Kare\"\n\nhttp://instagram.com/theyoungthugworld\nhttps://www.facebook.com/ThuggerThuggerCashMoney\n",
+                "uploader": "Young Thug World"
+            }
+        }
+    ]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        api_response = self._download_json(
+            "http://www.audiomack.com/api/music/url/song/%s?_=%d" % (
+                video_id, time.time()),
+            video_id)
+
+        if "url" not in api_response:
+            raise ExtractorError("Unable to deduce api url of song")
+        realurl = api_response["url"]
+
+        #Audiomack wraps a lot of soundcloud tracks in their branded wrapper
+        # - if so, pass the work off to the soundcloud extractor
+        if SoundcloudIE.suitable(realurl):
+            return {'_type': 'url', 'url': realurl, 'ie_key': 'Soundcloud'}
+
+        webpage = self._download_webpage(url, video_id)
+        artist = self._html_search_regex(
+            r'<span class="artist">(.*?)</span>', webpage, "artist")
+        songtitle = self._html_search_regex(
+            r'<h1 class="profile-title song-title"><span class="artist">.*?</span>(.*?)</h1>',
+            webpage, "title")
+        title = artist + " - " + songtitle
+
+        return {
+            'id': video_id,
+            'title': title,
+            'url': realurl,
+        }

youtube_dl/extractor/auengine.py

@@ -24,8 +24,7 @@ class AUEngineIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
         title = self._html_search_regex(r'<title>(?P<title>.+?)</title>', webpage, 'title')

youtube_dl/extractor/bandcamp.py

@@ -110,20 +110,25 @@ class BandcampAlbumIE(InfoExtractor):
         'url': 'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1',
         'playlist': [
             {
-                'file': '1353101989.mp3',
                 'md5': '39bc1eded3476e927c724321ddf116cf',
                 'info_dict': {
+                    'id': '1353101989',
+                    'ext': 'mp3',
                     'title': 'Intro',
                 }
             },
             {
-                'file': '38097443.mp3',
                 'md5': '1a2c32e2691474643e912cc6cd4bffaa',
                 'info_dict': {
+                    'id': '38097443',
+                    'ext': 'mp3',
                     'title': 'Kero One - Keep It Alive (Blazo remix)',
                 }
             },
         ],
+        'info_dict': {
+            'title': 'Jazz Format Mixtape vol.1',
+        },
         'params': {
             'playlistend': 2
         },

youtube_dl/extractor/bild.py

@@ -0,0 +1,39 @@
+#coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import int_or_none
+
+
+class BildIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?bild\.de/(?:[^/]+/)+(?P<display_id>[^/]+)-(?P<id>\d+)(?:,auto=true)?\.bild\.html'
+    IE_DESC = 'Bild.de'
+    _TEST = {
+        'url': 'http://www.bild.de/video/clip/apple-ipad-air/das-koennen-die-neuen-ipads-38184146.bild.html',
+        'md5': 'dd495cbd99f2413502a1713a1156ac8a',
+        'info_dict': {
+            'id': '38184146',
+            'ext': 'mp4',
+            'title': 'BILD hat sie getestet',
+            'thumbnail': 'http://bilder.bild.de/fotos/stand-das-koennen-die-neuen-ipads-38184138/Bild/1.bild.jpg',
+            'duration': 196,
+            'description': 'Mit dem iPad Air 2 und dem iPad Mini 3 hat Apple zwei neue Tablet-Modelle präsentiert. BILD-Reporter Sven Stein durfte die Geräte bereits testen. ',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        xml_url = url.split(".bild.html")[0] + ",view=xml.bild.xml"
+        doc = self._download_xml(xml_url, video_id)
+
+        duration = int_or_none(doc.attrib.get('duration'), scale=1000)
+
+        return {
+            'id': video_id,
+            'title': doc.attrib['ueberschrift'],
+            'description': doc.attrib.get('text'),
+            'url': doc.attrib['src'],
+            'thumbnail': doc.attrib.get('img'),
+            'duration': duration,
+        }

youtube_dl/extractor/br.py

@@ -1,8 +1,6 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,

youtube_dl/extractor/brightcove.py

@@ -14,6 +14,7 @@ from ..utils import (
     compat_str,
     compat_urllib_request,
     compat_parse_qs,
+    compat_urllib_parse_urlparse,
 
     determine_ext,
     ExtractorError,
@@ -23,7 +24,7 @@ from ..utils import (
 
 
 class BrightcoveIE(InfoExtractor):
-    _VALID_URL = r'https?://.*brightcove\.com/(services|viewer).*\?(?P<query>.*)'
+    _VALID_URL = r'https?://.*brightcove\.com/(services|viewer).*?\?(?P<query>.*)'
     _FEDERATED_URL_TEMPLATE = 'http://c.brightcove.com/services/viewer/htmlFederated?%s'
 
     _TESTS = [
@@ -87,6 +88,15 @@ class BrightcoveIE(InfoExtractor):
                 'description': 'UCI MTB World Cup 2014: Fort William, UK - Downhill Finals',
             },
         },
+        {
+            # playlist test
+            # from http://support.brightcove.com/en/video-cloud/docs/playlist-support-single-video-players
+            'url': 'http://c.brightcove.com/services/viewer/htmlFederated?playerID=3550052898001&playerKey=AQ%7E%7E%2CAAABmA9XpXk%7E%2C-Kp7jNgisre1fG5OdqpAFUTcs0lP_ZoL',
+            'info_dict': {
+                'title': 'Sealife',
+            },
+            'playlist_mincount': 7,
+        },
     ]
 
     @classmethod
@@ -251,11 +261,19 @@ class BrightcoveIE(InfoExtractor):
             formats = []
             for rend in renditions:
                 url = rend['defaultURL']
+                if not url:
+                    continue
                 if rend['remote']:
-                    # This type of renditions are served through akamaihd.net,
-                    # but they don't use f4m manifests
-                    url = url.replace('control/', '') + '?&v=3.3.0&fp=13&r=FEEFJ&g=RTSJIMBMPFPB'
-                    ext = 'flv'
+                    url_comp = compat_urllib_parse_urlparse(url)
+                    if url_comp.path.endswith('.m3u8'):
+                        formats.extend(
+                            self._extract_m3u8_formats(url, info['id'], 'mp4'))
+                        continue
+                    elif 'akamaihd.net' in url_comp.netloc:
+                        # This type of renditions are served through
+                        # akamaihd.net, but they don't use f4m manifests
+                        url = url.replace('control/', '') + '?&v=3.3.0&fp=13&r=FEEFJ&g=RTSJIMBMPFPB'
+                        ext = 'flv'
                 else:
                     ext = determine_ext(url)
                 size = rend.get('size')

youtube_dl/extractor/byutv.py

@@ -10,12 +10,12 @@ from ..utils import ExtractorError
 class BYUtvIE(InfoExtractor):
     _VALID_URL = r'^https?://(?:www\.)?byutv.org/watch/[0-9a-f-]+/(?P<video_id>[^/?#]+)'
     _TEST = {
-        'url': 'http://www.byutv.org/watch/44e80f7b-e3ba-43ba-8c51-b1fd96c94a79/granite-flats-talking',
+        'url': 'http://www.byutv.org/watch/6587b9a3-89d2-42a6-a7f7-fd2f81840a7d/studio-c-season-5-episode-5',
         'info_dict': {
-            'id': 'granite-flats-talking',
+            'id': 'studio-c-season-5-episode-5',
             'ext': 'mp4',
-            'description': 'md5:4e9a7ce60f209a33eca0ac65b4918e1c',
-            'title': 'Talking',
+            'description': 'md5:5438d33774b6bdc662f9485a340401cc',
+            'title': 'Season 5 Episode 5',
             'thumbnail': 're:^https?://.*promo.*'
         },
         'params': {

youtube_dl/extractor/canalplus.py

@@ -7,15 +7,21 @@ from .common import InfoExtractor
 from ..utils import (
     unified_strdate,
     url_basename,
+    qualities,
 )
 
 
 class CanalplusIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.canalplus\.fr/.*?/(?P<path>.*)|player\.canalplus\.fr/#/(?P<id>[0-9]+))'
-    _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/cplus/%s'
-    IE_NAME = 'canalplus.fr'
+    IE_DESC = 'canalplus.fr, piwiplus.fr and d8.tv'
+    _VALID_URL = r'https?://(?:www\.(?P<site>canalplus\.fr|piwiplus\.fr|d8\.tv)/.*?/(?P<path>.*)|player\.canalplus\.fr/#/(?P<id>[0-9]+))'
+    _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/%s/%s'
+    _SITE_ID_MAP = {
+        'canalplus.fr': 'cplus',
+        'piwiplus.fr': 'teletoon',
+        'd8.tv': 'd8',
+    }
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.canalplus.fr/c-infos-documentaires/pid1830-c-zapping.html?vid=922470',
         'md5': '3db39fb48b9685438ecf33a1078023e4',
         'info_dict': {
@@ -25,36 +31,73 @@ class CanalplusIE(InfoExtractor):
             'description': 'Le meilleur de toutes les chaînes, tous les jours.\nEmission du 26 août 2013',
             'upload_date': '20130826',
         },
-    }
+    }, {
+        'url': 'http://www.piwiplus.fr/videos-piwi/pid1405-le-labyrinthe-boing-super-ranger.html?vid=1108190',
+        'info_dict': {
+            'id': '1108190',
+            'ext': 'flv',
+            'title': 'Le labyrinthe - Boing super ranger',
+            'description': 'md5:4cea7a37153be42c1ba2c1d3064376ff',
+            'upload_date': '20140724',
+        },
+        'skip': 'Only works from France',
+    }, {
+        'url': 'http://www.d8.tv/d8-docs-mags/pid6589-d8-campagne-intime.html',
+        'info_dict': {
+            'id': '966289',
+            'ext': 'flv',
+            'title': 'Campagne intime - Documentaire exceptionnel',
+            'description': 'md5:d2643b799fb190846ae09c61e59a859f',
+            'upload_date': '20131108',
+        },
+        'skip': 'videos get deleted after a while',
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.groupdict().get('id')
 
+        site_id = self._SITE_ID_MAP[mobj.group('site') or 'canal']
+
         # Beware, some subclasses do not define an id group
         display_id = url_basename(mobj.group('path'))
 
         if video_id is None:
             webpage = self._download_webpage(url, display_id)
-            video_id = self._search_regex(r'<canal:player videoId="(\d+)"', webpage, 'video id')
+            video_id = self._search_regex(
+                r'<canal:player[^>]+?videoId="(\d+)"', webpage, 'video id')
 
-        info_url = self._VIDEO_INFO_TEMPLATE % video_id
+        info_url = self._VIDEO_INFO_TEMPLATE % (site_id, video_id)
         doc = self._download_xml(info_url, video_id, 'Downloading video XML')
 
         video_info = [video for video in doc if video.find('ID').text == video_id][0]
         media = video_info.find('MEDIA')
         infos = video_info.find('INFOS')
 
-        preferences = ['MOBILE', 'BAS_DEBIT', 'HAUT_DEBIT', 'HD', 'HLS', 'HDS']
+        preference = qualities(['MOBILE', 'BAS_DEBIT', 'HAUT_DEBIT', 'HD', 'HLS', 'HDS'])
 
-        formats = [
-            {
-                'url': fmt.text + '?hdcore=2.11.3' if fmt.tag == 'HDS' else fmt.text,
-                'format_id': fmt.tag,
-                'ext': 'mp4' if fmt.tag == 'HLS' else 'flv',
-                'preference': preferences.index(fmt.tag) if fmt.tag in preferences else -1,
-            } for fmt in media.find('VIDEOS') if fmt.text
-        ]
+        formats = []
+        for fmt in media.find('VIDEOS'):
+            format_url = fmt.text
+            if not format_url:
+                continue
+            format_id = fmt.tag
+            if format_id == 'HLS':
+                hls_formats = self._extract_m3u8_formats(format_url, video_id, 'flv')
+                for fmt in hls_formats:
+                    fmt['preference'] = preference(format_id)
+                formats.extend(hls_formats)
+            elif format_id == 'HDS':
+                hds_formats = self._extract_f4m_formats(format_url + '?hdcore=2.11.3', video_id)
+                for fmt in hds_formats:
+                    fmt['preference'] = preference(format_id)
+                formats.extend(hds_formats)
+            else:
+                formats.append({
+                    'url': format_url,
+                    'format_id': format_id,
+                    'preference': preference(format_id),
+                })
         self._sort_formats(formats)
 
         return {

youtube_dl/extractor/channel9.py

@@ -27,7 +27,7 @@ class Channel9IE(InfoExtractor):
                 'title': 'Developer Kick-Off Session: Stuff We Love',
                 'description': 'md5:c08d72240b7c87fcecafe2692f80e35f',
                 'duration': 4576,
-                'thumbnail': 'http://media.ch9.ms/ch9/9d51/03902f2d-fc97-4d3c-b195-0bfe15a19d51/KOS002_220.jpg',
+                'thumbnail': 'http://video.ch9.ms/ch9/9d51/03902f2d-fc97-4d3c-b195-0bfe15a19d51/KOS002_220.jpg',
                 'session_code': 'KOS002',
                 'session_day': 'Day 1',
                 'session_room': 'Arena 1A',
@@ -43,7 +43,7 @@ class Channel9IE(InfoExtractor):
                 'title': 'Self-service BI with Power BI - nuclear testing',
                 'description': 'md5:d1e6ecaafa7fb52a2cacdf9599829f5b',
                 'duration': 1540,
-                'thumbnail': 'http://media.ch9.ms/ch9/87e1/0300391f-a455-4c72-bec3-4422f19287e1/selfservicenuk_512.jpg',
+                'thumbnail': 'http://video.ch9.ms/ch9/87e1/0300391f-a455-4c72-bec3-4422f19287e1/selfservicenuk_512.jpg',
                 'authors': [ 'Mike Wilmot' ],
             },
         }
@@ -94,7 +94,7 @@ class Channel9IE(InfoExtractor):
 
     def _extract_title(self, html):
         title = self._html_search_meta('title', html, 'title')
-        if title is None:           
+        if title is None:
             title = self._og_search_title(html)
             TITLE_SUFFIX = ' (Channel 9)'
             if title is not None and title.endswith(TITLE_SUFFIX):
@@ -115,7 +115,7 @@ class Channel9IE(InfoExtractor):
         return self._html_search_meta('description', html, 'description')
 
     def _extract_duration(self, html):
-        m = re.search(r'data-video_duration="(?P<hours>\d{2}):(?P<minutes>\d{2}):(?P<seconds>\d{2})"', html)
+        m = re.search(r'"length": *"(?P<hours>\d{2}):(?P<minutes>\d{2}):(?P<seconds>\d{2})"', html)
         return ((int(m.group('hours')) * 60 * 60) + (int(m.group('minutes')) * 60) + int(m.group('seconds'))) if m else None
 
     def _extract_slides(self, html):
@@ -167,7 +167,7 @@ class Channel9IE(InfoExtractor):
         return re.findall(r'<a href="/Events/Speakers/[^"]+">([^<]+)</a>', html)
 
     def _extract_content(self, html, content_path):
-        # Look for downloadable content        
+        # Look for downloadable content
         formats = self._formats_from_html(html)
         slides = self._extract_slides(html)
         zip_ = self._extract_zip(html)
@@ -258,16 +258,17 @@ class Channel9IE(InfoExtractor):
 
         webpage = self._download_webpage(url, content_path, 'Downloading web page')
 
-        page_type_m = re.search(r'<meta name="Search.PageType" content="(?P<pagetype>[^"]+)"/>', webpage)
-        if page_type_m is None:
-            raise ExtractorError('Search.PageType not found, don\'t know how to process this page', expected=True)
+        page_type_m = re.search(r'<meta name="WT.entryid" content="(?P<pagetype>[^:]+)[^"]+"/>', webpage)
+        if page_type_m is not None:
+            page_type = page_type_m.group('pagetype')
+            if page_type == 'Entry':      # Any 'item'-like page, may contain downloadable content
+                return self._extract_entry_item(webpage, content_path)
+            elif page_type == 'Session':  # Event session page, may contain downloadable content
+                return self._extract_session(webpage, content_path)
+            elif page_type == 'Event':
+                return self._extract_list(content_path)
+            else:
+                raise ExtractorError('Unexpected WT.entryid %s' % page_type, expected=True)
 
