aboutsummaryrefslogtreecommitdiff
path: root/test
diff options
context:
space:
mode:
Diffstat (limited to 'test')
-rw-r--r--test/helper.py75
-rw-r--r--test/parameters.json3
-rw-r--r--test/test_InfoExtractor.py1237
-rw-r--r--test/test_YoutubeDL.py442
-rw-r--r--test/test_YoutubeDLCookieJar.py65
-rw-r--r--test/test_aes.py17
-rw-r--r--test/test_age_restriction.py12
-rw-r--r--test/test_all_urls.py45
-rw-r--r--test/test_cache.py28
-rw-r--r--test/test_compat.py45
-rw-r--r--test/test_download.py61
-rw-r--r--test/test_downloader_external.py272
-rw-r--r--test/test_downloader_http.py108
-rw-r--r--test/test_execution.py38
-rw-r--r--test/test_http.py574
-rw-r--r--test/test_jsinterp.py672
-rw-r--r--test/test_options.py26
-rw-r--r--test/test_postprocessors.py2
-rw-r--r--test/test_subtitles.py129
-rw-r--r--test/test_swfinterp.py14
-rw-r--r--test/test_traversal.py509
-rw-r--r--test/test_unicode_literals.py13
-rw-r--r--test/test_utils.py663
-rw-r--r--test/test_write_annotations.py5
-rw-r--r--test/test_youtube_lists.py56
-rw-r--r--test/test_youtube_misc.py26
-rw-r--r--test/test_youtube_signature.py420
-rw-r--r--test/testdata/cookies/httponly_cookies.txt6
-rw-r--r--test/testdata/cookies/malformed_cookies.txt9
-rw-r--r--test/testdata/cookies/session_cookies.txt6
-rw-r--r--test/testdata/f4m/custom_base_url.f4m10
-rw-r--r--test/testdata/m3u8/pluzz_francetv_11507.m3u814
-rw-r--r--test/testdata/m3u8/teamcoco_11995.m3u816
-rw-r--r--test/testdata/m3u8/ted_18923.m3u828
-rw-r--r--test/testdata/m3u8/toggle_mobile_12211.m3u813
-rw-r--r--test/testdata/m3u8/twitch_vod.m3u820
-rw-r--r--test/testdata/m3u8/vidio.m3u810
-rw-r--r--test/testdata/mpd/float_duration.mpd18
-rw-r--r--test/testdata/mpd/range_only.mpd35
-rw-r--r--test/testdata/mpd/subtitles.mpd351
-rw-r--r--test/testdata/mpd/unfragmented.mpd28
-rw-r--r--test/testdata/mpd/url_and_range.mpd32
-rw-r--r--test/testdata/mpd/urls_only.mpd218
-rw-r--r--test/testdata/xspf/foo_xspf.xspf34
44 files changed, 5952 insertions, 453 deletions
diff --git a/test/helper.py b/test/helper.py
index dfee217a9..6f2129eff 100644
--- a/test/helper.py
+++ b/test/helper.py
@@ -1,21 +1,24 @@
from __future__ import unicode_literals
import errno
-import io
import hashlib
import json
import os.path
import re
-import types
+import ssl
import sys
+import types
+import unittest
import youtube_dl.extractor
from youtube_dl import YoutubeDL
from youtube_dl.compat import (
+ compat_open as open,
compat_os_name,
compat_str,
)
from youtube_dl.utils import (
+ IDENTITY,
preferredencoding,
write_string,
)
@@ -26,10 +29,10 @@ def get_params(override=None):
"parameters.json")
LOCAL_PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)),
"local_parameters.json")
- with io.open(PARAMETERS_FILE, encoding='utf-8') as pf:
+ with open(PARAMETERS_FILE, encoding='utf-8') as pf:
parameters = json.load(pf)
if os.path.exists(LOCAL_PARAMETERS_FILE):
- with io.open(LOCAL_PARAMETERS_FILE, encoding='utf-8') as pf:
+ with open(LOCAL_PARAMETERS_FILE, encoding='utf-8') as pf:
parameters.update(json.load(pf))
if override:
parameters.update(override)
@@ -71,7 +74,8 @@ class FakeYDL(YoutubeDL):
def to_screen(self, s, skip_eol=None):
print(s)
- def trouble(self, s, tb=None):
+ def trouble(self, *args, **kwargs):
+ s = args[0] if len(args) > 0 else kwargs.get('message', 'Missing message')
raise Exception(s)
def download(self, x):
@@ -88,6 +92,17 @@ class FakeYDL(YoutubeDL):
self.report_warning = types.MethodType(report_warning, self)
+class FakeLogger(object):
+ def debug(self, msg):
+ pass
+
+ def warning(self, msg):
+ pass
+
+ def error(self, msg):
+ pass
+
+
def gettestcases(include_onlymatching=False):
for ie in youtube_dl.extractor.gen_extractors():
for tc in ie.get_testcases(include_onlymatching):
@@ -127,6 +142,12 @@ def expect_value(self, got, expected, field):
self.assertTrue(
contains_str in got,
'field %s (value: %r) should contain %r' % (field, got, contains_str))
+ elif isinstance(expected, compat_str) and re.match(r'lambda \w+:', expected):
+ fn = eval(expected)
+ suite = expected.split(':', 1)[1].strip()
+ self.assertTrue(
+ fn(got),
+ 'Expected field %s to meet condition %s, but value %r failed ' % (field, suite, got))
elif isinstance(expected, type):
self.assertTrue(
isinstance(got, expected),
@@ -136,7 +157,7 @@ def expect_value(self, got, expected, field):
elif isinstance(expected, list) and isinstance(got, list):
self.assertEqual(
len(expected), len(got),
- 'Expect a list of length %d, but got a list of length %d for field %s' % (
+ 'Expected a list of length %d, but got a list of length %d for field %s' % (
len(expected), len(got), field))
for index, (item_got, item_expected) in enumerate(zip(got, expected)):
type_got = type(item_got)
@@ -152,15 +173,27 @@ def expect_value(self, got, expected, field):
isinstance(got, compat_str),
'Expected field %s to be a unicode object, but got value %r of type %r' % (field, got, type(got)))
got = 'md5:' + md5(got)
- elif isinstance(expected, compat_str) and expected.startswith('mincount:'):
+ elif isinstance(expected, compat_str) and re.match(r'^(?:min|max)?count:\d+', expected):
self.assertTrue(
isinstance(got, (list, dict)),
'Expected field %s to be a list or a dict, but it is of type %s' % (
field, type(got).__name__))
- expected_num = int(expected.partition(':')[2])
- assertGreaterEqual(
- self, len(got), expected_num,
- 'Expected %d items in field %s, but only got %d' % (expected_num, field, len(got)))
+ op, _, expected_num = expected.partition(':')
+ expected_num = int(expected_num)
+ if op == 'mincount':
+ assert_func = self.assertGreaterEqual
+ msg_tmpl = 'Expected %d items in field %s, but only got %d'
+ elif op == 'maxcount':
+ assert_func = self.assertLessEqual
+ msg_tmpl = 'Expected maximum %d items in field %s, but got %d'
+ elif op == 'count':
+ assert_func = self.assertEqual
+ msg_tmpl = 'Expected exactly %d items in field %s, but got %d'
+ else:
+ assert False
+ assert_func(
+ len(got), expected_num,
+ msg_tmpl % (expected_num, field, len(got)))
return
self.assertEqual(
expected, got,
@@ -229,13 +262,6 @@ def assertRegexpMatches(self, text, regexp, msg=None):
self.assertTrue(m, msg)
-def assertGreaterEqual(self, got, expected, msg=None):
- if not (got >= expected):
- if msg is None:
- msg = '%r not greater than or equal to %r' % (got, expected)
- self.assertTrue(got >= expected, msg)
-
-
def expect_warnings(ydl, warnings_re):
real_warning = ydl.report_warning
@@ -244,3 +270,16 @@ def expect_warnings(ydl, warnings_re):
real_warning(w)
ydl.report_warning = _report_warning
+
+
+def http_server_port(httpd):
+ if os.name == 'java' and isinstance(httpd.socket, ssl.SSLSocket):
+ # In Jython SSLSocket is not a subclass of socket.socket
+ sock = httpd.socket.sock
+ else:
+ sock = httpd.socket
+ return sock.getsockname()[1]
+
+
+def expectedFailureIf(cond):
+ return unittest.expectedFailure if cond else IDENTITY
diff --git a/test/parameters.json b/test/parameters.json
index 7bf59c25f..864c9d130 100644
--- a/test/parameters.json
+++ b/test/parameters.json
@@ -18,7 +18,6 @@
"noprogress": false,
"outtmpl": "%(id)s.%(ext)s",
"password": null,
- "playlistend": -1,
"playliststart": 1,
"prefer_free_formats": false,
"quiet": false,
@@ -37,7 +36,7 @@
"writeinfojson": true,
"writesubtitles": false,
"allsubtitles": false,
- "listssubtitles": false,
+ "listsubtitles": false,
"socket_timeout": 20,
"fixup": "never"
}
diff --git a/test/test_InfoExtractor.py b/test/test_InfoExtractor.py
index 881197afb..09100a1d6 100644
--- a/test/test_InfoExtractor.py
+++ b/test/test_InfoExtractor.py
@@ -6,21 +6,60 @@ from __future__ import unicode_literals
import os
import sys
import unittest
+
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-from test.helper import FakeYDL, expect_dict
+import threading
+
+from test.helper import (
+ expect_dict,
+ expect_value,
+ FakeYDL,
+ http_server_port,
+)
+from youtube_dl.compat import (
+ compat_etree_fromstring,
+ compat_http_server,
+ compat_open as open,
+)
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
+from youtube_dl.extractor import (
+ get_info_extractor,
+ YoutubeIE,
+)
+from youtube_dl.utils import (
+ encode_data_uri,
+ ExtractorError,
+ RegexNotFoundError,
+ strip_jsonp,
+)
+
+
+TEAPOT_RESPONSE_STATUS = 418
+TEAPOT_RESPONSE_BODY = "<h1>418 I'm a teapot</h1>"
+
+
+class InfoExtractorTestRequestHandler(compat_http_server.BaseHTTPRequestHandler):
+ def log_message(self, format, *args):
+ pass
+ def do_GET(self):
+ if self.path == '/teapot':
+ self.send_response(TEAPOT_RESPONSE_STATUS)
+ self.send_header('Content-Type', 'text/html; charset=utf-8')
+ self.end_headers()
+ self.wfile.write(TEAPOT_RESPONSE_BODY.encode())
+ else:
+ assert False
-class TestIE(InfoExtractor):
+
+class DummyIE(InfoExtractor):
pass
class TestInfoExtractor(unittest.TestCase):
def setUp(self):
- self.ie = TestIE(FakeYDL())
+ self.ie = DummyIE(FakeYDL())
def test_ie_key(self):
self.assertEqual(get_info_extractor(YoutubeIE.ie_key()), YoutubeIE)
@@ -40,6 +79,8 @@ 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'/>
+ <meta property=og:test4 content=unquoted-value/>
'''
self.assertEqual(ie._og_search_title(html), 'Foo')
self.assertEqual(ie._og_search_description(html), 'Some video\'s description ')
@@ -48,9 +89,11 @@ 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)
+ self.assertEqual(ie._og_search_property('test4', html), 'unquoted-value')
def test_html_search_meta(self):
ie = self.ie
@@ -75,6 +118,123 @@ class TestInfoExtractor(unittest.TestCase):
self.assertRaises(RegexNotFoundError, ie._html_search_meta, 'z', html, None, fatal=True)
self.assertRaises(RegexNotFoundError, ie._html_search_meta, ('z', 'x'), html, None, fatal=True)
+ def test_search_nextjs_data(self):
+ html = '''
+<!DOCTYPE html>
+<html>
+<head>
+ <meta http-equiv="content-type" content=
+ "text/html; charset=utf-8">
+ <meta name="viewport" content="width=device-width">
+ <title>Test _search_nextjs_data()</title>
+</head>
+<body>
+ <div id="__next">
+ <div style="background-color:#17171E" class="FU" dir="ltr">
+ <div class="sc-93de261d-0 dyzzYE">
+ <div>
+ <header class="HD"></header>
+ <main class="MN">
+ <div style="height:0" class="HT0">
+ <div style="width:NaN%" data-testid=
+ "stream-container" class="WDN"></div>
+ </div>
+ </main>
+ </div>
+ <footer class="sc-6e5faf91-0 dEGaHS"></footer>
+ </div>
+ </div>
+ </div>
+ <script id="__NEXT_DATA__" type="application/json">
+ {"props":{"pageProps":{"video":{"id":"testid"}}}}
+ </script>
+</body>
+</html>
+'''
+ search = self.ie._search_nextjs_data(html, 'testID')
+ self.assertEqual(search['props']['pageProps']['video']['id'], 'testid')
+ search = self.ie._search_nextjs_data(
+ 'no next.js data here, move along', 'testID', default={'status': 0})
+ self.assertEqual(search['status'], 0)
+
+ def test_search_nuxt_data(self):
+ html = '''
+<!DOCTYPE html>
+<html>
+<head>
+ <meta http-equiv="content-type" content=
+ "text/html; charset=utf-8">
+ <title>Nuxt.js Test Page</title>
+ <meta name="viewport" content=
+ "width=device-width, initial-scale=1">
+ <meta data-hid="robots" name="robots" content="all">
+</head>
+<body class="BD">
+ <div id="__layout">
+ <h1 class="H1">Example heading</h1>
+ <div class="IN">
+ <p>Decoy text</p>
+ </div>
+ </div>
+ <script>
+ window.__NUXT__=(function(a,b,c,d,e,f,g,h){return {decoy:" default",data:[{track:{id:f,title:g}}]}}(null,null,"c",null,null,"testid","Nuxt.js title",null));
+ </script>
+ <script src="/_nuxt/a12345b.js" defer="defer"></script>
+</body>
+</html>
+'''
+ search = self.ie._search_nuxt_data(html, 'testID')
+ self.assertEqual(search['track']['id'], 'testid')
+
+ def test_search_json_ld_realworld(self):
+ # https://github.com/ytdl-org/youtube-dl/issues/23306
+ expect_dict(
+ self,
+ self.ie._search_json_ld(r'''<script type="application/ld+json">
+{
+"@context": "http://schema.org/",
+"@type": "VideoObject",
+"name": "1 On 1 With Kleio",
+"url": "https://www.eporner.com/hd-porn/xN49A1cT3eB/1-On-1-With-Kleio/",
+"duration": "PT0H12M23S",
+"thumbnailUrl": ["https://static-eu-cdn.eporner.com/thumbs/static4/7/78/780/780814/9_360.jpg", "https://imggen.eporner.com/780814/1920/1080/9.jpg"],
+"contentUrl": "https://gvideo.eporner.com/xN49A1cT3eB/xN49A1cT3eB.mp4",
+"embedUrl": "https://www.eporner.com/embed/xN49A1cT3eB/1-On-1-With-Kleio/",
+"image": "https://static-eu-cdn.eporner.com/thumbs/static4/7/78/780/780814/9_360.jpg",
+"width": "1920",
+"height": "1080",
+"encodingFormat": "mp4",
+"bitrate": "6617kbps",
+"isFamilyFriendly": "False",
+"description": "Kleio Valentien",
+"uploadDate": "2015-12-05T21:24:35+01:00",
+"interactionStatistic": {
+"@type": "InteractionCounter",
+"interactionType": { "@type": "http://schema.org/WatchAction" },
+"userInteractionCount": 1120958
+}, "aggregateRating": {
+"@type": "AggregateRating",
+"ratingValue": "88",
+"ratingCount": "630",
+"bestRating": "100",
+"worstRating": "0"
+}, "actor": [{
+"@type": "Person",
+"name": "Kleio Valentien",
+"url": "https://www.eporner.com/pornstar/kleio-valentien/"
+}]}
+</script>''', None),
+ {
+ 'title': '1 On 1 With Kleio',
+ 'description': 'Kleio Valentien',
+ 'url': 'https://gvideo.eporner.com/xN49A1cT3eB/xN49A1cT3eB.mp4',
+ 'timestamp': 1449347075,
+ 'duration': 743.0,
+ 'view_count': 1120958,
+ 'width': 1920,
+ 'height': 1080,
+ })
+
def test_download_json(self):
uri = encode_data_uri(b'{"foo": "blah"}', 'application/json')
self.assertEqual(self.ie._download_json(uri, None), {'foo': 'blah'})
@@ -84,6 +244,214 @@ class TestInfoExtractor(unittest.TestCase):
self.assertRaises(ExtractorError, self.ie._download_json, uri, None)
self.assertEqual(self.ie._download_json(uri, None, fatal=False), None)
+ def test_parse_html5_media_entries(self):
+ # inline video tag
+ expect_dict(
+ self,
+ self.ie._parse_html5_media_entries(
+ 'https://127.0.0.1/video.html',
+ r'<html><video src="/vid.mp4" /></html>', None)[0],
+ {
+ 'formats': [{
+ 'url': 'https://127.0.0.1/vid.mp4',
+ }],
+ })
+
+ # from https://www.r18.com/
+ # with kpbs in label
+ expect_dict(
+ self,
+ self.ie._parse_html5_media_entries(
+ 'https://www.r18.com/',
+ r'''
+ <video id="samplevideo_amateur" class="js-samplevideo video-js vjs-default-skin vjs-big-play-centered" controls preload="auto" width="400" height="225" poster="//pics.r18.com/digital/amateur/mgmr105/mgmr105jp.jpg">
+ <source id="video_source" src="https://awscc3001.r18.com/litevideo/freepv/m/mgm/mgmr105/mgmr105_sm_w.mp4" type="video/mp4" res="240" label="300kbps">
+ <source id="video_source" src="https://awscc3001.r18.com/litevideo/freepv/m/mgm/mgmr105/mgmr105_dm_w.mp4" type="video/mp4" res="480" label="1000kbps">
+ <source id="video_source" src="https://awscc3001.r18.com/litevideo/freepv/m/mgm/mgmr105/mgmr105_dmb_w.mp4" type="video/mp4" res="740" label="1500kbps">
+ <p>Your browser does not support the video tag.</p>
+ </video>
+ ''', None)[0],
+ {
+ 'formats': [{
+ 'url': 'https://awscc3001.r18.com/litevideo/freepv/m/mgm/mgmr105/mgmr105_sm_w.mp4',
+ 'ext': 'mp4',
+ 'format_id': '300kbps',
+ 'height': 240,
+ 'tbr': 300,
+ }, {
+ 'url': 'https://awscc3001.r18.com/litevideo/freepv/m/mgm/mgmr105/mgmr105_dm_w.mp4',
+ 'ext': 'mp4',
+ 'format_id': '1000kbps',
