[rtl2] Add new extractor
authorDavid-Development <david-dev@live.de>
Sat, 24 Jan 2015 17:28:16 +0000 (18:28 +0100)
committerDavid Development <david-dev@live.de>
Sat, 24 Jan 2015 23:07:15 +0000 (00:07 +0100)
youtube_dl/downloader/rtmp.py
youtube_dl/extractor/__init__.py
youtube_dl/extractor/rtl2.py [new file with mode: 0644]

index 6dbbc053c0a5e59bfbefa97449ca33e6c9b9d565..6f7ad588e9b262f6801ae01c6520db389571423e 100644 (file)
@@ -104,7 +104,8 @@ class RtmpFD(FileDownloader):
         live = info_dict.get('rtmp_live', False)
         conn = info_dict.get('rtmp_conn', None)
         protocol = info_dict.get('rtmp_protocol', None)
-
+        no_resume = info_dict.get('no_resume', False)
+        
         self.report_destination(filename)
         tmpfilename = self.temp_name(filename)
         test = self.params.get('test', False)
@@ -141,7 +142,10 @@ class RtmpFD(FileDownloader):
             basic_args += ['--conn', conn]
         if protocol is not None:
             basic_args += ['--protocol', protocol]
-        args = basic_args + [[], ['--resume', '--skip', '1']][not live and self.params.get('continuedl', False)]
+        if not no_resume:
+            basic_args += ['--resume']
+        
+        args = basic_args + [[], ['--skip', '1']][not live and self.params.get('continuedl', False)]
 
         if sys.platform == 'win32' and sys.version_info < (3, 0):
             # Windows subprocess module does not actually support Unicode
index 3f7ca6f7df8ffed659b4c94b76155d6fb8dab199..03c56156a97728863b23e02fea6ab7f62fec990e 100644 (file)
@@ -349,6 +349,7 @@ from .rtbf import RTBFIE
 from .rte import RteIE
 from .rtlnl import RtlXlIE
 from .rtlnow import RTLnowIE
+from .rtl2 import RTL2IE
 from .rtp import RTPIE
 from .rts import RTSIE
 from .rtve import RTVEALaCartaIE, RTVELiveIE
diff --git a/youtube_dl/extractor/rtl2.py b/youtube_dl/extractor/rtl2.py
new file mode 100644 (file)
index 0000000..14b45e8
--- /dev/null
@@ -0,0 +1,100 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    clean_html,
+    unified_strdate,
+    int_or_none,
+)
+
+
+class RTL2IE(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>(www\.)?rtl2\.de)/.*/(?P<video_id>.*))'
+    _TESTS = [{
+            'url': 'http://www.rtl2.de/sendung/grip-das-motormagazin/folge/folge-203-0',
+            'info_dict': {
+                'id': 'folge-203-0',
+                'ext': 'f4v',
+                'title': 'GRIP sucht den Sommerk\xf6nig',
+                'description' : 'Matthias, Det und Helge treten gegeneinander an.'
+            },
+            'params': {
+                # rtmp download
+                #'skip_download': True,
+            },
+        },
+        {
+            'url': 'http://www.rtl2.de/sendung/koeln-50667/video/5512-anna/21040-anna-erwischt-alex/',
+            'info_dict': {
+                'id': '21040-anna-erwischt-alex',
+                'ext': 'f4v',
+                'title': 'GRIP sucht den Sommerk\xf6nig',
+                'description' : 'Matthias, Det und Helge treten gegeneinander an.'
+            },
+            'params': {
+                # rtmp download
+                #'skip_download': True,
+            },
+        },
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_page_url = 'http://%s/' % mobj.group('domain')
+        video_id = mobj.group('video_id')
+    
+        webpage = self._download_webpage('http://' + mobj.group('url'), video_id)
+
+        vico_id = self._html_search_regex(r'vico_id\s*:\s*([0-9]+)', webpage, '%s');
+        vivi_id = self._html_search_regex(r'vivi_id\s*:\s*([0-9]+)', webpage, '%s');
+
+        info_url = 'http://www.rtl2.de/video/php/get_video.php?vico_id=' + vico_id + '&vivi_id=' + vivi_id
+        webpage = self._download_webpage(info_url, '')
+
+        video_info = json.loads(webpage)
+
+        download_url = video_info["video"]["streamurl"] # self._html_search_regex(r'streamurl\":\"(.*?)\"', webpage, '%s');
+        title = video_info["video"]["titel"] # self._html_search_regex(r'titel\":\"(.*?)\"', webpage, '%s');
+        description = video_info["video"]["beschreibung"] # self._html_search_regex(r'beschreibung\":\"(.*?)\"', webpage, '%s');
+        #ext = self._html_search_regex(r'streamurl\":\".*?(\..{2,4})\"', webpage, '%s');
+
+        thumbnail = video_info["video"]["image"]
+
+        download_url = download_url.replace("\\", "")
+
+        stream_url = 'mp4:' + self._html_search_regex(r'ondemand/(.*)', download_url, '%s')
+
+        #print(download_url)
+        #print(stream_url)
+        #print(title)
+        #print(description)
+        #print(video_id)
+        
+        formats = []
+
+        fmt = {
+            'url' : download_url,
+                #'app': 'ondemand?_fcs_vhost=cp108781.edgefcs.net',
+                'play_path': stream_url,
+                'player_url': 'http://www.rtl2.de/flashplayer/vipo_player.swf',
+                'page_url': url,
+                'flash_version' : "LNX 11,2,202,429",
+                'rtmp_conn' : ["S:connect", "O:1", "NS:pageUrl:" + url, "NB:fpad:0", "NN:videoFunction:1", "O:0"],
+                'no_resume' : 1,
+        }
+
+        formats.append(fmt)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail' : thumbnail,
+            'description' : description,
+            'formats': formats,
+        }