-        page_type = page_type_m.group('pagetype')
-        if page_type == 'List':         # List page, may contain list of 'item'-like objects
+        else: # Assuming list
             return self._extract_list(content_path)
-        elif page_type == 'Entry.Item': # Any 'item'-like page, may contain downloadable content
-            return self._extract_entry_item(webpage, content_path)
-        elif page_type == 'Session':    # Event session page, may contain downloadable content
-            return self._extract_session(webpage, content_path)
-        else:
-            raise ExtractorError('Unexpected Search.PageType %s' % page_type, expected=True)

youtube_dl/extractor/cinemassacre.py

@@ -42,53 +42,71 @@ class CinemassacreIE(InfoExtractor):
 
         webpage = self._download_webpage(url, display_id)
         video_date = mobj.group('date_Y') + mobj.group('date_m') + mobj.group('date_d')
-        mobj = re.search(r'src="(?P<embed_url>http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?id=(?:Cinemassacre-)?(?P<video_id>.+?))"', webpage)
+        mobj = re.search(r'src="(?P<embed_url>http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=(?P<full_video_id>(?:Cinemassacre-)?(?P<video_id>.+?)))"', webpage)
         if not mobj:
             raise ExtractorError('Can\'t extract embed url and video id')
         playerdata_url = mobj.group('embed_url')
         video_id = mobj.group('video_id')
+        full_video_id = mobj.group('full_video_id')
 
         video_title = self._html_search_regex(
             r'<title>(?P<title>.+?)\|', webpage, 'title')
         video_description = self._html_search_regex(
             r'<div class="entry-content">(?P<description>.+?)</div>',
             webpage, 'description', flags=re.DOTALL, fatal=False)
+        video_thumbnail = self._og_search_thumbnail(webpage)
 
         playerdata = self._download_webpage(playerdata_url, video_id, 'Downloading player webpage')
-        video_thumbnail = self._search_regex(
-            r'image: \'(?P<thumbnail>[^\']+)\'', playerdata, 'thumbnail', fatal=False)
-        sd_url = self._search_regex(r'file: \'([^\']+)\', label: \'SD\'', playerdata, 'sd_file')
-        videolist_url = self._search_regex(r'file: \'([^\']+\.smil)\'}', playerdata, 'videolist_url')
 
-        videolist = self._download_xml(videolist_url, video_id, 'Downloading videolist XML')
+        vidurl = self._search_regex(
+            r'\'vidurl\'\s*:\s*"([^\']+)"', playerdata, 'vidurl').replace('\\/', '/')
 
-        formats = []
-        baseurl = sd_url[:sd_url.rfind('/')+1]
-        for video in videolist.findall('.//video'):
-            src = video.get('src')
-            if not src:
-                continue
-            file_ = src.partition(':')[-1]
-            width = int_or_none(video.get('width'))
-            height = int_or_none(video.get('height'))
-            bitrate = int_or_none(video.get('system-bitrate'))
-            format = {
-                'url': baseurl + file_,
-                'format_id': src.rpartition('.')[0].rpartition('_')[-1],
-            }
-            if width or height:
-                format.update({
-                    'tbr': bitrate // 1000 if bitrate else None,
-                    'width': width,
-                    'height': height,
-                })
-            else:
-                format.update({
-                    'abr': bitrate // 1000 if bitrate else None,
-                    'vcodec': 'none',
-                })
-            formats.append(format)
-        self._sort_formats(formats)
+        videolist_url = None
+
+        mobj = re.search(r"'videoserver'\s*:\s*'(?P<videoserver>[^']+)'", playerdata)
+        if mobj:
+            videoserver = mobj.group('videoserver')
+            mobj = re.search(r'\'vidid\'\s*:\s*"(?P<vidid>[^\']+)"', playerdata)
+            vidid = mobj.group('vidid') if mobj else full_video_id
+            videolist_url = 'http://%s/vod/smil:%s.smil/jwplayer.smil' % (videoserver, vidid)
+        else:
+            mobj = re.search(r"file\s*:\s*'(?P<smil>http.+?/jwplayer\.smil)'", playerdata)
+            if mobj:
+                videolist_url = mobj.group('smil')
+
+        if videolist_url:
+            videolist = self._download_xml(videolist_url, video_id, 'Downloading videolist XML')
+            formats = []
+            baseurl = vidurl[:vidurl.rfind('/')+1]
+            for video in videolist.findall('.//video'):
+                src = video.get('src')
+                if not src:
+                    continue
+                file_ = src.partition(':')[-1]
+                width = int_or_none(video.get('width'))
+                height = int_or_none(video.get('height'))
+                bitrate = int_or_none(video.get('system-bitrate'))
+                format = {
+                    'url': baseurl + file_,
+                    'format_id': src.rpartition('.')[0].rpartition('_')[-1],
+                }
+                if width or height:
+                    format.update({
+                        'tbr': bitrate // 1000 if bitrate else None,
+                        'width': width,
+                        'height': height,
+                    })
+                else:
+                    format.update({
+                        'abr': bitrate // 1000 if bitrate else None,
+                        'vcodec': 'none',
+                    })
+                formats.append(format)
+            self._sort_formats(formats)
+        else:
+            formats = [{
+                'url': vidurl,
+            }]
 
         return {
             'id': video_id,

youtube_dl/extractor/cliphunter.py

@@ -4,7 +4,6 @@ import json
 import re
 
 from .common import InfoExtractor
-from ..utils import int_or_none
 
 
 _translation_table = {
@@ -39,9 +38,7 @@ class CliphunterIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
         video_title = self._search_regex(

youtube_dl/extractor/cloudy.py

@@ -4,14 +4,16 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
+from ..compat import (
     compat_parse_qs,
     compat_urllib_parse,
-    remove_end,
-    HEADRequest,
     compat_HTTPError,
 )
+from ..utils import (
+    ExtractorError,
+    HEADRequest,
+    remove_end,
+)
 
 
 class CloudyIE(InfoExtractor):

youtube_dl/extractor/cnn.py

@@ -12,13 +12,14 @@ from ..utils import (
 
 class CNNIE(InfoExtractor):
     _VALID_URL = r'''(?x)https?://((edition|www)\.)?cnn\.com/video/(data/.+?|\?)/
-        (?P<path>.+?/(?P<title>[^/]+?)(?:\.cnn|(?=&)))'''
+        (?P<path>.+?/(?P<title>[^/]+?)(?:\.cnn(-ap)?|(?=&)))'''
 
     _TESTS = [{
         'url': 'http://edition.cnn.com/video/?/video/sports/2013/06/09/nadal-1-on-1.cnn',
-        'file': 'sports_2013_06_09_nadal-1-on-1.cnn.mp4',
         'md5': '3e6121ea48df7e2259fe73a0628605c4',
         'info_dict': {
+            'id': 'sports_2013_06_09_nadal-1-on-1.cnn',
+            'ext': 'mp4',
             'title': 'Nadal wins 8th French Open title',
             'description': 'World Sport\'s Amanda Davies chats with 2013 French Open champion Rafael Nadal.',
             'duration': 135,
@@ -27,9 +28,10 @@ class CNNIE(InfoExtractor):
     },
     {
         "url": "http://edition.cnn.com/video/?/video/us/2013/08/21/sot-student-gives-epic-speech.georgia-institute-of-technology&utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%3A+rss%2Fcnn_topstories+%28RSS%3A+Top+Stories%29",
-        "file": "us_2013_08_21_sot-student-gives-epic-speech.georgia-institute-of-technology.mp4",
         "md5": "b5cc60c60a3477d185af8f19a2a26f4e",
         "info_dict": {
+            'id': 'us/2013/08/21/sot-student-gives-epic-speech.georgia-institute-of-technology',
+            'ext': 'mp4',
             "title": "Student's epic speech stuns new freshmen",
             "description": "A Georgia Tech student welcomes the incoming freshmen with an epic speech backed by music from \"2001: A Space Odyssey.\"",
             "upload_date": "20130821",

youtube_dl/extractor/common.py

@@ -12,13 +12,14 @@ import sys
 import time
 import xml.etree.ElementTree
 
-from ..utils import (
+from ..compat import (
     compat_http_client,
     compat_urllib_error,
     compat_urllib_parse_urlparse,
     compat_urlparse,
     compat_str,
-
+)
+from ..utils import (
     clean_html,
     compiled_regex_type,
     ExtractorError,
@@ -72,6 +73,7 @@ class InfoExtractor(object):
                     * acodec     Name of the audio codec in use
                     * asr        Audio sampling rate in Hertz
                     * vbr        Average video bitrate in KBit/s
+                    * fps        Frame rate
                     * vcodec     Name of the video codec in use
                     * container  Name of the container format
                     * filesize   The number of bytes, if known in advance
@@ -89,6 +91,10 @@ class InfoExtractor(object):
                                  format, irrespective of the file format.
                                  -1 for default (order by other properties),
                                  -2 or smaller for less than default.
+                    * source_preference  Order number for this video source
+                                  (quality takes higher priority)
+                                 -1 for default (order by other properties),
+                                 -2 or smaller for less than default.
                     * http_referer  HTTP Referer header value to set.
                     * http_method  HTTP method to use for the download.
                     * http_headers  A dictionary of additional HTTP headers
@@ -238,7 +244,6 @@ class InfoExtractor(object):
 
     def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True):
         """ Returns a tuple (page content as string, URL handle) """
-
         # Strip hashes from the URL (#1038)
         if isinstance(url_or_request, (compat_str, str)):
             url_or_request = url_or_request.partition('#')[0]
@@ -247,6 +252,10 @@ class InfoExtractor(object):
         if urlh is False:
             assert not fatal
             return False
+        content = self._webpage_read_content(urlh, url_or_request, video_id, note, errnote, fatal)
+        return (content, urlh)
+
+    def _webpage_read_content(self, urlh, url_or_request, video_id, note=None, errnote=None, fatal=True):
         content_type = urlh.headers.get('Content-Type', '')
         webpage_bytes = urlh.read()
         m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type)
@@ -281,6 +290,12 @@ class InfoExtractor(object):
             raw_filename = basen + '.dump'
             filename = sanitize_filename(raw_filename, restricted=True)
             self.to_screen('Saving request to ' + filename)
+            # Working around MAX_PATH limitation on Windows (see
+            # http://msdn.microsoft.com/en-us/library/windows/desktop/aa365247(v=vs.85).aspx)
+            if os.name == 'nt':
+                absfilepath = os.path.abspath(filename)
+                if len(absfilepath) > 259:
+                    filename = '\\\\?\\' + absfilepath
             with open(filename, 'wb') as outf:
                 outf.write(webpage_bytes)
 
@@ -299,7 +314,7 @@ class InfoExtractor(object):
                 msg += ' Visit %s for more details' % blocked_iframe
             raise ExtractorError(msg, expected=True)
 
-        return (content, urlh)
+        return content
 
     def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True):
         """ Returns the data of the page as a string """
@@ -389,7 +404,7 @@ class InfoExtractor(object):
             video_info['title'] = playlist_title
         return video_info
 
-    def _search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0):
+    def _search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0, group=None):
         """
         Perform a regex search on the given string, using a single or a list of
         patterns returning the first matching group.
@@ -410,8 +425,11 @@ class InfoExtractor(object):
             _name = name
 
         if mobj:
-            # return the first matching group
-            return next(g for g in mobj.groups() if g is not None)
+            if group is None:
+                # return the first matching group
+                return next(g for g in mobj.groups() if g is not None)
+            else:
+                return mobj.group(group)
         elif default is not _NO_DEFAULT:
             return default
         elif fatal:
@@ -421,11 +439,11 @@ class InfoExtractor(object):
                 'please report this issue on http://yt-dl.org/bug' % _name)
             return None
 
-    def _html_search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0):
+    def _html_search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0, group=None):
         """
         Like _search_regex, but strips HTML tags and unescapes entities.
         """
-        res = self._search_regex(pattern, string, name, default, fatal, flags)
+        res = self._search_regex(pattern, string, name, default, fatal, flags, group)
         if res:
             return clean_html(res).strip()
         else:
@@ -519,9 +537,9 @@ class InfoExtractor(object):
             display_name = name
         return self._html_search_regex(
             r'''(?ix)<meta
-                    (?=[^>]+(?:itemprop|name|property)=["\']?%s["\']?)
-                    [^>]+content=["\']([^"\']+)["\']''' % re.escape(name),
-            html, display_name, fatal=fatal, **kwargs)
+                    (?=[^>]+(?:itemprop|name|property)=(["\']?)%s\1)
+                    [^>]+content=(["\'])(?P<content>.*?)\1''' % re.escape(name),
+            html, display_name, fatal=fatal, group='content', **kwargs)
 
     def _dc_search_uploader(self, html):
         return self._html_search_meta('dc.creator', html, 'uploader')
@@ -605,14 +623,16 @@ class InfoExtractor(object):
                 f.get('vbr') if f.get('vbr') is not None else -1,
                 f.get('abr') if f.get('abr') is not None else -1,
                 audio_ext_preference,
+                f.get('fps') if f.get('fps') is not None else -1,
                 f.get('filesize') if f.get('filesize') is not None else -1,
                 f.get('filesize_approx') if f.get('filesize_approx') is not None else -1,
+                f.get('source_preference') if f.get('source_preference') is not None else -1,
                 f.get('format_id'),
             )
         formats.sort(key=_formats_key)
 
     def http_scheme(self):
-        """ Either "https:" or "https:", depending on the user's preferences """
+        """ Either "http:" or "https:", depending on the user's preferences """
         return (
             'http:'
             if self._downloader.params.get('prefer_insecure', False)
@@ -675,7 +695,10 @@ class InfoExtractor(object):
             if re.match(r'^https?://', u)
             else compat_urlparse.urljoin(m3u8_url, u))
 
-        m3u8_doc = self._download_webpage(m3u8_url, video_id)
+        m3u8_doc = self._download_webpage(
+            m3u8_url, video_id,
+            note='Downloading m3u8 information',
+            errnote='Failed to download m3u8 information')
         last_info = None
         kv_rex = re.compile(
             r'(?P<key>[a-zA-Z_-]+)=(?P<val>"[^"]+"|[^",]+)(?:,|$)')

youtube_dl/extractor/condenast.py

@@ -34,6 +34,8 @@ class CondeNastIE(InfoExtractor):
     _VALID_URL = r'http://(video|www|player)\.(?P<site>%s)\.com/(?P<type>watch|series|video|embed)/(?P<id>[^/?#]+)' % '|'.join(_SITES.keys())
     IE_DESC = 'Condé Nast media group: %s' % ', '.join(sorted(_SITES.values()))
 
+    EMBED_URL = r'(?:https?:)?//player\.(?P<site>%s)\.com/(?P<type>embed)/.+?' % '|'.join(_SITES.keys())
+
     _TEST = {
         'url': 'http://video.wired.com/watch/3d-printed-speakers-lit-with-led',
         'md5': '1921f713ed48aabd715691f774c451f7',

youtube_dl/extractor/crunchyroll.py

@@ -17,13 +17,13 @@ from ..utils import (
     bytes_to_intlist,
     intlist_to_bytes,
     unified_strdate,
-    clean_html,
     urlencode_postdata,
 )
 from ..aes import (
     aes_cbc_decrypt,
     inc,
 )
+from .common import InfoExtractor
 
 
 class CrunchyrollIE(SubtitlesInfoExtractor):
@@ -39,6 +39,7 @@ class CrunchyrollIE(SubtitlesInfoExtractor):
             'thumbnail': 'http://img1.ak.crunchyroll.com/i/spire1-tmb/20c6b5e10f1a47b10516877d3c039cae1380951166_full.jpg',
             'uploader': 'Yomiuri Telecasting Corporation (YTV)',
             'upload_date': '20131013',
+            'url': 're:(?!.*&amp)',
         },
         'params': {
             # rtmp
@@ -107,19 +108,17 @@ class CrunchyrollIE(SubtitlesInfoExtractor):
         decrypted_data = intlist_to_bytes(aes_cbc_decrypt(data, key, iv))
         return zlib.decompress(decrypted_data)
 
-    def _convert_subtitles_to_srt(self, subtitles):
+    def _convert_subtitles_to_srt(self, sub_root):
         output = ''
-        for i, (start, end, text) in enumerate(re.findall(r'<event [^>]*?start="([^"]+)" [^>]*?end="([^"]+)" [^>]*?text="([^"]+)"[^>]*?>', subtitles), 1):
-            start = start.replace('.', ',')
-            end = end.replace('.', ',')
-            text = clean_html(text)
-            text = text.replace('\\N', '\n')
-            if not text:
-                continue
+
+        for i, event in enumerate(sub_root.findall('./events/event'), 1):
+            start = event.attrib['start'].replace('.', ',')
+            end = event.attrib['end'].replace('.', ',')
+            text = event.attrib['text'].replace('\\N', '\n')
             output += '%d\n%s --> %s\n%s\n\n' % (i, start, end, text)
         return output
 
-    def _convert_subtitles_to_ass(self, subtitles):
+    def _convert_subtitles_to_ass(self, sub_root):
         output = ''
 
         def ass_bool(strvalue):
@@ -128,10 +127,6 @@ class CrunchyrollIE(SubtitlesInfoExtractor):
                 assvalue = '-1'
             return assvalue
 
