release 2014.02.26

Accept any character except `/` for uploader and the name, caused problems with non ASCII characters

README.md

@@ -20,7 +20,7 @@ which means you can modify it, redistribute it or use it however you like.
                                      sure that you have sufficient permissions
                                      (run with sudo if needed)
     -i, --ignore-errors              continue on download errors, for example to
-                                     to skip unavailable videos in a playlist
+                                     skip unavailable videos in a playlist
     --abort-on-error                 Abort downloading of further videos (in the
                                      playlist or the command line) if an error
                                      occurs
@@ -246,7 +246,7 @@ which means you can modify it, redistribute it or use it however you like.
 
 # CONFIGURATION
 
-You can configure youtube-dl by placing default arguments (such as `--extract-audio --no-mtime` to always extract the audio and not copy the mtime) into `/etc/youtube-dl.conf` and/or `~/.config/youtube-dl.conf`. On Windows, the configuration file locations are `%APPDATA%\youtube-dl\config.txt` and `C:\Users\<Yourname>\youtube-dl.conf`.
+You can configure youtube-dl by placing default arguments (such as `--extract-audio --no-mtime` to always extract the audio and not copy the mtime) into `/etc/youtube-dl.conf` and/or `~/.config/youtube-dl/config`. On Windows, the configuration file locations are `%APPDATA%\youtube-dl\config.txt` and `C:\Users\<Yourname>\youtube-dl.conf`.
 
 # OUTPUT TEMPLATE
 
@@ -281,12 +281,14 @@ Videos can be filtered by their upload date using the options `--date`, `--dateb
  
 Examples:
 
-  $ # Download only the videos uploaded in the last 6 months
-	$ youtube-dl --dateafter now-6months
-  $ # Download only the videos uploaded on January 1, 1970
-	$ youtube-dl --date 19700101
-  $ # will only download the videos uploaded in the 200x decade
-	$ youtube-dl --dateafter 20000101 --datebefore 20091231
+    # Download only the videos uploaded in the last 6 months
+    $ youtube-dl --dateafter now-6months
+
+    # Download only the videos uploaded on January 1, 1970
+    $ youtube-dl --date 19700101
+
+    $ # will only download the videos uploaded in the 200x decade
+    $ youtube-dl --dateafter 20000101 --datebefore 20091231
 
 # FAQ
 
@@ -355,7 +357,7 @@ If you want to create a build of youtube-dl yourself, you'll need
 
 ### Adding support for a new site
 
-If you want to add support for a new site, copy *any* [recently modified](https://github.com/rg3/youtube-dl/commits/master/youtube_dl/extractor) file in `youtube_dl/extractor`, add an import in [`youtube_dl/extractor/__init__.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/__init__.py). 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). Don't forget to run the tests with `python test/test_download.py Test_Download.test_YourExtractor`! For a detailed tutorial, refer to [this blog post](http://filippo.io/add-support-for-a-new-video-site-to-youtube-dl/).
+If you want to add support for a new site, copy *any* [recently modified](https://github.com/rg3/youtube-dl/commits/master/youtube_dl/extractor) file in `youtube_dl/extractor`, add an import in [`youtube_dl/extractor/__init__.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/__init__.py). 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). Don't forget to run the tests with `python test/test_download.py TestDownload.test_YourExtractor`! For a detailed tutorial, refer to [this blog post](http://filippo.io/add-support-for-a-new-video-site-to-youtube-dl/).
 
 # BUGS
 

devscripts/release.sh

@@ -14,9 +14,9 @@
 
 set -e
 
-skip_tests=false
-if [ "$1" = '--skip-test' ]; then
-    skip_tests=true
+skip_tests=true
+if [ "$1" = '--run-tests' ]; then
+    skip_tests=false
     shift
 fi
 

test/test_all_urls.py

@@ -68,6 +68,9 @@ class TestAllURLsMatching(unittest.TestCase):
     def test_youtube_show_matching(self):
         self.assertMatch('http://www.youtube.com/show/airdisasters', ['youtube:show'])
 
+    def test_youtube_truncated(self):
+        self.assertMatch('http://www.youtube.com/watch?', ['youtube:truncated_url'])
+
     def test_justin_tv_channelid_matching(self):
         self.assertTrue(JustinTVIE.suitable(u"justin.tv/vanillatv"))
         self.assertTrue(JustinTVIE.suitable(u"twitch.tv/vanillatv"))
@@ -85,7 +88,7 @@ class TestAllURLsMatching(unittest.TestCase):
         self.assertTrue(JustinTVIE.suitable(u"http://www.twitch.tv/tsm_theoddone/c/2349361"))
 
     def test_youtube_extract(self):
-        assertExtractId = lambda url, id: self.assertEqual(YoutubeIE()._extract_id(url), id)
+        assertExtractId = lambda url, id: self.assertEqual(YoutubeIE.extract_id(url), id)
         assertExtractId('http://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
         assertExtractId('https://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
         assertExtractId('https://www.youtube.com/watch?feature=player_embedded&v=BaW_jenozKc', 'BaW_jenozKc')

test/test_download.py

@@ -18,6 +18,7 @@ from test.helper import (
 import hashlib
 import io
 import json
+import re
 import socket
 
 import youtube_dl.YoutubeDL
@@ -72,9 +73,7 @@ def generator(test_case):
         if 'playlist' not in test_case:
             info_dict = test_case.get('info_dict', {})
             if not test_case.get('file') and not (info_dict.get('id') and info_dict.get('ext')):
-                print_skipping('The output file cannot be know, the "file" '
-                    'key is missing or the info_dict is incomplete')
-                return
+                raise Exception('Test definition incorrect. The output file cannot be known. Are both \'id\' and \'ext\' keys present?')
         if 'skip' in test_case:
             print_skipping(test_case['skip'])
             return
@@ -137,12 +136,21 @@ def generator(test_case):
                 with io.open(info_json_fn, encoding='utf-8') as infof:
                     info_dict = json.load(infof)
                 for (info_field, expected) in tc.get('info_dict', {}).items():
-                    if isinstance(expected, compat_str) and expected.startswith('md5:'):
-                        got = 'md5:' + md5(info_dict.get(info_field))
-                    else:
+                    if isinstance(expected, compat_str) and expected.startswith('re:'):
                         got = info_dict.get(info_field)
-                    self.assertEqual(expected, got,
-                        u'invalid value for field %s, expected %r, got %r' % (info_field, expected, got))
+                        match_str = expected[len('re:'):]
+                        match_rex = re.compile(match_str)
+
+                        self.assertTrue(
+                            isinstance(got, compat_str) and match_rex.match(got),
+                            u'field %s (value: %r) should match %r' % (info_field, got, match_str))
+                    else:
+                        if isinstance(expected, compat_str) and expected.startswith('md5:'):
+                            got = 'md5:' + md5(info_dict.get(info_field))
+                        else:
+                            got = info_dict.get(info_field)
+                        self.assertEqual(expected, got,
+                            u'invalid value for field %s, expected %r, got %r' % (info_field, expected, got))
 
                 # If checkable fields are missing from the test case, print the info_dict
                 test_info_dict = dict((key, value if not isinstance(value, compat_str) or len(value) < 250 else 'md5:' + md5(value))

test/test_playlists.py

@@ -55,10 +55,10 @@ class TestPlaylists(unittest.TestCase):
     def test_dailymotion_user(self):
         dl = FakeYDL()
         ie = DailymotionUserIE(dl)
-        result = ie.extract('http://www.dailymotion.com/user/generation-quoi/')
+        result = ie.extract('https://www.dailymotion.com/user/nqtv')
         self.assertIsPlaylist(result)
-        self.assertEqual(result['title'], 'Génération Quoi')
-        self.assertTrue(len(result['entries']) >= 26)
+        self.assertEqual(result['title'], 'Rémi Gaillard')
+        self.assertTrue(len(result['entries']) >= 100)
 
     def test_vimeo_channel(self):
         dl = FakeYDL()
@@ -170,12 +170,12 @@ class TestPlaylists(unittest.TestCase):
     def test_AcademicEarthCourse(self):
         dl = FakeYDL()
         ie = AcademicEarthCourseIE(dl)
-        result = ie.extract('http://academicearth.org/courses/building-dynamic-websites/')
+        result = ie.extract('http://academicearth.org/playlists/laws-of-nature/')
         self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], 'building-dynamic-websites')
-        self.assertEqual(result['title'], 'Building Dynamic Websites')
-        self.assertEqual(result['description'], u"Today's websites are increasingly dynamic. Pages are no longer static HTML files but instead generated by scripts and database calls. User interfaces are more seamless, with technologies like Ajax replacing traditional page reloads. This course teaches students how to build dynamic websites with Ajax and with Linux, Apache, MySQL, and PHP (LAMP), one of today's most popular frameworks. Students learn how to set up domain names with DNS, how to structure pages with XHTML and CSS, how to program in JavaScript and PHP, how to configure Apache and MySQL, how to design and query databases with SQL, how to use Ajax with both XML and JSON, and how to build mashups. The course explores issues of security, scalability, and cross-browser support and also discusses enterprise-level deployments of websites, including third-party hosting, virtualization, colocation in data centers, firewalling, and load-balancing.")
-        self.assertEqual(len(result['entries']), 10)
+        self.assertEqual(result['id'], 'laws-of-nature')
+        self.assertEqual(result['title'], 'Laws of Nature')
+        self.assertEqual(result['description'],u'Introduce yourself to the laws of nature with these free online college lectures from Yale, Harvard, and MIT.')# u"Today's websites are increasingly dynamic. Pages are no longer static HTML files but instead generated by scripts and database calls. User interfaces are more seamless, with technologies like Ajax replacing traditional page reloads. This course teaches students how to build dynamic websites with Ajax and with Linux, Apache, MySQL, and PHP (LAMP), one of today's most popular frameworks. Students learn how to set up domain names with DNS, how to structure pages with XHTML and CSS, how to program in JavaScript and PHP, how to configure Apache and MySQL, how to design and query databases with SQL, how to use Ajax with both XML and JSON, and how to build mashups. The course explores issues of security, scalability, and cross-browser support and also discusses enterprise-level deployments of websites, including third-party hosting, virtualization, colocation in data centers, firewalling, and load-balancing.")
+        self.assertEqual(len(result['entries']), 4)
         
     def test_ivi_compilation(self):
         dl = FakeYDL()
@@ -250,5 +250,14 @@ class TestPlaylists(unittest.TestCase):
         self.assertEqual(result['title'], 'python language')
         self.assertTrue(len(result['entries']) == 15)
 
+    def test_generic_rss_feed(self):
+        dl = FakeYDL()
+        ie = GenericIE(dl)
+        result = ie.extract('http://www.escapistmagazine.com/rss/videos/list/1.xml')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], 'http://www.escapistmagazine.com/rss/videos/list/1.xml')
+        self.assertEqual(result['title'], 'Zero Punctuation')
+        self.assertTrue(len(result['entries']) > 10)
+
 if __name__ == '__main__':
     unittest.main()

test/test_utils.py

@@ -9,6 +9,7 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 
 # Various small unit tests
+import io
 import xml.etree.ElementTree
 
 #from youtube_dl.utils import htmlentity_transform
@@ -21,10 +22,12 @@ from youtube_dl.utils import (
     orderedSet,
     PagedList,
     parse_duration,
+    read_batch_urls,
     sanitize_filename,
     shell_quote,
     smuggle_url,
     str_to_int,
+    struct_unpack,
     timeconvert,
     unescapeHTML,
     unified_strdate,
@@ -127,6 +130,7 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(unified_strdate('8/7/2009'), '20090708')
         self.assertEqual(unified_strdate('Dec 14, 2012'), '20121214')
         self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
+        self.assertEqual(unified_strdate('1968-12-10'), '19681210')
 
     def test_find_xpath_attr(self):
         testxml = u'''<root>
@@ -200,7 +204,16 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(parse_duration('1'), 1)
         self.assertEqual(parse_duration('1337:12'), 80232)
         self.assertEqual(parse_duration('9:12:43'), 33163)
+        self.assertEqual(parse_duration('12:00'), 720)
+        self.assertEqual(parse_duration('00:01:01'), 61)
         self.assertEqual(parse_duration('x:y'), None)
+        self.assertEqual(parse_duration('3h11m53s'), 11513)
+        self.assertEqual(parse_duration('62m45s'), 3765)
+        self.assertEqual(parse_duration('6m59s'), 419)
+        self.assertEqual(parse_duration('49s'), 49)
+        self.assertEqual(parse_duration('0h0m0s'), 0)
+        self.assertEqual(parse_duration('0m0s'), 0)
+        self.assertEqual(parse_duration('0s'), 0)
 
     def test_fix_xml_ampersands(self):
         self.assertEqual(
@@ -236,5 +249,17 @@ class TestUtil(unittest.TestCase):
         testPL(5, 2, (2, 99), [2, 3, 4])
         testPL(5, 2, (20, 99), [])
 
+    def test_struct_unpack(self):
+        self.assertEqual(struct_unpack(u'!B', b'\x00'), (0,))
+
+    def test_read_batch_urls(self):
+        f = io.StringIO(u'''\xef\xbb\xbf foo
+            bar\r
+            baz
+            # More after this line\r
+            ; or after this
+            bam''')
+        self.assertEqual(read_batch_urls(f), [u'foo', u'bar', u'baz', u'bam'])
+
 if __name__ == '__main__':
     unittest.main()

test/test_youtube_lists.py

@@ -30,7 +30,7 @@ class TestYoutubeLists(unittest.TestCase):
         result = ie.extract('https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re')
         self.assertIsPlaylist(result)
         self.assertEqual(result['title'], 'ytdl test PL')
-        ytie_results = [YoutubeIE()._extract_id(url['url']) for url in result['entries']]
+        ytie_results = [YoutubeIE().extract_id(url['url']) for url in result['entries']]
         self.assertEqual(ytie_results, [ 'bV9L5Ht9LgY', 'FXxLjLQi3Fg', 'tU3Bgo5qJZE'])
 
     def test_youtube_playlist_noplaylist(self):
@@ -39,7 +39,7 @@ class TestYoutubeLists(unittest.TestCase):
         ie = YoutubePlaylistIE(dl)
         result = ie.extract('https://www.youtube.com/watch?v=FXxLjLQi3Fg&list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re')
         self.assertEqual(result['_type'], 'url')
-        self.assertEqual(YoutubeIE()._extract_id(result['url']), 'FXxLjLQi3Fg')
+        self.assertEqual(YoutubeIE().extract_id(result['url']), 'FXxLjLQi3Fg')
 
     def test_issue_673(self):
         dl = FakeYDL()
@@ -59,7 +59,7 @@ class TestYoutubeLists(unittest.TestCase):
         dl = FakeYDL()
         ie = YoutubePlaylistIE(dl)
         result = ie.extract('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')
-        ytie_results = [YoutubeIE()._extract_id(url['url']) for url in result['entries']]
+        ytie_results = [YoutubeIE().extract_id(url['url']) for url in result['entries']]
         self.assertFalse('pElCt5oNDuI' in ytie_results)
         self.assertFalse('KdPEApIVdWM' in ytie_results)
         
@@ -76,9 +76,9 @@ class TestYoutubeLists(unittest.TestCase):
         # TODO find a > 100 (paginating?) videos course
         result = ie.extract('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
         entries = result['entries']
-        self.assertEqual(YoutubeIE()._extract_id(entries[0]['url']), 'j9WZyLZCBzs')
+        self.assertEqual(YoutubeIE().extract_id(entries[0]['url']), 'j9WZyLZCBzs')
         self.assertEqual(len(entries), 25)
-        self.assertEqual(YoutubeIE()._extract_id(entries[-1]['url']), 'rYefUsYuEp0')
+        self.assertEqual(YoutubeIE().extract_id(entries[-1]['url']), 'rYefUsYuEp0')
 
     def test_youtube_channel(self):
         dl = FakeYDL()
@@ -118,6 +118,8 @@ class TestYoutubeLists(unittest.TestCase):
         self.assertEqual(original_video['id'], 'rjFaenf1T-Y')
 
     def test_youtube_toptracks(self):
+        print('Skipping: The playlist page gives error 500')
+        return
         dl = FakeYDL()
         ie = YoutubePlaylistIE(dl)
         result = ie.extract('https://www.youtube.com/playlist?list=MCUS')

youtube_dl/__init__.py

@@ -41,13 +41,20 @@ __authors__  = (
     'Chris Gahan',
     'Saimadhav Heblikar',
     'Mike Col',
+    'Oleg Prutz',
+    'pulpe',
     'Andreas Schmitz',
+    'Michael Kaiser',
+    'Niklas Laxström',
+    'David Triendl',
+    'Anthony Weems',
 )
 
 __license__ = 'Public Domain'
 
 import codecs
 import getpass
+import io
 import locale
 import optparse
 import os
@@ -66,6 +73,7 @@ from .utils import (
     get_cachedir,
     MaxDownloadsReached,
     preferredencoding,
+    read_batch_urls,
     SameFileError,
     setproctitle,
     std_headers,
@@ -204,7 +212,7 @@ def parseOpts(overrideArguments=None):
     general.add_option('-U', '--update',
             action='store_true', dest='update_self', help='update this program to latest version. Make sure that you have sufficient permissions (run with sudo if needed)')
     general.add_option('-i', '--ignore-errors',
-            action='store_true', dest='ignoreerrors', help='continue on download errors, for example to to skip unavailable videos in a playlist', default=False)
+            action='store_true', dest='ignoreerrors', help='continue on download errors, for example to skip unavailable videos in a playlist', default=False)
     general.add_option('--abort-on-error',
             action='store_false', dest='ignoreerrors',
             help='Abort downloading of further videos (in the playlist or the command line) if an error occurs')
@@ -547,21 +555,19 @@ def _real_main(argv=None):
         sys.exit(0)
 
     # Batch file verification
-    batchurls = []
+    batch_urls = []
     if opts.batchfile is not None:
         try:
             if opts.batchfile == '-':
                 batchfd = sys.stdin
             else:
-                batchfd = open(opts.batchfile, 'r')
-            batchurls = batchfd.readlines()
-            batchurls = [x.strip() for x in batchurls]
-            batchurls = [x for x in batchurls if len(x) > 0 and not re.search(r'^[#/;]', x)]
+                batchfd = io.open(opts.batchfile, 'r', encoding='utf-8', errors='ignore')
+            batch_urls = read_batch_urls(batchfd)
             if opts.verbose:
-                write_string(u'[debug] Batch file urls: ' + repr(batchurls) + u'\n')
+                write_string(u'[debug] Batch file urls: ' + repr(batch_urls) + u'\n')
         except IOError:
             sys.exit(u'ERROR: batch file could not be read')
-    all_urls = batchurls + args
+    all_urls = batch_urls + args
     all_urls = [url.strip() for url in all_urls]
     _enc = preferredencoding()
     all_urls = [url.decode(_enc, 'ignore') if isinstance(url, bytes) else url for url in all_urls]

youtube_dl/downloader/__init__.py

@@ -5,6 +5,7 @@ from .hls import HlsFD
 from .http import HttpFD
 from .mplayer import MplayerFD
 from .rtmp import RtmpFD
+from .f4m import F4mFD
 
 from ..utils import (
     determine_ext,
@@ -22,5 +23,7 @@ def get_suitable_downloader(info_dict):
         return HlsFD
     if url.startswith('mms') or url.startswith('rtsp'):
         return MplayerFD
+    if determine_ext(url) == 'f4m':
+        return F4mFD
     else:
         return HttpFD

youtube_dl/downloader/f4m.py

@@ -0,0 +1,314 @@
+from __future__ import unicode_literals
+
+import base64
+import io
+import itertools
+import os
+import time
+import xml.etree.ElementTree as etree
+
+from .common import FileDownloader
+from .http import HttpFD
+from ..utils import (
+    struct_pack,
+    struct_unpack,
+    compat_urlparse,
+    format_bytes,
+    encodeFilename,
+    sanitize_open,
+)
+
+
+class FlvReader(io.BytesIO):
+    """
+    Reader for Flv files
+    The file format is documented in https://www.adobe.com/devnet/f4v.html
+    """
+
+    # Utility functions for reading numbers and strings
+    def read_unsigned_long_long(self):
+        return struct_unpack('!Q', self.read(8))[0]
+
+    def read_unsigned_int(self):
+        return struct_unpack('!I', self.read(4))[0]
+
+    def read_unsigned_char(self):
+        return struct_unpack('!B', self.read(1))[0]
+
+    def read_string(self):
+        res = b''
+        while True:
+            char = self.read(1)
+            if char == b'\x00':
+                break
+            res += char
+        return res
+
+    def read_box_info(self):
+        """
+        Read a box and return the info as a tuple: (box_size, box_type, box_data)
+        """
+        real_size = size = self.read_unsigned_int()
+        box_type = self.read(4)
+        header_end = 8
+        if size == 1:
+            real_size = self.read_unsigned_long_long()
+            header_end = 16
+        return real_size, box_type, self.read(real_size-header_end)
+
+    def read_asrt(self):
+        # version
+        self.read_unsigned_char()
+        # flags
+        self.read(3)
+        quality_entry_count = self.read_unsigned_char()
+        # QualityEntryCount
+        for i in range(quality_entry_count):
+            self.read_string()
+
+        segment_run_count = self.read_unsigned_int()
+        segments = []
+        for i in range(segment_run_count):
+            first_segment = self.read_unsigned_int()
+            fragments_per_segment = self.read_unsigned_int()
+            segments.append((first_segment, fragments_per_segment))
+
+        return {
+            'segment_run': segments,
+        }
+
+    def read_afrt(self):
+        # version
+        self.read_unsigned_char()
+        # flags
+        self.read(3)
+        # time scale
+        self.read_unsigned_int()
+
+        quality_entry_count = self.read_unsigned_char()
+        # QualitySegmentUrlModifiers
+        for i in range(quality_entry_count):
+            self.read_string()
+
+        fragments_count = self.read_unsigned_int()
+        fragments = []
+        for i in range(fragments_count):
+            first = self.read_unsigned_int()
+            first_ts = self.read_unsigned_long_long()
+            duration = self.read_unsigned_int()
+            if duration == 0:
+                discontinuity_indicator = self.read_unsigned_char()
+            else:
+                discontinuity_indicator = None
+            fragments.append({
+                'first': first,
+                'ts': first_ts,
+                'duration': duration,
+                'discontinuity_indicator': discontinuity_indicator,
+            })
+
+        return {
+            'fragments': fragments,
+        }
+
+    def read_abst(self):
+        # version
+        self.read_unsigned_char()
+        # flags
+        self.read(3)
+
+        self.read_unsigned_int()  # BootstrapinfoVersion
+        # Profile,Live,Update,Reserved
+        self.read(1)
+        # time scale
+        self.read_unsigned_int()
+        # CurrentMediaTime
+        self.read_unsigned_long_long()
+        # SmpteTimeCodeOffset
+        self.read_unsigned_long_long()
+
+        self.read_string()  # MovieIdentifier
+        server_count = self.read_unsigned_char()
+        # ServerEntryTable
+        for i in range(server_count):
+            self.read_string()
+        quality_count = self.read_unsigned_char()
+        # QualityEntryTable
+        for i in range(quality_count):
+            self.read_string()
+        # DrmData
+        self.read_string()
+        # MetaData
+        self.read_string()
+
+        segments_count = self.read_unsigned_char()
+        segments = []
+        for i in range(segments_count):
+            box_size, box_type, box_data = self.read_box_info()
+            assert box_type == b'asrt'
+            segment = FlvReader(box_data).read_asrt()
+            segments.append(segment)
+        fragments_run_count = self.read_unsigned_char()
+        fragments = []
+        for i in range(fragments_run_count):
+            box_size, box_type, box_data = self.read_box_info()
+            assert box_type == b'afrt'
+            fragments.append(FlvReader(box_data).read_afrt())
+
+        return {
+            'segments': segments,
+            'fragments': fragments,
+        }
+
+    def read_bootstrap_info(self):
+        total_size, box_type, box_data = self.read_box_info()
+        assert box_type == b'abst'
+        return FlvReader(box_data).read_abst()
+
+
+def read_bootstrap_info(bootstrap_bytes):
+    return FlvReader(bootstrap_bytes).read_bootstrap_info()
+
+
+def build_fragments_list(boot_info):
+    """ Return a list of (segment, fragment) for each fragment in the video """
+    res = []
+    segment_run_table = boot_info['segments'][0]
+    # I've only found videos with one segment
+    segment_run_entry = segment_run_table['segment_run'][0]
+    n_frags = segment_run_entry[1]
+    fragment_run_entry_table = boot_info['fragments'][0]['fragments']
+    first_frag_number = fragment_run_entry_table[0]['first']
+    for (i, frag_number) in zip(range(1, n_frags+1), itertools.count(first_frag_number)):
+        res.append((1, frag_number))
+    return res
+
+
+def write_flv_header(stream, metadata):
+    """Writes the FLV header and the metadata to stream"""
+    # FLV header
+    stream.write(b'FLV\x01')
+    stream.write(b'\x05')
+    stream.write(b'\x00\x00\x00\x09')
+    # FLV File body
+    stream.write(b'\x00\x00\x00\x00')
+    # FLVTAG
+    # Script data
+    stream.write(b'\x12')
+    # Size of the metadata with 3 bytes
+    stream.write(struct_pack('!L', len(metadata))[1:])
+    stream.write(b'\x00\x00\x00\x00\x00\x00\x00')
+    stream.write(metadata)
+    # Magic numbers extracted from the output files produced by AdobeHDS.php
+    #(https://github.com/K-S-V/Scripts)
+    stream.write(b'\x00\x00\x01\x73')
+
+
+def _add_ns(prop):
+    return '{http://ns.adobe.com/f4m/1.0}%s' % prop
+
+
+class HttpQuietDownloader(HttpFD):
+    def to_screen(self, *args, **kargs):
+        pass
+
+
+class F4mFD(FileDownloader):
+    """
+    A downloader for f4m manifests or AdobeHDS.
+    """
+
+    def real_download(self, filename, info_dict):
+        man_url = info_dict['url']
+        self.to_screen('[download] Downloading f4m manifest')
+        manifest = self.ydl.urlopen(man_url).read()
+        self.report_destination(filename)
+        http_dl = HttpQuietDownloader(self.ydl,
+            {
+                'continuedl': True,
+                'quiet': True,
+                'noprogress': True,
+                'test': self.params.get('test', False),
+            })
+
+        doc = etree.fromstring(manifest)
+        formats = [(int(f.attrib.get('bitrate', -1)), f) for f in doc.findall(_add_ns('media'))]
+        formats = sorted(formats, key=lambda f: f[0])
+        rate, media = formats[-1]
+        base_url = compat_urlparse.urljoin(man_url, media.attrib['url'])
+        bootstrap = base64.b64decode(doc.find(_add_ns('bootstrapInfo')).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
+            fragments_list = fragments_list[:1]
+        total_frags = len(fragments_list)
+
+        tmpfilename = self.temp_name(filename)
+        (dest_stream, tmpfilename) = sanitize_open(tmpfilename, 'wb')
+        write_flv_header(dest_stream, metadata)
+
+        # This dict stores the download progress, it's updated by the progress
+        # hook
+        state = {
+            'downloaded_bytes': 0,
+            'frag_counter': 0,
+        }
+        start = time.time()
+
+        def frag_progress_hook(status):
+            frag_total_bytes = status.get('total_bytes', 0)
+            estimated_size = (state['downloaded_bytes'] +
+                (total_frags - state['frag_counter']) * frag_total_bytes)
+            if status['status'] == 'finished':
+                state['downloaded_bytes'] += frag_total_bytes
+                state['frag_counter'] += 1
+                progress = self.calc_percent(state['frag_counter'], total_frags)
+                byte_counter = state['downloaded_bytes']
+            else:
+                frag_downloaded_bytes = status['downloaded_bytes']
+                byte_counter = state['downloaded_bytes'] + frag_downloaded_bytes
+                frag_progress = self.calc_percent(frag_downloaded_bytes,
+                    frag_total_bytes)
+                progress = self.calc_percent(state['frag_counter'], total_frags)
+                progress += frag_progress / float(total_frags)
+
+            eta = self.calc_eta(start, time.time(), estimated_size, byte_counter)
+            self.report_progress(progress, format_bytes(estimated_size),
+                status.get('speed'), eta)
+        http_dl.add_progress_hook(frag_progress_hook)
+
+        frags_filenames = []
+        for (seg_i, frag_i) in fragments_list:
+            name = 'Seg%d-Frag%d' % (seg_i, frag_i)
+            url = base_url + name
+            frag_filename = '%s-%s' % (tmpfilename, name)
+            success = http_dl.download(frag_filename, {'url': url})
+            if not success:
+                return False
+            with open(frag_filename, 'rb') as down:
+                down_data = down.read()
+                reader = FlvReader(down_data)
+                while True:
+                    _, box_type, box_data = reader.read_box_info()
+                    if box_type == b'mdat':
+                        dest_stream.write(box_data)
+                        break
+            frags_filenames.append(frag_filename)
+
+        self.report_finish(format_bytes(state['downloaded_bytes']), time.time() - start)
+
+        self.try_rename(tmpfilename, filename)
+        for frag_file in frags_filenames:
+            os.remove(frag_file)
+
+        fsize = os.path.getsize(encodeFilename(filename))
+        self._hook_progress({
+            'downloaded_bytes': fsize,
+            'total_bytes': fsize,
+            'filename': filename,
+            'status': 'finished',
+        })
+
+        return True