+ 'height': 480,
+ 'tbr': 1000,
+ }, {
+ 'url': 'https://awscc3001.r18.com/litevideo/freepv/m/mgm/mgmr105/mgmr105_dmb_w.mp4',
+ 'ext': 'mp4',
+ 'format_id': '1500kbps',
+ 'height': 740,
+ 'tbr': 1500,
+ }],
+ 'thumbnail': '//pics.r18.com/digital/amateur/mgmr105/mgmr105jp.jpg'
+ })
+
+ # from https://www.csfd.cz/
+ # with width and height
+ expect_dict(
+ self,
+ self.ie._parse_html5_media_entries(
+ 'https://www.csfd.cz/',
+ r'''
+ <video width="770" height="328" preload="none" controls poster="https://img.csfd.cz/files/images/film/video/preview/163/344/163344118_748d20.png?h360" >
+ <source src="https://video.csfd.cz/files/videos/157/750/157750813/163327358_eac647.mp4" type="video/mp4" width="640" height="360">
+ <source src="https://video.csfd.cz/files/videos/157/750/157750813/163327360_3d2646.mp4" type="video/mp4" width="1280" height="720">
+ <source src="https://video.csfd.cz/files/videos/157/750/157750813/163327356_91f258.mp4" type="video/mp4" width="1920" height="1080">
+ <source src="https://video.csfd.cz/files/videos/157/750/157750813/163327359_962b4a.webm" type="video/webm" width="640" height="360">
+ <source src="https://video.csfd.cz/files/videos/157/750/157750813/163327361_6feee0.webm" type="video/webm" width="1280" height="720">
+ <source src="https://video.csfd.cz/files/videos/157/750/157750813/163327357_8ab472.webm" type="video/webm" width="1920" height="1080">
+ <track src="https://video.csfd.cz/files/subtitles/163/344/163344115_4c388b.srt" type="text/x-srt" kind="subtitles" srclang="cs" label="cs">
+ </video>
+ ''', None)[0],
+ {
+ 'formats': [{
+ 'url': 'https://video.csfd.cz/files/videos/157/750/157750813/163327358_eac647.mp4',
+ 'ext': 'mp4',
+ 'width': 640,
+ 'height': 360,
+ }, {
+ 'url': 'https://video.csfd.cz/files/videos/157/750/157750813/163327360_3d2646.mp4',
+ 'ext': 'mp4',
+ 'width': 1280,
+ 'height': 720,
+ }, {
+ 'url': 'https://video.csfd.cz/files/videos/157/750/157750813/163327356_91f258.mp4',
+ 'ext': 'mp4',
+ 'width': 1920,
+ 'height': 1080,
+ }, {
+ 'url': 'https://video.csfd.cz/files/videos/157/750/157750813/163327359_962b4a.webm',
+ 'ext': 'webm',
+ 'width': 640,
+ 'height': 360,
+ }, {
+ 'url': 'https://video.csfd.cz/files/videos/157/750/157750813/163327361_6feee0.webm',
+ 'ext': 'webm',
+ 'width': 1280,
+ 'height': 720,
+ }, {
+ 'url': 'https://video.csfd.cz/files/videos/157/750/157750813/163327357_8ab472.webm',
+ 'ext': 'webm',
+ 'width': 1920,
+ 'height': 1080,
+ }],
+ 'subtitles': {
+ 'cs': [{'url': 'https://video.csfd.cz/files/subtitles/163/344/163344115_4c388b.srt'}]
+ },
+ 'thumbnail': 'https://img.csfd.cz/files/images/film/video/preview/163/344/163344118_748d20.png?h360'
+ })
+
+ # from https://tamasha.com/v/Kkdjw
+ # with height in label
+ expect_dict(
+ self,
+ self.ie._parse_html5_media_entries(
+ 'https://tamasha.com/v/Kkdjw',
+ r'''
+ <video crossorigin="anonymous">
+ <source src="https://s-v2.tamasha.com/statics/videos_file/19/8f/Kkdjw_198feff8577d0057536e905cce1fb61438dd64e0_n_240.mp4" type="video/mp4" label="AUTO" res="0"/>
+ <source src="https://s-v2.tamasha.com/statics/videos_file/19/8f/Kkdjw_198feff8577d0057536e905cce1fb61438dd64e0_n_240.mp4" type="video/mp4"
+ label="240p" res="240"/>
+ <source src="https://s-v2.tamasha.com/statics/videos_file/20/00/Kkdjw_200041c66f657fc967db464d156eafbc1ed9fe6f_n_144.mp4" type="video/mp4"
+ label="144p" res="144"/>
+ </video>
+ ''', None)[0],
+ {
+ 'formats': [{
+ 'url': 'https://s-v2.tamasha.com/statics/videos_file/19/8f/Kkdjw_198feff8577d0057536e905cce1fb61438dd64e0_n_240.mp4',
+ }, {
+ 'url': 'https://s-v2.tamasha.com/statics/videos_file/19/8f/Kkdjw_198feff8577d0057536e905cce1fb61438dd64e0_n_240.mp4',
+ 'ext': 'mp4',
+ 'format_id': '240p',
+ 'height': 240,
+ }, {
+ 'url': 'https://s-v2.tamasha.com/statics/videos_file/20/00/Kkdjw_200041c66f657fc967db464d156eafbc1ed9fe6f_n_144.mp4',
+ 'ext': 'mp4',
+ 'format_id': '144p',
+ 'height': 144,
+ }]
+ })
+
+ # from https://www.directvnow.com
+ # with data-src
+ expect_dict(
+ self,
+ self.ie._parse_html5_media_entries(
+ 'https://www.directvnow.com',
+ r'''
+ <video id="vid1" class="header--video-masked active" muted playsinline>
+ <source data-src="https://cdn.directv.com/content/dam/dtv/prod/website_directvnow-international/videos/DTVN_hdr_HBO_v3.mp4" type="video/mp4" />
+ </video>
+ ''', None)[0],
+ {
+ 'formats': [{
+ 'ext': 'mp4',
+ 'url': 'https://cdn.directv.com/content/dam/dtv/prod/website_directvnow-international/videos/DTVN_hdr_HBO_v3.mp4',
+ }]
+ })
+
+ # from https://www.directvnow.com
+ # with data-src
+ expect_dict(
+ self,
+ self.ie._parse_html5_media_entries(
+ 'https://www.directvnow.com',
+ r'''
+ <video id="vid1" class="header--video-masked active" muted playsinline>
+ <source data-src="https://cdn.directv.com/content/dam/dtv/prod/website_directvnow-international/videos/DTVN_hdr_HBO_v3.mp4" type="video/mp4" />
+ </video>
+ ''', None)[0],
+ {
+ 'formats': [{
+ 'url': 'https://cdn.directv.com/content/dam/dtv/prod/website_directvnow-international/videos/DTVN_hdr_HBO_v3.mp4',
+ 'ext': 'mp4',
+ }]
+ })
+
+ # from https://www.klarna.com/uk/
+ # with data-video-src
+ expect_dict(
+ self,
+ self.ie._parse_html5_media_entries(
+ 'https://www.directvnow.com',
+ r'''
+ <video loop autoplay muted class="responsive-video block-kl__video video-on-medium">
+ <source src="" data-video-desktop data-video-src="https://www.klarna.com/uk/wp-content/uploads/sites/11/2019/01/KL062_Smooth3_0_DogWalking_5s_920x080_.mp4" type="video/mp4" />
+ </video>
+ ''', None)[0],
+ {
+ 'formats': [{
+ 'url': 'https://www.klarna.com/uk/wp-content/uploads/sites/11/2019/01/KL062_Smooth3_0_DogWalking_5s_920x080_.mp4',
+ 'ext': 'mp4',
+ }],
+ })
+
+ # from https://0000.studio/
+ # with type attribute but without extension in URL
+ expect_dict(
+ self,
+ self.ie._parse_html5_media_entries(
+ 'https://0000.studio',
+ r'''
+ <video src="https://d1ggyt9m8pwf3g.cloudfront.net/protected/ap-northeast-1:1864af40-28d5-492b-b739-b32314b1a527/archive/clip/838db6a7-8973-4cd6-840d-8517e4093c92"
+ controls="controls" type="video/mp4" preload="metadata" autoplay="autoplay" playsinline class="object-contain">
+ </video>
+ ''', None)[0],
+ {
+ 'formats': [{
+ 'url': 'https://d1ggyt9m8pwf3g.cloudfront.net/protected/ap-northeast-1:1864af40-28d5-492b-b739-b32314b1a527/archive/clip/838db6a7-8973-4cd6-840d-8517e4093c92',
+ 'ext': 'mp4',
+ }],
+ })
+
def test_extract_jwplayer_data_realworld(self):
# from http://www.suffolk.edu/sjc/
expect_dict(
@@ -175,6 +543,865 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
}]
})
+ def test_parse_m3u8_formats(self):
+ _TEST_CASES = [
+ (
+ # 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',
+ [{
+ 'url': 'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/index_0_av.m3u8?null=0',
+ 'manifest_url': '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',
+ 'ext': 'mp4',
+ 'format_id': '180',
+ 'protocol': 'm3u8',
+ 'acodec': 'mp4a.40.2',
+ 'vcodec': 'avc1.66.30',
+ 'tbr': 180,
+ 'width': 256,
+ 'height': 144,
+ }, {
+ 'url': 'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/index_1_av.m3u8?null=0',
+ 'manifest_url': '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',
+ 'ext': 'mp4',
+ 'format_id': '303',
+ 'protocol': 'm3u8',
+ 'acodec': 'mp4a.40.2',
+ 'vcodec': 'avc1.66.30',
+ 'tbr': 303,
+ 'width': 320,
+ 'height': 180,
+ }, {
+ 'url': 'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/index_2_av.m3u8?null=0',
+ 'manifest_url': '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',
+ 'ext': 'mp4',
+ 'format_id': '575',
+ 'protocol': 'm3u8',
+ 'acodec': 'mp4a.40.2',
+ 'vcodec': 'avc1.66.30',
+ 'tbr': 575,
+ 'width': 512,
+ 'height': 288,
+ }, {
+ 'url': 'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/index_3_av.m3u8?null=0',
+ 'manifest_url': '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',
+ 'ext': 'mp4',
+ 'format_id': '831',
+ 'protocol': 'm3u8',
+ 'acodec': 'mp4a.40.2',
+ 'vcodec': 'avc1.77.30',
+ 'tbr': 831,
+ 'width': 704,
+ 'height': 396,
+ }, {
+ 'url': 'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/index_4_av.m3u8?null=0',
+ 'manifest_url': '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',
+ 'ext': 'mp4',
+ 'protocol': 'm3u8',
+ 'format_id': '1467',
+ 'acodec': 'mp4a.40.2',
+ 'vcodec': 'avc1.77.30',
+ 'tbr': 1467,
+ 'width': 1024,
+ 'height': 576,
+ }]
+ ),
+ (
+ # 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',
+ [{
+ 'url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/hls/CONAN_020217_Highlight_show-audio-160k_v4.m3u8',
+ 'manifest_url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/main.m3u8',
+ 'ext': 'mp4',
+ 'format_id': 'audio-0-Default',
+ 'protocol': 'm3u8',
+ 'vcodec': 'none',
+ }, {
+ 'url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/hls/CONAN_020217_Highlight_show-audio-64k_v4.m3u8',
+ 'manifest_url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/main.m3u8',
+ 'ext': 'mp4',
+ 'format_id': 'audio-1-Default',
+ 'protocol': 'm3u8',
+ 'vcodec': 'none',
+ }, {
+ 'url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/hls/CONAN_020217_Highlight_show-audio-64k_v4.m3u8',
+ 'manifest_url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/main.m3u8',
+ 'ext': 'mp4',
+ 'format_id': '71',
+ 'protocol': 'm3u8',
+ 'acodec': 'mp4a.40.5',
+ 'vcodec': 'none',
+ 'tbr': 71,
+ }, {
+ 'url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/hls/CONAN_020217_Highlight_show-400k_v4.m3u8',
+ 'manifest_url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/main.m3u8',
+ 'ext': 'mp4',
+ 'format_id': '413',
+ 'protocol': 'm3u8',
+ 'acodec': 'none',
+ 'vcodec': 'avc1.42001e',
+ 'tbr': 413,
+ 'width': 400,
+ 'height': 224,
+ }, {
+ 'url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/hls/CONAN_020217_Highlight_show-400k_v4.m3u8',
+ 'manifest_url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/main.m3u8',
+ 'ext': 'mp4',
+ 'format_id': '522',
+ 'protocol': 'm3u8',
+ 'acodec': 'none',
+ 'vcodec': 'avc1.42001e',
+ 'tbr': 522,
+ 'width': 400,
+ 'height': 224,
+ }, {
+ 'url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/hls/CONAN_020217_Highlight_show-1m_v4.m3u8',
+ 'manifest_url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/main.m3u8',
+ 'ext': 'mp4',
+ 'format_id': '1205',
+ 'protocol': 'm3u8',
+ 'acodec': 'none',
+ 'vcodec': 'avc1.4d001e',
+ 'tbr': 1205,
+ 'width': 640,
+ 'height': 360,
+ }, {
+ 'url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/hls/CONAN_020217_Highlight_show-2m_v4.m3u8',
+ 'manifest_url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/main.m3u8',
+ 'ext': 'mp4',
+ 'format_id': '2374',
+ 'protocol': 'm3u8',
+ 'acodec': 'none',
+ 'vcodec': 'avc1.4d001f',
+ 'tbr': 2374,
+ 'width': 1024,
+ 'height': 576,
+ }]
+ ),
+ (
+ # 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',
+ [{
+ 'url': 'http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/2/pv/1/flavorId/0_sa2ntrdg/name/a.mp4/index.m3u8',
+ 'manifest_url': 'http://cdnapi.kaltura.com/p/2082311/sp/208231100/playManifest/protocol/http/entryId/0_89q6e8ku/format/applehttp/tags/mobile_sd/f/a.m3u8',
+ 'ext': 'mp4',
+ 'format_id': 'audio-English',
+ 'protocol': 'm3u8',
+ 'language': 'eng',
+ 'vcodec': 'none',
+ }, {
+ 'url': 'http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/2/pv/1/flavorId/0_r7y0nitg/name/a.mp4/index.m3u8',
+ 'manifest_url': 'http://cdnapi.kaltura.com/p/2082311/sp/208231100/playManifest/protocol/http/entryId/0_89q6e8ku/format/applehttp/tags/mobile_sd/f/a.m3u8',
+ 'ext': 'mp4',
+ 'format_id': 'audio-Undefined',
+ 'protocol': 'm3u8',
+ 'language': 'und',
+ 'vcodec': 'none',
+ }, {
+ 'url': 'http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/2/pv/1/flavorId/0_qlk9hlzr/name/a.mp4/index.m3u8',
+ 'manifest_url': 'http://cdnapi.kaltura.com/p/2082311/sp/208231100/playManifest/protocol/http/entryId/0_89q6e8ku/format/applehttp/tags/mobile_sd/f/a.m3u8',
+ 'ext': 'mp4',
+ 'format_id': '155',
+ 'protocol': 'm3u8',
+ 'tbr': 155.648,
+ 'width': 320,
+ 'height': 180,
+ }, {
+ 'url': 'http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/2/pv/1/flavorId/0_oefackmi/name/a.mp4/index.m3u8',
+ 'manifest_url': 'http://cdnapi.kaltura.com/p/2082311/sp/208231100/playManifest/protocol/http/entryId/0_89q6e8ku/format/applehttp/tags/mobile_sd/f/a.m3u8',
+ 'ext': 'mp4',
+ 'format_id': '502',
+ 'protocol': 'm3u8',
+ 'tbr': 502.784,
+ 'width': 480,
+ 'height': 270,
+ }, {
+ 'url': 'http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/12/pv/1/flavorId/0_vyg9pj7k/name/a.mp4/index.m3u8',
+ 'manifest_url': 'http://cdnapi.kaltura.com/p/2082311/sp/208231100/playManifest/protocol/http/entryId/0_89q6e8ku/format/applehttp/tags/mobile_sd/f/a.m3u8',
+ 'ext': 'mp4',
+ 'format_id': '827',
+ 'protocol': 'm3u8',
+ 'tbr': 827.392,
+ 'width': 640,
+ 'height': 360,
+ }, {
+ 'url': 'http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/12/pv/1/flavorId/0_50n4psvx/name/a.mp4/index.m3u8',
+ 'manifest_url': 'http://cdnapi.kaltura.com/p/2082311/sp/208231100/playManifest/protocol/http/entryId/0_89q6e8ku/format/applehttp/tags/mobile_sd/f/a.m3u8',
+ 'ext': 'mp4',
+ 'format_id': '1396',
+ 'protocol': 'm3u8',
+ 'tbr': 1396.736,
+ 'width': 854,
+ 'height': 480,
+ }]
+ ),
+ (
+ # http://www.twitch.tv/riotgames/v/6528877
+ 'twitch_vod',
+ 'https://usher.ttvnw.net/vod/6528877?allow_source=true&allow_audio_only=true&allow_spectre=true&player=twitchweb&nauth=%7B%22user_id%22%3Anull%2C%22vod_id%22%3A6528877%2C%22expires%22%3A1492887874%2C%22chansub%22%3A%7B%22restricted_bitrates%22%3A%5B%5D%7D%2C%22privileged%22%3Afalse%2C%22https_required%22%3Afalse%7D&nauthsig=3e29296a6824a0f48f9e731383f77a614fc79bee',
+ [{
+ 'url': 'https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/audio_only/index-muted-HM49I092CC.m3u8',
+ 'manifest_url': 'https://usher.ttvnw.net/vod/6528877?allow_source=true&allow_audio_only=true&allow_spectre=true&player=twitchweb&nauth=%7B%22user_id%22%3Anull%2C%22vod_id%22%3A6528877%2C%22expires%22%3A1492887874%2C%22chansub%22%3A%7B%22restricted_bitrates%22%3A%5B%5D%7D%2C%22privileged%22%3Afalse%2C%22https_required%22%3Afalse%7D&nauthsig=3e29296a6824a0f48f9e731383f77a614fc79bee',
+ 'ext': 'mp4',
+ 'format_id': 'Audio Only',
+ 'protocol': 'm3u8',
+ 'acodec': 'mp4a.40.2',
+ 'vcodec': 'none',
+ 'tbr': 182.725,
+ }, {
+ 'url': 'https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/mobile/index-muted-HM49I092CC.m3u8',
+ 'manifest_url': 'https://usher.ttvnw.net/vod/6528877?allow_source=true&allow_audio_only=true&allow_spectre=true&player=twitchweb&nauth=%7B%22user_id%22%3Anull%2C%22vod_id%22%3A6528877%2C%22expires%22%3A1492887874%2C%22chansub%22%3A%7B%22restricted_bitrates%22%3A%5B%5D%7D%2C%22privileged%22%3Afalse%2C%22https_required%22%3Afalse%7D&nauthsig=3e29296a6824a0f48f9e731383f77a614fc79bee',
+ 'ext': 'mp4',
+ 'format_id': 'Mobile',
+ 'protocol': 'm3u8',
+ 'acodec': 'mp4a.40.2',
+ 'vcodec': 'avc1.42C00D',
+ 'tbr': 280.474,
+ 'width': 400,
+ 'height': 226,
+ }, {
+ 'url': 'https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/low/index-muted-HM49I092CC.m3u8',
