release 2013.12.17

This fixes #1982
Test video: http://www.youtube.com/watch?v=gi2uH3YxohU

test/test_all_urls.py

@@ -10,6 +10,7 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 from test.helper import get_testcases
 
 from youtube_dl.extractor import (
+    FacebookIE,
     gen_extractors,
     JustinTVIE,
     YoutubeIE,
@@ -87,12 +88,15 @@ class TestAllURLsMatching(unittest.TestCase):
         assertExtractId('http://www.youtube.com/watch?v=BaW_jenozKcsharePLED17F32AD9753930', 'BaW_jenozKc')
         assertExtractId('BaW_jenozKc', 'BaW_jenozKc')
 
+    def test_facebook_matching(self):
+        self.assertTrue(FacebookIE.suitable(u'https://www.facebook.com/Shiniknoh#!/photo.php?v=10153317450565268'))
+
     def test_no_duplicates(self):
         ies = gen_extractors()
         for tc in get_testcases():
             url = tc['url']
             for ie in ies:
-                if type(ie).__name__ in ['GenericIE', tc['name'] + 'IE']:
+                if type(ie).__name__ in ('GenericIE', tc['name'] + 'IE'):
                     self.assertTrue(ie.suitable(url), '%s should match URL %r' % (type(ie).__name__, url))
                 else:
                     self.assertFalse(ie.suitable(url), '%s should not match URL %r' % (type(ie).__name__, url))

test/test_playlists.py

@@ -12,6 +12,7 @@ from test.helper import FakeYDL
 
 
 from youtube_dl.extractor import (
+    AcademicEarthCourseIE,
     DailymotionPlaylistIE,
     DailymotionUserIE,
     VimeoChannelIE,
@@ -158,5 +159,16 @@ class TestPlaylists(unittest.TestCase):
         self.assertEqual(result['title'], u'Inspector')
         self.assertTrue(len(result['entries']) >= 9)
 
+    def test_AcademicEarthCourse(self):
+        dl = FakeYDL()
+        ie = AcademicEarthCourseIE(dl)
+        result = ie.extract(u'http://academicearth.org/courses/building-dynamic-websites/')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], u'building-dynamic-websites')
+        self.assertEqual(result['title'], u'Building Dynamic Websites')
+        self.assertEqual(result['description'], u"Today's websites are increasingly dynamic. Pages are no longer static HTML files but instead generated by scripts and database calls. User interfaces are more seamless, with technologies like Ajax replacing traditional page reloads. This course teaches students how to build dynamic websites with Ajax and with Linux, Apache, MySQL, and PHP (LAMP), one of today's most popular frameworks. Students learn how to set up domain names with DNS, how to structure pages with XHTML and CSS, how to program in JavaScript and PHP, how to configure Apache and MySQL, how to design and query databases with SQL, how to use Ajax with both XML and JSON, and how to build mashups. The course explores issues of security, scalability, and cross-browser support and also discusses enterprise-level deployments of websites, including third-party hosting, virtualization, colocation in data centers, firewalling, and load-balancing.")
+        self.assertEqual(len(result['entries']), 10)
+
+
 if __name__ == '__main__':
     unittest.main()

youtube_dl/YoutubeDL.py

@@ -845,7 +845,7 @@ class YoutubeDL(object):
             if info_dict.get('thumbnail') is not None:
                 thumb_format = determine_ext(info_dict['thumbnail'], u'jpg')
                 thumb_filename = os.path.splitext(filename)[0] + u'.' + thumb_format
-                if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(infofn)):
+                if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(thumb_filename)):
                     self.to_screen(u'[%s] %s: Thumbnail is already present' %
                                    (info_dict['extractor'], info_dict['id']))
                 else:

youtube_dl/extractor/__init__.py

@@ -1,6 +1,7 @@
-from .appletrailers import AppleTrailersIE
+from .academicearth import AcademicEarthCourseIE
 from .addanime import AddAnimeIE
 from .anitube import AnitubeIE
+from .appletrailers import AppleTrailersIE
 from .archiveorg import ArchiveOrgIE
 from .ard import ARDIE
 from .arte import (
@@ -119,6 +120,7 @@ from .pornhd import PornHdIE
 from .pornhub import PornHubIE
 from .pornotube import PornotubeIE
 from .pyvideo import PyvideoIE
+from .radiofrance import RadioFranceIE
 from .rbmaradio import RBMARadioIE
 from .redtube import RedTubeIE
 from .ringtv import RingTVIE