youtube_dl/extractor/__init__.py

@@ -19,6 +19,7 @@ from .bbccouk import BBCCoUkIE
 from .blinkx import BlinkxIE
 from .bliptv import BlipTVIE, BlipTVUserIE
 from .bloomberg import BloombergIE
+from .br import BRIE
 from .breakcom import BreakIE
 from .brightcove import BrightcoveIE
 from .c56 import C56IE
@@ -32,7 +33,10 @@ from .clipfish import ClipfishIE
 from .cliphunter import CliphunterIE
 from .clipsyndicate import ClipsyndicateIE
 from .cmt import CMTIE
-from .cnn import CNNIE
+from .cnn import (
+    CNNIE,
+    CNNBlogsIE,
+)
 from .collegehumor import CollegeHumorIE
 from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE
 from .condenast import CondeNastIE
@@ -64,11 +68,13 @@ from .extremetube import ExtremeTubeIE
 from .facebook import FacebookIE
 from .faz import FazIE
 from .firstpost import FirstpostIE
+from .firsttv import FirstTVIE
 from .fktv import (
     FKTVIE,
     FKTVPosteckeIE,
 )
 from .flickr import FlickrIE
+from .fourtube import FourTubeIE
 from .franceinter import FranceInterIE
 from .francetv import (
     PluzzIE,
@@ -87,6 +93,7 @@ from .generic import GenericIE
 from .googleplus import GooglePlusIE
 from .googlesearch import GoogleSearchIE
 from .hark import HarkIE
+from .helsinki import HelsinkiIE
 from .hotnewhiphop import HotNewHipHopIE
 from .howcast import HowcastIE
 from .huffpost import HuffPostIE
@@ -105,6 +112,7 @@ from .ivi import (
     IviIE,
     IviCompilationIE
 )
+from .jadorecettepub import JadoreCettePubIE
 from .jeuxvideo import JeuxVideoIE
 from .jukebox import JukeboxIE
 from .justintv import JustinTVIE
@@ -114,6 +122,7 @@ from .keezmovies import KeezMoviesIE
 from .khanacademy import KhanAcademyIE
 from .kickstarter import KickStarterIE
 from .keek import KeekIE
+from .kontrtube import KontrTubeIE
 from .la7 import LA7IE
 from .lifenews import LifeNewsIE
 from .liveleak import LiveLeakIE
@@ -128,7 +137,7 @@ from .malemotion import MalemotionIE
 from .mdr import MDRIE
 from .metacafe import MetacafeIE
 from .metacritic import MetacriticIE
-from .mit import TechTVMITIE, MITIE
+from .mit import TechTVMITIE, MITIE, OCWMITIE
 from .mixcloud import MixcloudIE
 from .mpora import MporaIE
 from .mofosex import MofosexIE
@@ -143,7 +152,10 @@ from .myspass import MySpassIE
 from .myvideo import MyVideoIE
 from .naver import NaverIE
 from .nba import NBAIE
-from .nbc import NBCNewsIE
+from .nbc import (
+    NBCIE,
+    NBCNewsIE,
+)
 from .ndr import NDRIE
 from .ndtv import NDTVIE
 from .newgrounds import NewgroundsIE
@@ -152,7 +164,7 @@ from .nhl import NHLIE, NHLVideocenterIE
 from .niconico import NiconicoIE
 from .ninegag import NineGagIE
 from .normalboots import NormalbootsIE
-from .novamov import NovamovIE
+from .novamov import NovaMovIE
 from .nowness import NownessIE
 from .nowvideo import NowVideoIE
 from .ooyala import OoyalaIE
@@ -178,6 +190,7 @@ from .rutube import (
     RutubeMovieIE,
     RutubePersonIE,
 )
+from .savefrom import SaveFromIE
 from .servingsys import ServingSysIE
 from .sina import SinaIE
 from .slashdot import SlashdotIE
@@ -202,10 +215,13 @@ from .stanfordoc import StanfordOpenClassroomIE
 from .statigram import StatigramIE
 from .steam import SteamIE
 from .streamcloud import StreamcloudIE
+from .streamcz import StreamCZIE
+from .syfy import SyfyIE
 from .sztvhu import SztvHuIE
 from .teamcoco import TeamcocoIE
 from .techtalks import TechTalksIE
 from .ted import TEDIE
+from .testurl import TestURLIE
 from .tf1 import TF1IE
 from .theplatform import ThePlatformIE
 from .thisav import ThisAVIE
@@ -213,6 +229,7 @@ from .tinypic import TinyPicIE
 from .toutv import TouTvIE
 from .traileraddict import TrailerAddictIE
 from .trilulilu import TriluliluIE
+from .trutube import TruTubeIE
 from .tube8 import Tube8IE
 from .tudou import TudouIE
 from .tumblr import TumblrIE
@@ -223,9 +240,11 @@ from .ustream import UstreamIE, UstreamChannelIE
 from .vbox7 import Vbox7IE
 from .veehd import VeeHDIE
 from .veoh import VeohIE
+from .vesti import VestiIE
 from .vevo import VevoIE
 from .vice import ViceIE
 from .viddler import ViddlerIE
+from .videobam import VideoBamIE
 from .videodetective import VideoDetectiveIE
 from .videofyme import VideofyMeIE
 from .videopremium import VideoPremiumIE

youtube_dl/extractor/academicearth.py

@@ -5,7 +5,7 @@ from .common import InfoExtractor
 
 
 class AcademicEarthCourseIE(InfoExtractor):
-    _VALID_URL = r'^https?://(?:www\.)?academicearth\.org/(?:courses|playlists)/(?P<id>[^?#/]+)'
+    _VALID_URL = r'^https?://(?:www\.)?academicearth\.org/playlists/(?P<id>[^?#/]+)'
     IE_NAME = 'AcademicEarth:Course'
 
     def _real_extract(self, url):
@@ -14,12 +14,12 @@ class AcademicEarthCourseIE(InfoExtractor):
 
         webpage = self._download_webpage(url, playlist_id)
         title = self._html_search_regex(
-            r'<h1 class="playlist-name">(.*?)</h1>', webpage, u'title')
+            r'<h1 class="playlist-name"[^>]*?>(.*?)</h1>', webpage, u'title')
         description = self._html_search_regex(
-            r'<p class="excerpt">(.*?)</p>',
+            r'<p class="excerpt"[^>]*?>(.*?)</p>',
             webpage, u'description', fatal=False)
         urls = re.findall(
-            r'<h3 class="lecture-title"><a target="_blank" href="([^"]+)">',
+            r'<li class="lecture-preview">\s*?<a target="_blank" href="([^"]+)">',
             webpage)
         entries = [self.url_result(u) for u in urls]
 

youtube_dl/extractor/bbccouk.py

@@ -2,115 +2,222 @@ from __future__ import unicode_literals
 
 import re
 
-from .common import InfoExtractor
+from .subtitles import SubtitlesInfoExtractor
 from ..utils import ExtractorError
 
 
-class BBCCoUkIE(InfoExtractor):
+class BBCCoUkIE(SubtitlesInfoExtractor):
     IE_NAME = 'bbc.co.uk'
-    IE_DESC = 'BBC - iPlayer Radio'
+    IE_DESC = 'BBC iPlayer'
     _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:programmes|iplayer/episode)/(?P<id>[\da-z]{8})'
 
-    _TEST = {
-        'url': 'http://www.bbc.co.uk/programmes/p01q7wz1',
-        'info_dict': {
-            'id': 'p01q7wz4',
-            'ext': 'flv',
-            'title': 'Friction: Blu Mar Ten guest mix: Blu Mar Ten - Guest Mix',
-            'description': 'Blu Mar Ten deliver a Guest Mix for Friction.',
-            'duration': 1936,
+    _TESTS = [
+        {
+            'url': 'http://www.bbc.co.uk/programmes/b039g8p7',
+            'info_dict': {
+                'id': 'b039d07m',
+                'ext': 'flv',
+                'title': 'Kaleidoscope: Leonard Cohen',
+                'description': 'md5:db4755d7a665ae72343779f7dacb402c',
+                'duration': 1740,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            }
         },
-        'params': {
-            # rtmp download
-            'skip_download': True,
+        {
+            'url': 'http://www.bbc.co.uk/iplayer/episode/b00yng5w/The_Man_in_Black_Series_3_The_Printed_Name/',
+            'info_dict': {
+                'id': 'b00yng1d',
+                'ext': 'flv',
+                'title': 'The Man in Black: Series 3: The Printed Name',
+                'description': "Mark Gatiss introduces Nicholas Pierpan's chilling tale of a writer's devilish pact with a mysterious man. Stars Ewan Bailey.",
+                'duration': 1800,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+            'skip': 'Episode is no longer available on BBC iPlayer Radio',
+        },
+        {
+            'url': 'http://www.bbc.co.uk/iplayer/episode/b03vhd1f/The_Voice_UK_Series_3_Blind_Auditions_5/',
+            'info_dict': {
+                'id': 'b00yng1d',
+                'ext': 'flv',
+                'title': 'The Voice UK: Series 3: Blind Auditions 5',
+                'description': "Emma Willis and Marvin Humes present the fifth set of blind auditions in the singing competition, as the coaches continue to build their teams based on voice alone.",
+                'duration': 5100,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+            'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only',
         }
-    }
+    ]
+
+    def _extract_asx_playlist(self, connection, programme_id):
+        asx = self._download_xml(connection.get('href'), programme_id, 'Downloading ASX playlist')
+        return [ref.get('href') for ref in asx.findall('./Entry/ref')]
+
+    def _extract_connection(self, connection, programme_id):
+        formats = []
+        protocol = connection.get('protocol')
+        supplier = connection.get('supplier')
+        if protocol == 'http':
+            href = connection.get('href')
+            # ASX playlist
+            if supplier == 'asx':
+                for i, ref in enumerate(self._extract_asx_playlist(connection, programme_id)):
+                    formats.append({
+                        'url': ref,
+                        'format_id': 'ref%s_%s' % (i, supplier),
+                    })
+            # Direct link
+            else:
+                formats.append({
+                    'url': href,
+                    'format_id': supplier,
+                })
+        elif protocol == 'rtmp':
+            application = connection.get('application', 'ondemand')
+            auth_string = connection.get('authString')
+            identifier = connection.get('identifier')
+            server = connection.get('server')
+            formats.append({
+                'url': '%s://%s/%s?%s' % (protocol, server, application, auth_string),
+                'play_path': identifier,
+                'app': '%s?%s' % (application, auth_string),
+                'page_url': 'http://www.bbc.co.uk',
+                'player_url': 'http://www.bbc.co.uk/emp/releases/iplayer/revisions/617463_618125_4/617463_618125_4_emp.swf',
+                'rtmp_live': False,
+                'ext': 'flv',
+                'format_id': supplier,
+            })
+        return formats
+
+    def _extract_items(self, playlist):
+        return playlist.findall('./{http://bbc.co.uk/2008/emp/playlist}item')
+
+    def _extract_medias(self, media_selection):
+        return media_selection.findall('./{http://bbc.co.uk/2008/mp/mediaselection}media')
+
+    def _extract_connections(self, media):
+        return media.findall('./{http://bbc.co.uk/2008/mp/mediaselection}connection')
+
+    def _extract_video(self, media, programme_id):
+        formats = []
+        vbr = int(media.get('bitrate'))
+        vcodec = media.get('encoding')
+        service = media.get('service')
+        width = int(media.get('width'))
+        height = int(media.get('height'))
+        file_size = int(media.get('media_file_size'))
+        for connection in self._extract_connections(media):
+            conn_formats = self._extract_connection(connection, programme_id)
+            for format in conn_formats:
+                format.update({
+                    'format_id': '%s_%s' % (service, format['format_id']),
+                    'width': width,
+                    'height': height,
+                    'vbr': vbr,
+                    'vcodec': vcodec,
+                    'filesize': file_size,
+                })
+            formats.extend(conn_formats)
+        return formats
+
+    def _extract_audio(self, media, programme_id):
+        formats = []
+        abr = int(media.get('bitrate'))
+        acodec = media.get('encoding')
+        service = media.get('service')
+        for connection in self._extract_connections(media):
+            conn_formats = self._extract_connection(connection, programme_id)
+            for format in conn_formats:
+                format.update({
+                    'format_id': '%s_%s' % (service, format['format_id']),
+                    'abr': abr,
+                    'acodec': acodec,
+                })
+            formats.extend(conn_formats)
+        return formats
+
+    def _extract_captions(self, media, programme_id):
+        subtitles = {}
+        for connection in self._extract_connections(media):
+            captions = self._download_xml(connection.get('href'), programme_id, 'Downloading captions')
+            lang = captions.get('{http://www.w3.org/XML/1998/namespace}lang', 'en')
+            ps = captions.findall('./{0}body/{0}div/{0}p'.format('{http://www.w3.org/2006/10/ttaf1}'))
+            srt = ''
+            for pos, p in enumerate(ps):
+                srt += '%s\r\n%s --> %s\r\n%s\r\n\r\n' % (str(pos), p.get('begin'), p.get('end'),
+                                                          p.text.strip() if p.text is not None else '')
+            subtitles[lang] = srt
+        return subtitles
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         group_id = mobj.group('id')
 
+        webpage = self._download_webpage(url, group_id, 'Downloading video page')
+        if re.search(r'id="emp-error" class="notinuk">', webpage):
+            raise ExtractorError('Currently BBC iPlayer TV programmes are available to play in the UK only',
+                expected=True)
+
         playlist = self._download_xml('http://www.bbc.co.uk/iplayer/playlist/%s' % group_id, group_id,
             'Downloading playlist XML')
 
-        item = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}item')
-        if item is None:
-            no_items = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}noItems')
-            if no_items is not None:
-                reason = no_items.get('reason')
-                if reason == 'preAvailability':
-                    msg = 'Episode %s is not yet available' % group_id
-                elif reason == 'postAvailability':
-                    msg = 'Episode %s is no longer available' % group_id
-                else:
-                    msg = 'Episode %s is not available: %s' % (group_id, reason)
-                raise ExtractorError(msg, expected=True)
-            raise ExtractorError('Failed to extract media for episode %s' % group_id, expected=True)
-
-        title = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}title').text
-        description = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}summary').text
-
-        radio_programme_id = item.get('identifier')
-        duration = int(item.get('duration'))
-
-        media_selection = self._download_xml(
-            'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s'  % radio_programme_id,
-            radio_programme_id, 'Downloading media selection XML')
+        no_items = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}noItems')
+        if no_items is not None:
+            reason = no_items.get('reason')
+            if reason == 'preAvailability':
+                msg = 'Episode %s is not yet available' % group_id
+            elif reason == 'postAvailability':
+                msg = 'Episode %s is no longer available' % group_id
+            else:
+                msg = 'Episode %s is not available: %s' % (group_id, reason)
+            raise ExtractorError(msg, expected=True)
 
         formats = []
-        for media in media_selection.findall('./{http://bbc.co.uk/2008/mp/mediaselection}media'):
-            bitrate = int(media.get('bitrate'))
-            encoding = media.get('encoding')
-            service = media.get('service')
-            connection = media.find('./{http://bbc.co.uk/2008/mp/mediaselection}connection')
-            protocol = connection.get('protocol')
-            priority = connection.get('priority')
-            supplier = connection.get('supplier')
-            if protocol == 'http':
-                href = connection.get('href')
-                # ASX playlist
-                if supplier == 'asx':
-                    asx = self._download_xml(href, radio_programme_id, 'Downloading %s ASX playlist' % service)
-                    for i, ref in enumerate(asx.findall('./Entry/ref')):
-                        formats.append({
-                            'url': ref.get('href'),
-                            'format_id': '%s_ref%s' % (service, i),
-                            'abr': bitrate,
-                            'acodec': encoding,
-                            'preference': priority,
-                        })
-                    continue
-                # Direct link
-                formats.append({
-                    'url': href,
-                    'format_id': service,
-                    'abr': bitrate,
-                    'acodec': encoding,
-                    'preference': priority,
-                })
-            elif protocol == 'rtmp':
-                application = connection.get('application', 'ondemand')
-                auth_string = connection.get('authString')
-                identifier = connection.get('identifier')
-                server = connection.get('server')
-                formats.append({
-                    'url': '%s://%s/%s?%s' % (protocol, server, application, auth_string),
-                    'play_path': identifier,
-                    'app': '%s?%s' % (application, auth_string),
-                    'rtmp_live': False,
-                    'ext': 'flv',
-                    'format_id': service,
-                    'abr': bitrate,
-                    'acodec': encoding,
-                    'preference': priority,
-                })
+        subtitles = None
+
+        for item in self._extract_items(playlist):
+            kind = item.get('kind')
+            if kind != 'programme' and kind != 'radioProgramme':
+                continue
+            title = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}title').text
+            description = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}summary').text
+
+            programme_id = item.get('identifier')
+            duration = int(item.get('duration'))
+
+            media_selection = self._download_xml(
+                'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s'  % programme_id,
+                programme_id, 'Downloading media selection XML')
+
+            for media in self._extract_medias(media_selection):
+                kind = media.get('kind')
+                if kind == 'audio':
+                    formats.extend(self._extract_audio(media, programme_id))
+                elif kind == 'video':
+                    formats.extend(self._extract_video(media, programme_id))
+                elif kind == 'captions':
+                    subtitles = self._extract_captions(media, programme_id)
+
+        if self._downloader.params.get('listsubtitles', False):
+            self._list_available_subtitles(programme_id, subtitles)
+            return
 
         self._sort_formats(formats)
 
         return {
-            'id': radio_programme_id,
+            'id': programme_id,
             'title': title,
             'description': description,
             'duration': duration,
             'formats': formats,
+            'subtitles': subtitles,
         }

youtube_dl/extractor/bloomberg.py

@@ -24,5 +24,7 @@ class BloombergIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         name = mobj.group('name')
         webpage = self._download_webpage(url, name)
-        ooyala_url = self._twitter_search_player(webpage)
-        return self.url_result(ooyala_url, OoyalaIE.ie_key())
+        embed_code = self._search_regex(
+            r'<source src="https?://[^/]+/[^/]+/[^/]+/([^/]+)', webpage,
+            'embed code')
+        return OoyalaIE._build_url_result(embed_code)

youtube_dl/extractor/br.py

@@ -0,0 +1,80 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+
+class BRIE(InfoExtractor):
+    IE_DESC = "Bayerischer Rundfunk Mediathek"
+    _VALID_URL = r"^https?://(?:www\.)?br\.de/mediathek/video/(?:sendungen/)?(?P<id>[a-z0-9\-]+)\.html$"
+    _BASE_URL = "http://www.br.de"
+
+    _TEST = {
+        "url": "http://www.br.de/mediathek/video/anselm-gruen-114.html",
+        "md5": "c4f83cf0f023ba5875aba0bf46860df2",
+        "info_dict": {
+            "id": "2c8d81c5-6fb7-4a74-88d4-e768e5856532",
+            "ext": "mp4",
+            "title": "Feiern und Verzichten",
+            "description": "Anselm Grün: Feiern und Verzichten",
+            "uploader": "BR/Birgit Baier",
+            "upload_date": "20140301"
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        display_id = mobj.group('id')
+        page = self._download_webpage(url, display_id)
+        xml_url = self._search_regex(
+            r"return BRavFramework\.register\(BRavFramework\('avPlayer_(?:[a-f0-9-]{36})'\)\.setup\({dataURL:'(/mediathek/video/[a-z0-9/~_.-]+)'}\)\);", page, "XMLURL")
+        xml = self._download_xml(self._BASE_URL + xml_url, None)
+
+        videos = [{
+            "id": xml_video.get("externalId"),
+            "title": xml_video.find("title").text,
+            "formats": self._extract_formats(xml_video.find("assets")),
+            "thumbnails": self._extract_thumbnails(xml_video.find("teaserImage/variants")),
+            "description": " ".join(xml_video.find("shareTitle").text.splitlines()),
+            "uploader": xml_video.find("author").text,
+            "upload_date": "".join(reversed(xml_video.find("broadcastDate").text.split("."))),
+            "webpage_url": xml_video.find("permalink").text,
+        } for xml_video in xml.findall("video")]
+
+        if len(videos) > 1:
+            self._downloader.report_warning(
+                'found multiple videos; please '
+                'report this with the video URL to http://yt-dl.org/bug')
+        if not videos:
+            raise ExtractorError('No video entries found')
+        return videos[0]
+
+    def _extract_formats(self, assets):
+        formats = [{
+            "url": asset.find("downloadUrl").text,
+            "ext": asset.find("mediaType").text,
+            "format_id": asset.get("type"),
+            "width": int(asset.find("frameWidth").text),
+            "height": int(asset.find("frameHeight").text),
+            "tbr": int(asset.find("bitrateVideo").text),
+            "abr": int(asset.find("bitrateAudio").text),
+            "vcodec": asset.find("codecVideo").text,
+            "container": asset.find("mediaType").text,
+            "filesize": int(asset.find("size").text),
+        } for asset in assets.findall("asset")
+            if asset.find("downloadUrl") is not None]
+
+        self._sort_formats(formats)
+        return formats
+
+    def _extract_thumbnails(self, variants):
+        thumbnails = [{
+            "url": self._BASE_URL + variant.find("url").text,
+            "width": int(variant.find("width").text),
+            "height": int(variant.find("height").text),
+        } for variant in variants.findall("variant")]
+        thumbnails.sort(key=lambda x: x["width"] * x["height"], reverse=True)
+        return thumbnails

youtube_dl/extractor/breakcom.py

@@ -1,18 +1,20 @@
+from __future__ import unicode_literals
+
 import re
 import json
 
 from .common import InfoExtractor
-from ..utils import determine_ext
 
 
 class BreakIE(InfoExtractor):
-    _VALID_URL = r'(?:http://)?(?:www\.)?break\.com/video/([^/]+)'
+    _VALID_URL = r'http://(?:www\.)?break\.com/video/([^/]+)'
     _TEST = {
-        u'url': u'http://www.break.com/video/when-girls-act-like-guys-2468056',
-        u'file': u'2468056.mp4',
-        u'md5': u'a3513fb1547fba4fb6cfac1bffc6c46b',
-        u'info_dict': {
-            u"title": u"When Girls Act Like D-Bags"
+        'url': 'http://www.break.com/video/when-girls-act-like-guys-2468056',
+        'md5': 'a3513fb1547fba4fb6cfac1bffc6c46b',
+        'info_dict': {
+            'id': '2468056',
+            'ext': 'mp4',
+            'title': 'When Girls Act Like D-Bags',
         }
     }
 
@@ -21,18 +23,17 @@ class BreakIE(InfoExtractor):
         video_id = mobj.group(1).split("-")[-1]
         embed_url = 'http://www.break.com/embed/%s' % video_id
         webpage = self._download_webpage(embed_url, video_id)
-        info_json = self._search_regex(r'var embedVars = ({.*?});', webpage,
-                                       u'info json', flags=re.DOTALL)
+        info_json = self._search_regex(r'var embedVars = ({.*})\s*?</script>',
+            webpage, 'info json', flags=re.DOTALL)
         info = json.loads(info_json)
         video_url = info['videoUri']
         m_youtube = re.search(r'(https?://www\.youtube\.com/watch\?v=.*)', video_url)
         if m_youtube is not None:
             return self.url_result(m_youtube.group(1), 'Youtube')
         final_url = video_url + '?' + info['AuthToken']
-        return [{
-            'id':        video_id,
-            'url':       final_url,
-            'ext':       determine_ext(final_url),
-            'title':     info['contentName'],
+        return {
+            'id': video_id,
+            'url': final_url,
+            'title': info['contentName'],
             'thumbnail': info['thumbUri'],
-        }]
+        }

youtube_dl/extractor/brightcove.py

@@ -17,6 +17,7 @@ from ..utils import (
 
     ExtractorError,
     unsmuggle_url,
+    unescapeHTML,
 )
 
 
@@ -139,7 +140,7 @@ class BrightcoveIE(InfoExtractor):
 
         url_m = re.search(r'<meta\s+property="og:video"\s+content="(http://c.brightcove.com/[^"]+)"', webpage)
         if url_m:
-            return [url_m.group(1)]
+            return [unescapeHTML(url_m.group(1))]
 
         matches = re.findall(
             r'''(?sx)<object

youtube_dl/extractor/canalc2.py

@@ -1,4 +1,6 @@
 # coding: utf-8
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -9,11 +11,12 @@ class Canalc2IE(InfoExtractor):
     _VALID_URL = r'http://.*?\.canalc2\.tv/video\.asp\?.*?idVideo=(?P<id>\d+)'
 
     _TEST = {
-        u'url': u'http://www.canalc2.tv/video.asp?idVideo=12163&voir=oui',
-        u'file': u'12163.mp4',
-        u'md5': u'060158428b650f896c542dfbb3d6487f',
-        u'info_dict': {
-            u'title': u'Terrasses du Numérique'
+        'url': 'http://www.canalc2.tv/video.asp?idVideo=12163&voir=oui',
+        'md5': '060158428b650f896c542dfbb3d6487f',
+        'info_dict': {
+            'id': '12163',
+            'ext': 'mp4',
+            'title': 'Terrasses du Numérique'
         }
     }
 
@@ -28,10 +31,11 @@ class Canalc2IE(InfoExtractor):
         video_url = 'http://vod-flash.u-strasbg.fr:8080/' + file_name
 
         title = self._html_search_regex(
-            r'class="evenement8">(.*?)</a>', webpage, u'title')
-        
-        return {'id': video_id,
-                'ext': 'mp4',
-                'url': video_url,
-                'title': title,
-                }
+            r'class="evenement8">(.*?)</a>', webpage, 'title')
+
+        return {
+            'id': video_id,
+            'ext': 'mp4',
+            'url': video_url,
+            'title': title,
+        }

youtube_dl/extractor/chilloutzone.py

@@ -42,7 +42,7 @@ class ChilloutzoneIE(InfoExtractor):
             'id': '85523671',
             'ext': 'mp4',
             'title': 'The Sunday Times - Icons',
-            'description': 'md5:3e5e8e839f076a637c6b9406c8f25c4c',
+            'description': 'md5:3e1c0dc6047498d6728dcdaad0891762',
             'uploader': 'Us',
             'uploader_id': 'usfilms',
             'upload_date': '20140131'

youtube_dl/extractor/cinemassacre.py

@@ -1,4 +1,5 @@
 # encoding: utf-8
+from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
@@ -8,73 +9,63 @@ from ..utils import (
 
 
 class CinemassacreIE(InfoExtractor):
-    _VALID_URL = r'(?:http://)?(?:www\.)?(?P<url>cinemassacre\.com/(?P<date_Y>[0-9]{4})/(?P<date_m>[0-9]{2})/(?P<date_d>[0-9]{2})/.+?)(?:[/?].*)?'
-    _TESTS = [{
-        u'url': u'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/',
-        u'file': u'19911.flv',
-        u'info_dict': {
-            u'upload_date': u'20121110',
-            u'title': u'“Angry Video Game Nerd: The Movie” – Trailer',
-            u'description': u'md5:fb87405fcb42a331742a0dce2708560b',
+    _VALID_URL = r'http://(?:www\.)?cinemassacre\.com/(?P<date_Y>[0-9]{4})/(?P<date_m>[0-9]{2})/(?P<date_d>[0-9]{2})/.+?'
+    _TESTS = [
+        {
+            'url': 'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/',
+            'file': '19911.mp4',
+            'md5': 'fde81fbafaee331785f58cd6c0d46190',
+            'info_dict': {
+                'upload_date': '20121110',
+                'title': '“Angry Video Game Nerd: The Movie” – Trailer',
+                'description': 'md5:fb87405fcb42a331742a0dce2708560b',
+            },
         },
-        u'params': {
-            # rtmp download
-            u'skip_download': True,
-        },
-    },
-    {
-        u'url': u'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940',
-        u'file': u'521be8ef82b16.flv',
-        u'info_dict': {
-            u'upload_date': u'20131002',
-            u'title': u'The Mummy’s Hand (1940)',
-        },
-        u'params': {
-            # rtmp download
-            u'skip_download': True,
-        },
-    }]
+        {
+            'url': 'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940',
+            'file': '521be8ef82b16.mp4',
+            'md5': 'd72f10cd39eac4215048f62ab477a511',
+            'info_dict': {
+                'upload_date': '20131002',
+                'title': 'The Mummy’s Hand (1940)',
+            },
+        }
+    ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
 
