release 2014.06.09

Ask to install them, as we do in the postprocessor.
We get some reports with it, like #3061 or #3048.

youtube_dl/downloader/hls.py

@@ -25,7 +25,7 @@ class HlsFD(FileDownloader):
             except (OSError, IOError):
                 pass
         else:
-            self.report_error(u'm3u8 download detected but ffmpeg or avconv could not be found')
+            self.report_error(u'm3u8 download detected but ffmpeg or avconv could not be found. Please install one.')
         cmd = [program] + args
 
         retval = subprocess.call(cmd)

youtube_dl/downloader/rtmp.py

@@ -106,7 +106,7 @@ class RtmpFD(FileDownloader):
         try:
             subprocess.call(['rtmpdump', '-h'], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
         except (OSError, IOError):
-            self.report_error('RTMP download detected but "rtmpdump" could not be run')
+            self.report_error('RTMP download detected but "rtmpdump" could not be run. Please install it.')
             return False
 
         # Download using rtmpdump. rtmpdump returns exit code 2 when

youtube_dl/extractor/__init__.py

@@ -332,6 +332,7 @@ from .viki import VikiIE
 from .vk import VKIE
 from .vube import VubeIE
 from .vuclip import VuClipIE
+from .vulture import VultureIE
 from .washingtonpost import WashingtonPostIE
 from .wat import WatIE
 from .wdr import (

youtube_dl/extractor/dreisat.py

@@ -1,39 +1,37 @@
-# coding: utf-8
+from __future__ import unicode_literals
 
 import re
 
 from .common import InfoExtractor
-from ..utils import (
-    unified_strdate,
-)
+from ..utils import unified_strdate
 
 
 class DreiSatIE(InfoExtractor):
     IE_NAME = '3sat'
     _VALID_URL = r'(?:http://)?(?:www\.)?3sat\.de/mediathek/(?:index\.php)?\?(?:(?:mode|display)=[^&]+&)*obj=(?P<id>[0-9]+)$'
     _TEST = {
-        u"url": u"http://www.3sat.de/mediathek/index.php?obj=36983",
-        u'file': u'36983.mp4',
-        u'md5': u'9dcfe344732808dbfcc901537973c922',
-        u'info_dict': {
-            u"title": u"Kaffeeland Schweiz",
-            u"description": u"Über 80 Kaffeeröstereien liefern in der Schweiz das Getränk, in das das Land so vernarrt ist: Mehr als 1000 Tassen trinkt ein Schweizer pro Jahr. SCHWEIZWEIT nimmt die Kaffeekultur unter die...", 
-            u"uploader": u"3sat",
-            u"upload_date": u"20130622"
+        'url': 'http://www.3sat.de/mediathek/index.php?obj=36983',
+        'md5': '9dcfe344732808dbfcc901537973c922',
+        'info_dict': {
+            'id': '36983',
+            'ext': 'mp4',
+            'title': 'Kaffeeland Schweiz',
+            'description': 'md5:cc4424b18b75ae9948b13929a0814033',
+            'uploader': '3sat',
+            'upload_date': '20130622'
         }
     }
 
-
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
         details_url = 'http://www.3sat.de/mediathek/xmlservice/web/beitragsDetails?ak=web&id=%s' % video_id
-        details_doc = self._download_xml(details_url, video_id, note=u'Downloading video details')
+        details_doc = self._download_xml(details_url, video_id, 'Downloading video details')
 
         thumbnail_els = details_doc.findall('.//teaserimage')
         thumbnails = [{
-            'width': te.attrib['key'].partition('x')[0],
-            'height': te.attrib['key'].partition('x')[2],
+            'width': int(te.attrib['key'].partition('x')[0]),
+            'height': int(te.attrib['key'].partition('x')[2]),
             'url': te.text,
         } for te in thumbnail_els]
 