+ 'manifest_url': 'https://usher.ttvnw.net/vod/6528877?allow_source=true&allow_audio_only=true&allow_spectre=true&player=twitchweb&nauth=%7B%22user_id%22%3Anull%2C%22vod_id%22%3A6528877%2C%22expires%22%3A1492887874%2C%22chansub%22%3A%7B%22restricted_bitrates%22%3A%5B%5D%7D%2C%22privileged%22%3Afalse%2C%22https_required%22%3Afalse%7D&nauthsig=3e29296a6824a0f48f9e731383f77a614fc79bee',
+ 'ext': 'mp4',
+ 'format_id': 'Low',
+ 'protocol': 'm3u8',
+ 'acodec': 'mp4a.40.2',
+ 'vcodec': 'avc1.42C01E',
+ 'tbr': 628.347,
+ 'width': 640,
+ 'height': 360,
+ }, {
+ 'url': 'https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/medium/index-muted-HM49I092CC.m3u8',
+ 'manifest_url': 'https://usher.ttvnw.net/vod/6528877?allow_source=true&allow_audio_only=true&allow_spectre=true&player=twitchweb&nauth=%7B%22user_id%22%3Anull%2C%22vod_id%22%3A6528877%2C%22expires%22%3A1492887874%2C%22chansub%22%3A%7B%22restricted_bitrates%22%3A%5B%5D%7D%2C%22privileged%22%3Afalse%2C%22https_required%22%3Afalse%7D&nauthsig=3e29296a6824a0f48f9e731383f77a614fc79bee',
+ 'ext': 'mp4',
+ 'format_id': 'Medium',
+ 'protocol': 'm3u8',
+ 'acodec': 'mp4a.40.2',
+ 'vcodec': 'avc1.42C01E',
+ 'tbr': 893.387,
+ 'width': 852,
+ 'height': 480,
+ }, {
+ 'url': 'https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/high/index-muted-HM49I092CC.m3u8',
+ 'manifest_url': 'https://usher.ttvnw.net/vod/6528877?allow_source=true&allow_audio_only=true&allow_spectre=true&player=twitchweb&nauth=%7B%22user_id%22%3Anull%2C%22vod_id%22%3A6528877%2C%22expires%22%3A1492887874%2C%22chansub%22%3A%7B%22restricted_bitrates%22%3A%5B%5D%7D%2C%22privileged%22%3Afalse%2C%22https_required%22%3Afalse%7D&nauthsig=3e29296a6824a0f48f9e731383f77a614fc79bee',
+ 'ext': 'mp4',
+ 'format_id': 'High',
+ 'protocol': 'm3u8',
+ 'acodec': 'mp4a.40.2',
+ 'vcodec': 'avc1.42C01F',
+ 'tbr': 1603.789,
+ 'width': 1280,
+ 'height': 720,
+ }, {
+ 'url': 'https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/chunked/index-muted-HM49I092CC.m3u8',
+ 'manifest_url': 'https://usher.ttvnw.net/vod/6528877?allow_source=true&allow_audio_only=true&allow_spectre=true&player=twitchweb&nauth=%7B%22user_id%22%3Anull%2C%22vod_id%22%3A6528877%2C%22expires%22%3A1492887874%2C%22chansub%22%3A%7B%22restricted_bitrates%22%3A%5B%5D%7D%2C%22privileged%22%3Afalse%2C%22https_required%22%3Afalse%7D&nauthsig=3e29296a6824a0f48f9e731383f77a614fc79bee',
+ 'ext': 'mp4',
+ 'format_id': 'Source',
+ 'protocol': 'm3u8',
+ 'acodec': 'mp4a.40.2',
+ 'vcodec': 'avc1.100.31',
+ 'tbr': 3214.134,
+ 'width': 1280,
+ 'height': 720,
+ }]
+ ),
+ (
+ # http://www.vidio.com/watch/165683-dj_ambred-booyah-live-2015
+ # EXT-X-STREAM-INF tag with NAME attribute that is not defined
+ # in HLS specification
+ 'vidio',
+ 'https://www.vidio.com/videos/165683/playlist.m3u8',
+ [{
+ 'url': 'https://cdn1-a.production.vidio.static6.com/uploads/165683/dj_ambred-4383-b300.mp4.m3u8',
+ 'manifest_url': 'https://www.vidio.com/videos/165683/playlist.m3u8',
+ 'ext': 'mp4',
+ 'format_id': '270p 3G',
+ 'protocol': 'm3u8',
+ 'tbr': 300,
+ 'width': 480,
+ 'height': 270,
+ }, {
+ 'url': 'https://cdn1-a.production.vidio.static6.com/uploads/165683/dj_ambred-4383-b600.mp4.m3u8',
+ 'manifest_url': 'https://www.vidio.com/videos/165683/playlist.m3u8',
+ 'ext': 'mp4',
+ 'format_id': '360p SD',
+ 'protocol': 'm3u8',
+ 'tbr': 600,
+ 'width': 640,
+ 'height': 360,
+ }, {
+ 'url': 'https://cdn1-a.production.vidio.static6.com/uploads/165683/dj_ambred-4383-b1200.mp4.m3u8',
+ 'manifest_url': 'https://www.vidio.com/videos/165683/playlist.m3u8',
+ 'ext': 'mp4',
+ 'format_id': '720p HD',
+ 'protocol': 'm3u8',
+ 'tbr': 1200,
+ '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:
+ with open('./test/testdata/m3u8/%s.m3u8' % m3u8_file,
+ mode='r', encoding='utf-8') as f:
+ formats = self.ie._parse_m3u8_formats(
+ f.read(), m3u8_url, ext='mp4')
+ self.ie._sort_formats(formats)
+ expect_value(self, formats, expected_formats, None)
+
+ def test_parse_mpd_formats(self):
+ _TEST_CASES = [
+ (
+ # https://github.com/ytdl-org/youtube-dl/issues/13919
+ # Also tests duplicate representation ids, see
+ # https://github.com/ytdl-org/youtube-dl/issues/15111
+ 'float_duration',
+ 'http://unknown/manifest.mpd', # mpd_url
+ None, # mpd_base_url
+ [{
+ 'manifest_url': 'http://unknown/manifest.mpd',
+ 'ext': 'm4a',
+ 'format_id': '318597',
+ 'format_note': 'DASH audio',
+ 'protocol': 'http_dash_segments',
+ 'acodec': 'mp4a.40.2',
+ 'vcodec': 'none',
+ 'tbr': 61.587,
+ }, {
+ '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,
+ }],
+ {},
+ ), (
+ # https://github.com/ytdl-org/youtube-dl/pull/14844
+ 'urls_only',
+ 'http://unknown/manifest.mpd', # mpd_url
+ None, # mpd_base_url
+ [{
+ 'manifest_url': 'http://unknown/manifest.mpd',
+ 'ext': 'mp4',
+ 'format_id': 'h264_aac_144p_m4s',
+ 'format_note': 'DASH video',
+ 'protocol': 'http_dash_segments',
+ 'acodec': 'mp4a.40.2',
+ 'vcodec': 'avc3.42c01e',
+ 'tbr': 200,
+ 'width': 256,
+ 'height': 144,
+ }, {
+ 'manifest_url': 'http://unknown/manifest.mpd',
+ 'ext': 'mp4',
+ 'format_id': 'h264_aac_240p_m4s',
+ 'format_note': 'DASH video',
+ 'protocol': 'http_dash_segments',
+ 'acodec': 'mp4a.40.2',
+ 'vcodec': 'avc3.42c01e',
+ 'tbr': 400,
+ 'width': 424,
+ 'height': 240,
+ }, {
+ 'manifest_url': 'http://unknown/manifest.mpd',
+ 'ext': 'mp4',
+ 'format_id': 'h264_aac_360p_m4s',
+ 'format_note': 'DASH video',
+ 'protocol': 'http_dash_segments',
+ 'acodec': 'mp4a.40.2',
+ 'vcodec': 'avc3.42c01e',
+ 'tbr': 800,
+ 'width': 640,
+ 'height': 360,
+ }, {
+ 'manifest_url': 'http://unknown/manifest.mpd',
+ 'ext': 'mp4',
+ 'format_id': 'h264_aac_480p_m4s',
+ 'format_note': 'DASH video',
+ 'protocol': 'http_dash_segments',
+ 'acodec': 'mp4a.40.2',
+ 'vcodec': 'avc3.42c01e',
+ 'tbr': 1200,
+ 'width': 856,
+ 'height': 480,
+ }, {
+ 'manifest_url': 'http://unknown/manifest.mpd',
+ 'ext': 'mp4',
+ 'format_id': 'h264_aac_576p_m4s',
+ 'format_note': 'DASH video',
+ 'protocol': 'http_dash_segments',
+ 'acodec': 'mp4a.40.2',
+ 'vcodec': 'avc3.42c01e',
+ 'tbr': 1600,
+ 'width': 1024,
+ 'height': 576,
+ }, {
+ 'manifest_url': 'http://unknown/manifest.mpd',
+ 'ext': 'mp4',
+ 'format_id': 'h264_aac_720p_m4s',
+ 'format_note': 'DASH video',
+ 'protocol': 'http_dash_segments',
+ 'acodec': 'mp4a.40.2',
+ 'vcodec': 'avc3.42c01e',
+ 'tbr': 2400,
+ 'width': 1280,
+ 'height': 720,
+ }, {
+ 'manifest_url': 'http://unknown/manifest.mpd',
+ 'ext': 'mp4',
+ 'format_id': 'h264_aac_1080p_m4s',
+ 'format_note': 'DASH video',
+ 'protocol': 'http_dash_segments',
+ 'acodec': 'mp4a.40.2',
+ 'vcodec': 'avc3.42c01e',
+ 'tbr': 4400,
+ '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,
+ }],
+ {},
+ ), (
+ # https://github.com/ytdl-org/youtube-dl/issues/30235
+ # Bento4 generated test mpd
+ # mp4dash --mpd-name=manifest.mpd --no-split --use-segment-list mediafiles
+ 'url_and_range',
+ 'http://unknown/manifest.mpd', # mpd_url
+ 'http://unknown/', # mpd_base_url
+ [{
+ 'manifest_url': 'http://unknown/manifest.mpd',
+ 'fragment_base_url': 'http://unknown/',
+ 'ext': 'm4a',
+ 'format_id': 'audio-und-mp4a.40.2',
+ 'format_note': 'DASH audio',
+ 'container': 'm4a_dash',
+ 'protocol': 'http_dash_segments',
+ 'acodec': 'mp4a.40.2',
+ 'vcodec': 'none',
+ 'tbr': 98.808,
+ }, {
+ 'manifest_url': 'http://unknown/manifest.mpd',
+ 'fragment_base_url': 'http://unknown/',
+ 'ext': 'mp4',
+ 'format_id': 'video-avc1',
+ 'format_note': 'DASH video',
+ 'container': 'mp4_dash',
+ 'protocol': 'http_dash_segments',
+ 'acodec': 'none',
+ 'vcodec': 'avc1.4D401E',
+ 'tbr': 699.597,
+ 'width': 768,
+ 'height': 432
+ }],
+ {},
+ ), (
+ # https://github.com/ytdl-org/youtube-dl/issues/27575
+ # GPAC generated test mpd
+ # MP4Box -dash 10000 -single-file -out manifest.mpd mediafiles
+ 'range_only',
+ 'http://unknown/manifest.mpd', # mpd_url
+ 'http://unknown/', # mpd_base_url
+ [{
+ 'manifest_url': 'http://unknown/manifest.mpd',
+ 'fragment_base_url': 'http://unknown/audio_dashinit.mp4',
+ 'ext': 'm4a',
+ 'format_id': '2',
+ 'format_note': 'DASH audio',
+ 'container': 'm4a_dash',
+ 'protocol': 'http_dash_segments',
+ 'acodec': 'mp4a.40.2',
+ 'vcodec': 'none',
+ 'tbr': 98.096,
+ }, {
+ 'manifest_url': 'http://unknown/manifest.mpd',
+ 'fragment_base_url': 'http://unknown/video_dashinit.mp4',
+ 'ext': 'mp4',
+ 'format_id': '1',
+ 'format_note': 'DASH video',
+ 'container': 'mp4_dash',
+ 'protocol': 'http_dash_segments',
+ 'acodec': 'none',
+ 'vcodec': 'avc1.4D401E',
+ 'tbr': 526.987,
+ 'width': 768,
+ 'height': 432
+ }],
+ {},
+ ), (
+ 'subtitles',
+ 'https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/manifest.mpd',
+ 'https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/',
+ [{
+ 'format_id': 'audio=128001',
+ 'manifest_url': 'https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/manifest.mpd',
+ 'ext': 'm4a',
+ 'tbr': 128.001,
+ 'asr': 48000,
+ 'format_note': 'DASH audio',
+ 'container': 'm4a_dash',
+ 'vcodec': 'none',
+ 'acodec': 'mp4a.40.2',
+ 'url': 'https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/manifest.mpd',
+ 'fragment_base_url': 'https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/dash/',
+ 'protocol': 'http_dash_segments',
+ }, {
+ 'format_id': 'video=100000',
+ 'manifest_url': 'https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/manifest.mpd',
+ 'ext': 'mp4',
+ 'width': 336,
+ 'height': 144,
+ 'tbr': 100,
+ 'format_note': 'DASH video',
+ 'container': 'mp4_dash',
+ 'vcodec': 'avc1.4D401F',
+ 'acodec': 'none',
+ 'url': 'https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/manifest.mpd',
+ 'fragment_base_url': 'https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/dash/',
+ 'protocol': 'http_dash_segments',
+ }, {
+ 'format_id': 'video=326000',
+ 'manifest_url': 'https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/manifest.mpd',
+ 'ext': 'mp4',
+ 'width': 562,
+ 'height': 240,
+ 'tbr': 326,
+ 'format_note': 'DASH video',
+ 'container': 'mp4_dash',
+ 'vcodec': 'avc1.4D401F',
+ 'acodec': 'none',
+ 'url': 'https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/manifest.mpd',
+ 'fragment_base_url': 'https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/dash/',
+ 'protocol': 'http_dash_segments',
+ }, {
+ 'format_id': 'video=698000',
+ 'manifest_url': 'https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/manifest.mpd',
+ 'ext': 'mp4',
+ 'width': 844,
+ 'height': 360,
+ 'tbr': 698,
+ 'format_note': 'DASH video',
+ 'container': 'mp4_dash',
+ 'vcodec': 'avc1.4D401F',
+ 'acodec': 'none',
+ 'url': 'https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/manifest.mpd',
+ 'fragment_base_url': 'https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/dash/',
+ 'protocol': 'http_dash_segments',
+ }, {
+ 'format_id': 'video=1493000',
+ 'manifest_url': 'https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/manifest.mpd',
+ 'ext': 'mp4',
+ 'width': 1126,
+ 'height': 480,
+ 'tbr': 1493,
+ 'format_note': 'DASH video',
+ 'container': 'mp4_dash',
+ 'vcodec': 'avc1.4D401F',
+ 'acodec': 'none',
+ 'url': 'https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/manifest.mpd',
+ 'fragment_base_url': 'https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/dash/',
+ 'protocol': 'http_dash_segments',
+ }, {
+ 'format_id': 'video=4482000',
+ 'manifest_url': 'https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/manifest.mpd',
+ 'ext': 'mp4',
+ 'width': 1688,
+ 'height': 720,
+ 'tbr': 4482,
+ 'format_note': 'DASH video',
+ 'container': 'mp4_dash',
+ 'vcodec': 'avc1.4D401F',
+ 'acodec': 'none',
+ 'url': 'https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/manifest.mpd',
+ 'fragment_base_url': 'https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/dash/',
+ 'protocol': 'http_dash_segments',
+ }],
+ {
+ 'en': [
+ {
+ 'ext': 'mp4',
+ 'manifest_url': 'https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/manifest.mpd',
+ 'url': 'https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/manifest.mpd',
+ 'fragment_base_url': 'https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/dash/',
+ 'protocol': 'http_dash_segments',
+ }
+ ]
+ },
+ )
+ ]
+
+ for mpd_file, mpd_url, mpd_base_url, expected_formats, expected_subtitles in _TEST_CASES:
+ with open('./test/testdata/mpd/%s.mpd' % mpd_file,
+ mode='r', encoding='utf-8') as f:
+ formats, subtitles = self.ie._parse_mpd_formats_and_subtitles(
+ compat_etree_fromstring(f.read().encode('utf-8')),
+ mpd_base_url=mpd_base_url, mpd_url=mpd_url)
+ self.ie._sort_formats(formats)
+ expect_value(self, formats, expected_formats, None)
+ expect_value(self, subtitles, expected_subtitles, None)
+
+ def test_parse_f4m_formats(self):
+ _TEST_CASES = [
+ (
+ # https://github.com/ytdl-org/youtube-dl/issues/14660
+ 'custom_base_url',
+ 'http://api.new.livestream.com/accounts/6115179/events/6764928/videos/144884262.f4m',
+ [{
+ 'manifest_url': 'http://api.new.livestream.com/accounts/6115179/events/6764928/videos/144884262.f4m',
+ 'ext': 'flv',
+ 'format_id': '2148',
+ 'protocol': 'f4m',
+ 'tbr': 2148,
+ 'width': 1280,
+ 'height': 720,
+ }]
+ ),
+ ]
+
+ for f4m_file, f4m_url, expected_formats in _TEST_CASES:
+ with open('./test/testdata/f4m/%s.f4m' % f4m_file,
+ mode='r', encoding='utf-8') as f:
+ formats = self.ie._parse_f4m_formats(
+ compat_etree_fromstring(f.read().encode('utf-8')),
+ f4m_url, None)
+ self.ie._sort_formats(formats)
+ expect_value(self, formats, expected_formats, None)
+
+ def test_parse_xspf(self):
+ _TEST_CASES = [
+ (
+ 'foo_xspf',
+ 'https://example.org/src/foo_xspf.xspf',
+ [{
+ 'id': 'foo_xspf',
+ 'title': 'Pandemonium',
+ 'description': 'Visit http://bigbrother404.bandcamp.com',
+ 'duration': 202.416,
+ 'formats': [{
+ 'manifest_url': 'https://example.org/src/foo_xspf.xspf',
+ 'url': 'https://example.org/src/cd1/track%201.mp3',
+ }],
+ }, {
+ 'id': 'foo_xspf',
+ 'title': 'Final Cartridge (Nichico Twelve Remix)',
+ 'description': 'Visit http://bigbrother404.bandcamp.com',
+ 'duration': 255.857,
+ 'formats': [{
+ 'manifest_url': 'https://example.org/src/foo_xspf.xspf',
+ 'url': 'https://example.org/%E3%83%88%E3%83%A9%E3%83%83%E3%82%AF%E3%80%80%EF%BC%92.mp3',
+ }],
+ }, {
+ 'id': 'foo_xspf',
+ 'title': 'Rebuilding Nightingale',
+ 'description': 'Visit http://bigbrother404.bandcamp.com',
+ 'duration': 287.915,
+ 'formats': [{
+ 'manifest_url': 'https://example.org/src/foo_xspf.xspf',
+ 'url': 'https://example.org/src/track3.mp3',
+ }, {
+ 'manifest_url': 'https://example.org/src/foo_xspf.xspf',
+ 'url': 'https://example.com/track3.mp3',
+ }]
+ }]
+ ),
+ ]
+
+ for xspf_file, xspf_url, expected_entries in _TEST_CASES:
+ with open('./test/testdata/xspf/%s.xspf' % xspf_file,
+ mode='r', encoding='utf-8') as f:
+ entries = self.ie._parse_xspf(
+ compat_etree_fromstring(f.read().encode('utf-8')),
+ xspf_file, xspf_url=xspf_url, xspf_base_url=xspf_url)
+ expect_value(self, entries, expected_entries, None)
+ for i in range(len(entries)):
+ expect_dict(self, entries[i], expected_entries[i])
+
+ def test_response_with_expected_status_returns_content(self):
+ # Checks for mitigations against the effects of
+ # <https://bugs.python.org/issue15002> that affect Python 3.4.1+, which
+ # manifest as `_download_webpage`, `_download_xml`, `_download_json`,
+ # or the underlying `_download_webpage_handle` returning no content
+ # when a response matches `expected_status`.