youtube_dl/extractor/academicearth.py

@@ -0,0 +1,36 @@
+import datetime
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    remove_start,
+)
+
+
+class AcademicEarthCourseIE(InfoExtractor):
+    _VALID_URL = r'^https?://(?:www\.)?academicearth\.org/(?:courses|playlists)/(?P<id>[^?#/]+)'
+    IE_NAME = u'AcademicEarth:Course'
+
+    def _real_extract(self, url):
+        m = re.match(self._VALID_URL, url)
+        playlist_id = m.group('id')
+
+        webpage = self._download_webpage(url, playlist_id)
+        title = self._html_search_regex(
+            r'<h1 class="playlist-name">(.*?)</h1>', webpage, u'title')
+        description = self._html_search_regex(
+            r'<p class="excerpt">(.*?)</p>',
+            webpage, u'description', fatal=False)
+        urls = re.findall(
+            r'<h3 class="lecture-title"><a target="_blank" href="([^"]+)">',
+            webpage)
+        entries = [self.url_result(u) for u in urls]
+
+        return {
+            '_type': 'playlist',
+            'id': playlist_id,
+            'title': title,
+            'description': description,
+            'entries': entries,
+        }

youtube_dl/extractor/arte.py

@@ -266,20 +266,6 @@ class ArteTVDDCIE(ArteTVPlus7IE):
     IE_NAME = u'arte.tv:ddc'
     _VALID_URL = r'http?://ddc\.arte\.tv/(?P<lang>emission|folge)/(?P<id>.+)'
 
-    _TEST = {
-        u'url': u'http://ddc.arte.tv/folge/neues-aus-mauretanien',
-        u'file': u'049881-009_PLUS7-D.flv',
-        u'info_dict': {
-            u'title': u'Mit offenen Karten',
-            u'description': u'md5:57929b0eaeddeb8a0c983f58e9ebd3b6',
-            u'upload_date': u'20131207',
-        },
-        u'params': {
-            # rtmp download
-            u'skip_download': True,
-        },
-    }
-
     def _real_extract(self, url):
         video_id, lang = self._extract_url_info(url)
         if lang == 'folge':

youtube_dl/extractor/common.py

@@ -18,6 +18,7 @@ from ..utils import (
     sanitize_filename,
     unescapeHTML,
 )
+_NO_DEFAULT = object()
 
 
 class InfoExtractor(object):
@@ -281,7 +282,7 @@ class InfoExtractor(object):
             video_info['title'] = playlist_title
         return video_info
 
-    def _search_regex(self, pattern, string, name, default=None, fatal=True, flags=0):
+    def _search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0):
         """
         Perform a regex search on the given string, using a single or a list of
         patterns returning the first matching group.
@@ -295,7 +296,7 @@ class InfoExtractor(object):
                 mobj = re.search(p, string, flags)
                 if mobj: break
 
-        if sys.stderr.isatty() and os.name != 'nt':
+        if os.name != 'nt' and sys.stderr.isatty():
             _name = u'\033[0;34m%s\033[0m' % name
         else:
             _name = name
@@ -303,7 +304,7 @@ class InfoExtractor(object):
         if mobj:
             # return the first matching group
             return next(g for g in mobj.groups() if g is not None)
-        elif default is not None:
+        elif default is not _NO_DEFAULT:
             return default
         elif fatal:
             raise RegexNotFoundError(u'Unable to extract %s' % _name)
@@ -312,7 +313,7 @@ class InfoExtractor(object):
                 u'please report this issue on http://yt-dl.org/bug' % _name)
             return None
 
-    def _html_search_regex(self, pattern, string, name, default=None, fatal=True, flags=0):
+    def _html_search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0):
         """
         Like _search_regex, but strips HTML tags and unescapes entities.
         """

youtube_dl/extractor/facebook.py

@@ -17,7 +17,7 @@ from ..utils import (
 class FacebookIE(InfoExtractor):
     """Information Extractor for Facebook"""
 