-        sub_root = xml.etree.ElementTree.fromstring(subtitles)
-        if not sub_root:
-            return output
-
         output = '[Script Info]\n'
         output += 'Title: %s\n' % sub_root.attrib["title"]
         output += 'ScriptType: v4.00+\n'
@@ -237,12 +232,14 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
             streamdata_req.data = 'req=RpcApiVideoEncode%5FGetStreamInfo&video%5Fencode%5Fquality='+stream_quality+'&media%5Fid='+stream_id+'&video%5Fformat='+stream_format
             streamdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
             streamdata_req.add_header('Content-Length', str(len(streamdata_req.data)))
-            streamdata = self._download_webpage(streamdata_req, video_id, note='Downloading media info for '+video_format)
-            video_url = self._search_regex(r'<host>([^<]+)', streamdata, 'video_url')
-            video_play_path = self._search_regex(r'<file>([^<]+)', streamdata, 'video_play_path')
+            streamdata = self._download_xml(
+                streamdata_req, video_id,
+                note='Downloading media info for %s' % video_format)
+            video_url = streamdata.find('.//host').text
+            video_play_path = streamdata.find('.//file').text
             formats.append({
                 'url': video_url,
-                'play_path':   video_play_path,
+                'play_path': video_play_path,
                 'ext': 'flv',
                 'format': video_format,
                 'format_id': video_format,
@@ -266,10 +263,13 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
             lang_code = self._search_regex(r'lang_code=["\']([^"\']+)', subtitle, 'subtitle_lang_code', fatal=False)
             if not lang_code:
                 continue
+            sub_root = xml.etree.ElementTree.fromstring(subtitle)
+            if not sub_root:
+                subtitles[lang_code] = ''
             if sub_format == 'ass':
-                subtitles[lang_code] = self._convert_subtitles_to_ass(subtitle)
+                subtitles[lang_code] = self._convert_subtitles_to_ass(sub_root)
             else:
-                subtitles[lang_code] = self._convert_subtitles_to_srt(subtitle)
+                subtitles[lang_code] = self._convert_subtitles_to_srt(sub_root)
 
         if self._downloader.params.get('listsubtitles', False):
             self._list_available_subtitles(video_id, subtitles)
@@ -285,3 +285,40 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
             'subtitles':   subtitles,
             'formats':     formats,
         }
+
+
+class CrunchyrollShowPlaylistIE(InfoExtractor):
+    IE_NAME = "crunchyroll:playlist"
+    _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?!(?:news|anime-news|library|forum|launchcalendar|lineup|store|comics|freetrial|login))(?P<id>[\w\-]+))/?$'
+
+    _TESTS = [{
+        'url': 'http://www.crunchyroll.com/a-bridge-to-the-starry-skies-hoshizora-e-kakaru-hashi',
+        'info_dict': {
+            'id': 'a-bridge-to-the-starry-skies-hoshizora-e-kakaru-hashi',
+            'title': 'A Bridge to the Starry Skies - Hoshizora e Kakaru Hashi'
+        },
+        'playlist_count': 13,
+    }]
+
+    def _real_extract(self, url):
+        show_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, show_id)
+        title = self._html_search_regex(
+            r'(?s)<h1[^>]*>\s*<span itemprop="name">(.*?)</span>',
+            webpage, 'title')
+        episode_paths = re.findall(
+            r'(?s)<li id="showview_videos_media_[0-9]+"[^>]+>.*?<a href="([^"]+)"',
+            webpage)
+        entries = [
+            self.url_result('http://www.crunchyroll.com' + ep, 'Crunchyroll')
+            for ep in episode_paths
+        ]
+        entries.reverse()
+
+        return {
+            '_type': 'playlist',
+            'id': show_id,
+            'title': title,
+            'entries': entries,
+        }

youtube_dl/extractor/d8.py

@@ -1,25 +0,0 @@
-# encoding: utf-8
-from __future__ import unicode_literals
-
-from .canalplus import CanalplusIE
-
-
-class D8IE(CanalplusIE):
-    _VALID_URL = r'https?://www\.d8\.tv/.*?/(?P<path>.*)'
-    _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/d8/%s'
-    IE_NAME = 'd8.tv'
-
-    _TEST = {
-        'url': 'http://www.d8.tv/d8-docs-mags/pid6589-d8-campagne-intime.html',
-        'file': '966289.flv',
-        'info_dict': {
-            'title': 'Campagne intime - Documentaire exceptionnel',
-            'description': 'md5:d2643b799fb190846ae09c61e59a859f',
-            'upload_date': '20131108',
-        },
-        'params': {
-            # rtmp
-            'skip_download': True,
-        },
-        'skip': 'videos get deleted after a while',
-    }

youtube_dl/extractor/dailymotion.py

@@ -94,7 +94,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
 
         # It may just embed a vevo video:
         m_vevo = re.search(
-            r'<link rel="video_src" href="[^"]*?vevo.com[^"]*?videoId=(?P<id>[\w]*)',
+            r'<link rel="video_src" href="[^"]*?vevo.com[^"]*?video=(?P<id>[\w]*)',
             webpage)
         if m_vevo is not None:
             vevo_id = m_vevo.group('id')

youtube_dl/extractor/dropbox.py

@@ -5,7 +5,8 @@ import os.path
 import re
 
 from .common import InfoExtractor
-from ..utils import compat_urllib_parse_unquote, url_basename
+from ..compat import compat_urllib_parse_unquote
+from ..utils import url_basename
 
 
 class DropboxIE(InfoExtractor):

youtube_dl/extractor/drtv.py

@@ -1,7 +1,5 @@
 from __future__ import unicode_literals
 
-import re
-
 from .subtitles import SubtitlesInfoExtractor
 from .common import ExtractorError
 from ..utils import parse_iso8601
@@ -25,8 +23,7 @@ class DRTVIE(SubtitlesInfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
 
         programcard = self._download_json(
             'http://www.dr.dk/mu/programcard/expanded/%s' % video_id, video_id, 'Downloading video JSON')
@@ -35,7 +32,7 @@ class DRTVIE(SubtitlesInfoExtractor):
 
         title = data['Title']
         description = data['Description']
-        timestamp = parse_iso8601(data['CreatedTime'][:-5])
+        timestamp = parse_iso8601(data['CreatedTime'])
 
         thumbnail = None
         duration = None

youtube_dl/extractor/facebook.py

@@ -5,12 +5,14 @@ import re
 import socket
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_http_client,
     compat_str,
     compat_urllib_error,
     compat_urllib_parse,
     compat_urllib_request,
+)
+from ..utils import (
     urlencode_postdata,
     ExtractorError,
     limit_length,

youtube_dl/extractor/faz.py

@@ -1,49 +1,48 @@
 # encoding: utf-8
-import re
+from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import (
-    determine_ext,
-)
 
 
 class FazIE(InfoExtractor):
-    IE_NAME = u'faz.net'
+    IE_NAME = 'faz.net'
     _VALID_URL = r'https?://www\.faz\.net/multimedia/videos/.*?-(?P<id>\d+)\.html'
 
     _TEST = {
-        u'url': u'http://www.faz.net/multimedia/videos/stockholm-chemie-nobelpreis-fuer-drei-amerikanische-forscher-12610585.html',
-        u'file': u'12610585.mp4',
-        u'info_dict': {
-            u'title': u'Stockholm: Chemie-Nobelpreis für drei amerikanische Forscher',
-            u'description': u'md5:1453fbf9a0d041d985a47306192ea253',
+        'url': 'http://www.faz.net/multimedia/videos/stockholm-chemie-nobelpreis-fuer-drei-amerikanische-forscher-12610585.html',
+        'info_dict': {
+            'id': '12610585',
+            'ext': 'mp4',
+            'title': 'Stockholm: Chemie-Nobelpreis für drei amerikanische Forscher',
+            'description': 'md5:1453fbf9a0d041d985a47306192ea253',
         },
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        self.to_screen(video_id)
+        video_id = self._match_id(url)
+
         webpage = self._download_webpage(url, video_id)
-        config_xml_url = self._search_regex(r'writeFLV\(\'(.+?)\',', webpage,
-            u'config xml url')
-        config = self._download_xml(config_xml_url, video_id,
-            u'Downloading config xml')
+        config_xml_url = self._search_regex(
+            r'writeFLV\(\'(.+?)\',', webpage, 'config xml url')
+        config = self._download_xml(
+            config_xml_url, video_id, 'Downloading config xml')
 
         encodings = config.find('ENCODINGS')
         formats = []
-        for code in ['LOW', 'HIGH', 'HQ']:
+        for pref, code in enumerate(['LOW', 'HIGH', 'HQ']):
             encoding = encodings.find(code)
             if encoding is None:
                 continue
             encoding_url = encoding.find('FILENAME').text
             formats.append({
                 'url': encoding_url,
-                'ext': determine_ext(encoding_url),
                 'format_id': code.lower(),
+                'quality': pref,
             })
+        self._sort_formats(formats)
 
-        descr = self._html_search_regex(r'<p class="Content Copy">(.*?)</p>', webpage, u'description')
+        descr = self._html_search_regex(
+            r'<p class="Content Copy">(.*?)</p>', webpage, 'description', fatal=False)
         return {
             'id': video_id,
             'title': self._og_search_title(webpage),

youtube_dl/extractor/fktv.py

@@ -1,25 +1,27 @@
+from __future__ import unicode_literals
+
 import re
 import random
 import json
 
 from .common import InfoExtractor
 from ..utils import (
-    determine_ext,
     get_element_by_id,
     clean_html,
 )
 
 
 class FKTVIE(InfoExtractor):
-    IE_NAME = u'fernsehkritik.tv'
-    _VALID_URL = r'(?:http://)?(?:www\.)?fernsehkritik\.tv/folge-(?P<ep>[0-9]+)(?:/.*)?'
+    IE_NAME = 'fernsehkritik.tv'
+    _VALID_URL = r'http://(?:www\.)?fernsehkritik\.tv/folge-(?P<ep>[0-9]+)(?:/.*)?'
 
     _TEST = {
-        u'url': u'http://fernsehkritik.tv/folge-1',
-        u'file': u'00011.flv',
-        u'info_dict': {
-            u'title': u'Folge 1 vom 10. April 2007',
-            u'description': u'md5:fb4818139c7cfe6907d4b83412a6864f',
+        'url': 'http://fernsehkritik.tv/folge-1',
+        'info_dict': {
+            'id': '00011',
+            'ext': 'flv',
+            'title': 'Folge 1 vom 10. April 2007',
+            'description': 'md5:fb4818139c7cfe6907d4b83412a6864f',
         },
     }
 
@@ -32,7 +34,7 @@ class FKTVIE(InfoExtractor):
         start_webpage = self._download_webpage('http://fernsehkritik.tv/folge-%d/Start' % episode,
             episode)
         playlist = self._search_regex(r'playlist = (\[.*?\]);', start_webpage,
-            u'playlist', flags=re.DOTALL)
+            'playlist', flags=re.DOTALL)
         files = json.loads(re.sub('{[^{}]*?}', '{}', playlist))
         # TODO: return a single multipart video
         videos = []
@@ -42,7 +44,6 @@ class FKTVIE(InfoExtractor):
             videos.append({
                 'id': video_id,
                 'url': video_url,
-                'ext': determine_ext(video_url),
                 'title': clean_html(get_element_by_id('eptitle', start_webpage)),
                 'description': clean_html(get_element_by_id('contentlist', start_webpage)),
                 'thumbnail': video_thumbnail
@@ -51,14 +52,15 @@ class FKTVIE(InfoExtractor):
 
 
 class FKTVPosteckeIE(InfoExtractor):
-    IE_NAME = u'fernsehkritik.tv:postecke'
-    _VALID_URL = r'(?:http://)?(?:www\.)?fernsehkritik\.tv/inline-video/postecke\.php\?(.*&)?ep=(?P<ep>[0-9]+)(&|$)'
+    IE_NAME = 'fernsehkritik.tv:postecke'
+    _VALID_URL = r'http://(?:www\.)?fernsehkritik\.tv/inline-video/postecke\.php\?(.*&)?ep=(?P<ep>[0-9]+)(&|$)'
     _TEST = {
-        u'url': u'http://fernsehkritik.tv/inline-video/postecke.php?iframe=true&width=625&height=440&ep=120',
-        u'file': u'0120.flv',
-        u'md5': u'262f0adbac80317412f7e57b4808e5c4',
-        u'info_dict': {
-            u"title": u"Postecke 120"
+        'url': 'http://fernsehkritik.tv/inline-video/postecke.php?iframe=true&width=625&height=440&ep=120',
+        'md5': '262f0adbac80317412f7e57b4808e5c4',
+        'info_dict': {
+            'id': '0120',
+            'ext': 'flv',
+            'title': 'Postecke 120',
         }
     }
 
@@ -71,8 +73,7 @@ class FKTVPosteckeIE(InfoExtractor):
         video_url = 'http://dl%d.fernsehkritik.tv/postecke/postecke%d.flv' % (server, episode)
         video_title = 'Postecke %d' % episode
         return {
-            'id':       video_id,
-            'url':      video_url,
-            'ext':      determine_ext(video_url),
-            'title':    video_title,
+            'id': video_id,
+            'url': video_url,
+            'title': video_title,
         }

youtube_dl/extractor/francetv.py

@@ -46,7 +46,7 @@ class FranceTVBaseInfoExtractor(InfoExtractor):
                         f4m_format['preference'] = 1
                     formats.extend(f4m_formats)
             elif video_url.endswith('.m3u8'):
-                formats.extend(self._extract_m3u8_formats(video_url, video_id))
+                formats.extend(self._extract_m3u8_formats(video_url, video_id, 'mp4'))
             elif video_url.startswith('rtmp'):
                 formats.append({
                     'url': video_url,
@@ -58,7 +58,7 @@ class FranceTVBaseInfoExtractor(InfoExtractor):
                 formats.append({
                     'url': video_url,
                     'format_id': format_id,
-                    'preference': 2,
+                    'preference': -1,
                 })
         self._sort_formats(formats)
 
@@ -93,7 +93,6 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor):
 
     _TESTS = [{
         'url': 'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html',
-        'md5': '9cecf35f99c4079c199e9817882a9a1c',
         'info_dict': {
             'id': '84981923',
             'ext': 'flv',

youtube_dl/extractor/freevideo.py

@@ -0,0 +1,38 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+
+class FreeVideoIE(InfoExtractor):
+    _VALID_URL = r'^http://www.freevideo.cz/vase-videa/(?P<id>[^.]+)\.html(?:$|[?#])'
+
+    _TEST = {
+        'url': 'http://www.freevideo.cz/vase-videa/vysukany-zadecek-22033.html',
+        'info_dict': {
+            'id': 'vysukany-zadecek-22033',
+            'ext': 'mp4',
+            "title": "vysukany-zadecek-22033",
+            "age_limit": 18,
+        },
+        'skip': 'Blocked outside .cz',
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage, handle = self._download_webpage_handle(url, video_id)
+        if '//www.czechav.com/' in handle.geturl():
+            raise ExtractorError(
+                'Access to freevideo is blocked from your location',
+                expected=True)
+
+        video_url = self._search_regex(
+            r'\s+url: "(http://[a-z0-9-]+.cdn.freevideo.cz/stream/.*?/video.mp4)"',
+            webpage, 'video URL')
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': video_id,
+            'age_limit': 18,
+        }

youtube_dl/extractor/funnyordie.py

@@ -8,7 +8,7 @@ from ..utils import ExtractorError
 
 
 class FunnyOrDieIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?funnyordie\.com/(?P<type>embed|videos)/(?P<id>[0-9a-f]+)(?:$|[?#/])'
+    _VALID_URL = r'https?://(?:www\.)?funnyordie\.com/(?P<type>embed|articles|videos)/(?P<id>[0-9a-f]+)(?:$|[?#/])'
     _TESTS = [{
         'url': 'http://www.funnyordie.com/videos/0732f586d7/heart-shaped-box-literal-video-version',
         'md5': 'bcd81e0c4f26189ee09be362ad6e6ba9',
@@ -21,7 +21,6 @@ class FunnyOrDieIE(InfoExtractor):
         },
     }, {
         'url': 'http://www.funnyordie.com/embed/e402820827',
-        'md5': '29f4c5e5a61ca39dfd7e8348a75d0aad',
         'info_dict': {
             'id': 'e402820827',
             'ext': 'mp4',
@@ -29,6 +28,9 @@ class FunnyOrDieIE(InfoExtractor):
             'description': 'Please use this to sell something.  www.jonlajoie.com',
             'thumbnail': 're:^http:.*\.jpg$',
         },
+    }, {
+        'url': 'http://www.funnyordie.com/articles/ebf5e34fc8/10-hours-of-walking-in-nyc-as-a-man',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -37,7 +39,7 @@ class FunnyOrDieIE(InfoExtractor):
         video_id = mobj.group('id')
         webpage = self._download_webpage(url, video_id)
 
-        links = re.findall(r'<source src="([^"]+/v)\d+\.([^"]+)" type=\'video', webpage)
+        links = re.findall(r'<source src="([^"]+/v)[^"]+\.([^"]+)" type=\'video', webpage)
         if not links:
             raise ExtractorError('No media links available for %s' % video_id)
 

youtube_dl/extractor/gamespot.py

@@ -8,12 +8,11 @@ from ..utils import (
     compat_urllib_parse,
     compat_urlparse,
     unescapeHTML,
-    get_meta_content,
 )
 
 
 class GameSpotIE(InfoExtractor):
-    _VALID_URL = r'(?:http://)?(?:www\.)?gamespot\.com/.*-(?P<page_id>\d+)/?'
+    _VALID_URL = r'(?:http://)?(?:www\.)?gamespot\.com/.*-(?P<id>\d+)/?'
     _TEST = {
         'url': 'http://www.gamespot.com/videos/arma-3-community-guide-sitrep-i/2300-6410818/',
         'md5': 'b2a30deaa8654fcccd43713a6b6a4825',
@@ -26,10 +25,10 @@ class GameSpotIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        page_id = mobj.group('page_id')
+        page_id = self._match_id(url)
         webpage = self._download_webpage(url, page_id)
-        data_video_json = self._search_regex(r'data-video=["\'](.*?)["\']', webpage, 'data video')
+        data_video_json = self._search_regex(
+            r'data-video=["\'](.*?)["\']', webpage, 'data video')
         data_video = json.loads(unescapeHTML(data_video_json))
 
