[test_InfoExtractor] Add test for #20346
[youtube-dl] / test / test_InfoExtractor.py
index 06be726166c164e29c9af54f4a66590001846e53..d23d94349034aa2a482e24f55f6c21ae814754c6 100644 (file)
@@ -61,6 +61,7 @@ class TestInfoExtractor(unittest.TestCase):
             <meta content='Foo' property=og:foobar>
             <meta name="og:test1" content='foo > < bar'/>
             <meta name="og:test2" content="foo >//< bar"/>
+            <meta property=og-test3 content='Ill-formatted opengraph'/>
             '''
         self.assertEqual(ie._og_search_title(html), 'Foo')
         self.assertEqual(ie._og_search_description(html), 'Some video\'s description ')
@@ -69,6 +70,7 @@ class TestInfoExtractor(unittest.TestCase):
         self.assertEqual(ie._og_search_property('foobar', html), 'Foo')
         self.assertEqual(ie._og_search_property('test1', html), 'foo > < bar')
         self.assertEqual(ie._og_search_property('test2', html), 'foo >//< bar')
+        self.assertEqual(ie._og_search_property('test3', html), 'Ill-formatted opengraph')
         self.assertEqual(ie._og_search_property(('test0', 'test1'), html), 'foo > < bar')
         self.assertRaises(RegexNotFoundError, ie._og_search_property, 'test0', html, None, fatal=True)
         self.assertRaises(RegexNotFoundError, ie._og_search_property, ('test0', 'test00'), html, None, fatal=True)
@@ -199,7 +201,7 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
     def test_parse_m3u8_formats(self):
         _TEST_CASES = [
             (
-                # https://github.com/rg3/youtube-dl/issues/11507
+                # https://github.com/ytdl-org/youtube-dl/issues/11507
                 # http://pluzz.francetv.fr/videos/le_ministere.html
                 'pluzz_francetv_11507',
                 'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/master.m3u8?caption=2017%2F16%2F156589847-1492488987.m3u8%3Afra%3AFrancais&audiotrack=0%3Afra%3AFrancais',
@@ -261,7 +263,7 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                 }]
             ),
             (
-                # https://github.com/rg3/youtube-dl/issues/11995
+                # https://github.com/ytdl-org/youtube-dl/issues/11995
                 # http://teamcoco.com/video/clueless-gamer-super-bowl-for-honor
                 'teamcoco_11995',
                 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/main.m3u8',
@@ -335,7 +337,7 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                 }]
             ),
             (
-                # https://github.com/rg3/youtube-dl/issues/12211
+                # https://github.com/ytdl-org/youtube-dl/issues/12211
                 # http://video.toggle.sg/en/series/whoopie-s-world/ep3/478601
                 'toggle_mobile_12211',
                 'http://cdnapi.kaltura.com/p/2082311/sp/208231100/playManifest/protocol/http/entryId/0_89q6e8ku/format/applehttp/tags/mobile_sd/f/a.m3u8',
@@ -497,7 +499,64 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                     'width': 1280,
                     'height': 720,
                 }]
-            )
+            ),
+            (
+                # https://github.com/ytdl-org/youtube-dl/issues/18923
+                # https://www.ted.com/talks/boris_hesser_a_grassroots_healthcare_revolution_in_africa
+                'ted_18923',
+                'http://hls.ted.com/talks/31241.m3u8',
+                [{
+                    'url': 'http://hls.ted.com/videos/BorisHesser_2018S/audio/600k.m3u8?nobumpers=true&uniqueId=76011e2b',
+                    'format_id': '600k-Audio',
+                    'vcodec': 'none',
+                }, {
+                    'url': 'http://hls.ted.com/videos/BorisHesser_2018S/audio/600k.m3u8?nobumpers=true&uniqueId=76011e2b',
+                    'format_id': '68',
+                    'vcodec': 'none',
+                }, {
+                    'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/64k.m3u8?nobumpers=true&uniqueId=76011e2b',
+                    'format_id': '163',
+                    'acodec': 'none',
+                    'width': 320,
+                    'height': 180,
+                }, {
+                    'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/180k.m3u8?nobumpers=true&uniqueId=76011e2b',
+                    'format_id': '481',
+                    'acodec': 'none',
+                    'width': 512,
+                    'height': 288,
+                }, {
+                    'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/320k.m3u8?nobumpers=true&uniqueId=76011e2b',
+                    'format_id': '769',
+                    'acodec': 'none',
+                    'width': 512,
+                    'height': 288,
+                }, {
+                    'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/450k.m3u8?nobumpers=true&uniqueId=76011e2b',
+                    'format_id': '984',
+                    'acodec': 'none',
+                    'width': 512,
+                    'height': 288,
+                }, {
+                    'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/600k.m3u8?nobumpers=true&uniqueId=76011e2b',
+                    'format_id': '1255',
+                    'acodec': 'none',
+                    'width': 640,
+                    'height': 360,
+                }, {
+                    'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/950k.m3u8?nobumpers=true&uniqueId=76011e2b',
+                    'format_id': '1693',
+                    'acodec': 'none',
+                    'width': 853,
+                    'height': 480,
+                }, {
+                    'url': 'http://hls.ted.com/videos/BorisHesser_2018S/video/1500k.m3u8?nobumpers=true&uniqueId=76011e2b',
+                    'format_id': '2462',
+                    'acodec': 'none',
+                    'width': 1280,
+                    'height': 720,
+                }]
+            ),
         ]
 