-    _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/(?:video/video|photo)\.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)'
+    _VALID_URL = r'^(?:https?://)?(?:\w+\.)?facebook\.com/(?:[^#?]*#!/)?(?:video/video|photo)\.php\?(?:.*?)v=(?P<ID>\d+)(?:.*)'
     _LOGIN_URL = 'https://www.facebook.com/login.php?next=http%3A%2F%2Ffacebook.com%2Fhome.php&login_attempt=1'
     _CHECKPOINT_URL = 'https://www.facebook.com/checkpoint/?next=http%3A%2F%2Ffacebook.com%2Fhome.php&_fb_noscript=1'
     _NETRC_MACHINE = 'facebook'
@@ -27,7 +27,7 @@ class FacebookIE(InfoExtractor):
         u'file': u'120708114770723.mp4',
         u'md5': u'48975a41ccc4b7a581abd68651c1a5a8',
         u'info_dict': {
-            u"duration": 279, 
+            u"duration": 279,
             u"title": u"PEOPLE ARE AWESOME 2013"
         }
     }

youtube_dl/extractor/generic.py

@@ -222,6 +222,18 @@ class GenericIE(InfoExtractor):
                 'id': video_id,
             }
 
+        # Look for embedded blip.tv player
+        mobj = re.search(r'<meta\s[^>]*https?://api.blip.tv/\w+/redirect/\w+/(\d+)', webpage)
+        if mobj:
+            return self.url_result('http://blip.tv/seo/-'+mobj.group(1), 'BlipTV')
+        mobj = re.search(r'<(?:iframe|embed|object)\s[^>]*https?://(?:\w+\.)?blip.tv/(?:play/|api\.swf#)([a-zA-Z0-9]+)', webpage)
+        if mobj:
+            player_url = 'http://blip.tv/play/%s.x?p=1' % mobj.group(1)
+            player_page = self._download_webpage(player_url, mobj.group(1))
+            blip_video_id = self._search_regex(r'data-episode-id="(\d+)', player_page, u'blip_video_id', fatal=False)
+            if blip_video_id:
+                return self.url_result('http://blip.tv/seo/-'+blip_video_id, 'BlipTV')
+
         # Look for Bandcamp pages with custom domain
         mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
         if mobj is not None:
@@ -229,6 +241,12 @@ class GenericIE(InfoExtractor):
             # Don't set the extractor because it can be a track url or an album
             return self.url_result(burl)
 
+        # Look for embedded Vevo player
+        mobj = re.search(
+            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'))
+
         # Start with something easy: JW Player in SWFObject
         mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
         if mobj is None:

youtube_dl/extractor/mtv.py

@@ -93,7 +93,9 @@ class MTVServicesInfoExtractor(InfoExtractor):
 
 
 class MTVIE(MTVServicesInfoExtractor):
-    _VALID_URL = r'^https?://(?:www\.)?mtv\.com/videos/.+?/(?P<videoid>[0-9]+)/[^/]+$'
+    _VALID_URL = r'''(?x)^https?://
+        (?:(?:www\.)?mtv\.com/videos/.+?/(?P<videoid>[0-9]+)/[^/]+$|
+           m\.mtv\.com/videos/video\.rbml\?.*?id=(?P<mgid>[^&]+))'''
 
     _FEED_URL = 'http://www.mtv.com/player/embed/AS3/rss/'
 
