release 2014.09.29

This messes up the format when people paste it outside of code tags.

README.md

@@ -442,8 +442,6 @@ If you want to add support for a new site, you can follow this quick list (assum
     # coding: utf-8
     from __future__ import unicode_literals
 
-    import re
-
     from .common import InfoExtractor
 
 
@@ -451,7 +449,7 @@ If you want to add support for a new site, you can follow this quick list (assum
         _VALID_URL = r'https?://(?:www\.)?yourextractor\.com/watch/(?P<id>[0-9]+)'
         _TEST = {
             'url': 'http://yourextractor.com/watch/42',
-            'md5': 'TODO: md5 sum of the first 10KiB of the video file',
+            'md5': 'TODO: md5 sum of the first 10241 bytes of the video file (use --test)',
             'info_dict': {
                 'id': '42',
                 'ext': 'mp4',
@@ -466,8 +464,7 @@ If you want to add support for a new site, you can follow this quick list (assum
         }
 
         def _real_extract(self, url):
-            mobj = re.match(self._VALID_URL, url)
-            video_id = mobj.group('id')
+            video_id = self._match_id(url)
 
             # TODO more code goes here, for example ...
             webpage = self._download_webpage(url, video_id)

test/test_download.py

@@ -139,7 +139,9 @@ def generator(test_case):
 
             if is_playlist:
                 self.assertEqual(res_dict['_type'], 'playlist')
+                self.assertTrue('entries' in res_dict)
                 expect_info_dict(self, test_case.get('info_dict', {}), res_dict)
+
             if 'playlist_mincount' in test_case:
                 assertGreaterEqual(
                     self,
@@ -188,7 +190,7 @@ def generator(test_case):
                 expect_info_dict(self, tc.get('info_dict', {}), info_dict)
         finally:
             try_rm_tcs_files()
-            if is_playlist and res_dict is not None:
+            if is_playlist and res_dict is not None and res_dict.get('entries'):
                 # Remove all other files that may have been extracted if the
                 # extractor returns full results even with extract_flat
                 res_tcs = [{'info_dict': e} for e in res_dict['entries']]

test/test_utils.py

@@ -22,7 +22,8 @@ from youtube_dl.utils import (
     fix_xml_ampersands,
     get_meta_content,
     orderedSet,
-    PagedList,
+    OnDemandPagedList,
+    InAdvancePagedList,
     parse_duration,
     read_batch_urls,
     sanitize_filename,
@@ -246,10 +247,14 @@ class TestUtil(unittest.TestCase):
                 for i in range(firstid, upto):
                     yield i
 
-            pl = PagedList(get_page, pagesize)
+            pl = OnDemandPagedList(get_page, pagesize)
             got = pl.getslice(*sliceargs)
             self.assertEqual(got, expected)
 
+            iapl = InAdvancePagedList(get_page, size // pagesize + 1, pagesize)
+            got = iapl.getslice(*sliceargs)
+            self.assertEqual(got, expected)
+
         testPL(5, 2, (), [0, 1, 2, 3, 4])
         testPL(5, 2, (1,), [1, 2, 3, 4])
         testPL(5, 2, (2,), [2, 3, 4])

youtube_dl/YoutubeDL.py

@@ -1250,12 +1250,13 @@ class YoutubeDL(object):
         # urllib chokes on URLs with non-ASCII characters (see http://bugs.python.org/issue3991)
         # To work around aforementioned issue we will replace request's original URL with
         # percent-encoded one
-        url = req if isinstance(req, compat_str) else req.get_full_url()
+        req_is_string = isinstance(req, basestring if sys.version_info < (3, 0) else compat_str)
+        url = req if req_is_string else req.get_full_url()
         url_escaped = escape_url(url)
 
         # Substitute URL if any change after escaping
         if url != url_escaped:
-            if isinstance(req, compat_str):
+            if req_is_string:
                 req = url_escaped
             else:
                 req = compat_urllib_request.Request(

youtube_dl/__init__.py

@@ -78,6 +78,7 @@ __authors__  = (
     'Hari Padmanaban',
     'Carlos Ramos',
     '5moufl',
+    'lenaten',
 )
 
 __license__ = 'Public Domain'

youtube_dl/downloader/common.py

@@ -42,6 +42,7 @@ class FileDownloader(object):
     Subclasses of this one must re-define the real_download method.
     """
 
+    _TEST_FILE_SIZE = 10241
     params = None
 
     def __init__(self, ydl, params):

youtube_dl/downloader/hls.py

@@ -7,6 +7,7 @@ import subprocess
 from .common import FileDownloader
 from ..utils import (
     compat_urlparse,
+    compat_urllib_request,
     check_executable,
     encodeFilename,
 )
@@ -71,15 +72,26 @@ class NativeHlsFD(FileDownloader):
                     else compat_urlparse.urljoin(url, line))
                 segment_urls.append(segment_url)
 
+        is_test = self.params.get('test', False)
+        remaining_bytes = self._TEST_FILE_SIZE if is_test else None
         byte_counter = 0
         with open(tmpfilename, 'wb') as outf:
             for i, segurl in enumerate(segment_urls):
-                segment = self.ydl.urlopen(segurl).read()
-                outf.write(segment)
-                byte_counter += len(segment)
                 self.to_screen(
                     '[hlsnative] %s: Downloading segment %d / %d' %
                     (info_dict['id'], i + 1, len(segment_urls)))
+                seg_req = compat_urllib_request.Request(segurl)
+                if remaining_bytes is not None:
+                    seg_req.add_header('Range', 'bytes=0-%d' % (remaining_bytes - 1))
+
+                segment = self.ydl.urlopen(seg_req).read()
+                if remaining_bytes is not None:
+                    segment = segment[:remaining_bytes]
+                    remaining_bytes -= len(segment)
+                outf.write(segment)
+                byte_counter += len(segment)
+                if remaining_bytes is not None and remaining_bytes <= 0:
+                    break
 
         self._hook_progress({
             'downloaded_bytes': byte_counter,

youtube_dl/downloader/http.py

@@ -14,8 +14,6 @@ from ..utils import (
 
 
 class HttpFD(FileDownloader):
-    _TEST_FILE_SIZE = 10241
-
     def real_download(self, filename, info_dict):
         url = info_dict['url']
         tmpfilename = self.temp_name(filename)