youtube_dl/extractor/fc2.py

@@ -50,10 +50,13 @@ class FC2IE(InfoExtractor):
             raise ExtractorError('Error code: %s' % info['err_code'][0])
 
         video_url = info['filepath'][0] + '?mid=' + info['mid'][0]
+        title_info = info.get('title')
+        if title_info:
+            title = title_info[0]
 
         return {
             'id': video_id,
-            'title': info['title'][0],
+            'title': title,
             'url': video_url,
             'ext': 'flv',
             'thumbnail': thumbnail,

youtube_dl/extractor/generic.py

@@ -260,7 +260,24 @@ class GenericIE(InfoExtractor):
                 'uploader': 'Spi0n',
             },
             'add_ie': ['Dailymotion'],
-        }
+        },
+        # YouTube embed
+        {
+            'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
+            'info_dict': {
+                'id': 'FXRb4ykk4S0',
+                'ext': 'mp4',
+                'title': 'The NBL Auction 2014',
+                'uploader': 'BADMINTON England',
+                'uploader_id': 'BADMINTONEvents',
+                'upload_date': '20140603',
+                'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
+            },
+            'add_ie': ['Youtube'],
+            'params': {
+                'skip_download': True,
+            }
+        },
     ]
 
     def report_download_webpage(self, video_id):
@@ -478,8 +495,13 @@ class GenericIE(InfoExtractor):
 
         # Look for embedded YouTube player
         matches = re.findall(r'''(?x)
-            (?:<iframe[^>]+?src=|embedSWF\(\s*)
-            (["\'])(?P<url>(?:https?:)?//(?:www\.)?youtube\.com/
+            (?:
+                <iframe[^>]+?src=|
+                <embed[^>]+?src=|
+                embedSWF\(?:\s*
+            )
+            (["\'])
+                (?P<url>(?:https?:)?//(?:www\.)?youtube\.com/
                 (?:embed|v)/.+?)
             \1''', webpage)
         if matches:
@@ -646,6 +668,14 @@ class GenericIE(InfoExtractor):
             url = unescapeHTML(mobj.group('url'))
             return self.url_result(url)
 
+        # Look for embedded vulture.com player
+        mobj = re.search(
+            r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
+            webpage)
+        if mobj is not None:
+            url = unescapeHTML(mobj.group('url'))
+            return self.url_result(url, ie='Vulture')
+
         # Start with something easy: JW Player in SWFObject
         found = re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
         if not found:

youtube_dl/extractor/hypem.py

@@ -1,10 +1,11 @@
+from __future__ import unicode_literals
+
 import json
 import re
 import time
 
 from .common import InfoExtractor
 from ..utils import (
-    compat_str,
     compat_urllib_parse,
     compat_urllib_request,
 
@@ -13,59 +14,55 @@ from ..utils import (
 
 
 class HypemIE(InfoExtractor):
-    """Information Extractor for hypem"""
-    _VALID_URL = r'(?:http://)?(?:www\.)?hypem\.com/track/([^/]+)/([^/]+)'
+    _VALID_URL = r'http://(?:www\.)?hypem\.com/track/([^/]+)/([^/]+)'
     _TEST = {
-        u'url': u'http://hypem.com/track/1v6ga/BODYWORK+-+TAME',
-        u'file': u'1v6ga.mp3',
-        u'md5': u'b9cc91b5af8995e9f0c1cee04c575828',
-        u'info_dict': {
-            u"title": u"Tame"
+        'url': 'http://hypem.com/track/1v6ga/BODYWORK+-+TAME',
+        'md5': 'b9cc91b5af8995e9f0c1cee04c575828',
+        'info_dict': {
+            'id': '1v6ga',
+            'ext': 'mp3',
+            'title': 'Tame',
+            'uploader': 'BODYWORK',
         }
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError(u'Invalid URL: %s' % url)
         track_id = mobj.group(1)
 
         data = {'ax': 1, 'ts': time.time()}
         data_encoded = compat_urllib_parse.urlencode(data)
         complete_url = url + "?" + data_encoded
         request = compat_urllib_request.Request(complete_url)
-        response, urlh = self._download_webpage_handle(request, track_id, u'Downloading webpage with the url')
+        response, urlh = self._download_webpage_handle(
+            request, track_id, 'Downloading webpage with the url')
         cookie = urlh.headers.get('Set-Cookie', '')
 