@@ -127,16 +129,17 @@ class MTVIE(MTVServicesInfoExtractor):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('videoid')
-
-        webpage = self._download_webpage(url, video_id)
-
-        # Some videos come from Vevo.com
-        m_vevo = re.search(r'isVevoVideo = true;.*?vevoVideoId = "(.*?)";',
-                           webpage, re.DOTALL)
-        if m_vevo:
-            vevo_id = m_vevo.group(1);
-            self.to_screen(u'Vevo video detected: %s' % vevo_id)
-            return self.url_result('vevo:%s' % vevo_id, ie='Vevo')
-
-        uri = self._html_search_regex(r'/uri/(.*?)\?', webpage, u'uri')
+        uri = mobj.group('mgid')
+        if uri is None:
+            webpage = self._download_webpage(url, video_id)
+    
+            # Some videos come from Vevo.com
+            m_vevo = re.search(r'isVevoVideo = true;.*?vevoVideoId = "(.*?)";',
+                               webpage, re.DOTALL)
+            if m_vevo:
+                vevo_id = m_vevo.group(1);
+                self.to_screen(u'Vevo video detected: %s' % vevo_id)
+                return self.url_result('vevo:%s' % vevo_id, ie='Vevo')
+    
+            uri = self._html_search_regex(r'/uri/(.*?)\?', webpage, u'uri')
         return self._get_videos_info(uri)

youtube_dl/extractor/radiofrance.py

@@ -0,0 +1,60 @@
+# coding: utf-8
+import datetime
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    remove_start,
+)
+
+
+class RadioFranceIE(InfoExtractor):
+    _VALID_URL = r'^https?://maison\.radiofrance\.fr/radiovisions/(?P<id>[^?#]+)'
+    IE_NAME = u'radiofrance'
+
+    _TEST = {
+        u'url': u'http://maison.radiofrance.fr/radiovisions/one-one',
+        u'file': u'one-one.ogg',
+        u'md5': u'bdbb28ace95ed0e04faab32ba3160daf',
+        u'info_dict': {
+            u"title": u"One to one",
+            u"description": u"Plutôt que d'imaginer la radio de demain comme technologie ou comme création de contenu, je veux montrer que quelles que soient ses évolutions, j'ai l'intime conviction que la radio continuera d'être un grand média de proximité pour les auditeurs.",
+            u"uploader": u"Thomas Hercouët",
+        },
+    }
+
+    def _real_extract(self, url):
+        m = re.match(self._VALID_URL, url)
+        video_id = m.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+        title = self._html_search_regex(r'<h1>(.*?)</h1>', webpage, u'title')
+        description = self._html_search_regex(
+            r'<div class="bloc_page_wrapper"><div class="text">(.*?)</div>',
+            webpage, u'description', fatal=False)
+        uploader = self._html_search_regex(
+            r'<div class="credit">&nbsp;&nbsp;&copy;&nbsp;(.*?)</div>',
+            webpage, u'uploader', fatal=False)
+
+        formats_str = self._html_search_regex(
+            r'class="jp-jplayer[^"]*" data-source="([^"]+)">',
+            webpage, u'audio URLs')
+        formats = [
+            {
+                'format_id': m[0],
+                'url': m[1],
+                'vcodec': 'none',
+            }
+            for m in
+            re.findall(r"([a-z0-9]+)\s*:\s*'([^']+)'", formats_str)
+        ]
+        # No sorting, we don't know any more about these formats
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'description': description,
+            'uploader': uploader,
+        }

youtube_dl/extractor/rtlnow.py

@@ -10,7 +10,7 @@ from ..utils import (
 
 class RTLnowIE(InfoExtractor):
     """Information Extractor for RTL NOW, RTL2 NOW, RTL NITRO, SUPER RTL NOW, VOX NOW and n-tv NOW"""
-    _VALID_URL = r'(?:http://)?(?P<url>(?P<base_url>rtl-now\.rtl\.de|rtl2now\.rtl2\.de|(?:www\.)?voxnow\.de|(?:www\.)?rtlnitronow\.de|(?:www\.)?superrtlnow\.de|(?:www\.)?n-tvnow\.de)/+[a-zA-Z0-9-]+/[a-zA-Z0-9-]+\.php\?(?:container_id|film_id)=(?P<video_id>[0-9]+)&player=1(?:&season=[0-9]+)?(?:&.*)?)'
+    _VALID_URL = r'(?:http://)?(?P<url>(?P<domain>rtl-now\.rtl\.de|rtl2now\.rtl2\.de|(?:www\.)?voxnow\.de|(?:www\.)?rtlnitronow\.de|(?:www\.)?superrtlnow\.de|(?:www\.)?n-tvnow\.de)/+[a-zA-Z0-9-]+/[a-zA-Z0-9-]+\.php\?(?:container_id|film_id)=(?P<video_id>[0-9]+)&player=1(?:&season=[0-9]+)?(?:&.*)?)'
     _TESTS = [{
         u'url': u'http://rtl-now.rtl.de/ahornallee/folge-1.php?film_id=90419&player=1&season=1',
         u'file': u'90419.flv',
@@ -82,7 +82,7 @@ class RTLnowIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
 
