[cbsinteractive] Add support for ZDNet videos
authorremitamine <remitamine@gmail.com>
Fri, 1 Apr 2016 22:53:32 +0000 (23:53 +0100)
committerremitamine <remitamine@gmail.com>
Fri, 1 Apr 2016 22:53:32 +0000 (23:53 +0100)
youtube_dl/extractor/__init__.py
youtube_dl/extractor/cbsinteractive.py [new file with mode: 0644]
youtube_dl/extractor/cnet.py [deleted file]

index 438e1cc63922ee31bba1e9d532aa37d992e342a5..ebf5ca3e93a27f97cb5d76dc4c80611f983b7f35 100644 (file)
@@ -104,6 +104,7 @@ from .cbc import (
     CBCPlayerIE,
 )
 from .cbs import CBSIE
+from .cbsinteractive import CBSInteractiveIE
 from .cbsnews import (
     CBSNewsIE,
     CBSNewsLiveVideoIE,
@@ -129,7 +130,6 @@ from .clubic import ClubicIE
 from .clyp import ClypIE
 from .cmt import CMTIE
 from .cnbc import CNBCIE
-from .cnet import CNETIE
 from .cnn import (
     CNNIE,
     CNNBlogsIE,
diff --git a/youtube_dl/extractor/cbsinteractive.py b/youtube_dl/extractor/cbsinteractive.py
new file mode 100644 (file)
index 0000000..0011c30
--- /dev/null
@@ -0,0 +1,108 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .theplatform import ThePlatformIE
+from ..utils import int_or_none
+
+
+class CBSInteractiveIE(ThePlatformIE):
+    _VALID_URL = r'https?://(?:www\.)?(?P<site>cnet|zdnet)\.com/(?:videos|video/share)/(?P<id>[^/?]+)'
+    _TESTS = [{
+        'url': 'http://www.cnet.com/videos/hands-on-with-microsofts-windows-8-1-update/',
+        'info_dict': {
+            'id': '56f4ea68-bd21-4852-b08c-4de5b8354c60',
+            'ext': 'flv',
+            'title': 'Hands-on with Microsoft Windows 8.1 Update',
+            'description': 'The new update to the Windows 8 OS brings improved performance for mouse and keyboard users.',
+            'uploader_id': '6085384d-619e-11e3-b231-14feb5ca9861',
+            'uploader': 'Sarah Mitroff',
+            'duration': 70,
+            'timestamp': 1396479627,
+            'upload_date': '20140402',
+        },
+    }, {
+        'url': 'http://www.cnet.com/videos/whiny-pothole-tweets-at-local-government-when-hit-by-cars-tomorrow-daily-187/',
+        'info_dict': {
+            'id': '56527b93-d25d-44e3-b738-f989ce2e49ba',
+            'ext': 'flv',
+            'title': 'Whiny potholes tweet at local government when hit by cars (Tomorrow Daily 187)',
+            'description': 'Khail and Ashley wonder what other civic woes can be solved by self-tweeting objects, investigate a new kind of VR camera and watch an origami robot self-assemble, walk, climb, dig and dissolve. #TDPothole',
+            'uploader_id': 'b163284d-6b73-44fc-b3e6-3da66c392d40',
+            'uploader': 'Ashley Esqueda',
+            'duration': 1482,
+            'timestamp': 1433289889,
+            'upload_date': '20150603',
+        },
+    }, {
+        'url': 'http://www.zdnet.com/video/share/video-keeping-android-smartphones-and-tablets-secure/',
+        'info_dict': {
+            'id': 'bc1af9f0-a2b5-4e54-880d-0d95525781c0',
+            'ext': 'mp4',
+            'title': 'Video: Keeping Android smartphones and tablets secure',
+            'description': 'Here\'s the best way to keep Android devices secure, and what you do when they\'ve come to the end of their lives.',
+            'uploader_id': 'f2d97ea2-8175-11e2-9d12-0018fe8a00b0',
+            'uploader': 'Adrian Kingsley-Hughes',
+            'timestamp': 1448961720,
+            'upload_date': '20151201',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        }
+    }]
+    TP_RELEASE_URL_TEMPLATE = 'http://link.theplatform.com/s/kYEXFC/%s?mbr=true'
+    MPX_ACCOUNTS = {
+        'cnet': 2288573011,
+        'zdnet': 2387448114,
+    }
+
+    def _real_extract(self, url):
+        site, display_id = re.match(self._VALID_URL, url).groups()
+        webpage = self._download_webpage(url, display_id)
+
+        data_json = self._html_search_regex(
+            r"data-(?:cnet|zdnet)-video(?:-uvp)?-options='([^']+)'",
+            webpage, 'data json')
+        data = self._parse_json(data_json, display_id)
+        vdata = data.get('video') or data['videos'][0]
+
+        video_id = vdata['id']
+        title = vdata['title']
+        author = vdata.get('author')
+        if author:
+            uploader = '%s %s' % (author['firstName'], author['lastName'])
+            uploader_id = author.get('id')
+        else:
+            uploader = None
+            uploader_id = None
+
+        media_guid_path = 'media/guid/%d/%s' % (self.MPX_ACCOUNTS[site], vdata['mpxRefId'])
+        formats, subtitles = [], {}
+        if site == 'cnet':
+            formats, subtitles = self._extract_theplatform_smil(
+                self.TP_RELEASE_URL_TEMPLATE % media_guid_path, video_id)
+        for (fkey, vid) in vdata['files'].items():