youtube_dl/extractor/__init__.py

@@ -135,12 +135,14 @@ from .gametrailers import GametrailersIE
 from .gdcvault import GDCVaultIE
 from .generic import GenericIE
 from .godtube import GodTubeIE
+from .golem import GolemIE
 from .googleplus import GooglePlusIE
 from .googlesearch import GoogleSearchIE
 from .gorillavid import GorillaVidIE
 from .goshgay import GoshgayIE
 from .grooveshark import GroovesharkIE
 from .hark import HarkIE
+from .heise import HeiseIE
 from .helsinki import HelsinkiIE
 from .hentaistigma import HentaiStigmaIE
 from .hornbunny import HornBunnyIE
@@ -261,6 +263,7 @@ from .nrk import (
 from .ntv import NTVIE
 from .nytimes import NYTimesIE
 from .nuvid import NuvidIE
+from .oktoberfesttv import OktoberfestTVIE
 from .ooyala import OoyalaIE
 from .orf import (
     ORFTVthekIE,
@@ -271,6 +274,7 @@ from .parliamentliveuk import ParliamentLiveUKIE
 from .patreon import PatreonIE
 from .pbs import PBSIE
 from .photobucket import PhotobucketIE
+from .played import PlayedIE
 from .playfm import PlayFMIE
 from .playvid import PlayvidIE
 from .podomatic import PodomaticIE
@@ -339,6 +343,7 @@ from .spankwire import SpankwireIE
 from .spiegel import SpiegelIE, SpiegelArticleIE
 from .spiegeltv import SpiegeltvIE
 from .spike import SpikeIE
+from .sport5 import Sport5IE
 from .sportdeutschland import SportDeutschlandIE
 from .stanfordoc import StanfordOpenClassroomIE
 from .steam import SteamIE
@@ -366,7 +371,10 @@ from .thisav import ThisAVIE
 from .tinypic import TinyPicIE
 from .tlc import TlcIE, TlcDeIE
 from .tnaflix import TNAFlixIE
-from .thvideo import THVideoIE
+from .thvideo import (
+    THVideoIE,
+    THVideoPlaylistIE
+)
 from .toutv import TouTvIE
 from .toypics import ToypicsUserIE, ToypicsIE
 from .traileraddict import TrailerAddictIE
@@ -407,11 +415,12 @@ from .videoweed import VideoWeedIE
 from .vidme import VidmeIE
 from .vimeo import (
     VimeoIE,
-    VimeoChannelIE,
-    VimeoUserIE,
     VimeoAlbumIE,
+    VimeoChannelIE,
     VimeoGroupsIE,
+    VimeoLikesIE,
     VimeoReviewIE,
+    VimeoUserIE,
     VimeoWatchLaterIE,
 )
 from .vimple import VimpleIE
@@ -450,6 +459,7 @@ from .yahoo import (
     YahooNewsIE,
     YahooSearchIE,
 )
+from .ynet import YnetIE
 from .youjizz import YouJizzIE
 from .youku import YoukuIE
 from .youporn import YouPornIE

youtube_dl/extractor/abc.py

@@ -22,8 +22,7 @@ class ABCIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
         urls_info_json = self._search_regex(

youtube_dl/extractor/anysex.py

@@ -35,7 +35,7 @@ class AnySexIE(InfoExtractor):
 
         title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title')
         description = self._html_search_regex(
-            r'<div class="description">([^<]+)</div>', webpage, 'description', fatal=False)
+            r'<div class="description"[^>]*>([^<]+)</div>', webpage, 'description', fatal=False)
         thumbnail = self._html_search_regex(
             r'preview_url\s*:\s*\'(.*?)\'', webpage, 'thumbnail', fatal=False)
 
@@ -43,7 +43,7 @@ class AnySexIE(InfoExtractor):
             r'<a href="http://anysex\.com/categories/[^"]+" title="[^"]*">([^<]+)</a>', webpage)
 
         duration = parse_duration(self._search_regex(
-            r'<b>Duration:</b> (\d+:\d+)', webpage, 'duration', fatal=False))
+            r'<b>Duration:</b> (?:<q itemprop="duration">)?(\d+:\d+)', webpage, 'duration', fatal=False))
         view_count = int_or_none(self._html_search_regex(
             r'<b>Views:</b> (\d+)', webpage, 'view count', fatal=False))
 

youtube_dl/extractor/ard.py

@@ -8,8 +8,6 @@ from ..utils import (
     determine_ext,
     ExtractorError,
     qualities,
-    compat_urllib_parse_urlparse,
-    compat_urllib_parse,
     int_or_none,
     parse_duration,
     unified_strdate,

youtube_dl/extractor/common.py

@@ -1,6 +1,7 @@
 from __future__ import unicode_literals
 
 import base64
+import datetime
 import hashlib
 import json
 import netrc
@@ -21,6 +22,7 @@ from ..utils import (
     clean_html,
     compiled_regex_type,
     ExtractorError,
+    float_or_none,
     int_or_none,
     RegexNotFoundError,
     sanitize_filename,
@@ -164,6 +166,14 @@ class InfoExtractor(object):
             cls._VALID_URL_RE = re.compile(cls._VALID_URL)
         return cls._VALID_URL_RE.match(url) is not None
 
+    @classmethod
+    def _match_id(cls, url):
+        if '_VALID_URL_RE' not in cls.__dict__:
+            cls._VALID_URL_RE = re.compile(cls._VALID_URL)
+        m = cls._VALID_URL_RE.match(url)
+        assert m
+        return m.group('id')
+
     @classmethod
     def working(cls):
         """Getter method for _WORKING."""
@@ -705,6 +715,34 @@ class InfoExtractor(object):
         self._sort_formats(formats)
         return formats
 
+    def _live_title(self, name):
+        """ Generate the title for a live video """
+        now = datetime.datetime.now()
+        now_str = now.strftime("%Y-%m-%d %H:%M")
+        return name + ' ' + now_str
+
+    def _int(self, v, name, fatal=False, **kwargs):
+        res = int_or_none(v, **kwargs)
+        if 'get_attr' in kwargs:
+            print(getattr(v, kwargs['get_attr']))
+        if res is None:
+            msg = 'Failed to extract %s: Could not parse value %r' % (name, v)
+            if fatal:
+                raise ExtractorError(msg)
+            else:
+                self._downloader.report_warning(msg)
+        return res
+
+    def _float(self, v, name, fatal=False, **kwargs):
+        res = float_or_none(v, **kwargs)
+        if res is None:
+            msg = 'Failed to extract %s: Could not parse value %r' % (name, v)
+            if fatal:
+                raise ExtractorError(msg)
+            else:
+                self._downloader.report_warning(msg)
+        return res
+
 
 class SearchInfoExtractor(InfoExtractor):
     """

youtube_dl/extractor/crunchyroll.py

@@ -9,7 +9,7 @@ import xml.etree.ElementTree
 
 from hashlib import sha1
 from math import pow, sqrt, floor
-from .common import InfoExtractor
+from .subtitles import SubtitlesInfoExtractor
 from ..utils import (
     ExtractorError,
     compat_urllib_parse,
@@ -26,7 +26,7 @@ from ..aes import (
 )
 
 
-class CrunchyrollIE(InfoExtractor):
+class CrunchyrollIE(SubtitlesInfoExtractor):
     _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',
@@ -271,6 +271,10 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
             else:
                 subtitles[lang_code] = self._convert_subtitles_to_srt(subtitle)
 
+        if self._downloader.params.get('listsubtitles', False):
+            self._list_available_subtitles(video_id, subtitles)
+            return
+
         return {
             'id':          video_id,
             'title':       video_title,

youtube_dl/extractor/eitb.py

@@ -1,4 +1,6 @@
 # encoding: utf-8
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -7,20 +9,20 @@ from ..utils import ExtractorError
 
 
 class EitbIE(InfoExtractor):
-    IE_NAME = u'eitb.tv'
+    IE_NAME = 'eitb.tv'
     _VALID_URL = r'https?://www\.eitb\.tv/(eu/bideoa|es/video)/[^/]+/(?P<playlist_id>\d+)/(?P<chapter_id>\d+)'
 
     _TEST = {
-        u'add_ie': ['Brightcove'],
-        u'url': u'http://www.eitb.tv/es/video/60-minutos-60-minutos-2013-2014/2677100210001/2743577154001/lasa-y-zabala-30-anos/',
-        u'md5': u'edf4436247185adee3ea18ce64c47998',
-        u'info_dict': {
-            u'id': u'2743577154001',
-            u'ext': u'mp4',
-            u'title': u'60 minutos (Lasa y Zabala, 30 años)',
+        'add_ie': ['Brightcove'],
+        'url': 'http://www.eitb.tv/es/video/60-minutos-60-minutos-2013-2014/2677100210001/2743577154001/lasa-y-zabala-30-anos/',
+        'md5': 'edf4436247185adee3ea18ce64c47998',
+        'info_dict': {
+            'id': '2743577154001',
+            'ext': 'mp4',
+            'title': '60 minutos (Lasa y Zabala, 30 años)',
             # All videos from eitb has this description in the brightcove info
-            u'description': u'.',
-            u'uploader': u'Euskal Telebista',
+            'description': '.',
+            'uploader': 'Euskal Telebista',
         },
     }
 