-        self.report_extraction(track_id)
-
-        html_tracks = self._html_search_regex(r'<script type="application/json" id="displayList-data">(.*?)</script>',
-            response, u'tracks', flags=re.MULTILINE|re.DOTALL).strip()
+        html_tracks = self._html_search_regex(
+            r'(?ms)<script type="application/json" id="displayList-data">\s*(.*?)\s*</script>',
+            response, 'tracks')
         try:
             track_list = json.loads(html_tracks)
-            track = track_list[u'tracks'][0]
+            track = track_list['tracks'][0]
         except ValueError:
-            raise ExtractorError(u'Hypemachine contained invalid JSON.')
+            raise ExtractorError('Hypemachine contained invalid JSON.')
 
-        key = track[u"key"]
-        track_id = track[u"id"]
-        artist = track[u"artist"]
-        title = track[u"song"]
+        key = track['key']
+        track_id = track['id']
+        artist = track['artist']
+        title = track['song']
 
-        serve_url = "http://hypem.com/serve/source/%s/%s" % (compat_str(track_id), compat_str(key))
-        request = compat_urllib_request.Request(serve_url, "" , {'Content-Type': 'application/json'})
+        serve_url = "http://hypem.com/serve/source/%s/%s" % (track_id, key)
+        request = compat_urllib_request.Request(
+            serve_url, '', {'Content-Type': 'application/json'})
         request.add_header('cookie', cookie)
-        song_data_json = self._download_webpage(request, track_id, u'Downloading metadata')
-        try:
-            song_data = json.loads(song_data_json)
-        except ValueError:
-            raise ExtractorError(u'Hypemachine contained invalid JSON.')
-        final_url = song_data[u"url"]
+        song_data = self._download_json(request, track_id, 'Downloading metadata')
+        final_url = song_data["url"]
 
-        return [{
-            'id':       track_id,
-            'url':      final_url,
-            'ext':      "mp3",
-            'title':    title,
-            'artist':   artist,
-        }]
+        return {
+            'id': track_id,
+            'url': final_url,
+            'ext': 'mp3',
+            'title': title,
+            'uploader': artist,
+        }

youtube_dl/extractor/nrk.py

@@ -6,7 +6,7 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
-    int_or_none,
+    float_or_none,
     unified_strdate,
 )
 
@@ -89,7 +89,7 @@ class NRKTVIE(InfoExtractor):
         },
         {
             'url': 'http://tv.nrk.no/program/mdfp15000514',
-            'md5': '383650ece2b25ecec996ad7b5bb2a384',
+            'md5': 'af01795a31f1cf7265c8657534d8077b',
             'info_dict': {
                 'id': 'mdfp15000514',
                 'ext': 'flv',
@@ -111,9 +111,8 @@ class NRKTVIE(InfoExtractor):
         description = self._html_search_meta('description', page, 'description')
         thumbnail = self._html_search_regex(r'data-posterimage="([^"]+)"', page, 'thumbnail', fatal=False)
         upload_date = unified_strdate(self._html_search_meta('rightsfrom', page, 'upload date', fatal=False))
-        duration = self._html_search_regex(r'data-duration="([^"]+)"', page, 'duration', fatal=False)
-        if duration:
-            duration = float(duration)
+        duration = float_or_none(
+            self._html_search_regex(r'data-duration="([^"]+)"', page, 'duration', fatal=False))
 
         formats = []
 