+
+ httpd = compat_http_server.HTTPServer(
+ ('127.0.0.1', 0), InfoExtractorTestRequestHandler)
+ port = http_server_port(httpd)
+ server_thread = threading.Thread(target=httpd.serve_forever)
+ server_thread.daemon = True
+ server_thread.start()
+
+ (content, urlh) = self.ie._download_webpage_handle(
+ 'http://127.0.0.1:%d/teapot' % port, None,
+ expected_status=TEAPOT_RESPONSE_STATUS)
+ self.assertEqual(content, TEAPOT_RESPONSE_BODY)
+
if __name__ == '__main__':
unittest.main()
diff --git a/test/test_YoutubeDL.py b/test/test_YoutubeDL.py
index 75945e38f..d994682b2 100644
--- a/test/test_YoutubeDL.py
+++ b/test/test_YoutubeDL.py
@@ -10,14 +10,31 @@ import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
import copy
+import json
-from test.helper import FakeYDL, assertRegexpMatches
+from test.helper import (
+ FakeYDL,
+ assertRegexpMatches,
+ try_rm,
+)
from youtube_dl import YoutubeDL
-from youtube_dl.compat import compat_str, compat_urllib_error
+from youtube_dl.compat import (
+ compat_http_cookiejar_Cookie,
+ compat_http_cookies_SimpleCookie,
+ compat_kwargs,
+ compat_open as open,
+ compat_str,
+ compat_urllib_error,
+)
+
from youtube_dl.extractor import YoutubeIE
from youtube_dl.extractor.common import InfoExtractor
from youtube_dl.postprocessor.common import PostProcessor
-from youtube_dl.utils import ExtractorError, match_filter_func
+from youtube_dl.utils import (
+ ExtractorError,
+ match_filter_func,
+ traverse_obj,
+)
TEST_URL = 'http://localhost/sample.mp4'
@@ -29,11 +46,14 @@ class YDL(FakeYDL):
self.msgs = []
def process_info(self, info_dict):
- self.downloaded_info_dicts.append(info_dict)
+ self.downloaded_info_dicts.append(info_dict.copy())
def to_screen(self, msg):
self.msgs.append(msg)
+ def dl(self, *args, **kwargs):
+ assert False, 'Downloader must not be invoked for test_YoutubeDL'
+
def _make_result(formats, **kwargs):
res = {
@@ -41,8 +61,10 @@ def _make_result(formats, **kwargs):
'id': 'testid',
'title': 'testttitle',
'extractor': 'testex',
+ 'extractor_key': 'TestEx',
+ 'webpage_url': 'http://example.com/watch?v=shenanigans',
}
- res.update(**kwargs)
+ res.update(**compat_kwargs(kwargs))
return res
@@ -238,6 +260,76 @@ class TestFormatSelection(unittest.TestCase):
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'vid-vcodec-dot')
+ def test_format_selection_string_ops(self):
+ formats = [
+ {'format_id': 'abc-cba', 'ext': 'mp4', 'url': TEST_URL},
+ {'format_id': 'zxc-cxz', 'ext': 'webm', 'url': TEST_URL},
+ ]
+ info_dict = _make_result(formats)
+
+ # equals (=)
+ ydl = YDL({'format': '[format_id=abc-cba]'})
+ ydl.process_ie_result(info_dict.copy())
+ downloaded = ydl.downloaded_info_dicts[0]
+ self.assertEqual(downloaded['format_id'], 'abc-cba')
+
+ # does not equal (!=)
+ ydl = YDL({'format': '[format_id!=abc-cba]'})
+ ydl.process_ie_result(info_dict.copy())
+ downloaded = ydl.downloaded_info_dicts[0]
+ self.assertEqual(downloaded['format_id'], 'zxc-cxz')
+
+ ydl = YDL({'format': '[format_id!=abc-cba][format_id!=zxc-cxz]'})
+ self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy())
+
+ # starts with (^=)
+ ydl = YDL({'format': '[format_id^=abc]'})
+ ydl.process_ie_result(info_dict.copy())
+ downloaded = ydl.downloaded_info_dicts[0]
+ self.assertEqual(downloaded['format_id'], 'abc-cba')
+
+ # does not start with (!^=)
+ ydl = YDL({'format': '[format_id!^=abc]'})
+ ydl.process_ie_result(info_dict.copy())
+ downloaded = ydl.downloaded_info_dicts[0]
+ self.assertEqual(downloaded['format_id'], 'zxc-cxz')
+
+ ydl = YDL({'format': '[format_id!^=abc][format_id!^=zxc]'})
+ self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy())
+
+ # ends with ($=)
+ ydl = YDL({'format': '[format_id$=cba]'})
+ ydl.process_ie_result(info_dict.copy())
+ downloaded = ydl.downloaded_info_dicts[0]
+ self.assertEqual(downloaded['format_id'], 'abc-cba')
+
+ # does not end with (!$=)
+ ydl = YDL({'format': '[format_id!$=cba]'})
+ ydl.process_ie_result(info_dict.copy())
+ downloaded = ydl.downloaded_info_dicts[0]
+ self.assertEqual(downloaded['format_id'], 'zxc-cxz')
+
+ ydl = YDL({'format': '[format_id!$=cba][format_id!$=cxz]'})
+ self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy())
+
+ # contains (*=)
+ ydl = YDL({'format': '[format_id*=bc-cb]'})
+ ydl.process_ie_result(info_dict.copy())
+ downloaded = ydl.downloaded_info_dicts[0]
+ self.assertEqual(downloaded['format_id'], 'abc-cba')
+
+ # does not contain (!*=)
+ ydl = YDL({'format': '[format_id!*=bc-cb]'})
+ ydl.process_ie_result(info_dict.copy())
+ downloaded = ydl.downloaded_info_dicts[0]
+ self.assertEqual(downloaded['format_id'], 'zxc-cxz')
+
+ ydl = YDL({'format': '[format_id!*=abc][format_id!*=zxc]'})
+ self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy())
+
+ ydl = YDL({'format': '[format_id!*=-]'})
+ self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy())
+
def test_youtube_format_selection(self):
order = [
'38', '37', '46', '22', '45', '35', '44', '18', '34', '43', '6', '5', '17', '36', '13',
@@ -340,7 +432,7 @@ class TestFormatSelection(unittest.TestCase):
# For extractors with incomplete formats (all formats are audio-only or
# video-only) best and worst should fallback to corresponding best/worst
# video-only or audio-only formats (as per
- # https://github.com/rg3/youtube-dl/pull/5556)
+ # https://github.com/ytdl-org/youtube-dl/pull/5556)
formats = [
{'format_id': 'low', 'ext': 'mp3', 'preference': 1, 'vcodec': 'none', 'url': TEST_URL},
{'format_id': 'high', 'ext': 'mp3', 'preference': 2, 'vcodec': 'none', 'url': TEST_URL},
@@ -370,6 +462,19 @@ class TestFormatSelection(unittest.TestCase):
ydl = YDL({'format': 'best[height>360]'})
self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy())
+ def test_format_selection_issue_10083(self):
+ # See https://github.com/ytdl-org/youtube-dl/issues/10083
+ formats = [
+ {'format_id': 'regular', 'height': 360, 'url': TEST_URL},
+ {'format_id': 'video', 'height': 720, 'acodec': 'none', 'url': TEST_URL},
+ {'format_id': 'audio', 'vcodec': 'none', 'url': TEST_URL},
+ ]
+ info_dict = _make_result(formats)
+
+ ydl = YDL({'format': 'best[height>360]/bestvideo[height>360]+bestaudio'})
+ ydl.process_ie_result(info_dict.copy())
+ self.assertEqual(ydl.downloaded_info_dicts[0]['format_id'], 'video+audio')
+
def test_invalid_format_specs(self):
def assert_syntax_error(format_spec):
ydl = YDL({'format': format_spec})
@@ -380,6 +485,7 @@ class TestFormatSelection(unittest.TestCase):
assert_syntax_error('+bestaudio')
assert_syntax_error('bestvideo+')
assert_syntax_error('/')
+ assert_syntax_error('bestvideo+bestvideo+bestaudio')
def test_format_filtering(self):
formats = [
@@ -448,6 +554,23 @@ class TestFormatSelection(unittest.TestCase):
pass
self.assertEqual(ydl.downloaded_info_dicts, [])
+ def test_default_format_spec(self):
+ ydl = YDL({'simulate': True})
+ self.assertEqual(ydl._default_format_spec({}), 'bestvideo+bestaudio/best')
+
+ ydl = YDL({})
+ self.assertEqual(ydl._default_format_spec({'is_live': True}), 'best/bestvideo+bestaudio')
+
+ ydl = YDL({'simulate': True})
+ self.assertEqual(ydl._default_format_spec({'is_live': True}), 'bestvideo+bestaudio/best')
+
+ ydl = YDL({'outtmpl': '-'})
+ self.assertEqual(ydl._default_format_spec({}), 'best/bestvideo+bestaudio')
+
+ ydl = YDL({})
+ self.assertEqual(ydl._default_format_spec({}, download=False), 'bestvideo+bestaudio/best')
+ self.assertEqual(ydl._default_format_spec({'is_live': True}), 'best/bestvideo+bestaudio')
+
class TestYoutubeDL(unittest.TestCase):
def test_subtitles(self):
@@ -527,15 +650,24 @@ class TestYoutubeDL(unittest.TestCase):
'ext': 'mp4',
'width': None,
'height': 1080,
+ 'title1': '$PATH',
+ 'title2': '%PATH%',
}
- def fname(templ):
- ydl = YoutubeDL({'outtmpl': templ})
+ def fname(templ, na_placeholder='NA'):
+ params = {'outtmpl': templ}
+ if na_placeholder != 'NA':
+ params['outtmpl_na_placeholder'] = na_placeholder
+ ydl = YoutubeDL(params)
return ydl.prepare_filename(info)
self.assertEqual(fname('%(id)s.%(ext)s'), '1234.mp4')
self.assertEqual(fname('%(id)s-%(width)s.%(ext)s'), '1234-NA.mp4')
- # Replace missing fields with 'NA'
- self.assertEqual(fname('%(uploader_date)s-%(id)s.%(ext)s'), 'NA-1234.mp4')
+ NA_TEST_OUTTMPL = '%(uploader_date)s-%(width)d-%(id)s.%(ext)s'
+ # Replace missing fields with 'NA' by default
+ self.assertEqual(fname(NA_TEST_OUTTMPL), 'NA-NA-1234.mp4')
+ # Or by provided placeholder
+ self.assertEqual(fname(NA_TEST_OUTTMPL, na_placeholder='none'), 'none-none-1234.mp4')
+ self.assertEqual(fname(NA_TEST_OUTTMPL, na_placeholder=''), '--1234.mp4')
self.assertEqual(fname('%(height)d.%(ext)s'), '1080.mp4')
self.assertEqual(fname('%(height)6d.%(ext)s'), ' 1080.mp4')
self.assertEqual(fname('%(height)-6d.%(ext)s'), '1080 .mp4')
@@ -545,10 +677,14 @@ class TestYoutubeDL(unittest.TestCase):
self.assertEqual(fname('%(height)0 6d.%(ext)s'), ' 01080.mp4')
self.assertEqual(fname('%(height)0 6d.%(ext)s'), ' 01080.mp4')
self.assertEqual(fname('%(height) 0 6d.%(ext)s'), ' 01080.mp4')
+ self.assertEqual(fname('%%'), '%')
+ self.assertEqual(fname('%%%%'), '%%')
self.assertEqual(fname('%%(height)06d.%(ext)s'), '%(height)06d.mp4')
self.assertEqual(fname('%(width)06d.%(ext)s'), 'NA.mp4')
self.assertEqual(fname('%(width)06d.%%(ext)s'), 'NA.%(ext)s')
self.assertEqual(fname('%%(width)06d.%(ext)s'), '%(width)06d.mp4')
+ self.assertEqual(fname('Hello %(title1)s'), 'Hello $PATH')
+ self.assertEqual(fname('Hello %(title2)s'), 'Hello %PATH%')
def test_format_note(self):
ydl = YoutubeDL()
@@ -566,12 +702,12 @@ class TestYoutubeDL(unittest.TestCase):
class SimplePP(PostProcessor):
def run(self, info):
- with open(audiofile, 'wt') as f:
+ with open(audiofile, 'w') as f:
f.write('EXAMPLE')
return [info['filepath']], info
def run_pp(params, PP):
- with open(filename, 'wt') as f:
+ with open(filename, 'w') as f:
f.write('EXAMPLE')
ydl = YoutubeDL(params)
ydl.add_post_processor(PP())
@@ -590,7 +726,7 @@ class TestYoutubeDL(unittest.TestCase):
class ModifierPP(PostProcessor):
def run(self, info):
- with open(info['filepath'], 'wt') as f:
+ with open(info['filepath'], 'w') as f:
f.write('MODIFIED')
return [], info
@@ -709,11 +845,15 @@ class TestYoutubeDL(unittest.TestCase):
'webpage_url': 'http://example.com',
}
- def get_ids(params):
+ def get_downloaded_info_dicts(params):
ydl = YDL(params)
- # make a copy because the dictionary can be modified
- ydl.process_ie_result(playlist.copy())
- return [int(v['id']) for v in ydl.downloaded_info_dicts]
+ # make a deep copy because the dictionary and nested entries
+ # can be modified
+ ydl.process_ie_result(copy.deepcopy(playlist))
+ return ydl.downloaded_info_dicts
+
+ def get_ids(params):
+ return [int(v['id']) for v in get_downloaded_info_dicts(params)]
result = get_ids({})
self.assertEqual(result, [1, 2, 3, 4])
@@ -739,8 +879,30 @@ class TestYoutubeDL(unittest.TestCase):
result = get_ids({'playlist_items': '10'})
self.assertEqual(result, [])
+ result = get_ids({'playlist_items': '3-10'})
+ self.assertEqual(result, [3, 4])
+
+ result = get_ids({'playlist_items': '2-4,3-4,3'})
+ self.assertEqual(result, [2, 3, 4])
+
+ # Tests for https://github.com/ytdl-org/youtube-dl/issues/10591
+ # @{
+ result = get_downloaded_info_dicts({'playlist_items': '2-4,3-4,3'})
+ self.assertEqual(result[0]['playlist_index'], 2)
+ self.assertEqual(result[1]['playlist_index'], 3)
+
+ result = get_downloaded_info_dicts({'playlist_items': '2-4,3-4,3'})
+ self.assertEqual(result[0]['playlist_index'], 2)
+ self.assertEqual(result[1]['playlist_index'], 3)
+ self.assertEqual(result[2]['playlist_index'], 4)
+
+ result = get_downloaded_info_dicts({'playlist_items': '4,2'})
+ self.assertEqual(result[0]['playlist_index'], 4)
+ self.assertEqual(result[1]['playlist_index'], 2)
+ # @}
+
def test_urlopen_no_file_protocol(self):
- # see https://github.com/rg3/youtube-dl/issues/8227
+ # see https://github.com/ytdl-org/youtube-dl/issues/8227
ydl = YDL()
self.assertRaises(compat_urllib_error.URLError, ydl.urlopen, 'file:///etc/passwd')
@@ -755,7 +917,8 @@ class TestYoutubeDL(unittest.TestCase):
'_type': 'url_transparent',
'url': 'foo2:',
'ie_key': 'Foo2',
- 'title': 'foo1 title'
+ 'title': 'foo1 title',
+ 'id': 'foo1_id',
}
class Foo2IE(InfoExtractor):
@@ -781,6 +944,247 @@ class TestYoutubeDL(unittest.TestCase):
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['url'], TEST_URL)
self.assertEqual(downloaded['title'], 'foo1 title')
+ self.assertEqual(downloaded['id'], 'testid')
+ self.assertEqual(downloaded['extractor'], 'testex')
+ self.assertEqual(downloaded['extractor_key'], 'TestEx')
+
+ # Test case for https://github.com/ytdl-org/youtube-dl/issues/27064
+ def test_ignoreerrors_for_playlist_with_url_transparent_iterable_entries(self):
+
+ ydl = YDL({
+ 'format': 'extra',
+ 'ignoreerrors': True,
+ })
+ ydl.trouble = lambda *_, **__: None
+
+ class VideoIE(InfoExtractor):
+ _VALID_URL = r'video:(?P<id>\d+)'
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+ formats = [{
+ 'format_id': 'default',
+ 'url': 'url:',
+ }]
+ if video_id == '0':
+ raise ExtractorError('foo')
+ if video_id == '2':
+ formats.append({
+ 'format_id': 'extra',
+ 'url': TEST_URL,
+ })
+ return {
+ 'id': video_id,
+ 'title': 'Video %s' % video_id,
+ 'formats': formats,
+ }
+
+ class PlaylistIE(InfoExtractor):
+ _VALID_URL = r'playlist:'
+
+ def _entries(self):
+ for n in range(3):
+ video_id = compat_str(n)
+ yield {
+ '_type': 'url_transparent',
+ 'ie_key': VideoIE.ie_key(),
+ 'id': video_id,
+ 'url': 'video:%s' % video_id,
+ 'title': 'Video Transparent %s' % video_id,
+ }
+
+ def _real_extract(self, url):
+ return self.playlist_result(self._entries())
+
+ ydl.add_info_extractor(VideoIE(ydl))
+ ydl.add_info_extractor(PlaylistIE(ydl))
+ info = ydl.extract_info('playlist:')
+ entries = info['entries']
+ self.assertEqual(len(entries), 3)
+ self.assertTrue(entries[0] is None)
+ self.assertTrue(entries[1] is None)
+ self.assertEqual(len(ydl.downloaded_info_dicts), 1)
+ downloaded = ydl.downloaded_info_dicts[0]
+ self.assertEqual(entries[2], downloaded)
+ self.assertEqual(downloaded['url'], TEST_URL)
+ self.assertEqual(downloaded['title'], 'Video Transparent 2')
+ self.assertEqual(downloaded['id'], '2')
+ self.assertEqual(downloaded['extractor'], 'Video')
+ self.assertEqual(downloaded['extractor_key'], 'Video')
+
+ def test_default_times(self):
+ """Test addition of missing upload/release/_date from /release_/timestamp"""
+ info = {
+ 'id': '1234',
+ 'url': TEST_URL,
+ 'title': 'Title',
+ 'ext': 'mp4',
+ 'timestamp': 1631352900,
+ 'release_timestamp': 1632995931,
+ }
+
+ params = {'simulate': True, }
+ ydl = FakeYDL(params)
+ out_info = ydl.process_ie_result(info)
+ self.assertTrue(isinstance(out_info['upload_date'], compat_str))
+ self.assertEqual(out_info['upload_date'], '20210911')
+ self.assertTrue(isinstance(out_info['release_date'], compat_str))
+ self.assertEqual(out_info['release_date'], '20210930')
+
+
+class TestYoutubeDLCookies(unittest.TestCase):
+
+ @staticmethod
+ def encode_cookie(cookie):
+ if not isinstance(cookie, dict):
+ cookie = vars(cookie)
+ for name, value in cookie.items():
+ yield name, compat_str(value)
+
+ @classmethod
+ def comparable_cookies(cls, cookies):
+ # Work around cookiejar cookies not being unicode strings
+ return sorted(map(tuple, map(sorted, map(cls.encode_cookie, cookies))))
+
+ def assertSameCookies(self, c1, c2, msg=None):
+ return self.assertEqual(
+ *map(self.comparable_cookies, (c1, c2)),
+ msg=msg)
+
+ def assertSameCookieStrings(self, c1, c2, msg=None):
+ return self.assertSameCookies(
+ *map(lambda c: compat_http_cookies_SimpleCookie(c).values(), (c1, c2)),
+ msg=msg)
+
+ def test_header_cookies(self):
+
+ ydl = FakeYDL()
+ ydl.report_warning = lambda *_, **__: None
+
+ def cookie(name, value, version=None, domain='', path='', secure=False, expires=None):
+ return compat_http_cookiejar_Cookie(
+ version or 0, name, value, None, False,
+ domain, bool(domain), bool(domain), path, bool(path),
+ secure, expires, False, None, None, rest={})
+
+ test_url, test_domain = (t % ('yt.dl',) for t in ('https://%s/test', '.%s'))
+
+ def test(encoded_cookies, cookies, headers=False, round_trip=None, error_re=None):
+ def _test():
+ ydl.cookiejar.clear()
+ ydl._load_cookies(encoded_cookies, autoscope=headers)
+ if headers:
+ ydl._apply_header_cookies(test_url)
+ data = {'url': test_url}
+ ydl._calc_headers(data)
+ self.assertSameCookies(
+ cookies, ydl.cookiejar,
+ 'Extracted cookiejar.Cookie is not the same')
+ if not headers:
+ self.assertSameCookieStrings(
+ data.get('cookies'), round_trip or encoded_cookies,
+ msg='Cookie is not the same as round trip')
+ ydl.__dict__['_YoutubeDL__header_cookies'] = []
+
+ try:
+ _test()
+ except AssertionError:
+ raise
+ except Exception as e:
+ if not error_re:
+ raise
+ assertRegexpMatches(self, e.args[0], error_re.join(('.*',) * 2))
+
+ test('test=value; Domain=' + test_domain, [cookie('test', 'value', domain=test_domain)])
+ test('test=value', [cookie('test', 'value')], error_re='Unscoped cookies are not allowed')
+ test('cookie1=value1; Domain={0}; Path=/test; cookie2=value2; Domain={0}; Path=/'.format(test_domain), [
