]> gitweb @ CieloNegro.org - youtube-dl.git/commitdiff
Add new extractor
authorLucas <mikotosc@gmail.com>
Thu, 24 Sep 2015 20:19:09 +0000 (22:19 +0200)
committerJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>
Sat, 31 Oct 2015 14:18:23 +0000 (15:18 +0100)
youtube_dl/extractor/__init__.py
youtube_dl/extractor/kika.py [new file with mode: 0644]

index f98e6487e467f63c5476bd7682723e8f6770773b..5ad4e9c36dc1b7b26903abc2a05555a8ab3a636a 100644 (file)
@@ -274,6 +274,7 @@ from .karrierevideos import KarriereVideosIE
 from .keezmovies import KeezMoviesIE
 from .khanacademy import KhanAcademyIE
 from .kickstarter import KickStarterIE
+from .kika import KikaIE
 from .keek import KeekIE
 from .kontrtube import KontrTubeIE
 from .krasview import KrasViewIE
diff --git a/youtube_dl/extractor/kika.py b/youtube_dl/extractor/kika.py
new file mode 100644 (file)
index 0000000..db0f333
--- /dev/null
@@ -0,0 +1,115 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+
+class KikaIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?kika\.de/(?:[a-z-]+/)*(?:video|sendung)(?P<id>\d+).*'
+
+    _TESTS = [
+        {
+            'url': 'http://www.kika.de/baumhaus/videos/video9572.html',
+            'md5': '94fc748cf5d64916571d275a07ffe2d5',
+            'info_dict': {
+                'id': '9572',
+                'ext': 'mp4',
+                'title': 'Baumhaus vom 29. Oktober 2014',
+                'description': None
+            }
+        },
+        {
+            'url': 'http://www.kika.de/sendungen/einzelsendungen/weihnachtsprogramm/videos/video8182.html',
+            'md5': '5fe9c4dd7d71e3b238f04b8fdd588357',
+            'info_dict': {
+                'id': '8182',
+                'ext': 'mp4',
+                'title': 'Beutolomäus und der geheime Weihnachtswunsch',
+                'description': 'md5:b69d32d7b2c55cbe86945ab309d39bbd'
+            }
+        },
+        {
+            'url': 'http://www.kika.de/videos/allevideos/video9572_zc-32ca94ad_zs-3f535991.html',
+            'md5': '94fc748cf5d64916571d275a07ffe2d5',
+            'info_dict': {
+                'id': '9572',
+                'ext': 'mp4',
+                'title': 'Baumhaus vom 29. Oktober 2014',
+                'description': None
+            }
+        },
+        {
+            'url': 'http://www.kika.de/sendungen/einzelsendungen/weihnachtsprogramm/videos/sendung81244_zc-81d703f8_zs-f82d5e31.html',
+            'md5': '5fe9c4dd7d71e3b238f04b8fdd588357',
+            'info_dict': {
+                'id': '8182',
+                'ext': 'mp4',
+                'title': 'Beutolomäus und der geheime Weihnachtswunsch',
+                'description': 'md5:b69d32d7b2c55cbe86945ab309d39bbd'
+            }
+        }
+    ]
+
+    def _real_extract(self, url):
+        # broadcast_id may be the same as the video_id
+        broadcast_id = self._match_id(url)
+        webpage = self._download_webpage(url, broadcast_id)
+
+        xml_re = r'sectionArticle[ "](?:(?!sectionA[ "])(?:.|\n))*?dataURL:\'(?:/[a-z-]+?)*?/video(\d+)-avCustom\.xml'
+        video_id = self._search_regex(xml_re, webpage, "xml_url", default=None)
+        if not video_id:
+            # Video is not available online
+            err_msg = 'Video %s is not available online' % broadcast_id
+            raise ExtractorError(err_msg, expected=True)
+
+        xml_url = 'http://www.kika.de/video%s-avCustom.xml' % (video_id)
+        xml_tree = self._download_xml(xml_url, video_id)
+
+        title = xml_tree.find('title').text
+        webpage_url = xml_tree.find('htmlUrl').text
+
+        # Try to get the description, not available for all videos
+        try:
+            broadcast_elem = xml_tree.find('broadcast')
+            description = broadcast_elem.find('broadcastDescription').text
+        except AttributeError:
+            # No description available
+            description = None
+
+        # duration string format is mm:ss (even if it is >= 1 hour, e.g. 78:42)
+        tmp = xml_tree.find('duration').text.split(':')
+        duration = int(tmp[0]) * 60 + int(tmp[1])
+
+        formats_list = []
+        for elem in xml_tree.find('assets'):
+            format_dict = {}
+            format_dict['url'] = elem.find('progressiveDownloadUrl').text
+            format_dict['ext'] = elem.find('mediaType').text.lower()
+            format_dict['format'] = elem.find('profileName').text
+            width = int(elem.find('frameWidth').text)
+            height = int(elem.find('frameHeight').text)
+            format_dict['width'] = width
+            format_dict['height'] = height
+            format_dict['resolution'] = '%dx%d' % (width, height)
+            format_dict['abr'] = int(elem.find('bitrateAudio').text)
+            format_dict['vbr'] = int(elem.find('bitrateVideo').text)
+            format_dict['tbr'] = format_dict['abr'] + format_dict['vbr']
+            format_dict['filesize'] = int(elem.find('fileSize').text)
+
+            # append resolution and dict for sorting by resolution
+            formats_list.append((width * height, format_dict))
+
+        # Sort by resolution (=quality)
+        formats_list.sort()
+
+        out_list = [x[1] for x in formats_list]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'formats': out_list,
+            'duration': duration,
+            'webpage_url': webpage_url
+        }