release 2014.11.15.1

It produces the right mp4 urls, so we stop prefering the rtmp urls.

AUTHORS

@@ -81,3 +81,4 @@ winwon
 Xavier Beynon
 Gabriel Schubiner
 xantares
+Jan Matějka

test/helper.py

@@ -145,7 +145,8 @@ def expect_info_dict(self, expected_dict, got_dict):
         info_dict_str = ''.join(
             '    %s: %s,\n' % (_repr(k), _repr(v))
             for k, v in test_info_dict.items())
-        write_string('\n"info_dict": {\n' + info_dict_str + '}\n', out=sys.stderr)
+        write_string(
+            '\n\'info_dict\': {\n' + info_dict_str + '}\n', out=sys.stderr)
         self.assertFalse(
             missing_keys,
             'Missing keys in test definition: %s' % (

test/test_utils.py

@@ -16,6 +16,7 @@ import json
 import xml.etree.ElementTree
 
 from youtube_dl.utils import (
+    clean_html,
     DateRange,
     encodeFilename,
     find_xpath_attr,
@@ -45,6 +46,7 @@ from youtube_dl.utils import (
     escape_url,
     js_to_json,
     get_filesystem_encoding,
+    intlist_to_bytes,
 )
 
 
@@ -282,6 +284,10 @@ class TestUtil(unittest.TestCase):
         d = json.loads(stripped)
         self.assertEqual(d, [{"id": "532cb", "x": 3}])
 
+        stripped = strip_jsonp('parseMetadata({"STATUS":"OK"})\n\n\n//epc')
+        d = json.loads(stripped)
+        self.assertEqual(d, {'STATUS': 'OK'})
+
     def test_uppercase_escape(self):
         self.assertEqual(uppercase_escape('aä'), 'aä')
         self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐')
@@ -345,5 +351,14 @@ class TestUtil(unittest.TestCase):
         on = js_to_json('{"abc": true}')
         self.assertEqual(json.loads(on), {'abc': True})
 
+    def test_clean_html(self):
+        self.assertEqual(clean_html('a:\nb'), 'a: b')
+        self.assertEqual(clean_html('a:\n   "b"'), 'a:    "b"')
+
+    def test_intlist_to_bytes(self):
+        self.assertEqual(
+            intlist_to_bytes([0, 1, 127, 128, 255]),
+            b'\x00\x01\x7f\x80\xff')
+
 if __name__ == '__main__':
     unittest.main()

youtube_dl/compat.py

@@ -288,6 +288,14 @@ if sys.version_info < (3, 0) and sys.platform == 'win32':
 else:
     compat_getpass = getpass.getpass
 
+# Old 2.6 and 2.7 releases require kwargs to be bytes
+try:
+    (lambda x: x)(**{'x': 0})
+except TypeError:
+    def compat_kwargs(kwargs):
+        return dict((bytes(k), v) for k, v in kwargs.items())
+else:
+    compat_kwargs = lambda kwargs: kwargs
 
 __all__ = [
     'compat_HTTPError',
@@ -299,6 +307,7 @@ __all__ = [
     'compat_html_entities',
     'compat_html_parser',
     'compat_http_client',
+    'compat_kwargs',
     'compat_ord',
     'compat_parse_qs',
     'compat_print',

youtube_dl/extractor/__init__.py

@@ -127,6 +127,7 @@ from .francetv import (
 )
 from .freesound import FreesoundIE
 from .freespeech import FreespeechIE
+from .freevideo import FreeVideoIE
 from .funnyordie import FunnyOrDieIE
 from .gamekings import GamekingsIE
 from .gameone import (
@@ -324,6 +325,7 @@ from .sbs import SBSIE
 from .scivee import SciVeeIE
 from .screencast import ScreencastIE
 from .servingsys import ServingSysIE
+from .sexu import SexuIE
 from .sexykarma import SexyKarmaIE
 from .shared import SharedIE
 from .sharesix import ShareSixIE

youtube_dl/extractor/comedycentral.py

@@ -31,7 +31,7 @@ class ComedyCentralIE(MTVServicesInfoExtractor):
     }
 
 
-class ComedyCentralShowsIE(InfoExtractor):
+class ComedyCentralShowsIE(MTVServicesInfoExtractor):
     IE_DESC = 'The Daily Show / The Colbert Report'
     # urls can be abbreviations like :thedailyshow or :colbert
     # urls for episodes like:
@@ -109,14 +109,6 @@ class ComedyCentralShowsIE(InfoExtractor):
         '400': (384, 216),
     }
 
