release 2014.09.12

On 2.x, we now try TLS first, and fall back to the compat 23 (basically anything) afterwards.
On 3.4+, we now use the proper function so that we get all the latest security configurations.
We allow SSLv3 though for the time being, since a lot of older pages use that.
On 3.3, we default to SSLv23 (basically "anything, including TLS") because that has the widest compatibility.

youtube_dl/extractor/__init__.py

@@ -140,6 +140,7 @@ from .hark import HarkIE
 from .helsinki import HelsinkiIE
 from .hentaistigma import HentaiStigmaIE
 from .hornbunny import HornBunnyIE
+from .hostingbulk import HostingBulkIE
 from .hotnewhiphop import HotNewHipHopIE
 from .howcast import HowcastIE
 from .howstuffworks import HowStuffWorksIE

youtube_dl/extractor/generic.py

@@ -628,7 +628,7 @@ class GenericIE(InfoExtractor):
                 embedSWF\(?:\s*
             )
             (["\'])
-                (?P<url>(?:https?:)?//(?:www\.)?youtube\.com/
+                (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
                 (?:embed|v)/.+?)
             \1''', webpage)
         if matches:

youtube_dl/extractor/hostingbulk.py

@@ -0,0 +1,84 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    compat_urllib_request,
+    int_or_none,
+    urlencode_postdata,
+)
+
+
+class HostingBulkIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+        https?://(?:www\.)?hostingbulk\.com/
+        (?:embed-)?(?P<id>[A-Za-z0-9]{12})(?:-\d+x\d+)?\.html'''
+    _FILE_DELETED_REGEX = r'<b>File Not Found</b>'
+    _TEST = {
+        'url': 'http://hostingbulk.com/n0ulw1hv20fm.html',
+        'md5': '6c8653c8ecf7ebfa83b76e24b7b2fe3f',
+        'info_dict': {
+            'id': 'n0ulw1hv20fm',
+            'ext': 'mp4',
+            'title': 'md5:5afeba33f48ec87219c269e054afd622',
+            'filesize': 6816081,
+            'thumbnail': 're:^http://.*\.jpg$',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        url = 'http://hostingbulk.com/{0:}.html'.format(video_id)
+
+        # Custom request with cookie to set language to English, so our file
+        # deleted regex would work.
+        request = compat_urllib_request.Request(
+            url, headers={'Cookie': 'lang=english'})
+        webpage = self._download_webpage(request, video_id)
+
+        if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
+            raise ExtractorError('Video %s does not exist' % video_id,
+                                 expected=True)
+
+        title = self._html_search_regex(r'<h3>(.*?)</h3>', webpage, 'title')
+        filesize = int_or_none(
+            self._search_regex(
+                r'<small>\((\d+)\sbytes?\)</small>',
+                webpage,
+                'filesize',
+                fatal=False
+            )
+        )
+        thumbnail = self._search_regex(
+            r'<img src="([^"]+)".+?class="pic"',
+            webpage, 'thumbnail', fatal=False)
+
+        fields = dict(re.findall(r'''(?x)<input\s+
+            type="hidden"\s+
+            name="([^"]+)"\s+
+            value="([^"]*)"
+            ''', webpage))
+
+        request = compat_urllib_request.Request(url, urlencode_postdata(fields))
+        request.add_header('Content-type', 'application/x-www-form-urlencoded')
+        response = self._request_webpage(request, video_id,
+                                         'Submiting download request')
+        video_url = response.geturl()
+
+        formats = [{
+            'format_id': 'sd',
+            'filesize': filesize,
+            'url': video_url,
+        }]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'formats': formats,
+        }

youtube_dl/extractor/izlesene.py

@@ -9,29 +9,50 @@ from ..utils import (
     parse_iso8601,
     determine_ext,
     int_or_none,
+    float_or_none,
     str_to_int,
 )
 
