Merge branch 'master' of github.com:rg3/youtube-dl

youtube_dl/extractor/mit.py

@@ -73,7 +73,6 @@ class MITIE(TechTVMITIE):
 
     _TEST = {
         'url': 'http://video.mit.edu/watch/the-government-is-profiling-you-13222/',
-        'file': '.mp4',
         'md5': '7db01d5ccc1895fc5010e9c9e13648da',
         'info_dict': {
             'id': '21783',

youtube_dl/extractor/rtlnow.py

@@ -1,148 +1,165 @@
 # encoding: utf-8
-
 from __future__ import unicode_literals
 
 import re
 
 from .common import InfoExtractor
 from ..utils import (
-    clean_html,
     ExtractorError,
+    clean_html,
+    unified_strdate,
+    int_or_none,
 )
 
 
 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<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]+)?(?:&.*)?)'
+    _VALID_URL = r'''(?x)
-    _TESTS = [{
+                        (?:https?://)?
-        'url': 'http://rtl-now.rtl.de/ahornallee/folge-1.php?film_id=90419&player=1&season=1',
+                        (?P<url>
-        'file': '90419.flv',
+                            (?P<domain>
-        'info_dict': {
+                                rtl-now\.rtl\.de|
-            'upload_date': '20070416',
+                                rtl2now\.rtl2\.de|
-            'title': 'Ahornallee - Folge 1 - Der Einzug',
+                                (?:www\.)?voxnow\.de|
-            'description': 'Folge 1 - Der Einzug',
+                                (?: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 = [
+        {
+            'url': 'http://rtl-now.rtl.de/ahornallee/folge-1.php?film_id=90419&player=1&season=1',
+            'info_dict': {
+                'id': '90419',
+                'ext': 'flv',
+                'title': 'Ahornallee - Folge 1 - Der Einzug',
+                'description': 'md5:ce843b6b5901d9a7f7d04d1bbcdb12de',
+                'upload_date': '20070416',
+                'duration': 1685,
+            },
+            'params': {
+                'skip_download': True,
+            },
+            'skip': 'Only works from Germany',
         },
-        'params': {
+        {
-            'skip_download': True,
+            'url': 'http://rtl2now.rtl2.de/aerger-im-revier/episode-15-teil-1.php?film_id=69756&player=1&season=2&index=5',
+            'info_dict': {
+                'id': '69756',
+                'ext': 'flv',
+                'title': 'Ärger im Revier - Ein junger Ladendieb, ein handfester Streit u.a.',
+                'description': 'md5:3fb247005ed21a935ffc82b7dfa70cf0',
+                'thumbnail': 'http://autoimg.static-fra.de/rtl2now/219850/1500x1500/image2.jpg',
+                'upload_date': '20120519',
+                'duration': 1245,
+            },
+            'params': {
+                'skip_download': True,
+            },
+            'skip': 'Only works from Germany',
         },
-        'skip': 'Only works from Germany',
+        {
-    },
+            'url': 'http://www.voxnow.de/voxtours/suedafrika-reporter-ii.php?film_id=13883&player=1&season=17',
-    {
+            'info_dict': {
-        'url': 'http://rtl2now.rtl2.de/aerger-im-revier/episode-15-teil-1.php?film_id=69756&player=1&season=2&index=5',
+                'id': '13883',
-        'file': '69756.flv',
+                'ext': 'flv',
-        'info_dict': {
+                'title': 'Voxtours - Südafrika-Reporter II',
-            'upload_date': '20120519',
+                'description': 'md5:de7f8d56be6fd4fed10f10f57786db00',