         webpage_url = u'http://' + mobj.group('url')
-        video_page_url = u'http://' + mobj.group('base_url')
+        video_page_url = u'http://' + mobj.group('domain') + u'/'
         video_id = mobj.group(u'video_id')
 
         webpage = self._download_webpage(webpage_url, video_id)

youtube_dl/extractor/vevo.py

@@ -15,7 +15,12 @@ class VevoIE(InfoExtractor):
     Accepts urls from vevo.com or in the format 'vevo:{id}'
     (currently used by MTVIE)
     """
-    _VALID_URL = r'((http://www\.vevo\.com/watch/(?:[^/]+/[^/]+/)?)|(vevo:))(?P<id>.*?)(\?|$)'
+    _VALID_URL = r'''(?x)
+        (?:https?://www\.vevo\.com/watch/(?:[^/]+/[^/]+/)?|
+           https?://cache\.vevo\.com/m/html/embed\.html\?video=|
+           https?://videoplayer\.vevo\.com/embed/embedded\?videoId=|
+           vevo:)
+        (?P<id>[^&?#]+)'''
     _TESTS = [{
         u'url': u'http://www.vevo.com/watch/hurts/somebody-to-die-for/GB1101300280',
         u'file': u'GB1101300280.mp4',

youtube_dl/extractor/videopremium.py

@@ -15,6 +15,7 @@ class VideoPremiumIE(InfoExtractor):
         u'params': {
             u'skip_download': True,
         },
+        u'skip': u'Test file has been deleted.',
     }
 
     def _real_extract(self, url):

youtube_dl/extractor/xtube.py

@@ -32,7 +32,7 @@ class XTubeIE(InfoExtractor):
 
         video_title = self._html_search_regex(r'<div class="p_5px[^>]*>([^<]+)', webpage, u'title')
         video_uploader = self._html_search_regex(r'so_s\.addVariable\("owner_u", "([^"]+)', webpage, u'uploader', fatal=False)
-        video_description = self._html_search_regex(r'<p class="video_description">([^<]+)', webpage, u'description', default=None)
+        video_description = self._html_search_regex(r'<p class="video_description">([^<]+)', webpage, u'description', fatal=False)
         video_url= self._html_search_regex(r'var videoMp4 = "([^"]+)', webpage, u'video_url').replace('\\/', '/')
         path = compat_urllib_parse_urlparse(video_url).path
         extension = os.path.splitext(path)[1][1:]

youtube_dl/extractor/youtube.py

@@ -1361,7 +1361,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
                 video_description = u''
 
         def _extract_count(klass):
-            count = self._search_regex(r'class="%s">([\d,]+)</span>' % re.escape(klass), video_webpage, klass, fatal=False)
+            count = self._search_regex(
+                r'class="%s">([\d,]+)</span>' % re.escape(klass),
+                video_webpage, klass, default=None)
             if count is not None:
                 return int(count.replace(',', ''))
             return None

youtube_dl/utils.py

@@ -1066,13 +1066,14 @@ def fix_xml_all_ampersand(xml_str):
 
 
 def setproctitle(title):
+    assert isinstance(title, type(u''))
     try:
         libc = ctypes.cdll.LoadLibrary("libc.so.6")
     except OSError:
         return
     title = title
     buf = ctypes.create_string_buffer(len(title) + 1)
-    buf.value = title
+    buf.value = title.encode('utf-8')
     try:
         libc.prctl(15, ctypes.byref(buf), 0, 0, 0)
     except AttributeError:

youtube_dl/version.py

@@ -1,2 +1,2 @@
 
-__version__ = '2013.12.16.2'
+__version__ = '2013.12.17'