 
 class IzleseneIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:(?:www|m)\.)?izlesene\.com/(?:video|embedplayer)/(?:[^/]+/)?(?P<id>[0-9]+)'
-    _STREAM_URL = 'http://panel.izlesene.com/api/streamurl/{id:}/{format:}'
-    _TEST = {
-        'url': 'http://www.izlesene.com/video/sevincten-cildirtan-dogum-gunu-hediyesi/7599694',
-        'md5': '4384f9f0ea65086734b881085ee05ac2',
-        'info_dict': {
-            'id': '7599694',
-            'ext': 'mp4',
-            'title': 'Sevinçten Çıldırtan Doğum Günü Hediyesi',
-            'description': 'Annesi oğluna doğum günü hediyesi olarak minecraft cd si alıyor, ve çocuk hunharca seviniyor',
-            'thumbnail': 're:^http://.*\.jpg',
-            'uploader_id': 'pelikzzle',
-            'timestamp': 1404298698,
-            'upload_date': '20140702',
-            'duration': 95.395,
-            'age_limit': 0,
-        }
-    }
+    _VALID_URL = r'''(?x)
+        https?://(?:(?:www|m)\.)?izlesene\.com/
+        (?:video|embedplayer)/(?:[^/]+/)?(?P<id>[0-9]+)
+        '''
+    _TESTS = [
+        {
+            'url': 'http://www.izlesene.com/video/sevincten-cildirtan-dogum-gunu-hediyesi/7599694',
+            'md5': '4384f9f0ea65086734b881085ee05ac2',
+            'info_dict': {
+                'id': '7599694',
+                'ext': 'mp4',
+                'title': 'Sevinçten Çıldırtan Doğum Günü Hediyesi',
+                'description': 'md5:253753e2655dde93f59f74b572454f6d',
+                'thumbnail': 're:^http://.*\.jpg',
+                'uploader_id': 'pelikzzle',
+                'timestamp': 1404298698,
+                'upload_date': '20140702',
+                'duration': 95.395,
+                'age_limit': 0,
+            }
+        },
+        {
+            'url': 'http://www.izlesene.com/video/tarkan-dortmund-2006-konseri/17997',
+            'md5': '97f09b6872bffa284cb7fa4f6910cb72',
+            'info_dict': {
+                'id': '17997',
+                'ext': 'mp4',
+                'title': 'Tarkan Dortmund 2006 Konseri',
+                'description': 'Tarkan Dortmund 2006 Konseri',
+                'thumbnail': 're:^http://.*\.jpg',
+                'uploader_id': 'parlayankiz',
+                'timestamp': 1163318593,
+                'upload_date': '20061112',
+                'duration': 253.666,
+                'age_limit': 0,
+            }
+        },
+    ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -45,18 +66,19 @@ class IzleseneIE(InfoExtractor):
         thumbnail = self._og_search_thumbnail(webpage)
 
         uploader = self._html_search_regex(
-            r"adduserUsername\s*=\s*'([^']+)';", webpage, 'uploader', fatal=False, default='')
+            r"adduserUsername\s*=\s*'([^']+)';",
+            webpage, 'uploader', fatal=False, default='')
         timestamp = parse_iso8601(self._html_search_meta(
             'uploadDate', webpage, 'upload date', fatal=False))
 
-        duration = int_or_none(self._html_search_regex(
-            r'"videoduration"\s*:\s*"([^"]+)"', webpage, 'duration', fatal=False))
-        if duration:
-            duration /= 1000.0
+        duration = float_or_none(self._html_search_regex(
+            r'"videoduration"\s*:\s*"([^"]+)"',
+            webpage, 'duration', fatal=False), scale=1000)
 
         view_count = str_to_int(get_element_by_id('videoViewCount', webpage))
         comment_count = self._html_search_regex(
-            r'comment_count\s*=\s*\'([^\']+)\';', webpage, 'uploader', fatal=False)
+            r'comment_count\s*=\s*\'([^\']+)\';',
+            webpage, 'comment_count', fatal=False)
 
         family_friendly = self._html_search_meta(
             'isFamilyFriendly', webpage, 'age limit', fatal=False)
@@ -66,20 +88,26 @@ class IzleseneIE(InfoExtractor):
         ext = determine_ext(content_url, 'mp4')
 