         # Transform the manifest url to a link to the mp4 files
@@ -41,7 +40,8 @@ class GameSpotIE(InfoExtractor):
         http_path = f4m_path[1:].split('/', 1)[1]
         http_template = re.sub(QUALITIES_RE, r'%s', http_path)
         http_template = http_template.replace('.csmil/manifest.f4m', '')
-        http_template = compat_urlparse.urljoin('http://video.gamespotcdn.com/', http_template)
+        http_template = compat_urlparse.urljoin(
+            'http://video.gamespotcdn.com/', http_template)
         formats = []
         for q in qualities:
             formats.append({
@@ -52,8 +52,9 @@ class GameSpotIE(InfoExtractor):
 
         return {
             'id': data_video['guid'],
+            'display_id': page_id,
             'title': compat_urllib_parse.unquote(data_video['title']),
             'formats': formats,
-            'description': get_meta_content('description', webpage),
+            'description': self._html_search_meta('description', webpage),
             'thumbnail': self._og_search_thumbnail(webpage),
         }

youtube_dl/extractor/generic.py

@@ -7,11 +7,12 @@ import re
 
 from .common import InfoExtractor
 from .youtube import YoutubeIE
-from ..utils import (
+from ..compat import (
     compat_urllib_parse,
     compat_urlparse,
     compat_xml_parse_error,
-
+)
+from ..utils import (
     determine_ext,
     ExtractorError,
     float_or_none,
@@ -28,6 +29,7 @@ from .brightcove import BrightcoveIE
 from .ooyala import OoyalaIE
 from .rutv import RUTVIE
 from .smotri import SmotriIE
+from .condenast import CondeNastIE
 
 
 class GenericIE(InfoExtractor):
@@ -98,6 +100,22 @@ class GenericIE(InfoExtractor):
                 'uploader': 'Championat',
             },
         },
+        {
+            # https://github.com/rg3/youtube-dl/issues/3541
+            'add_ie': ['Brightcove'],
+            'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
+            'info_dict': {
+                'id': '3866516442001',
+                'ext': 'mp4',
+                'title': 'Leer mij vrouwen kennen: Aflevering 1',
+                'description': 'Leer mij vrouwen kennen: Aflevering 1',
+                'uploader': 'SBS Broadcasting',
+            },
+            'skip': 'Restricted to Netherlands',
+            'params': {
+                'skip_download': True,  # m3u8 download
+            },
+        },
         # Direct link to a video
         {
             'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
@@ -324,7 +342,7 @@ class GenericIE(InfoExtractor):
                 'ext': 'mp4',
                 'age_limit': 18,
                 'uploader': 'www.handjobhub.com',
-                'title': 'Busty Blonde Siri Tit Fuck While Wank at Handjob Hub',
+                'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
             }
         },
         # RSS feed
@@ -379,6 +397,54 @@ class GenericIE(InfoExtractor):
                 'uploader': 'education-portal.com',
             },
         },
+        {
+            'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
+            'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
+            'info_dict': {
+                'id': 'uxjb0lwrcz',
+                'ext': 'mp4',
+                'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
+                'duration': 1715.0,
+                'uploader': 'thoughtworks.wistia.com',
+            },
+        },
+        # Direct download with broken HEAD
+        {
+            'url': 'http://ai-radio.org:8000/radio.opus',
+            'info_dict': {
+                'id': 'radio',
+                'ext': 'opus',
+                'title': 'radio',
+            },
+            'params': {
+                'skip_download': True,  # infinite live stream
+            },
+            'expected_warnings': [
+                r'501.*Not Implemented'
+            ],
+        },
+        # Soundcloud embed
+        {
+            'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
+            'info_dict': {
+                'id': '174391317',
+                'ext': 'mp3',
+                'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
+                'uploader': 'Sophos Security',
+                'title': 'Chet Chat 171 - Oct 29, 2014',
+                'upload_date': '20141029',
+            }
+        },
+        # Livestream embed
+        {
+            'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
+            'info_dict': {
+                'id': '67864563',
+                'ext': 'flv',
+                'upload_date': '20141112',
+                'title': 'Rosetta #CometLanding webcast HL 10',
+            }
+        },
     ]
 
     def report_following_redirect(self, new_url):
@@ -475,7 +541,8 @@ class GenericIE(InfoExtractor):
                      'Set --default-search "ytsearch" (or run  youtube-dl "ytsearch:%s" ) to search YouTube'
                     ) % (url, url), expected=True)
             else:
-                assert ':' in default_search
+                if ':' not in default_search:
+                    default_search += ':'
                 return self.url_result(default_search + url)
 
         url, smuggled_data = unsmuggle_url(url)
@@ -490,14 +557,14 @@ class GenericIE(InfoExtractor):
         self.to_screen('%s: Requesting header' % video_id)
 
         head_req = HEADRequest(url)
-        response = self._request_webpage(
+        head_response = self._request_webpage(
             head_req, video_id,
             note=False, errnote='Could not send HEAD request to %s' % url,
             fatal=False)
 
-        if response is not False:
+        if head_response is not False:
             # Check for redirect
-            new_url = response.geturl()
+            new_url = head_response.geturl()
             if url != new_url:
                 self.report_following_redirect(new_url)
                 if force_videoid:
@@ -505,34 +572,36 @@ class GenericIE(InfoExtractor):
                         new_url, {'force_videoid': force_videoid})
                 return self.url_result(new_url)
 
-            # Check for direct link to a video
-            content_type = response.headers.get('Content-Type', '')
-            m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type)
-            if m:
-                upload_date = response.headers.get('Last-Modified')
-                if upload_date:
-                    upload_date = unified_strdate(upload_date)
-                return {
-                    'id': video_id,
-                    'title': os.path.splitext(url_basename(url))[0],
-                    'formats': [{
-                        'format_id': m.group('format_id'),
-                        'url': url,
-                        'vcodec': 'none' if m.group('type') == 'audio' else None
-                    }],
-                    'upload_date': upload_date,
-                }
+        full_response = None
+        if head_response is False:
+            full_response = self._request_webpage(url, video_id)
+            head_response = full_response
+
+        # Check for direct link to a video
+        content_type = head_response.headers.get('Content-Type', '')
+        m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type)
+        if m:
+            upload_date = unified_strdate(
+                head_response.headers.get('Last-Modified'))
+            return {
+                'id': video_id,
+                'title': os.path.splitext(url_basename(url))[0],
+                'direct': True,
+                'formats': [{
+                    'format_id': m.group('format_id'),
+                    'url': url,
+                    'vcodec': 'none' if m.group('type') == 'audio' else None
+                }],
+                'upload_date': upload_date,
+            }
 
         if not self._downloader.params.get('test', False) and not is_intentional:
             self._downloader.report_warning('Falling back on generic information extractor.')
 
-        try:
+        if full_response:
+            webpage = self._webpage_read_content(full_response, url, video_id)
+        else:
             webpage = self._download_webpage(url, video_id)
-        except ValueError:
-            # since this is the last-resort InfoExtractor, if
-            # this error is thrown, it'll be thrown here
-            raise ExtractorError('Failed to download URL: %s' % url)
-
         self.report_extraction(video_id)
 
         # Is it an RSS feed?
@@ -608,13 +677,13 @@ class GenericIE(InfoExtractor):
         if mobj:
             player_url = unescapeHTML(mobj.group('url'))
             surl = smuggle_url(player_url, {'Referer': url})
-            return self.url_result(surl, 'Vimeo')
+            return self.url_result(surl)
 
         # Look for embedded (swf embed) Vimeo player
         mobj = re.search(
-            r'<embed[^>]+?src="(https?://(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage)
+            r'<embed[^>]+?src="((?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage)
         if mobj:
-            return self.url_result(mobj.group(1), 'Vimeo')
+            return self.url_result(mobj.group(1))
 
         # Look for embedded YouTube player
         matches = re.findall(r'''(?x)
@@ -622,7 +691,8 @@ class GenericIE(InfoExtractor):
                 <iframe[^>]+?src=|
                 data-video-url=|
                 <embed[^>]+?src=|
-                embedSWF\(?:\s*
+                embedSWF\(?:\s*|
+                new\s+SWFObject\(
             )
             (["\'])
                 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
@@ -651,17 +721,20 @@ class GenericIE(InfoExtractor):
 
         # Look for embedded Wistia player
         match = re.search(
-            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
+            r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
         if match:
+            embed_url = self._proto_relative_url(
+                unescapeHTML(match.group('url')))
             return {
                 '_type': 'url_transparent',
-                'url': unescapeHTML(match.group('url')),
+                'url': embed_url,
                 'ie_key': 'Wistia',
                 'uploader': video_uploader,
                 'title': video_title,
                 'id': video_id,
             }
-        match = re.search(r'(?:id=["\']wistia_|data-wistiaid=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
+            
+        match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
         if match:
             return {
                 '_type': 'url_transparent',
@@ -805,7 +878,7 @@ class GenericIE(InfoExtractor):
 
         # Look for embeded soundcloud player
         mobj = re.search(
-            r'<iframe src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
+            r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
             webpage)
         if mobj is not None:
             url = unescapeHTML(mobj.group('url'))
@@ -842,11 +915,23 @@ class GenericIE(InfoExtractor):
             return self.url_result(mobj.group('url'), 'SBS')
 
         mobj = re.search(
-            r'<iframe[^>]+?src=(["\'])(?P<url>https?://m\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
+            r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
             webpage)
         if mobj is not None:
             return self.url_result(mobj.group('url'), 'MLB')
 
+        mobj = re.search(
+            r'<iframe[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
+            webpage)
+        if mobj is not None:
+            return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
+
+        mobj = re.search(
+            r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
+            webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'), 'Livestream')
+
         def check_video(vurl):
             vpath = compat_urlparse.urlparse(vurl).path
             vext = determine_ext(vpath)
@@ -894,7 +979,7 @@ class GenericIE(InfoExtractor):
                 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
         if not found:
             # HTML5 video
-            found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]+)? src="([^"]+)"', webpage)
+            found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]*)?\s+src="([^"]+)"', webpage)
         if not found:
             found = re.search(
                 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'

youtube_dl/extractor/glide.py

@@ -0,0 +1,40 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class GlideIE(InfoExtractor):
+    IE_DESC = 'Glide mobile video messages (glide.me)'
+    _VALID_URL = r'https?://share\.glide\.me/(?P<id>[A-Za-z0-9\-=_+]+)'
+    _TEST = {
+        'url': 'http://share.glide.me/UZF8zlmuQbe4mr+7dCiQ0w==',
+        'md5': '4466372687352851af2d131cfaa8a4c7',
+        'info_dict': {
+            'id': 'UZF8zlmuQbe4mr+7dCiQ0w==',
+            'ext': 'mp4',
+            'title': 'Damon Timm\'s Glide message',
+            'thumbnail': 're:^https?://.*?\.cloudfront\.net/.*\.jpg$',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        title = self._html_search_regex(
+            r'<title>(.*?)</title>', webpage, 'title')
+        video_url = self.http_scheme() + self._search_regex(
+            r'<source src="(.*?)" type="video/mp4">', webpage, 'video URL')
+        thumbnail_url = self._search_regex(
+            r'<img id="video-thumbnail" src="(.*?)"',
+            webpage, 'thumbnail url', fatal=False)
+        thumbnail = (
+            thumbnail_url if thumbnail_url is None
+            else self.http_scheme() + thumbnail_url)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'url': video_url,
+            'thumbnail': thumbnail,
+        }

youtube_dl/extractor/globo.py

@@ -5,13 +5,15 @@ import random
 import math
 
 from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-    float_or_none,
+from ..compat import (
     compat_str,
     compat_chr,
     compat_ord,
 )
+from ..utils import (
+    ExtractorError,
+    float_or_none,
+)
 
 
 class GloboIE(InfoExtractor):

youtube_dl/extractor/goldenmoustache.py

@@ -0,0 +1,48 @@
+from __future__ import unicode_literals
+
+import re
+from .common import InfoExtractor
+from ..utils import (
+    parse_duration,
+    int_or_none,
+)
+
+
+class GoldenMoustacheIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?goldenmoustache\.com/(?P<display_id>[\w-]+)-(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://www.goldenmoustache.com/suricate-le-poker-3700/',
+        'md5': '0f904432fa07da5054d6c8beb5efb51a',
+        'info_dict': {
+            'id': '3700',
+            'ext': 'mp4',
+            'title': 'Suricate - Le Poker',
+            'description': 'md5:3d1f242f44f8c8cb0a106f1fd08e5dc9',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'view_count': int,
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        video_url = self._html_search_regex(
+            r'data-src-type="mp4" data-src="([^"]+)"', webpage, 'video URL')
+        title = self._html_search_regex(
+            r'<title>(.*?) - Golden Moustache</title>', webpage, 'title')
+        thumbnail = self._og_search_thumbnail(webpage)
+        description = self._og_search_description(webpage)
+        view_count = int_or_none(self._html_search_regex(
+            r'<strong>([0-9]+)</strong>\s*VUES</span>',
+            webpage, 'view count', fatal=False))
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'ext': 'mp4',
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'view_count': view_count,
+        }

youtube_dl/extractor/gorillavid.py

@@ -46,9 +46,9 @@ class GorillaVidIE(InfoExtractor):
         'info_dict': {
             'id': '3rso4kdn6f9m',
             'ext': 'mp4',
-            'title': 'Micro Pig piglets ready on 16th July 2009',
+            'title': 'Micro Pig piglets ready on 16th July 2009-bG0PdrCdxUc',
             'thumbnail': 're:http://.*\.jpg',
-        },
+        }
     }, {
         'url': 'http://movpod.in/0wguyyxi1yca',
         'only_matching': True,

youtube_dl/extractor/goshgay.py

@@ -1,15 +1,11 @@
 # -*- coding: utf-8 -*-
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 from ..utils import (
     compat_urlparse,
-    str_to_int,
     ExtractorError,
 )
-import json
 
 
 class GoshgayIE(InfoExtractor):
@@ -27,36 +23,27 @@ class GoshgayIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
-        title = self._search_regex(r'class="video-title"><h1>(.+?)<', webpage, 'title')
+        title = self._og_search_title(webpage)
+        thumbnail = self._og_search_thumbnail(webpage)
+        family_friendly = self._html_search_meta(
+            'isFamilyFriendly', webpage, default='false')
+        config_url = self._search_regex(
+            r"'config'\s*:\s*'([^']+)'", webpage, 'config URL')
 
-        player_config = self._search_regex(
-            r'(?s)jwplayer\("player"\)\.setup\(({.+?})\)', webpage, 'config settings')
-        player_vars = json.loads(player_config.replace("'", '"'))
-        width = str_to_int(player_vars.get('width'))
-        height = str_to_int(player_vars.get('height'))
-        config_uri = player_vars.get('config')
+        config = self._download_xml(
+            config_url, video_id, 'Downloading player config XML')
 
-        if config_uri is None:
-            raise ExtractorError('Missing config URI')
-        node = self._download_xml(config_uri, video_id, 'Downloading player config XML',
-                                  errnote='Unable to download XML')
-        if node is None:
+        if config is None:
             raise ExtractorError('Missing config XML')
-        if node.tag != 'config':
+        if config.tag != 'config':
             raise ExtractorError('Missing config attribute')
-        fns = node.findall('file')
-        imgs = node.findall('image')
-        if len(fns) != 1:
+        fns = config.findall('file')
+        if len(fns) < 1:
             raise ExtractorError('Missing media URI')
         video_url = fns[0].text
-        if len(imgs) < 1:
-            thumbnail = None
-        else:
-            thumbnail = imgs[0].text
 
         url_comp = compat_urlparse.urlparse(url)
         ref = "%s://%s%s" % (url_comp[0], url_comp[1], url_comp[2])
@@ -65,9 +52,7 @@ class GoshgayIE(InfoExtractor):
             'id': video_id,
             'url': video_url,
             'title': title,
-            'width': width,
-            'height': height,
             'thumbnail': thumbnail,
             'http_referer': ref,
-            'age_limit': 18,
+            'age_limit': 0 if family_friendly == 'true' else 18,
         }

youtube_dl/extractor/grooveshark.py

@@ -8,12 +8,13 @@ import re
 
 
 from .common import InfoExtractor
-from ..utils import ExtractorError, compat_urllib_request, compat_html_parser
-
-from ..utils import (
+from ..compat import (
+    compat_html_parser,
     compat_urllib_parse,
+    compat_urllib_request,
     compat_urlparse,
 )
+from ..utils import ExtractorError
 
 
 class GroovesharkHtmlParser(compat_html_parser.HTMLParser):

youtube_dl/extractor/hark.py

@@ -1,37 +1,33 @@
 # -*- coding: utf-8 -*-
-
-import re
-import json
+from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import determine_ext
+
 
 class HarkIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.hark\.com/clips/(.+?)-.+'
+    _VALID_URL = r'https?://www\.hark\.com/clips/(?P<id>.+?)-.+'
     _TEST = {
-        u'url': u'http://www.hark.com/clips/mmbzyhkgny-obama-beyond-the-afghan-theater-we-only-target-al-qaeda-on-may-23-2013',
-        u'file': u'mmbzyhkgny.mp3',
-        u'md5': u'6783a58491b47b92c7c1af5a77d4cbee',
-        u'info_dict': {
-            u'title': u"Obama: 'Beyond The Afghan Theater, We Only Target Al Qaeda' on May 23, 2013",
-            u'description': u'President Barack Obama addressed the nation live on May 23, 2013 in a speech aimed at addressing counter-terrorism policies including the use of drone strikes, detainees at Guantanamo Bay prison facility, and American citizens who are terrorists.',
-            u'duration': 11,
+        'url': 'http://www.hark.com/clips/mmbzyhkgny-obama-beyond-the-afghan-theater-we-only-target-al-qaeda-on-may-23-2013',
+        'md5': '6783a58491b47b92c7c1af5a77d4cbee',
+        'info_dict': {
+            'id': 'mmbzyhkgny',
+            'ext': 'mp3',
+            'title': 'Obama: \'Beyond The Afghan Theater, We Only Target Al Qaeda\' on May 23, 2013',
+            'description': 'President Barack Obama addressed the nation live on May 23, 2013 in a speech aimed at addressing counter-terrorism policies including the use of drone strikes, detainees at Guantanamo Bay prison facility, and American citizens who are terrorists.',
+            'duration': 11,
         }
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group(1)
-        json_url = "http://www.hark.com/clips/%s.json" %(video_id)
-        info_json = self._download_webpage(json_url, video_id)
-        info = json.loads(info_json)
-        final_url = info['url']
+        video_id = self._match_id(url)
+        data = self._download_json(
+            'http://www.hark.com/clips/%s.json' % video_id, video_id)
 
