youtube-dl

commit ebdb64d60511cc281c14431b894091bf32a6b97b
parent a6ffb92f0ba9b64b82a56bcf8417744ff3e829f3
Author: Philipp Hagemeister <phihag@phihag.de>
Date:   Sat,  7 Jun 2014 12:43:31 +0200

Merge remote-tracking branch 'pulpe/tagesschau'

Diffstat:
M
youtube_dl/extractor/__init__.py
 | 
1
+
A
youtube_dl/extractor/tagesschau.py
 | 
82
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++

2 files changed, 83 insertions(+), 0 deletions(-)
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
@@ -266,6 +266,7 @@ from .streamcz import StreamCZIE
 from .swrmediathek import SWRMediathekIE
 from .syfy import SyfyIE
 from .sztvhu import SztvHuIE
+from .tagesschau import TagesschauIE
 from .teamcoco import TeamcocoIE
 from .techtalks import TechTalksIE
 from .ted import TEDIE
diff --git a/youtube_dl/extractor/tagesschau.py b/youtube_dl/extractor/tagesschau.py
@@ -0,0 +1,82 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class TagesschauIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?tagesschau\.de/multimedia/video/video(?P<id>-?\d+)\.html'
+
+    _TESTS = [{
+        'url': 'http://www.tagesschau.de/multimedia/video/video1399128.html',
+        'md5': 'bcdeac2194fb296d599ce7929dfa4009',
+        'info_dict': {
+            'id': '1399128',
+            'ext': 'mp4',
+            'title': 'Harald Range, Generalbundesanwalt, zu den Ermittlungen',
+            'description': 'md5:69da3c61275b426426d711bde96463ab',
+            'thumbnail': 're:^http:.*\.jpg$',
+        },
+    }, {
+        'url': 'http://www.tagesschau.de/multimedia/video/video-196.html',
+        'md5': '8aaa8bf3ae1ca2652309718c03019128',
+        'info_dict': {
+            'id': '196',
+            'ext': 'mp4',
+            'title': 'Ukraine-Konflikt: Klitschko in Kiew als B\xfcrgermeister vereidigt',
+            'description': 'md5:f22e4af75821d174fa6c977349682691',
+            'thumbnail': 're:http://.*\.jpg',
+        },
+    }]      
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        if video_id.startswith('-'):
+            display_id = video_id.strip('-')
+        else:
+            display_id = video_id
+
+        webpage = self._download_webpage(url, display_id)
+
+        playerpage = self._download_webpage(
+            'http://www.tagesschau.de/multimedia/video/video%s~player_autoplay-true.html' % video_id, display_id, 'Downloading player page')
+
+        medias = re.findall(r'"(http://media.+?)", type:"video/(.+?)", quality:"(.+?)"', playerpage)
+
+        formats = []
+        for url, ext, res in medias:
+            
+            if res == 's':
+                res = 'small'
+                quality = 0
+            elif res == 'm':
+                res = 'medium'
+                quality = 1
+            elif res == 'l':
+                res = 'large'
+                quality = 2
+            else:
+                quality = 0
+
+            formats.append({
+                'format_id': res+'_'+ext,
+                'url': url,
+                'quality': quality,
+                'ext': ext,
+            })
+
+        self._sort_formats(formats)
+
+        thumbnail = re.findall(r'"(/multimedia/.+?\.jpg)"', playerpage)[-1]
+
+        return {
+            'id': display_id,
+            'title': self._og_search_title(webpage).strip(),
+            'thumbnail': 'http://www.tagesschau.de'+thumbnail,
+            'formats': formats,
+            'description': self._og_search_description(webpage).strip(),
+        }