         # Might be empty for some videos.
-        qualities = self._html_search_regex(
-            r'"quality"\s*:\s*"([^"]+)"', webpage, 'qualities', fatal=False, default='')
+        streams = self._html_search_regex(
+            r'"qualitylevel"\s*:\s*"([^"]+)"',
+            webpage, 'streams', fatal=False, default='')
 
         formats = []
-        for quality in qualities.split('|'):
-            json = self._download_json(
-                self._STREAM_URL.format(id=video_id, format=quality), video_id,
-                note='Getting video URL for "%s" quality' % quality,
-                errnote='Failed to get video URL for "%s" quality' % quality
-            )
+        if streams:
+            for stream in streams.split('|'):
+                quality, url = re.search(r'\[(\w+)\](.+)', stream).groups()
+                formats.append({
+                    'format_id': '%sp' % quality if quality else 'sd',
+                    'url': url,
+                    'ext': ext,
+                })
+        else:
+            stream_url = self._search_regex(
+                r'"streamurl"\s?:\s?"([^"]+)"', webpage, 'stream URL')
             formats.append({
-                'url': json.get('streamurl'),
+                'format_id': 'sd',
+                'url': stream_url,
                 'ext': ext,
-                'format_id': '%sp' % quality if quality else 'sd',
             })
 
         return {

youtube_dl/extractor/nosvideo.py

@@ -5,8 +5,9 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
-    compat_urllib_parse,
+    ExtractorError,
     compat_urllib_request,
+    urlencode_postdata,
     xpath_with_ns,
 )
 
@@ -18,11 +19,12 @@ class NosVideoIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?nosvideo\.com/' + \
                  '(?:embed/|\?v=)(?P<id>[A-Za-z0-9]{12})/?'
     _PLAYLIST_URL = 'http://nosvideo.com/xml/{xml_id:s}.xml'
+    _FILE_DELETED_REGEX = r'<b>File Not Found</b>'
     _TEST = {
-        'url': 'http://nosvideo.com/?v=drlp6s40kg54',
-        'md5': '4b4ac54c6ad5d70ab88f2c2c6ccec71c',
+        'url': 'http://nosvideo.com/?v=mu8fle7g7rpq',
+        'md5': '6124ed47130d8be3eacae635b071e6b6',
         'info_dict': {
-            'id': 'drlp6s40kg54',
+            'id': 'mu8fle7g7rpq',
             'ext': 'mp4',
             'title': 'big_buck_bunny_480p_surround-fix.avi.mp4',
             'thumbnail': 're:^https?://.*\.jpg$',
@@ -38,11 +40,14 @@ class NosVideoIE(InfoExtractor):
             'op': 'download1',
             'method_free': 'Continue to Video',
         }
-        post = compat_urllib_parse.urlencode(fields)
-        req = compat_urllib_request.Request(url, post)
+        req = compat_urllib_request.Request(url, urlencode_postdata(fields))
         req.add_header('Content-type', 'application/x-www-form-urlencoded')
         webpage = self._download_webpage(req, video_id,
                                          'Downloading download page')
+        if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
+            raise ExtractorError('Video %s does not exist' % video_id,
+                                 expected=True)
+
         xml_id = self._search_regex(r'php\|([^\|]+)\|', webpage, 'XML ID')
         playlist_url = self._PLAYLIST_URL.format(xml_id=xml_id)
         playlist = self._download_xml(playlist_url, video_id)

youtube_dl/extractor/tvplay.py

@@ -6,13 +6,28 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
+    compat_str,
     parse_iso8601,
     qualities,
 )
 