@@ -30,7 +32,7 @@ class EitbIE(InfoExtractor):
         webpage = self._download_webpage(url, chapter_id)
         bc_url = BrightcoveIE._extract_brightcove_url(webpage)
         if bc_url is None:
-            raise ExtractorError(u'Could not extract the Brightcove url')
+            raise ExtractorError('Could not extract the Brightcove url')
         # The BrightcoveExperience object doesn't contain the video id, we set
         # it manually
         bc_url += '&%40videoPlayer={0}'.format(chapter_id)

youtube_dl/extractor/extremetube.py

@@ -7,6 +7,7 @@ from ..utils import (
     compat_urllib_parse_urlparse,
     compat_urllib_request,
     compat_urllib_parse,
+    str_to_int,
 )
 
 
@@ -20,6 +21,7 @@ class ExtremeTubeIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Music Video 14 british euro brit european cumshots swallow',
             'uploader': 'unknown',
+            'view_count': int,
             'age_limit': 18,
         }
     }, {
@@ -39,8 +41,12 @@ class ExtremeTubeIE(InfoExtractor):
         video_title = self._html_search_regex(
             r'<h1 [^>]*?title="([^"]+)"[^>]*>', webpage, 'title')
         uploader = self._html_search_regex(
-            r'>Posted by:(?=<)(?:\s|<[^>]*>)*(.+?)\|', webpage, 'uploader',
-            fatal=False)
+            r'Uploaded by:\s*</strong>\s*(.+?)\s*</div>',
+            webpage, 'uploader', fatal=False)
+        view_count = str_to_int(self._html_search_regex(
+            r'Views:\s*</strong>\s*<span>([\d,\.]+)</span>',
+            webpage, 'view count', fatal=False))
+
         video_url = compat_urllib_parse.unquote(self._html_search_regex(
             r'video_url=(.+?)&amp;', webpage, 'video_url'))
         path = compat_urllib_parse_urlparse(video_url).path
@@ -51,6 +57,7 @@ class ExtremeTubeIE(InfoExtractor):
             'id': video_id,
             'title': video_title,
             'uploader': uploader,
+            'view_count': view_count,
             'url': video_url,
             'format': format,
             'format_id': format,

youtube_dl/extractor/generic.py

@@ -382,14 +382,21 @@ class GenericIE(InfoExtractor):
                 'thumbnail': 're:^https?://.*\.jpg$',
             },
         },
+        # Wistia embed
+        {
+            'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
+            'md5': '8788b683c777a5cf25621eaf286d0c23',
+            'info_dict': {
+                'id': '1cfaf6b7ea',
+                'ext': 'mov',
+                'title': 'md5:51364a8d3d009997ba99656004b5e20d',
+                'duration': 643.0,
+                'filesize': 182808282,
+                'uploader': 'education-portal.com',
+            },
+        },
     ]
 
-    def report_download_webpage(self, video_id):
-        """Report webpage download."""
-        if not self._downloader.params.get('test', False):
-            self._downloader.report_warning('Falling back on generic information extractor.')
-        super(GenericIE, self).report_download_webpage(video_id)
-
     def report_following_redirect(self, new_url):
         """Report information extraction."""
         self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
@@ -489,6 +496,7 @@ class GenericIE(InfoExtractor):
 
         url, smuggled_data = unsmuggle_url(url)
         force_videoid = None
+        is_intentional = smuggled_data and smuggled_data.get('to_generic')
         if smuggled_data and 'force_videoid' in smuggled_data:
             force_videoid = smuggled_data['force_videoid']
             video_id = force_videoid
@@ -531,6 +539,9 @@ class GenericIE(InfoExtractor):
                     'upload_date': upload_date,
                 }
 
+        if not self._downloader.params.get('test', False) and not is_intentional:
+            self._downloader.report_warning('Falling back on generic information extractor.')
+
         try:
             webpage = self._download_webpage(url, video_id)
         except ValueError:
@@ -631,7 +642,7 @@ class GenericIE(InfoExtractor):
             )
             (["\'])
                 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
-                (?:embed|v)/.+?)
+                (?:embed|v|p)/.+?)
             \1''', webpage)
         if matches:
             return _playlist_from_matches(
@@ -656,6 +667,16 @@ class GenericIE(InfoExtractor):
                 'title': video_title,
                 'id': video_id,
             }
+        match = re.search(r'(?:id=["\']wistia_|data-wistiaid=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
+        if match:
+            return {
+                '_type': 'url_transparent',
+                'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
+                'ie_key': 'Wistia',
+                'uploader': video_uploader,
+                'title': video_title,
+                'id': match.group('id')
+            }
 
         # Look for embedded blip.tv player
         mobj = re.search(r'<meta\s[^>]*https?://api\.blip\.tv/\w+/redirect/\w+/(\d+)', webpage)

youtube_dl/extractor/golem.py

@@ -0,0 +1,71 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urlparse,
+    determine_ext,
+)
+
+
+class GolemIE(InfoExtractor):
+    _VALID_URL = r'^https?://video\.golem\.de/.+?/(?P<id>.+?)/'
+    _TEST = {
+        'url': 'http://video.golem.de/handy/14095/iphone-6-und-6-plus-test.html',
+        'md5': 'c1a2c0a3c863319651c7c992c5ee29bf',
+        'info_dict': {
+            'id': '14095',
+            'format_id': 'high',
+            'ext': 'mp4',
+            'title': 'iPhone 6 und 6 Plus - Test',
+            'duration': 300.44,
+            'filesize': 65309548,
+        }
+    }
+
+    _PREFIX = 'http://video.golem.de'
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        config = self._download_xml(
+            'https://video.golem.de/xml/{0}.xml'.format(video_id), video_id)
+
+        info = {
+            'id': video_id,
+            'title': config.findtext('./title', 'golem'),
+            'duration': self._float(config.findtext('./playtime'), 'duration'),
+        }
+
+        formats = []
+        for e in config.findall('./*[url]'):
+            url = e.findtext('./url')
+            if not url:
+                self._downloader.report_warning(
+                    "{0}: url: empty, skipping".format(e.tag))
+                continue
+
+            formats.append({
+                'format_id': e.tag,
+                'url': compat_urlparse.urljoin(self._PREFIX, url),
+                'height': self._int(e.get('height'), 'height'),
+                'width': self._int(e.get('width'), 'width'),
+                'filesize': self._int(e.findtext('filesize'), 'filesize'),
+                'ext': determine_ext(e.findtext('./filename')),
+            })
+        self._sort_formats(formats)
+        info['formats'] = formats
+
+        thumbnails = []
+        for e in config.findall('.//teaser[url]'):
+            url = e.findtext('./url')
+            if not url:
+                continue
+            thumbnails.append({
+                'url': compat_urlparse.urljoin(self._PREFIX, url),
+                'width': self._int(e.get('width'), 'thumbnail width'),
+                'height': self._int(e.get('height'), 'thumbnail height'),
+            })
+        info['thumbnails'] = thumbnails
+
+        return info