youtube_dl/extractor/ntv.py

@@ -5,7 +5,6 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
-    ExtractorError,
     unescapeHTML
 )
 

youtube_dl/extractor/nuvid.py

@@ -3,6 +3,11 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..utils import (
+    parse_duration,
+    unified_strdate,
+    compat_urllib_request,
+)
 
 
 class NuvidIE(InfoExtractor):
@@ -13,8 +18,10 @@ class NuvidIE(InfoExtractor):
         'info_dict': {
             'id': '1310741',
             'ext': 'mp4',
-            "title": "Horny babes show their awesome bodeis and",
-            "age_limit": 18,
+            'title': 'Horny babes show their awesome bodeis and',
+            'duration': 129,
+            'upload_date': '20140508',
+            'age_limit': 18,
         }
     }
 
@@ -22,27 +29,41 @@ class NuvidIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
 
-        murl = url.replace('://www.', '://m.')
-        webpage = self._download_webpage(murl, video_id)
+        formats = []
 
+        for dwnld_speed, format_id in [(0, '3gp'), (5, 'mp4')]:
+            request = compat_urllib_request.Request(
+                'http://m.nuvid.com/play/%s' % video_id)
+            request.add_header('Cookie', 'skip_download_page=1; dwnld_speed=%d; adv_show=1' % dwnld_speed)
+            webpage = self._download_webpage(
+                request, video_id, 'Downloading %s page' % format_id)
+            video_url = self._html_search_regex(
+                r'<a href="([^"]+)"\s*>Continue to watch video', webpage, '%s video URL' % format_id, fatal=False)
+            if not video_url:
+                continue
+            formats.append({
+                'url': video_url,
+                'format_id': format_id,
+            })
+
+        webpage = self._download_webpage(
+            'http://m.nuvid.com/video/%s' % video_id, video_id, 'Downloading video page')
         title = self._html_search_regex(
-            r'<div class="title">\s+<h2[^>]*>([^<]+)</h2>',
-            webpage, 'title').strip()
-
-        url_end = self._html_search_regex(
-            r'href="(/[^"]+)"[^>]*data-link_type="mp4"',
-            webpage, 'video_url')
-        video_url = 'http://m.nuvid.com' + url_end
-
+            r'<div class="title">\s+<h2[^>]*>([^<]+)</h2>', webpage, 'title').strip()
         thumbnail = self._html_search_regex(
             r'href="(/thumbs/[^"]+)"[^>]*data-link_type="thumbs"',
             webpage, 'thumbnail URL', fatal=False)
+        duration = parse_duration(self._html_search_regex(
+            r'Length:\s*<span>(\d{2}:\d{2})</span>',webpage, 'duration', fatal=False))
+        upload_date = unified_strdate(self._html_search_regex(
+            r'Added:\s*<span>(\d{4}-\d{2}-\d{2})</span>', webpage, 'upload date', fatal=False))
 
         return {
             'id': video_id,
-            'url': video_url,
-            'ext': 'mp4',
             'title': title,
-            'thumbnail': thumbnail,
+            'thumbnail': 'http://m.nuvid.com%s' % thumbnail,
+            'duration': duration,
+            'upload_date': upload_date,
             'age_limit': 18,
-        }
+            'formats': formats,
+        }

youtube_dl/extractor/slutload.py

@@ -3,9 +3,6 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-)
 
 
 class SlutloadIE(InfoExtractor):

youtube_dl/extractor/soundcloud.py

@@ -1,7 +1,6 @@
 # encoding: utf-8
 from __future__ import unicode_literals
 
-import json
 import re
 import itertools
 

youtube_dl/extractor/teachertube.py

@@ -55,11 +55,13 @@ class TeacherTubeIE(InfoExtractor):
 
         quality = qualities(['mp3', 'flv', 'mp4'])
 