-        webpage_url = u'http://' + mobj.group('url')
-        webpage = self._download_webpage(webpage_url, None) # Don't know video id yet
+        webpage = self._download_webpage(url, None)  # Don't know video id yet
         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)
         if not mobj:
-            raise ExtractorError(u'Can\'t extract embed url and video id')
-        playerdata_url = mobj.group(u'embed_url')
-        video_id = mobj.group(u'video_id')
+            raise ExtractorError('Can\'t extract embed url and video id')
+        playerdata_url = mobj.group('embed_url')
+        video_id = mobj.group('video_id')
 
         video_title = self._html_search_regex(r'<title>(?P<title>.+?)\|',
-            webpage, u'title')
+            webpage, 'title')
         video_description = self._html_search_regex(r'<div class="entry-content">(?P<description>.+?)</div>',
-            webpage, u'description', flags=re.DOTALL, fatal=False)
+            webpage, 'description', flags=re.DOTALL, fatal=False)
         if len(video_description) == 0:
             video_description = None
 
         playerdata = self._download_webpage(playerdata_url, video_id)
-        url = self._html_search_regex(r'\'streamer\': \'(?P<url>[^\']+)\'', playerdata, u'url')
 
-        sd_file = self._html_search_regex(r'\'file\': \'(?P<sd_file>[^\']+)\'', playerdata, u'sd_file')
-        hd_file = self._html_search_regex(r'\'?file\'?: "(?P<hd_file>[^"]+)"', playerdata, u'hd_file')
-        video_thumbnail = self._html_search_regex(r'\'image\': \'(?P<thumbnail>[^\']+)\'', playerdata, u'thumbnail', fatal=False)
+        sd_url = self._html_search_regex(r'file: \'(?P<sd_file>[^\']+)\', label: \'SD\'', playerdata, 'sd_file')
+        hd_url = self._html_search_regex(r'file: \'(?P<hd_file>[^\']+)\', label: \'HD\'', playerdata, 'hd_file')
+        video_thumbnail = self._html_search_regex(r'image: \'(?P<thumbnail>[^\']+)\'', playerdata, 'thumbnail', fatal=False)
 
         formats = [
             {
-                'url': url,
-                'play_path': 'mp4:' + sd_file,
-                'rtmp_live': True, # workaround
-                'ext': 'flv',
+                'url': sd_url,
+                'ext': 'mp4',
                 'format': 'sd',
                 'format_id': 'sd',
             },
             {
-                'url': url,
-                'play_path': 'mp4:' + hd_file,
-                'rtmp_live': True, # workaround
-                'ext': 'flv',
+                'url': hd_url,
+                'ext': 'mp4',
                 'format': 'hd',
                 'format_id': 'hd',
             },

youtube_dl/extractor/cnn.py

@@ -6,6 +6,7 @@ from .common import InfoExtractor
 from ..utils import (
     int_or_none,
     parse_duration,
+    url_basename,
 )
 
 
@@ -98,3 +99,28 @@ class CNNIE(InfoExtractor):
             'duration': duration,
             'upload_date': upload_date,
         }
+
+
+class CNNBlogsIE(InfoExtractor):
+    _VALID_URL = r'https?://[^\.]+\.blogs\.cnn\.com/.+'
+    _TEST = {
+        'url': 'http://reliablesources.blogs.cnn.com/2014/02/09/criminalizing-journalism/',
+        'md5': '3e56f97b0b6ffb4b79f4ea0749551084',
+        'info_dict': {
+            'id': 'bestoftv/2014/02/09/criminalizing-journalism.cnn',
+            'ext': 'mp4',
+            'title': 'Criminalizing journalism?',
+            'description': 'Glenn Greenwald responds to comments made this week on Capitol Hill that journalists could be criminal accessories.',
+            'upload_date': '20140209',
+        },
+        'add_ie': ['CNN'],
+    }
+
+    def _real_extract(self, url):
+        webpage = self._download_webpage(url, url_basename(url))
+        cnn_url = self._html_search_regex(r'data-url="(.+?)"', webpage, 'cnn url')
+        return {
+            '_type': 'url',
+            'url': cnn_url,
+            'ie_key': CNNIE.ie_key(),
+        }

youtube_dl/extractor/collegehumor.py

@@ -42,7 +42,7 @@ class CollegeHumorIE(InfoExtractor):
             'title': 'Funny Dogs Protecting Babies Compilation 2014 [NEW HD]',
             'uploader': 'Funnyplox TV',
             'uploader_id': 'funnyploxtv',
-            'description': 'md5:11812366244110c3523968aa74f02521',
+            'description': 'md5:7ded37421526d54afdf005e25bc2b7a3',
             'upload_date': '20140128',
         },
         'params': {

youtube_dl/extractor/common.py

@@ -271,8 +271,11 @@ class InfoExtractor(object):
 
     def _download_json(self, url_or_request, video_id,
                        note=u'Downloading JSON metadata',
-                       errnote=u'Unable to download JSON metadata'):
+                       errnote=u'Unable to download JSON metadata',
+                       transform_source=None):
         json_string = self._download_webpage(url_or_request, video_id, note, errnote)
+        if transform_source:
+            json_string = transform_source(json_string)
         try:
             return json.loads(json_string)
         except ValueError as ve:

youtube_dl/extractor/crunchyroll.py

@@ -1,7 +1,11 @@
 # encoding: utf-8
 from __future__ import unicode_literals
 
-import re, base64, zlib
+import re
+import json
+import base64
+import zlib
+
 from hashlib import sha1
 from math import pow, sqrt, floor
 from .common import InfoExtractor
@@ -19,13 +23,15 @@ from ..aes import (
     inc,
 )
 
+
 class CrunchyrollIE(InfoExtractor):
-    _VALID_URL = r'(?:https?://)?(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?:[^/]*/[^/?&]*?|media/\?id=)(?P<video_id>[0-9]+))(?:[/?&]|$)'
-    _TESTS = [{
+    _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?:[^/]*/[^/?&]*?|media/\?id=)(?P<video_id>[0-9]+))(?:[/?&]|$)'
+    _TEST = {
         'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
-        'file': '645513.flv',
         #'md5': 'b1639fd6ddfaa43788c85f6d1dddd412',
         'info_dict': {
+            'id': '645513',
+            'ext': 'flv',
             'title': 'Wanna be the Strongest in the World Episode 1 – An Idol-Wrestler is Born!',
             'description': 'md5:2d17137920c64f2f49981a7797d275ef',
             'thumbnail': 'http://img1.ak.crunchyroll.com/i/spire1-tmb/20c6b5e10f1a47b10516877d3c039cae1380951166_full.jpg',
@@ -36,7 +42,7 @@ class CrunchyrollIE(InfoExtractor):
             # rtmp
             'skip_download': True,
         },
-    }]
+    }
 
     _FORMAT_IDS = {
         '360': ('60', '106'),
@@ -68,7 +74,7 @@ class CrunchyrollIE(InfoExtractor):
             shaHash = bytes_to_intlist(sha1(prefix + str(num4).encode('ascii')).digest())
             # Extend 160 Bit hash to 256 Bit
             return shaHash + [0] * 12
-        
+
         key = obfuscate_key(id)
         class Counter:
             __value = iv
@@ -80,9 +86,8 @@ class CrunchyrollIE(InfoExtractor):
         return zlib.decompress(decrypted_data)
 
     def _convert_subtitles_to_srt(self, subtitles):
-        i=1
         output = ''
-        for start, end, text in re.findall(r'<event [^>]*?start="([^"]+)" [^>]*?end="([^"]+)" [^>]*?text="([^"]+)"[^>]*?>', subtitles):
+        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)
@@ -90,7 +95,6 @@ class CrunchyrollIE(InfoExtractor):
             if not text:
                 continue
             output += '%d\n%s --> %s\n%s\n\n' % (i, start, end, text)
-            i+=1
         return output
 
     def _real_extract(self,url):
@@ -108,6 +112,12 @@ class CrunchyrollIE(InfoExtractor):
         if note_m:
             raise ExtractorError(note_m)
 
+        mobj = re.search(r'Page\.messaging_box_controller\.addItems\(\[(?P<msg>{.+?})\]\)', webpage)
+        if mobj:
+            msg = json.loads(mobj.group('msg'))
+            if msg.get('type') == 'error':
+                raise ExtractorError('crunchyroll returned error: %s' % msg['message_body'], expected=True)
+
         video_title = self._html_search_regex(r'<h1[^>]*>(.+?)</h1>', webpage, 'video_title', flags=re.DOTALL)
         video_title = re.sub(r' {2,}', ' ', video_title)
         video_description = self._html_search_regex(r'"description":"([^"]+)', webpage, 'video_description', default='')
@@ -123,7 +133,7 @@ class CrunchyrollIE(InfoExtractor):
         playerdata_req.data = compat_urllib_parse.urlencode({'current_page': webpage_url})
         playerdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
         playerdata = self._download_webpage(playerdata_req, video_id, note='Downloading media info')
-        
+
         stream_id = self._search_regex(r'<media_id>([^<]+)', playerdata, 'stream_id')
         video_thumbnail = self._search_regex(r'<episode_image_url>([^<]+)', playerdata, 'thumbnail', fatal=False)
 
@@ -161,7 +171,7 @@ class CrunchyrollIE(InfoExtractor):
             data = base64.b64decode(data)
 
             subtitle = self._decrypt_subtitles(data, iv, id).decode('utf-8')
-            lang_code = self._search_regex(r'lang_code=\'([^\']+)', subtitle, 'subtitle_lang_code', fatal=False)
+            lang_code = self._search_regex(r'lang_code=["\']([^"\']+)', subtitle, 'subtitle_lang_code', fatal=False)
             if not lang_code:
                 continue
             subtitles[lang_code] = self._convert_subtitles_to_srt(subtitle)

youtube_dl/extractor/dotsub.py

@@ -1,41 +1,42 @@
+from __future__ import unicode_literals
+
 import re
-import json
 import time
 
 from .common import InfoExtractor
 
 
 class DotsubIE(InfoExtractor):
-    _VALID_URL = r'(?:http://)?(?:www\.)?dotsub\.com/view/([^/]+)'
+    _VALID_URL = r'http://(?:www\.)?dotsub\.com/view/(?P<id>[^/]+)'
     _TEST = {
-        u'url': u'http://dotsub.com/view/aed3b8b2-1889-4df5-ae63-ad85f5572f27',
-        u'file': u'aed3b8b2-1889-4df5-ae63-ad85f5572f27.flv',
-        u'md5': u'0914d4d69605090f623b7ac329fea66e',
-        u'info_dict': {
-            u"title": u"Pyramids of Waste (2010), AKA The Lightbulb Conspiracy - Planned obsolescence documentary",
-            u"uploader": u"4v4l0n42",
-            u'description': u'Pyramids of Waste (2010) also known as "The lightbulb conspiracy" is a documentary about how our economic system based on consumerism  and planned obsolescence is breaking our planet down.\r\n\r\nSolutions to this can be found at:\r\nhttp://robotswillstealyourjob.com\r\nhttp://www.federicopistono.org\r\n\r\nhttp://opensourceecology.org\r\nhttp://thezeitgeistmovement.com',
-            u'thumbnail': u'http://dotsub.com/media/aed3b8b2-1889-4df5-ae63-ad85f5572f27/p',
-            u'upload_date': u'20101213',
+        'url': 'http://dotsub.com/view/aed3b8b2-1889-4df5-ae63-ad85f5572f27',
+        'md5': '0914d4d69605090f623b7ac329fea66e',
+        'info_dict': {
+            'id': 'aed3b8b2-1889-4df5-ae63-ad85f5572f27',
+            'ext': 'flv',
+            'title': 'Pyramids of Waste (2010), AKA The Lightbulb Conspiracy - Planned obsolescence documentary',
+            'uploader': '4v4l0n42',
+            'description': 'Pyramids of Waste (2010) also known as "The lightbulb conspiracy" is a documentary about how our economic system based on consumerism  and planned obsolescence is breaking our planet down.\r\n\r\nSolutions to this can be found at:\r\nhttp://robotswillstealyourjob.com\r\nhttp://www.federicopistono.org\r\n\r\nhttp://opensourceecology.org\r\nhttp://thezeitgeistmovement.com',
+            'thumbnail': 'http://dotsub.com/media/aed3b8b2-1889-4df5-ae63-ad85f5572f27/p',
+            'upload_date': '20101213',
         }
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group(1)
-        info_url = "https://dotsub.com/api/media/%s/metadata" %(video_id)
-        webpage = self._download_webpage(info_url, video_id)
-        info = json.loads(webpage)
+        video_id = mobj.group('id')
+        info_url = "https://dotsub.com/api/media/%s/metadata" % video_id
+        info = self._download_json(info_url, video_id)
         date = time.gmtime(info['dateCreated']/1000) # The timestamp is in miliseconds
 
-        return [{
-            'id':          video_id,
-            'url':         info['mediaURI'],
-            'ext':         'flv',
-            'title':       info['title'],
-            'thumbnail':   info['screenshotURI'],
+        return {
+            'id': video_id,
+            'url': info['mediaURI'],
+            'ext': 'flv',
+            'title': info['title'],
+            'thumbnail': info['screenshotURI'],
             'description': info['description'],
-            'uploader':    info['user'],
-            'view_count':  info['numberOfViews'],
-            'upload_date': u'%04i%02i%02i' % (date.tm_year, date.tm_mon, date.tm_mday),
-        }]
+            'uploader': info['user'],
+            'view_count': info['numberOfViews'],
+            'upload_date': '%04i%02i%02i' % (date.tm_year, date.tm_mon, date.tm_mday),
+        }

youtube_dl/extractor/dropbox.py

@@ -10,11 +10,12 @@ from .common import InfoExtractor
 class DropboxIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?dropbox[.]com/s/(?P<id>[a-zA-Z0-9]{15})/(?P<title>[^?#]*)'
     _TEST = {
-        'url': 'https://www.dropbox.com/s/mcnzehi9wo55th4/20131219_085616.mp4',
-        'file': 'mcnzehi9wo55th4.mp4',
-        'md5': 'f6d65b1b326e82fd7ab7720bea3dacae',
+        'url': 'https://www.dropbox.com/s/0qr9sai2veej4f8/THE_DOCTOR_GAMES.mp4',
+        'md5': '8ae17c51172fb7f93bdd6a214cc8c896',
         'info_dict': {
-            'title': '20131219_085616'
+            'id': '0qr9sai2veej4f8',
+            'ext': 'mp4',
+            'title': 'THE_DOCTOR_GAMES'
         }
     }
 

youtube_dl/extractor/escapist.py

@@ -1,9 +1,9 @@
-import json
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
 from ..utils import (
-    compat_str,
     compat_urllib_parse,
 
     ExtractorError,
@@ -11,70 +11,68 @@ from ..utils import (
 
 
 class EscapistIE(InfoExtractor):
-    _VALID_URL = r'^https?://?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$'
+    _VALID_URL = r'^https?://?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<id>[0-9]+)-'
     _TEST = {
-        u'url': u'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate',
-        u'file': u'6618-Breaking-Down-Baldurs-Gate.mp4',
-        u'md5': u'ab3a706c681efca53f0a35f1415cf0d1',
-        u'info_dict': {
-            u"description": u"Baldur's Gate: Original, Modded or Enhanced Edition? I'll break down what you can expect from the new Baldur's Gate: Enhanced Edition.", 
-            u"uploader": u"the-escapist-presents", 
-            u"title": u"Breaking Down Baldur's Gate"
+        'url': 'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate',
+        'md5': 'ab3a706c681efca53f0a35f1415cf0d1',
+        'info_dict': {
+            'id': '6618',
+            'ext': 'mp4',
+            'description': "Baldur's Gate: Original, Modded or Enhanced Edition? I'll break down what you can expect from the new Baldur's Gate: Enhanced Edition.",
+            'uploader': 'the-escapist-presents',
+            'title': "Breaking Down Baldur's Gate",
         }
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         showName = mobj.group('showname')
-        videoId = mobj.group('episode')
+        video_id = mobj.group('id')
 
-        self.report_extraction(videoId)
-        webpage = self._download_webpage(url, videoId)
+        self.report_extraction(video_id)
+        webpage = self._download_webpage(url, video_id)
 
         videoDesc = self._html_search_regex(
             r'<meta name="description" content="([^"]*)"',
-            webpage, u'description', fatal=False)
+            webpage, 'description', fatal=False)
 
         playerUrl = self._og_search_video_url(webpage, name=u'player URL')
 
         title = self._html_search_regex(
             r'<meta name="title" content="([^"]*)"',
-            webpage, u'title').split(' : ')[-1]
+            webpage, 'title').split(' : ')[-1]
 
-        configUrl = self._search_regex('config=(.*)$', playerUrl, u'config URL')
+        configUrl = self._search_regex('config=(.*)$', playerUrl, 'config URL')
         configUrl = compat_urllib_parse.unquote(configUrl)
 
         formats = []
 
-        def _add_format(name, cfgurl):
-            configJSON = self._download_webpage(
-                cfgurl, videoId,
-                u'Downloading ' + name + ' configuration',
-                u'Unable to download ' + name + ' configuration')
+        def _add_format(name, cfgurl, quality):
+            config = self._download_json(
+                cfgurl, video_id,
+                'Downloading ' + name + ' configuration',
+                'Unable to download ' + name + ' configuration',
+                transform_source=lambda s: s.replace("'", '"'))
 
-            # Technically, it's JavaScript, not JSON
-            configJSON = configJSON.replace("'", '"')
-
-            try:
-                config = json.loads(configJSON)
-            except (ValueError,) as err:
-                raise ExtractorError(u'Invalid JSON in configuration file: ' + compat_str(err))
             playlist = config['playlist']
             formats.append({
                 'url': playlist[1]['url'],
                 'format_id': name,
+                'quality': quality,
             })
 
-        _add_format(u'normal', configUrl)
+        _add_format('normal', configUrl, quality=0)
         hq_url = (configUrl +
                   ('&hq=1' if '?' in configUrl else configUrl + '?hq=1'))
         try:
-            _add_format(u'hq', hq_url)
+            _add_format('hq', hq_url, quality=1)
         except ExtractorError:
             pass  # That's fine, we'll just use normal quality
 
+        self._sort_formats(formats)
+
         return {
-            'id': videoId,
+            'id': video_id,
             'formats': formats,
             'uploader': showName,
             'title': title,

youtube_dl/extractor/exfm.py

@@ -1,56 +1,58 @@
+from __future__ import unicode_literals
+
 import re
-import json
 
 from .common import InfoExtractor
 
 
 class ExfmIE(InfoExtractor):
-    IE_NAME = u'exfm'
-    IE_DESC = u'ex.fm'
-    _VALID_URL = r'(?:http://)?(?:www\.)?ex\.fm/song/([^/]+)'
-    _SOUNDCLOUD_URL = r'(?:http://)?(?:www\.)?api\.soundcloud\.com/tracks/([^/]+)/stream'
+    IE_NAME = 'exfm'
+    IE_DESC = 'ex.fm'
+    _VALID_URL = r'http://(?:www\.)?ex\.fm/song/(?P<id>[^/]+)'
+    _SOUNDCLOUD_URL = r'http://(?:www\.)?api\.soundcloud\.com/tracks/([^/]+)/stream'
     _TESTS = [
         {
-            u'url': u'http://ex.fm/song/eh359',
-            u'file': u'44216187.mp3',
-            u'md5': u'e45513df5631e6d760970b14cc0c11e7',
-            u'info_dict': {
-                u"title": u"Test House \"Love Is Not Enough\" (Extended Mix) DeadJournalist Exclusive",
-                u"uploader": u"deadjournalist",
-                u'upload_date': u'20120424',
-                u'description': u'Test House \"Love Is Not Enough\" (Extended Mix) DeadJournalist Exclusive',
+            'url': 'http://ex.fm/song/eh359',
+            'md5': 'e45513df5631e6d760970b14cc0c11e7',
+            'info_dict': {
+                'id': '44216187',
+                'ext': 'mp3',
+                'title': 'Test House "Love Is Not Enough" (Extended Mix) DeadJournalist Exclusive',
+                'uploader': 'deadjournalist',
+                'upload_date': '20120424',
+                'description': 'Test House \"Love Is Not Enough\" (Extended Mix) DeadJournalist Exclusive',
             },
-            u'note': u'Soundcloud song',
-            u'skip': u'The site is down too often',
+            'note': 'Soundcloud song',
+            'skip': 'The site is down too often',
         },
         {
-            u'url': u'http://ex.fm/song/wddt8',
-            u'file': u'wddt8.mp3',
-            u'md5': u'966bd70741ac5b8570d8e45bfaed3643',
-            u'info_dict': {
-                u'title': u'Safe and Sound',
-                u'uploader': u'Capital Cities',
+            'url': 'http://ex.fm/song/wddt8',
+            'md5': '966bd70741ac5b8570d8e45bfaed3643',
+            'info_dict': {
+                'id': 'wddt8',
+                'ext': 'mp3',
+                'title': 'Safe and Sound',
+                'uploader': 'Capital Cities',
             },
-            u'skip': u'The site is down too often',
+            'skip': 'The site is down too often',
         },
     ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        song_id = mobj.group(1)
-        info_url = "http://ex.fm/api/v3/song/%s" %(song_id)
-        webpage = self._download_webpage(info_url, song_id)
-        info = json.loads(webpage)
-        song_url = info['song']['url']
+        song_id = mobj.group('id')
+        info_url = "http://ex.fm/api/v3/song/%s" % song_id
+        info = self._download_json(info_url, song_id)['song']
+        song_url = info['url']
         if re.match(self._SOUNDCLOUD_URL, song_url) is not None:
             self.to_screen('Soundcloud song detected')
-            return self.url_result(song_url.replace('/stream',''), 'Soundcloud')
-        return [{
-            'id':          song_id,
-            'url':         song_url,
-            'ext':         'mp3',
-            'title':       info['song']['title'],
-            'thumbnail':   info['song']['image']['large'],
-            'uploader':    info['song']['artist'],
-            'view_count':  info['song']['loved_count'],
-        }]
+            return self.url_result(song_url.replace('/stream', ''), 'Soundcloud')
+        return {
+            'id': song_id,
+            'url': song_url,
+            'ext': 'mp3',
+            'title': info['title'],
+            'thumbnail': info['image']['large'],
+            'uploader': info['artist'],
+            'view_count': info['loved_count'],
+        }

youtube_dl/extractor/firsttv.py

@@ -0,0 +1,60 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import int_or_none
+
+
+class FirstTVIE(InfoExtractor):
+    IE_NAME = 'firsttv'
+    IE_DESC = 'Видеоархив - Первый канал'
+    _VALID_URL = r'http://(?:www\.)?1tv\.ru/videoarchive/(?P<id>\d+)'
+
+    _TEST = {
+        'url': 'http://www.1tv.ru/videoarchive/73390',
+        'md5': '3de6390cf0cca4a5eae1d1d83895e5ad',
+        'info_dict': {
+            'id': '73390',
+            'ext': 'mp4',
+            'title': 'Олимпийские канатные дороги',
+            'description': 'md5:cc730d2bf4215463e37fff6a1e277b13',
+            'thumbnail': 'http://img1.1tv.ru/imgsize640x360/PR20140210114657.JPG',
+            'duration': 149,
+        },
+        'skip': 'Only works from Russia',
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id, 'Downloading page')
+
+        video_url = self._html_search_regex(
+            r'''(?s)jwplayer\('flashvideoportal_1'\)\.setup\({.*?'file': '([^']+)'.*?}\);''', webpage, 'video URL')
+
+        title = self._html_search_regex(
+            r'<div class="tv_translation">\s*<h1><a href="[^"]+">([^<]*)</a>', webpage, 'title')
+        description = self._html_search_regex(
+            r'<div class="descr">\s*<div>&nbsp;</div>\s*<p>([^<]*)</p></div>', webpage, 'description', fatal=False)
+
+        thumbnail = self._og_search_thumbnail(webpage)
+        duration = self._og_search_property('video:duration', webpage, 'video duration', fatal=False)
+
+        like_count = self._html_search_regex(r'title="Понравилось".*?/></label> \[(\d+)\]',
+            webpage, 'like count', fatal=False)
+        dislike_count = self._html_search_regex(r'title="Не понравилось".*?/></label> \[(\d+)\]',
+            webpage, 'dislike count', fatal=False)
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'thumbnail': thumbnail,
+            'title': title,
+            'description': description,
+            'duration': int_or_none(duration),
+            'like_count': int_or_none(like_count),
+            'dislike_count': int_or_none(dislike_count),
+        }

youtube_dl/extractor/fourtube.py

@@ -0,0 +1,95 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_request,
+    unified_strdate,
+    str_to_int,
+    parse_duration,
+)
+from youtube_dl.utils import clean_html
+
+
+class FourTubeIE(InfoExtractor):
+    IE_NAME = '4tube'
+    _VALID_URL = r'https?://(?:www\.)?4tube\.com/videos/(?P<id>\d+)'
+
+    _TEST = {
+        'url': 'http://www.4tube.com/videos/209733/hot-babe-holly-michaels-gets-her-ass-stuffed-by-black',
+        'md5': '6516c8ac63b03de06bc8eac14362db4f',
+        'info_dict': {
+            'id': '209733',
+            'ext': 'mp4',
+            'title': 'Hot Babe Holly Michaels gets her ass stuffed by black',
+            'uploader': 'WCP Club',
+            'uploader_id': 'wcp-club',
+            'upload_date': '20131031',
+            'duration': 583,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+
+        video_id = mobj.group('id')
+        webpage_url = 'http://www.4tube.com/videos/' + video_id
+        webpage = self._download_webpage(webpage_url, video_id)
+
+        self.report_extraction(video_id)
+
+        playlist_json = self._html_search_regex(r'var playerConfigPlaylist\s+=\s+([^;]+)', webpage, 'Playlist')
+        media_id = self._search_regex(r'idMedia:\s*(\d+)', playlist_json, 'Media Id')
+        sources = self._search_regex(r'sources:\s*\[([^\]]*)\]', playlist_json, 'Sources').split(',')
+        title = self._search_regex(r'title:\s*"([^"]*)', playlist_json, 'Title')
+        thumbnail_url = self._search_regex(r'image:\s*"([^"]*)', playlist_json, 'Thumbnail', fatal=False)
+
+        uploader_str = self._search_regex(r'<span>Uploaded by</span>(.*?)<span>', webpage, 'uploader', fatal=False)
+        mobj = re.search(r'<a href="/sites/(?P<id>[^"]+)"><strong>(?P<name>[^<]+)</strong></a>', uploader_str)
+        (uploader, uploader_id) = (mobj.group('name'), mobj.group('id')) if mobj else (clean_html(uploader_str), None)
+
+        upload_date = None
+        view_count = None
+        duration = None
+        description = self._html_search_meta('description', webpage, 'description')
+        if description:
+            upload_date = self._search_regex(r'Published Date: (\d{2} [a-zA-Z]{3} \d{4})', description, 'upload date',
+                fatal=False)
+            if upload_date:
+                upload_date = unified_strdate(upload_date)
+            view_count = self._search_regex(r'Views: ([\d,\.]+)', description, 'view count', fatal=False)
+            if view_count:
+                view_count = str_to_int(view_count)
+            duration = parse_duration(self._search_regex(r'Length: (\d+m\d+s)', description, 'duration', fatal=False))
+
+        token_url = "http://tkn.4tube.com/{0}/desktop/{1}".format(media_id, "+".join(sources))
+        headers = {
+                b'Content-Type': b'application/x-www-form-urlencoded',
+                b'Origin': b'http://www.4tube.com',
+                }
+        token_req = compat_urllib_request.Request(token_url, b'{}', headers)
+        tokens = self._download_json(token_req, video_id)
+
+        formats = [{
+            'url': tokens[format]['token'],
+            'format_id': format + 'p',
+            'resolution': format + 'p',
+            'quality': int(format),
+            } for format in sources]
+
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'thumbnail': thumbnail_url,
+            'uploader': uploader,
+            'uploader_id': uploader_id,
+            'upload_date': upload_date,
+            'view_count': view_count,
+            'duration': duration,
+            'age_limit': 18,
+            'webpage_url': webpage_url,
+        }

youtube_dl/extractor/francetv.py

@@ -184,6 +184,7 @@ class GenerationQuoiIE(InfoExtractor):
             # It uses Dailymotion
             'skip_download': True,
         },
+        'skip': 'Only available from France',
     }
 
     def _real_extract(self, url):

youtube_dl/extractor/freesound.py

@@ -1,18 +1,21 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
-from ..utils import determine_ext
+
 
 class FreesoundIE(InfoExtractor):
-    _VALID_URL = r'(?:https?://)?(?:www\.)?freesound\.org/people/([^/]+)/sounds/(?P<id>[^/]+)'
+    _VALID_URL = r'https?://(?:www\.)?freesound\.org/people/([^/]+)/sounds/(?P<id>[^/]+)'
     _TEST = {
-        u'url': u'http://www.freesound.org/people/miklovan/sounds/194503/',
-        u'file': u'194503.mp3',
-        u'md5': u'12280ceb42c81f19a515c745eae07650',
-        u'info_dict': {
-            u"title": u"gulls in the city.wav",
-            u"uploader" : u"miklovan",
-            u'description': u'the sounds of seagulls in the city',
+        'url': 'http://www.freesound.org/people/miklovan/sounds/194503/',
+        'md5': '12280ceb42c81f19a515c745eae07650',
+        'info_dict': {
+            'id': '194503',
+            'ext': 'mp3',
+            'title': 'gulls in the city.wav',
+            'uploader': 'miklovan',
+            'description': 'the sounds of seagulls in the city',
         }
     }
 
