release 2014.02.21.1

`ParseError` is not available, it raises `xml.parsers.expat.ExpatError`.
The webpage needs to be encoded.

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
 

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"))

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()
@@ -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

@@ -25,6 +25,7 @@ from youtube_dl.utils import (
     shell_quote,
     smuggle_url,
     str_to_int,
+    struct_unpack,
     timeconvert,
     unescapeHTML,
     unified_strdate,
@@ -201,7 +202,16 @@ 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(
@@ -237,5 +247,8 @@ 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,))
+
 if __name__ == '__main__':
     unittest.main()

youtube_dl/__init__.py

@@ -41,7 +41,11 @@ __authors__  = (
     'Chris Gahan',
     'Saimadhav Heblikar',
     'Mike Col',
+    'Oleg Prutz',
+    'pulpe',
     'Andreas Schmitz',
+    'Michael Kaiser',
+    'Niklas Laxström',
 )
 
 __license__ = 'Public Domain'
@@ -204,7 +208,7 @@ 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')

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 +1,315 @@
+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_urllib_request,
+    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)
+        # BootstrapinfoVersion
+        bootstrap_info_version = self.read_unsigned_int()
+        # 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()
+        # MovieIdentifier
+        movie_identifier = self.read_string()
+        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(server_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

@@ -73,6 +73,7 @@ from .fktv import (
     FKTVPosteckeIE,
 )
 from .flickr import FlickrIE
+from .fourtube import FourTubeIE
 from .franceinter import FranceInterIE
 from .francetv import (
     PluzzIE,
@@ -91,6 +92,7 @@ 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
@@ -209,10 +211,12 @@ 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

youtube_dl/extractor/bbccouk.py

@@ -13,13 +13,13 @@ class BBCCoUkIE(SubtitlesInfoExtractor):
 
     _TESTS = [
         {
-            'url': 'http://www.bbc.co.uk/programmes/p01q7wz1',
+            'url': 'http://www.bbc.co.uk/programmes/b039g8p7',
             'info_dict': {
-                'id': 'p01q7wz4',
+                'id': 'b039d07m',
                 '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,
+                'title': 'Kaleidoscope: Leonard Cohen',
+                'description': 'md5:db4755d7a665ae72343779f7dacb402c',
+                'duration': 1740,
             },
             'params': {
                 # rtmp download
@@ -38,7 +38,8 @@ class BBCCoUkIE(SubtitlesInfoExtractor):
             '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/',
@@ -161,6 +162,11 @@ class BBCCoUkIE(SubtitlesInfoExtractor):
         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')
 

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/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

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/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/ndr.py

@@ -26,15 +26,15 @@ class NDRIE(InfoExtractor):
             },
         },
         {
-            '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/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/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 +1,66 @@
+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)
+
+        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)/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 +51,34 @@ 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:
+            formats = [{
+                'ext': 'flv',
+                # the parameters are from syfy.com, other sites may use others
+                'url': f4m_node.attrib['src'] + '?g=UXWGVKRWHFSP&hdcore=3.0.3',
+            }]
+        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 +92,13 @@ 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_json = self._download_webpage(config_url, video_id, u'Downloading config')
+            config = json.loads(config_json)
+            smil_url = config['releaseUrl'] + '&format=SMIL&formats=MPEG4'
+        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/vesti.py

@@ -57,6 +57,7 @@ class VestiIE(InfoExtractor):
                 # m3u8 download
                 'skip_download': True,
             },
+            'skip': 'Blocked outside Russia'
         },
         {
             'url': 'http://sochi2014.vesti.ru/live/play/live_id/301',
@@ -86,8 +87,7 @@ class VestiIE(InfoExtractor):
             video_id = mobj.group('id')
         else:
             mobj = re.search(
-                r'<div.+?id="current-video-holder".*?>\s*<iframe src="http://player\.rutv\.ru/iframe/(?P<type>[^/]+)/id/(?P<id>\d+)[^"]*"',
-                page)
+                r'<iframe.+?src="http://player\.rutv\.ru/iframe/(?P<type>[^/]+)/id/(?P<id>\d+)[^"]*".*?></iframe>', page)
 
             if not mobj:
                 raise ExtractorError('No media found')

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/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/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/youtube.py

@@ -138,13 +138,14 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
                          (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/|
                             (?:www\.)?deturl\.com/www\.youtube\.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=
@@ -296,6 +297,23 @@ 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',
+            },
+        },
     ]
 
 
@@ -1271,8 +1289,8 @@ 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:
@@ -1365,12 +1383,24 @@ 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'):
@@ -1442,9 +1472,9 @@ 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):
@@ -1492,29 +1522,31 @@ 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)
@@ -1694,7 +1726,8 @@ 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
@@ -1814,7 +1847,7 @@ 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/utils.py

@@ -17,6 +17,7 @@ import platform
 import re
 import ssl
 import socket
+import struct
 import subprocess
 import sys
 import traceback
@@ -173,6 +174,11 @@ 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)
@@ -761,6 +767,7 @@ def unified_strdate(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',
@@ -1143,7 +1150,7 @@ 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'))
@@ -1220,3 +1227,20 @@ 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

youtube_dl/version.py

@@ -1,2 +1,2 @@
 
-__version__ = '2014.02.13'
+__version__ = '2014.02.21.1'