+ cookie('cookie1', 'value1', domain=test_domain, path='/test'),
+ cookie('cookie2', 'value2', domain=test_domain, path='/')])
+ cookie_kw = compat_kwargs(
+ {'domain': test_domain, 'path': '/test', 'secure': True, 'expires': '9999999999', })
+ test('test=value; Domain={domain}; Path={path}; Secure; Expires={expires}'.format(**cookie_kw), [
+ cookie('test', 'value', **cookie_kw)])
+ test('test="value; "; path=/test; domain=' + test_domain, [
+ cookie('test', 'value; ', domain=test_domain, path='/test')],
+ round_trip='test="value\\073 "; Domain={0}; Path=/test'.format(test_domain))
+ test('name=; Domain=' + test_domain, [cookie('name', '', domain=test_domain)],
+ round_trip='name=""; Domain=' + test_domain)
+ test('test=value', [cookie('test', 'value', domain=test_domain)], headers=True)
+ test('cookie1=value; Domain={0}; cookie2=value'.format(test_domain), [],
+ headers=True, error_re='Invalid syntax')
+ ydl.report_warning = ydl.report_error
+ test('test=value', [], headers=True, error_re='Passing cookies as a header is a potential security risk')
+
+ def test_infojson_cookies(self):
+ TEST_FILE = 'test_infojson_cookies.info.json'
+ TEST_URL = 'https://example.com/example.mp4'
+ COOKIES = 'a=b; Domain=.example.com; c=d; Domain=.example.com'
+ COOKIE_HEADER = {'Cookie': 'a=b; c=d'}
+
+ ydl = FakeYDL()
+ ydl.process_info = lambda x: ydl._write_info_json('test', x, TEST_FILE)
+
+ def make_info(info_header_cookies=False, fmts_header_cookies=False, cookies_field=False):
+ fmt = {'url': TEST_URL}
+ if fmts_header_cookies:
+ fmt['http_headers'] = COOKIE_HEADER
+ if cookies_field:
+ fmt['cookies'] = COOKIES
+ return _make_result([fmt], http_headers=COOKIE_HEADER if info_header_cookies else None)
+
+ def test(initial_info, note):
+
+ def failure_msg(why):
+ return ' when '.join((why, note))
+
+ result = {}
+ result['processed'] = ydl.process_ie_result(initial_info)
+ self.assertTrue(ydl.cookiejar.get_cookies_for_url(TEST_URL),
+ msg=failure_msg('No cookies set in cookiejar after initial process'))
+ ydl.cookiejar.clear()
+ with open(TEST_FILE) as infojson:
+ result['loaded'] = ydl.sanitize_info(json.load(infojson), True)
+ result['final'] = ydl.process_ie_result(result['loaded'].copy(), download=False)
+ self.assertTrue(ydl.cookiejar.get_cookies_for_url(TEST_URL),
+ msg=failure_msg('No cookies set in cookiejar after final process'))
+ ydl.cookiejar.clear()
+ for key in ('processed', 'loaded', 'final'):
+ info = result[key]
+ self.assertIsNone(
+ traverse_obj(info, ((None, ('formats', 0)), 'http_headers', 'Cookie'), casesense=False, get_all=False),
+ msg=failure_msg('Cookie header not removed in {0} result'.format(key)))
+ self.assertSameCookieStrings(
+ traverse_obj(info, ((None, ('formats', 0)), 'cookies'), get_all=False), COOKIES,
+ msg=failure_msg('No cookies field found in {0} result'.format(key)))
+
+ test({'url': TEST_URL, 'http_headers': COOKIE_HEADER, 'id': '1', 'title': 'x'}, 'no formats field')
+ test(make_info(info_header_cookies=True), 'info_dict header cokies')
+ test(make_info(fmts_header_cookies=True), 'format header cookies')
+ test(make_info(info_header_cookies=True, fmts_header_cookies=True), 'info_dict and format header cookies')
+ test(make_info(info_header_cookies=True, fmts_header_cookies=True, cookies_field=True), 'all cookies fields')
+ test(make_info(cookies_field=True), 'cookies format field')
+ test({'url': TEST_URL, 'cookies': COOKIES, 'id': '1', 'title': 'x'}, 'info_dict cookies field only')
+
+ try_rm(TEST_FILE)
+
+ def test_add_headers_cookie(self):
+ def check_for_cookie_header(result):
+ return traverse_obj(result, ((None, ('formats', 0)), 'http_headers', 'Cookie'), casesense=False, get_all=False)
+
+ ydl = FakeYDL({'http_headers': {'Cookie': 'a=b'}})
+ ydl._apply_header_cookies(_make_result([])['webpage_url']) # Scope to input webpage URL: .example.com
+
+ fmt = {'url': 'https://example.com/video.mp4'}
+ result = ydl.process_ie_result(_make_result([fmt]), download=False)
+ self.assertIsNone(check_for_cookie_header(result), msg='http_headers cookies in result info_dict')
+ self.assertEqual(result.get('cookies'), 'a=b; Domain=.example.com', msg='No cookies were set in cookies field')
+ self.assertIn('a=b', ydl.cookiejar.get_cookie_header(fmt['url']), msg='No cookies were set in cookiejar')
+
+ fmt = {'url': 'https://wrong.com/video.mp4'}
+ result = ydl.process_ie_result(_make_result([fmt]), download=False)
+ self.assertIsNone(check_for_cookie_header(result), msg='http_headers cookies for wrong domain')
+ self.assertFalse(result.get('cookies'), msg='Cookies set in cookies field for wrong domain')
+ self.assertFalse(ydl.cookiejar.get_cookie_header(fmt['url']), msg='Cookies set in cookiejar for wrong domain')
if __name__ == '__main__':
diff --git a/test/test_YoutubeDLCookieJar.py b/test/test_YoutubeDLCookieJar.py
new file mode 100644
index 000000000..4f9dd71ae
--- /dev/null
+++ b/test/test_YoutubeDLCookieJar.py
@@ -0,0 +1,65 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+from __future__ import unicode_literals
+
+import os
+import re
+import sys
+import tempfile
+import unittest
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from youtube_dl.utils import YoutubeDLCookieJar
+
+
+class TestYoutubeDLCookieJar(unittest.TestCase):
+ def test_keep_session_cookies(self):
+ cookiejar = YoutubeDLCookieJar('./test/testdata/cookies/session_cookies.txt')
+ cookiejar.load(ignore_discard=True, ignore_expires=True)
+ tf = tempfile.NamedTemporaryFile(delete=False)
+ try:
+ cookiejar.save(filename=tf.name, ignore_discard=True, ignore_expires=True)
+ temp = tf.read().decode('utf-8')
+ self.assertTrue(re.search(
+ r'www\.foobar\.foobar\s+FALSE\s+/\s+TRUE\s+0\s+YoutubeDLExpiresEmpty\s+YoutubeDLExpiresEmptyValue', temp))
+ self.assertTrue(re.search(
+ r'www\.foobar\.foobar\s+FALSE\s+/\s+TRUE\s+0\s+YoutubeDLExpires0\s+YoutubeDLExpires0Value', temp))
+ finally:
+ tf.close()
+ os.remove(tf.name)
+
+ def test_strip_httponly_prefix(self):
+ cookiejar = YoutubeDLCookieJar('./test/testdata/cookies/httponly_cookies.txt')
+ cookiejar.load(ignore_discard=True, ignore_expires=True)
+
+ def assert_cookie_has_value(key):
+ self.assertEqual(cookiejar._cookies['www.foobar.foobar']['/'][key].value, key + '_VALUE')
+
+ assert_cookie_has_value('HTTPONLY_COOKIE')
+ assert_cookie_has_value('JS_ACCESSIBLE_COOKIE')
+
+ def test_malformed_cookies(self):
+ cookiejar = YoutubeDLCookieJar('./test/testdata/cookies/malformed_cookies.txt')
+ cookiejar.load(ignore_discard=True, ignore_expires=True)
+ # Cookies should be empty since all malformed cookie file entries
+ # will be ignored
+ self.assertFalse(cookiejar._cookies)
+
+ def test_get_cookie_header(self):
+ cookiejar = YoutubeDLCookieJar('./test/testdata/cookies/httponly_cookies.txt')
+ cookiejar.load(ignore_discard=True, ignore_expires=True)
+ header = cookiejar.get_cookie_header('https://www.foobar.foobar')
+ self.assertIn('HTTPONLY_COOKIE', header)
+
+ def test_get_cookies_for_url(self):
+ cookiejar = YoutubeDLCookieJar('./test/testdata/cookies/session_cookies.txt')
+ cookiejar.load(ignore_discard=True, ignore_expires=True)
+ cookies = cookiejar.get_cookies_for_url('https://www.foobar.foobar/')
+ self.assertEqual(len(cookies), 2)
+ cookies = cookiejar.get_cookies_for_url('https://foobar.foobar/')
+ self.assertFalse(cookies)
+
+
+if __name__ == '__main__':
+ unittest.main()
diff --git a/test/test_aes.py b/test/test_aes.py
index 78a28751b..0f181466b 100644
--- a/test/test_aes.py
+++ b/test/test_aes.py
@@ -8,7 +8,7 @@ import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-from youtube_dl.aes import aes_decrypt, aes_encrypt, aes_cbc_decrypt, aes_cbc_encrypt, aes_decrypt_text
+from youtube_dl.aes import aes_decrypt, aes_encrypt, aes_cbc_decrypt, aes_cbc_encrypt, aes_decrypt_text, aes_ecb_encrypt
from youtube_dl.utils import bytes_to_intlist, intlist_to_bytes
import base64
@@ -44,20 +44,27 @@ class TestAES(unittest.TestCase):
def test_decrypt_text(self):
password = intlist_to_bytes(self.key).decode('utf-8')
encrypted = base64.b64encode(
- intlist_to_bytes(self.iv[:8]) +
- b'\x17\x15\x93\xab\x8d\x80V\xcdV\xe0\t\xcdo\xc2\xa5\xd8ksM\r\xe27N\xae'
+ intlist_to_bytes(self.iv[:8])
+ + b'\x17\x15\x93\xab\x8d\x80V\xcdV\xe0\t\xcdo\xc2\xa5\xd8ksM\r\xe27N\xae'
).decode('utf-8')
decrypted = (aes_decrypt_text(encrypted, password, 16))
self.assertEqual(decrypted, self.secret_msg)
password = intlist_to_bytes(self.key).decode('utf-8')
encrypted = base64.b64encode(
- intlist_to_bytes(self.iv[:8]) +
- b'\x0b\xe6\xa4\xd9z\x0e\xb8\xb9\xd0\xd4i_\x85\x1d\x99\x98_\xe5\x80\xe7.\xbf\xa5\x83'
+ intlist_to_bytes(self.iv[:8])
+ + b'\x0b\xe6\xa4\xd9z\x0e\xb8\xb9\xd0\xd4i_\x85\x1d\x99\x98_\xe5\x80\xe7.\xbf\xa5\x83'
).decode('utf-8')
decrypted = (aes_decrypt_text(encrypted, password, 32))
self.assertEqual(decrypted, self.secret_msg)
+ def test_ecb_encrypt(self):
+ data = bytes_to_intlist(self.secret_msg)
+ encrypted = intlist_to_bytes(aes_ecb_encrypt(data, self.key))
+ self.assertEqual(
+ encrypted,
+ b'\xaa\x86]\x81\x97>\x02\x92\x9d\x1bR[[L/u\xd3&\xd1(h\xde{\x81\x94\xba\x02\xae\xbd\xa6\xd0:')
+
if __name__ == '__main__':
unittest.main()
diff --git a/test/test_age_restriction.py b/test/test_age_restriction.py
index 6f5513faa..db98494ab 100644
--- a/test/test_age_restriction.py
+++ b/test/test_age_restriction.py
@@ -11,6 +11,7 @@ from test.helper import try_rm
from youtube_dl import YoutubeDL
+from youtube_dl.utils import DownloadError
def _download_restricted(url, filename, age):
@@ -26,7 +27,10 @@ def _download_restricted(url, filename, age):
ydl.add_default_info_extractors()
json_filename = os.path.splitext(filename)[0] + '.info.json'
try_rm(json_filename)
- ydl.download([url])
+ try:
+ ydl.download([url])
+ except DownloadError:
+ try_rm(json_filename)
res = os.path.exists(json_filename)
try_rm(json_filename)
return res
@@ -38,12 +42,12 @@ class TestAgeRestriction(unittest.TestCase):
self.assertFalse(_download_restricted(url, filename, age))
def test_youtube(self):
- self._assert_restricted('07FYdnEawAQ', '07FYdnEawAQ.mp4', 10)
+ self._assert_restricted('HtVdAasjOgU', 'HtVdAasjOgU.mp4', 10)
def test_youporn(self):
self._assert_restricted(
- 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
- '505835.mp4', 2, old_age=25)
+ 'https://www.youporn.com/watch/16715086/sex-ed-in-detention-18-asmr/',
+ '16715086.mp4', 2, old_age=25)
if __name__ == '__main__':
diff --git a/test/test_all_urls.py b/test/test_all_urls.py
index cd1cd4b24..26df356b4 100644
--- a/test/test_all_urls.py
+++ b/test/test_all_urls.py
@@ -31,16 +31,17 @@ class TestAllURLsMatching(unittest.TestCase):
def test_youtube_playlist_matching(self):
assertPlaylist = lambda url: self.assertMatch(url, ['youtube:playlist'])
+ assertTab = lambda url: self.assertMatch(url, ['youtube:tab'])
assertPlaylist('ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
assertPlaylist('UUBABnxM4Ar9ten8Mdjj1j0Q') # 585
assertPlaylist('PL63F0C78739B09958')
- assertPlaylist('https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q')
- assertPlaylist('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
- assertPlaylist('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')
- assertPlaylist('https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012') # 668
+ assertTab('https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q')
+ assertTab('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
+ assertTab('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')
+ assertTab('https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012') # 668
self.assertFalse('youtube:playlist' in self.matching_ies('PLtS2H6bU1M'))
# Top tracks
- assertPlaylist('https://www.youtube.com/playlist?list=MCUS.20142101')
+ assertTab('https://www.youtube.com/playlist?list=MCUS.20142101')
def test_youtube_matching(self):
self.assertTrue(YoutubeIE.suitable('PLtS2H6bU1M'))
@@ -51,36 +52,24 @@ class TestAllURLsMatching(unittest.TestCase):
self.assertMatch('http://www.cleanvideosearch.com/media/action/yt/watch?videoId=8v_4O44sfjM', ['youtube'])
def test_youtube_channel_matching(self):
- assertChannel = lambda url: self.assertMatch(url, ['youtube:channel'])
+ assertChannel = lambda url: self.assertMatch(url, ['youtube:tab'])
assertChannel('https://www.youtube.com/channel/HCtnHdj3df7iM')
assertChannel('https://www.youtube.com/channel/HCtnHdj3df7iM?feature=gb_ch_rec')
assertChannel('https://www.youtube.com/channel/HCtnHdj3df7iM/videos')
def test_youtube_user_matching(self):
- self.assertMatch('http://www.youtube.com/NASAgovVideo/videos', ['youtube:user'])
+ self.assertMatch('http://www.youtube.com/NASAgovVideo/videos', ['youtube:tab'])
def test_youtube_feeds(self):
- self.assertMatch('https://www.youtube.com/feed/watch_later', ['youtube:watchlater'])
- self.assertMatch('https://www.youtube.com/feed/subscriptions', ['youtube:subscriptions'])
- self.assertMatch('https://www.youtube.com/feed/recommended', ['youtube:recommended'])
- self.assertMatch('https://www.youtube.com/my_favorites', ['youtube:favorites'])
-
- def test_youtube_show_matching(self):
- self.assertMatch('http://www.youtube.com/show/airdisasters', ['youtube:show'])
+ self.assertMatch('https://www.youtube.com/feed/library', ['youtube:tab'])
+ self.assertMatch('https://www.youtube.com/feed/history', ['youtube:tab'])
+ self.assertMatch('https://www.youtube.com/feed/watch_later', ['youtube:tab'])
+ self.assertMatch('https://www.youtube.com/feed/subscriptions', ['youtube:tab'])
def test_youtube_search_matching(self):
self.assertMatch('http://www.youtube.com/results?search_query=making+mustard', ['youtube:search_url'])
self.assertMatch('https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', ['youtube:search_url'])
- def test_youtube_extract(self):
- assertExtractId = lambda url, id: self.assertEqual(YoutubeIE.extract_id(url), id)
- assertExtractId('http://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
- assertExtractId('https://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
- assertExtractId('https://www.youtube.com/watch?feature=player_embedded&v=BaW_jenozKc', 'BaW_jenozKc')
- assertExtractId('https://www.youtube.com/watch_popup?v=BaW_jenozKc', 'BaW_jenozKc')
- assertExtractId('http://www.youtube.com/watch?v=BaW_jenozKcsharePLED17F32AD9753930', 'BaW_jenozKc')
- assertExtractId('BaW_jenozKc', 'BaW_jenozKc')
-
def test_facebook_matching(self):
self.assertTrue(FacebookIE.suitable('https://www.facebook.com/Shiniknoh#!/photo.php?v=10153317450565268'))
self.assertTrue(FacebookIE.suitable('https://www.facebook.com/cindyweather?fref=ts#!/photo.php?v=10152183998945793'))
@@ -110,7 +99,7 @@ class TestAllURLsMatching(unittest.TestCase):
self.assertMatch('https://vimeo.com/user7108434/videos', ['vimeo:user'])
self.assertMatch('https://vimeo.com/user21297594/review/75524534/3c257a1b5d', ['vimeo:review'])
- # https://github.com/rg3/youtube-dl/issues/1930
+ # https://github.com/ytdl-org/youtube-dl/issues/1930
def test_soundcloud_not_matching_sets(self):
self.assertMatch('http://soundcloud.com/floex/sets/gone-ep', ['soundcloud:set'])
@@ -119,16 +108,10 @@ class TestAllURLsMatching(unittest.TestCase):
self.assertMatch('http://tatianamaslanydaily.tumblr.com/post/54196191430', ['Tumblr'])
def test_pbs(self):
- # https://github.com/rg3/youtube-dl/issues/2350
+ # https://github.com/ytdl-org/youtube-dl/issues/2350
self.assertMatch('http://video.pbs.org/viralplayer/2365173446/', ['pbs'])
self.assertMatch('http://video.pbs.org/widget/partnerplayer/980042464/', ['pbs'])
- def test_yahoo_https(self):
- # https://github.com/rg3/youtube-dl/issues/2701
- self.assertMatch(
- 'https://screen.yahoo.com/smartwatches-latest-wearable-gadgets-163745379-cbs.html',
- ['Yahoo'])
-
def test_no_duplicated_ie_names(self):
name_accu = collections.defaultdict(list)
for ie in self.ies:
diff --git a/test/test_cache.py b/test/test_cache.py
index a16160142..0431f4f15 100644
--- a/test/test_cache.py
+++ b/test/test_cache.py
@@ -3,17 +3,18 @@
from __future__ import unicode_literals
-import shutil
-
# Allow direct execution
import os
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+import shutil
from test.helper import FakeYDL
from youtube_dl.cache import Cache
+from youtube_dl.utils import version_tuple
+from youtube_dl.version import __version__
def _is_empty(d):
@@ -54,6 +55,29 @@ class TestCache(unittest.TestCase):
self.assertFalse(os.path.exists(self.test_dir))
self.assertEqual(c.load('test_cache', 'k.'), None)
+ def test_cache_validation(self):
+ ydl = FakeYDL({
+ 'cachedir': self.test_dir,
+ })
+ c = Cache(ydl)
+ obj = {'x': 1, 'y': ['ä', '\\a', True]}
+ c.store('test_cache', 'k.', obj)
+ self.assertEqual(c.load('test_cache', 'k.', min_ver='1970.01.01'), obj)
+ new_version = '.'.join(('%0.2d' % ((v + 1) if i == 0 else v, )) for i, v in enumerate(version_tuple(__version__)))
+ self.assertIs(c.load('test_cache', 'k.', min_ver=new_version), None)
+
+ def test_cache_clear(self):
+ ydl = FakeYDL({
+ 'cachedir': self.test_dir,
+ })
+ c = Cache(ydl)
+ c.store('test_cache', 'k.', 'kay')
+ c.store('test_cache', 'l.', 'ell')
+ self.assertEqual(c.load('test_cache', 'k.'), 'kay')
+ c.clear('test_cache', 'k.')