youtube_dl/extractor/heise.py

@@ -0,0 +1,81 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    get_meta_content,
+    parse_iso8601,
+)
+
+
+class HeiseIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+        https?://(?:www\.)?heise\.de/video/artikel/
+        .+?(?P<id>[0-9]+)\.html(?:$|[?#])
+    '''
+    _TEST = {
+        'url': (
+            'http://www.heise.de/video/artikel/Podcast-c-t-uplink-3-3-Owncloud-Tastaturen-Peilsender-Smartphone-2404147.html'
+        ),
+        'md5': 'ffed432483e922e88545ad9f2f15d30e',
+        'info_dict': {
+            'id': '2404147',
+            'ext': 'mp4',
+            'title': (
+                "Podcast: c't uplink 3.3 – Owncloud / Tastaturen / Peilsender Smartphone"
+            ),
+            'format_id': 'mp4_720',
+            'timestamp': 1411812600,
+            'upload_date': '20140927',
+            'description': 'In uplink-Episode 3.3 geht es darum, wie man sich von Cloud-Anbietern emanzipieren kann, worauf man beim Kauf einer Tastatur achten sollte und was Smartphones über uns verraten.',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+        json_url = self._search_regex(
+            r'json_url:\s*"([^"]+)"', webpage, 'json URL')
+        config = self._download_json(json_url, video_id)
+
+        info = {
+            'id': video_id,
+            'thumbnail': config.get('poster'),
+            'timestamp': parse_iso8601(get_meta_content('date', webpage)),
+            'description': self._og_search_description(webpage),
+        }
+
+        title = get_meta_content('fulltitle', webpage)
+        if title:
+            info['title'] = title
+        elif config.get('title'):
+            info['title'] = config['title']
+        else:
+            info['title'] = self._og_search_title(webpage)
+
+        formats = []
+        for t, rs in config['formats'].items():
+            if not rs or not hasattr(rs, 'items'):
+                self._downloader.report_warning(
+                    'formats: {0}: no resolutions'.format(t))
+                continue
+
+            for height_str, obj in rs.items():
+                format_id = '{0}_{1}'.format(t, height_str)
+
+                if not obj or not obj.get('url'):
+                    self._downloader.report_warning(
+                        'formats: {0}: no url'.format(format_id))
+                    continue
+
+                formats.append({
+                    'url': obj['url'],
+                    'format_id': format_id,
+                    'height': self._int(height_str, 'height'),
+                })
+
+        self._sort_formats(formats)
+        info['formats'] = formats
+
+        return info

youtube_dl/extractor/muenchentv.py

@@ -1,7 +1,6 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import datetime
 import json
 
 from .common import InfoExtractor
@@ -23,6 +22,7 @@ class MuenchenTVIE(InfoExtractor):
             'ext': 'mp4',
             'title': 're:^münchen.tv-Livestream [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
             'is_live': True,
+            'thumbnail': 're:^https?://.*\.jpg$'
         },
         'params': {
             'skip_download': True,
@@ -33,9 +33,7 @@ class MuenchenTVIE(InfoExtractor):
         display_id = 'live'
         webpage = self._download_webpage(url, display_id)
 
-        now = datetime.datetime.now()
-        now_str = now.strftime("%Y-%m-%d %H:%M")
-        title = self._og_search_title(webpage) + ' ' + now_str
+        title = self._live_title(self._og_search_title(webpage))
 
         data_js = self._search_regex(
             r'(?s)\nplaylist:\s*(\[.*?}\]),related:',
@@ -73,5 +71,6 @@ class MuenchenTVIE(InfoExtractor):
             'title': title,
             'formats': formats,
             'is_live': True,
+            'thumbnail': thumbnail,
         }
 

youtube_dl/extractor/nfl.py

@@ -6,6 +6,7 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
+    compat_urllib_parse,
     int_or_none,
     remove_end,
 )
@@ -13,76 +14,116 @@ from ..utils import (
 
 class NFLIE(InfoExtractor):
     IE_NAME = 'nfl.com'
-    _VALID_URL = r'(?x)https?://(?:www\.)?nfl\.com/(?:videos/(?:.+)/|.*?\#video=)(?P<id>\d..[0-9]+)'
-    _PLAYER_CONFIG_URL = 'http://www.nfl.com/static/content/static/config/video/config.json'
-    _TEST = {
-        'url': 'http://www.nfl.com/videos/nfl-game-highlights/0ap3000000398478/Week-3-Redskins-vs-Eagles-highlights',
-        # 'md5': '5eb8c40a727dda106d510e5d6ffa79e5',  # md5 checksum fluctuates
-        'info_dict': {
-            'id': '0ap3000000398478',
-            'ext': 'mp4',
-            'title': 'Week 3: Washington Redskins vs. Philadelphia Eagles highlights',
-            'description': 'md5:56323bfb0ac4ee5ab24bd05fdf3bf478',
-            'upload_date': '20140921',
-            'timestamp': 1411337580,
-            'thumbnail': 're:^https?://.*\.jpg$',
+    _VALID_URL = r'''(?x)https?://
+        (?P<host>(?:www\.)?(?:nfl\.com|.*?\.clubs\.nfl\.com))/
+        (?:.+?/)*
+        (?P<id>(?:\d[a-z]{2}\d{13}|\w{8}\-(?:\w{4}\-){3}\w{12}))'''
+    _TESTS = [
+        {
+            'url': 'http://www.nfl.com/videos/nfl-game-highlights/0ap3000000398478/Week-3-Redskins-vs-Eagles-highlights',
+            'md5': '394ef771ddcd1354f665b471d78ec4c6',
+            'info_dict': {
+                'id': '0ap3000000398478',
+                'ext': 'mp4',
+                'title': 'Week 3: Redskins vs. Eagles highlights',
+                'description': 'md5:56323bfb0ac4ee5ab24bd05fdf3bf478',
+                'upload_date': '20140921',
+                'timestamp': 1411337580,
+                'thumbnail': 're:^https?://.*\.jpg$',
+            }
+        },
+        {
+            'url': 'http://prod.www.steelers.clubs.nfl.com/video-and-audio/videos/LIVE_Post_Game_vs_Browns/9d72f26a-9e2b-4718-84d3-09fb4046c266',
+            'md5': 'cf85bdb4bc49f6e9d3816d130c78279c',
+            'info_dict': {
+                'id': '9d72f26a-9e2b-4718-84d3-09fb4046c266',
+                'ext': 'mp4',
+                'title': 'LIVE: Post Game vs. Browns',
+                'description': 'md5:6a97f7e5ebeb4c0e69a418a89e0636e8',
+                'upload_date': '20131229',
+                'timestamp': 1388354455,
+                'thumbnail': 're:^https?://.*\.jpg$',
+            }
+        }
+    ]
+
+    @staticmethod
+    def prepend_host(host, url):
+        if not url.startswith('http'):
+            if not url.startswith('/'):
+                url = '/%s' % url
+            url = 'http://{0:}{1:}'.format(host, url)
+        return url
+
+    @staticmethod
+    def format_from_stream(stream, protocol, host, path_prefix='',
+                           preference=0, note=None):
+        url = '{protocol:}://{host:}/{prefix:}{path:}'.format(
+            protocol=protocol,
+            host=host,
+            prefix=path_prefix,
+            path=stream.get('path'),
+        )
+        return {
+            'url': url,
+            'vbr': int_or_none(stream.get('rate', 0), 1000),
+            'preference': preference,
+            'format_note': note,
         }
-    }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id, host = mobj.group('id'), mobj.group('host')
 