-            'title': 'Ärger im Revier - Ein junger Ladendieb, ein handfester Streit...',
+                'upload_date': '20090627',
-            'description': 'Ärger im Revier - Ein junger Ladendieb, ein handfester Streit u.a.',
+                'duration': 1800,
-            'thumbnail': 'http://autoimg.static-fra.de/rtl2now/219850/1500x1500/image2.jpg',
+            },
+            'params': {
+                'skip_download': True,
+            },
         },
-        'params': {
+        {
-            'skip_download': True,
+            'url': 'http://superrtlnow.de/medicopter-117/angst.php?film_id=99205&player=1',
+            'info_dict': {
+                'id': '99205',
+                'ext': 'flv',
+                'title': 'Medicopter 117 - Angst!',
+                'description': 'md5:895b1df01639b5f61a04fc305a5cb94d',
+                'thumbnail': 'http://autoimg.static-fra.de/superrtlnow/287529/1500x1500/image2.jpg',
+                'upload_date': '20080928',
+                'duration': 2691,
+            },
+            'params': {
+                'skip_download': True,
+            },
         },
-        'skip': 'Only works from Germany',
+        {
-    },
+            'url': 'http://www.n-tvnow.de/deluxe-alles-was-spass-macht/thema-ua-luxushotel-fuer-vierbeiner.php?container_id=153819&player=1&season=0',
-    {
+            'info_dict': {
-        'url': 'http://www.voxnow.de/voxtours/suedafrika-reporter-ii.php?film_id=13883&player=1&season=17',
+                'id': '153819',
-        'file': '13883.flv',
+                'ext': 'flv',
-        'info_dict': {
+                'title': 'Deluxe - Alles was Spaß macht - Thema u.a.: Luxushotel für Vierbeiner',
-            'upload_date': '20090627',
+                'description': 'md5:c3705e1bb32e1a5b2bcd634fc065c631',
-            'title': 'Voxtours - Südafrika-Reporter II',
+                'thumbnail': 'http://autoimg.static-fra.de/ntvnow/383157/1500x1500/image2.jpg',
-            'description': 'Südafrika-Reporter II',
+                'upload_date': '20140221',
+                'duration': 2429,
+            },
+            'skip': 'Only works from Germany',
         },
-        'params': {
+    ]
-            'skip_download': True,
-        },
-    },
-    {
-        'url': 'http://superrtlnow.de/medicopter-117/angst.php?film_id=99205&player=1',
-        'file': '99205.flv',
-        'info_dict': {
-            'upload_date': '20080928', 
-            'title': 'Medicopter 117 - Angst!',
-            'description': 'Angst!',
-            'thumbnail': 'http://autoimg.static-fra.de/superrtlnow/287529/1500x1500/image2.jpg'
-        },
-        'params': {
-            'skip_download': True,
-        },
-    },
-    {
-        'url': 'http://www.n-tvnow.de/top-gear/episode-1-2013-01-01-00-00-00.php?film_id=124903&player=1&season=10',
-        'file': '124903.flv',
-        'info_dict': {
-            'upload_date': '20130101',
-            'title': 'Top Gear vom 01.01.2013',
-            'description': 'Episode 1',
-        },
-        'params': {
-            'skip_download': True,
-        },
-        'skip': 'Only works from Germany',
-    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-
+        video_page_url = 'http://%s/' % mobj.group('domain')
-        webpage_url = 'http://' + mobj.group('url')
-        video_page_url = 'http://' + mobj.group('domain') + '/'
         video_id = mobj.group('video_id')
 
