[ninenow] Add new extractor(closes #5181)

diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
index 71baee90d6ac8f591b29247ddc4b7f6dcf1319f2..45817d7df8a0196763411b50eada48f15f9f4205 100644 (file)
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@@ -537,6 +537,7 @@ from .nick import (
 from .niconico import NiconicoIE, NiconicoPlaylistIE
 from .ninecninemedia import NineCNineMediaIE
 from .ninegag import NineGagIE
+from .ninenow import NineNowIE
 from .noco import NocoIE
 from .normalboots import NormalbootsIE
 from .nosvideo import NosVideoIE

diff --git a/youtube_dl/extractor/ninenow.py b/youtube_dl/extractor/ninenow.py
new file mode 100644 (file)
index 0000000..f54e74d
--- /dev/null
+++ b/youtube_dl/extractor/ninenow.py
@@ -0,0 +1,72 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    int_or_none,
+    float_or_none,
+    ExtractorError,
+)
+
+
+class NineNowIE(InfoExtractor):
+    IE_NAME = '9now.com.au'
+    _VALID_URL = r'https?://(?:www\.)?9now\.com\.au/(?:[^/]+/){2}(?P<id>[^/?#]+)'
+    _TESTS = [{
+        # clip
+        'url': 'https://www.9now.com.au/afl-footy-show/2016/clip-ciql02091000g0hp5oktrnytc',
+        'md5': '17cf47d63ec9323e562c9957a968b565',
+        'info_dict': {
+            'id': '16801',
+            'ext': 'mp4',
+            'title': 'St. Kilda\'s Joey Montagna on the potential for a player\'s strike',
+            'description': 'Is a boycott of the NAB Cup "on the table"?',
+            'uploader_id': '4460760524001',
+            'upload_date': '20160713',
+            'timestamp': 1468421266,
+        },
+        'skip': 'Only available in Australia',
+    }, {
+        # episode
+        'url': 'https://www.9now.com.au/afl-footy-show/2016/episode-19',
+        'only_matching': True,
+    }, {
+        # DRM protected
+        'url': 'https://www.9now.com.au/afl-footy-show/2016/episode-19',
+        'only_matching': True,
+    }]
+    BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/4460760524001/default_default/index.html?videoId=%s'
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        page_data = self._parse_json(self._search_regex(
+            r'window\.__data\s*=\s*({.*?});', webpage,
+            'page data'), display_id)
+        common_data = page_data.get('episode', {}).get('episode') or page_data.get('clip', {}).get('clip')
+        video_data = common_data['video']
+
+        if video_data.get('drm'):
+            raise ExtractorError('This video is DRM protected.', expected=True)
+
+        brightcove_id = video_data.get('brightcoveId') or 'ref:' + video_data['referenceId']
+        video_id = compat_str(video_data.get('id') or brightcove_id)
+        title = common_data['name']
+
+        thumbnails = [{
+            'id': thumbnail_id,
+            'url': thumbnail_url,
+            'width': int_or_none(thumbnail_id[1:])
+        } for thumbnail_id, thumbnail_url in common_data.get('image', {}).get('sizes', {}).items()]
+
+        return {
+            '_type': 'url_transparent',
+            'url': self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id,
+            'id': video_id,
+            'title': title,
+            'description': common_data.get('description'),
+            'duration': float_or_none(video_data.get('duration'), 1000),
+            'thumbnails': thumbnails,
+            'ie_key': 'BrightcoveNew',
+        }