+ self.assertEqual(c.load('test_cache', 'k.'), None)
+ self.assertEqual(c.load('test_cache', 'l.'), 'ell')
+
if __name__ == '__main__':
unittest.main()
diff --git a/test/test_compat.py b/test/test_compat.py
index d6c54e135..b83c8cb41 100644
--- a/test/test_compat.py
+++ b/test/test_compat.py
@@ -11,8 +11,10 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from youtube_dl.compat import (
+ compat_casefold,
compat_getenv,
compat_setenv,
+ compat_etree_Element,
compat_etree_fromstring,
compat_expanduser,
compat_shlex_split,
@@ -21,6 +23,7 @@ from youtube_dl.compat import (
compat_urllib_parse_unquote,
compat_urllib_parse_unquote_plus,
compat_urllib_parse_urlencode,
+ compat_urllib_request,
)
@@ -39,17 +42,18 @@ class TestCompat(unittest.TestCase):
def test_compat_expanduser(self):
old_home = os.environ.get('HOME')
- test_str = 'C:\Documents and Settings\тест\Application Data'
+ test_str = r'C:\Documents and Settings\тест\Application Data'
compat_setenv('HOME', test_str)
self.assertEqual(compat_expanduser('~'), test_str)
compat_setenv('HOME', old_home or '')
def test_all_present(self):
import youtube_dl.compat
- all_names = youtube_dl.compat.__all__
- present_names = set(filter(
+ all_names = sorted(
+ youtube_dl.compat.__all__ + youtube_dl.compat.legacy)
+ present_names = set(map(compat_str, filter(
lambda c: '_' in c and not c.startswith('_'),
- dir(youtube_dl.compat))) - set(['unicode_literals'])
+ dir(youtube_dl.compat)))) - set(['unicode_literals'])
self.assertEqual(all_names, sorted(present_names))
def test_compat_urllib_parse_unquote(self):
@@ -90,6 +94,12 @@ class TestCompat(unittest.TestCase):
self.assertEqual(compat_shlex_split('-option "one\ntwo" \n -flag'), ['-option', 'one\ntwo', '-flag'])
self.assertEqual(compat_shlex_split('-val 中文'), ['-val', '中文'])
+ def test_compat_etree_Element(self):
+ try:
+ compat_etree_Element.items
+ except AttributeError:
+ self.fail('compat_etree_Element is not a type')
+
def test_compat_etree_fromstring(self):
xml = '''
<root foo="bar" spam="中文">
@@ -111,9 +121,34 @@ class TestCompat(unittest.TestCase):
<smil xmlns="http://www.w3.org/2001/SMIL20/Language"></smil>'''
compat_etree_fromstring(xml)
- def test_struct_unpack(self):
+ def test_compat_struct_unpack(self):
self.assertEqual(compat_struct_unpack('!B', b'\x00'), (0,))
+ def test_compat_casefold(self):
+ if hasattr(compat_str, 'casefold'):
+ # don't bother to test str.casefold() (again)
+ return
+ # thanks https://bugs.python.org/file24232/casefolding.patch
+ self.assertEqual(compat_casefold('hello'), 'hello')
+ self.assertEqual(compat_casefold('hELlo'), 'hello')
+ self.assertEqual(compat_casefold('ß'), 'ss')
+ self.assertEqual(compat_casefold('fi'), 'fi')
+ self.assertEqual(compat_casefold('\u03a3'), '\u03c3')
+ self.assertEqual(compat_casefold('A\u0345\u03a3'), 'a\u03b9\u03c3')
+
+ def test_compat_urllib_request_Request(self):
+ self.assertEqual(
+ compat_urllib_request.Request('http://127.0.0.1', method='PUT').get_method(),
+ 'PUT')
+
+ class PUTrequest(compat_urllib_request.Request):
+ def get_method(self):
+ return 'PUT'
+
+ self.assertEqual(
+ PUTrequest('http://127.0.0.1').get_method(),
+ 'PUT')
+
if __name__ == '__main__':
unittest.main()
diff --git a/test/test_download.py b/test/test_download.py
index 0e9f293b5..f7d6a23bc 100644
--- a/test/test_download.py
+++ b/test/test_download.py
@@ -9,7 +9,6 @@ import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from test.helper import (
- assertGreaterEqual,
expect_warnings,
get_params,
gettestcases,
@@ -20,26 +19,35 @@ from test.helper import (
import hashlib
-import io
import json
import socket
import youtube_dl.YoutubeDL
from youtube_dl.compat import (
compat_http_client,
- compat_urllib_error,
compat_HTTPError,
+ compat_open as open,
+ compat_urllib_error,
)
from youtube_dl.utils import (
DownloadError,
ExtractorError,
+ error_to_compat_str,
format_bytes,
+ IDENTITY,
+ preferredencoding,
UnavailableVideoError,
)
from youtube_dl.extractor import get_info_extractor
RETRIES = 3
+# Some unittest APIs require actual str
+if not isinstance('TEST', str):
+ _encode_str = lambda s: s.encode(preferredencoding())
+else:
+ _encode_str = IDENTITY
+
class YoutubeDL(youtube_dl.YoutubeDL):
def __init__(self, *args, **kwargs):
@@ -92,35 +100,39 @@ class TestDownload(unittest.TestCase):
def generator(test_case, tname):
def test_template(self):
- ie = youtube_dl.extractor.get_info_extractor(test_case['name'])
- other_ies = [get_info_extractor(ie_key) for ie_key in test_case.get('add_ie', [])]
+ ie = youtube_dl.extractor.get_info_extractor(test_case['name'])()
+ other_ies = [get_info_extractor(ie_key)() for ie_key in test_case.get('add_ie', [])]
is_playlist = any(k.startswith('playlist') for k in test_case)
test_cases = test_case.get(
'playlist', [] if is_playlist else [test_case])
def print_skipping(reason):
print('Skipping %s: %s' % (test_case['name'], reason))
+ self.skipTest(_encode_str(reason))
+
if not ie.working():
print_skipping('IE marked as not _WORKING')
- return
for tc in test_cases:
info_dict = tc.get('info_dict', {})
if not (info_dict.get('id') and info_dict.get('ext')):
- raise Exception('Test definition incorrect. The output file cannot be known. Are both \'id\' and \'ext\' keys present?')
+ raise Exception('Test definition (%s) requires both \'id\' and \'ext\' keys present to define the output file' % (tname, ))
if 'skip' in test_case:
print_skipping(test_case['skip'])
- return
+
for other_ie in other_ies:
if not other_ie.working():
print_skipping('test depends on %sIE, marked as not WORKING' % other_ie.ie_key())
- return
params = get_params(test_case.get('params', {}))
params['outtmpl'] = tname + '_' + params['outtmpl']
if is_playlist and 'playlist' not in test_case:
params.setdefault('extract_flat', 'in_playlist')
+ params.setdefault('playlistend',
+ test_case['playlist_maxcount'] + 1
+ if test_case.get('playlist_maxcount')
+ else test_case.get('playlist_mincount'))
params.setdefault('skip_download', True)
ydl = YoutubeDL(params, auto_init=False)
@@ -146,6 +158,7 @@ def generator(test_case, tname):
try_rm(tc_filename)
try_rm(tc_filename + '.part')
try_rm(os.path.splitext(tc_filename)[0] + '.info.json')
+
try_rm_tcs_files()
try:
try_num = 1
@@ -160,7 +173,9 @@ def generator(test_case, tname):
except (DownloadError, ExtractorError) as err:
# Check if the exception is not a network related one
if not err.exc_info[0] in (compat_urllib_error.URLError, socket.timeout, UnavailableVideoError, compat_http_client.BadStatusLine) or (err.exc_info[0] == compat_HTTPError and err.exc_info[1].code == 503):
- raise
+ msg = getattr(err, 'msg', error_to_compat_str(err))
+ err.msg = '%s (%s)' % (msg, tname, )
+ raise err
if try_num == RETRIES:
report_warning('%s failed due to network errors, skipping...' % tname)
@@ -178,13 +193,19 @@ def generator(test_case, tname):
expect_info_dict(self, res_dict, test_case.get('info_dict', {}))
if 'playlist_mincount' in test_case:
- assertGreaterEqual(
- self,
+ self.assertGreaterEqual(
len(res_dict['entries']),
test_case['playlist_mincount'],
'Expected at least %d in playlist %s, but got only %d' % (
test_case['playlist_mincount'], test_case['url'],
len(res_dict['entries'])))
+ if 'playlist_maxcount' in test_case:
+ self.assertLessEqual(
+ len(res_dict['entries']),
+ test_case['playlist_maxcount'],
+ 'Expected at most %d in playlist %s, but got %d' % (
+ test_case['playlist_maxcount'], test_case['url'],
+ len(res_dict['entries'])))
if 'playlist_count' in test_case:
self.assertEqual(
len(res_dict['entries']),
@@ -209,7 +230,15 @@ def generator(test_case, tname):
# First, check test cases' data against extracted data alone
expect_info_dict(self, tc_res_dict, tc.get('info_dict', {}))
# Now, check downloaded file consistency
+ # support test-case with volatile ID, signalled by regexp value
+ if tc.get('info_dict', {}).get('id', '').startswith('re:'):
+ test_id = tc['info_dict']['id']
+ tc['info_dict']['id'] = tc_res_dict['id']
+ else:
+ test_id = None
tc_filename = get_tc_filename(tc)
+ if test_id:
+ tc['info_dict']['id'] = test_id
if not test_case.get('params', {}).get('skip_download', False):
self.assertTrue(os.path.exists(tc_filename), msg='Missing file ' + tc_filename)
self.assertTrue(tc_filename in finished_hook_called)
@@ -218,21 +247,21 @@ def generator(test_case, tname):
if params.get('test'):
expected_minsize = max(expected_minsize, 10000)
got_fsize = os.path.getsize(tc_filename)
- assertGreaterEqual(
- self, got_fsize, expected_minsize,
+ self.assertGreaterEqual(
+ got_fsize, expected_minsize,
'Expected %s to be at least %s, but it\'s only %s ' %
(tc_filename, format_bytes(expected_minsize),
format_bytes(got_fsize)))
if 'md5' in tc:
md5_for_file = _file_md5(tc_filename)
- self.assertEqual(md5_for_file, tc['md5'])
+ self.assertEqual(tc['md5'], md5_for_file)
# Finally, check test cases' data again but this time against
# extracted data from info JSON file written during processing
info_json_fn = os.path.splitext(tc_filename)[0] + '.info.json'
self.assertTrue(
os.path.exists(info_json_fn),
'Missing info file %s' % info_json_fn)
- with io.open(info_json_fn, encoding='utf-8') as infof:
+ with open(info_json_fn, encoding='utf-8') as infof:
info_dict = json.load(infof)
expect_info_dict(self, info_dict, tc.get('info_dict', {}))
finally:
diff --git a/test/test_downloader_external.py b/test/test_downloader_external.py
new file mode 100644
index 000000000..4491bd9de
--- /dev/null
+++ b/test/test_downloader_external.py
@@ -0,0 +1,272 @@
+#!/usr/bin/env python
+# coding: utf-8
+from __future__ import unicode_literals
+
+# Allow direct execution
+import os
+import re
+import sys
+import subprocess
+import unittest
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from test.helper import (
+ FakeLogger,
+ FakeYDL,
+ http_server_port,
+ try_rm,
+)
+from youtube_dl import YoutubeDL
+from youtube_dl.compat import (
+ compat_contextlib_suppress,
+ compat_http_cookiejar_Cookie,
+ compat_http_server,
+ compat_kwargs,
+)
+from youtube_dl.utils import (
+ encodeFilename,
+ join_nonempty,
+)
+from youtube_dl.downloader.external import (
+ Aria2cFD,
+ Aria2pFD,
+ AxelFD,
+ CurlFD,
+ FFmpegFD,
+ HttpieFD,
+ WgetFD,
+)
+from youtube_dl.postprocessor import (
+ FFmpegPostProcessor,
+)
+import threading
+
+TEST_SIZE = 10 * 1024
+
+TEST_COOKIE = {
+ 'version': 0,
+ 'name': 'test',
+ 'value': 'ytdlp',
+ 'port': None,
+ 'port_specified': False,
+ 'domain': '.example.com',
+ 'domain_specified': True,
+ 'domain_initial_dot': False,
+ 'path': '/',
+ 'path_specified': True,
+ 'secure': False,
+ 'expires': None,
+ 'discard': False,
+ 'comment': None,
+ 'comment_url': None,
+ 'rest': {},
+}
+
+TEST_COOKIE_VALUE = join_nonempty('name', 'value', delim='=', from_dict=TEST_COOKIE)
+
+TEST_INFO = {'url': 'http://www.example.com/'}
+
+
+def cookiejar_Cookie(**cookie_args):
+ return compat_http_cookiejar_Cookie(**compat_kwargs(cookie_args))
+
+
+def ifExternalFDAvailable(externalFD):
+ return unittest.skipUnless(externalFD.available(),
+ externalFD.get_basename() + ' not found')
+
+
+class HTTPTestRequestHandler(compat_http_server.BaseHTTPRequestHandler):
+ def log_message(self, format, *args):
+ pass
+
+ def send_content_range(self, total=None):
+ range_header = self.headers.get('Range')
+ start = end = None
+ if range_header:
+ mobj = re.match(r'bytes=(\d+)-(\d+)', range_header)
+ if mobj:
+ start, end = (int(mobj.group(i)) for i in (1, 2))
+ valid_range = start is not None and end is not None
+ if valid_range:
+ content_range = 'bytes %d-%d' % (start, end)
+ if total:
+ content_range += '/%d' % total
+ self.send_header('Content-Range', content_range)
+ return (end - start + 1) if valid_range else total
+
+ def serve(self, range=True, content_length=True):
+ self.send_response(200)
+ self.send_header('Content-Type', 'video/mp4')
+ size = TEST_SIZE
+ if range:
+ size = self.send_content_range(TEST_SIZE)
+ if content_length:
+ self.send_header('Content-Length', size)
+ self.end_headers()
+ self.wfile.write(b'#' * size)
+
+ def do_GET(self):
+ if self.path == '/regular':
+ self.serve()
+ elif self.path == '/no-content-length':
+ self.serve(content_length=False)
+ elif self.path == '/no-range':
+ self.serve(range=False)
+ elif self.path == '/no-range-no-content-length':
+ self.serve(range=False, content_length=False)
+ else:
+ assert False, 'unrecognised server path'
+
+
+@ifExternalFDAvailable(Aria2pFD)
+class TestAria2pFD(unittest.TestCase):
+ def setUp(self):
+ self.httpd = compat_http_server.HTTPServer(
+ ('127.0.0.1', 0), HTTPTestRequestHandler)
+ self.port = http_server_port(self.httpd)
+ self.server_thread = threading.Thread(target=self.httpd.serve_forever)
+ self.server_thread.daemon = True
+ self.server_thread.start()
+
+ def download(self, params, ep):
+ with subprocess.Popen(
+ ['aria2c', '--enable-rpc'],
+ stdout=subprocess.DEVNULL,
+ stderr=subprocess.DEVNULL
+ ) as process:
+ if not process.poll():
+ filename = 'testfile.mp4'
+ params['logger'] = FakeLogger()
+ params['outtmpl'] = filename
+ ydl = YoutubeDL(params)
+ try_rm(encodeFilename(filename))
+ self.assertEqual(ydl.download(['http://127.0.0.1:%d/%s' % (self.port, ep)]), 0)
+ self.assertEqual(os.path.getsize(encodeFilename(filename)), TEST_SIZE)
+ try_rm(encodeFilename(filename))
+ process.kill()
+
+ def download_all(self, params):
+ for ep in ('regular', 'no-content-length', 'no-range', 'no-range-no-content-length'):
+ self.download(params, ep)
+
+ def test_regular(self):
+ self.download_all({'external_downloader': 'aria2p'})
+
+ def test_chunked(self):
+ self.download_all({
+ 'external_downloader': 'aria2p',
+ 'http_chunk_size': 1000,
+ })
+
+
+@ifExternalFDAvailable(HttpieFD)
+class TestHttpieFD(unittest.TestCase):
+ def test_make_cmd(self):
+ with FakeYDL() as ydl:
+ downloader = HttpieFD(ydl, {})
+ self.assertEqual(
+ downloader._make_cmd('test', TEST_INFO),
+ ['http', '--download', '--output', 'test', 'http://www.example.com/'])
+
+ # Test cookie header is added
+ ydl.cookiejar.set_cookie(cookiejar_Cookie(**TEST_COOKIE))
+ self.assertEqual(
+ downloader._make_cmd('test', TEST_INFO),
+ ['http', '--download', '--output', 'test',
+ 'http://www.example.com/', 'Cookie:' + TEST_COOKIE_VALUE])
+
+
+@ifExternalFDAvailable(AxelFD)
+class TestAxelFD(unittest.TestCase):
+ def test_make_cmd(self):
+ with FakeYDL() as ydl:
+ downloader = AxelFD(ydl, {})
+ self.assertEqual(
+ downloader._make_cmd('test', TEST_INFO),
+ ['axel', '-o', 'test', '--', 'http://www.example.com/'])
+
+ # Test cookie header is added
+ ydl.cookiejar.set_cookie(cookiejar_Cookie(**TEST_COOKIE))
+ self.assertEqual(
+ downloader._make_cmd('test', TEST_INFO),
+ ['axel', '-o', 'test', '-H', 'Cookie: ' + TEST_COOKIE_VALUE,
+ '--max-redirect=0', '--', 'http://www.example.com/'])
+
+
+@ifExternalFDAvailable(WgetFD)
+class TestWgetFD(unittest.TestCase):
+ def test_make_cmd(self):
+ with FakeYDL() as ydl:
+ downloader = WgetFD(ydl, {})
+ self.assertNotIn('--load-cookies', downloader._make_cmd('test', TEST_INFO))
+ # Test cookiejar tempfile arg is added
+ ydl.cookiejar.set_cookie(cookiejar_Cookie(**TEST_COOKIE))
+ self.assertIn('--load-cookies', downloader._make_cmd('test', TEST_INFO))
+
+
+@ifExternalFDAvailable(CurlFD)
+class TestCurlFD(unittest.TestCase):
+ def test_make_cmd(self):
+ with FakeYDL() as ydl:
+ downloader = CurlFD(ydl, {})
+ self.assertNotIn('--cookie', downloader._make_cmd('test', TEST_INFO))
+ # Test cookie header is added
+ ydl.cookiejar.set_cookie(cookiejar_Cookie(**TEST_COOKIE))
+ self.assertIn('--cookie', downloader._make_cmd('test', TEST_INFO))
+ self.assertIn(TEST_COOKIE_VALUE, downloader._make_cmd('test', TEST_INFO))
+
+
+@ifExternalFDAvailable(Aria2cFD)
+class TestAria2cFD(unittest.TestCase):
+ def test_make_cmd(self):
+ with FakeYDL() as ydl:
+ downloader = Aria2cFD(ydl, {})
+ downloader._make_cmd('test', TEST_INFO)
+ self.assertFalse(hasattr(downloader, '_cookies_tempfile'))
+
+ # Test cookiejar tempfile arg is added
+ ydl.cookiejar.set_cookie(cookiejar_Cookie(**TEST_COOKIE))
+ cmd = downloader._make_cmd('test', TEST_INFO)
+ self.assertIn('--load-cookies=%s' % downloader._cookies_tempfile, cmd)
+
+
+# Handle delegated availability
+def ifFFmpegFDAvailable(externalFD):
+ # raise SkipTest, or set False!