-        config = self._download_json(self._PLAYER_CONFIG_URL, video_id,
+        webpage = self._download_webpage(url, video_id)
+
+        config_url = NFLIE.prepend_host(host, self._search_regex(
+            r'(?:config|configURL)\s*:\s*"([^"]+)"', webpage, 'config URL'))
+        config = self._download_json(config_url, video_id,
                                      note='Downloading player config')
-        url_template = 'http://nfl.com{contentURLTemplate:s}'.format(**config)
-        video_data = self._download_json(url_template.format(id=video_id), video_id)
-
-        cdns = config.get('cdns')
-        if not cdns:
-            raise ExtractorError('Failed to get CDN data', expected=True)
+        url_template = NFLIE.prepend_host(
+            host, '{contentURLTemplate:}'.format(**config))
+        video_data = self._download_json(
+            url_template.format(id=video_id), video_id)
 
         formats = []
-        streams = video_data.get('cdnData', {}).get('bitrateInfo', [])
-        for name, cdn in cdns.items():
-            # LimeLight streams don't seem to work
-            if cdn.get('name') == 'LIMELIGHT':
-                continue
-
-            protocol = cdn.get('protocol')
-            host = remove_end(cdn.get('host', ''), '/')
-            if not (protocol and host):
-                continue
-
-            path_prefix = cdn.get('pathprefix', '')
-            if path_prefix and not path_prefix.endswith('/'):
-                path_prefix = '%s/' % path_prefix
-
-            get_url = lambda p: '{protocol:s}://{host:s}/{prefix:s}{path:}'.format(
-                protocol=protocol,
-                host=host,
-                prefix=path_prefix,
-                path=p,
-            )
-
-            if protocol == 'rtmp':
-                preference = -2
-            elif 'prog' in name.lower():
-                preference = -1
-            else:
-                preference = 0
-
+        cdn_data = video_data.get('cdnData', {})
+        streams = cdn_data.get('bitrateInfo', [])
+        if cdn_data.get('format') == 'EXTERNAL_HTTP_STREAM':
+            parts = compat_urllib_parse.urlparse(cdn_data.get('uri'))
+            protocol, host = parts.scheme, parts.netloc
             for stream in streams:
-                path = stream.get('path')
-                if not path:
+                formats.append(
+                    NFLIE.format_from_stream(stream, protocol, host))
+        else:
+            cdns = config.get('cdns')
+            if not cdns:
+                raise ExtractorError('Failed to get CDN data', expected=True)
+
+            for name, cdn in cdns.items():
+                # LimeLight streams don't seem to work
+                if cdn.get('name') == 'LIMELIGHT':
                     continue
 
-                formats.append({
-                    'url': get_url(path),
-                    'vbr': int_or_none(stream.get('rate', 0), 1000),
-                    'preference': preference,
-                    'format_note': name,
-                })
+                protocol = cdn.get('protocol')
+                host = remove_end(cdn.get('host', ''), '/')
+                if not (protocol and host):
+                    continue
+
+                prefix = cdn.get('pathprefix', '')
+                if prefix and not prefix.endswith('/'):
+                    prefix = '%s/' % prefix
+
+                preference = 0
+                if protocol == 'rtmp':
+                    preference = -2
+                elif 'prog' in name.lower():
+                    preference = 1
+
+                for stream in streams:
+                    formats.append(
+                        NFLIE.format_from_stream(stream, protocol, host,
+                                                 prefix, preference, name))
 
         self._sort_formats(formats)
 
@@ -94,7 +135,7 @@ class NFLIE(InfoExtractor):
 
         return {
             'id': video_id,
-            'title': video_data.get('storyHeadline'),
+            'title': video_data.get('headline'),
             'formats': formats,
             'description': video_data.get('caption'),
             'duration': video_data.get('duration'),

youtube_dl/extractor/oktoberfesttv.py

@@ -0,0 +1,47 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class OktoberfestTVIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.oktoberfest-tv\.de/[^/]+/[^/]+/video/(?P<id>[^/?#]+)'
+
+    _TEST = {
+        'url': 'http://www.oktoberfest-tv.de/de/kameras/video/hb-zelt',
+        'info_dict': {
+            'id': 'hb-zelt',
+            'ext': 'mp4',
+            'title': 're:^Live-Kamera: Hofbräuzelt [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'is_live': True,
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._live_title(self._html_search_regex(
+            r'<h1><strong>.*?</strong>(.*?)</h1>', webpage, 'title'))
+
+        clip = self._search_regex(
+            r"clip:\s*\{\s*url:\s*'([^']+)'", webpage, 'clip')
+        ncurl = self._search_regex(
+            r"netConnectionUrl:\s*'([^']+)'", webpage, 'rtmp base')
+        video_url = ncurl + clip
+        thumbnail = self._search_regex(
+            r"canvas:\s*\{\s*backgroundImage:\s*'url\(([^)]+)\)'", webpage,
+            'thumbnail', fatal=False)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'url': video_url,
+            'ext': 'mp4',
+            'is_live': True,
+            'thumbnail': thumbnail,
+        }

youtube_dl/extractor/played.py

@@ -0,0 +1,55 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+import os.path
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_parse,
+    compat_urllib_request,
+)
+
+
+class PlayedIE(InfoExtractor):
+    IE_NAME = 'played.to'
+    _VALID_URL = r'https?://(?:www\.)?played\.to/(?P<id>[a-zA-Z0-9_-]+)'
+
+    _TEST = {
+        'url': 'http://played.to/j2f2sfiiukgt',
+        'md5': 'c2bd75a368e82980e7257bf500c00637',
+        'info_dict': {
+            'id': 'j2f2sfiiukgt',
+            'ext': 'flv',
+            'title': 'youtube-dl_test_video.mp4',
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        orig_webpage = self._download_webpage(url, video_id)
+        fields = re.findall(
+            r'type="hidden" name="([^"]+)"\s+value="([^"]+)">', orig_webpage)
+        data = dict(fields)
+
+        self._sleep(2, video_id)
+
+        post = compat_urllib_parse.urlencode(data)
+        headers = {
+            b'Content-Type': b'application/x-www-form-urlencoded',
+        }
+        req = compat_urllib_request.Request(url, post, headers)
+        webpage = self._download_webpage(
+            req, video_id, note='Downloading video page ...')
+
+        title = os.path.splitext(data['fname'])[0]
+
+        video_url = self._search_regex(
+            r'file: "?(.+?)",', webpage, 'video URL')
+
+        return {
+            'id': video_id,
+            'title': title,
+            'url': video_url,
+        }