-        webpage = self._download_webpage(webpage_url, video_id)
+        webpage = self._download_webpage('http://' + mobj.group('url'), video_id)
 
-        note_m = re.search(r'''(?sx)
+        mobj = re.search(r'(?s)<div style="margin-left: 20px; font-size: 13px;">(.*?)<div id="playerteaser">', webpage)
-            <div[ ]style="margin-left:[ ]20px;[ ]font-size:[ ]13px;">(.*?)
+        if mobj:
-            <div[ ]id="playerteaser">''', webpage)
+            raise ExtractorError(clean_html(mobj.group(1)), expected=True)
-        if note_m:
+
-            msg = clean_html(note_m.group(1))
+        title = self._og_search_title(webpage)
-            raise ExtractorError(msg)
+        description = self._og_search_description(webpage)
+        thumbnail = self._og_search_thumbnail(webpage, default=None)
+
+        upload_date = unified_strdate(self._html_search_meta('uploadDate', webpage, 'upload date'))
+
+        mobj = re.search(r'<meta itemprop="duration" content="PT(?P<seconds>\d+)S" />', webpage)
+        duration = int(mobj.group('seconds')) if mobj else None
 
-        video_title = self._html_search_regex(
-            r'<title>(?P<title>[^<]+?)( \| [^<]*)?</title>',
-            webpage, 'title')
         playerdata_url = self._html_search_regex(
-            r'\'playerdata\': \'(?P<playerdata_url>[^\']+)\'',
+            r"'playerdata': '(?P<playerdata_url>[^']+)'", webpage, 'playerdata_url')
-            webpage, 'playerdata_url')
 
-        playerdata = self._download_webpage(playerdata_url, video_id)
+        playerdata = self._download_xml(playerdata_url, video_id, 'Downloading player data XML')
-        mobj = re.search(r'<title><!\[CDATA\[(?P<description>.+?)(?:\s+- (?:Sendung )?vom (?P<upload_date_d>[0-9]{2})\.(?P<upload_date_m>[0-9]{2})\.(?:(?P<upload_date_Y>[0-9]{4})|(?P<upload_date_y>[0-9]{2})) [0-9]{2}:[0-9]{2} Uhr)?\]\]></title>', playerdata)
+
-        if mobj:
+        videoinfo = playerdata.find('./playlist/videoinfo')
-            video_description = mobj.group('description')
+        
-            if mobj.group('upload_date_Y'):
+        formats = []
-                video_upload_date = mobj.group('upload_date_Y')
+        for filename in videoinfo.findall('filename'):
-            elif mobj.group('upload_date_y'):
+            mobj = re.search(r'(?P<url>rtmpe://(?:[^/]+/){2})(?P<play_path>.+)', filename.text)
-                video_upload_date = '20' + mobj.group('upload_date_y')
+            if mobj:
+                fmt = {
+                    'url': mobj.group('url'),
+                    'play_path': 'mp4:' + mobj.group('play_path'),
+                    'page_url': video_page_url,
+                    'player_url': video_page_url + 'includes/vodplayer.swf',
+                }
             else:
-                video_upload_date = None
+                fmt = {
-            if video_upload_date:
+                    'url': filename.text,
-                video_upload_date += mobj.group('upload_date_m') + mobj.group('upload_date_d')
+                }
-        else:
+            fmt.update({
-            video_description = None
+                'width': int_or_none(filename.get('width')),
-            video_upload_date = None
+                'height': int_or_none(filename.get('height')),
-            self._downloader.report_warning('Unable to extract description and upload date')
+                'vbr': int_or_none(filename.get('bitrate')),
-
+                'ext': 'flv',
-        # Thumbnail: not every video has an thumbnail
+            })
-        mobj = re.search(r'<meta property="og:image" content="(?P<thumbnail>[^"]+)">', webpage)
+            formats.append(fmt)
-        if mobj:
-            video_thumbnail = mobj.group('thumbnail')
-        else:
-            video_thumbnail = None
-
-        mobj = re.search(r'<filename [^>]+><!\[CDATA\[(?P<url>rtmpe://(?:[^/]+/){2})(?P<play_path>[^\]]+)\]\]></filename>', playerdata)
-        if mobj is None:
-            raise ExtractorError('Unable to extract media URL')
-        video_url = mobj.group('url')
-        video_play_path = 'mp4:' + mobj.group('play_path')
-        video_player_url = video_page_url + 'includes/vodplayer.swf'
 
         return {
             'id': video_id,
-            'url': video_url,
+            'title': title,
-            'play_path': video_play_path,
+            'description': description,
-            'page_url': video_page_url,
+            'thumbnail': thumbnail,
-            'player_url': video_player_url,
+            'upload_date': upload_date,
-            'ext': 'flv',
+            'duration': duration,
-            'title': video_title,
+            'formats': formats,
-            'description': video_description,
+        }
-            'upload_date': video_upload_date,
-            'thumbnail': video_thumbnail,
-        }

youtube_dl/extractor/xhamster.py

@@ -103,6 +103,7 @@ class XHamsterIE(InfoExtractor):
         }]
 
         if not hd:
+            mrss_url = self._search_regex(r'<link rel="canonical" href="([^"]+)', webpage, 'mrss_url')
             webpage = self._download_webpage(mrss_url + '?hd', video_id, note='Downloading HD webpage')
             if is_hd(webpage):
                 video_url = extract_video_url(webpage)