 
 class TVPlayIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?tvplay\.lv/parraides/[^/]+/(?P<id>\d+)'
+    IE_DESC = 'TV3Play and related services'
+    _VALID_URL = r'''(?x)http://(?:www\.)?
+        (?:tvplay\.lv/parraides|
+           tv3play\.lt/programos|
+           tv3play\.ee/sisu|
+           tv3play\.se/program|
+           tv6play\.se/program|
+           tv8play\.se/program|
+           tv10play\.se/program|
+           tv3play\.no/programmer|
+           viasat4play\.no/programmer|
+           tv6play\.no/programmer|
+           tv3play\.dk/programmer|
+        )/[^/]+/(?P<id>\d+)
+        '''
     _TESTS = [
         {
             'url': 'http://www.tvplay.lv/parraides/vinas-melo-labak/418113?autostart=true',
@@ -30,6 +45,134 @@ class TVPlayIE(InfoExtractor):
                 'skip_download': True,
             },
         },
+        {
+            'url': 'http://www.tv3play.lt/programos/moterys-meluoja-geriau/409229?autostart=true',
+            'info_dict': {
+                'id': '409229',
+                'ext': 'flv',
+                'title': 'Moterys meluoja geriau',
+                'description': 'md5:9aec0fc68e2cbc992d2a140bd41fa89e',
+                'duration': 1330,
+                'timestamp': 1403769181,
+                'upload_date': '20140626',
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+        },
+        {
+            'url': 'http://www.tv3play.ee/sisu/kodu-keset-linna/238551?autostart=true',
+            'info_dict': {
+                'id': '238551',
+                'ext': 'flv',
+                'title': 'Kodu keset linna 398537',
+                'description': 'md5:7df175e3c94db9e47c0d81ffa5d68701',
+                'duration': 1257,
+                'timestamp': 1292449761,
+                'upload_date': '20101215',
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+        },
+        {
+            'url': 'http://www.tv3play.se/program/husraddarna/395385?autostart=true',
+            'info_dict': {
+                'id': '395385',
+                'ext': 'flv',
+                'title': 'Husräddarna S02E07',
+                'description': 'md5:f210c6c89f42d4fc39faa551be813777',
+                'duration': 2574,
+                'timestamp': 1400596321,
+                'upload_date': '20140520',
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+        },
+        {
+            'url': 'http://www.tv6play.se/program/den-sista-dokusapan/266636?autostart=true',
+            'info_dict': {
+                'id': '266636',
+                'ext': 'flv',
+                'title': 'Den sista dokusåpan S01E08',
+                'description': 'md5:295be39c872520221b933830f660b110',
+                'duration': 1492,
+                'timestamp': 1330522854,
+                'upload_date': '20120229',
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+        },
+        {
+            'url': 'http://www.tv8play.se/program/antikjakten/282756?autostart=true',
+            'info_dict': {
+                'id': '282756',
+                'ext': 'flv',
+                'title': 'Antikjakten S01E10',
+                'description': 'md5:1b201169beabd97e20c5ad0ad67b13b8',
+                'duration': 2646,
+                'timestamp': 1348575868,
+                'upload_date': '20120925',
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+        },
+        {
+            'url': 'http://www.tv3play.no/programmer/anna-anka-soker-assistent/230898?autostart=true',
+            'info_dict': {
+                'id': '230898',
+                'ext': 'flv',
+                'title': 'Anna Anka søker assistent - Ep. 8',
+                'description': 'md5:f80916bf5bbe1c5f760d127f8dd71474',
+                'duration': 2656,
+                'timestamp': 1277720005,
+                'upload_date': '20100628',
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+        },
+        {
+            'url': 'http://www.viasat4play.no/programmer/budbringerne/21873?autostart=true',
+            'info_dict': {
+                'id': '21873',
+                'ext': 'flv',
+                'title': 'Budbringerne program 10',
+                'description': 'md5:4db78dc4ec8a85bb04fd322a3ee5092d',
+                'duration': 1297,
+                'timestamp': 1254205102,
+                'upload_date': '20090929',
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+        },
+        {
+            'url': 'http://www.tv6play.no/programmer/hotelinspektor-alex-polizzi/361883?autostart=true',
+            'info_dict': {
+                'id': '361883',
+                'ext': 'flv',
+                'title': 'Hotelinspektør Alex Polizzi - Ep. 10',
+                'description': 'md5:3ecf808db9ec96c862c8ecb3a7fdaf81',
+                'duration': 2594,
+                'timestamp': 1393236292,
+                'upload_date': '20140224',
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+        },
     ]
 