+        _, media_urls = zip(*re.findall(r'([\'"])file\1\s*:\s*"([^"]+)"', webpage))
+
         formats = [
             {
                 'url': media_url,
                 'quality': quality(determine_ext(media_url))
-            } for media_url in set(zip(*re.findall(r'([\'"])file\1\s*:\s*"([^"]+)"', webpage))[1])
+            } for media_url in set(media_urls)
         ]
 
         self._sort_formats(formats)

youtube_dl/extractor/veoh.py

@@ -7,6 +7,7 @@ from .common import InfoExtractor
 from ..utils import (
     compat_urllib_request,
     int_or_none,
+    ExtractorError,
 )
 
 
@@ -94,8 +95,12 @@ class VeohIE(InfoExtractor):
         if video_id.startswith('v'):
             rsp = self._download_xml(
                 r'http://www.veoh.com/api/findByPermalink?permalink=%s' % video_id, video_id, 'Downloading video XML')
-            if rsp.get('stat') == 'ok':
+            stat = rsp.get('stat')
+            if stat == 'ok':
                 return self._extract_video(rsp.find('./videoList/video'))
+            elif stat == 'fail':
+                raise ExtractorError(
+                    '%s said: %s' % (self.IE_NAME, rsp.find('./errorList/error').get('errorMessage')), expected=True)
 
         webpage = self._download_webpage(url, video_id)
         age_limit = 0

youtube_dl/extractor/vulture.py

@@ -0,0 +1,69 @@
+from __future__ import unicode_literals
+
+import json
+import os.path
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    parse_iso8601,
+)
+
+
+class VultureIE(InfoExtractor):
+    IE_NAME = 'vulture.com'
+    _VALID_URL = r'https?://video\.vulture\.com/video/(?P<display_id>[^/]+)/'
+    _TEST = {
+        'url': 'http://video.vulture.com/video/Mindy-Kaling-s-Harvard-Speech/player?layout=compact&read_more=1',
+        'md5': '8d997845642a2b5152820f7257871bc8',
+        'info_dict': {
+            'id': '6GHRQL3RV7MSD1H4',
+            'ext': 'mp4',
+            'title': 'kaling-speech-2-MAGNIFY STANDARD CONTAINER REVISED',
+            'uploader_id': 'Sarah',
+            'thumbnail': 're:^http://.*\.jpg$',
+            'timestamp': 1401288564,
+            'upload_date': '20140528',
+            'description': 'Uplifting and witty, as predicted.',
+            'duration': 1015,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        display_id = mobj.group('display_id')
+
+        webpage = self._download_webpage(url, display_id)
+        query_string = self._search_regex(
+            r"queryString\s*=\s*'([^']+)'", webpage, 'query string')
+        video_id = self._search_regex(
+            r'content=([^&]+)', query_string, 'video ID')
+        query_url = 'http://video.vulture.com/embed/player/container/1000/1000/?%s' % query_string
+
+        query_webpage = self._download_webpage(
+            query_url, display_id, note='Downloading query page')
+        params_json = self._search_regex(
+            r'(?sm)new MagnifyEmbeddablePlayer\({.*?contentItem:\s*(\{.*?\})\n,\n',
+            query_webpage,
+            'player params')
+        params = json.loads(params_json)
+
+        upload_timestamp = parse_iso8601(params['posted'].replace(' ', 'T'))
+        uploader_id = params.get('user', {}).get('handle')
+
+        media_item = params['media_item']
+        title = os.path.splitext(media_item['title'])[0]
+        duration = int_or_none(media_item.get('duration_seconds'))
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'url': media_item['pipeline_xid'],
+            'title': title,
+            'timestamp': upload_timestamp,
+            'thumbnail': params.get('thumbnail_url'),
+            'uploader_id': uploader_id,
+            'description': params.get('description'),
+            'duration': duration,
+        }

youtube_dl/version.py

@@ -1,2 +1,2 @@
 
-__version__ = '2014.06.07'
+__version__ = '2014.06.09'