+ avail = ifExternalFDAvailable(externalFD) and False
+ with compat_contextlib_suppress(Exception):
+ avail = FFmpegPostProcessor(downloader=None).available
+ return unittest.skipUnless(
+ avail, externalFD.get_basename() + ' not found')
+
+
+@ifFFmpegFDAvailable(FFmpegFD)
+class TestFFmpegFD(unittest.TestCase):
+ _args = []
+
+ def _test_cmd(self, args):
+ self._args = args
+
+ def test_make_cmd(self):
+ with FakeYDL() as ydl:
+ downloader = FFmpegFD(ydl, {})
+ downloader._debug_cmd = self._test_cmd
+ info_dict = TEST_INFO.copy()
+ info_dict['ext'] = 'mp4'
+
+ downloader._call_downloader('test', info_dict)
+ self.assertEqual(self._args, [
+ 'ffmpeg', '-y', '-i', 'http://www.example.com/',
+ '-c', 'copy', '-f', 'mp4', 'file:test'])
+
+ # Test cookies arg is added
+ ydl.cookiejar.set_cookie(cookiejar_Cookie(**TEST_COOKIE))
+ downloader._call_downloader('test', info_dict)
+ self.assertEqual(self._args, [
+ 'ffmpeg', '-y', '-cookies', TEST_COOKIE_VALUE + '; path=/; domain=.example.com;\r\n',
+ '-i', 'http://www.example.com/', '-c', 'copy', '-f', 'mp4', 'file:test'])
+
+
+if __name__ == '__main__':
+ unittest.main()
diff --git a/test/test_downloader_http.py b/test/test_downloader_http.py
new file mode 100644
index 000000000..6af86ae48
--- /dev/null
+++ b/test/test_downloader_http.py
@@ -0,0 +1,108 @@
+#!/usr/bin/env python
+# coding: utf-8
+from __future__ import unicode_literals
+
+# Allow direct execution
+import os
+import re
+import sys
+import unittest
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from test.helper import (
+ FakeLogger,
+ http_server_port,
+ try_rm,
+)
+from youtube_dl import YoutubeDL
+from youtube_dl.compat import compat_http_server
+from youtube_dl.downloader.http import HttpFD
+from youtube_dl.utils import encodeFilename
+import threading
+
+TEST_DIR = os.path.dirname(os.path.abspath(__file__))
+
+
+TEST_SIZE = 10 * 1024
+
+
+class HTTPTestRequestHandler(compat_http_server.BaseHTTPRequestHandler):
+ def log_message(self, format, *args):
+ pass
+
+ def send_content_range(self, total=None):
+ range_header = self.headers.get('Range')
+ start = end = None
+ if range_header:
+ mobj = re.search(r'^bytes=(\d+)-(\d+)', range_header)
+ if mobj:
+ start = int(mobj.group(1))
+ end = int(mobj.group(2))
+ valid_range = start is not None and end is not None
+ if valid_range:
+ content_range = 'bytes %d-%d' % (start, end)
+ if total:
+ content_range += '/%d' % total
+ self.send_header('Content-Range', content_range)
+ return (end - start + 1) if valid_range else total
+
+ def serve(self, range=True, content_length=True):
+ self.send_response(200)
+ self.send_header('Content-Type', 'video/mp4')
+ size = TEST_SIZE
+ if range:
+ size = self.send_content_range(TEST_SIZE)
+ if content_length:
+ self.send_header('Content-Length', size)
+ self.end_headers()
+ self.wfile.write(b'#' * size)
+
+ def do_GET(self):
+ if self.path == '/regular':
+ self.serve()
+ elif self.path == '/no-content-length':
+ self.serve(content_length=False)
+ elif self.path == '/no-range':
+ self.serve(range=False)
+ elif self.path == '/no-range-no-content-length':
+ self.serve(range=False, content_length=False)
+ else:
+ assert False
+
+
+class TestHttpFD(unittest.TestCase):
+ def setUp(self):
+ self.httpd = compat_http_server.HTTPServer(
+ ('127.0.0.1', 0), HTTPTestRequestHandler)
+ self.port = http_server_port(self.httpd)
+ self.server_thread = threading.Thread(target=self.httpd.serve_forever)
+ self.server_thread.daemon = True
+ self.server_thread.start()
+
+ def download(self, params, ep):
+ params['logger'] = FakeLogger()
+ ydl = YoutubeDL(params)
+ downloader = HttpFD(ydl, params)
+ filename = 'testfile.mp4'
+ try_rm(encodeFilename(filename))
+ self.assertTrue(downloader.real_download(filename, {
+ 'url': 'http://127.0.0.1:%d/%s' % (self.port, ep),
+ }))
+ self.assertEqual(os.path.getsize(encodeFilename(filename)), TEST_SIZE, ep)
+ try_rm(encodeFilename(filename))
+
+ def download_all(self, params):
+ for ep in ('regular', 'no-content-length', 'no-range', 'no-range-no-content-length'):
+ self.download(params, ep)
+
+ def test_regular(self):
+ self.download_all({})
+
+ def test_chunked(self):
+ self.download_all({
+ 'http_chunk_size': 1000,
+ })
+
+
+if __name__ == '__main__':
+ unittest.main()
diff --git a/test/test_execution.py b/test/test_execution.py
index 11661bb68..9daaafa6c 100644
--- a/test/test_execution.py
+++ b/test/test_execution.py
@@ -8,37 +8,55 @@ import unittest
import sys
import os
import subprocess
-sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+rootDir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+
+sys.path.insert(0, rootDir)
+
+from youtube_dl.compat import compat_register_utf8, compat_subprocess_get_DEVNULL
from youtube_dl.utils import encodeArgument
-rootDir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+compat_register_utf8()
-try:
- _DEV_NULL = subprocess.DEVNULL
-except AttributeError:
- _DEV_NULL = open(os.devnull, 'wb')
+_DEV_NULL = compat_subprocess_get_DEVNULL()
class TestExecution(unittest.TestCase):
+ def setUp(self):
+ self.module = 'youtube_dl'
+ if sys.version_info < (2, 7):
+ self.module += '.__main__'
+
def test_import(self):
subprocess.check_call([sys.executable, '-c', 'import youtube_dl'], cwd=rootDir)
def test_module_exec(self):
- if sys.version_info >= (2, 7): # Python 2.6 doesn't support package execution
- subprocess.check_call([sys.executable, '-m', 'youtube_dl', '--version'], cwd=rootDir, stdout=_DEV_NULL)
+ subprocess.check_call([sys.executable, '-m', self.module, '--version'], cwd=rootDir, stdout=_DEV_NULL)
def test_main_exec(self):
- subprocess.check_call([sys.executable, 'youtube_dl/__main__.py', '--version'], cwd=rootDir, stdout=_DEV_NULL)
+ subprocess.check_call([sys.executable, os.path.normpath('youtube_dl/__main__.py'), '--version'], cwd=rootDir, stdout=_DEV_NULL)
def test_cmdline_umlauts(self):
+ os.environ['PYTHONIOENCODING'] = 'utf-8'
p = subprocess.Popen(
- [sys.executable, 'youtube_dl/__main__.py', encodeArgument('ä'), '--version'],
+ [sys.executable, '-m', self.module, encodeArgument('ä'), '--version'],
cwd=rootDir, stdout=_DEV_NULL, stderr=subprocess.PIPE)
_, stderr = p.communicate()
self.assertFalse(stderr)
+ def test_lazy_extractors(self):
+ lazy_extractors = os.path.normpath('youtube_dl/extractor/lazy_extractors.py')
+ try:
+ subprocess.check_call([sys.executable, os.path.normpath('devscripts/make_lazy_extractors.py'), lazy_extractors], cwd=rootDir, stdout=_DEV_NULL)
+ subprocess.check_call([sys.executable, os.path.normpath('test/test_all_urls.py')], cwd=rootDir, stdout=_DEV_NULL)
+ finally:
+ for x in ('', 'c') if sys.version_info[0] < 3 else ('',):
+ try:
+ os.remove(lazy_extractors + x)
+ except OSError:
+ pass
+
if __name__ == '__main__':
unittest.main()
diff --git a/test/test_http.py b/test/test_http.py
index 7a7a3510f..485c4c6fc 100644
--- a/test/test_http.py
+++ b/test/test_http.py
@@ -8,38 +8,163 @@ import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-from youtube_dl import YoutubeDL
-from youtube_dl.compat import compat_http_server, compat_urllib_request
+import contextlib
+import gzip
+import io
import ssl
+import tempfile
import threading
+import zlib
+
+# avoid deprecated alias assertRaisesRegexp
+if hasattr(unittest.TestCase, 'assertRaisesRegex'):
+ unittest.TestCase.assertRaisesRegexp = unittest.TestCase.assertRaisesRegex
+
+try:
+ import brotli
+except ImportError:
+ brotli = None
+try:
+ from urllib.request import pathname2url
+except ImportError:
+ from urllib import pathname2url
+
+from youtube_dl.compat import (
+ compat_http_cookiejar_Cookie,
+ compat_http_server,
+ compat_str as str,
+ compat_urllib_error,
+ compat_urllib_HTTPError,
+ compat_urllib_parse,
+ compat_urllib_request,
+)
+
+from youtube_dl.utils import (
+ sanitized_Request,
+ update_Request,
+ urlencode_postdata,
+)
+
+from test.helper import (
+ expectedFailureIf,
+ FakeYDL,
+ FakeLogger,
+ http_server_port,
+)
+from youtube_dl import YoutubeDL
TEST_DIR = os.path.dirname(os.path.abspath(__file__))
-def http_server_port(httpd):
- if os.name == 'java' and isinstance(httpd.socket, ssl.SSLSocket):
- # In Jython SSLSocket is not a subclass of socket.socket
- sock = httpd.socket.sock
- else:
- sock = httpd.socket
- return sock.getsockname()[1]
-
-
class HTTPTestRequestHandler(compat_http_server.BaseHTTPRequestHandler):
+ protocol_version = 'HTTP/1.1'
+
+ # work-around old/new -style class inheritance
+ def super(self, meth_name, *args, **kwargs):
+ from types import MethodType
+ try:
+ super()
+ fn = lambda s, m, *a, **k: getattr(super(), m)(*a, **k)
+ except TypeError:
+ fn = lambda s, m, *a, **k: getattr(compat_http_server.BaseHTTPRequestHandler, m)(s, *a, **k)
+ self.super = MethodType(fn, self)
+ return self.super(meth_name, *args, **kwargs)
+
def log_message(self, format, *args):
pass
+ def _headers(self):
+ payload = str(self.headers).encode('utf-8')
+ self.send_response(200)
+ self.send_header('Content-Type', 'application/json')
+ self.send_header('Content-Length', str(len(payload)))
+ self.end_headers()
+ self.wfile.write(payload)
+
+ def _redirect(self):
+ self.send_response(int(self.path[len('/redirect_'):]))
+ self.send_header('Location', '/method')
+ self.send_header('Content-Length', '0')
+ self.end_headers()
+
+ def _method(self, method, payload=None):
+ self.send_response(200)
+ self.send_header('Content-Length', str(len(payload or '')))
+ self.send_header('Method', method)
+ self.end_headers()
+ if payload:
+ self.wfile.write(payload)
+
+ def _status(self, status):
+ payload = '<html>{0} NOT FOUND</html>'.format(status).encode('utf-8')
+ self.send_response(int(status))
+ self.send_header('Content-Type', 'text/html; charset=utf-8')
+ self.send_header('Content-Length', str(len(payload)))
+ self.end_headers()
+ self.wfile.write(payload)
+
+ def _read_data(self):
+ if 'Content-Length' in self.headers:
+ return self.rfile.read(int(self.headers['Content-Length']))
+
+ def _test_url(self, path, host='127.0.0.1', scheme='http', port=None):
+ return '{0}://{1}:{2}/{3}'.format(
+ scheme, host,
+ port if port is not None
+ else http_server_port(self.server), path)
+
+ def do_POST(self):
+ data = self._read_data()
+ if self.path.startswith('/redirect_'):
+ self._redirect()
+ elif self.path.startswith('/method'):
+ self._method('POST', data)
+ elif self.path.startswith('/headers'):
+ self._headers()
+ else:
+ self._status(404)
+
+ def do_HEAD(self):
+ if self.path.startswith('/redirect_'):
+ self._redirect()
+ elif self.path.startswith('/method'):
+ self._method('HEAD')
+ else:
+ self._status(404)
+
+ def do_PUT(self):
+ data = self._read_data()
+ if self.path.startswith('/redirect_'):
+ self._redirect()
+ elif self.path.startswith('/method'):
+ self._method('PUT', data)
+ else:
+ self._status(404)
+
def do_GET(self):
- if self.path == '/video.html':
- self.send_response(200)
- self.send_header('Content-Type', 'text/html; charset=utf-8')
+
+ def respond(payload=b'<html><video src="/vid.mp4" /></html>',
+ payload_type='text/html; charset=utf-8',
+ payload_encoding=None,
+ resp_code=200):
+ self.send_response(resp_code)
+ self.send_header('Content-Type', payload_type)
+ if payload_encoding:
+ self.send_header('Content-Encoding', payload_encoding)
+ self.send_header('Content-Length', str(len(payload))) # required for persistent connections
self.end_headers()
- self.wfile.write(b'<html><video src="/vid.mp4" /></html>')
+ self.wfile.write(payload)
+
+ def gzip_compress(p):
+ buf = io.BytesIO()
+ with contextlib.closing(gzip.GzipFile(fileobj=buf, mode='wb')) as f:
+ f.write(p)
+ return buf.getvalue()
+
+ if self.path == '/video.html':
+ respond()
elif self.path == '/vid.mp4':
- self.send_response(200)
- self.send_header('Content-Type', 'video/mp4')
- self.end_headers()
- self.wfile.write(b'\x00\x00\x00\x00\x20\x66\x74[video]')
+ respond(b'\x00\x00\x00\x00\x20\x66\x74[video]', 'video/mp4')
elif self.path == '/302':
if sys.version_info[0] == 3:
# XXX: Python 3 http server does not allow non-ASCII header values
@@ -47,71 +172,336 @@ class HTTPTestRequestHandler(compat_http_server.BaseHTTPRequestHandler):
self.end_headers()
return
- new_url = 'http://localhost:%d/中文.html' % http_server_port(self.server)
+ new_url = self._test_url('中文.html')
self.send_response(302)
self.send_header(b'Location', new_url.encode('utf-8'))
self.end_headers()
elif self.path == '/%E4%B8%AD%E6%96%87.html':
- self.send_response(200)
- self.send_header('Content-Type', 'text/html; charset=utf-8')
+ respond()
+ elif self.path == '/%c7%9f':
+ respond()
+ elif self.path == '/redirect_dotsegments':
+ self.send_response(301)
+ # redirect to /headers but with dot segments before
+ self.send_header('Location', '/a/b/./../../headers')
+ self.send_header('Content-Length', '0')
+ self.end_headers()
+ elif self.path.startswith('/redirect_'):
+ self._redirect()
+ elif self.path.startswith('/method'):
+ self._method('GET')
+ elif self.path.startswith('/headers'):
+ self._headers()
+ elif self.path.startswith('/308-to-headers'):
+ self.send_response(308)
+ self.send_header('Location', '/headers')
+ self.send_header('Content-Length', '0')
self.end_headers()
- self.wfile.write(b'<html><video src="/vid.mp4" /></html>')
+ elif self.path == '/trailing_garbage':
+ payload = b'<html><video src="/vid.mp4" /></html>'
+ compressed = gzip_compress(payload) + b'trailing garbage'
+ respond(compressed, payload_encoding='gzip')
+ elif self.path == '/302-non-ascii-redirect':
+ new_url = self._test_url('中文.html')
+ # actually respond with permanent redirect
+ self.send_response(301)
+ self.send_header('Location', new_url)
+ self.send_header('Content-Length', '0')
+ self.end_headers()
+ elif self.path == '/content-encoding':
+ encodings = self.headers.get('ytdl-encoding', '')
+ payload = b'<html><video src="/vid.mp4" /></html>'
+ for encoding in filter(None, (e.strip() for e in encodings.split(','))):
+ if encoding == 'br' and brotli:
+ payload = brotli.compress(payload)
+ elif encoding == 'gzip':
+ payload = gzip_compress(payload)
+ elif encoding == 'deflate':
+ payload = zlib.compress(payload)
+ elif encoding == 'unsupported':
+ payload = b'raw'
+ break
+ else:
+ self._status(415)
+ return
+ respond(payload, payload_encoding=encodings)
+
else:
- assert False
+ self._status(404)
+ def send_header(self, keyword, value):
+ """
+ Forcibly allow HTTP server to send non percent-encoded non-ASCII characters in headers.