@@ -20,17 +23,17 @@ class FreesoundIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         music_id = mobj.group('id')
         webpage = self._download_webpage(url, music_id)
-        title = self._html_search_regex(r'<div id="single_sample_header">.*?<a href="#">(.+?)</a>',
-                                webpage, 'music title', flags=re.DOTALL)
-        music_url = self._og_search_property('audio', webpage, 'music url')
-        description = self._html_search_regex(r'<div id="sound_description">(.*?)</div>',
-                                webpage, 'description', fatal=False, flags=re.DOTALL)
+        title = self._html_search_regex(
+            r'<div id="single_sample_header">.*?<a href="#">(.+?)</a>',
+            webpage, 'music title', flags=re.DOTALL)
+        description = self._html_search_regex(
+            r'<div id="sound_description">(.*?)</div>', webpage, 'description',
+            fatal=False, flags=re.DOTALL)
 
-        return [{
-            'id':       music_id,
-            'title':    title,            
-            'url':      music_url,
+        return {
+            'id': music_id,
+            'title': title,
+            'url': self._og_search_property('audio', webpage, 'music url'),
             'uploader': self._og_search_property('audio:artist', webpage, 'music uploader'),
-            'ext':      determine_ext(music_url),
             'description': description,
-        }]
+        }

youtube_dl/extractor/gametrailers.py

@@ -7,10 +7,11 @@ class GametrailersIE(MTVServicesInfoExtractor):
     _VALID_URL = r'http://www\.gametrailers\.com/(?P<type>videos|reviews|full-episodes)/(?P<id>.*?)/(?P<title>.*)'
     _TEST = {
         'url': 'http://www.gametrailers.com/videos/zbvr8i/mirror-s-edge-2-e3-2013--debut-trailer',
-        'file': '70e9a5d7-cf25-4a10-9104-6f3e7342ae0d.mp4',
         'md5': '4c8e67681a0ea7ec241e8c09b3ea8cf7',
         'info_dict': {
-            'title': 'Mirror\'s Edge 2|E3 2013: Debut Trailer',
+            'id': '70e9a5d7-cf25-4a10-9104-6f3e7342ae0d',
+            'ext': 'mp4',
+            'title': 'E3 2013: Debut Trailer',
             'description': 'Faith is back!  Check out the World Premiere trailer for Mirror\'s Edge 2 straight from the EA Press Conference at E3 2013!',
         },
     }

youtube_dl/extractor/generic.py

@@ -4,6 +4,7 @@ from __future__ import unicode_literals
 
 import os
 import re
+import xml.etree.ElementTree
 
 from .common import InfoExtractor
 from .youtube import YoutubeIE
@@ -12,6 +13,7 @@ from ..utils import (
     compat_urllib_parse,
     compat_urllib_request,
     compat_urlparse,
+    compat_xml_parse_error,
 
     ExtractorError,
     HEADRequest,
@@ -159,6 +161,25 @@ class GenericIE(InfoExtractor):
             raise ExtractorError('Invalid URL protocol')
         return response
 
+    def _extract_rss(self, url, video_id, doc):
+        playlist_title = doc.find('./channel/title').text
+        playlist_desc_el = doc.find('./channel/description')
+        playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
+
+        entries = [{
+            '_type': 'url',
+            'url': e.find('link').text,
+            'title': e.find('title').text,
+        } for e in doc.findall('./channel/item')]
+
+        return {
+            '_type': 'playlist',
+            'id': url,
+            'title': playlist_title,
+            'description': playlist_desc,
+            'entries': entries,
+        }
+
     def _real_extract(self, url):
         parsed_url = compat_urlparse.urlparse(url)
         if not parsed_url.scheme:
@@ -219,6 +240,14 @@ class GenericIE(InfoExtractor):
 
         self.report_extraction(video_id)
 
+        # Is it an RSS feed?
+        try:
+            doc = xml.etree.ElementTree.fromstring(webpage.encode('utf-8'))
+            if doc.tag == 'rss':
+                return self._extract_rss(url, video_id, doc)
+        except compat_xml_parse_error:
+            pass
+
         # it's tempting to parse this further, but you would
         # have to take into account all the variations like
         #   Video Title - Site Name
@@ -334,11 +363,17 @@ class GenericIE(InfoExtractor):
         if mobj is not None:
             return self.url_result(mobj.group(1), 'Mpora')
 
-        # Look for embedded Novamov player
+        # Look for embedded NovaMov player
         mobj = re.search(
             r'<iframe[^>]+?src=(["\'])(?P<url>http://(?:(?:embed|www)\.)?novamov\.com/embed\.php.+?)\1', webpage)
         if mobj is not None:
-            return self.url_result(mobj.group('url'), 'Novamov')
+            return self.url_result(mobj.group('url'), 'NovaMov')
+
+        # Look for embedded NowVideo player
+        mobj = re.search(
+            r'<iframe[^>]+?src=(["\'])(?P<url>http://(?:(?:embed|www)\.)?nowvideo\.(?:ch|sx|eu)/embed\.php.+?)\1', webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'), 'NowVideo')
 
         # Look for embedded Facebook player
         mobj = re.search(

youtube_dl/extractor/googleplus.py

@@ -1,4 +1,5 @@
 # coding: utf-8
+from __future__ import unicode_literals
 
 import datetime
 import re
@@ -10,32 +11,28 @@ from ..utils import (
 
 
 class GooglePlusIE(InfoExtractor):
-    IE_DESC = u'Google Plus'
-    _VALID_URL = r'(?:https://)?plus\.google\.com/(?:[^/]+/)*?posts/(\w+)'
-    IE_NAME = u'plus.google'
+    IE_DESC = 'Google Plus'
+    _VALID_URL = r'https://plus\.google\.com/(?:[^/]+/)*?posts/(?P<id>\w+)'
+    IE_NAME = 'plus.google'
     _TEST = {
-        u"url": u"https://plus.google.com/u/0/108897254135232129896/posts/ZButuJc6CtH",
-        u"file": u"ZButuJc6CtH.flv",
-        u"info_dict": {
-            u"upload_date": u"20120613",
-            u"uploader": u"井上ヨシマサ",
-            u"title": u"嘆きの天使 降臨"
+        'url': 'https://plus.google.com/u/0/108897254135232129896/posts/ZButuJc6CtH',
+        'info_dict': {
+            'id': 'ZButuJc6CtH',
+            'ext': 'flv',
+            'upload_date': '20120613',
+            'uploader': '井上ヨシマサ',
+            'title': '嘆きの天使 降臨',
         }
     }
 
     def _real_extract(self, url):
         # Extract id from URL
         mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError(u'Invalid URL: %s' % url)
 
-        post_url = mobj.group(0)
-        video_id = mobj.group(1)
-
-        video_extension = 'flv'
+        video_id = mobj.group('id')
 
         # Step 1, Retrieve post webpage to extract further information
-        webpage = self._download_webpage(post_url, video_id, u'Downloading entry webpage')
+        webpage = self._download_webpage(url, video_id, 'Downloading entry webpage')
 
         self.report_extraction(video_id)
 
@@ -43,7 +40,7 @@ class GooglePlusIE(InfoExtractor):
         upload_date = self._html_search_regex(
             r'''(?x)<a.+?class="o-U-s\s[^"]+"\s+style="display:\s*none"\s*>
                     ([0-9]{4}-[0-9]{2}-[0-9]{2})</a>''',
-            webpage, u'upload date', fatal=False, flags=re.VERBOSE)
+            webpage, 'upload date', fatal=False, flags=re.VERBOSE)
         if upload_date:
             # Convert timestring to a format suitable for filename
             upload_date = datetime.datetime.strptime(upload_date, "%Y-%m-%d")
@@ -51,28 +48,27 @@ class GooglePlusIE(InfoExtractor):
 
         # Extract uploader
         uploader = self._html_search_regex(r'rel\="author".*?>(.*?)</a>',
-            webpage, u'uploader', fatal=False)
+            webpage, 'uploader', fatal=False)
 
         # Extract title
         # Get the first line for title
         video_title = self._html_search_regex(r'<meta name\=\"Description\" content\=\"(.*?)[\n<"]',
-            webpage, 'title', default=u'NA')
+            webpage, 'title', default='NA')
 
         # Step 2, Simulate clicking the image box to launch video
         DOMAIN = 'https://plus.google.com/'
         video_page = self._search_regex(r'<a href="((?:%s)?photos/.*?)"' % re.escape(DOMAIN),
-            webpage, u'video page URL')
+            webpage, 'video page URL')
         if not video_page.startswith(DOMAIN):
             video_page = DOMAIN + video_page
 
-        webpage = self._download_webpage(video_page, video_id, u'Downloading video page')
+        webpage = self._download_webpage(video_page, video_id, 'Downloading video page')
 
-        # Extract video links on video page
-        """Extract video links of all sizes"""
+        # Extract video links all sizes
         pattern = r'\d+,\d+,(\d+),"(http\://redirector\.googlevideo\.com.*?)"'
         mobj = re.findall(pattern, webpage)
         if len(mobj) == 0:
-            raise ExtractorError(u'Unable to extract video links')
+            raise ExtractorError('Unable to extract video links')
 
         # Sort in resolution
         links = sorted(mobj)
@@ -87,12 +83,11 @@ class GooglePlusIE(InfoExtractor):
         except AttributeError: # Python 3
             video_url = bytes(video_url, 'ascii').decode('unicode-escape')
 
-
-        return [{
-            'id':       video_id,
-            'url':      video_url,
+        return {
+            'id': video_id,
+            'url': video_url,
             'uploader': uploader,
-            'upload_date':  upload_date,
-            'title':    video_title,
-            'ext':      video_extension,
-        }]
+            'upload_date': upload_date,
+            'title': video_title,
+            'ext': 'flv',
+        }

youtube_dl/extractor/helsinki.py

@@ -0,0 +1,62 @@
+# -*- coding: utf-8 -*-
+
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class HelsinkiIE(InfoExtractor):
+    IE_DESC = 'helsinki.fi'
+    _VALID_URL = r'https?://video\.helsinki\.fi/Arkisto/flash\.php\?id=(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://video.helsinki.fi/Arkisto/flash.php?id=20258',
+        'info_dict': {
+            'id': '20258',
+            'ext': 'mp4',
+            'title': 'Tietotekniikkafoorumi-iltapäivä',
+            'description': 'md5:f5c904224d43c133225130fe156a5ee0',
+        },
+        'params': {
+            'skip_download': True,  # RTMP
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        webpage = self._download_webpage(url, video_id)
+        formats = []
+
+        mobj = re.search(r'file=((\w+):[^&]+)', webpage)
+        if mobj:
+            formats.append({
+                'ext': mobj.group(2),
+                'play_path': mobj.group(1),
+                'url': 'rtmp://flashvideo.it.helsinki.fi/vod/',
+                'player_url': 'http://video.helsinki.fi/player.swf',
+                'format_note': 'sd',
+                'quality': 0,
+            })
+
+        mobj = re.search(r'hd\.file=((\w+):[^&]+)', webpage)
+        if mobj:
+            formats.append({
+                'ext': mobj.group(2),
+                'play_path': mobj.group(1),
+                'url': 'rtmp://flashvideo.it.helsinki.fi/vod/',
+                'player_url': 'http://video.helsinki.fi/player.swf',
+                'format_note': 'hd',
+                'quality': 1,
+            })
+
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': self._og_search_title(webpage).replace('Video: ', ''),
+            'description': self._og_search_description(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'formats': formats,
+        }

youtube_dl/extractor/howcast.py

@@ -1,17 +1,20 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
 
 
 class HowcastIE(InfoExtractor):
-    _VALID_URL = r'(?:https?://)?(?:www\.)?howcast\.com/videos/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?howcast\.com/videos/(?P<id>\d+)'
     _TEST = {
-        u'url': u'http://www.howcast.com/videos/390161-How-to-Tie-a-Square-Knot-Properly',
-        u'file': u'390161.mp4',
-        u'md5': u'8b743df908c42f60cf6496586c7f12c3',
-        u'info_dict': {
-            u"description": u"The square knot, also known as the reef knot, is one of the oldest, most basic knots to tie, and can be used in many different ways. Here's the proper way to tie a square knot.", 
-            u"title": u"How to Tie a Square Knot Properly"
+        'url': 'http://www.howcast.com/videos/390161-How-to-Tie-a-Square-Knot-Properly',
+        'md5': '8b743df908c42f60cf6496586c7f12c3',
+        'info_dict': {
+            'id': '390161',
+            'ext': 'mp4',
+            'description': 'The square knot, also known as the reef knot, is one of the oldest, most basic knots to tie, and can be used in many different ways. Here\'s the proper way to tie a square knot.', 
+            'title': 'How to Tie a Square Knot Properly',
         }
     }
 
@@ -24,22 +27,15 @@ class HowcastIE(InfoExtractor):
         self.report_extraction(video_id)
 
         video_url = self._search_regex(r'\'?file\'?: "(http://mobile-media\.howcast\.com/[0-9]+\.mp4)',
-            webpage, u'video URL')
-
-        video_title = self._html_search_regex(r'<meta content=(?:"([^"]+)"|\'([^\']+)\') property=\'og:title\'',
-            webpage, u'title')
+            webpage, 'video URL')
 
         video_description = self._html_search_regex(r'<meta content=(?:"([^"]+)"|\'([^\']+)\') name=\'description\'',
-            webpage, u'description', fatal=False)
+            webpage, 'description', fatal=False)
 
-        thumbnail = self._html_search_regex(r'<meta content=\'(.+?)\' property=\'og:image\'',
-            webpage, u'thumbnail', fatal=False)
-
-        return [{
-            'id':       video_id,
-            'url':      video_url,
-            'ext':      'mp4',
-            'title':    video_title,
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': self._og_search_title(webpage),
             'description': video_description,
-            'thumbnail': thumbnail,
-        }]
+            'thumbnail': self._og_search_thumbnail(webpage),
+        }

youtube_dl/extractor/instagram.py

@@ -1,35 +1,39 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
 
+
 class InstagramIE(InfoExtractor):
-    _VALID_URL = r'(?:http://)?instagram\.com/p/(.*?)/'
+    _VALID_URL = r'http://instagram\.com/p/(?P<id>.*?)/'
     _TEST = {
-        u'url': u'http://instagram.com/p/aye83DjauH/?foo=bar#abc',
-        u'file': u'aye83DjauH.mp4',
-        u'md5': u'0d2da106a9d2631273e192b372806516',
-        u'info_dict': {
-            u"uploader_id": u"naomipq", 
-            u"title": u"Video by naomipq",
-            u'description': u'md5:1f17f0ab29bd6fe2bfad705f58de3cb8',
+        'url': 'http://instagram.com/p/aye83DjauH/?foo=bar#abc',
+        'md5': '0d2da106a9d2631273e192b372806516',
+        'info_dict': {
+            'id': 'aye83DjauH',
+            'ext': 'mp4',
+            'uploader_id': 'naomipq',
+            'title': 'Video by naomipq',
+            'description': 'md5:1f17f0ab29bd6fe2bfad705f58de3cb8',
         }
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group(1)
+        video_id = mobj.group('id')
         webpage = self._download_webpage(url, video_id)
         uploader_id = self._search_regex(r'"owner":{"username":"(.+?)"',
-            webpage, u'uploader id', fatal=False)
-        desc = self._search_regex(r'"caption":"(.*?)"', webpage, u'description',
+            webpage, 'uploader id', fatal=False)
+        desc = self._search_regex(r'"caption":"(.*?)"', webpage, 'description',
             fatal=False)
 
-        return [{
-            'id':        video_id,
-            'url':       self._og_search_video_url(webpage, secure=False),
-            'ext':       'mp4',
-            'title':     u'Video by %s' % uploader_id,
+        return {
+            'id': video_id,
+            'url': self._og_search_video_url(webpage, secure=False),
+            'ext': 'mp4',
+            'title': 'Video by %s' % uploader_id,
             'thumbnail': self._og_search_thumbnail(webpage),
-            'uploader_id' : uploader_id,
+            'uploader_id': uploader_id,
             'description': desc,
-        }]
+        }

youtube_dl/extractor/iprima.py

@@ -10,7 +10,7 @@ from ..utils import compat_urllib_request
 
 
 class IPrimaIE(InfoExtractor):
-    _VALID_URL = r'https?://play\.iprima\.cz/(?P<videogroup>.+)/(?P<videoid>.+)'
+    _VALID_URL = r'https?://play\.iprima\.cz/[^?#]+/(?P<id>[^?#]+)'
 
     _TESTS = [{
         'url': 'http://play.iprima.cz/particka/particka-92',
@@ -22,20 +22,32 @@ class IPrimaIE(InfoExtractor):
             'thumbnail': 'http://play.iprima.cz/sites/default/files/image_crops/image_620x349/3/491483_particka-92_image_620x349.jpg',
         },
         'params': {
-            'skip_download': True,
+            'skip_download': True,  # requires rtmpdump
         },
-    },
-    ]
+    }, {
+        'url': 'http://play.iprima.cz/particka/tchibo-particka-jarni-moda',
+        'info_dict': {
+            'id': '9718337',
+            'ext': 'flv',
+            'title': 'Tchibo Partička - Jarní móda',
+            'description': 'md5:589f8f59f414220621ff8882eb3ce7be',
+            'thumbnail': 're:^http:.*\.jpg$',
+        },
+        'params': {
+            'skip_download': True,  # requires rtmpdump
+        },
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('videoid')
+        video_id = mobj.group('id')
 
         webpage = self._download_webpage(url, video_id)
 
-        player_url = 'http://embed.livebox.cz/iprimaplay/player-embed-v2.js?__tok%s__=%s' % (
-                         floor(random()*1073741824),
-                         floor(random()*1073741824))
+        player_url = (
+            'http://embed.livebox.cz/iprimaplay/player-embed-v2.js?__tok%s__=%s' %
+            (floor(random()*1073741824), floor(random()*1073741824))
+        )
 
         req = compat_urllib_request.Request(player_url)
         req.add_header('Referer', url)
@@ -44,18 +56,20 @@ class IPrimaIE(InfoExtractor):
         base_url = ''.join(re.findall(r"embed\['stream'\] = '(.+?)'.+'(\?auth=)'.+'(.+?)';", playerpage)[1])
 
         zoneGEO = self._html_search_regex(r'"zoneGEO":(.+?),', webpage, 'zoneGEO')
-
         if zoneGEO != '0':
-            base_url = base_url.replace('token', 'token_'+zoneGEO)
+            base_url = base_url.replace('token', 'token_' + zoneGEO)
 
         formats = []
         for format_id in ['lq', 'hq', 'hd']:
-            filename = self._html_search_regex(r'"%s_id":(.+?),' % format_id, webpage, 'filename')
+            filename = self._html_search_regex(
+                r'"%s_id":(.+?),' % format_id, webpage, 'filename')
 
             if filename == 'null':
                 continue
 
-            real_id = self._search_regex(r'Prima-[0-9]{10}-([0-9]+)_', filename, 'real video id')
+            real_id = self._search_regex(
+                r'Prima-(?:[0-9]{10}|WEB)-([0-9]+)[-_]',
+                filename, 'real video id')
 
             if format_id == 'lq':
                 quality = 0
@@ -63,13 +77,13 @@ class IPrimaIE(InfoExtractor):
                 quality = 1
             elif format_id == 'hd':
                 quality = 2
-                filename = 'hq/'+filename
+                filename = 'hq/' + filename
 
             formats.append({
                 'format_id': format_id,
                 'url': base_url,
                 'quality': quality,
-                'play_path': 'mp4:'+filename.replace('"', '')[:-4],
+                'play_path': 'mp4:' + filename.replace('"', '')[:-4],
                 'rtmp_live': True,
                 'ext': 'flv',
             })

youtube_dl/extractor/jadorecettepub.py

@@ -0,0 +1,48 @@
+# coding: utf-8
+
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from .youtube import YoutubeIE
+
+
+class JadoreCettePubIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?jadorecettepub\.com/[0-9]{4}/[0-9]{2}/(?P<id>.*?)\.html'
+
+    _TEST = {
+        'url': 'http://www.jadorecettepub.com/2010/12/star-wars-massacre-par-les-japonais.html',
+        'md5': '401286a06067c70b44076044b66515de',
+        'info_dict': {
+            'id': 'jLMja3tr7a4',
+            'ext': 'mp4',
+            'title': 'La pire utilisation de Star Wars',
+            'description': "Jadorecettepub.com vous a gratifié de plusieurs pubs géniales utilisant Star Wars et Dark Vador plus particulièrement... Mais l'heure est venue de vous proposer une version totalement massacrée, venue du Japon.  Quand les Japonais détruisent l'image de Star Wars pour vendre du thon en boite, ça promet...",
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        display_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, display_id)
+
+        title = self._html_search_regex(
+            r'<span style="font-size: x-large;"><b>(.*?)</b></span>',
+            webpage, 'title')
+        description = self._html_search_regex(
+            r'(?s)<div id="fb-root">(.*?)<script>', webpage, 'description',
+            fatal=False)
+        real_url = self._search_regex(
+            r'\[/postlink\](.*)endofvid', webpage, 'video URL')
+        video_id = YoutubeIE.extract_id(real_url)
+
+        return {
+            '_type': 'url_transparent',
+            'url': real_url,
+            'id': video_id,
+            'title': title,
+            'description': description,
+        }
+

youtube_dl/extractor/jeuxvideo.py

@@ -1,5 +1,7 @@
 # coding: utf-8
 
+from __future__ import unicode_literals
+
 import json
 import re
 
@@ -10,12 +12,13 @@ class JeuxVideoIE(InfoExtractor):
     _VALID_URL = r'http://.*?\.jeuxvideo\.com/.*/(.*?)-\d+\.htm'
 
     _TEST = {
-        u'url': u'http://www.jeuxvideo.com/reportages-videos-jeux/0004/00046170/tearaway-playstation-vita-gc-2013-tearaway-nous-presente-ses-papiers-d-identite-00115182.htm',
-        u'file': u'5182.mp4',
-        u'md5': u'046e491afb32a8aaac1f44dd4ddd54ee',
-        u'info_dict': {
-            u'title': u'GC 2013 : Tearaway nous présente ses papiers d\'identité',
-            u'description': u'Lorsque les développeurs de LittleBigPlanet proposent un nouveau titre, on ne peut que s\'attendre à un résultat original et fort attrayant.\n',
+        'url': 'http://www.jeuxvideo.com/reportages-videos-jeux/0004/00046170/tearaway-playstation-vita-gc-2013-tearaway-nous-presente-ses-papiers-d-identite-00115182.htm',
+        'md5': '046e491afb32a8aaac1f44dd4ddd54ee',
+        'info_dict': {
+            'id': '5182',
+            'ext': 'mp4',
+            'title': 'GC 2013 : Tearaway nous présente ses papiers d\'identité',
+            'description': 'Lorsque les développeurs de LittleBigPlanet proposent un nouveau titre, on ne peut que s\'attendre à un résultat original et fort attrayant.\n',
         },
     }
 
@@ -25,14 +28,14 @@ class JeuxVideoIE(InfoExtractor):
         webpage = self._download_webpage(url, title)
         xml_link = self._html_search_regex(
             r'<param name="flashvars" value="config=(.*?)" />',
-            webpage, u'config URL')
+            webpage, 'config URL')
         
         video_id = self._search_regex(
             r'http://www\.jeuxvideo\.com/config/\w+/\d+/(.*?)/\d+_player\.xml',
-            xml_link, u'video ID')
+            xml_link, 'video ID')
 
         config = self._download_xml(
-            xml_link, title, u'Downloading XML config')
+            xml_link, title, 'Downloading XML config')
         info_json = config.find('format.json').text
         info = json.loads(info_json)['versions'][0]
         

youtube_dl/extractor/kontrtube.py

@@ -0,0 +1,66 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class KontrTubeIE(InfoExtractor):
+    IE_NAME = 'kontrtube'
+    IE_DESC = 'KontrTube.ru - Труба зовёт'
+    _VALID_URL = r'http://(?:www\.)?kontrtube\.ru/videos/(?P<id>\d+)/.+'
+
+    _TEST = {
+        'url': 'http://www.kontrtube.ru/videos/2678/nad-olimpiyskoy-derevney-v-sochi-podnyat-rossiyskiy-flag/',
+        'md5': '975a991a4926c9a85f383a736a2e6b80',
+        'info_dict': {
+            'id': '2678',
+            'ext': 'mp4',
+            'title': 'Над олимпийской деревней в Сочи поднят российский флаг',
+            'description': 'md5:80edc4c613d5887ae8ccf1d59432be41',
+            'thumbnail': 'http://www.kontrtube.ru/contents/videos_screenshots/2000/2678/preview.mp4.jpg',
+            'duration': 270,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id, 'Downloading page')
+
+        video_url = self._html_search_regex(r"video_url: '(.+?)/?',", webpage, 'video URL')
+        thumbnail = self._html_search_regex(r"preview_url: '(.+?)/?',", webpage, 'video thumbnail', fatal=False)
+        title = self._html_search_regex(r'<title>(.+?) - Труба зовёт - Интересный видеохостинг</title>', webpage,
+            'video title')
+        description = self._html_search_meta('description', webpage, 'video description')
+
+        mobj = re.search(r'<div class="col_2">Длительность: <span>(?P<minutes>\d+)м:(?P<seconds>\d+)с</span></div>',
+            webpage)
+        duration = int(mobj.group('minutes')) * 60 + int(mobj.group('seconds')) if mobj else None
+
+        view_count = self._html_search_regex(r'<div class="col_2">Просмотров: <span>(\d+)</span></div>', webpage,
+            'view count', fatal=False)
+        view_count = int(view_count) if view_count is not None else None
+
+        comment_count = None
+        comment_str = self._html_search_regex(r'Комментарии: <span>([^<]+)</span>', webpage, 'comment count',
+            fatal=False)
+        if comment_str.startswith('комментариев нет'):
+            comment_count = 0
+        else:
+            mobj = re.search(r'\d+ из (?P<total>\d+) комментариев', comment_str)
+            if mobj:
+                comment_count = int(mobj.group('total'))
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'thumbnail': thumbnail,
+            'title': title,
+            'description': description,
+            'duration': duration,
+            'view_count': view_count,
+            'comment_count': comment_count,
+        }

youtube_dl/extractor/lifenews.py

@@ -4,19 +4,23 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import unified_strdate
+from ..utils import (
+    int_or_none,
+    unified_strdate
+)
 
 
 class LifeNewsIE(InfoExtractor):
     IE_NAME = 'lifenews'
     IE_DESC = 'LIFE | NEWS'
     _VALID_URL = r'http://lifenews\.ru/(?:mobile/)?news/(?P<id>\d+)'
-    
+
     _TEST = {
         'url': 'http://lifenews.ru/news/126342',
-        'file': '126342.mp4',
         'md5': 'e1b50a5c5fb98a6a544250f2e0db570a',
         'info_dict': {
+            'id': '126342',
+            'ext': 'mp4',
             'title': 'МВД разыскивает мужчин, оставивших в IKEA сумку с автоматом',
             'description': 'Камеры наблюдения гипермаркета зафиксировали троих мужчин, спрятавших оружейный арсенал в камере хранения.',
             'thumbnail': 'http://lifenews.ru/static/posts/2014/1/126342/.video.jpg',
@@ -32,7 +36,7 @@ class LifeNewsIE(InfoExtractor):
 
         video_url = self._html_search_regex(
             r'<video.*?src="([^"]+)".*?></video>', webpage, 'video URL')
-        
+
         thumbnail = self._html_search_regex(
             r'<video.*?poster="([^"]+)".*?"></video>', webpage, 'video thumbnail')
 
