youtube-dl

commit 3f59b0154a8b6dc85425edfbb3dfdc64f41a6ecb
parent 089b97cfee8553886d33cd52b7ede178cebd7034
Author: Sergey M․ <dstftw@gmail.com>
Date:   Sun, 16 Jul 2017 04:32:37 +0700

[nexx:embed] Add extractor for iframe embeds

Diffstat:
M
youtube_dl/extractor/extractors.py
 | 
5
++++-
M
youtube_dl/extractor/generic.py
 | 
31
++++++++++++++++++++++++++++++-
M
youtube_dl/extractor/nexx.py
 | 
46
++++++++++++++++++++++++++++++++++++++++++++++

3 files changed, 80 insertions(+), 2 deletions(-)
diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
@@ -653,7 +653,10 @@ from .nextmedia import (
     AppleDailyIE,
     NextTVIE,
 )
-from .nexx import NexxIE
+from .nexx import (
+    NexxIE,
+    NexxEmbedIE,
+)
 from .nfb import NFBIE
 from .nfl import NFLIE
 from .nhk import NhkVodIE
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
@@ -36,7 +36,10 @@ from .brightcove import (
     BrightcoveLegacyIE,
     BrightcoveNewIE,
 )
-from .nexx import NexxIE
+from .nexx import (
+    NexxIE,
+    NexxEmbedIE,
+)
 from .nbc import NBCSportsVPlayerIE
 from .ooyala import OoyalaIE
 from .rutv import RUTVIE
@@ -1566,6 +1569,27 @@ class GenericIE(InfoExtractor):
                 'skip_download': True,
             },
         },
+        # Nexx iFrame embed
+        {
+            'url': 'http://www.spiegel.de/sptv/spiegeltv/spiegel-tv-ueber-schnellste-katapult-achterbahn-der-welt-taron-a-1137884.html',
+            'info_dict': {
+                'id': '161464',
+                'ext': 'mp4',
+                'title': 'Nervenkitzel Achterbahn',
+                'alt_title': 'Karussellbauer in Deutschland',
+                'description': 'md5:ffe7b1cc59a01f585e0569949aef73cc',
+                'release_year': 2005,
+                'creator': 'SPIEGEL TV',
+                'thumbnail': r're:^https?://.*\.jpg$',
+                'duration': 2761,
+                'timestamp': 1394021479,
+                'upload_date': '20140305',
+            },
+            'params': {
+                'format': 'bestvideo',
+                'skip_download': True,
+            },
+        },
         # Facebook <iframe> embed
         {
             'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
@@ -2155,6 +2179,11 @@ class GenericIE(InfoExtractor):
         if nexx_urls:
             return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
 
+        # Look for Nexx iFrame embeds
+        nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
+        if nexx_embed_urls:
+            return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
+
         # Look for ThePlatform embeds
         tp_urls = ThePlatformIE._extract_urls(webpage)
         if tp_urls:
diff --git a/youtube_dl/extractor/nexx.py b/youtube_dl/extractor/nexx.py
@@ -88,6 +88,10 @@ class NexxIE(InfoExtractor):
 
         return entries
 
+    @staticmethod
+    def _extract_url(webpage):
+        return NexxIE._extract_urls(webpage)[0]
+
     def _handle_error(self, response):
         status = int_or_none(try_get(
             response, lambda x: x['metadata']['status']) or 200)
@@ -223,3 +227,45 @@ class NexxIE(InfoExtractor):
                 video, lambda x: x['episodedata']['season'])),
             'formats': formats,
         }
+
+
+class NexxEmbedIE(InfoExtractor):
+    _VALID_URL = r'https?://embed\.nexx(?:\.cloud|cdn\.com)/\d+/(?P<id>[^/?#&]+)'
+    _TEST = {
+        'url': 'http://embed.nexx.cloud/748/KC1614647Z27Y7T?autoplay=1',
+        'md5': '16746bfc28c42049492385c989b26c4a',
+        'info_dict': {
+            'id': '161464',
+            'ext': 'mp4',
+            'title': 'Nervenkitzel Achterbahn',
+            'alt_title': 'Karussellbauer in Deutschland',
+            'description': 'md5:ffe7b1cc59a01f585e0569949aef73cc',
+            'release_year': 2005,
+            'creator': 'SPIEGEL TV',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 2761,
+            'timestamp': 1394021479,
+            'upload_date': '20140305',
+        },
+        'params': {
+            'format': 'bestvideo',
+            'skip_download': True,
+        },
+    }
+
+    @staticmethod
+    def _extract_urls(webpage):
+        # Reference:
+        # 1. https://nx-s.akamaized.net/files/201510/44.pdf
+
+        # iFrame Embed Integration
+        return [mobj.group('url') for mobj in re.finditer(
+                r'<iframe[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//embed\.nexx(?:\.cloud|cdn\.com)/\d+/(?:(?!\1).)+)\1',
+            webpage)]
+
+    def _real_extract(self, url):
+        embed_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, embed_id)
+
+        return self.url_result(NexxIE._extract_url(webpage), ie=NexxIE.ie_key())