youtube_dl/extractor/sport5.py

@@ -0,0 +1,92 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+
+class Sport5IE(InfoExtractor):
+    _VALID_URL = r'http://(?:www|vod)?\.sport5\.co\.il/.*\b(?:Vi|docID)=(?P<id>\d+)'
+    _TESTS = [
+        {
+            'url': 'http://vod.sport5.co.il/?Vc=147&Vi=176331&Page=1',
+            'info_dict': {
+                'id': 's5-Y59xx1-GUh2',
+                'ext': 'mp4',
+                'title': 'ולנסיה-קורדובה 0:3',
+                'description': 'אלקאסר, גאייה ופגולי סידרו לקבוצה של נונו ניצחון על קורדובה ואת המקום הראשון בליגה',
+                'duration': 228,
+                'categories': list,
+            },
+            'skip': 'Blocked outside of Israel',
+        }, {
+            'url': 'http://www.sport5.co.il/articles.aspx?FolderID=3075&docID=176372&lang=HE',
+            'info_dict': {
+                'id': 's5-SiXxx1-hKh2',
+                'ext': 'mp4',
+                'title': 'GOALS_CELTIC_270914.mp4',
+                'description': '',
+                'duration': 87,
+                'categories': list,
+            },
+            'skip': 'Blocked outside of Israel',
+        }
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        media_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, media_id)
+
+        video_id = self._html_search_regex('clipId=([\w-]+)', webpage, 'video id')
+
+        metadata = self._download_xml(
+            'http://sport5-metadata-rr-d.nsacdn.com/vod/vod/%s/HDS/metadata.xml' % video_id,
+            video_id)
+
+        error = metadata.find('./Error')
+        if error is not None:
+            raise ExtractorError(
+                '%s returned error: %s - %s' % (
+                    self.IE_NAME,
+                    error.find('./Name').text,
+                    error.find('./Description').text),
+                expected=True)
+
+        title = metadata.find('./Title').text
+        description = metadata.find('./Description').text
+        duration = int(metadata.find('./Duration').text)
+
+        posters_el = metadata.find('./PosterLinks')
+        thumbnails = [{
+            'url': thumbnail.text,
+            'width': int(thumbnail.get('width')),
+            'height': int(thumbnail.get('height')),
+        } for thumbnail in posters_el.findall('./PosterIMG')] if posters_el is not None else []
+
+        categories_el = metadata.find('./Categories')
+        categories = [
+            cat.get('name') for cat in categories_el.findall('./Category')
+        ] if categories_el is not None else []
+
+        formats = [{
+            'url': fmt.text,
+            'ext': 'mp4',
+            'vbr': int(fmt.get('bitrate')),
+            'width': int(fmt.get('width')),
+            'height': int(fmt.get('height')),
+        } for fmt in metadata.findall('./PlaybackLinks/FileURL')]
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnails': thumbnails,
+            'duration': duration,
+            'categories': categories,
+            'formats': formats,
+        }

youtube_dl/extractor/thvideo.py

@@ -26,8 +26,7 @@ class THVideoIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
 
         # extract download link from mobile player page
         webpage_player = self._download_webpage(
@@ -57,3 +56,29 @@ class THVideoIE(InfoExtractor):
             'description': description,
             'upload_date': upload_date
         }
+
+
+class THVideoPlaylistIE(InfoExtractor):
+    _VALID_URL = r'http?://(?:www\.)?thvideo\.tv/mylist(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://thvideo.tv/mylist2',
+        'info_dict': {
+            'id': '2',
+            'title': '幻想万華鏡',
+        },
+        'playlist_mincount': 23,
+    }
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, playlist_id)
+        list_title = self._html_search_regex(
+            r'<h1 class="show_title">(.*?)<b id', webpage, 'playlist title',
+            fatal=False)
+
+        entries = [
+            self.url_result('http://thvideo.tv/v/th' + id, 'THVideo')
+            for id in re.findall(r'<dd><a href="http://thvideo.tv/v/th(\d+)/" target=', webpage)]
+
+        return self.playlist_result(entries, playlist_id, list_title)

youtube_dl/extractor/vbox7.py

@@ -19,7 +19,7 @@ class Vbox7IE(InfoExtractor):
         'md5': '99f65c0c9ef9b682b97313e052734c3f',
         'info_dict': {
             'id': '249bb972c2',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': 'Смях! Чудо - чист за секунди - Скрита камера',
         },
     }
@@ -50,7 +50,6 @@ class Vbox7IE(InfoExtractor):
         return {
             'id': video_id,
             'url': final_url,
-            'ext': 'flv',
             'title': title,
             'thumbnail': thumbnail_url,
         }

youtube_dl/extractor/vevo.py

@@ -5,7 +5,6 @@ import xml.etree.ElementTree
 
 from .common import InfoExtractor
 from ..utils import (
-    compat_HTTPError,
     compat_urllib_request,
     ExtractorError,
 )
@@ -25,7 +24,7 @@ class VevoIE(InfoExtractor):
 
     _TESTS = [{
         'url': 'http://www.vevo.com/watch/hurts/somebody-to-die-for/GB1101300280',
-        "md5": "06bea460acb744eab74a9d7dcb4bfd61",
+        "md5": "95ee28ee45e70130e3ab02b0f579ae23",
         'info_dict': {
             'id': 'GB1101300280',
             'ext': 'mp4',
@@ -41,7 +40,7 @@ class VevoIE(InfoExtractor):
     }, {
         'note': 'v3 SMIL format',
         'url': 'http://www.vevo.com/watch/cassadee-pope/i-wish-i-could-break-your-heart/USUV71302923',
-        'md5': '893ec0e0d4426a1d96c01de8f2bdff58',
+        'md5': 'f6ab09b034f8c22969020b042e5ac7fc',
         'info_dict': {
             'id': 'USUV71302923',
             'ext': 'mp4',

youtube_dl/extractor/vimeo.py

@@ -8,17 +8,19 @@ import itertools
 from .common import InfoExtractor
 from .subtitles import SubtitlesInfoExtractor
 from ..utils import (
+    clean_html,
     compat_HTTPError,
     compat_urllib_parse,
     compat_urllib_request,
-    clean_html,
-    get_element_by_attribute,
+    compat_urlparse,
     ExtractorError,
+    get_element_by_attribute,
+    InAdvancePagedList,
+    int_or_none,
     RegexNotFoundError,
     std_headers,
     unsmuggle_url,
     urlencode_postdata,
-    int_or_none,
 )
 
 
@@ -529,3 +531,58 @@ class VimeoWatchLaterIE(VimeoBaseInfoExtractor, VimeoChannelIE):
 
     def _real_extract(self, url):
         return self._extract_videos('watchlater', 'https://vimeo.com/home/watchlater')
+
+
+class VimeoLikesIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?vimeo\.com/user(?P<id>[0-9]+)/likes/?(?:$|[?#]|sort:)'
+    IE_NAME = 'vimeo:likes'
+    IE_DESC = 'Vimeo user likes'
+    _TEST = {
+        'url': 'https://vimeo.com/user755559/likes/',
+        'playlist_mincount': 293,
+        "info_dict": {
+            "description": "See all the videos urza likes",
+            "title": 'Videos urza likes',
+        },
+    }
+
+    def _real_extract(self, url):
+        user_id = self._match_id(url)
+        webpage = self._download_webpage(url, user_id)
+        page_count = self._int(
+            self._search_regex(
+                r'''(?x)<li><a\s+href="[^"]+"\s+data-page="([0-9]+)">
+                    .*?</a></li>\s*<li\s+class="pagination_next">
+                ''', webpage, 'page count'),
+            'page count', fatal=True)
+        PAGE_SIZE = 12
+        title = self._html_search_regex(
+            r'(?s)<h1>(.+?)</h1>', webpage, 'title', fatal=False)
+        description = self._html_search_meta('description', webpage)
+
+        def _get_page(idx):
+            page_url = '%s//vimeo.com/user%s/likes/page:%d/sort:date' % (
+                self.http_scheme(), user_id, idx + 1)
+            webpage = self._download_webpage(
+                page_url, user_id,
+                note='Downloading page %d/%d' % (idx + 1, page_count))
+            video_list = self._search_regex(
+                r'(?s)<ol class="js-browse_list[^"]+"[^>]*>(.*?)</ol>',
+                webpage, 'video content')
+            paths = re.findall(
+                r'<li[^>]*>\s*<a\s+href="([^"]+)"', video_list)
+            for path in paths:
+                yield {
+                    '_type': 'url',
+                    'url': compat_urlparse.urljoin(page_url, path),
+                }
+
+        pl = InAdvancePagedList(_get_page, page_count, PAGE_SIZE)
+
+        return {
+            '_type': 'playlist',
+            'id': 'user%s_likes' % user_id,
+            'title': title,
+            'description': description,
+            'entries': pl,
+        }

youtube_dl/extractor/vube.py

@@ -6,6 +6,7 @@ from .common import InfoExtractor
 from ..utils import (
     int_or_none,
     compat_str,
+    ExtractorError,
 )
 
