diff --git a/test/test_InfoExtractor.py b/test/test_InfoExtractor.py
index 6f52e11f7..f18a823fc 100644
--- a/test/test_InfoExtractor.py
+++ b/test/test_InfoExtractor.py
@@ -10,6 +10,7 @@ import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from test.helper import FakeYDL, expect_dict, expect_value
+from youtube_dl.compat import compat_etree_fromstring
from youtube_dl.extractor.common import InfoExtractor
from youtube_dl.extractor import YoutubeIE, get_info_extractor
from youtube_dl.utils import encode_data_uri, strip_jsonp, ExtractorError, RegexNotFoundError
@@ -488,6 +489,91 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
self.ie._sort_formats(formats)
expect_value(self, formats, expected_formats, None)
+ def test_parse_mpd_formats(self):
+ _TEST_CASES = [
+ (
+ # https://github.com/rg3/youtube-dl/issues/13919
+ 'float_duration',
+ 'http://unknown/manifest.mpd',
+ [{
+ 'manifest_url': 'http://unknown/manifest.mpd',
+ 'ext': 'mp4',
+ 'format_id': '318597',
+ 'format_note': 'DASH video',
+ 'protocol': 'http_dash_segments',
+ 'acodec': 'none',
+ 'vcodec': 'avc1.42001f',
+ 'tbr': 318.597,
+ 'width': 340,
+ 'height': 192,
+ }, {
+ 'manifest_url': 'http://unknown/manifest.mpd',
+ 'ext': 'mp4',
+ 'format_id': '638590',
+ 'format_note': 'DASH video',
+ 'protocol': 'http_dash_segments',
+ 'acodec': 'none',
+ 'vcodec': 'avc1.42001f',
+ 'tbr': 638.59,
+ 'width': 512,
+ 'height': 288,
+ }, {
+ 'manifest_url': 'http://unknown/manifest.mpd',
+ 'ext': 'mp4',
+ 'format_id': '1022565',
+ 'format_note': 'DASH video',
+ 'protocol': 'http_dash_segments',
+ 'acodec': 'none',
+ 'vcodec': 'avc1.4d001f',
+ 'tbr': 1022.565,
+ 'width': 688,
+ 'height': 384,
+ }, {
+ 'manifest_url': 'http://unknown/manifest.mpd',
+ 'ext': 'mp4',
+ 'format_id': '2046506',
+ 'format_note': 'DASH video',
+ 'protocol': 'http_dash_segments',
+ 'acodec': 'none',
+ 'vcodec': 'avc1.4d001f',
+ 'tbr': 2046.506,
+ 'width': 1024,
+ 'height': 576,
+ }, {
+ 'manifest_url': 'http://unknown/manifest.mpd',
+ 'ext': 'mp4',
+ 'format_id': '3998017',
+ 'format_note': 'DASH video',
+ 'protocol': 'http_dash_segments',
+ 'acodec': 'none',
+ 'vcodec': 'avc1.640029',
+ 'tbr': 3998.017,
+ 'width': 1280,
+ 'height': 720,
+ }, {
+ 'manifest_url': 'http://unknown/manifest.mpd',
+ 'ext': 'mp4',
+ 'format_id': '5997485',
+ 'format_note': 'DASH video',
+ 'protocol': 'http_dash_segments',
+ 'acodec': 'none',
+ 'vcodec': 'avc1.640032',
+ 'tbr': 5997.485,
+ 'width': 1920,
+ 'height': 1080,
+ }]
+ ),
+ ]
+
+ for mpd_file, mpd_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)
+ self.ie._sort_formats(formats)
+ expect_value(self, formats, expected_formats, None)
+
if __name__ == '__main__':
unittest.main()
diff --git a/test/testdata/mpd/float_duration.mpd b/test/testdata/mpd/float_duration.mpd
new file mode 100644
index 000000000..8dc1d2d5e
--- /dev/null
+++ b/test/testdata/mpd/float_duration.mpd
@@ -0,0 +1,18 @@
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
\ No newline at end of file
diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
index 7fe888462..e747258aa 100644
--- a/youtube_dl/extractor/common.py
+++ b/youtube_dl/extractor/common.py
@@ -1786,7 +1786,7 @@ class InfoExtractor(object):
ms_info['timescale'] = int(timescale)
segment_duration = source.get('duration')
if segment_duration:
- ms_info['segment_duration'] = int(segment_duration)
+ ms_info['segment_duration'] = float(segment_duration)
def extract_Initialization(source):
initialization = source.find(_add_ns('Initialization'))
diff --git a/youtube_dl/extractor/mixcloud.py b/youtube_dl/extractor/mixcloud.py
index 52f7428e0..fcf7beeb2 100644
--- a/youtube_dl/extractor/mixcloud.py
+++ b/youtube_dl/extractor/mixcloud.py
@@ -9,6 +9,7 @@ from .common import InfoExtractor
from ..compat import (
compat_chr,
compat_ord,
+ compat_str,
compat_urllib_parse_unquote,
compat_urlparse,
)
@@ -53,15 +54,18 @@ class MixcloudIE(InfoExtractor):
'only_matching': True,
}]
+ _keys = [
+ 'return { requestAnimationFrame: function(callback) { callback(); }, innerHeight: 500 };',
+ 'pleasedontdownloadourmusictheartistswontgetpaid',
+ 'window.addEventListener = window.addEventListener || function() {};',
+ '(function() { return new Date().toLocaleDateString(); })()'
+ ]
+ _current_key = None
+
# See https://www.mixcloud.com/media/js2/www_js_2.9e23256562c080482435196ca3975ab5.js
def _decrypt_play_info(self, play_info, video_id):
- KEYS = (
- 'pleasedontdownloadourmusictheartistswontgetpaid',
- 'window.addEventListener = window.addEventListener || function() {};',
- '(function() { return new Date().toLocaleDateString(); })()',
- )
play_info = base64.b64decode(play_info.encode('ascii'))
- for num, key in enumerate(KEYS, start=1):
+ for num, key in enumerate(self._keys, start=1):
try:
return self._parse_json(
''.join([
@@ -69,7 +73,7 @@ class MixcloudIE(InfoExtractor):
for idx, ch in enumerate(play_info)]),
video_id)
except ExtractorError:
- if num == len(KEYS):
+ if num == len(self._keys):
raise
def _real_extract(self, url):
@@ -80,6 +84,20 @@ class MixcloudIE(InfoExtractor):
webpage = self._download_webpage(url, track_id)
+ if not self._current_key:
+ js_url = self._search_regex(
+ r']+\bsrc=["\"](https://(?:www\.)?mixcloud\.com/media/js2/www_js_4\.[^>]+\.js)',
+ webpage, 'js url', default=None)
+ if js_url:
+ js = self._download_webpage(js_url, track_id, fatal=False)
+ if js:
+ key = self._search_regex(
+ r'player\s*:\s*{.*?\bvalue\s*:\s*(["\'])(?P(?:(?!\1).)+)\1',
+ js, 'key', default=None, group='key')
+ if key and isinstance(key, compat_str):
+ self._keys.insert(0, key)
+ self._current_key = key
+
message = self._html_search_regex(
r'(?s)]+class="global-message cloudcast-disabled-notice-light"[^>]*>(.+?)<(?:a|/div)',
webpage, 'error message', default=None)