@@ -44,12 +48,14 @@ class LifeNewsIE(InfoExtractor):
         description = self._og_search_description(webpage)
 
         view_count = self._html_search_regex(
-            r'<div class=\'views\'>(\d+)</div>', webpage, 'view count')
+            r'<div class=\'views\'>(\d+)</div>', webpage, 'view count', fatal=False)
         comment_count = self._html_search_regex(
-            r'<div class=\'comments\'>(\d+)</div>', webpage, 'comment count')
+            r'<div class=\'comments\'>(\d+)</div>', webpage, 'comment count', fatal=False)
 
         upload_date = self._html_search_regex(
-            r'<time datetime=\'([^\']+)\'>', webpage, 'upload date')
+            r'<time datetime=\'([^\']+)\'>', webpage, 'upload date',fatal=False)
+        if upload_date is not None:
+            upload_date = unified_strdate(upload_date)
 
         return {
             'id': video_id,
@@ -57,7 +63,7 @@ class LifeNewsIE(InfoExtractor):
             'thumbnail': thumbnail,
             'title': title,
             'description': description,
-            'view_count': view_count,
-            'comment_count': comment_count,
-            'upload_date': unified_strdate(upload_date),
+            'view_count': int_or_none(view_count),
+            'comment_count': int_or_none(comment_count),
+            'upload_date': upload_date,
         }

youtube_dl/extractor/liveleak.py

@@ -4,15 +4,17 @@ import json
 import re
 
 from .common import InfoExtractor
+from ..utils import int_or_none
 
 
 class LiveLeakIE(InfoExtractor):
     _VALID_URL = r'^(?:http://)?(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<video_id>[\w_]+)(?:.*)'
     _TESTS = [{
         'url': 'http://www.liveleak.com/view?i=757_1364311680',
-        'file': '757_1364311680.mp4',
         'md5': '0813c2430bea7a46bf13acf3406992f4',
         'info_dict': {
+            'id': '757_1364311680',
+            'ext': 'mp4',
             'description': 'extremely bad day for this guy..!',
             'uploader': 'ljfriel2',
             'title': 'Most unlucky car accident'
@@ -20,25 +22,62 @@ class LiveLeakIE(InfoExtractor):
     },
     {
         'url': 'http://www.liveleak.com/view?i=f93_1390833151',
-        'file': 'f93_1390833151.mp4',
         'md5': 'd3f1367d14cc3c15bf24fbfbe04b9abf',
         'info_dict': {
+            'id': 'f93_1390833151',
+            'ext': 'mp4',
             'description': 'German Television Channel NDR does an exclusive interview with Edward Snowden.\r\nUploaded on LiveLeak cause German Television thinks the rest of the world isn\'t intereseted in Edward Snowden.',
             'uploader': 'ARD_Stinkt',
             'title': 'German Television does first Edward Snowden Interview (ENGLISH)',
         }
+    },
+    {
+        'url': 'http://www.liveleak.com/view?i=4f7_1392687779',
+        'md5': '42c6d97d54f1db107958760788c5f48f',
+        'info_dict': {
+            'id': '4f7_1392687779',
+            'ext': 'mp4',
+            'description': "The guy with the cigarette seems amazingly nonchalant about the whole thing...  I really hope my friends' reactions would be a bit stronger.\r\n\r\nAction-go to 0:55.",
+            'uploader': 'CapObveus',
+            'title': 'Man is Fatally Struck by Reckless Car While Packing up a Moving Truck',
+            'age_limit': 18,
+        }
     }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-
         video_id = mobj.group('video_id')
         webpage = self._download_webpage(url, video_id)
+
+        video_title = self._og_search_title(webpage).replace('LiveLeak.com -', '').strip()
+        video_description = self._og_search_description(webpage)
+        video_uploader = self._html_search_regex(
+            r'By:.*?(\w+)</a>', webpage, 'uploader', fatal=False)
+        age_limit = int_or_none(self._search_regex(
+            r'you confirm that you are ([0-9]+) years and over.',
+            webpage, 'age limit', default=None))
+
         sources_raw = self._search_regex(
             r'(?s)sources:\s*(\[.*?\]),', webpage, 'video URLs', default=None)
         if sources_raw is None:
-            sources_raw = '[{ %s}]' % (
-                self._search_regex(r'(file: ".*?"),', webpage, 'video URL'))
+            alt_source = self._search_regex(
+                r'(file: ".*?"),', webpage, 'video URL', default=None)
+            if alt_source:
+                sources_raw = '[{ %s}]' % alt_source
+            else:
+                # Maybe an embed?
+                embed_url = self._search_regex(
+                    r'<iframe[^>]+src="(http://www.prochan.com/embed\?[^"]+)"',
+                    webpage, 'embed URL')
+                return {
+                    '_type': 'url_transparent',
+                    'url': embed_url,
+                    'id': video_id,
+                    'title': video_title,
+                    'description': video_description,
+                    'uploader': video_uploader,
+                    'age_limit': age_limit,
+                }
 
         sources_json = re.sub(r'\s([a-z]+):\s', r'"\1": ', sources_raw)
         sources = json.loads(sources_json)
@@ -49,15 +88,11 @@ class LiveLeakIE(InfoExtractor):
         } for s in sources]
         self._sort_formats(formats)
 
-        video_title = self._og_search_title(webpage).replace('LiveLeak.com -', '').strip()
-        video_description = self._og_search_description(webpage)
-        video_uploader = self._html_search_regex(
-            r'By:.*?(\w+)</a>', webpage, 'uploader', fatal=False)
-
         return {
             'id': video_id,
             'title': video_title,
             'description': video_description,
             'uploader': video_uploader,
             'formats': formats,
+            'age_limit': age_limit,
         }

youtube_dl/extractor/metacafe.py

@@ -166,6 +166,7 @@ class MetacafeIE(InfoExtractor):
 
         video_title = self._html_search_regex(r'(?im)<title>(.*) - Video</title>', webpage, u'title')
         description = self._og_search_description(webpage)
+        thumbnail = self._og_search_thumbnail(webpage)
         video_uploader = self._html_search_regex(
                 r'submitter=(.*?);|googletag\.pubads\(\)\.setTargeting\("(?:channel|submiter)","([^"]+)"\);',
                 webpage, u'uploader nickname', fatal=False)
@@ -183,6 +184,7 @@ class MetacafeIE(InfoExtractor):
             'uploader': video_uploader,
             'upload_date':  None,
             'title':    video_title,
+            'thumbnail':thumbnail,
             'ext':      video_ext,
             'age_limit': age_limit,
         }

youtube_dl/extractor/mit.py

@@ -1,24 +1,29 @@
+from __future__ import unicode_literals
+
 import re
 import json
 
 from .common import InfoExtractor
+from .youtube import YoutubeIE
 from ..utils import (
+    compat_urlparse,
     clean_html,
     get_element_by_id,
 )
 
 
 class TechTVMITIE(InfoExtractor):
-    IE_NAME = u'techtv.mit.edu'
+    IE_NAME = 'techtv.mit.edu'
     _VALID_URL = r'https?://techtv\.mit\.edu/(videos|embeds)/(?P<id>\d+)'
 
     _TEST = {
-        u'url': u'http://techtv.mit.edu/videos/25418-mit-dna-learning-center-set',
-        u'file': u'25418.mp4',
-        u'md5': u'1f8cb3e170d41fd74add04d3c9330e5f',
-        u'info_dict': {
-            u'title': u'MIT DNA Learning Center Set',
-            u'description': u'md5:82313335e8a8a3f243351ba55bc1b474',
+        'url': 'http://techtv.mit.edu/videos/25418-mit-dna-learning-center-set',
+        'md5': '1f8cb3e170d41fd74add04d3c9330e5f',
+        'info_dict': {
+            'id': '25418',
+            'ext': 'mp4',
+            'title': 'MIT DNA Learning Center Set',
+            'description': 'md5:82313335e8a8a3f243351ba55bc1b474',
         },
     }
 
@@ -27,12 +32,12 @@ class TechTVMITIE(InfoExtractor):
         video_id = mobj.group('id')
         raw_page = self._download_webpage(
             'http://techtv.mit.edu/videos/%s' % video_id, video_id)
-        clean_page = re.compile(u'<!--.*?-->', re.S).sub(u'', raw_page)
+        clean_page = re.compile(r'<!--.*?-->', re.S).sub('', raw_page)
 
-        base_url = self._search_regex(r'ipadUrl: \'(.+?cloudfront.net/)',
-            raw_page, u'base url')
-        formats_json = self._search_regex(r'bitrates: (\[.+?\])', raw_page,
-            u'video formats')
+        base_url = self._search_regex(
+            r'ipadUrl: \'(.+?cloudfront.net/)', raw_page, 'base url')
+        formats_json = self._search_regex(
+            r'bitrates: (\[.+?\])', raw_page, 'video formats')
         formats_mit = json.loads(formats_json)
         formats = [
             {
@@ -48,28 +53,32 @@ class TechTVMITIE(InfoExtractor):
 
         title = get_element_by_id('edit-title', clean_page)
         description = clean_html(get_element_by_id('edit-description', clean_page))
-        thumbnail = self._search_regex(r'playlist:.*?url: \'(.+?)\'',
-            raw_page, u'thumbnail', flags=re.DOTALL)
+        thumbnail = self._search_regex(
+            r'playlist:.*?url: \'(.+?)\'',
+            raw_page, 'thumbnail', flags=re.DOTALL)
 
-        return {'id': video_id,
-                'title': title,
-                'formats': formats,
-                'description': description,
-                'thumbnail': thumbnail,
-                }
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'description': description,
+            'thumbnail': thumbnail,
+        }
 
 
 class MITIE(TechTVMITIE):
-    IE_NAME = u'video.mit.edu'
+    IE_NAME = 'video.mit.edu'
     _VALID_URL = r'https?://video\.mit\.edu/watch/(?P<title>[^/]+)'
 
     _TEST = {
-        u'url': u'http://video.mit.edu/watch/the-government-is-profiling-you-13222/',
-        u'file': u'21783.mp4',
-        u'md5': u'7db01d5ccc1895fc5010e9c9e13648da',
-        u'info_dict': {
-            u'title': u'The Government is Profiling You',
-            u'description': u'md5:ad5795fe1e1623b73620dbfd47df9afd',
+        'url': 'http://video.mit.edu/watch/the-government-is-profiling-you-13222/',
+        'file': '.mp4',
+        'md5': '7db01d5ccc1895fc5010e9c9e13648da',
+        'info_dict': {
+            'id': '21783',
+            'ext': 'mp4',
+            'title': 'The Government is Profiling You',
+            'description': 'md5:ad5795fe1e1623b73620dbfd47df9afd',
         },
     }
 
@@ -77,7 +86,73 @@ class MITIE(TechTVMITIE):
         mobj = re.match(self._VALID_URL, url)
         page_title = mobj.group('title')
         webpage = self._download_webpage(url, page_title)
-        self.to_screen('%s: Extracting %s url' % (page_title, TechTVMITIE.IE_NAME))
-        embed_url = self._search_regex(r'<iframe .*?src="(.+?)"', webpage,
-            u'embed url')
+        embed_url = self._search_regex(
+            r'<iframe .*?src="(.+?)"', webpage, 'embed url')
         return self.url_result(embed_url, ie='TechTVMIT')
+
+
+class OCWMITIE(InfoExtractor):
+    IE_NAME = 'ocw.mit.edu'
+    _VALID_URL = r'^http://ocw\.mit\.edu/courses/(?P<topic>[a-z0-9\-]+)'
+    _BASE_URL = 'http://ocw.mit.edu/'
+
+    _TESTS = [
+        {
+            'url': 'http://ocw.mit.edu/courses/electrical-engineering-and-computer-science/6-041-probabilistic-systems-analysis-and-applied-probability-fall-2010/video-lectures/lecture-7-multiple-variables-expectations-independence/',
+            'info_dict': {
+                'id': 'EObHWIEKGjA',
+                'ext': 'mp4',
+                'title': 'Lecture 7: Multiple Discrete Random Variables: Expectations, Conditioning, Independence',
+                'description': 'In this lecture, the professor discussed multiple random variables, expectations, and binomial distribution.',
+                #'subtitles': 'http://ocw.mit.edu/courses/electrical-engineering-and-computer-science/6-041-probabilistic-systems-analysis-and-applied-probability-fall-2010/video-lectures/lecture-7-multiple-variables-expectations-independence/MIT6_041F11_lec07_300k.mp4.srt'
+            }
+        },
+        {
+            'url': 'http://ocw.mit.edu/courses/mathematics/18-01sc-single-variable-calculus-fall-2010/1.-differentiation/part-a-definition-and-basic-rules/session-1-introduction-to-derivatives/',
+            'info_dict': {
+                'id': '7K1sB05pE0A',
+                'ext': 'mp4',
+                'title': 'Session 1: Introduction to Derivatives',
+                'description': 'This section contains lecture video excerpts, lecture notes, an interactive mathlet with supporting documents, and problem solving videos.',
+                #'subtitles': 'http://ocw.mit.edu//courses/mathematics/18-01sc-single-variable-calculus-fall-2010/ocw-18.01-f07-lec01_300k.SRT'
+            }
+        }
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        topic = mobj.group('topic')
+
+        webpage = self._download_webpage(url, topic)
+        title = self._html_search_meta('WT.cg_s', webpage)
+        description = self._html_search_meta('Description', webpage)
+
+        # search for call to ocw_embed_chapter_media(container_id, media_url, provider, page_url, image_url, start, stop, captions_file)
+        embed_chapter_media = re.search(r'ocw_embed_chapter_media\((.+?)\)', webpage)
+        if embed_chapter_media:
+            metadata = re.sub(r'[\'"]', '', embed_chapter_media.group(1))
+            metadata = re.split(r', ?', metadata)
+            yt = metadata[1]
+            subs = compat_urlparse.urljoin(self._BASE_URL, metadata[7])
+        else:
+            # search for call to ocw_embed_chapter_media(container_id, media_url, provider, page_url, image_url, captions_file)
+            embed_media = re.search(r'ocw_embed_media\((.+?)\)', webpage)
+            if embed_media:
+                metadata = re.sub(r'[\'"]', '', embed_media.group(1))
+                metadata = re.split(r', ?', metadata)
+                yt = metadata[1]
+                subs = compat_urlparse.urljoin(self._BASE_URL, metadata[5])
+            else:
+                raise ExtractorError('Unable to find embedded YouTube video.')
+        video_id = YoutubeIE.extract_id(yt)
+
+        return {
+            '_type': 'url_transparent',
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'url': yt,
+            'url_transparent'
+            'subtitles': subs,
+            'ie_key': 'Youtube',
+        }

youtube_dl/extractor/mixcloud.py

@@ -10,7 +10,7 @@ from ..utils import (
 
 
 class MixcloudIE(InfoExtractor):
-    _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([\w\d-]+)/([\w\d-]+)'
+    _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([^/]+)/([^/]+)'
     IE_NAME = 'mixcloud'
 
     _TEST = {

youtube_dl/extractor/mtv.py

@@ -82,12 +82,12 @@ class MTVServicesInfoExtractor(InfoExtractor):
             title_el = find_xpath_attr(
                 itemdoc, './/{http://search.yahoo.com/mrss/}category',
                 'scheme', 'urn:mtvn:video_title')
+        if title_el is None:
+            title_el = itemdoc.find('.//{http://search.yahoo.com/mrss/}title')
         if title_el is None:
             title_el = itemdoc.find('.//title')
             if title_el.text is None:
                 title_el = None
-        if title_el is None:
-            title_el = itemdoc.find('.//{http://search.yahoo.com/mrss/}title')
 
         title = title_el.text
         if title is None:

youtube_dl/extractor/nbc.py

@@ -1,19 +1,46 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
 from ..utils import find_xpath_attr, compat_str
 
 
+class NBCIE(InfoExtractor):
+    _VALID_URL = r'http://www\.nbc\.com/[^/]+/video/[^/]+/(?P<id>n?\d+)'
+
+    _TEST = {
+        'url': 'http://www.nbc.com/chicago-fire/video/i-am-a-firefighter/2734188',
+        'md5': '54d0fbc33e0b853a65d7b4de5c06d64e',
+        'info_dict': {
+            'id': 'u1RInQZRN7QJ',
+            'ext': 'flv',
+            'title': 'I Am a Firefighter',
+            'description': 'An emergency puts Dawson\'sf irefighter skills to the ultimate test in this four-part digital series.',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        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('//'):
+            theplatform_url = 'http:' + theplatform_url
+        return self.url_result(theplatform_url)
+
+
 class NBCNewsIE(InfoExtractor):
     _VALID_URL = r'https?://www\.nbcnews\.com/video/.+?/(?P<id>\d+)'
 
     _TEST = {
-        u'url': u'http://www.nbcnews.com/video/nbc-news/52753292',
-        u'file': u'52753292.flv',
-        u'md5': u'47abaac93c6eaf9ad37ee6c4463a5179',
-        u'info_dict': {
-            u'title': u'Crew emerges after four-month Mars food study',
-            u'description': u'md5:24e632ffac72b35f8b67a12d1b6ddfc1',
+        'url': 'http://www.nbcnews.com/video/nbc-news/52753292',
+        'md5': '47abaac93c6eaf9ad37ee6c4463a5179',
+        'info_dict': {
+            'id': '52753292',
+            'ext': 'flv',
+            'title': 'Crew emerges after four-month Mars food study',
+            'description': 'md5:24e632ffac72b35f8b67a12d1b6ddfc1',
         },
     }
 
@@ -23,10 +50,11 @@ class NBCNewsIE(InfoExtractor):
         all_info = self._download_xml('http://www.nbcnews.com/id/%s/displaymode/1219' % video_id, video_id)
         info = all_info.find('video')
 
-        return {'id': video_id,
-                'title': info.find('headline').text,
-                'ext': 'flv',
-                'url': find_xpath_attr(info, 'media', 'type', 'flashVideo').text,
-                'description': compat_str(info.find('caption').text),
-                'thumbnail': find_xpath_attr(info, 'media', 'type', 'thumbnail').text,
-                }
+        return {
+            'id': video_id,
+            'title': info.find('headline').text,
+            'ext': 'flv',
+            'url': find_xpath_attr(info, 'media', 'type', 'flashVideo').text,
+            'description': compat_str(info.find('caption').text),
+            'thumbnail': find_xpath_attr(info, 'media', 'type', 'thumbnail').text,
+        }

youtube_dl/extractor/ndr.py

@@ -13,28 +13,28 @@ class NDRIE(InfoExtractor):
     _VALID_URL = r'https?://www\.ndr\.de/.+?(?P<id>\d+)\.html'
 
     _TESTS = [
-        # video
         {
-            'url': 'http://www.ndr.de/fernsehen/sendungen/hallo_niedersachsen/media/hallonds19925.html',
-            'md5': '20eba151ff165f386643dad9c1da08f7',
+            'url': 'http://www.ndr.de/fernsehen/sendungen/markt/markt7959.html',
+            'md5': 'e7a6079ca39d3568f4996cb858dd6708',
+            'note': 'Video file',
             'info_dict': {
-                'id': '19925',
+                'id': '7959',
                 'ext': 'mp4',
-                'title': 'Hallo Niedersachsen  ',
-                'description': 'Bei Hallo Niedersachsen um 19:30 Uhr erfahren Sie alles, was am Tag in Niedersachsen los war.',
-                'duration': 1722,
+                'title': 'Markt - die ganze Sendung',
+                'description': 'md5:af9179cf07f67c5c12dc6d9997e05725',
+                'duration': 2655,
             },
         },
-        # audio
         {
-            'url': 'http://www.ndr.de/903/audio191719.html',
-            'md5': '41ed601768534dd18a9ae34d84798129',
+            'url': 'http://www.ndr.de/info/audio51535.html',
+            'md5': 'bb3cd38e24fbcc866d13b50ca59307b8',
+            'note': 'Audio file',
             'info_dict': {
-                'id': '191719',
+                'id': '51535',
                 'ext': 'mp3',
-                'title': '"Es war schockierend"',
-                'description': 'md5:ed7ff8364793545021a6355b97e95f10',
-                'duration': 112,
+                'title': 'La Valette entgeht der Hinrichtung',
+                'description': 'md5:22f9541913a40fe50091d5cdd7c9f536',
+                'duration': 884,
             }
         }
     ]

youtube_dl/extractor/nfb.py

@@ -74,7 +74,8 @@ class NFBIE(InfoExtractor):
                 description = media.find('description').text
                 # It seems assets always go from lower to better quality, so no need to sort
                 formats = [{
-                    'url': x.find('default/streamerURI').text + '/',
+                    'url': x.find('default/streamerURI').text,
+                    'app': x.find('default/streamerURI').text.split('/', 3)[3],
                     'play_path': x.find('default/url').text,
                     'rtmp_live': False,
                     'ext': 'mp4',

youtube_dl/extractor/normalboots.py

@@ -1,61 +1,51 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
 
 from ..utils import (
-    ExtractorError,
     unified_strdate,
 )
 
+
 class NormalbootsIE(InfoExtractor):
-    _VALID_URL = r'(?:http://)?(?:www\.)?normalboots\.com/video/(?P<videoid>[0-9a-z-]*)/?$'
+    _VALID_URL = r'http://(?:www\.)?normalboots\.com/video/(?P<videoid>[0-9a-z-]*)/?$'
     _TEST = {
-        u'url': u'http://normalboots.com/video/home-alone-games-jontron/',
-        u'file': u'home-alone-games-jontron.mp4',
-        u'md5': u'8bf6de238915dd501105b44ef5f1e0f6',
-        u'info_dict': {
-            u'title': u'Home Alone Games - JonTron - NormalBoots',
-            u'description': u'Jon is late for Christmas. Typical. Thanks to: Paul Ritchey for Co-Writing/Filming: http://www.youtube.com/user/ContinueShow Michael Azzi for Christmas Intro Animation: http://michafrar.tumblr.com/ Jerrod Waters for Christmas Intro Music: http://www.youtube.com/user/xXJerryTerryXx Casey Ormond for \u2018Tense Battle Theme\u2019:\xa0http://www.youtube.com/Kiamet/',
-            u'uploader': u'JonTron',
-            u'upload_date': u'20140125',
+        'url': 'http://normalboots.com/video/home-alone-games-jontron/',
+        'md5': '8bf6de238915dd501105b44ef5f1e0f6',
+        'info_dict': {
+            'id': 'home-alone-games-jontron',
+            'ext': 'mp4',
+            'title': 'Home Alone Games - JonTron - NormalBoots',
+            'description': 'Jon is late for Christmas. Typical. Thanks to: Paul Ritchey for Co-Writing/Filming: http://www.youtube.com/user/ContinueShow Michael Azzi for Christmas Intro Animation: http://michafrar.tumblr.com/ Jerrod Waters for Christmas Intro Music: http://www.youtube.com/user/xXJerryTerryXx Casey Ormond for ‘Tense Battle Theme’:\xa0http://www.youtube.com/Kiamet/',
+            'uploader': 'JonTron',
+            'upload_date': '20140125',
         }
     }
-    
+
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError(u'Invalid URL: %s' % url)
         video_id = mobj.group('videoid')
-        
-        info = {
-            'id': video_id,
-            'uploader': None,
-            'upload_date': None,
-        }
-        
-        if url[:4] != 'http':
-            url = 'http://' + url
-        
+
         webpage = self._download_webpage(url, video_id)
-        video_title = self._og_search_title(webpage)
-        video_description = self._og_search_description(webpage)
-        video_thumbnail = self._og_search_thumbnail(webpage)
         video_uploader = self._html_search_regex(r'Posted\sby\s<a\shref="[A-Za-z0-9/]*">(?P<uploader>[A-Za-z]*)\s</a>',
             webpage, 'uploader')
-        raw_upload_date = self._html_search_regex('<span style="text-transform:uppercase; font-size:inherit;">[A-Za-z]+, (?P<date>.*)</span>', 
+        raw_upload_date = self._html_search_regex('<span style="text-transform:uppercase; font-size:inherit;">[A-Za-z]+, (?P<date>.*)</span>',
             webpage, 'date')
         video_upload_date = unified_strdate(raw_upload_date)
-        video_upload_date = unified_strdate(raw_upload_date)
-            
+
         player_url = self._html_search_regex(r'<iframe\swidth="[0-9]+"\sheight="[0-9]+"\ssrc="(?P<url>[\S]+)"', webpage, 'url')
         player_page = self._download_webpage(player_url, video_id)
-        video_url = u'http://player.screenwavemedia.com/' + self._html_search_regex(r"'file':\s'(?P<file>[0-9A-Za-z-_\.]+)'", player_page, 'file')
-        
-        info['url'] = video_url
-        info['title'] = video_title
-        info['description'] = video_description
-        info['thumbnail'] = video_thumbnail
-        info['uploader'] = video_uploader
-        info['upload_date'] = video_upload_date
-        
-        return info
+        video_url = self._html_search_regex(r"file:\s'(?P<file>[^']+\.mp4)'", player_page, 'file')
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': self._og_search_title(webpage),
+            'description': self._og_search_description(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'uploader': video_uploader,
+            'upload_date': video_upload_date,
+        }

youtube_dl/extractor/novamov.py

@@ -9,14 +9,25 @@ from ..utils import (
 )
 
 
-class NovamovIE(InfoExtractor):
-    _VALID_URL = r'http://(?:(?:www\.)?novamov\.com/video/|(?:(?:embed|www)\.)novamov\.com/embed\.php\?v=)(?P<videoid>[a-z\d]{13})'
+class NovaMovIE(InfoExtractor):
+    IE_NAME = 'novamov'
+    IE_DESC = 'NovaMov'
+
+    _VALID_URL = r'http://(?:(?:www\.)?%(host)s/video/|(?:(?:embed|www)\.)%(host)s/embed\.php\?(?:.*?&)?v=)(?P<videoid>[a-z\d]{13})' % {'host': 'novamov\.com'}
+
+    _HOST = 'www.novamov.com'
+
+    _FILE_DELETED_REGEX = r'This file no longer exists on our servers!</h2>'
+    _FILEKEY_REGEX = r'flashvars\.filekey="(?P<filekey>[^"]+)";'
+    _TITLE_REGEX = r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>([^<]+)</h3>'
+    _DESCRIPTION_REGEX = r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>[^<]+</h3><p>([^<]+)</p>'
 
     _TEST = {
         'url': 'http://www.novamov.com/video/4rurhn9x446jj',
-        'file': '4rurhn9x446jj.flv',
         'md5': '7205f346a52bbeba427603ba10d4b935',
         'info_dict': {
+            'id': '4rurhn9x446jj',
+            'ext': 'flv',
             'title': 'search engine optimization',
             'description': 'search engine optimization is used to rank the web page in the google search engine'
         },
@@ -27,31 +38,26 @@ class NovamovIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('videoid')
 