 
@@ -16,6 +17,24 @@ class VubeIE(InfoExtractor):
 
     _TESTS = [
         {
+            'url': 'http://vube.com/trending/William+Wei/Y8NUZ69Tf7?t=s',
+            'md5': 'e7aabe1f8f1aa826b9e4735e1f9cee42',
+            'info_dict': {
+                'id': 'Y8NUZ69Tf7',
+                'ext': 'mp4',
+                'title': 'Best Drummer Ever [HD]',
+                'description': 'md5:2d63c4b277b85c2277761c2cf7337d71',
+                'thumbnail': 're:^https?://.*\.jpg',
+                'uploader': 'William',
+                'timestamp': 1406876915,
+                'upload_date': '20140801',
+                'duration': 258.051,
+                'like_count': int,
+                'dislike_count': int,
+                'comment_count': int,
+                'categories': ['amazing', 'hd', 'best drummer ever', 'william wei', 'bucket drumming', 'street drummer', 'epic street drumming'],
+            },
+        }, {
             'url': 'http://vube.com/Chiara+Grispo+Video+Channel/YL2qNPkqon',
             'md5': 'db7aba89d4603dadd627e9d1973946fe',
             'info_dict': {
@@ -32,7 +51,8 @@ class VubeIE(InfoExtractor):
                 'dislike_count': int,
                 'comment_count': int,
                 'categories': ['pop', 'music', 'cover', 'singing', 'jessie j', 'price tag', 'chiara grispo'],
-            }
+            },
+            'skip': 'Removed due to DMCA',
         },
         {
             'url': 'http://vube.com/SerainaMusic/my-7-year-old-sister-and-i-singing-alive-by-krewella/UeBhTudbfS?t=s&n=1',
@@ -51,7 +71,8 @@ class VubeIE(InfoExtractor):
                 'dislike_count': int,
                 'comment_count': int,
                 'categories': ['seraina', 'jessica', 'krewella', 'alive'],
-            }
+            },
+            'skip': 'Removed due to DMCA',
         }, {
             'url': 'http://vube.com/vote/Siren+Gene/0nmsMY5vEq?n=2&t=s',
             'md5': '0584fc13b50f887127d9d1007589d27f',
@@ -69,7 +90,8 @@ class VubeIE(InfoExtractor):
                 'dislike_count': int,
                 'comment_count': int,
                 'categories': ['let it go', 'cover', 'idina menzel', 'frozen', 'singing', 'disney', 'siren gene'],
-            }
+            },
+            'skip': 'Removed due to DMCA',
         }
     ]
 
@@ -102,6 +124,11 @@ class VubeIE(InfoExtractor):
 
         self._sort_formats(formats)
 
+        if not formats and video.get('vst') == 'dmca':
+            raise ExtractorError(
+                'This video has been removed in response to a complaint received under the US Digital Millennium Copyright Act.',
+                expected=True)
+
         title = video['title']
         description = video.get('description')
         thumbnail = self._proto_relative_url(video.get('thumbnail_src'), scheme='http:')

youtube_dl/extractor/wat.py

@@ -40,6 +40,7 @@ class WatIE(InfoExtractor):
                 'upload_date': '20140816',
                 'duration': 2910,
             },
+            'skip': "Ce contenu n'est pas disponible pour l'instant.",
         },
     ]
 

youtube_dl/extractor/wistia.py

@@ -1,13 +1,14 @@
 from __future__ import unicode_literals
 
-import json
 import re
 
 from .common import InfoExtractor
+from ..utils import ExtractorError, compat_urllib_request
 
 
 class WistiaIE(InfoExtractor):
     _VALID_URL = r'https?://(?:fast\.)?wistia\.net/embed/iframe/(?P<id>[a-z0-9]+)'
+    _API_URL = 'http://fast.wistia.com/embed/medias/{0:}.json'
 
     _TEST = {
         'url': 'http://fast.wistia.net/embed/iframe/sh7fpupwlt',
@@ -24,11 +25,13 @@ class WistiaIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
 
-        webpage = self._download_webpage(url, video_id)
-        data_json = self._html_search_regex(
-            r'Wistia\.iframeInit\((.*?), {}\);', webpage, 'video data')
-
-        data = json.loads(data_json)
+        request = compat_urllib_request.Request(self._API_URL.format(video_id))
+        request.add_header('Referer', url)  # Some videos require this.
+        data_json = self._download_json(request, video_id)
+        if data_json.get('error'):
+            raise ExtractorError('Error while getting the playlist',
+                                 expected=True)
+        data = data_json['media']
 
         formats = []
         thumbnails = []

youtube_dl/extractor/ynet.py

@@ -0,0 +1,54 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import compat_urllib_parse
+
+
+class YnetIE(InfoExtractor):
+    _VALID_URL = r'http://(?:.+?\.)?ynet\.co\.il/(?:.+?/)?0,7340,(?P<id>L(?:-[0-9]+)+),00\.html'
+    _TESTS = [
+        {
+            'url': 'http://hot.ynet.co.il/home/0,7340,L-11659-99244,00.html',
+            'md5': '002b44ee2f33d50363a1c153bed524cf',
+            'info_dict': {
+                'id': 'L-11659-99244',
+                'ext': 'flv',
+                'title': 'איש לא יודע מאיפה באנו',
+                'thumbnail': 're:^https?://.*\.jpg',
+            }
+        }, {
+            'url': 'http://hot.ynet.co.il/home/0,7340,L-8859-84418,00.html',
+            'md5': '6455046ae1b48cf7e2b7cae285e53a16',
+            'info_dict': {
+                'id': 'L-8859-84418',
+                'ext': 'flv',
+                'title': "צפו: הנשיקה הלוהטת של תורגי' ויוליה פלוטקין",
+                'thumbnail': 're:^https?://.*\.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)
+
+        content = compat_urllib_parse.unquote_plus(self._og_search_video_url(webpage))
+        config = json.loads(self._search_regex(r'config=({.+?})$', content, 'video config'))
+        f4m_url = config['clip']['url']
+        title = self._og_search_title(webpage)
+        m = re.search(r'ynet - HOT -- (["\']+)(?P<title>.+?)\1', title)
+        if m:
+            title = m.group('title')
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': self._extract_f4m_formats(f4m_url, video_id),
+            'thumbnail': self._og_search_thumbnail(webpage),
+        }

youtube_dl/extractor/youku.py

@@ -1,6 +1,7 @@
 # coding: utf-8
 
-import json
+from __future__ import unicode_literals
+
 import math
 import random
 import re
@@ -13,18 +14,25 @@ from ..utils import (
 
 
 class YoukuIE(InfoExtractor):
-    _VALID_URL =  r'(?:(?:http://)?(?:v|player)\.youku\.com/(?:v_show/id_|player\.php/sid/)|youku:)(?P<ID>[A-Za-z0-9]+)(?:\.html|/v\.swf|)'
-    _TEST =   {
-        u"url": u"http://v.youku.com/v_show/id_XNDgyMDQ2NTQw.html",
-        u"file": u"XNDgyMDQ2NTQw_part00.flv",
-        u"md5": u"ffe3f2e435663dc2d1eea34faeff5b5b",
-        u"params": {u"test": False},
-        u"info_dict": {
-            u"title": u"youtube-dl test video \"'/\\ä↭𝕐"
+    _VALID_URL = r'''(?x)
+        (?:
+            http://(?:v|player)\.youku\.com/(?:v_show/id_|player\.php/sid/)|
+            youku:)
+        (?P<id>[A-Za-z0-9]+)(?:\.html|/v\.swf|)
+    '''
+    _TEST = {
+        'url': 'http://v.youku.com/v_show/id_XNDgyMDQ2NTQw.html',
+        'md5': 'ffe3f2e435663dc2d1eea34faeff5b5b',
+        'params': {
+            'test': False
+        },
+        'info_dict': {
+            'id': 'XNDgyMDQ2NTQw_part00',
+            'ext': 'flv',
+            'title': 'youtube-dl test video "\'/\\ä↭𝕐'
         }
     }
 