-        return {'id': video_id,
-                'url' : final_url,
-                'title': info['name'],
-                'ext': determine_ext(final_url),
-                'description': info['description'],
-                'thumbnail': info['image_original'],
-                'duration': info['duration'],
-                }
+        return {
+            'id': video_id,
+            'url': data['url'],
+            'title': data['name'],
+            'description': data.get('description'),
+            'thumbnail': data.get('image_original'),
+            'duration': data.get('duration'),
+        }

youtube_dl/extractor/heise.py

@@ -3,7 +3,8 @@ from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from ..utils import (
-    get_meta_content,
+    determine_ext,
+    int_or_none,
     parse_iso8601,
 )
 
@@ -24,57 +25,54 @@ class HeiseIE(InfoExtractor):
             'title': (
                 "Podcast: c't uplink 3.3 – Owncloud / Tastaturen / Peilsender Smartphone"
             ),
-            'format_id': 'mp4_720',
+            'format_id': 'mp4_720p',
             'timestamp': 1411812600,
             'upload_date': '20140927',
             'description': 'In uplink-Episode 3.3 geht es darum, wie man sich von Cloud-Anbietern emanzipieren kann, worauf man beim Kauf einer Tastatur achten sollte und was Smartphones über uns verraten.',
+            'thumbnail': 're:^https?://.*\.jpe?g$',
         }
     }
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-
         webpage = self._download_webpage(url, video_id)
-        json_url = self._search_regex(
-            r'json_url:\s*"([^"]+)"', webpage, 'json URL')
-        config = self._download_json(json_url, video_id)
+
+        container_id = self._search_regex(
+            r'<div class="videoplayerjw".*?data-container="([0-9]+)"',
+            webpage, 'container ID')
+        sequenz_id = self._search_regex(
+            r'<div class="videoplayerjw".*?data-sequenz="([0-9]+)"',
+            webpage, 'sequenz ID')
+        data_url = 'http://www.heise.de/videout/feed?container=%s&sequenz=%s' % (container_id, sequenz_id)
+        doc = self._download_xml(data_url, video_id)
 
         info = {
             'id': video_id,
-            'thumbnail': config.get('poster'),
-            'timestamp': parse_iso8601(get_meta_content('date', webpage)),
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'timestamp': parse_iso8601(
+                self._html_search_meta('date', webpage)),
             'description': self._og_search_description(webpage),
         }
 
-        title = get_meta_content('fulltitle', webpage)
+        title = self._html_search_meta('fulltitle', webpage)
         if title:
             info['title'] = title
-        elif config.get('title'):
-            info['title'] = config['title']
         else:
             info['title'] = self._og_search_title(webpage)
 
         formats = []
-        for t, rs in config['formats'].items():
-            if not rs or not hasattr(rs, 'items'):
-                self._downloader.report_warning(
-                    'formats: {0}: no resolutions'.format(t))
-                continue
-
-            for height_str, obj in rs.items():
-                format_id = '{0}_{1}'.format(t, height_str)
-
-                if not obj or not obj.get('url'):
-                    self._downloader.report_warning(
-                        'formats: {0}: no url'.format(format_id))
-                    continue
-
-                formats.append({
-                    'url': obj['url'],
-                    'format_id': format_id,
-                    'height': self._int(height_str, 'height'),
-                })
-
+        for source_node in doc.findall('.//{http://rss.jwpcdn.com/}source'):
+            label = source_node.attrib['label']
+            height = int_or_none(self._search_regex(
+                r'^(.*?_)?([0-9]+)p$', label, 'height', default=None))
+            video_url = source_node.attrib['file']
+            ext = determine_ext(video_url, '')
+            formats.append({
+                'url': video_url,
+                'format_note': label,
+                'format_id': '%s_%s' % (ext, label),
+                'height': height,
+            })
         self._sort_formats(formats)
         info['formats'] = formats
 

youtube_dl/extractor/iconosquare.py

@@ -1,7 +1,5 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 
 
@@ -20,13 +18,11 @@ class IconosquareIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
-        html_title = self._html_search_regex(
-            r'<title>(.+?)</title>',
+        title = self._html_search_regex(
+            r'<title>(.+?)(?: *\(Videos?\))? \| (?:Iconosquare|Statigram)</title>',
             webpage, 'title')
-        title = re.sub(r'(?: *\(Videos?\))? \| (?:Iconosquare|Statigram)$', '', html_title)
         uploader_id = self._html_search_regex(
             r'@([^ ]+)', title, 'uploader name', fatal=False)
 

youtube_dl/extractor/imdb.py

@@ -6,7 +6,6 @@ import json
 from .common import InfoExtractor
 from ..utils import (
     compat_urlparse,
-    get_element_by_attribute,
 )
 
 
@@ -27,10 +26,11 @@ class ImdbIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
         webpage = self._download_webpage('http://www.imdb.com/video/imdb/vi%s' % video_id, video_id)
-        descr = get_element_by_attribute('itemprop', 'description', webpage)
+        descr = self._html_search_regex(
+            r'(?s)<span itemprop="description">(.*?)</span>',
+            webpage, 'description', fatal=False)
         available_formats = re.findall(
             r'case \'(?P<f_id>.*?)\' :$\s+url = \'(?P<path>.*?)\'', webpage,
             flags=re.MULTILINE)
@@ -73,9 +73,7 @@ class ImdbListIE(InfoExtractor):
     }
     
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        list_id = mobj.group('id')
-
+        list_id = self._match_id(url)
         webpage = self._download_webpage(url, list_id)
         entries = [
             self.url_result('http://www.imdb.com' + m, 'Imdb')

youtube_dl/extractor/izlesene.py

@@ -5,11 +5,11 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
-    get_element_by_id,
-    parse_iso8601,
     determine_ext,
-    int_or_none,
     float_or_none,
+    get_element_by_id,
+    int_or_none,
+    parse_iso8601,
     str_to_int,
 )
 
@@ -30,7 +30,7 @@ class IzleseneIE(InfoExtractor):
                 'description': 'md5:253753e2655dde93f59f74b572454f6d',
                 'thumbnail': 're:^http://.*\.jpg',
                 'uploader_id': 'pelikzzle',
-                'timestamp': 1404298698,
+                'timestamp': 1404302298,
                 'upload_date': '20140702',
                 'duration': 95.395,
                 'age_limit': 0,
@@ -46,7 +46,7 @@ class IzleseneIE(InfoExtractor):
                 'description': 'Tarkan Dortmund 2006 Konseri',
                 'thumbnail': 're:^http://.*\.jpg',
                 'uploader_id': 'parlayankiz',
-                'timestamp': 1163318593,
+                'timestamp': 1163322193,
                 'upload_date': '20061112',
                 'duration': 253.666,
                 'age_limit': 0,
@@ -55,10 +55,9 @@ class IzleseneIE(InfoExtractor):
     ]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        url = 'http://www.izlesene.com/video/%s' % video_id
+        video_id = self._match_id(url)
 
+        url = 'http://www.izlesene.com/video/%s' % video_id
         webpage = self._download_webpage(url, video_id)
 
         title = self._og_search_title(webpage)

youtube_dl/extractor/justintv.py

@@ -1,155 +0,0 @@
-from __future__ import unicode_literals
-
-import itertools
-import json
-import os
-import re
-
-from .common import InfoExtractor
-from ..utils import (
-    compat_str,
-    ExtractorError,
-    formatSeconds,
-)
-
-
-class JustinTVIE(InfoExtractor):
-    """Information extractor for justin.tv and twitch.tv"""
-    # TODO: One broadcast may be split into multiple videos. The key
-    # 'broadcast_id' is the same for all parts, and 'broadcast_part'
-    # starts at 1 and increases. Can we treat all parts as one video?
-
-    _VALID_URL = r"""(?x)^(?:http://)?(?:www\.)?(?:twitch|justin)\.tv/
-        (?:
-            (?P<channelid>[^/]+)|
-            (?:(?:[^/]+)/b/(?P<videoid>[^/]+))|
-            (?:(?:[^/]+)/c/(?P<chapterid>[^/]+))
-        )
-        /?(?:\#.*)?$
-        """
-    _JUSTIN_PAGE_LIMIT = 100
-    IE_NAME = 'justin.tv'
-    IE_DESC = 'justin.tv and twitch.tv'
-    _TEST = {
-        'url': 'http://www.twitch.tv/thegamedevhub/b/296128360',
-        'md5': 'ecaa8a790c22a40770901460af191c9a',
-        'info_dict': {
-            'id': '296128360',
-            'ext': 'flv',
-            'upload_date': '20110927',
-            'uploader_id': 25114803,
-            'uploader': 'thegamedevhub',
-            'title': 'Beginner Series - Scripting With Python Pt.1'
-        }
-    }
-
-    # Return count of items, list of *valid* items
-    def _parse_page(self, url, video_id, counter):
-        info_json = self._download_webpage(
-            url, video_id,
-            'Downloading video info JSON on page %d' % counter,
-            'Unable to download video info JSON %d' % counter)
-
-        response = json.loads(info_json)
-        if type(response) != list:
-            error_text = response.get('error', 'unknown error')
-            raise ExtractorError('Justin.tv API: %s' % error_text)
-        info = []
-        for clip in response:
-            video_url = clip['video_file_url']
-            if video_url:
-                video_extension = os.path.splitext(video_url)[1][1:]
-                video_date = re.sub('-', '', clip['start_time'][:10])
-                video_uploader_id = clip.get('user_id', clip.get('channel_id'))
-                video_id = clip['id']
-                video_title = clip.get('title', video_id)
-                info.append({
-                    'id': compat_str(video_id),
-                    'url': video_url,
-                    'title': video_title,
-                    'uploader': clip.get('channel_name', video_uploader_id),
-                    'uploader_id': video_uploader_id,
-                    'upload_date': video_date,
-                    'ext': video_extension,
-                })
-        return (len(response), info)
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-
-        api_base = 'http://api.justin.tv'
-        paged = False
-        if mobj.group('channelid'):
-            paged = True
-            video_id = mobj.group('channelid')
-            api = api_base + '/channel/archives/%s.json' % video_id
-        elif mobj.group('chapterid'):
-            chapter_id = mobj.group('chapterid')
-
-            webpage = self._download_webpage(url, chapter_id)
-            m = re.search(r'PP\.archive_id = "([0-9]+)";', webpage)
-            if not m:
-                raise ExtractorError('Cannot find archive of a chapter')
-            archive_id = m.group(1)
-
-            api = api_base + '/broadcast/by_chapter/%s.xml' % chapter_id
-            doc = self._download_xml(
-                api, chapter_id,
-                note='Downloading chapter information',
-                errnote='Chapter information download failed')
-            for a in doc.findall('.//archive'):
-                if archive_id == a.find('./id').text:
-                    break
-            else:
-                raise ExtractorError('Could not find chapter in chapter information')
-
-            video_url = a.find('./video_file_url').text
-            video_ext = video_url.rpartition('.')[2] or 'flv'
-
-            chapter_api_url = 'https://api.twitch.tv/kraken/videos/c' + chapter_id
-            chapter_info = self._download_json(
-                chapter_api_url, 'c' + chapter_id,
-                note='Downloading chapter metadata',
-                errnote='Download of chapter metadata failed')
-
-            bracket_start = int(doc.find('.//bracket_start').text)
-            bracket_end = int(doc.find('.//bracket_end').text)
-
-            # TODO determine start (and probably fix up file)
-            #  youtube-dl -v http://www.twitch.tv/firmbelief/c/1757457
-            #video_url += '?start=' + TODO:start_timestamp
-            # bracket_start is 13290, but we want 51670615
-            self._downloader.report_warning('Chapter detected, but we can just download the whole file. '
-                                            'Chapter starts at %s and ends at %s' % (formatSeconds(bracket_start), formatSeconds(bracket_end)))
-
-            info = {
-                'id': 'c' + chapter_id,
-                'url': video_url,
-                'ext': video_ext,
-                'title': chapter_info['title'],
-                'thumbnail': chapter_info['preview'],
-                'description': chapter_info['description'],
-                'uploader': chapter_info['channel']['display_name'],
-                'uploader_id': chapter_info['channel']['name'],
-            }
-            return info
-        else:
-            video_id = mobj.group('videoid')
-            api = api_base + '/broadcast/by_archive/%s.json' % video_id
-
-        entries = []
-        offset = 0
-        limit = self._JUSTIN_PAGE_LIMIT
-        for counter in itertools.count(1):
-            page_url = api + ('?offset=%d&limit=%d' % (offset, limit))
-            page_count, page_info = self._parse_page(
-                page_url, video_id, counter)
-            entries.extend(page_info)
-            if not paged or page_count != limit:
-                break
-            offset += limit
-        return {
-            '_type': 'playlist',
-            'id': video_id,
-            'entries': entries,
-        }

youtube_dl/extractor/kickstarter.py

@@ -1,8 +1,6 @@
 # encoding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 
 
@@ -21,22 +19,17 @@ class KickStarterIE(InfoExtractor):
     }, {
         'note': 'Embedded video (not using the native kickstarter video service)',
         'url': 'https://www.kickstarter.com/projects/597507018/pebble-e-paper-watch-for-iphone-and-android/posts/659178',
-        'playlist': [
-            {
-                'info_dict': {
-                    'id': '78704821',
-                    'ext': 'mp4',
-                    'uploader_id': 'pebble',
-                    'uploader': 'Pebble Technology',
-                    'title': 'Pebble iOS Notifications',
-                }
-            }
-        ],
+        'info_dict': {
+            'id': '78704821',
+            'ext': 'mp4',
+            'uploader_id': 'pebble',
+            'uploader': 'Pebble Technology',
+            'title': 'Pebble iOS Notifications',
+        }
     }]
 
     def _real_extract(self, url):
-        m = re.match(self._VALID_URL, url)
-        video_id = m.group('id')
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
         title = self._html_search_regex(

youtube_dl/extractor/ku6.py

@@ -1,7 +1,5 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 
 
@@ -18,11 +16,11 @@ class Ku6IE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
-        title = self._search_regex(r'<h1 title=.*>(.*?)</h1>', webpage, 'title')
+
+        title = self._html_search_regex(
+            r'<h1 title=.*>(.*?)</h1>', webpage, 'title')
         dataUrl = 'http://v.ku6.com/fetchVideo4Player/%s.html' % video_id
         jsonData = self._download_json(dataUrl, video_id)
         downloadUrl = jsonData['data']['f']