-    @staticmethod
-    def _transform_rtmp_url(rtmp_video_url):
-        m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp\.comedystor/.*)$', rtmp_video_url)
-        if not m:
-            raise ExtractorError('Cannot transform RTMP url')
-        base = 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=1+_pxI0=Ripod-h264+_pxL0=undefined+_pxM0=+_pxK=18639+_pxE=mp4/44620/mtvnorigin/'
-        return base + m.group('finalid')
-
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url, re.VERBOSE)
         if mobj is None:
@@ -212,9 +204,6 @@ class ComedyCentralShowsIE(InfoExtractor):
                     'ext': self._video_extensions.get(format, 'mp4'),
                     'height': h,
                     'width': w,
-
-                    'format_note': 'HTTP 400 at the moment (patches welcome!)',
-                    'preference': -100,
                 })
                 formats.append({
                     'format_id': 'rtmp-%s' % format,

youtube_dl/extractor/crunchyroll.py

@@ -264,8 +264,6 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
             if not lang_code:
                 continue
             sub_root = xml.etree.ElementTree.fromstring(subtitle)
-            if not sub_root:
-                subtitles[lang_code] = ''
             if sub_format == 'ass':
                 subtitles[lang_code] = self._convert_subtitles_to_ass(sub_root)
             else:

youtube_dl/extractor/freevideo.py

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

youtube_dl/extractor/generic.py

@@ -434,7 +434,17 @@ class GenericIE(InfoExtractor):
                 'title': 'Chet Chat 171 - Oct 29, 2014',
                 'upload_date': '20141029',
             }
-        }
+        },
+        # Livestream embed
+        {
+            'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
+            'info_dict': {
+                'id': '67864563',
+                'ext': 'flv',
+                'upload_date': '20141112',
+                'title': 'Rosetta #CometLanding webcast HL 10',
+            }
+        },
     ]
 
     def report_following_redirect(self, new_url):
@@ -916,6 +926,12 @@ class GenericIE(InfoExtractor):
         if mobj is not None:
             return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
 
+        mobj = re.search(
+            r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
+            webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'), 'Livestream')
+
         def check_video(vurl):
             vpath = compat_urlparse.urlparse(vurl).path
             vext = determine_ext(vpath)

youtube_dl/extractor/goldenmoustache.py

@@ -10,7 +10,7 @@ from ..utils import (
 
 class GoldenMoustacheIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?goldenmoustache\.com/(?P<display_id>[\w-]+)-(?P<id>\d+)'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.goldenmoustache.com/suricate-le-poker-3700/',
         'md5': '0f904432fa07da5054d6c8beb5efb51a',
         'info_dict': {
@@ -21,7 +21,18 @@ class GoldenMoustacheIE(InfoExtractor):
             'thumbnail': 're:^https?://.*\.jpg$',
             'view_count': int,
         }
-    }
+    }, {
+        'url': 'http://www.goldenmoustache.com/le-lab-tout-effacer-mc-fly-et-carlito-55249/',
+        'md5': '27f0c50fb4dd5f01dc9082fc67cd5700',
+        'info_dict': {
+            'id': '55249',
+            'ext': 'mp4',
+            'title': 'Le LAB - Tout Effacer (Mc Fly et Carlito)',
+            'description': 'md5:9b7fbf11023fb2250bd4b185e3de3b2a',
+            'thumbnail': 're:^https?://.*\.(?:png|jpg)$',
+            'view_count': int,
+        }
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
@@ -30,7 +41,7 @@ class GoldenMoustacheIE(InfoExtractor):
         video_url = self._html_search_regex(
             r'data-src-type="mp4" data-src="([^"]+)"', webpage, 'video URL')
         title = self._html_search_regex(
-            r'<title>(.*?) - Golden Moustache</title>', webpage, 'title')
+            r'<title>(.*?)(?: - Golden Moustache)?</title>', webpage, 'title')
         thumbnail = self._og_search_thumbnail(webpage)
         description = self._og_search_description(webpage)
         view_count = int_or_none(self._html_search_regex(

youtube_dl/extractor/livestream.py

@@ -18,7 +18,7 @@ from ..utils import (
 
 class LivestreamIE(InfoExtractor):
     IE_NAME = 'livestream'
-    _VALID_URL = r'http://new\.livestream\.com/.*?/(?P<event_name>.*?)(/videos/(?P<id>\d+))?/?$'
+    _VALID_URL = r'https?://new\.livestream\.com/.*?/(?P<event_name>.*?)(/videos/(?P<id>[0-9]+)(?:/player)?)?/?(?:$|[?#])'
     _TESTS = [{
         'url': 'http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370',
         'md5': '53274c76ba7754fb0e8d072716f2292b',
@@ -37,6 +37,9 @@ class LivestreamIE(InfoExtractor):
             'title': 'TEDCity2.0 (English)',
         },
         'playlist_mincount': 4,
+    }, {
+        'url': 'https://new.livestream.com/accounts/362/events/3557232/videos/67864563/player?autoPlay=false&height=360&mute=false&width=640',
+        'only_matching': True,
     }]
 
     def _parse_smil(self, video_id, smil_url):

