[cloudflarestream] Add support for cloudflare streams (closes #16375)

youtube_dl/extractor/cloudflarestream.py

@@ -0,0 +1,60 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class CloudflareStreamIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:
+                            (?:watch\.)?cloudflarestream\.com/|
+                            embed\.cloudflarestream\.com/embed/[^/]+\.js\?.*?\bvideo=
+                        )
+                        (?P<id>[\da-f]+)
+                    '''
+    _TESTS = [{
+        'url': 'https://embed.cloudflarestream.com/embed/we4g.fla9.latest.js?video=31c9291ab41fac05471db4e73aa11717',
+        'info_dict': {
+            'id': '31c9291ab41fac05471db4e73aa11717',
+            'ext': 'mp4',
+            'title': '31c9291ab41fac05471db4e73aa11717',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'https://watch.cloudflarestream.com/9df17203414fd1db3e3ed74abbe936c1',
+        'only_matching': True,
+    }, {
+        'url': 'https://cloudflarestream.com/31c9291ab41fac05471db4e73aa11717/manifest/video.mpd',
+        'only_matching': True,
+    }]
+
+    @staticmethod
+    def _extract_urls(webpage):
+        return [
+            mobj.group('url')
+            for mobj in re.finditer(
+                r'<script[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//embed\.cloudflarestream\.com/embed/[^/]+\.js\?.*?\bvideo=[\da-f]+?.*?)\1',
+                webpage)]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        formats = self._extract_m3u8_formats(
+            'https://cloudflarestream.com/%s/manifest/video.m3u8' % video_id,
+            video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls',
+            fatal=False)
+        formats.extend(self._extract_mpd_formats(
+            'https://cloudflarestream.com/%s/manifest/video.mpd' % video_id,
+            video_id, mpd_id='dash', fatal=False))
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': video_id,
+            'formats': formats,
+        }

youtube_dl/extractor/extractors.py

@@ -195,6 +195,7 @@ from .clippit import ClippitIE
 from .cliprs import ClipRsIE
 from .clipsyndicate import ClipsyndicateIE
 from .closertotruth import CloserToTruthIE
+from .cloudflarestream import CloudflareStreamIE
 from .cloudy import CloudyIE
 from .clubic import ClubicIE
 from .clyp import ClypIE

youtube_dl/extractor/generic.py

@@ -107,6 +107,7 @@ from .springboardplatform import SpringboardPlatformIE
 from .yapfiles import YapFilesIE
 from .vice import ViceIE
 from .xfileshare import XFileShareIE
+from .cloudflarestream import CloudflareStreamIE
 
 
 class GenericIE(InfoExtractor):
@@ -2013,6 +2014,19 @@ class GenericIE(InfoExtractor):
                 'skip_download': True,
             },
         },
+        {
+            # CloudflareStream embed
+            'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
+            'info_dict': {
+                'id': '31c9291ab41fac05471db4e73aa11717',
+                'ext': 'mp4',
+                'title': '31c9291ab41fac05471db4e73aa11717',
+            },
+            'add_ie': [CloudflareStreamIE.ie_key()],
+            'params': {
+                'skip_download': True,
+            },
+        },
         {
             'url': 'http://share-videos.se/auto/video/83645793?uid=13',
             'md5': 'b68d276de422ab07ee1d49388103f457',
@@ -3025,6 +3039,11 @@ class GenericIE(InfoExtractor):
             return self.playlist_from_matches(
                 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
 
+        cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
+        if cloudflarestream_urls:
+            return self.playlist_from_matches(
+                cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
+
         sharevideos_urls = [mobj.group('url') for mobj in re.finditer(
             r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
             webpage)]