youtube_dl/extractor/laola1tv.py

@@ -0,0 +1,78 @@
+from __future__ import unicode_literals
+
+import random
+import re
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+
+class Laola1TvIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?laola1\.tv/(?P<lang>[a-z]+)-(?P<portal>[a-z]+)/.*?/(?P<id>[0-9]+)\.html'
+    _TEST = {
+        'url': 'http://www.laola1.tv/de-de/live/bwf-bitburger-open-grand-prix-gold-court-1/250019.html',
+        'info_dict': {
+            'id': '250019',
+            'ext': 'mp4',
+            'title': 'Bitburger Open Grand Prix Gold - Court 1',
+            'categories': ['Badminton'],
+            'uploader': 'BWF - Badminton World Federation',
+            'is_live': True,
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }
+
+    _BROKEN = True  # Not really - extractor works fine, but f4m downloader does not support live streams yet.
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        lang = mobj.group('lang')
+        portal = mobj.group('portal')
+
+        webpage = self._download_webpage(url, video_id)
+        iframe_url = self._search_regex(
+            r'<iframe[^>]*?class="main_tv_player"[^>]*?src="([^"]+)"',
+            webpage, 'iframe URL')
+
+        iframe = self._download_webpage(
+            iframe_url, video_id, note='Downloading iframe')
+        flashvars_m = re.findall(
+            r'flashvars\.([_a-zA-Z0-9]+)\s*=\s*"([^"]*)";', iframe)
+        flashvars = dict((m[0], m[1]) for m in flashvars_m)
+
+        xml_url = ('http://www.laola1.tv/server/hd_video.php?' +
+                   'play=%s&partner=1&portal=%s&v5ident=&lang=%s' % (
+                       video_id, portal, lang))
+        hd_doc = self._download_xml(xml_url, video_id)
+
+        title = hd_doc.find('.//video/title').text
+        flash_url = hd_doc.find('.//video/url').text
+        categories = hd_doc.find('.//video/meta_sports').text.split(',')
+        uploader = hd_doc.find('.//video/meta_organistation').text
+
+        ident = random.randint(10000000, 99999999)
+        token_url = '%s&ident=%s&klub=0&unikey=0&timestamp=%s&auth=%s' % (
+            flash_url, ident, flashvars['timestamp'], flashvars['auth'])
+
+        token_doc = self._download_xml(
+            token_url, video_id, note='Downloading token')
+        token_attrib = token_doc.find('.//token').attrib
+        if token_attrib.get('auth') == 'blocked':
+            raise ExtractorError('Token error: ' % token_attrib.get('comment'))
+
+        video_url = '%s?hdnea=%s&hdcore=3.2.0' % (
+            token_attrib['url'], token_attrib['auth'])
+
+        return {
+            'id': video_id,
+            'is_live': True,
+            'title': title,
+            'url': video_url,
+            'uploader': uploader,
+            'categories': categories,
+            'ext': 'mp4',
+        }
+

youtube_dl/extractor/livestream.py

@@ -18,7 +18,7 @@ from ..utils import (
 
 class LivestreamIE(InfoExtractor):
     IE_NAME = 'livestream'
-    _VALID_URL = r'http://new\.livestream\.com/.*?/(?P<event_name>.*?)(/videos/(?P<id>\d+))?/?$'
+    _VALID_URL = r'https?://new\.livestream\.com/.*?/(?P<event_name>.*?)(/videos/(?P<id>[0-9]+)(?:/player)?)?/?(?:$|[?#])'
     _TESTS = [{
         'url': 'http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370',
         'md5': '53274c76ba7754fb0e8d072716f2292b',
@@ -37,6 +37,9 @@ class LivestreamIE(InfoExtractor):
             'title': 'TEDCity2.0 (English)',
         },
         'playlist_mincount': 4,
+    }, {
+        'url': 'https://new.livestream.com/accounts/362/events/3557232/videos/67864563/player?autoPlay=false&height=360&mute=false&width=640',
+        'only_matching': True,
     }]
 
     def _parse_smil(self, video_id, smil_url):
@@ -190,7 +193,8 @@ class LivestreamOriginalIE(InfoExtractor):
             'id': video_id,
             'title': item.find('title').text,
             'url': 'rtmp://extondemand.livestream.com/ondemand',
-            'play_path': 'mp4:trans/dv15/mogulus-{0}.mp4'.format(path),
+            'play_path': 'trans/dv15/mogulus-{0}'.format(path),
+            'player_url': 'http://static.livestream.com/chromelessPlayer/v21/playerapi.swf?hash=5uetk&v=0803&classid=D27CDB6E-AE6D-11cf-96B8-444553540000&jsEnabled=false&wmode=opaque',
             'ext': 'flv',
             'thumbnail': thumbnail_url,
         }

youtube_dl/extractor/lrt.py

@@ -22,7 +22,7 @@ class LRTIE(InfoExtractor):
             'id': '54391',
             'ext': 'mp4',
             'title': 'Septynios Kauno dienos',
-            'description': 'Kauno miesto ir apskrities naujienos',
+            'description': 'md5:24d84534c7dc76581e59f5689462411a',
             'duration': 1783,
         },
         'params': {
@@ -32,9 +32,7 @@ class LRTIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
         title = remove_end(self._og_search_title(webpage), ' - LRT')

youtube_dl/extractor/mitele.py

@@ -6,6 +6,7 @@ import json
 from .common import InfoExtractor
 from ..utils import (
     compat_urllib_parse,
+    compat_urlparse,
     get_element_by_attribute,
     parse_duration,
     strip_jsonp,
@@ -39,13 +40,21 @@ class MiTeleIE(InfoExtractor):
         ).replace('\'', '"')
         embed_data = json.loads(embed_data_json)
 
-        info_url = embed_data['flashvars']['host']
+        domain = embed_data['mediaUrl']
+        if not domain.startswith('http'):
+            # only happens in telecinco.es videos
+            domain = 'http://' + domain
+        info_url = compat_urlparse.urljoin(
+            domain,
+            compat_urllib_parse.unquote(embed_data['flashvars']['host'])
+        )
         info_el = self._download_xml(info_url, episode).find('./video/info')
 
         video_link = info_el.find('videoUrl/link').text
         token_query = compat_urllib_parse.urlencode({'id': video_link})
         token_info = self._download_json(
-            'http://token.mitele.es/?' + token_query, episode,
+            embed_data['flashvars']['ov_tk'] + '?' + token_query,
+            episode,
             transform_source=strip_jsonp
         )
 

youtube_dl/extractor/mixcloud.py

@@ -33,22 +33,22 @@ class MixcloudIE(InfoExtractor):
         },
     }
 
-    def check_urls(self, url_list):
-        """Returns 1st active url from list"""
-        for url in url_list:
+    def _get_url(self, track_id, template_url):
+        server_count = 30
+        for i in range(server_count):
+            url = template_url % i
             try:
                 # We only want to know if the request succeed
                 # don't download the whole file
-                self._request_webpage(HEADRequest(url), None, False)
+                self._request_webpage(
+                    HEADRequest(url), track_id,
+                    'Checking URL %d/%d ...' % (i + 1, server_count + 1))
                 return url
             except ExtractorError:
-                url = None
+                pass
 
         return None
 
-    def _get_url(self, template_url):
-        return self.check_urls(template_url % i for i in range(30))
-
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         uploader = mobj.group(1)
@@ -61,11 +61,11 @@ class MixcloudIE(InfoExtractor):
             r'\s(?:data-preview-url|m-preview)="(.+?)"', webpage, 'preview url')
         song_url = preview_url.replace('/previews/', '/c/originals/')
         template_url = re.sub(r'(stream\d*)', 'stream%d', song_url)
-        final_song_url = self._get_url(template_url)
+        final_song_url = self._get_url(track_id, template_url)
         if final_song_url is None:
             self.to_screen('Trying with m4a extension')
             template_url = template_url.replace('.mp3', '.m4a').replace('originals/', 'm4a/64/')
-            final_song_url = self._get_url(template_url)
+            final_song_url = self._get_url(track_id, template_url)
         if final_song_url is None:
             raise ExtractorError('Unable to extract track url')
 

youtube_dl/extractor/mlb.py

@@ -10,7 +10,7 @@ from ..utils import (
 
 
 class MLBIE(InfoExtractor):
-    _VALID_URL = r'https?://m\.mlb\.com/(?:(?:.*?/)?video/(?:topic/[\da-z_-]+/)?v|shared/video/embed/embed\.html\?.*?\bcontent_id=)(?P<id>n?\d+)'
+    _VALID_URL = r'https?://m(?:lb)?\.mlb\.com/(?:(?:.*?/)?video/(?:topic/[\da-z_-]+/)?v|(?:shared/video/embed/embed\.html|[^/]+/video/play\.jsp)\?.*?\bcontent_id=)(?P<id>n?\d+)'
     _TESTS = [
         {
             'url': 'http://m.mlb.com/sea/video/topic/51231442/v34698933/nymsea-ackley-robs-a-home-run-with-an-amazing-catch/?c_id=sea',
@@ -72,6 +72,14 @@ class MLBIE(InfoExtractor):
             'url': 'http://m.mlb.com/shared/video/embed/embed.html?content_id=35692085&topic_id=6479266&width=400&height=224&property=mlb',
             'only_matching': True,
         },
+        {
+            'url': 'http://mlb.mlb.com/shared/video/embed/embed.html?content_id=36599553',
+            'only_matching': True,
+        },
+        {
+            'url': 'http://mlb.mlb.com/es/video/play.jsp?content_id=36599553',
+            'only_matching': True,
+        },
     ]
 
     def _real_extract(self, url):

youtube_dl/extractor/motherless.py

@@ -5,20 +5,20 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
-    int_or_none,
+    str_to_int,
     unified_strdate,
 )
 
 
 class MotherlessIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?motherless\.com/(?P<id>[A-Z0-9]+)'
+    _VALID_URL = r'http://(?:www\.)?motherless\.com/(?:g/[a-z0-9_]+/)?(?P<id>[A-Z0-9]+)'
     _TESTS = [
         {
             'url': 'http://motherless.com/AC3FFE1',
-            'md5': '5527fef81d2e529215dad3c2d744a7d9',
+            'md5': '310f62e325a9fafe64f68c0bccb6e75f',
             'info_dict': {
                 'id': 'AC3FFE1',
-                'ext': 'flv',
+                'ext': 'mp4',
                 'title': 'Fucked in the ass while playing PS3',
                 'categories': ['Gaming', 'anal', 'reluctant', 'rough', 'Wife'],
                 'upload_date': '20100913',
@@ -40,33 +40,51 @@ class MotherlessIE(InfoExtractor):
                 'thumbnail': 're:http://.*\.jpg',
                 'age_limit': 18,
             }
+        },
+        {
+            'url': 'http://motherless.com/g/cosplay/633979F',
+            'md5': '0b2a43f447a49c3e649c93ad1fafa4a0',
+            'info_dict': {
+                'id': '633979F',
+                'ext': 'mp4',
+                'title': 'Turtlette',
+                'categories': ['superheroine heroine  superher'],
+                'upload_date': '20140827',
+                'uploader_id': 'shade0230',
+                'thumbnail': 're:http://.*\.jpg',
+                'age_limit': 18,
+            }
         }
     ]
 
-    def _real_extract(self,url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
-        title = self._html_search_regex(r'id="view-upload-title">\s+([^<]+)<', webpage, 'title')
-        
-        video_url = self._html_search_regex(r'setup\(\{\s+"file".+: "([^"]+)",', webpage, 'video_url')
+        title = self._html_search_regex(
+            r'id="view-upload-title">\s+([^<]+)<', webpage, 'title')
+        video_url = self._html_search_regex(
+            r'setup\(\{\s+"file".+: "([^"]+)",', webpage, 'video URL')
         age_limit = self._rta_search(webpage)
-
-        view_count = self._html_search_regex(r'<strong>Views</strong>\s+([^<]+)<', webpage, 'view_count')
+        view_count = str_to_int(self._html_search_regex(
+            r'<strong>Views</strong>\s+([^<]+)<',
+            webpage, 'view count', fatal=False))
+        like_count = str_to_int(self._html_search_regex(
+            r'<strong>Favorited</strong>\s+([^<]+)<',
+            webpage, 'like count', fatal=False))
  
-        upload_date = self._html_search_regex(r'<strong>Uploaded</strong>\s+([^<]+)<', webpage, 'upload_date')
+        upload_date = self._html_search_regex(
+            r'<strong>Uploaded</strong>\s+([^<]+)<', webpage, 'upload date')
         if 'Ago' in upload_date:
             days = int(re.search(r'([0-9]+)', upload_date).group(1))
             upload_date = (datetime.datetime.now() - datetime.timedelta(days=days)).strftime('%Y%m%d')
         else:
             upload_date = unified_strdate(upload_date)
 
-        like_count = self._html_search_regex(r'<strong>Favorited</strong>\s+([^<]+)<', webpage, 'like_count')
-
         comment_count = webpage.count('class="media-comment-contents"')
-        uploader_id = self._html_search_regex(r'"thumb-member-username">\s+<a href="/m/([^"]+)"', webpage, 'uploader_id')
+        uploader_id = self._html_search_regex(
+            r'"thumb-member-username">\s+<a href="/m/([^"]+)"',
+            webpage, 'uploader_id')
 
         categories = self._html_search_meta('keywords', webpage)
         if categories:
@@ -79,8 +97,8 @@ class MotherlessIE(InfoExtractor):
             'uploader_id': uploader_id,
             'thumbnail': self._og_search_thumbnail(webpage),
             'categories': categories,
-            'view_count': int_or_none(view_count.replace(',', '')),
-            'like_count': int_or_none(like_count.replace(',', '')),
+            'view_count': view_count,
+            'like_count': like_count,
             'comment_count': comment_count,
             'age_limit': age_limit,
             'url': video_url,

youtube_dl/extractor/mtv.py

@@ -33,7 +33,7 @@ class MTVServicesInfoExtractor(InfoExtractor):
         m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp\..+?/.*)$', rtmp_video_url)
         if not m:
             return rtmp_video_url
-        base = 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=1+_pxI0=Ripod-h264+_pxL0=undefined+_pxM0=+_pxK=18639+_pxE=mp4/44620/mtvnorigin/'
+        base = 'http://viacommtvstrmfs.fplive.net/'
         return base + m.group('finalid')
 
     def _get_feed_url(self, uri):

youtube_dl/extractor/myspass.py

@@ -13,9 +13,10 @@ class MySpassIE(InfoExtractor):
     _VALID_URL = r'http://www\.myspass\.de/.*'
     _TEST = {
         'url': 'http://www.myspass.de/myspass/shows/tvshows/absolute-mehrheit/Absolute-Mehrheit-vom-17022013-Die-Highlights-Teil-2--/11741/',
-        'file': '11741.mp4',
         'md5': '0b49f4844a068f8b33f4b7c88405862b',
         'info_dict': {
+            'id': '11741',
+            'ext': 'mp4',
             "description": "Wer kann in die Fu\u00dfstapfen von Wolfgang Kubicki treten und die Mehrheit der Zuschauer hinter sich versammeln? Wird vielleicht sogar die Absolute Mehrheit geknackt und der Jackpot von 200.000 Euro mit nach Hause genommen?",
             "title": "Absolute Mehrheit vom 17.02.2013 - Die Highlights, Teil 2",
         },

youtube_dl/extractor/myvideo.py

@@ -7,11 +7,12 @@ import re
 import json
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_ord,
     compat_urllib_parse,
     compat_urllib_request,
-
+)
+from ..utils import (
     ExtractorError,
 )
 

youtube_dl/extractor/naver.py

@@ -7,6 +7,7 @@ from .common import InfoExtractor
 from ..utils import (
     compat_urllib_parse,
     ExtractorError,
+    clean_html,
 )
 
 
@@ -31,6 +32,11 @@ class NaverIE(InfoExtractor):
         m_id = re.search(r'var rmcPlayer = new nhn.rmcnmv.RMCVideoPlayer\("(.+?)", "(.+?)"',
             webpage)
         if m_id is None:
+            m_error = re.search(
+                r'(?s)<div class="nation_error">\s*(?:<!--.*?-->)?\s*<p class="[^"]+">(?P<msg>.+?)</p>\s*</div>',
+                webpage)
+            if m_error:
+                raise ExtractorError(clean_html(m_error.group('msg')), expected=True)
             raise ExtractorError('couldn\'t extract vid and key')
         vid = m_id.group(1)
         key = m_id.group(2)

youtube_dl/extractor/nbc.py

@@ -26,8 +26,7 @@ class NBCIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
         theplatform_url = self._search_regex('class="video-player video-player-full" data-mpx-url="(.*?)"', webpage, 'theplatform url')
         if theplatform_url.startswith('//'):
@@ -57,7 +56,7 @@ class NBCNewsIE(InfoExtractor):
             'md5': 'b2421750c9f260783721d898f4c42063',
             'info_dict': {
                 'id': 'I1wpAI_zmhsQ',
-                'ext': 'flv',
+                'ext': 'mp4',
                 'title': 'How Twitter Reacted To The Snowden Interview',
                 'description': 'md5:65a0bd5d76fe114f3c2727aa3a81fe64',
             },
@@ -97,6 +96,8 @@ class NBCNewsIE(InfoExtractor):
             ]
 
             for base_url in base_urls:
+                if not base_url:
+                    continue
                 playlist_url = base_url + '?form=MPXNBCNewsAPI'
                 all_videos = self._download_json(playlist_url, title)['videos']
 

youtube_dl/extractor/ndr.py

@@ -67,7 +67,7 @@ class NDRIE(InfoExtractor):
 
         thumbnail = None
 
-        video_url = re.search(r'''3: \{src:'(?P<video>.+?)\.hi\.mp4', type:"video/mp4"},''', page)
+        video_url = re.search(r'''3: \{src:'(?P<video>.+?)\.(lo|hi|hq)\.mp4', type:"video/mp4"},''', page)
         if video_url:
             thumbnails = re.findall(r'''\d+: \{src: "([^"]+)"(?: \|\| '[^']+')?, quality: '([^']+)'}''', page)
             if thumbnails:

youtube_dl/extractor/nhl.py

@@ -7,7 +7,6 @@ from .common import InfoExtractor
 from ..utils import (
     compat_urlparse,
     compat_urllib_parse,
-    determine_ext,
     unified_strdate,
 )
 