         for m3u8_file, m3u8_url, expected_formats in _TEST_CASES:
@@ -511,11 +570,12 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
     def test_parse_mpd_formats(self):
         _TEST_CASES = [
             (
-                # https://github.com/rg3/youtube-dl/issues/13919
+                # https://github.com/ytdl-org/youtube-dl/issues/13919
                 # Also tests duplicate representation ids, see
-                # https://github.com/rg3/youtube-dl/issues/15111
+                # https://github.com/ytdl-org/youtube-dl/issues/15111
                 'float_duration',
-                'http://unknown/manifest.mpd',
+                'http://unknown/manifest.mpd',  # mpd_url
+                None,  # mpd_base_url
                 [{
                     'manifest_url': 'http://unknown/manifest.mpd',
                     'ext': 'm4a',
@@ -593,9 +653,10 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                     'height': 1080,
                 }]
             ), (
-                # https://github.com/rg3/youtube-dl/pull/14844
+                # https://github.com/ytdl-org/youtube-dl/pull/14844
                 'urls_only',
-                'http://unknown/manifest.mpd',
+                'http://unknown/manifest.mpd',  # mpd_url
+                None,  # mpd_base_url
                 [{
                     'manifest_url': 'http://unknown/manifest.mpd',
                     'ext': 'mp4',
@@ -674,22 +735,68 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                     'width': 1920,
                     'height': 1080,
                 }]
+            ), (
+                # https://github.com/ytdl-org/youtube-dl/issues/20346
+                # Media considered unfragmented even though it contains
+                # Initialization tag
+                'unfragmented',
+                'https://v.redd.it/hw1x7rcg7zl21/DASHPlaylist.mpd',  # mpd_url
+                'https://v.redd.it/hw1x7rcg7zl21',  # mpd_base_url
+                [{
+                    'url': 'https://v.redd.it/hw1x7rcg7zl21/audio',
+                    'manifest_url': 'https://v.redd.it/hw1x7rcg7zl21/DASHPlaylist.mpd',
+                    'ext': 'm4a',
+                    'format_id': 'AUDIO-1',
+                    'format_note': 'DASH audio',
+                    'container': 'm4a_dash',
+                    'acodec': 'mp4a.40.2',
+                    'vcodec': 'none',
+                    'tbr': 129.87,
+                    'asr': 48000,
+
+                }, {
+                    'url': 'https://v.redd.it/hw1x7rcg7zl21/DASH_240',
+                    'manifest_url': 'https://v.redd.it/hw1x7rcg7zl21/DASHPlaylist.mpd',
+                    'ext': 'mp4',
+                    'format_id': 'VIDEO-2',
+                    'format_note': 'DASH video',
+                    'container': 'mp4_dash',
+                    'acodec': 'none',
+                    'vcodec': 'avc1.4d401e',
+                    'tbr': 608.0,
+                    'width': 240,
+                    'height': 240,
+                    'fps': 30,
+                }, {
+                    'url': 'https://v.redd.it/hw1x7rcg7zl21/DASH_360',
+                    'manifest_url': 'https://v.redd.it/hw1x7rcg7zl21/DASHPlaylist.mpd',
+                    'ext': 'mp4',
+                    'format_id': 'VIDEO-1',
+                    'format_note': 'DASH video',
+                    'container': 'mp4_dash',
+                    'acodec': 'none',
+                    'vcodec': 'avc1.4d401e',
+                    'tbr': 804.261,
+                    'width': 360,
+                    'height': 360,
+                    'fps': 30,
+                }]
             )
         ]
 
-        for mpd_file, mpd_url, expected_formats in _TEST_CASES:
+        for mpd_file, mpd_url, mpd_base_url, expected_formats in _TEST_CASES:
             with io.open('./test/testdata/mpd/%s.mpd' % mpd_file,
                          mode='r', encoding='utf-8') as f:
                 formats = self.ie._parse_mpd_formats(
                     compat_etree_fromstring(f.read().encode('utf-8')),
-                    mpd_url=mpd_url)
+                    mpd_base_url=mpd_base_url, mpd_url=mpd_url)
                 self.ie._sort_formats(formats)
                 expect_value(self, formats, expected_formats, None)
 
     def test_parse_f4m_formats(self):
         _TEST_CASES = [
             (
-                # https://github.com/rg3/youtube-dl/issues/14660
+                # https://github.com/ytdl-org/youtube-dl/issues/14660
                 'custom_base_url',
                 'http://api.new.livestream.com/accounts/6115179/events/6764928/videos/144884262.f4m',
                 [{