     def _real_extract(self, url):
@@ -49,7 +192,7 @@ class TVPlayIE(InfoExtractor):
         quality = qualities(['hls', 'medium', 'high'])
         formats = []
         for format_id, video_url in streams['streams'].items():
-            if not video_url:
+            if not video_url or not isinstance(video_url, compat_str):
                 continue
             fmt = {
                 'format_id': format_id,

youtube_dl/extractor/youjizz.py

@@ -9,7 +9,7 @@ from ..utils import (
 
 
 class YouJizzIE(InfoExtractor):
-    _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+)\.html$'
+    _VALID_URL = r'^https?://(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+)\.html$'
     _TEST = {
         'url': 'http://www.youjizz.com/videos/zeichentrick-1-2189178.html',
         'file': '2189178.flv',

youtube_dl/extractor/youtube.py

@@ -199,7 +199,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
     IE_DESC = u'YouTube.com'
     _VALID_URL = r"""(?x)^
                      (
-                         (?:https?://|//)?                                    # http(s):// or protocol-independent URL (optional)
+                         (?:https?://|//)                                    # http(s):// or protocol-independent URL
                          (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/|
                             (?:www\.)?deturl\.com/www\.youtube\.com/|
                             (?:www\.)?pwnyoutube\.com/|
@@ -217,7 +217,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
                              )
                          ))
                          |youtu\.be/                                          # just youtu.be/xxxx
-                         |https?://(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
+                         |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
                          )
                      )?                                                       # all until now is optional -> you can pass the naked ID
                      ([0-9A-Za-z_-]{11})                                      # here is it! the YouTube video ID

youtube_dl/utils.py

@@ -617,7 +617,7 @@ def make_HTTPS_handler(opts_no_check_certificate, **kwargs):
                     self.sock = sock
                     self._tunnel()
                 try:
-                    self.sock = ssl.wrap_socket(sock, self.key_file, self.cert_file, ssl_version=ssl.PROTOCOL_SSLv3)
+                    self.sock = ssl.wrap_socket(sock, self.key_file, self.cert_file, ssl_version=ssl.PROTOCOL_TLSv1)
                 except ssl.SSLError:
                     self.sock = ssl.wrap_socket(sock, self.key_file, self.cert_file, ssl_version=ssl.PROTOCOL_SSLv23)
 
@@ -625,8 +625,14 @@ def make_HTTPS_handler(opts_no_check_certificate, **kwargs):
             def https_open(self, req):
                 return self.do_open(HTTPSConnectionV3, req)
         return HTTPSHandlerV3(**kwargs)
-    else:
-        context = ssl.SSLContext(ssl.PROTOCOL_SSLv3)
+    elif hasattr(ssl, 'create_default_context'):  # Python >= 3.4
+        context = ssl.create_default_context(ssl.Purpose.CLIENT_AUTH)
+        context.options &= ~ssl.OP_NO_SSLv3  # Allow older, not-as-secure SSLv3
+        if opts_no_check_certificate:
+            context.verify_mode = ssl.CERT_NONE
+        return compat_urllib_request.HTTPSHandler(context=context, **kwargs)
+    else:  # Python < 3.4
+        context = ssl.SSLContext(ssl.PROTOCOL_SSLv23)
         context.verify_mode = (ssl.CERT_NONE
                                if opts_no_check_certificate
                                else ssl.CERT_REQUIRED)

youtube_dl/version.py

@@ -1,2 +1,2 @@
 
-__version__ = '2014.09.10'
+__version__ = '2014.09.12'