@@ -22,21 +21,23 @@ class NHLBaseInfoExtractor(InfoExtractor):
         self.report_extraction(video_id)
 
         initial_video_url = info['publishPoint']
-        data = compat_urllib_parse.urlencode({
-            'type': 'fvod',
-            'path': initial_video_url.replace('.mp4', '_sd.mp4'),
-        })
-        path_url = 'http://video.nhl.com/videocenter/servlets/encryptvideopath?' + data
-        path_doc = self._download_xml(
-            path_url, video_id, 'Downloading final video url')
-        video_url = path_doc.find('path').text
+        if info['formats'] == '1':
+            data = compat_urllib_parse.urlencode({
+                'type': 'fvod',
+                'path': initial_video_url.replace('.mp4', '_sd.mp4'),
+            })
+            path_url = 'http://video.nhl.com/videocenter/servlets/encryptvideopath?' + data
+            path_doc = self._download_xml(
+                path_url, video_id, 'Downloading final video url')
+            video_url = path_doc.find('path').text
+        else:
+           video_url = initial_video_url
 
         join = compat_urlparse.urljoin
         return {
             'id': video_id,
             'title': info['name'],
             'url': video_url,
-            'ext': determine_ext(video_url),
             'description': info['description'],
             'duration': int(info['duration']),
             'thumbnail': join(join(video_url, '/u/'), info['bigImage']),
@@ -46,10 +47,11 @@ class NHLBaseInfoExtractor(InfoExtractor):
 
 class NHLIE(NHLBaseInfoExtractor):
     IE_NAME = 'nhl.com'
-    _VALID_URL = r'https?://video(?P<team>\.[^.]*)?\.nhl\.com/videocenter/console(?:\?(?:.*?[?&])?)id=(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://video(?P<team>\.[^.]*)?\.nhl\.com/videocenter/console(?:\?(?:.*?[?&])?)id=(?P<id>[0-9a-z-]+)'
 
     _TESTS = [{
         'url': 'http://video.canucks.nhl.com/videocenter/console?catid=6?id=453614',
+        'md5': 'db704a4ea09e8d3988c85e36cc892d09',
         'info_dict': {
             'id': '453614',
             'ext': 'mp4',
@@ -58,6 +60,17 @@ class NHLIE(NHLBaseInfoExtractor):
             'duration': 18,
             'upload_date': '20131006',
         },
+    }, {
+        'url': 'http://video.nhl.com/videocenter/console?id=2014020024-628-h',
+        'md5': 'd22e82bc592f52d37d24b03531ee9696',
+        'info_dict': {
+            'id': '2014020024-628-h',
+            'ext': 'mp4',
+            'title': 'Alex Galchenyuk Goal on Ray Emery (14:40/3rd)',
+            'description': 'Home broadcast - Montreal Canadiens at Philadelphia Flyers - October 11, 2014',
+            'duration': 0,
+            'upload_date': '20141011',
+        },
     }, {
         'url': 'http://video.flames.nhl.com/videocenter/console?id=630616',
         'only_matching': True,

youtube_dl/extractor/niconico.py

@@ -2,6 +2,7 @@
 from __future__ import unicode_literals
 
 import re
+import json
 
 from .common import InfoExtractor
 from ..utils import (
@@ -11,6 +12,7 @@ from ..utils import (
     unified_strdate,
     parse_duration,
     int_or_none,
+    ExtractorError,
 )
 
 
@@ -107,6 +109,9 @@ class NiconicoIE(InfoExtractor):
                 flv_info_request, video_id,
                 note='Downloading flv info', errnote='Unable to download flv info')
 
+        if 'deleted=' in flv_info_webpage:
+            raise ExtractorError('The video has been deleted.',
+                expected=True)
         video_real_url = compat_urlparse.parse_qs(flv_info_webpage)['url'][0]
 
         # Start extracting information
@@ -146,3 +151,37 @@ class NiconicoIE(InfoExtractor):
             'duration': duration,
             'webpage_url': webpage_url,
         }
+
+
+class NiconicoPlaylistIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.nicovideo\.jp/mylist/(?P<id>\d+)'
+
+    _TEST = {
+        'url': 'http://www.nicovideo.jp/mylist/27411728',
+        'info_dict': {
+            'id': '27411728',
+            'title': 'AKB48のオールナイトニッポン',
+        },
+        'playlist_mincount': 225,
+    }
+
+    def _real_extract(self, url):
+        list_id = self._match_id(url)
+        webpage = self._download_webpage(url, list_id)
+
+        entries_json = self._search_regex(r'Mylist\.preload\(\d+, (\[.*\])\);',
+            webpage, 'entries')
+        entries = json.loads(entries_json)
+        entries = [{
+            '_type': 'url',
+            'ie_key': NiconicoIE.ie_key(),
+            'url': ('http://www.nicovideo.jp/watch/%s' %
+                entry['item_data']['video_id']),
+        } for entry in entries]
+
+        return {
+            '_type': 'playlist',
+            'title': self._search_regex(r'\s+name: "(.*?)"', webpage, 'title'),
+            'id': list_id,
+            'entries': entries,
+        }

youtube_dl/extractor/npo.py

@@ -7,6 +7,7 @@ from ..utils import (
     unified_strdate,
     parse_duration,
     qualities,
+    strip_jsonp,
     url_basename,
 )
 
@@ -63,7 +64,7 @@ class NPOIE(InfoExtractor):
             'http://e.omroep.nl/metadata/aflevering/%s' % video_id,
             video_id,
             # We have to remove the javascript callback
-            transform_source=lambda j: re.sub(r'parseMetadata\((.*?)\);\n//.*$', r'\1', j)
+            transform_source=strip_jsonp,
         )
         token_page = self._download_webpage(
             'http://ida.omroep.nl/npoplayer/i.js',

youtube_dl/extractor/pbs.py

@@ -80,8 +80,14 @@ class PBSIE(InfoExtractor):
                 'thumbnail': 're:^https?://.*\.jpg$',
                 'upload_date': '20140122',
             }
+        },
+        {
+            'url': 'http://www.pbs.org/wgbh/pages/frontline/united-states-of-secrets/',
+            'info_dict': {
+                'id': 'united-states-of-secrets',
+            },
+            'playlist_count': 2,
         }
-
     ]
 
     def _extract_webpage(self, url):
@@ -96,6 +102,12 @@ class PBSIE(InfoExtractor):
                 r'<input type="hidden" id="air_date_[0-9]+" value="([^"]+)"',
                 webpage, 'upload date', default=None))
 
+            # tabbed frontline videos
+            tabbed_videos = re.findall(
+                r'<div[^>]+class="videotab[^"]*"[^>]+vid="(\d+)"', webpage)
+            if tabbed_videos:
+                return tabbed_videos, presumptive_id, upload_date
+
             MEDIA_ID_REGEXES = [
                 r"div\s*:\s*'videoembed'\s*,\s*mediaid\s*:\s*'(\d+)'",  # frontline video embed
                 r'class="coveplayerid">([^<]+)<',                       # coveplayer
@@ -130,6 +142,12 @@ class PBSIE(InfoExtractor):
     def _real_extract(self, url):
         video_id, display_id, upload_date = self._extract_webpage(url)
 
+        if isinstance(video_id, list):
+            entries = [self.url_result(
+                'http://video.pbs.org/video/%s' % vid_id, 'PBS', vid_id)
+                for vid_id in video_id]
+            return self.playlist_result(entries, display_id)
+
         info_url = 'http://video.pbs.org/videoInfo/%s?format=json' % video_id
         info = self._download_json(info_url, display_id)
 

youtube_dl/extractor/phoenix.py

@@ -0,0 +1,31 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from .zdf import extract_from_xml_url
+
+
+class PhoenixIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?phoenix\.de/content/(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://www.phoenix.de/content/884301',
+        'md5': 'ed249f045256150c92e72dbb70eadec6',
+        'info_dict': {
+            'id': '884301',
+            'ext': 'mp4',
+            'title': 'Michael Krons mit Hans-Werner Sinn',
+            'description': 'Im Dialog - Sa. 25.10.14, 00.00 - 00.35 Uhr',
+            'upload_date': '20141025',
+            'uploader': 'Im Dialog',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        internal_id = self._search_regex(
+            r'<div class="phx_vod" id="phx_vod_([0-9]+)"',
+            webpage, 'internal video ID')
+
+        api_url = 'http://www.phoenix.de/php/zdfplayer-v1.3/data/beitragsDetails.php?ak=web&id=%s' % internal_id
+        return extract_from_xml_url(self, video_id, api_url)

youtube_dl/extractor/played.py

@@ -6,6 +6,7 @@ import os.path
 
 from .common import InfoExtractor
 from ..utils import (
+    ExtractorError,
     compat_urllib_parse,
     compat_urllib_request,
 )
@@ -29,6 +30,12 @@ class PlayedIE(InfoExtractor):
         video_id = self._match_id(url)
 
         orig_webpage = self._download_webpage(url, video_id)
+
+        m_error = re.search(
+            r'(?s)Reason for deletion:.*?<b class="err"[^>]*>(?P<msg>[^<]+)</b>', orig_webpage)
+        if m_error:
+            raise ExtractorError(m_error.group('msg'), expected=True)
+
         fields = re.findall(
             r'type="hidden" name="([^"]+)"\s+value="([^"]+)">', orig_webpage)
         data = dict(fields)

youtube_dl/extractor/pornhub.py

@@ -16,13 +16,14 @@ from ..aes import (
 
 
 class PornHubIE(InfoExtractor):
-    _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>pornhub\.com/view_video\.php\?viewkey=(?P<videoid>[0-9a-f]+))'
+    _VALID_URL = r'^https?://(?:www\.)?pornhub\.com/view_video\.php\?viewkey=(?P<id>[0-9a-f]+)'
     _TEST = {
         'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
-        'file': '648719015.mp4',
         'md5': '882f488fa1f0026f023f33576004a2ed',
         'info_dict': {
-            "uploader": "BABES-COM",
+            'id': '648719015',
+            'ext': 'mp4',
+            "uploader": "Babes",
             "title": "Seductive Indian beauty strips down and fingers her pink pussy",
             "age_limit": 18
         }
@@ -35,9 +36,7 @@ class PornHubIE(InfoExtractor):
         return count
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('videoid')
-        url = 'http://www.' + mobj.group('url')
+        video_id = self._match_id(url)
 
         req = compat_urllib_request.Request(url)
         req.add_header('Cookie', 'age_verified=1')
@@ -45,7 +44,7 @@ class PornHubIE(InfoExtractor):
 
         video_title = self._html_search_regex(r'<h1 [^>]+>([^<]+)', webpage, 'title')
         video_uploader = self._html_search_regex(
-            r'(?s)From:&nbsp;.+?<(?:a href="/users/|<span class="username)[^>]+>(.+?)<',
+            r'(?s)From:&nbsp;.+?<(?:a href="/users/|a href="/channels/|<span class="username)[^>]+>(.+?)<',
             webpage, 'uploader', fatal=False)
         thumbnail = self._html_search_regex(r'"image_url":"([^"]+)', webpage, 'thumbnail', fatal=False)
         if thumbnail:

youtube_dl/extractor/promptfile.py

@@ -14,7 +14,6 @@ from ..utils import (
 
 class PromptFileIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?promptfile\.com/l/(?P<id>[0-9A-Z\-]+)'
-    _FILE_NOT_FOUND_REGEX = r'<div.+id="not_found_msg".+>.+</div>[^-]'
     _TEST = {
         'url': 'http://www.promptfile.com/l/D21B4746E9-F01462F0FF',
         'md5': 'd1451b6302da7215485837aaea882c4c',
@@ -27,11 +26,10 @@ class PromptFileIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
-        if re.search(self._FILE_NOT_FOUND_REGEX, webpage) is not None:
+        if re.search(r'<div.+id="not_found_msg".+>(?!We are).+</div>[^-]', webpage) is not None:
             raise ExtractorError('Video %s does not exist' % video_id,
                                  expected=True)
 

youtube_dl/extractor/quickvid.py

@@ -0,0 +1,51 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urlparse,
+    determine_ext,
+    int_or_none,
+)
+
+
+class QuickVidIE(InfoExtractor):
+    _VALID_URL = r'https?://(www\.)?quickvid\.org/watch\.php\?v=(?P<id>[a-zA-Z_0-9-]+)'
+    _TEST = {
+        'url': 'http://quickvid.org/watch.php?v=sUQT3RCG8dx',
+        'md5': 'c0c72dd473f260c06c808a05d19acdc5',
+        'info_dict': {
+            'id': 'sUQT3RCG8dx',
+            'ext': 'mp4',
+            'title': 'Nick Offerman\'s Summer Reading Recap',
+            'thumbnail': 're:^https?://.*\.(?:png|jpg|gif)$',
+            'view_count': int,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._html_search_regex(r'<h2>(.*?)</h2>', webpage, 'title')
+        view_count = int_or_none(self._html_search_regex(
+            r'(?s)<div id="views">(.*?)</div>',
+            webpage, 'view count', fatal=False))
+        video_code = self._search_regex(
+            r'(?s)<video id="video"[^>]*>(.*?)</video>', webpage, 'video code')
+        formats = [
+            {
+                'url': compat_urlparse.urljoin(url, src),
+                'format_id': determine_ext(src, None),
+            } for src in re.findall('<source\s+src="([^"]+)"', video_code)
+        ]
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'view_count': view_count,
+        }

youtube_dl/extractor/ro220.py

@@ -1,43 +1,43 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
-from ..utils import (
-    clean_html,
-    compat_parse_qs,
-)
+from ..compat import compat_urllib_parse_unquote
 
 
 class Ro220IE(InfoExtractor):
     IE_NAME = '220.ro'
-    _VALID_URL = r'(?x)(?:https?://)?(?:www\.)?220\.ro/(?P<category>[^/]+)/(?P<shorttitle>[^/]+)/(?P<video_id>[^/]+)'
+    _VALID_URL = r'(?x)(?:https?://)?(?:www\.)?220\.ro/(?P<category>[^/]+)/(?P<shorttitle>[^/]+)/(?P<id>[^/]+)'
     _TEST = {
-        "url": "http://www.220.ro/sport/Luati-Le-Banii-Sez-4-Ep-1/LYV6doKo7f/",
-        'file': 'LYV6doKo7f.mp4',
+        'url': 'http://www.220.ro/sport/Luati-Le-Banii-Sez-4-Ep-1/LYV6doKo7f/',
         'md5': '03af18b73a07b4088753930db7a34add',
         'info_dict': {
-            "title": "Luati-le Banii sez 4 ep 1",
-            "description": "re:^Iata-ne reveniti dupa o binemeritata vacanta\. +Va astept si pe Facebook cu pareri si comentarii.$",
+            'id': 'LYV6doKo7f',
+            'ext': 'mp4',
+            'title': 'Luati-le Banii sez 4 ep 1',
+            'description': 're:^Iata-ne reveniti dupa o binemeritata vacanta\. +Va astept si pe Facebook cu pareri si comentarii.$',
         }
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('video_id')
+        video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
-        flashVars_str = self._search_regex(
-            r'<param name="flashVars" value="([^"]+)"',
-            webpage, 'flashVars')
-        flashVars = compat_parse_qs(flashVars_str)
+        url = compat_urllib_parse_unquote(self._search_regex(
+            r'(?s)clip\s*:\s*{.*?url\s*:\s*\'([^\']+)\'', webpage, 'url'))
+        title = self._og_search_title(webpage)
+        description = self._og_search_description(webpage)
+        thumbnail = self._og_search_thumbnail(webpage)
+
+        formats = [{
+            'format_id': 'sd',
+            'url': url,
+            'ext': 'mp4',
+        }]
 
         return {
-            '_type': 'video',
             'id': video_id,
-            'ext': 'mp4',
-            'url': flashVars['videoURL'][0],
-            'title': flashVars['title'][0],
-            'description': clean_html(flashVars['desc'][0]),
-            'thumbnail': flashVars['preview'][0],
+            'formats': formats,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
         }

youtube_dl/extractor/rtlnow.py

@@ -81,7 +81,7 @@ class RTLnowIE(InfoExtractor):
                 'id': '99205',
                 'ext': 'flv',
                 'title': 'Medicopter 117 - Angst!',
-                'description': 'md5:895b1df01639b5f61a04fc305a5cb94d',
+                'description': 're:^Im Therapiezentrum \'Sonnalm\' kommen durch eine Unachtsamkeit die für die B.handlung mit Phobikern gehaltenen Voglespinnen frei\. Eine Ausreißerin',
                 'thumbnail': 'http://autoimg.static-fra.de/superrtlnow/287529/1500x1500/image2.jpg',
                 'upload_date': '20080928',
                 'duration': 2691,

youtube_dl/extractor/ruhd.py

@@ -1,8 +1,6 @@
 # -*- coding: utf-8 -*-
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 
 