-        page = self._download_webpage('http://www.novamov.com/video/%s' % video_id,
-                                      video_id, 'Downloading video page')
+        page = self._download_webpage(
+            'http://%s/video/%s' % (self._HOST, video_id), video_id, 'Downloading video page')
 
-        if re.search(r'This file no longer exists on our servers!</h2>', page) is not None:
+        if re.search(self._FILE_DELETED_REGEX, page) is not None:
             raise ExtractorError(u'Video %s does not exist' % video_id, expected=True)
 
-        filekey = self._search_regex(
-            r'flashvars\.filekey="(?P<filekey>[^"]+)";', page, 'filekey')
+        filekey = self._search_regex(self._FILEKEY_REGEX, page, 'filekey')
 
-        title = self._html_search_regex(
-            r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>([^<]+)</h3>',
-            page, 'title', fatal=False)
+        title = self._html_search_regex(self._TITLE_REGEX, page, 'title', fatal=False)
 
-        description = self._html_search_regex(
-            r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>[^<]+</h3><p>([^<]+)</p>',
-            page, 'description', fatal=False)
+        description = self._html_search_regex(self._DESCRIPTION_REGEX, page, 'description', default='', fatal=False)
 
         api_response = self._download_webpage(
-            'http://www.novamov.com/api/player.api.php?key=%s&file=%s' % (filekey, video_id),
-            video_id, 'Downloading video api response')
+            'http://%s/api/player.api.php?key=%s&file=%s' % (self._HOST, filekey, video_id), video_id,
+            'Downloading video api response')
 
         response = compat_urlparse.parse_qs(api_response)
 
         if 'error_msg' in response:
-            raise ExtractorError('novamov returned error: %s' % response['error_msg'][0], expected=True)
+            raise ExtractorError('%s returned error: %s' % (self.IE_NAME, response['error_msg'][0]), expected=True)
 
         video_url = response['url'][0]
 
@@ -60,4 +66,4 @@ class NovamovIE(InfoExtractor):
             'url': video_url,
             'title': title,
             'description': description
-        }
+        }

youtube_dl/extractor/nowvideo.py

@@ -1,46 +1,28 @@
-import re
+from __future__ import unicode_literals
 
-from .common import InfoExtractor
-from ..utils import compat_urlparse
+from .novamov import NovaMovIE
 
 
-class NowVideoIE(InfoExtractor):
-    _VALID_URL = r'(?:https?://)?(?:www\.)?nowvideo\.(?:ch|sx)/video/(?P<id>\w+)'
+class NowVideoIE(NovaMovIE):
+    IE_NAME = 'nowvideo'
+    IE_DESC = 'NowVideo'
+
+    _VALID_URL = r'http://(?:(?:www\.)?%(host)s/video/|(?:(?:embed|www)\.)%(host)s/embed\.php\?(?:.*?&)?v=)(?P<videoid>[a-z\d]{13})' % {'host': 'nowvideo\.(?:ch|sx|eu)'}
+
+    _HOST = 'www.nowvideo.ch'
+
+    _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
+    _FILEKEY_REGEX = r'var fkzd="([^"]+)";'
+    _TITLE_REGEX = r'<h4>([^<]+)</h4>'
+    _DESCRIPTION_REGEX = r'</h4>\s*<p>([^<]+)</p>'
+
     _TEST = {
-        u'url': u'http://www.nowvideo.ch/video/0mw0yow7b6dxa',
-        u'file': u'0mw0yow7b6dxa.flv',
-        u'md5': u'f8fbbc8add72bd95b7850c6a02fc8817',
-        u'info_dict': {
-            u"title": u"youtubedl test video _BaW_jenozKc.mp4"
+        'url': 'http://www.nowvideo.ch/video/0mw0yow7b6dxa',
+        'md5': 'f8fbbc8add72bd95b7850c6a02fc8817',
+        'info_dict': {
+            'id': '0mw0yow7b6dxa',
+            'ext': 'flv',
+            'title': 'youtubedl test video _BaW_jenozKc.mp4',
+            'description': 'Description',
         }
-    }
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-
-        video_id = mobj.group('id')
-        webpage_url = 'http://www.nowvideo.ch/video/' + video_id
-        embed_url = 'http://embed.nowvideo.ch/embed.php?v=' + video_id
-        webpage = self._download_webpage(webpage_url, video_id)
-        embed_page = self._download_webpage(embed_url, video_id,
-            u'Downloading embed page')
-
-        self.report_extraction(video_id)
-
-        video_title = self._html_search_regex(r'<h4>(.*)</h4>',
-            webpage, u'video title')
-
-        video_key = self._search_regex(r'var fkzd="(.*)";',
-            embed_page, u'video key')
-
-        api_call = "http://www.nowvideo.ch/api/player.api.php?file={0}&numOfErrors=0&cid=1&key={1}".format(video_id, video_key)
-        api_response = self._download_webpage(api_call, video_id,
-            u'Downloading API page')
-        video_url = compat_urlparse.parse_qs(api_response)[u'url'][0]
-
-        return [{
-            'id':        video_id,
-            'url':       video_url,
-            'ext':       'flv',
-            'title':     video_title,
-        }]
+    }

youtube_dl/extractor/podomatic.py

@@ -1,7 +1,10 @@
+from __future__ import unicode_literals
+
 import json
 import re
 
 from .common import InfoExtractor
+from ..utils import int_or_none
 
 
 class PodomaticIE(InfoExtractor):
@@ -9,14 +12,14 @@ class PodomaticIE(InfoExtractor):
     _VALID_URL = r'^(?P<proto>https?)://(?P<channel>[^.]+)\.podomatic\.com/entry/(?P<id>[^?]+)'
 
     _TEST = {
-        u"url": u"http://scienceteachingtips.podomatic.com/entry/2009-01-02T16_03_35-08_00",
-        u"file": u"2009-01-02T16_03_35-08_00.mp3",
-        u"md5": u"84bb855fcf3429e6bf72460e1eed782d",
-        u"info_dict": {
-            u"uploader": u"Science Teaching Tips",
-            u"uploader_id": u"scienceteachingtips",
-            u"title": u"64.  When the Moon Hits Your Eye",
-            u"duration": 446,
+        "url": "http://scienceteachingtips.podomatic.com/entry/2009-01-02T16_03_35-08_00",
+        "file": "2009-01-02T16_03_35-08_00.mp3",
+        "md5": "84bb855fcf3429e6bf72460e1eed782d",
+        "info_dict": {
+            "uploader": "Science Teaching Tips",
+            "uploader_id": "scienceteachingtips",
+            "title": "64.  When the Moon Hits Your Eye",
+            "duration": 446,
         }
     }
 
@@ -36,7 +39,7 @@ class PodomaticIE(InfoExtractor):
         uploader = data['podcast']
         title = data['title']
         thumbnail = data['imageLocation']
-        duration = int(data['length'] / 1000.0)
+        duration = int_or_none(data.get('length'), 1000)
 
         return {
             'id': video_id,

youtube_dl/extractor/savefrom.py

@@ -0,0 +1,37 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import os.path
+import re
+
+from .common import InfoExtractor
+
+
+class SaveFromIE(InfoExtractor):
+    IE_NAME = 'savefrom.net'
+    _VALID_URL = r'https?://[^.]+\.savefrom\.net/\#url=(?P<url>.*)$'
+
+    _TEST = {
+        'url': 'http://en.savefrom.net/#url=http://youtube.com/watch?v=UlVRAPW2WJY&utm_source=youtube.com&utm_medium=short_domains&utm_campaign=ssyoutube.com',
+        'info_dict': {
+            'id': 'UlVRAPW2WJY',
+            'ext': 'mp4',
+            'title': 'About Team Radical MMA | MMA Fighting',
+            'upload_date': '20120816',
+            'uploader': 'Howcast',
+            'uploader_id': 'Howcast',
+            'description': 'md5:4f0aac94361a12e1ce57d74f85265175',
+        },
+        'params': {
+            'skip_download': True
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = os.path.splitext(url.split('/')[-1])[0]
+        return {
+            '_type': 'url',
+            'id': video_id,
+            'url': mobj.group('url'),
+        }

youtube_dl/extractor/slideshare.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import re
 import json
 
@@ -12,11 +14,12 @@ class SlideshareIE(InfoExtractor):
     _VALID_URL = r'https?://www\.slideshare\.net/[^/]+?/(?P<title>.+?)($|\?)'
 
     _TEST = {
-        u'url': u'http://www.slideshare.net/Dataversity/keynote-presentation-managing-scale-and-complexity',
-        u'file': u'25665706.mp4',
-        u'info_dict': {
-            u'title': u'Managing Scale and Complexity',
-            u'description': u'This was a keynote presentation at the NoSQL Now! 2013 Conference & Expo (http://www.nosqlnow.com). This presentation was given by Adrian Cockcroft from Netflix',
+        'url': 'http://www.slideshare.net/Dataversity/keynote-presentation-managing-scale-and-complexity',
+        'info_dict': {
+            'id': '25665706',
+            'ext': 'mp4',
+            'title': 'Managing Scale and Complexity',
+            'description': 'This was a keynote presentation at the NoSQL Now! 2013 Conference & Expo (http://www.nosqlnow.com). This presentation was given by Adrian Cockcroft from Netflix.',
         },
     }
 
@@ -26,15 +29,17 @@ class SlideshareIE(InfoExtractor):
         webpage = self._download_webpage(url, page_title)
         slideshare_obj = self._search_regex(
             r'var slideshare_object =  ({.*?}); var user_info =',
-            webpage, u'slideshare object')
+            webpage, 'slideshare object')
         info = json.loads(slideshare_obj)
-        if info['slideshow']['type'] != u'video':
-            raise ExtractorError(u'Webpage type is "%s": only video extraction is supported for Slideshare' % info['slideshow']['type'], expected=True)
+        if info['slideshow']['type'] != 'video':
+            raise ExtractorError('Webpage type is "%s": only video extraction is supported for Slideshare' % info['slideshow']['type'], expected=True)
 
         doc = info['doc']
         bucket = info['jsplayer']['video_bucket']
         ext = info['jsplayer']['video_extension']
         video_url = compat_urlparse.urljoin(bucket, doc + '-SD.' + ext)
+        description = self._html_search_regex(
+            r'<p class="description.*?"[^>]*>(.*?)</p>', webpage, 'description')
 
         return {
             '_type': 'video',
@@ -43,5 +48,5 @@ class SlideshareIE(InfoExtractor):
             'ext': ext,
             'url': video_url,
             'thumbnail': info['slideshow']['pin_image_url'],
-            'description': self._og_search_description(webpage),
+            'description': description,
         }

youtube_dl/extractor/smotri.py

@@ -20,6 +20,7 @@ class SmotriIE(InfoExtractor):
     IE_DESC = 'Smotri.com'
     IE_NAME = 'smotri'
     _VALID_URL = r'^https?://(?:www\.)?(?P<url>smotri\.com/video/view/\?id=(?P<videoid>v(?P<realvideoid>[0-9]+)[a-z0-9]{4}))'
+    _NETRC_MACHINE = 'smotri'
 
     _TESTS = [
         # real video id 2610366

youtube_dl/extractor/sohu.py

@@ -17,6 +17,7 @@ class SohuIE(InfoExtractor):
         u'info_dict': {
             u'title': u'MV：Far East Movement《The Illest》',
         },
+        u'skip': u'Only available from China',
     }
 
     def _real_extract(self, url):

youtube_dl/extractor/space.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -8,14 +10,14 @@ from ..utils import RegexNotFoundError, ExtractorError
 class SpaceIE(InfoExtractor):
     _VALID_URL = r'https?://(?:(?:www|m)\.)?space\.com/\d+-(?P<title>[^/\.\?]*?)-video\.html'
     _TEST = {
-        u'add_ie': ['Brightcove'],
-        u'url': u'http://www.space.com/23373-huge-martian-landforms-detail-revealed-by-european-probe-video.html',
-        u'info_dict': {
-            u'id': u'2780937028001',
-            u'ext': u'mp4',
-            u'title': u'Huge Martian Landforms\' Detail Revealed By European Probe | Video',
-            u'description': u'md5:db81cf7f3122f95ed234b631a6ea1e61',
-            u'uploader': u'TechMedia Networks',
+        'add_ie': ['Brightcove'],
+        'url': 'http://www.space.com/23373-huge-martian-landforms-detail-revealed-by-european-probe-video.html',
+        'info_dict': {
+            'id': '2780937028001',
+            'ext': 'mp4',
+            'title': 'Huge Martian Landforms\' Detail Revealed By European Probe | Video',
+            'description': 'md5:db81cf7f3122f95ed234b631a6ea1e61',
+            'uploader': 'TechMedia Networks',
         },
     }
 

youtube_dl/extractor/spankwire.py

@@ -1,6 +1,5 @@
 from __future__ import unicode_literals
 
-import os
 import re
 
 from .common import InfoExtractor
@@ -8,23 +7,27 @@ from ..utils import (
     compat_urllib_parse_urlparse,
     compat_urllib_request,
     compat_urllib_parse,
+    unified_strdate,
+    str_to_int,
+    int_or_none,
 )
-from ..aes import (
-    aes_decrypt_text
-)
+from ..aes import aes_decrypt_text
 
 
 class SpankwireIE(InfoExtractor):
-    _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>spankwire\.com/[^/]*/video(?P<videoid>[0-9]+)/?)'
+    _VALID_URL = r'https?://(?:www\.)?(?P<url>spankwire\.com/[^/]*/video(?P<videoid>[0-9]+)/?)'
     _TEST = {
         'url': 'http://www.spankwire.com/Buckcherry-s-X-Rated-Music-Video-Crazy-Bitch/video103545/',
-        'file': '103545.mp4',
-        'md5': '1b3f55e345500552dbc252a3e9c1af43',
+        'md5': '8bbfde12b101204b39e4b9fe7eb67095',
         'info_dict': {
-            "uploader": "oreusz",
-            "title": "Buckcherry`s X Rated Music Video Crazy Bitch",
-            "description": "Crazy Bitch X rated music video.",
-            "age_limit": 18,
+            'id': '103545',
+            'ext': 'mp4',
+            'title': 'Buckcherry`s X Rated Music Video Crazy Bitch',
+            'description': 'Crazy Bitch X rated music video.',
+            'uploader': 'oreusz',
+            'uploader_id': '124697',
+            'upload_date': '20070508',
+            'age_limit': 18,
         }
     }
 
@@ -37,13 +40,26 @@ class SpankwireIE(InfoExtractor):
         req.add_header('Cookie', 'age_verified=1')
         webpage = self._download_webpage(req, video_id)
 
-        video_title = self._html_search_regex(r'<h1>([^<]+)', webpage, 'title')
-        video_uploader = self._html_search_regex(
-            r'by:\s*<a [^>]*>(.+?)</a>', webpage, 'uploader', fatal=False)
-        thumbnail = self._html_search_regex(
-            r'flashvars\.image_url = "([^"]+)', webpage, 'thumbnail', fatal=False)
+        title = self._html_search_regex(r'<h1>([^<]+)', webpage, 'title')
         description = self._html_search_regex(
             r'<div\s+id="descriptionContent">([^<]+)<', webpage, 'description', fatal=False)
+        thumbnail = self._html_search_regex(
+            r'flashvars\.image_url = "([^"]+)', webpage, 'thumbnail', fatal=False)
+
+        uploader = self._html_search_regex(
+            r'by:\s*<a [^>]*>(.+?)</a>', webpage, 'uploader', fatal=False)
+        uploader_id = self._html_search_regex(
+            r'by:\s*<a href="/Profile\.aspx\?.*?UserId=(\d+).*?"', webpage, 'uploader id', fatal=False)
+        upload_date = self._html_search_regex(r'</a> on (.+?) at \d+:\d+', webpage, 'upload date', fatal=False)
+        if upload_date:
+            upload_date = unified_strdate(upload_date)
+        
+        view_count = self._html_search_regex(
+            r'<div id="viewsCounter"><span>([^<]+)</span> views</div>', webpage, 'view count', fatal=False)
+        if view_count:
+            view_count = str_to_int(view_count)
+        comment_count = int_or_none(self._html_search_regex(
+            r'<span id="spCommentCount">\s*(\d+)</span> Comments</div>', webpage, 'comment count', fatal=False))
 
         video_urls = list(map(compat_urllib_parse.unquote , re.findall(r'flashvars\.quality_[0-9]{3}p = "([^"]+)', webpage)))
         if webpage.find('flashvars\.encrypted = "true"') != -1:
@@ -53,16 +69,13 @@ class SpankwireIE(InfoExtractor):
         formats = []
         for video_url in video_urls:
             path = compat_urllib_parse_urlparse(video_url).path
-            extension = os.path.splitext(path)[1][1:]
             format = path.split('/')[4].split('_')[:2]
             resolution, bitrate_str = format
             format = "-".join(format)
-            height = int(resolution.rstrip('P'))
-            tbr = int(bitrate_str.rstrip('K'))
-
+            height = int(resolution.rstrip('Pp'))
+            tbr = int(bitrate_str.rstrip('Kk'))
             formats.append({
                 'url': video_url,
-                'ext': extension,
                 'resolution': resolution,
                 'format': format,
                 'tbr': tbr,
@@ -75,10 +88,14 @@ class SpankwireIE(InfoExtractor):
 
         return {
             'id': video_id,
-            'uploader': video_uploader,
-            'title': video_title,
-            'thumbnail': thumbnail,
+            'title': title,
             'description': description,
+            'thumbnail': thumbnail,
+            'uploader': uploader,
+            'uploader_id': uploader_id,
+            'upload_date': upload_date,
+            'view_count': view_count,
+            'comment_count': comment_count,
             'formats': formats,
             'age_limit': age_limit,
         }

youtube_dl/extractor/streamcz.py

@@ -0,0 +1,67 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import int_or_none
+
+
+class StreamCZIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?stream\.cz/.+/(?P<videoid>.+)'
+
+    _TEST = {
+        'url': 'http://www.stream.cz/peklonataliri/765767-ecka-pro-deti',
+        'md5': '6d3ca61a8d0633c9c542b92fcb936b0c',
+        'info_dict': {
+            'id': '765767',
+            'ext': 'mp4',
+            'title': 'Peklo na talíři: Éčka pro děti',
+            'description': 'md5:49ace0df986e95e331d0fe239d421519',
+            'thumbnail': 'http://im.stream.cz/episode/52961d7e19d423f8f06f0100',
+            'duration': 256,
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('videoid')
+
+        webpage = self._download_webpage(url, video_id)
+
+        data = self._html_search_regex(r'Stream\.Data\.Episode\((.+?)\);', webpage, 'stream data')
+
+        jsonData = json.loads(data)
+
+        formats = []
+        for video in jsonData['instances']:
+            for video_format in video['instances']:
+                format_id = video_format['quality']
+
+                if format_id == '240p':
+                    quality = 0
+                elif format_id == '360p':
+                    quality = 1
+                elif format_id == '480p':
+                    quality = 2
+                elif format_id == '720p':
+                    quality = 3
+
+                formats.append({
+                    'format_id': '%s-%s' % (video_format['type'].split('/')[1], format_id),
+                    'url': video_format['source'],
+                    'quality': quality,
+                })
+
+        self._sort_formats(formats)
+
+        return {
+            'id': str(jsonData['id']),
+            'title': self._og_search_title(webpage),
+            'thumbnail': jsonData['episode_image_original_url'].replace('//', 'http://'),
+            'formats': formats,
+            'description': self._og_search_description(webpage),
+            'duration': int_or_none(jsonData['duration']),
+            'view_count': int_or_none(jsonData['stats_total']),
+        }

youtube_dl/extractor/syfy.py

@@ -0,0 +1,27 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class SyfyIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.syfy\.com/videos/.+?vid:(?P<id>\d+)'
+
+    _TEST = {
+        'url': 'http://www.syfy.com/videos/Robot%20Combat%20League/Behind%20the%20Scenes/vid:2631458',
+        'md5': 'e07de1d52c7278adbb9b9b1c93a66849',
+        'info_dict': {
+            'id': 'NmqMrGnXvmO1',
+            'ext': 'flv',
+            'title': 'George Lucas has Advice for his Daughter',
+            'description': 'Listen to what insights George Lucas give his daughter Amanda.',
+        },
+        'add_ie': ['ThePlatform'],
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        webpage = self._download_webpage(url, video_id)
+        return self.url_result(self._og_search_video_url(webpage))

youtube_dl/extractor/testurl.py

@@ -0,0 +1,68 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+
+class TestURLIE(InfoExtractor):
+    """ Allows adressing of the test cases as test:yout.*be_1 """
+
+    IE_DESC = False  # Do not list
+    _VALID_URL = r'test(?:url)?:(?P<id>(?P<extractor>.+?)(?:_(?P<num>[0-9]+))?)$'
+
+    def _real_extract(self, url):
+        from ..extractor import gen_extractors
+
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        extractor_id = mobj.group('extractor')
+        all_extractors = gen_extractors()
+
+        rex = re.compile(extractor_id, flags=re.IGNORECASE)
+        matching_extractors = [
+            e for e in all_extractors if rex.search(e.IE_NAME)]
+
+        if len(matching_extractors) == 0:
+            raise ExtractorError(
+                'No extractors matching %r found' % extractor_id,
+                expected=True)
+        elif len(matching_extractors) > 1:
+            # Is it obvious which one to pick?
+            try:
+                extractor = next(
+                    ie for ie in matching_extractors
+                    if ie.IE_NAME.lower() == extractor_id.lower())
+            except StopIteration:
+                raise ExtractorError(
+                    ('Found multiple matching extractors: %s' %
+                        ' '.join(ie.IE_NAME for ie in matching_extractors)),
+                    expected=True)
+        else:
+            extractor = matching_extractors[0]
+
+        num_str = mobj.group('num')
+        num = int(num_str) if num_str else 0
+
+        testcases = []
+        t = getattr(extractor, '_TEST', None)
+        if t:
+            testcases.append(t)
+        testcases.extend(getattr(extractor, '_TESTS', []))
+
+        try:
+            tc = testcases[num]
+        except IndexError:
+            raise ExtractorError(
+                ('Test case %d not found, got only %d tests' %
+                    (num, len(testcases))),
+                expected=True)
+
+        self.to_screen('Test URL: %s' % tc['url'])
+
+        return {
+            '_type': 'url',
+            'url': tc['url'],
+            'id': video_id,
+        }

youtube_dl/extractor/theplatform.py

@@ -11,7 +11,10 @@ _x = lambda p: xpath_with_ns(p, {'smil': 'http://www.w3.org/2005/SMIL21/Language
 
 
 class ThePlatformIE(InfoExtractor):
-    _VALID_URL = r'(?:https?://link\.theplatform\.com/s/[^/]+/|theplatform:)(?P<id>[^/\?]+)'
+    _VALID_URL = r'''(?x)
+        (?:https?://(?:link|player)\.theplatform\.com/[sp]/[^/]+/
+           (?P<config>(?:[^/\?]+/(?:swf|config)|onsite)/select/)?
+         |theplatform:)(?P<id>[^/\?&]+)'''
 
     _TEST = {
         # from http://www.metacafe.com/watch/cb-e9I_cZgTgIPd/blackberrys_big_bold_z30/
@@ -29,9 +32,7 @@ class ThePlatformIE(InfoExtractor):
         },
     }
 
-    def _get_info(self, video_id):
-        smil_url = ('http://link.theplatform.com/s/dJ5BDC/{0}/meta.smil?'
-            'format=smil&mbr=true'.format(video_id))
+    def _get_info(self, video_id, smil_url):
         meta = self._download_xml(smil_url, video_id)
 
         try:
@@ -50,26 +51,39 @@ class ThePlatformIE(InfoExtractor):
 
         head = meta.find(_x('smil:head'))
         body = meta.find(_x('smil:body'))
-        base_url = head.find(_x('smil:meta')).attrib['base']
-        switch = body.find(_x('smil:switch'))
-        formats = []
-        for f in switch.findall(_x('smil:video')):
-            attr = f.attrib
-            width = int(attr['width'])
-            height = int(attr['height'])
-            vbr = int(attr['system-bitrate']) // 1000
-            format_id = '%dx%d_%dk' % (width, height, vbr)
-            formats.append({
-                'format_id': format_id,
-                'url': base_url,
-                'play_path': 'mp4:' + attr['src'],
-                'ext': 'flv',
-                'width': width,
-                'height': height,
-                'vbr': vbr,
-            })
 