+            if fkey == 'hls_phone' and 'hls_tablet' in vdata['files']:
+                continue
+            release_url = self.TP_RELEASE_URL_TEMPLATE % vid
+            if fkey == 'hds':
+                release_url += '&manifest=f4m'
+            tp_formats, tp_subtitles = self._extract_theplatform_smil(release_url, video_id, 'Downloading %s SMIL data' % fkey)
+            formats.extend(tp_formats)
+            subtitles = self._merge_subtitles(subtitles, tp_subtitles)
+        self._sort_formats(formats)
+
+        info = self.get_metadata('kYEXFC/%s' % media_guid_path, video_id)
+        info.update({
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'duration': int_or_none(vdata.get('duration')),
+            'uploader': uploader,
+            'uploader_id': uploader_id,
+            'subtitles': subtitles,
+            'formats': formats,
+        })
+        return info
diff --git a/youtube_dl/extractor/cnet.py b/youtube_dl/extractor/cnet.py
deleted file mode 100644 (file)
index 58c26f2..0000000
+++ /dev/null
@@ -1,83 +0,0 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
-from .theplatform import ThePlatformIE
-from ..utils import int_or_none
-
-
-class CNETIE(ThePlatformIE):
-    _VALID_URL = r'https?://(?:www\.)?cnet\.com/videos/(?P<id>[^/]+)/'
-    _TESTS = [{
-        'url': 'http://www.cnet.com/videos/hands-on-with-microsofts-windows-8-1-update/',
-        'info_dict': {
-            'id': '56f4ea68-bd21-4852-b08c-4de5b8354c60',
-            'ext': 'flv',
-            'title': 'Hands-on with Microsoft Windows 8.1 Update',
-            'description': 'The new update to the Windows 8 OS brings improved performance for mouse and keyboard users.',
-            'uploader_id': '6085384d-619e-11e3-b231-14feb5ca9861',
-            'uploader': 'Sarah Mitroff',
-            'duration': 70,
-            'timestamp': 1396479627,
-            'upload_date': '20140402',
-        },
-    }, {
-        'url': 'http://www.cnet.com/videos/whiny-pothole-tweets-at-local-government-when-hit-by-cars-tomorrow-daily-187/',
-        'info_dict': {
-            'id': '56527b93-d25d-44e3-b738-f989ce2e49ba',
-            'ext': 'flv',
-            'title': 'Whiny potholes tweet at local government when hit by cars (Tomorrow Daily 187)',
-            'description': 'Khail and Ashley wonder what other civic woes can be solved by self-tweeting objects, investigate a new kind of VR camera and watch an origami robot self-assemble, walk, climb, dig and dissolve. #TDPothole',
-            'uploader_id': 'b163284d-6b73-44fc-b3e6-3da66c392d40',
-            'uploader': 'Ashley Esqueda',
-            'duration': 1482,
-            'timestamp': 1433289889,
-            'upload_date': '20150603',
-        },
-    }]
-    TP_RELEASE_URL_TEMPLATE = 'http://link.theplatform.com/s/kYEXFC/%s?mbr=true'
-
-    def _real_extract(self, url):
-        display_id = self._match_id(url)
-        webpage = self._download_webpage(url, display_id)
-
-        data_json = self._html_search_regex(
-            r"data-cnet-video(?:-uvp)?-options='([^']+)'",
-            webpage, 'data json')
-        data = self._parse_json(data_json, display_id)
-        vdata = data.get('video') or data['videos'][0]
-
-        video_id = vdata['id']
-        title = vdata['title']
-        author = vdata.get('author')
-        if author:
-            uploader = '%s %s' % (author['firstName'], author['lastName'])
-            uploader_id = author.get('id')
-        else:
-            uploader = None
-            uploader_id = None
-
-        media_guid_path = 'media/guid/2288573011/%s' % vdata['mpxRefId']
-        formats, subtitles = self._extract_theplatform_smil(self.TP_RELEASE_URL_TEMPLATE % media_guid_path, video_id)
-        for (fkey, vid) in vdata['files'].items():
-            if fkey == 'hls_phone' and 'hls_tablet' in vdata['files']:
-                continue
-            release_url = self.TP_RELEASE_URL_TEMPLATE % vid
-            if fkey == 'hds':
-                release_url += '&manifest=f4m'
-            tp_formats, tp_subtitles = self._extract_theplatform_smil(release_url, video_id, 'Downloading %s SMIL data' % fkey)
-            formats.extend(tp_formats)
-            subtitles = self._merge_subtitles(subtitles, tp_subtitles)
-        self._sort_formats(formats)
-
-        info = self.get_metadata('kYEXFC/%s' % media_guid_path, video_id)
-        info.update({
-            'id': video_id,
-            'display_id': display_id,
-            'title': title,
-            'duration': int_or_none(vdata.get('duration')),
-            'uploader': uploader,
-            'uploader_id': uploader_id,
-            'subtitles': subtitles,
-            'formats': formats,
-        })
-        return info