@@ -21,19 +19,20 @@ class RUHDIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
         video_url = self._html_search_regex(
             r'<param name="src" value="([^"]+)"', webpage, 'video url')
         title = self._html_search_regex(
-            r'<title>([^<]+)&nbsp;&nbsp; RUHD.ru - Видео Высокого качества №1 в России!</title>', webpage, 'title')
+            r'<title>([^<]+)&nbsp;&nbsp; RUHD.ru - Видео Высокого качества №1 в России!</title>',
+            webpage, 'title')
         description = self._html_search_regex(
-            r'(?s)<div id="longdesc">(.+?)<span id="showlink">', webpage, 'description', fatal=False)
+            r'(?s)<div id="longdesc">(.+?)<span id="showlink">',
+            webpage, 'description', fatal=False)
         thumbnail = self._html_search_regex(
-            r'<param name="previewImage" value="([^"]+)"', webpage, 'thumbnail', fatal=False)
+            r'<param name="previewImage" value="([^"]+)"',
+            webpage, 'thumbnail', fatal=False)
         if thumbnail:
             thumbnail = 'http://www.ruhd.ru' + thumbnail
 

youtube_dl/extractor/sexu.py

@@ -0,0 +1,61 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class SexuIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?sexu\.com/(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://sexu.com/961791/',
+        'md5': 'ff615aca9691053c94f8f10d96cd7884',
+        'info_dict': {
+            'id': '961791',
+            'ext': 'mp4',
+            'title': 'md5:4d05a19a5fc049a63dbbaf05fb71d91b',
+            'description': 'md5:c5ed8625eb386855d5a7967bd7b77a54',
+            'categories': list,  # NSFW
+            'thumbnail': 're:https?://.*\.jpg$',
+            'age_limit': 18,
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        quality_arr = self._search_regex(
+            r'sources:\s*\[([^\]]+)\]', webpage, 'forrmat string')
+        formats = [{
+            'url': fmt[0].replace('\\', ''),
+            'format_id': fmt[1],
+            'height': int(fmt[1][:3]),
+        } for fmt in re.findall(r'"file":"([^"]+)","label":"([^"]+)"', quality_arr)]
+        self._sort_formats(formats)
+
+        title = self._html_search_regex(
+            r'<title>([^<]+)\s*-\s*Sexu\.Com</title>', webpage, 'title')
+
+        description = self._html_search_meta(
+            'description', webpage, 'description')
+
+        thumbnail = self._html_search_regex(
+            r'image:\s*"([^"]+)"',
+            webpage, 'thumbnail', fatal=False)
+
+        categories_str = self._html_search_meta(
+            'keywords', webpage, 'categories')
+        categories = (
+            None if categories_str is None
+            else categories_str.split(','))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'categories': categories,
+            'formats': formats,
+            'age_limit': 18,
+        }

youtube_dl/extractor/sexykarma.py

@@ -0,0 +1,117 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    unified_strdate,
+    parse_duration,
+    int_or_none,
+)
+
+
+class SexyKarmaIE(InfoExtractor):
+    IE_DESC = 'Sexy Karma and Watch Indian Porn'
+    _VALID_URL = r'https?://(?:www\.)?(?:sexykarma\.com|watchindianporn\.net)/(?:[^/]+/)*video/(?P<display_id>[^/]+)-(?P<id>[a-zA-Z0-9]+)\.html'
+    _TESTS = [{
+        'url': 'http://www.sexykarma.com/gonewild/video/taking-a-quick-pee-yHI70cOyIHt.html',
+        'md5': 'b9798e7d1ef1765116a8f516c8091dbd',
+        'info_dict': {
+            'id': 'yHI70cOyIHt',
+            'display_id': 'taking-a-quick-pee',
+            'ext': 'mp4',
+            'title': 'Taking a quick pee.',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'uploader': 'wildginger7',
+            'upload_date': '20141007',
+            'duration': 22,
+            'view_count': int,
+            'comment_count': int,
+            'categories': list,
+        }
+    }, {
+        'url': 'http://www.sexykarma.com/gonewild/video/pot-pixie-tribute-8Id6EZPbuHf.html',
+        'md5': 'dd216c68d29b49b12842b9babe762a5d',
+        'info_dict': {
+            'id': '8Id6EZPbuHf',
+            'display_id': 'pot-pixie-tribute',
+            'ext': 'mp4',
+            'title': 'pot_pixie tribute',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'uploader': 'banffite',
+            'upload_date': '20141013',
+            'duration': 16,
+            'view_count': int,
+            'comment_count': int,
+            'categories': list,
+        }
+    }, {
+        'url': 'http://www.watchindianporn.net/video/desi-dancer-namrata-stripping-completely-nude-and-dancing-on-a-hot-number-dW2mtctxJfs.html',
+        'md5': '9afb80675550406ed9a63ac2819ef69d',
+        'info_dict': {
+            'id': 'dW2mtctxJfs',
+            'display_id': 'desi-dancer-namrata-stripping-completely-nude-and-dancing-on-a-hot-number',
+            'ext': 'mp4',
+            'title': 'Desi dancer namrata stripping completely nude and dancing on a hot number',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'uploader': 'Don',
+            'upload_date': '20140213',
+            'duration': 83,
+            'view_count': int,
+            'comment_count': int,
+            'categories': list,
+        }
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        display_id = mobj.group('display_id')
+
+        webpage = self._download_webpage(url, display_id)
+
+        video_url = self._html_search_regex(
+            r"url: escape\('([^']+)'\)", webpage, 'url')
+
+        title = self._html_search_regex(
+            r'<h2 class="he2"><span>(.*?)</span>',
+            webpage, 'title')
+        thumbnail = self._html_search_regex(
+            r'<span id="container"><img\s+src="([^"]+)"',
+            webpage, 'thumbnail', fatal=False)
+
+        uploader = self._html_search_regex(
+            r'class="aupa">\s*(.*?)</a>',
+            webpage, 'uploader')
+        upload_date = unified_strdate(self._html_search_regex(
+            r'Added: <strong>(.+?)</strong>', webpage, 'upload date', fatal=False))
+
+        duration = parse_duration(self._search_regex(
+            r'<td>Time:\s*</td>\s*<td align="right"><span>\s*(.+?)\s*</span>',
+            webpage, 'duration', fatal=False))
+
+        view_count = int_or_none(self._search_regex(
+            r'<td>Views:\s*</td>\s*<td align="right"><span>\s*(\d+)\s*</span>',
+            webpage, 'view count', fatal=False))
+        comment_count = int_or_none(self._search_regex(
+            r'<td>Comments:\s*</td>\s*<td align="right"><span>\s*(\d+)\s*</span>',
+            webpage, 'comment count', fatal=False))
+
+        categories = re.findall(
+            r'<a href="[^"]+/search/video/desi"><span>([^<]+)</span></a>',
+            webpage)
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'url': video_url,
+            'title': title,
+            'thumbnail': thumbnail,
+            'uploader': uploader,
+            'upload_date': upload_date,
+            'duration': duration,
+            'view_count': view_count,
+            'comment_count': comment_count,
+            'categories': categories,
+        }

youtube_dl/extractor/soundcloud.py

@@ -40,14 +40,15 @@ class SoundcloudIE(InfoExtractor):
     _TESTS = [
         {
             'url': 'http://soundcloud.com/ethmusic/lostin-powers-she-so-heavy',
-            'file': '62986583.mp3',
             'md5': 'ebef0a451b909710ed1d7787dddbf0d7',
             'info_dict': {
-                "upload_date": "20121011",
-                "description": "No Downloads untill we record the finished version this weekend, i was too pumped n i had to post it , earl is prolly gonna b hella p.o'd",
-                "uploader": "E.T. ExTerrestrial Music",
-                "title": "Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1",
-                "duration": 143,
+                'id': '62986583',
+                'ext': 'mp3',
+                'upload_date': '20121011',
+                'description': 'No Downloads untill we record the finished version this weekend, i was too pumped n i had to post it , earl is prolly gonna b hella p.o\'d',
+                'uploader': 'E.T. ExTerrestrial Music',
+                'title': 'Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1',
+                'duration': 143,
             }
         },
         # not streamable song
@@ -103,7 +104,7 @@ class SoundcloudIE(InfoExtractor):
                 'id': '128590877',
                 'ext': 'mp3',
                 'title': 'Bus Brakes',
-                'description': 'md5:0170be75dd395c96025d210d261c784e',
+                'description': 'md5:0053ca6396e8d2fd7b7e1595ef12ab66',
                 'uploader': 'oddsamples',
                 'upload_date': '20140109',
                 'duration': 17,
@@ -140,6 +141,7 @@ class SoundcloudIE(InfoExtractor):
             'description': info['description'],
             'thumbnail': thumbnail,
             'duration': int_or_none(info.get('duration'), 1000),
+            'webpage_url': info.get('permalink_url'),
         }
         formats = []
         if info.get('downloadable', False):

youtube_dl/extractor/spiegel.py

@@ -4,11 +4,11 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import compat_urlparse
+from ..compat import compat_urlparse
 
 
 class SpiegelIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<videoID>[0-9]+)(?:\.html)?(?:#.*)?$'
+    _VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<id>[0-9]+)(?:-embed)?(?:\.html)?(?:#.*)?$'
     _TESTS = [{
         'url': 'http://www.spiegel.de/video/vulkan-tungurahua-in-ecuador-ist-wieder-aktiv-video-1259285.html',
         'md5': '2c2754212136f35fb4b19767d242f66e',
@@ -29,16 +29,24 @@ class SpiegelIE(InfoExtractor):
             'description': 'md5:c2322b65e58f385a820c10fa03b2d088',
             'duration': 983,
         },
+    }, {
+        'url': 'http://www.spiegel.de/video/astronaut-alexander-gerst-von-der-iss-station-beantwortet-fragen-video-1519126-embed.html',
+        'md5': 'd8eeca6bfc8f1cd6f490eb1f44695d51',
+        'info_dict': {
+            'id': '1519126',
+            'ext': 'mp4',
+            'description': 'SPIEGEL ONLINE-Nutzer durften den deutschen Astronauten Alexander Gerst über sein Leben auf der ISS-Station befragen. Hier kommen seine Antworten auf die besten sechs Fragen.',
+            'title': 'Fragen an Astronaut Alexander Gerst: "Bekommen Sie die Tageszeiten mit?"',
+        }
     }]
 
     def _real_extract(self, url):
-        m = re.match(self._VALID_URL, url)
-        video_id = m.group('videoID')
-
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
-        title = self._html_search_regex(
-            r'<div class="module-title">(.*?)</div>', webpage, 'title')
+        title = re.sub(r'\s+', ' ', self._html_search_regex(
+            r'(?s)<(?:h1|div) class="module-title"[^>]*>(.*?)</(?:h1|div)>',
+            webpage, 'title'))
         description = self._html_search_meta('description', webpage, 'description')
 
         base_url = self._search_regex(
@@ -79,7 +87,7 @@ class SpiegelArticleIE(InfoExtractor):
     _VALID_URL = 'https?://www\.spiegel\.de/(?!video/)[^?#]*?-(?P<id>[0-9]+)\.html'
     IE_NAME = 'Spiegel:Article'
     IE_DESC = 'Articles on spiegel.de'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.spiegel.de/sport/sonst/badminton-wm-die-randsportart-soll-populaerer-werden-a-987092.html',
         'info_dict': {
             'id': '1516455',
@@ -87,20 +95,34 @@ class SpiegelArticleIE(InfoExtractor):
             'title': 'Faszination Badminton: Nennt es bloß nicht Federball',
             'description': 're:^Patrick Kämnitz gehört.{100,}',
         },
-    }
+    }, {
+        'url': 'http://www.spiegel.de/wissenschaft/weltall/astronaut-alexander-gerst-antwortet-spiegel-online-lesern-a-989876.html',
+        'info_dict': {
+
+        },
+        'playlist_count': 6,
+    }]
 
     def _real_extract(self, url):
-        m = re.match(self._VALID_URL, url)
-        video_id = m.group('id')
-
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
+
+        # Single video on top of the page
         video_link = self._search_regex(
             r'<a href="([^"]+)" onclick="return spOpenVideo\(this,', webpage,
-            'video page URL')
-        video_url = compat_urlparse.urljoin(
-            self.http_scheme() + '//spiegel.de/', video_link)
+            'video page URL', default=None)
+        if video_link:
+            video_url = compat_urlparse.urljoin(
+                self.http_scheme() + '//spiegel.de/', video_link)
+            return self.url_result(video_url)
 
-        return {
-            '_type': 'url',
-            'url': video_url,
-        }
+        # Multiple embedded videos
+        embeds = re.findall(
+            r'<div class="vid_holder[0-9]+.*?</div>\s*.*?url\s*=\s*"([^"]+)"',
+            webpage)
+        entries = [
+            self.url_result(compat_urlparse.urljoin(
+                self.http_scheme() + '//spiegel.de/', embed_path))
+            for embed_path in embeds
+        ]
+        return self.playlist_result(entries)

youtube_dl/extractor/sportbox.py

@@ -7,7 +7,6 @@ from .common import InfoExtractor
 from ..utils import (
     parse_duration,
     parse_iso8601,
-    int_or_none,
 )
 
 
@@ -26,7 +25,6 @@ class SportBoxIE(InfoExtractor):
                 'timestamp': 1411896237,
                 'upload_date': '20140928',
                 'duration': 4846,
-                'view_count': int,
             },
             'params': {
                 # m3u8 download
@@ -65,8 +63,6 @@ class SportBoxIE(InfoExtractor):
             r'<span itemprop="uploadDate">([^<]+)</span>', webpage, 'timestamp', fatal=False))
         duration = parse_duration(self._html_search_regex(
             r'<meta itemprop="duration" content="PT([^"]+)">', webpage, 'duration', fatal=False))
-        view_count = int_or_none(self._html_search_regex(
-            r'<span>Просмотров: (\d+)</span>', player, 'view count', fatal=False))
 
         return {
             'id': video_id,
@@ -76,6 +72,5 @@ class SportBoxIE(InfoExtractor):
             'thumbnail': thumbnail,
             'timestamp': timestamp,
             'duration': duration,
-            'view_count': view_count,
             'formats': formats,
         }

youtube_dl/extractor/srmediathek.py

@@ -0,0 +1,43 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import json
+
+from .common import InfoExtractor
+from ..utils import js_to_json
+
+
+class SRMediathekIE(InfoExtractor):
+    IE_DESC = 'Süddeutscher Rundfunk'
+    _VALID_URL = r'https?://sr-mediathek\.sr-online\.de/index\.php\?.*?&id=(?P<id>[0-9]+)'
+
+    _TEST = {
+        'url': 'http://sr-mediathek.sr-online.de/index.php?seite=7&id=28455',
+        'info_dict': {
+            'id': '28455',
+            'ext': 'mp4',
+            'title': 'sportarena (26.10.2014)',
+            'description': 'Ringen: KSV Köllerbach gegen Aachen-Walheim; Frauen-Fußball: 1. FC Saarbrücken gegen Sindelfingen; Motorsport: Rallye in Losheim; dazu: Interview mit Timo Bernhard; Turnen: TG Saar; Reitsport: Deutscher Voltigier-Pokal; Badminton: Interview mit Michael Fuchs ',
+            'thumbnail': 're:^https?://.*\.jpg$',
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        murls = json.loads(js_to_json(self._search_regex(
+            r'var mediaURLs\s*=\s*(.*?);\n', webpage, 'video URLs')))
+        formats = [{'url': murl} for murl in murls]
+        self._sort_formats(formats)
+
+        title = json.loads(js_to_json(self._search_regex(
+            r'var mediaTitles\s*=\s*(.*?);\n', webpage, 'title')))[0]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'description': self._og_search_description(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
+        }

youtube_dl/extractor/streamcloud.py

@@ -13,7 +13,7 @@ from ..utils import (
 
 class StreamcloudIE(InfoExtractor):
     IE_NAME = 'streamcloud.eu'
-    _VALID_URL = r'https?://streamcloud\.eu/(?P<id>[a-zA-Z0-9_-]+)/(?P<fname>[^#?]*)\.html'
+    _VALID_URL = r'https?://streamcloud\.eu/(?P<id>[a-zA-Z0-9_-]+)(?:/(?P<fname>[^#?]*)\.html)?'
 
     _TEST = {
         'url': 'http://streamcloud.eu/skp9j99s4bpz/youtube-dl_test_video_____________-BaW_jenozKc.mp4.html',
@@ -27,8 +27,8 @@ class StreamcloudIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
+        url = 'http://streamcloud.eu/%s' % video_id
 
         orig_webpage = self._download_webpage(url, video_id)
 

youtube_dl/extractor/swrmediathek.py

@@ -80,7 +80,7 @@ class SWRMediathekIE(InfoExtractor):
 
             if media_type == 'Video':
                 fmt.update({
-                    'format_note': ['144p', '288p', '544p'][quality-1],
+                    'format_note': ['144p', '288p', '544p', '720p'][quality-1],
                     'vcodec': codec,
                 })
             elif media_type == 'Audio':
@@ -101,4 +101,4 @@ class SWRMediathekIE(InfoExtractor):
             'uploader': attr['channel_title'],
             'uploader_id': attr['channel_idkey'],
             'formats': formats,
-        }
+        }

youtube_dl/extractor/syfy.py

@@ -10,7 +10,6 @@ class SyfyIE(InfoExtractor):
 
     _TESTS = [{
         'url': 'http://www.syfy.com/videos/Robot%20Combat%20League/Behind%20the%20Scenes/vid:2631458',
-        'md5': 'e07de1d52c7278adbb9b9b1c93a66849',
         'info_dict': {
             'id': 'NmqMrGnXvmO1',
             'ext': 'flv',

youtube_dl/extractor/tapely.py

@@ -50,6 +50,7 @@ class TapelyIE(InfoExtractor):
         request = compat_urllib_request.Request(playlist_url)
         request.add_header('X-Requested-With', 'XMLHttpRequest')
         request.add_header('Accept', 'application/json')
+        request.add_header('Referer', url)
 
         playlist = self._download_json(request, display_id)