-        self._sort_formats(formats)
+        f4m_node = body.find(_x('smil:seq/smil:video'))
+        if f4m_node is not None:
+            f4m_url = f4m_node.attrib['src']
+            if 'manifest.f4m?' not in f4m_url:
+                f4m_url += '?'
+            # the parameters are from syfy.com, other sites may use others,
+            # they also work for nbc.com
+            f4m_url += '&g=UXWGVKRWHFSP&hdcore=3.0.3'
+            formats = [{
+                'ext': 'flv',
+                'url': f4m_url,
+            }]
+        else:
+            base_url = head.find(_x('smil:meta')).attrib['base']
+            switch = body.find(_x('smil:switch'))
+            formats = []
+            for f in switch.findall(_x('smil:video')):
+                attr = f.attrib
+                width = int(attr['width'])
+                height = int(attr['height'])
+                vbr = int(attr['system-bitrate']) // 1000
+                format_id = '%dx%d_%dk' % (width, height, vbr)
+                formats.append({
+                    'format_id': format_id,
+                    'url': base_url,
+                    'play_path': 'mp4:' + attr['src'],
+                    'ext': 'flv',
+                    'width': width,
+                    'height': height,
+                    'vbr': vbr,
+                })
+            self._sort_formats(formats)
 
         return {
             'id': video_id,
@@ -83,4 +97,14 @@ class ThePlatformIE(InfoExtractor):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
-        return self._get_info(video_id)
+        if mobj.group('config'):
+            config_url = url+ '&form=json'
+            config_url = config_url.replace('swf/', 'config/')
+            config_url = config_url.replace('onsite/', 'onsite/config/')
+            config_json = self._download_webpage(config_url, video_id, u'Downloading config')
+            config = json.loads(config_json)
+            smil_url = config['releaseUrl'] + '&format=SMIL&formats=MPEG4&manifest=f4m'
+        else:
+            smil_url = ('http://link.theplatform.com/s/dJ5BDC/{0}/meta.smil?'
+                'format=smil&mbr=true'.format(video_id))
+        return self._get_info(video_id, smil_url)

youtube_dl/extractor/trutube.py

@@ -0,0 +1,44 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class TruTubeIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?trutube\.tv/video/(?P<id>[0-9]+)/.*'
+    _TEST = {
+        'url': 'http://trutube.tv/video/14880/Ramses-II-Proven-To-Be-A-Red-Headed-Caucasoid-',
+        'md5': 'c5b6e301b0a2040b074746cbeaa26ca1',
+        'info_dict': {
+            'id': '14880',
+            'ext': 'flv',
+            'title': 'Ramses II - Proven To Be A Red Headed Caucasoid',
+            'thumbnail': 're:^http:.*\.jpg$',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+        video_title = self._og_search_title(webpage).strip()
+        thumbnail = self._search_regex(
+            r"var splash_img = '([^']+)';", webpage, 'thumbnail', fatal=False)
+
+        all_formats = re.finditer(
+            r"var (?P<key>[a-z]+)_video_file\s*=\s*'(?P<url>[^']+)';", webpage)
+        formats = [{
+            'format_id': m.group('key'),
+            'quality': -i,
+            'url': m.group('url'),
+        } for i, m in enumerate(all_formats)]
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': video_title,
+            'formats': formats,
+            'thumbnail': thumbnail,
+        }

youtube_dl/extractor/veoh.py

@@ -4,6 +4,7 @@ import re
 import json
 
 from .common import InfoExtractor
+from ..utils import compat_urllib_request
 
 
 class VeohIE(InfoExtractor):
@@ -24,6 +25,13 @@ class VeohIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
         webpage = self._download_webpage(url, video_id)
+        age_limit = 0
+        if 'class="adultwarning-container"' in webpage:
+            self.report_age_confirmation()
+            age_limit = 18
+            request = compat_urllib_request.Request(url)
+            request.add_header('Cookie', 'confirmedAdult=true')
+            webpage = self._download_webpage(request, video_id)
 
         m_youtube = re.search(r'http://www\.youtube\.com/v/(.*?)(\&|")', webpage)
         if m_youtube is not None:
@@ -44,4 +52,5 @@ class VeohIE(InfoExtractor):
             'thumbnail': info.get('highResImage') or info.get('medResImage'),
             'description': info['description'],
             'view_count': info['views'],
+            'age_limit': age_limit,
         }

youtube_dl/extractor/vesti.py

@@ -0,0 +1,170 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    int_or_none
+)
+
+
+class VestiIE(InfoExtractor):
+    IE_NAME = 'vesti'
+    IE_DESC = 'Вести.Ru'
+    _VALID_URL = r'http://(?:.+?\.)?vesti\.ru/(?P<id>.+)'
+
+    _TESTS = [
+        {
+            'url': 'http://www.vesti.ru/videos?vid=575582&cid=1',
+            'info_dict': {
+                'id': '765035',
+                'ext': 'mp4',
+                'title': 'Вести.net: биткоины в России не являются законными',
+                'description': 'md5:d4bb3859dc1177b28a94c5014c35a36b',
+                'duration': 302,
+            },
+            'params': {
+                # m3u8 download
+                'skip_download': True,
+            },
+        },
+        {
+            'url': 'http://www.vesti.ru/only_video.html?vid=576180',
+            'info_dict': {
+                'id': '766048',
+                'ext': 'mp4',
+                'title': 'США заморозило, Британию затопило',
+                'description': 'md5:f0ed0695ec05aed27c56a70a58dc4cc1',
+                'duration': 87,
+            },
+            'params': {
+                # m3u8 download
+                'skip_download': True,
+            },
+        },
+        {
+            'url': 'http://sochi2014.vesti.ru/video/index/video_id/766403',
+            'info_dict': {
+                'id': '766403',
+                'ext': 'mp4',
+                'title': 'XXII зимние Олимпийские игры. Российские хоккеисты стартовали на Олимпиаде с победы',
+                'description': 'md5:55805dfd35763a890ff50fa9e35e31b3',
+                'duration': 271,
+            },
+            'params': {
+                # m3u8 download
+                'skip_download': True,
+            },
+            'skip': 'Blocked outside Russia'
+        },
+        {
+            'url': 'http://sochi2014.vesti.ru/live/play/live_id/301',
+            'info_dict': {
+                'id': '51499',
+                'ext': 'flv',
+                'title': 'Сочи-2014. Биатлон. Индивидуальная гонка. Мужчины ',
+                'description': 'md5:9e0ed5c9d2fa1efbfdfed90c9a6d179c',
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+            'skip': 'Translation has finished'
+        }
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        page = self._download_webpage(url, video_id, 'Downloading page')
+
+        mobj = re.search(r'<meta property="og:video" content=".+?\.swf\?v?id=(?P<id>\d+).*?" />', page)
+        if mobj:
+            video_type = 'video'
+            video_id = mobj.group('id')
+        else:
+            mobj = re.search(
+                r'<iframe.+?src="http://player\.rutv\.ru/iframe/(?P<type>[^/]+)/id/(?P<id>\d+)[^"]*".*?></iframe>', page)
+
+            if not mobj:
+                raise ExtractorError('No media found')
+
+            video_type = mobj.group('type')
+            video_id = mobj.group('id')
+
+        json_data = self._download_json(
+            'http://player.rutv.ru/iframe/%splay/id/%s' % ('live-' if video_type == 'live' else '', video_id),
+            video_id, 'Downloading JSON')
+
+        if json_data['errors']:
+            raise ExtractorError('vesti returned error: %s' % json_data['errors'], expected=True)
+
+        playlist = json_data['data']['playlist']
+        medialist = playlist['medialist']
+        media = medialist[0]
+
+        if media['errors']:
+            raise ExtractorError('vesti returned error: %s' % media['errors'], expected=True)
+
+        view_count = playlist.get('count_views')
+        priority_transport = playlist['priority_transport']
+
+        thumbnail = media['picture']
+        width = media['width']
+        height = media['height']
+        description = media['anons']
+        title = media['title']
+        duration = int_or_none(media.get('duration'))
+
+        formats = []
+
+        for transport, links in media['sources'].items():
+            for quality, url in links.items():
+                if transport == 'rtmp':
+                    mobj = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>.+))/(?P<playpath>.+)$', url)
+                    if not mobj:
+                        continue
+                    fmt = {
+                        'url': mobj.group('url'),
+                        'play_path': mobj.group('playpath'),
+                        'app': mobj.group('app'),
+                        'page_url': 'http://player.rutv.ru',
+                        'player_url': 'http://player.rutv.ru/flash2v/osmf.swf?i=22',
+                        'rtmp_live': True,
+                        'ext': 'flv',
+                        'vbr': int(quality),
+                    }
+                elif transport == 'm3u8':
+                    fmt = {
+                        'url': url,
+                        'ext': 'mp4',
+                    }
+                else:
+                    fmt = {
+                        'url': url
+                    }
+                fmt.update({
+                    'width': width,
+                    'height': height,
+                    'format_id': '%s-%s' % (transport, quality),
+                    'preference': -1 if priority_transport == transport else -2,
+                })
+                formats.append(fmt)
+
+        if not formats:
+            raise ExtractorError('No media links available for %s' % video_id)
+
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'view_count': view_count,
+            'duration': duration,
+            'formats': formats,
+        }

youtube_dl/extractor/vevo.py

@@ -24,9 +24,10 @@ class VevoIE(InfoExtractor):
         (?P<id>[^&?#]+)'''
     _TESTS = [{
         'url': 'http://www.vevo.com/watch/hurts/somebody-to-die-for/GB1101300280',
-        'file': 'GB1101300280.mp4',
         "md5": "06bea460acb744eab74a9d7dcb4bfd61",
         'info_dict': {
+            'id': 'GB1101300280',
+            'ext': 'mp4',
             "upload_date": "20130624",
             "uploader": "Hurts",
             "title": "Somebody to Die For",
@@ -34,6 +35,33 @@ class VevoIE(InfoExtractor):
             "width": 1920,
             "height": 1080,
         }
+    }, {
+        'note': 'v3 SMIL format',
+        'url': 'http://www.vevo.com/watch/cassadee-pope/i-wish-i-could-break-your-heart/USUV71302923',
+        'md5': '893ec0e0d4426a1d96c01de8f2bdff58',
+        'info_dict': {
+            'id': 'USUV71302923',
+            'ext': 'mp4',
+            'upload_date': '20140219',
+            'uploader': 'Cassadee Pope',
+            'title': 'I Wish I Could Break Your Heart',
+            'duration': 226.101,
+            'age_limit': 0,
+        }
+    }, {
+        'note': 'Age-limited video',
+        'url': 'https://www.vevo.com/watch/justin-timberlake/tunnel-vision-explicit/USRV81300282',
+        'info_dict': {
+            'id': 'USRV81300282',
+            'ext': 'mp4',
+            'age_limit': 18,
+            'title': 'Tunnel Vision (Explicit)',
+            'uploader': 'Justin Timberlake',
+            'upload_date': '20130704',
+        },
+        'params': {
+            'skip_download': 'true',
+        }
     }]
     _SMIL_BASE_URL = 'http://smil.lvl3.vevo.com/'
 
@@ -105,9 +133,31 @@ class VevoIE(InfoExtractor):
         video_info = self._download_json(json_url, video_id)['video']
 
         formats = self._formats_from_json(video_info)
+
+        is_explicit = video_info.get('isExplicit')
+        if is_explicit is True:
+            age_limit = 18
+        elif is_explicit is False:
+            age_limit = 0
+        else:
+            age_limit = None
+
+        # Download SMIL
+        smil_blocks = sorted((
+            f for f in video_info['videoVersions']
+            if f['sourceType'] == 13),
+            key=lambda f: f['version'])
+
+        smil_url = '%s/Video/V2/VFILE/%s/%sr.smil' % (
+            self._SMIL_BASE_URL, video_id, video_id.lower())
+        if smil_blocks:
+            smil_url_m = self._search_regex(
+                r'url="([^"]+)"', smil_blocks[-1]['data'], 'SMIL URL',
+                fatal=False)
+            if smil_url_m is not None:
+                smil_url = smil_url_m
+
         try:
-            smil_url = '%s/Video/V2/VFILE/%s/%sr.smil' % (
-                self._SMIL_BASE_URL, video_id, video_id.lower())
             smil_xml = self._download_webpage(smil_url, video_id,
                                               'Downloading SMIL info')
             formats.extend(self._formats_from_smil(smil_xml))
@@ -128,4 +178,5 @@ class VevoIE(InfoExtractor):
             'upload_date': upload_date.strftime('%Y%m%d'),
             'uploader': video_info['mainArtists'][0]['artistName'],
             'duration': video_info['duration'],
+            'age_limit': age_limit,
         }

youtube_dl/extractor/videobam.py

@@ -0,0 +1,80 @@
+from __future__ import unicode_literals
+
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import int_or_none
+
+
+class VideoBamIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?videobam\.com/(?:videos/download/)?(?P<id>[a-zA-Z]+)'
+
+    _TESTS = [
+        {
+            'url': 'http://videobam.com/OiJQM',
+            'md5': 'db471f27763a531f10416a0c58b5a1e0',
+            'info_dict': {
+                'id': 'OiJQM',
+                'ext': 'mp4',
+                'title': 'Is Alcohol Worse Than Ecstasy?',
+                'description': 'md5:d25b96151515c91debc42bfbb3eb2683',
+                'uploader': 'frihetsvinge',
+            },
+        },
+        {
+            'url': 'http://videobam.com/pqLvq',
+            'md5': 'd9a565b5379a99126ef94e1d7f9a383e',
+            'note': 'HD video',
+            'info_dict': {
+                'id': 'pqLvq',
+                'ext': 'mp4',
+            }
+        },
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        page = self._download_webpage('http://videobam.com/%s' % video_id, video_id, 'Downloading page')
+
+        formats = []
+
+        for preference, format_id in enumerate(['low', 'high']):
+            mobj = re.search(r"%s: '(?P<url>[^']+)'" % format_id, page)
+            if not mobj:
+                continue
+            formats.append({
+                'url': mobj.group('url'),
+                'ext': 'mp4',
+                'format_id': format_id,
+                'preference': preference,
+            })
+
+        if not formats:
+            player_config = json.loads(self._html_search_regex(r'var player_config = ({.+?});', page, 'player config'))
+            formats = [{
+                'url': item['url'],
+                'ext': 'mp4',
+            } for item in player_config['playlist'] if 'autoPlay' in item]
+
+        self._sort_formats(formats)
+
+        title = self._og_search_title(page, default='VideoBam', fatal=False)
+        description = self._og_search_description(page, default=None)
+        thumbnail = self._og_search_thumbnail(page)
+        uploader = self._html_search_regex(r'Upload by ([^<]+)</a>', page, 'uploader', fatal=False, default=None)
+        view_count = int_or_none(
+            self._html_search_regex(r'<strong>Views:</strong> (\d+) ', page, 'view count', fatal=False))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'uploader': uploader,
+            'view_count': view_count,
+            'formats': formats,
+            'age_limit': 18,
+        }

youtube_dl/extractor/vimeo.py

@@ -37,13 +37,14 @@ class VimeoIE(SubtitlesInfoExtractor):
     _TESTS = [
         {
             'url': 'http://vimeo.com/56015672#at=0',
-            'file': '56015672.mp4',
             'md5': '8879b6cc097e987f02484baf890129e5',
             'info_dict': {
-                "upload_date": "20121220", 
-                "description": "This is a test case for youtube-dl.\nFor more information, see github.com/rg3/youtube-dl\nTest chars: \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550", 
-                "uploader_id": "user7108434", 
-                "uploader": "Filippo Valsorda", 
+                'id': '56015672',
+                'ext': 'mp4',
+                "upload_date": "20121220",
+                "description": "This is a test case for youtube-dl.\nFor more information, see github.com/rg3/youtube-dl\nTest chars: \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
+                "uploader_id": "user7108434",
+                "uploader": "Filippo Valsorda",
                 "title": "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
             },
         },

youtube_dl/extractor/vine.py

@@ -1,8 +1,10 @@
 from __future__ import unicode_literals
 
 import re
+import json
 
 from .common import InfoExtractor
+from ..utils import unified_strdate
 
 
 class VineIE(InfoExtractor):
@@ -13,31 +15,46 @@ class VineIE(InfoExtractor):
         'info_dict': {
             'id': 'b9KOOWX7HUx',
             'ext': 'mp4',
-            'uploader': 'Jack Dorsey',
             'title': 'Chicken.',
+            'description': 'Chicken.',
+            'upload_date': '20130519',
+            'uploader': 'Jack Dorsey',
+            'uploader_id': '76',
         },
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-
         video_id = mobj.group('id')
-        webpage_url = 'https://vine.co/v/' + video_id
-        webpage = self._download_webpage(webpage_url, video_id)
 
-        self.report_extraction(video_id)
+        webpage = self._download_webpage('https://vine.co/v/' + video_id, video_id)
 
-        video_url = self._html_search_meta('twitter:player:stream', webpage,
-            'video URL')
+        data = json.loads(self._html_search_regex(
+            r'window\.POST_DATA = { %s: ({.+?}) }' % video_id, webpage, 'vine data'))
 
-        uploader = self._html_search_regex(r'<p class="username">(.*?)</p>',
-            webpage, 'uploader', fatal=False, flags=re.DOTALL)
+        formats = [
+            {
+                'url': data['videoLowURL'],
+                'ext': 'mp4',
+                'format_id': 'low',
+            },
+            {
+                'url': data['videoUrl'],
+                'ext': 'mp4',
+                'format_id': 'standard',
+            }
+        ]
 
         return {
             'id': video_id,
-            'url': video_url,
-            'ext': 'mp4',
             'title': self._og_search_title(webpage),
-            'thumbnail': self._og_search_thumbnail(webpage),
-            'uploader': uploader,
-        }
+            'description': data['description'],
+            'thumbnail': data['thumbnailUrl'],
+            'upload_date': unified_strdate(data['created']),
+            'uploader': data['username'],
+            'uploader_id': data['userIdStr'],
+            'like_count': data['likes']['count'],
+            'comment_count': data['comments']['count'],
+            'repost_count': data['reposts']['count'],
+            'formats': formats,
+        }

youtube_dl/extractor/vk.py

@@ -6,6 +6,9 @@ import json
 
 from .common import InfoExtractor
 from ..utils import (
+    ExtractorError,
+    compat_urllib_request,
+    compat_urllib_parse,
     compat_str,
     unescapeHTML,
 )
@@ -14,31 +17,80 @@ from ..utils import (
 class VKIE(InfoExtractor):
     IE_NAME = 'vk.com'
     _VALID_URL = r'https?://vk\.com/(?:videos.*?\?.*?z=)?video(?P<id>.*?)(?:\?|%2F|$)'
+    _NETRC_MACHINE = 'vk'
 
-    _TESTS = [{
-        'url': 'http://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521',
-        'file': '162222515.flv',
-        'md5': '0deae91935c54e00003c2a00646315f0',
-        'info_dict': {
-            'title': 'ProtivoGunz - Хуёвая песня',
-            'uploader': 'Noize MC',
+    _TESTS = [
+        {
+            'url': 'http://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521',
+            'md5': '0deae91935c54e00003c2a00646315f0',
+            'info_dict': {
+                'id': '162222515',
+                'ext': 'flv',
+                'title': 'ProtivoGunz - Хуёвая песня',
+                'uploader': 'Noize MC',
+                'duration': 195,
+            },
         },
-    },
-    {
-        'url': 'http://vk.com/video4643923_163339118',
-        'file': '163339118.mp4',
-        'md5': 'f79bccb5cd182b1f43502ca5685b2b36',
-        'info_dict': {
-            'uploader': 'Elvira Dzhonik',
-            'title': 'Dream Theater - Hollow Years Live at Budokan 720*',
+        {
+            'url': 'http://vk.com/video4643923_163339118',
+            'md5': 'f79bccb5cd182b1f43502ca5685b2b36',
+            'info_dict': {
+                'id': '163339118',
+                'ext': 'mp4',
+                'uploader': 'Elvira Dzhonik',
+                'title': 'Dream Theater - Hollow Years Live at Budokan 720*',
+                'duration': 558,
+            }
+        },
+        {
+            'url': 'http://vk.com/video-8871596_164049491',
+            'md5': 'a590bcaf3d543576c9bd162812387666',
+            'note': 'Only available for registered users',
+            'info_dict': {
+                'id': '164049491',
+                'ext': 'mp4',
+                'uploader': 'Триллеры',
+                'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]\u00a0',
+                'duration': 8352,
+            },
+            'skip': 'Requires vk account credentials',
         }
-    }]
+    ]
+
+    def _login(self):
+        (username, password) = self._get_login_info()
+        if username is None:
+            return
+
+        login_form = {
+            'act': 'login',
+            'role': 'al_frame',
+            'expire': '1',
+            'email': username,
+            'pass': password,
+        }
+
+        request = compat_urllib_request.Request('https://login.vk.com/?act=login',
+            compat_urllib_parse.urlencode(login_form).encode('utf-8'))
+        login_page = self._download_webpage(request, None, note='Logging in as %s' % username)
+
+        if re.search(r'onLoginFailed', login_page):
+            raise ExtractorError('Unable to login, incorrect username and/or password', expected=True)
+
+    def _real_initialize(self):
+        self._login()
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
+
         info_url = 'http://vk.com/al_video.php?act=show&al=1&video=%s' % video_id
         info_page = self._download_webpage(info_url, video_id)
+
+        if re.search(r'<!>Please log in or <', info_page):
+            raise ExtractorError('This video is only available for registered users, '
+                'use --username and --password options to provide account credentials.', expected=True)
+
         m_yt = re.search(r'src="(http://www.youtube.com/.*?)"', info_page)
         if m_yt is not None:
             self.to_screen(u'Youtube video detected')
@@ -60,4 +112,5 @@ class VKIE(InfoExtractor):
             'title': unescapeHTML(data['md_title']),
             'thumbnail': data.get('jpg'),
             'uploader': data.get('md_author'),
+            'duration': data.get('duration')
         }

youtube_dl/extractor/wimp.py

@@ -6,14 +6,15 @@ from .common import InfoExtractor
 
 
 class WimpIE(InfoExtractor):
-    _VALID_URL = r'(?:http://)?(?:www\.)?wimp\.com/([^/]+)/'
+    _VALID_URL = r'http://(?:www\.)?wimp\.com/([^/]+)/'
     _TEST = {
-        'url': 'http://www.wimp.com/deerfence/',
-        'file': 'deerfence.flv',
-        'md5': '8b215e2e0168c6081a1cf84b2846a2b5',
+        'url': 'http://www.wimp.com/maruexhausted/',
+        'md5': 'f1acced123ecb28d9bb79f2479f2b6a1',
         'info_dict': {
-            "title": "Watch Till End: Herd of deer jump over a fence.",
-            "description": "These deer look as fluid as running water when they jump over this fence as a herd. This video is one that needs to be watched until the very end for the true majesty to be witnessed, but once it comes, it's sure to take your breath away.",
+            'id': 'maruexhausted',
+            'ext': 'flv',
+            'title': 'Maru is exhausted.',
+            'description': 'md5:57e099e857c0a4ea312542b684a869b8',
         }
     }
 
@@ -30,4 +31,4 @@ class WimpIE(InfoExtractor):
             'title': self._og_search_title(webpage),
             'thumbnail': self._og_search_thumbnail(webpage),
             'description': self._og_search_description(webpage),
-        }
+        }

youtube_dl/extractor/worldstarhiphop.py

@@ -22,8 +22,8 @@ class WorldStarHipHopIE(InfoExtractor):
         webpage_src = self._download_webpage(url, video_id)
 
         m_vevo_id = re.search(r'videoId=(.*?)&amp?',
-            webpage_src)
-        
+                              webpage_src)
+
         if m_vevo_id is not None:
             self.to_screen(u'Vevo video detected:')
             return self.url_result('vevo:%s' % m_vevo_id.group(1), ie='Vevo')

youtube_dl/extractor/xhamster.py

@@ -4,51 +4,51 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
-    compat_urllib_parse,
     ExtractorError,
+    unified_strdate,
+    str_to_int,
+    int_or_none,
+    parse_duration,
 )
 
 
 class XHamsterIE(InfoExtractor):
     """Information Extractor for xHamster"""
-    _VALID_URL = r'(?:http://)?(?:www\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.+?)\.html(?:\?.*)?'
-    _TESTS = [{
-        'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
-        'file': '1509445.mp4',
-        'md5': '8281348b8d3c53d39fffb377d24eac4e',
-        'info_dict': {
-            "upload_date": "20121014",
-            "uploader_id": "Ruseful2011",
-            "title": "FemaleAgent Shy beauty takes the bait",
-            "age_limit": 18,
+    _VALID_URL = r'http://(?:www\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.+?)\.html(?:\?.*)?'
+    _TESTS = [
+        {
+            'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
+            'md5': '8281348b8d3c53d39fffb377d24eac4e',
+            'info_dict': {
+                'id': '1509445',
+                'ext': 'mp4',
+                'title': 'FemaleAgent Shy beauty takes the bait',
+                'upload_date': '20121014',
+                'uploader_id': 'Ruseful2011',
+                'duration': 893,
+                'age_limit': 18,
+            }
+        },
+        {
+            'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
+            'md5': '4cbd8d56708ecb4fb4124c23e4acb81a',
+            'info_dict': {
+                'id': '2221348',
+                'ext': 'mp4',
+                'title': 'Britney Spears  Sexy Booty',
+                'upload_date': '20130914',
+                'uploader_id': 'jojo747400',
+                'duration': 200,
+                'age_limit': 18,
+            }
         }
-    },
-    {
-        'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
-        'file': '2221348.flv',
-        'md5': 'e767b9475de189320f691f49c679c4c7',
-        'info_dict': {
-            "upload_date": "20130914",
-            "uploader_id": "jojo747400",
-            "title": "Britney Spears  Sexy Booty",
-            "age_limit": 18,
-        }
-    }]
+    ]
 
     def _real_extract(self,url):
         def extract_video_url(webpage):
-            mobj = re.search(r'\'srv\': \'(?P<server>[^\']*)\',\s*\'file\': \'(?P<file>[^\']+)\',', webpage)
-            if mobj is None:
-                raise ExtractorError('Unable to extract media URL')
-            if len(mobj.group('server')) == 0:
-                return compat_urllib_parse.unquote(mobj.group('file'))
-            else:
-                return mobj.group('server')+'/key='+mobj.group('file')
-
-        def extract_mp4_video_url(webpage):
-            mp4 = re.search(r'<a href=\"(.+?)\" class=\"mp4Play\"',webpage)
+            mp4 = re.search(r'<video\s+.*?file="([^"]+)".*?>', webpage)
             if mp4 is None:
-                return None
+                raise ExtractorError('Unable to extract media URL')
             else:
                 return mp4.group(1)
 
@@ -62,50 +62,48 @@ class XHamsterIE(InfoExtractor):
         mrss_url = 'http://xhamster.com/movies/%s/%s.html' % (video_id, seo)
         webpage = self._download_webpage(mrss_url, video_id)
 
-        video_title = self._html_search_regex(
-            r'<title>(?P<title>.+?) - xHamster\.com</title>', webpage, 'title')
+        title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>', webpage, 'title')
 
         # Only a few videos have an description
         mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
-        video_description = mobj.group(1) if mobj else None
+        description = mobj.group(1) if mobj else None
 
-        mobj = re.search(r'hint=\'(?P<upload_date_Y>[0-9]{4})-(?P<upload_date_m>[0-9]{2})-(?P<upload_date_d>[0-9]{2}) [0-9]{2}:[0-9]{2}:[0-9]{2} [A-Z]{3,4}\'', webpage)
-        if mobj:
-            video_upload_date = mobj.group('upload_date_Y')+mobj.group('upload_date_m')+mobj.group('upload_date_d')
-        else:
-            video_upload_date = None
-            self._downloader.report_warning('Unable to extract upload date')
+        upload_date = self._html_search_regex(r'hint=\'(\d{4}-\d{2}-\d{2}) \d{2}:\d{2}:\d{2} [A-Z]{3,4}\'',
+            webpage, 'upload date', fatal=False)
+        if upload_date:
+            upload_date = unified_strdate(upload_date)
 
-        video_uploader_id = self._html_search_regex(
-            r'<a href=\'/user/[^>]+>(?P<uploader_id>[^<]+)',
+        uploader_id = self._html_search_regex(r'<a href=\'/user/[^>]+>(?P<uploader_id>[^<]+)',
             webpage, 'uploader id', default='anonymous')
 
-        video_thumbnail = self._search_regex(
-            r'\'image\':\'(?P<thumbnail>[^\']+)\'',
-            webpage, 'thumbnail', fatal=False)
+        thumbnail = self._html_search_regex(r'<video\s+.*?poster="([^"]+)".*?>', webpage, 'thumbnail', fatal=False)
+
+        duration = parse_duration(self._html_search_regex(r'<span>Runtime:</span> (\d+:\d+)</div>',
+            webpage, 'duration', fatal=False))
+
+        view_count = self._html_search_regex(r'<span>Views:</span> ([^<]+)</div>', webpage, 'view count', fatal=False)
+        if view_count:
+            view_count = str_to_int(view_count)
+
+        mobj = re.search(r"hint='(?P<likecount>\d+) Likes / (?P<dislikecount>\d+) Dislikes'", webpage)
+        (like_count, dislike_count) = (mobj.group('likecount'), mobj.group('dislikecount')) if mobj else (None, None)
+
+        mobj = re.search(r'</label>Comments \((?P<commentcount>\d+)\)</div>', webpage)
+        comment_count = mobj.group('commentcount') if mobj else 0
 
         age_limit = self._rta_search(webpage)
 
         hd = is_hd(webpage)
+
         video_url = extract_video_url(webpage)
         formats = [{
             'url': video_url,
             'format_id': 'hd' if hd else 'sd',
-            'preference': 0,
+            'preference': 1,
         }]
 
-        video_mp4_url = extract_mp4_video_url(webpage)
-        if video_mp4_url is not None:
-            formats.append({
-                'url': video_mp4_url,
-                'ext': 'mp4',
-                'format_id': 'mp4-hd' if hd else 'mp4-sd',
-                'preference': 1,
-            })
-
         if not hd:
-            webpage = self._download_webpage(
-                mrss_url + '?hd', video_id, note='Downloading HD webpage')
+            webpage = self._download_webpage(mrss_url + '?hd', video_id, note='Downloading HD webpage')
             if is_hd(webpage):
                 video_url = extract_video_url(webpage)
                 formats.append({
@@ -118,11 +116,16 @@ class XHamsterIE(InfoExtractor):
 
         return {
             'id': video_id,
-            'title': video_title,
-            'formats': formats,
-            'description': video_description,
-            'upload_date': video_upload_date,
-            'uploader_id': video_uploader_id,
-            'thumbnail': video_thumbnail,
+            'title': title,
+            'description': description,
+            'upload_date': upload_date,
+            'uploader_id': uploader_id,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'view_count': view_count,
+            'like_count': int_or_none(like_count),
+            'dislike_count': int_or_none(dislike_count),
+            'comment_count': int_or_none(comment_count),
             'age_limit': age_limit,
+            'formats': formats,
         }

youtube_dl/extractor/xtube.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import os
 import re
 
@@ -10,14 +12,14 @@ from ..utils import (
 class XTubeIE(InfoExtractor):
     _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>xtube\.com/watch\.php\?v=(?P<videoid>[^/?&]+))'
     _TEST = {
-        u'url': u'http://www.xtube.com/watch.php?v=kVTUy_G222_',
-        u'file': u'kVTUy_G222_.mp4',
-        u'md5': u'092fbdd3cbe292c920ef6fc6a8a9cdab',
-        u'info_dict': {
-            u"title": u"strange erotica",
-            u"description": u"surreal gay themed erotica...almost an ET kind of thing",
-            u"uploader": u"greenshowers",
-            u"age_limit": 18,
+        'url': 'http://www.xtube.com/watch.php?v=kVTUy_G222_',
+        'file': 'kVTUy_G222_.mp4',
+        'md5': '092fbdd3cbe292c920ef6fc6a8a9cdab',
+        'info_dict': {
+            "title": "strange erotica",
+            "description": "surreal gay themed erotica...almost an ET kind of thing",
+            "uploader": "greenshowers",
+            "age_limit": 18,
         }
     }
 