youtube_dl/extractor/mailru.py

@@ -16,7 +16,7 @@ class MailRuIE(InfoExtractor):
             'url': 'http://my.mail.ru/video/top#video=/mail/sonypicturesrus/75/76',
             'md5': 'dea205f03120046894db4ebb6159879a',
             'info_dict': {
-                'id': '46301138',
+                'id': '46301138_76',
                 'ext': 'mp4',
                 'title': 'Новый Человек-Паук. Высокое напряжение. Восстание Электро',
                 'timestamp': 1393232740,
@@ -30,7 +30,7 @@ class MailRuIE(InfoExtractor):
             'url': 'http://my.mail.ru/corp/hitech/video/news_hi-tech_mail_ru/1263.html',
             'md5': '00a91a58c3402204dcced523777b475f',
             'info_dict': {
-                'id': '46843144',
+                'id': '46843144_1263',
                 'ext': 'mp4',
                 'title': 'Samsung Galaxy S5 Hammer Smash Fail Battery Explosion',
                 'timestamp': 1397217632,
@@ -54,33 +54,36 @@ class MailRuIE(InfoExtractor):
 
         author = video_data['author']
         uploader = author['name']
-        uploader_id = author['id']
+        uploader_id = author.get('id') or author.get('email')
+        view_count = video_data.get('views_count')
 
-        movie = video_data['movie']
-        content_id = str(movie['contentId'])
-        title = movie['title']
+        meta_data = video_data['meta']
+        content_id = '%s_%s' % (
+            meta_data.get('accId', ''), meta_data['itemId'])
+        title = meta_data['title']
         if title.endswith('.mp4'):
             title = title[:-4]
-        thumbnail = movie['poster']
-        duration = movie['duration']
-
-        view_count = video_data['views_count']
+        thumbnail = meta_data['poster']
+        duration = meta_data['duration']
+        timestamp = meta_data['timestamp']
 
         formats = [
             {
                 'url': video['url'],
-                'format_id': video['name'],
+                'format_id': video['key'],
+                'height': int(video['key'].rstrip('p'))
             } for video in video_data['videos']
         ]
+        self._sort_formats(formats)
 
         return {
             'id': content_id,
             'title': title,
             'thumbnail': thumbnail,
-            'timestamp': video_data['timestamp'],
+            'timestamp': timestamp,
             'uploader': uploader,
             'uploader_id': uploader_id,
             'duration': duration,
             'view_count': view_count,
             'formats': formats,
-        }
+        }

youtube_dl/extractor/mtv.py

@@ -186,7 +186,8 @@ class MTVServicesEmbeddedIE(MTVServicesInfoExtractor):
     def _get_feed_url(self, uri):
         video_id = self._id_from_uri(uri)
         site_id = uri.replace(video_id, '')
-        config_url = 'http://media.mtvnservices.com/pmt/e1/players/{0}/config.xml'.format(site_id)
+        config_url = ('http://media.mtvnservices.com/pmt/e1/players/{0}/'
+            'context4/context5/config.xml'.format(site_id))
         config_doc = self._download_xml(config_url, video_id)
         feed_node = config_doc.find('.//feed')
         feed_url = feed_node.text.strip().split('?')[0]

youtube_dl/extractor/npo.py

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

youtube_dl/extractor/sexu.py

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

youtube_dl/extractor/spiegel.py

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

youtube_dl/options.py

@@ -8,6 +8,7 @@ import sys
 from .compat import (
     compat_expanduser,
     compat_getenv,
+    compat_kwargs,
 )
 from .utils import (
     get_term_width,
@@ -112,7 +113,7 @@ def parseOpts(overrideArguments=None):
         'conflict_handler': 'resolve',
     }
 
-    parser = optparse.OptionParser(**kw)
+    parser = optparse.OptionParser(**compat_kwargs(kw))
 
     general = optparse.OptionGroup(parser, 'General Options')
     general.add_option(

youtube_dl/utils.py

@@ -843,10 +843,7 @@ def bytes_to_intlist(bs):
 def intlist_to_bytes(xs):
     if not xs:
         return b''
-    if isinstance(chr(0), bytes):  # Python 2
-        return ''.join([chr(x) for x in xs])
-    else:
-        return bytes(xs)
+    return struct_pack('%dB' % len(xs), *xs)
 
 
 # Cross-platform file locking
@@ -1334,7 +1331,8 @@ def parse_age_limit(s):
 
 
 def strip_jsonp(code):
-    return re.sub(r'(?s)^[a-zA-Z0-9_]+\s*\(\s*(.*)\);?\s*?\s*$', r'\1', code)
+    return re.sub(
+        r'(?s)^[a-zA-Z0-9_]+\s*\(\s*(.*)\);?\s*?(?://[^\n]*)*$', r'\1', code)
 
 
 def js_to_json(code):

youtube_dl/version.py

@@ -1,2 +1,2 @@
 
-__version__ = '2014.11.13'
+__version__ = '2014.11.15.1'