-
     def _gen_sid(self):
         nowTime = int(time.time() * 1000)
         random1 = random.randint(1000,1998)
@@ -55,49 +63,42 @@ class YoukuIE(InfoExtractor):
 
     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('ID')
+        video_id = mobj.group('id')
 
         info_url = 'http://v.youku.com/player/getPlayList/VideoIDS/' + video_id
 
-        jsondata = self._download_webpage(info_url, video_id)
+        config = self._download_json(info_url, video_id)
 
-        self.report_extraction(video_id)
-        try:
-            config = json.loads(jsondata)
-            error_code = config['data'][0].get('error_code')
-            if error_code:
-                # -8 means blocked outside China.
-                error = config['data'][0].get('error')  # Chinese and English, separated by newline.
-                raise ExtractorError(error or u'Server reported error %i' % error_code,
-                    expected=True)
+        error_code = config['data'][0].get('error_code')
+        if error_code:
+            # -8 means blocked outside China.
+            error = config['data'][0].get('error')  # Chinese and English, separated by newline.
+            raise ExtractorError(error or 'Server reported error %i' % error_code,
+                expected=True)
 
-            video_title =  config['data'][0]['title']
-            seed = config['data'][0]['seed']
+        video_title = config['data'][0]['title']
+        seed = config['data'][0]['seed']
 
-            format = self._downloader.params.get('format', None)
-            supported_format = list(config['data'][0]['streamfileids'].keys())
+        format = self._downloader.params.get('format', None)
+        supported_format = list(config['data'][0]['streamfileids'].keys())
 
-            if format is None or format == 'best':
-                if 'hd2' in supported_format:
-                    format = 'hd2'
-                else:
-                    format = 'flv'
-                ext = u'flv'
-            elif format == 'worst':
-                format = 'mp4'
-                ext = u'mp4'
+        # TODO proper format selection
+        if format is None or format == 'best':
+            if 'hd2' in supported_format:
+                format = 'hd2'
             else:
                 format = 'flv'
-                ext = u'flv'
+            ext = 'flv'
+        elif format == 'worst':
+            format = 'mp4'
+            ext = 'mp4'
+        else:
+            format = 'flv'
+            ext = 'flv'
 
-
-            fileid = config['data'][0]['streamfileids'][format]
-            keys = [s['k'] for s in config['data'][0]['segs'][format]]
-            # segs is usually a dictionary, but an empty *list* if an error occured.
-        except (UnicodeDecodeError, ValueError, KeyError):
-            raise ExtractorError(u'Unable to extract info section')
+        fileid = config['data'][0]['streamfileids'][format]
+        keys = [s['k'] for s in config['data'][0]['segs'][format]]
+        # segs is usually a dictionary, but an empty *list* if an error occured.
 
         files_info=[]
         sid = self._gen_sid()
@@ -106,9 +107,8 @@ class YoukuIE(InfoExtractor):
         #column 8,9 of fileid represent the segment number
         #fileid[7:9] should be changed
         for index, key in enumerate(keys):
-
             temp_fileid = '%s%02X%s' % (fileid[0:8], index, fileid[10:])
-            download_url = 'http://f.youku.com/player/getFlvPath/sid/%s_%02X/st/flv/fileid/%s?k=%s' % (sid, index, temp_fileid, key)
+            download_url = 'http://k.youku.com/player/getFlvPath/sid/%s_%02X/st/flv/fileid/%s?k=%s' % (sid, index, temp_fileid, key)
 
             info = {
                 'id': '%s_part%02d' % (video_id, index),

youtube_dl/extractor/youtube.py

@@ -26,7 +26,7 @@ from ..utils import (
     get_element_by_attribute,
     ExtractorError,
     int_or_none,
-    PagedList,
+    OnDemandPagedList,
     unescapeHTML,
     unified_strdate,
     orderedSet,
@@ -655,7 +655,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
 
         # Get video webpage
         url = proto + '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id
-        video_webpage = self._download_webpage(url, video_id)
+        req = compat_urllib_request.Request(url)
+        req.add_header('Cookie', 'PREF=hl=en')
+        video_webpage = self._download_webpage(req, video_id)
 
         # Attempt to extract SWF player URL
         mobj = re.search(r'swfConfig.*?"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage)
@@ -1068,6 +1070,13 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
         'info_dict': {
             'title': 'JODA15',
         }
+    }, {
+        'note': 'Embedded SWF player',
+        'url': 'http://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0',
+        'playlist_count': 4,
+        'info_dict': {
+            'title': 'JODA7',
+        }
     }]
 
     def _real_initialize(self):
@@ -1334,7 +1343,7 @@ class YoutubeUserIE(InfoExtractor):
                     'id': video_id,
                     'title': title,
                 }
-        url_results = PagedList(download_page, self._GDATA_PAGE_SIZE)
+        url_results = OnDemandPagedList(download_page, self._GDATA_PAGE_SIZE)
 
         return self.playlist_result(url_results, playlist_title=username)
 

youtube_dl/options.py

@@ -87,7 +87,7 @@ def parseOpts(overrideArguments=None):
         for private_opt in ['-p', '--password', '-u', '--username', '--video-password']:
             try:
                 i = opts.index(private_opt)
-                opts[i+1] = '<PRIVATE>'
+                opts[i+1] = 'PRIVATE'
             except ValueError:
                 pass
         return opts

youtube_dl/utils.py

@@ -1384,14 +1384,16 @@ def check_executable(exe, args=[]):
 
 
 class PagedList(object):
-    def __init__(self, pagefunc, pagesize):
-        self._pagefunc = pagefunc
-        self._pagesize = pagesize
-
     def __len__(self):
         # This is only useful for tests
         return len(self.getslice())
 
+
+class OnDemandPagedList(PagedList):
+    def __init__(self, pagefunc, pagesize):
+        self._pagefunc = pagefunc
+        self._pagesize = pagesize
+
     def getslice(self, start=0, end=None):
         res = []
         for pagenum in itertools.count(start // self._pagesize):
@@ -1430,6 +1432,35 @@ class PagedList(object):
         return res
 
 
+class InAdvancePagedList(PagedList):
+    def __init__(self, pagefunc, pagecount, pagesize):
+        self._pagefunc = pagefunc
+        self._pagecount = pagecount
+        self._pagesize = pagesize
+
+    def getslice(self, start=0, end=None):
+        res = []
+        start_page = start // self._pagesize
+        end_page = (
+            self._pagecount if end is None else (end // self._pagesize + 1))
+        skip_elems = start - start_page * self._pagesize
+        only_more = None if end is None else end - start
+        for pagenum in range(start_page, end_page):
+            page = list(self._pagefunc(pagenum))
+            if skip_elems:
+                page = page[skip_elems:]
+                skip_elems = None
+            if only_more is not None:
+                if len(page) < only_more:
+                    only_more -= len(page)
+                else:
+                    page = page[:only_more]
+                    res.extend(page)
+                    break
+            res.extend(page)
+        return res
+
+
 def uppercase_escape(s):
     unicode_escape = codecs.getdecoder('unicode_escape')
     return re.sub(

youtube_dl/version.py

@@ -1,2 +1,2 @@
 
-__version__ = '2014.09.24.1'
+__version__ = '2014.09.29'