@@ -30,10 +32,10 @@ class XTubeIE(InfoExtractor):
         req.add_header('Cookie', 'age_verified=1')
         webpage = self._download_webpage(req, video_id)
 
-        video_title = self._html_search_regex(r'<div class="p_5px[^>]*>([^<]+)', webpage, u'title')
-        video_uploader = self._html_search_regex(r'so_s\.addVariable\("owner_u", "([^"]+)', webpage, u'uploader', fatal=False)
-        video_description = self._html_search_regex(r'<p class="video_description">([^<]+)', webpage, u'description', fatal=False)
-        video_url= self._html_search_regex(r'var videoMp4 = "([^"]+)', webpage, u'video_url').replace('\\/', '/')
+        video_title = self._html_search_regex(r'<div class="p_5px[^>]*>([^<]+)', webpage, 'title')
+        video_uploader = self._html_search_regex(r'so_s\.addVariable\("owner_u", "([^"]+)', webpage, 'uploader', fatal=False)
+        video_description = self._html_search_regex(r'<p class="video_description">([^<]+)', webpage, 'description', fatal=False)
+        video_url= self._html_search_regex(r'var videoMp4 = "([^"]+)', webpage, 'video_url').replace('\\/', '/')
         path = compat_urllib_parse_urlparse(video_url).path
         extension = os.path.splitext(path)[1][1:]
         format = path.split('/')[5].split('_')[:2]

youtube_dl/extractor/yahoo.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import itertools
 import json
 import re
@@ -12,25 +14,25 @@ from ..utils import (
 
 
 class YahooIE(InfoExtractor):
-    IE_DESC = u'Yahoo screen'
+    IE_DESC = 'Yahoo screen'
     _VALID_URL = r'http://screen\.yahoo\.com/.*?-(?P<id>\d*?)\.html'
     _TESTS = [
         {
-            u'url': u'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html',
-            u'file': u'214727115.mp4',
-            u'md5': u'4962b075c08be8690a922ee026d05e69',
-            u'info_dict': {
-                u'title': u'Julian Smith & Travis Legg Watch Julian Smith',
-                u'description': u'Julian and Travis watch Julian Smith',
+            'url': 'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html',
+            'file': '214727115.mp4',
+            'md5': '4962b075c08be8690a922ee026d05e69',
+            'info_dict': {
+                'title': 'Julian Smith & Travis Legg Watch Julian Smith',
+                'description': 'Julian and Travis watch Julian Smith',
             },
         },
         {
-            u'url': u'http://screen.yahoo.com/wired/codefellas-s1-ep12-cougar-lies-103000935.html',
-            u'file': u'103000935.mp4',
-            u'md5': u'd6e6fc6e1313c608f316ddad7b82b306',
-            u'info_dict': {
-                u'title': u'Codefellas - The Cougar Lies with Spanish Moss',
-                u'description': u'Agent Topple\'s mustache does its dirty work, and Nicole brokers a deal for peace. But why is the NSA collecting millions of Instagram brunch photos? And if your waffles have nothing to hide, what are they so worried about?',
+            'url': 'http://screen.yahoo.com/wired/codefellas-s1-ep12-cougar-lies-103000935.html',
+            'file': '103000935.mp4',
+            'md5': 'd6e6fc6e1313c608f316ddad7b82b306',
+            'info_dict': {
+                'title': 'Codefellas - The Cougar Lies with Spanish Moss',
+                'description': 'Agent Topple\'s mustache does its dirty work, and Nicole brokers a deal for peace. But why is the NSA collecting millions of Instagram brunch photos? And if your waffles have nothing to hide, what are they so worried about?',
             },
         },
     ]
@@ -41,7 +43,7 @@ class YahooIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         items_json = self._search_regex(r'mediaItems: ({.*?})$',
-            webpage, u'items', flags=re.MULTILINE)
+            webpage, 'items', flags=re.MULTILINE)
         items = json.loads(items_json)
         info = items['mediaItems']['query']['results']['mediaObj'][0]
         # The 'meta' field is not always in the video webpage, we request it
@@ -60,7 +62,7 @@ class YahooIE(InfoExtractor):
         })
         query_result_json = self._download_webpage(
             'http://video.query.yahoo.com/v1/public/yql?' + data,
-            video_id, u'Downloading video info')
+            video_id, 'Downloading video info')
         query_result = json.loads(query_result_json)
         info = query_result['query']['results']['mediaObj'][0]
         meta = info['meta']
@@ -103,13 +105,13 @@ class YahooNewsIE(YahooIE):
     _VALID_URL = r'http://news\.yahoo\.com/video/.*?-(?P<id>\d*?)\.html'
 
     _TEST = {
-        u'url': u'http://news.yahoo.com/video/china-moses-crazy-blues-104538833.html',
-        u'md5': u'67010fdf3a08d290e060a4dd96baa07b',
-        u'info_dict': {
-            u'id': u'104538833',
-            u'ext': u'mp4',
-            u'title': u'China Moses Is Crazy About the Blues',
-            u'description': u'md5:9900ab8cd5808175c7b3fe55b979bed0',
+        'url': 'http://news.yahoo.com/video/china-moses-crazy-blues-104538833.html',
+        'md5': '67010fdf3a08d290e060a4dd96baa07b',
+        'info_dict': {
+            'id': '104538833',
+            'ext': 'mp4',
+            'title': 'China Moses Is Crazy About the Blues',
+            'description': 'md5:9900ab8cd5808175c7b3fe55b979bed0',
         },
     }
 
@@ -120,14 +122,14 @@ class YahooNewsIE(YahooIE):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
         webpage = self._download_webpage(url, video_id)
-        long_id = self._search_regex(r'contentId: \'(.+?)\',', webpage, u'long id')
+        long_id = self._search_regex(r'contentId: \'(.+?)\',', webpage, 'long id')
         return self._get_info(long_id, video_id)
 
 
 class YahooSearchIE(SearchInfoExtractor):
-    IE_DESC = u'Yahoo screen search'
+    IE_DESC = 'Yahoo screen search'
     _MAX_RESULTS = 1000
-    IE_NAME = u'screen.yahoo:search'
+    IE_NAME = 'screen.yahoo:search'
     _SEARCH_KEY = 'yvsearch'
 
     def _get_n_results(self, query, n):
@@ -139,12 +141,12 @@ class YahooSearchIE(SearchInfoExtractor):
             'entries': []
         }
         for pagenum in itertools.count(0): 
-            result_url = u'http://video.search.yahoo.com/search/?p=%s&fr=screen&o=js&gs=0&b=%d' % (compat_urllib_parse.quote_plus(query), pagenum * 30)
+            result_url = 'http://video.search.yahoo.com/search/?p=%s&fr=screen&o=js&gs=0&b=%d' % (compat_urllib_parse.quote_plus(query), pagenum * 30)
             webpage = self._download_webpage(result_url, query,
                                              note='Downloading results page '+str(pagenum+1))
             info = json.loads(webpage)
-            m = info[u'm']
-            results = info[u'results']
+            m = info['m']
+            results = info['results']
 
             for (i, r) in enumerate(results):
                 if (pagenum * 30) +i >= n:
@@ -152,7 +154,7 @@ class YahooSearchIE(SearchInfoExtractor):
                 mobj = re.search(r'(?P<url>screen\.yahoo\.com/.*?-\d*?\.html)"', r)
                 e = self.url_result('http://' + mobj.group('url'), 'Yahoo')
                 res['entries'].append(e)
-            if (pagenum * 30 +i >= n) or (m[u'last'] >= (m[u'total'] -1)):
+            if (pagenum * 30 +i >= n) or (m['last'] >= (m['total'] -1)):
                 break
 
         return res

youtube_dl/extractor/youtube.py

@@ -29,11 +29,11 @@ from ..utils import (
     ExtractorError,
     int_or_none,
     PagedList,
-    RegexNotFoundError,
     unescapeHTML,
     unified_strdate,
     orderedSet,
     write_json_file,
+    uppercase_escape,
 )
 
 class YoutubeBaseInfoExtractor(InfoExtractor):
@@ -136,14 +136,15 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
                          (?:https?://|//)?                                    # http(s):// or protocol-independent URL (optional)
                          (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/|
                             (?:www\.)?deturl\.com/www\.youtube\.com/|
-                            (?:www\.)?pwnyoutube\.com|
+                            (?:www\.)?pwnyoutube\.com/|
+                            (?:www\.)?yourepeat\.com/|
                             tube\.majestyc\.net/|
                             youtube\.googleapis\.com/)                        # the various hostnames, with wildcard subdomains
                          (?:.*?\#/)?                                          # handle anchor (#/) redirect urls
                          (?:                                                  # the various things that can precede the ID:
                              (?:(?:v|embed|e)/)                               # v/ or embed/ or e/
                              |(?:                                             # or the v= param in all its forms
-                                 (?:(?:watch|movie)(?:_popup)?(?:\.php)?)?    # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
+                                 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)?  # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
                                  (?:\?|\#!?)                                  # the params delimiter ? or # or #!
                                  (?:.*?&)?                                    # any other preceding param (like /?s=tuff&v=xxxx)
                                  v=
@@ -198,9 +199,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
         '135': {'ext': 'mp4', 'height': 480, 'resolution': '480p', 'format_note': 'DASH video', 'preference': -40},
         '136': {'ext': 'mp4', 'height': 720, 'resolution': '720p', 'format_note': 'DASH video', 'preference': -40},
         '137': {'ext': 'mp4', 'height': 1080, 'resolution': '1080p', 'format_note': 'DASH video', 'preference': -40},
-        '138': {'ext': 'mp4', 'height': 1081, 'resolution': '>1080p', 'format_note': 'DASH video', 'preference': -40},
+        '138': {'ext': 'mp4', 'height': 2160, 'resolution': '2160p', 'format_note': 'DASH video', 'preference': -40},
         '160': {'ext': 'mp4', 'height': 192, 'resolution': '192p', 'format_note': 'DASH video', 'preference': -40},
-        '264': {'ext': 'mp4', 'height': 1080, 'resolution': '1080p', 'format_note': 'DASH video', 'preference': -40},
+        '264': {'ext': 'mp4', 'height': 1440, 'resolution': '1440p', 'format_note': 'DASH video', 'preference': -40},
 
         # Dash mp4 audio
         '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'vcodec': 'none', 'abr': 48, 'preference': -50},
@@ -295,6 +296,23 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
                 u"format": "141",
             },
         },
+        # DASH manifest with encrypted signature
+        {
+            u'url': u'https://www.youtube.com/watch?v=IB3lcPjvWLA',
+            u'info_dict': {
+                u'id': u'IB3lcPjvWLA',
+                u'ext': u'm4a',
+                u'title': u'Afrojack - The Spark ft. Spree Wilson',
+                u'description': u'md5:3199ed45ee8836572865580804d7ac0f',
+                u'uploader': u'AfrojackVEVO',
+                u'uploader_id': u'AfrojackVEVO',
+                u'upload_date': u'20131011',
+            },
+            u"params": {
+                u'youtube_include_dash_manifest': True,
+                u'format': '141',
+            },
+        },
     ]
 
 
@@ -1085,8 +1103,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
             self._downloader.report_warning(err_msg)
             return {}
 
-    def _extract_id(self, url):
-        mobj = re.match(self._VALID_URL, url, re.VERBOSE)
+    @classmethod
+    def extract_id(cls, url):
+        mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
         if mobj is None:
             raise ExtractorError(u'Invalid URL: %s' % url)
         video_id = mobj.group(2)
@@ -1115,7 +1134,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
         mobj = re.search(self._NEXT_URL_RE, url)
         if mobj:
             url = 'https://www.youtube.com/' + compat_urllib_parse.unquote(mobj.group(1)).lstrip('/')
-        video_id = self._extract_id(url)
+        video_id = self.extract_id(url)
 
         # Get video webpage
         url = 'https://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id
@@ -1269,8 +1288,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
             mobj = re.search(r';ytplayer.config = ({.*?});', video_webpage)
             if not mobj:
                 raise ValueError('Could not find vevo ID')
-            info = json.loads(mobj.group(1))
-            args = info['args']
+            ytplayer_config = json.loads(mobj.group(1))
+            args = ytplayer_config['args']
             # Easy way to know if the 's' value is in url_encoded_fmt_stream_map
             # this signatures are encrypted
             if 'url_encoded_fmt_stream_map' not in args:
@@ -1363,12 +1382,24 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
             raise ExtractorError(u'no conn, hlsvp or url_encoded_fmt_stream_map information found in video info')
 
         # Look for the DASH manifest
-        dash_manifest_url_lst = video_info.get('dashmpd')
-        if (dash_manifest_url_lst and dash_manifest_url_lst[0] and
-                self._downloader.params.get('youtube_include_dash_manifest', False)):
+        if (self._downloader.params.get('youtube_include_dash_manifest', False)):
             try:
+                # The DASH manifest used needs to be the one from the original video_webpage.
+                # The one found in get_video_info seems to be using different signatures.
+                # However, in the case of an age restriction there won't be any embedded dashmpd in the video_webpage.
+                # Luckily, it seems, this case uses some kind of default signature (len == 86), so the
+                # combination of get_video_info and the _static_decrypt_signature() decryption fallback will work here.
+                if age_gate:
+                    dash_manifest_url = video_info.get('dashmpd')[0]
+                else:
+                    dash_manifest_url = ytplayer_config['args']['dashmpd']
+                def decrypt_sig(mobj):
+                    s = mobj.group(1)
+                    dec_s = self._decrypt_signature(s, video_id, player_url, age_gate)
+                    return '/signature/%s' % dec_s
+                dash_manifest_url = re.sub(r'/s/([\w\.]+)', decrypt_sig, dash_manifest_url)
                 dash_doc = self._download_xml(
-                    dash_manifest_url_lst[0], video_id,
+                    dash_manifest_url, video_id,
                     note=u'Downloading DASH manifest',
                     errnote=u'Could not download DASH manifest')
                 for r in dash_doc.findall(u'.//{urn:mpeg:DASH:schema:MPD:2011}Representation'):
@@ -1440,9 +1471,9 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
                      |
                         ((?:PL|EC|UU|FL|RD)[0-9A-Za-z-_]{10,})
                      )"""
-    _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s&page=%s'
+    _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s'
     _MORE_PAGES_INDICATOR = r'data-link-type="next"'
-    _VIDEO_RE = r'href="/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&amp;[^"]*?index=(?P<index>\d+)'
+    _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&amp;[^"]*?index=(?P<index>\d+)'
     IE_NAME = u'youtube:playlist'
 
     def _real_initialize(self):
@@ -1457,11 +1488,15 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
         # the id of the playlist is just 'RD' + video_id
         url = 'https://youtube.com/watch?v=%s&list=%s' % (playlist_id[-11:], playlist_id)
         webpage = self._download_webpage(url, playlist_id, u'Downloading Youtube mix')
-        title_span = (get_element_by_attribute('class', 'title long-title', webpage) or
-            get_element_by_attribute('class', 'title ', webpage))
+        search_title = lambda class_name: get_element_by_attribute('class', class_name, webpage)
+        title_span = (search_title('playlist-title') or
+            search_title('title long-title') or search_title('title'))
         title = clean_html(title_span)
-        video_re = r'data-index="\d+".*?href="/watch\?v=([0-9A-Za-z_-]{11})&amp;[^"]*?list=%s' % re.escape(playlist_id)
-        ids = orderedSet(re.findall(video_re, webpage))
+        video_re = r'''(?x)data-video-username="(.*?)".*?
+                       href="/watch\?v=([0-9A-Za-z_-]{11})&amp;[^"]*?list=%s''' % re.escape(playlist_id)
+        matches = orderedSet(re.findall(video_re, webpage, flags=re.DOTALL))
+        # Some of the videos may have been deleted, their username field is empty
+        ids = [video_id for (username, video_id) in matches if username]
         url_results = self._ids_to_results(ids)
 
         return self.playlist_result(url_results, playlist_id, title)
@@ -1490,29 +1525,31 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
             raise ExtractorError(u'For downloading YouTube.com top lists, use '
                 u'the "yttoplist" keyword, for example "youtube-dl \'yttoplist:music:Top Tracks\'"', expected=True)
 
+        url = self._TEMPLATE_URL % playlist_id
+        page = self._download_webpage(url, playlist_id)
+        more_widget_html = content_html = page
+
         # Extract the video ids from the playlist pages
         ids = []
 
         for page_num in itertools.count(1):
-            url = self._TEMPLATE_URL % (playlist_id, page_num)
-            page = self._download_webpage(url, playlist_id, u'Downloading page #%s' % page_num)
-            matches = re.finditer(self._VIDEO_RE, page)
+            matches = re.finditer(self._VIDEO_RE, content_html)
             # We remove the duplicates and the link with index 0
             # (it's not the first video of the playlist)
             new_ids = orderedSet(m.group('id') for m in matches if m.group('index') != '0')
             ids.extend(new_ids)
 
-            if re.search(self._MORE_PAGES_INDICATOR, page) is None:
+            mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
+            if not mobj:
                 break
 
-        try:
-            playlist_title = self._og_search_title(page)
-        except RegexNotFoundError:
-            self.report_warning(
-                u'Playlist page is missing OpenGraph title, falling back ...',
-                playlist_id)
-            playlist_title = self._html_search_regex(
-                r'<h1 class="pl-header-title">(.*?)</h1>', page, u'title')
+            more = self._download_json(
+                'https://youtube.com/%s' % mobj.group('more'), playlist_id, 'Downloading page #%s' % page_num)
+            content_html = more['content_html']
+            more_widget_html = more['load_more_widget_html']
+
+        playlist_title = self._html_search_regex(
+                r'<h1 class="pl-header-title">\s*(.*?)\s*</h1>', page, u'title')
 
         url_results = self._ids_to_results(ids)
         return self.playlist_result(url_results, playlist_id, playlist_title)
@@ -1589,11 +1626,10 @@ class YoutubeChannelIE(InfoExtractor):
             # Download all channel pages using the json-based channel_ajax query
             for pagenum in itertools.count(1):
                 url = self._MORE_PAGES_URL % (pagenum, channel_id)
-                page = self._download_webpage(url, channel_id,
-                                              u'Downloading page #%s' % pagenum)
-    
-                page = json.loads(page)
-    
+                page = self._download_json(
+                    url, channel_id, note=u'Downloading page #%s' % pagenum,
+                    transform_source=uppercase_escape)
+
                 ids_in_page = self.extract_videos_from_page(page['content_html'])
                 video_ids.extend(ids_in_page)
     
@@ -1693,7 +1729,8 @@ class YoutubeSearchIE(SearchInfoExtractor):
             api_response = data['data']
 
             if 'items' not in api_response:
-                raise ExtractorError(u'[youtube] No video results')
+                raise ExtractorError(
+                    u'[youtube] No video results', expected=True)
 
             new_ids = list(video['id'] for video in api_response['items'])
             video_ids += new_ids
@@ -1813,7 +1850,7 @@ class YoutubeTruncatedURLIE(InfoExtractor):
     IE_NAME = 'youtube:truncated_url'
     IE_DESC = False  # Do not list
     _VALID_URL = r'''(?x)
-        (?:https?://)?[^/]+/watch\?feature=[a-z_]+$|
+        (?:https?://)?[^/]+/watch\?(?:feature=[a-z_]+)?$|
         (?:https?://)?(?:www\.)?youtube\.com/attribution_link\?a=[^&]+$
     '''
 

youtube_dl/extractor/zdf.py

@@ -1,4 +1,5 @@
 # coding: utf-8
+from __future__ import unicode_literals
 
 import re
 
@@ -13,52 +14,42 @@ class ZDFIE(InfoExtractor):
     _VALID_URL = r'^https?://www\.zdf\.de/ZDFmediathek(?P<hash>#)?/(.*beitrag/(?:video/)?)(?P<video_id>[0-9]+)(?:/[^/?]+)?(?:\?.*)?'
 
     _TEST = {
-        u"url": u"http://www.zdf.de/ZDFmediathek/beitrag/video/2037704/ZDFspezial---Ende-des-Machtpokers--?bc=sts;stt",
-        u"file": u"2037704.webm",
-        u"info_dict": {
-            u"upload_date": u"20131127",
-            u"description": u"Union und SPD haben sich auf einen Koalitionsvertrag geeinigt. Aber was bedeutet das für die Bürger? Sehen Sie hierzu das ZDFspezial \"Ende des Machtpokers - Große Koalition für Deutschland\".",
-            u"uploader": u"spezial",
-            u"title": u"ZDFspezial - Ende des Machtpokers"
+        'url': 'http://www.zdf.de/ZDFmediathek/beitrag/video/2037704/ZDFspezial---Ende-des-Machtpokers--?bc=sts;stt',
+        'info_dict': {
+            'id': '2037704',
+            'ext': 'webm',
+            'title': 'ZDFspezial - Ende des Machtpokers',
+            'description': 'Union und SPD haben sich auf einen Koalitionsvertrag geeinigt. Aber was bedeutet das für die Bürger? Sehen Sie hierzu das ZDFspezial "Ende des Machtpokers - Große Koalition für Deutschland".',
+            'duration': 1022,
+            'uploader': 'spezial',
+            'uploader_id': '225948',
+            'upload_date': '20131127',
         },
-        u"skip": u"Videos on ZDF.de are depublicised in short order",
+        'skip': 'Videos on ZDF.de are depublicised in short order',
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('video_id')
 
-        xml_url = u'http://www.zdf.de/ZDFmediathek/xmlservice/web/beitragsDetails?ak=web&id=%s' % video_id
+        xml_url = 'http://www.zdf.de/ZDFmediathek/xmlservice/web/beitragsDetails?ak=web&id=%s' % video_id
         doc = self._download_xml(
             xml_url, video_id,
-            note=u'Downloading video info',
-            errnote=u'Failed to download video info')
+            note='Downloading video info',
+            errnote='Failed to download video info')
 
         title = doc.find('.//information/title').text
         description = doc.find('.//information/detail').text
+        duration = int(doc.find('.//details/lengthSec').text)
         uploader_node = doc.find('.//details/originChannelTitle')
         uploader = None if uploader_node is None else uploader_node.text
-        duration_str = doc.find('.//details/length').text
-        duration_m = re.match(r'''(?x)^
-            (?P<hours>[0-9]{2})
-            :(?P<minutes>[0-9]{2})
-            :(?P<seconds>[0-9]{2})
-            (?:\.(?P<ms>[0-9]+)?)
-            ''', duration_str)
-        duration = (
-            (
-                (int(duration_m.group('hours')) * 60 * 60) +
-                (int(duration_m.group('minutes')) * 60) +
-                int(duration_m.group('seconds'))
-            )
-            if duration_m
-            else None
-        )
+        uploader_id_node = doc.find('.//details/originChannelId')
+        uploader_id = None if uploader_id_node is None else uploader_id_node.text
         upload_date = unified_strdate(doc.find('.//details/airtime').text)
 
         def xml_to_format(fnode):
             video_url = fnode.find('url').text
-            is_available = u'http://www.metafilegenerator' not in video_url
+            is_available = 'http://www.metafilegenerator' not in video_url
 
             format_id = fnode.attrib['basetype']
             format_m = re.match(r'''(?x)
@@ -71,22 +62,28 @@ class ZDFIE(InfoExtractor):
 
             quality = fnode.find('./quality').text
             abr = int(fnode.find('./audioBitrate').text) // 1000
-            vbr = int(fnode.find('./videoBitrate').text) // 1000
+            vbr_node = fnode.find('./videoBitrate')
+            vbr = None if vbr_node is None else int(vbr_node.text) // 1000
 
-            format_note = u''
+            width_node = fnode.find('./width')
+            width = None if width_node is None else int_or_none(width_node.text)
+            height_node = fnode.find('./height')
+            height = None if height_node is None else int_or_none(height_node.text)
+
+            format_note = ''
             if not format_note:
                 format_note = None
 
             return {
-                'format_id': format_id + u'-' + quality,
+                'format_id': format_id + '-' + quality,
                 'url': video_url,
                 'ext': ext,
                 'acodec': format_m.group('acodec'),
                 'vcodec': format_m.group('vcodec'),
                 'abr': abr,
                 'vbr': vbr,
-                'width': int_or_none(fnode.find('./width').text),
-                'height': int_or_none(fnode.find('./height').text),
+                'width': width,
+                'height': height,
                 'filesize': int_or_none(fnode.find('./filesize').text),
                 'format_note': format_note,
                 'protocol': proto,
@@ -103,9 +100,10 @@ class ZDFIE(InfoExtractor):
         return {
             'id': video_id,
             'title': title,
-            'formats': formats,
             'description': description,
-            'uploader': uploader,
             'duration': duration,
+            'uploader': uploader,
+            'uploader_id': uploader_id,
             'upload_date': upload_date,
-        }
+            'formats': formats,
+        }

youtube_dl/utils.py

@@ -1,6 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 
+import contextlib
 import ctypes
 import datetime
 import email.utils
@@ -17,6 +18,7 @@ import platform
 import re
 import ssl
 import socket
+import struct
 import subprocess
 import sys
 import traceback
@@ -173,6 +175,11 @@ try:
 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
+
 def compat_ord(c):
     if type(c) is int: return c
     else: return ord(c)
@@ -756,11 +763,12 @@ def unified_strdate(date_str):
     """Return a string with the date in the format YYYYMMDD"""
     upload_date = None
     #Replace commas
-    date_str = date_str.replace(',',' ')
+    date_str = date_str.replace(',', ' ')
     # %z (UTC offset) is only supported in python>=3.2
-    date_str = re.sub(r' ?(\+|-)[0-9:]*$', '', date_str)
+    date_str = re.sub(r' ?(\+|-)[0-9]{2}:?[0-9]{2}$', '', date_str)
     format_expressions = [
         '%d %B %Y',
+        '%d %b %Y',
         '%B %d %Y',
         '%b %d %Y',
         '%Y-%m-%d',
@@ -772,6 +780,7 @@ def unified_strdate(date_str):
         '%Y-%m-%dT%H:%M:%S.%fZ',
         '%Y-%m-%dT%H:%M:%S.%f0Z',
         '%Y-%m-%dT%H:%M:%S',
+        '%Y-%m-%dT%H:%M:%S.%f',
         '%Y-%m-%dT%H:%M',
     ]
     for expression in format_expressions:
@@ -1143,7 +1152,7 @@ def parse_duration(s):
         return None
 
     m = re.match(
-        r'(?:(?:(?P<hours>[0-9]+):)?(?P<mins>[0-9]+):)?(?P<secs>[0-9]+)$', s)
+        r'(?:(?:(?P<hours>[0-9]+)[:h])?(?P<mins>[0-9]+)[:m])?(?P<secs>[0-9]+)s?$', s)
     if not m:
         return None
     res = int(m.group('secs'))
@@ -1214,3 +1223,42 @@ class PagedList(object):
             if end == nextfirstid:
                 break
         return res
+
+
+def uppercase_escape(s):
+    return re.sub(
+        r'\\U([0-9a-fA-F]{8})',
+        lambda m: compat_chr(int(m.group(1), base=16)), s)
+
+try:
+    struct.pack(u'!I', 0)
+except TypeError:
+    # In Python 2.6 (and some 2.7 versions), struct requires a bytes argument
+    def struct_pack(spec, *args):
+        if isinstance(spec, compat_str):
+            spec = spec.encode('ascii')
+        return struct.pack(spec, *args)
+
+    def struct_unpack(spec, *args):
+        if isinstance(spec, compat_str):
+            spec = spec.encode('ascii')
+        return struct.unpack(spec, *args)
+else:
+    struct_pack = struct.pack
+    struct_unpack = struct.unpack
+
+
+def read_batch_urls(batch_fd):
+    def fixup(url):
+        if not isinstance(url, compat_str):
+            url = url.decode('utf-8', 'replace')
+        BOM_UTF8 = u'\xef\xbb\xbf'
+        if url.startswith(BOM_UTF8):
+            url = url[len(BOM_UTF8):]
+        url = url.strip()
+        if url.startswith(('#', ';', ']')):
+            return False
+        return url
+
+    with contextlib.closing(batch_fd) as fd:
+        return [url for url in map(fixup, fd) if url]

youtube_dl/version.py

@@ -1,2 +1,2 @@
 
-__version__ = '2014.02.08.1'
+__version__ = '2014.02.26'