+ This is against what is defined in RFC 3986: but we need to test that we support this
+ since some sites incorrectly do this.
+ """
+ if keyword.lower() == 'connection':
+ return self.super('send_header', keyword, value)
-class FakeLogger(object):
- def debug(self, msg):
- pass
+ if not hasattr(self, '_headers_buffer'):
+ self._headers_buffer = []
- def warning(self, msg):
- pass
+ self._headers_buffer.append('{0}: {1}\r\n'.format(keyword, value).encode('utf-8'))
- def error(self, msg):
- pass
+ def end_headers(self):
+ if hasattr(self, '_headers_buffer'):
+ self.wfile.write(b''.join(self._headers_buffer))
+ self._headers_buffer = []
+ self.super('end_headers')
class TestHTTP(unittest.TestCase):
- def setUp(self):
- self.httpd = compat_http_server.HTTPServer(
- ('localhost', 0), HTTPTestRequestHandler)
- self.port = http_server_port(self.httpd)
- self.server_thread = threading.Thread(target=self.httpd.serve_forever)
- self.server_thread.daemon = True
- self.server_thread.start()
-
- def test_unicode_path_redirection(self):
- # XXX: Python 3 http server does not allow non-ASCII header values
- if sys.version_info[0] == 3:
- return
-
- ydl = YoutubeDL({'logger': FakeLogger()})
- r = ydl.extract_info('http://localhost:%d/302' % self.port)
- self.assertEqual(r['entries'][0]['url'], 'http://localhost:%d/vid.mp4' % self.port)
-
+ # when does it make sense to check the SSL certificate?
+ _check_cert = (
+ sys.version_info >= (3, 2)
+ or (sys.version_info[0] == 2 and sys.version_info[1:] >= (7, 19)))
-class TestHTTPS(unittest.TestCase):
def setUp(self):
+ # HTTP server
+ self.http_httpd = compat_http_server.HTTPServer(
+ ('127.0.0.1', 0), HTTPTestRequestHandler)
+ self.http_port = http_server_port(self.http_httpd)
+
+ self.http_server_thread = threading.Thread(target=self.http_httpd.serve_forever)
+ self.http_server_thread.daemon = True
+ self.http_server_thread.start()
+
+ try:
+ from http.server import ThreadingHTTPServer
+ except ImportError:
+ try:
+ from socketserver import ThreadingMixIn
+ except ImportError:
+ from SocketServer import ThreadingMixIn
+
+ class ThreadingHTTPServer(ThreadingMixIn, compat_http_server.HTTPServer):
+ pass
+
+ # HTTPS server
certfn = os.path.join(TEST_DIR, 'testcert.pem')
- self.httpd = compat_http_server.HTTPServer(
- ('localhost', 0), HTTPTestRequestHandler)
- self.httpd.socket = ssl.wrap_socket(
- self.httpd.socket, certfile=certfn, server_side=True)
- self.port = http_server_port(self.httpd)
- self.server_thread = threading.Thread(target=self.httpd.serve_forever)
- self.server_thread.daemon = True
- self.server_thread.start()
-
+ self.https_httpd = ThreadingHTTPServer(
+ ('127.0.0.1', 0), HTTPTestRequestHandler)
+ try:
+ sslctx = ssl.SSLContext(ssl.PROTOCOL_SSLv23)
+ sslctx.verify_mode = ssl.CERT_NONE
+ sslctx.check_hostname = False
+ sslctx.load_cert_chain(certfn, None)
+ self.https_httpd.socket = sslctx.wrap_socket(
+ self.https_httpd.socket, server_side=True)
+ except AttributeError:
+ self.https_httpd.socket = ssl.wrap_socket(
+ self.https_httpd.socket, certfile=certfn, server_side=True)
+
+ self.https_port = http_server_port(self.https_httpd)
+ self.https_server_thread = threading.Thread(target=self.https_httpd.serve_forever)
+ self.https_server_thread.daemon = True
+ self.https_server_thread.start()
+
+ def tearDown(self):
+
+ def closer(svr):
+ def _closer():
+ svr.shutdown()
+ svr.server_close()
+ return _closer
+
+ shutdown_thread = threading.Thread(target=closer(self.http_httpd))
+ shutdown_thread.start()
+ self.http_server_thread.join(2.0)
+
+ shutdown_thread = threading.Thread(target=closer(self.https_httpd))
+ shutdown_thread.start()
+ self.https_server_thread.join(2.0)
+
+ def _test_url(self, path, host='127.0.0.1', scheme='http', port=None):
+ return '{0}://{1}:{2}/{3}'.format(
+ scheme, host,
+ port if port is not None
+ else self.https_port if scheme == 'https'
+ else self.http_port, path)
+
+ @unittest.skipUnless(_check_cert, 'No support for certificate check in SSL')
def test_nocheckcertificate(self):
- if sys.version_info >= (2, 7, 9): # No certificate checking anyways
- ydl = YoutubeDL({'logger': FakeLogger()})
- self.assertRaises(
- Exception,
- ydl.extract_info, 'https://localhost:%d/video.html' % self.port)
+ with FakeYDL({'logger': FakeLogger()}) as ydl:
+ with self.assertRaises(compat_urllib_error.URLError):
+ ydl.urlopen(sanitized_Request(self._test_url('headers', scheme='https')))
+
+ with FakeYDL({'logger': FakeLogger(), 'nocheckcertificate': True}) as ydl:
+ r = ydl.urlopen(sanitized_Request(self._test_url('headers', scheme='https')))
+ self.assertEqual(r.getcode(), 200)
+ r.close()
+
+ def test_percent_encode(self):
+ with FakeYDL() as ydl:
+ # Unicode characters should be encoded with uppercase percent-encoding
+ res = ydl.urlopen(sanitized_Request(self._test_url('中文.html')))
+ self.assertEqual(res.getcode(), 200)
+ res.close()
+ # don't normalize existing percent encodings
+ res = ydl.urlopen(sanitized_Request(self._test_url('%c7%9f')))
+ self.assertEqual(res.getcode(), 200)
+ res.close()
- ydl = YoutubeDL({'logger': FakeLogger(), 'nocheckcertificate': True})
- r = ydl.extract_info('https://localhost:%d/video.html' % self.port)
- self.assertEqual(r['entries'][0]['url'], 'https://localhost:%d/vid.mp4' % self.port)
+ def test_unicode_path_redirection(self):
+ with FakeYDL() as ydl:
+ r = ydl.urlopen(sanitized_Request(self._test_url('302-non-ascii-redirect')))
+ self.assertEqual(r.url, self._test_url('%E4%B8%AD%E6%96%87.html'))
+ r.close()
+
+ def test_redirect(self):
+ with FakeYDL() as ydl:
+ def do_req(redirect_status, method, check_no_content=False):
+ data = b'testdata' if method in ('POST', 'PUT') else None
+ res = ydl.urlopen(sanitized_Request(
+ self._test_url('redirect_{0}'.format(redirect_status)),
+ method=method, data=data))
+ if check_no_content:
+ self.assertNotIn('Content-Type', res.headers)
+ return res.read().decode('utf-8'), res.headers.get('method', '')
+ # A 303 must either use GET or HEAD for subsequent request
+ self.assertEqual(do_req(303, 'POST'), ('', 'GET'))
+ self.assertEqual(do_req(303, 'HEAD'), ('', 'HEAD'))
+
+ self.assertEqual(do_req(303, 'PUT'), ('', 'GET'))
+
+ # 301 and 302 turn POST only into a GET, with no Content-Type
+ self.assertEqual(do_req(301, 'POST', True), ('', 'GET'))
+ self.assertEqual(do_req(301, 'HEAD'), ('', 'HEAD'))
+ self.assertEqual(do_req(302, 'POST', True), ('', 'GET'))
+ self.assertEqual(do_req(302, 'HEAD'), ('', 'HEAD'))
+
+ self.assertEqual(do_req(301, 'PUT'), ('testdata', 'PUT'))
+ self.assertEqual(do_req(302, 'PUT'), ('testdata', 'PUT'))
+
+ # 307 and 308 should not change method
+ for m in ('POST', 'PUT'):
+ self.assertEqual(do_req(307, m), ('testdata', m))
+ self.assertEqual(do_req(308, m), ('testdata', m))
+
+ self.assertEqual(do_req(307, 'HEAD'), ('', 'HEAD'))
+ self.assertEqual(do_req(308, 'HEAD'), ('', 'HEAD'))
+
+ # These should not redirect and instead raise an HTTPError
+ for code in (300, 304, 305, 306):
+ with self.assertRaises(compat_urllib_HTTPError):
+ do_req(code, 'GET')
+
+ # Jython 2.7.1 times out for some reason
+ @expectedFailureIf(sys.platform.startswith('java') and sys.version_info < (2, 7, 2))
+ def test_content_type(self):
+ # https://github.com/yt-dlp/yt-dlp/commit/379a4f161d4ad3e40932dcf5aca6e6fb9715ab28
+ with FakeYDL({'nocheckcertificate': True}) as ydl:
+ # method should be auto-detected as POST
+ r = sanitized_Request(self._test_url('headers', scheme='https'), data=urlencode_postdata({'test': 'test'}))
+
+ headers = ydl.urlopen(r).read().decode('utf-8')
+ self.assertIn('Content-Type: application/x-www-form-urlencoded', headers)
+
+ # test http
+ r = sanitized_Request(self._test_url('headers'), data=urlencode_postdata({'test': 'test'}))
+ headers = ydl.urlopen(r).read().decode('utf-8')
+ self.assertIn('Content-Type: application/x-www-form-urlencoded', headers)
+
+ def test_update_req(self):
+ req = sanitized_Request('http://example.com')
+ assert req.data is None
+ assert req.get_method() == 'GET'
+ assert not req.has_header('Content-Type')
+ # Test that zero-byte payloads will be sent
+ req = update_Request(req, data=b'')
+ assert req.data == b''
+ assert req.get_method() == 'POST'
+ # yt-dl expects data to be encoded and Content-Type to be added by sender
+ # assert req.get_header('Content-Type') == 'application/x-www-form-urlencoded'
+
+ def test_cookiejar(self):
+ with FakeYDL() as ydl:
+ ydl.cookiejar.set_cookie(compat_http_cookiejar_Cookie(
+ 0, 'test', 'ytdl', None, False, '127.0.0.1', True,
+ False, '/headers', True, False, None, False, None, None, {}))
+ data = ydl.urlopen(sanitized_Request(
+ self._test_url('headers'))).read().decode('utf-8')
+ self.assertIn('Cookie: test=ytdl', data)
+
+ def test_passed_cookie_header(self):
+ # We should accept a Cookie header being passed as in normal headers and handle it appropriately.
+ with FakeYDL() as ydl:
+ # Specified Cookie header should be used
+ res = ydl.urlopen(sanitized_Request(
+ self._test_url('headers'), headers={'Cookie': 'test=test'})).read().decode('utf-8')
+ self.assertIn('Cookie: test=test', res)
+
+ # Specified Cookie header should be removed on any redirect
+ res = ydl.urlopen(sanitized_Request(
+ self._test_url('308-to-headers'), headers={'Cookie': 'test=test'})).read().decode('utf-8')
+ self.assertNotIn('Cookie: test=test', res)
+
+ # Specified Cookie header should override global cookiejar for that request
+ ydl.cookiejar.set_cookie(compat_http_cookiejar_Cookie(
+ 0, 'test', 'ytdlp', None, False, '127.0.0.1', True,
+ False, '/headers', True, False, None, False, None, None, {}))
+ data = ydl.urlopen(sanitized_Request(
+ self._test_url('headers'), headers={'Cookie': 'test=test'})).read().decode('utf-8')
+ self.assertNotIn('Cookie: test=ytdlp', data)
+ self.assertIn('Cookie: test=test', data)
+
+ def test_no_compression_compat_header(self):
+ with FakeYDL() as ydl:
+ data = ydl.urlopen(
+ sanitized_Request(
+ self._test_url('headers'),
+ headers={'Youtubedl-no-compression': True})).read()
+ self.assertIn(b'Accept-Encoding: identity', data)
+ self.assertNotIn(b'youtubedl-no-compression', data.lower())
+
+ def test_gzip_trailing_garbage(self):
+ # https://github.com/ytdl-org/youtube-dl/commit/aa3e950764337ef9800c936f4de89b31c00dfcf5
+ # https://github.com/ytdl-org/youtube-dl/commit/6f2ec15cee79d35dba065677cad9da7491ec6e6f
+ with FakeYDL() as ydl:
+ data = ydl.urlopen(sanitized_Request(self._test_url('trailing_garbage'))).read().decode('utf-8')
+ self.assertEqual(data, '<html><video src="/vid.mp4" /></html>')
+
+ def __test_compression(self, encoding):
+ with FakeYDL() as ydl:
+ res = ydl.urlopen(
+ sanitized_Request(
+ self._test_url('content-encoding'),
+ headers={'ytdl-encoding': encoding}))
+ # decoded encodings are removed: only check for valid decompressed data
+ self.assertEqual(res.read(), b'<html><video src="/vid.mp4" /></html>')
+
+ @unittest.skipUnless(brotli, 'brotli support is not installed')
+ def test_brotli(self):
+ self.__test_compression('br')
+
+ def test_deflate(self):
+ self.__test_compression('deflate')
+
+ def test_gzip(self):
+ self.__test_compression('gzip')
+
+ def test_multiple_encodings(self):
+ # https://www.rfc-editor.org/rfc/rfc9110.html#section-8.4
+ for pair in ('gzip,deflate', 'deflate, gzip', 'gzip, gzip', 'deflate, deflate'):
+ self.__test_compression(pair)
+
+ def test_unsupported_encoding(self):
+ # it should return the raw content
+ with FakeYDL() as ydl:
+ res = ydl.urlopen(
+ sanitized_Request(
+ self._test_url('content-encoding'),
+ headers={'ytdl-encoding': 'unsupported'}))
+ self.assertEqual(res.headers.get('Content-Encoding'), 'unsupported')
+ self.assertEqual(res.read(), b'raw')
+
+ def test_remove_dot_segments(self):
+ with FakeYDL() as ydl:
+ res = ydl.urlopen(sanitized_Request(self._test_url('a/b/./../../headers')))
+ self.assertEqual(compat_urllib_parse.urlparse(res.geturl()).path, '/headers')
+
+ res = ydl.urlopen(sanitized_Request(self._test_url('redirect_dotsegments')))
+ self.assertEqual(compat_urllib_parse.urlparse(res.geturl()).path, '/headers')
def _build_proxy_handler(name):
@@ -125,30 +515,50 @@ def _build_proxy_handler(name):
self.send_response(200)
self.send_header('Content-Type', 'text/plain; charset=utf-8')
self.end_headers()
- self.wfile.write('{self.proxy_name}: {self.path}'.format(self=self).encode('utf-8'))
+ self.wfile.write('{0}: {1}'.format(self.proxy_name, self.path).encode('utf-8'))
return HTTPTestRequestHandler
class TestProxy(unittest.TestCase):
def setUp(self):
self.proxy = compat_http_server.HTTPServer(
- ('localhost', 0), _build_proxy_handler('normal'))
+ ('127.0.0.1', 0), _build_proxy_handler('normal'))
self.port = http_server_port(self.proxy)
self.proxy_thread = threading.Thread(target=self.proxy.serve_forever)
self.proxy_thread.daemon = True
self.proxy_thread.start()
self.geo_proxy = compat_http_server.HTTPServer(
- ('localhost', 0), _build_proxy_handler('geo'))
+ ('127.0.0.1', 0), _build_proxy_handler('geo'))
self.geo_port = http_server_port(self.geo_proxy)
self.geo_proxy_thread = threading.Thread(target=self.geo_proxy.serve_forever)
self.geo_proxy_thread.daemon = True
self.geo_proxy_thread.start()
+ def tearDown(self):
+
+ def closer(svr):
+ def _closer():
+ svr.shutdown()
+ svr.server_close()
+ return _closer
+
+ shutdown_thread = threading.Thread(target=closer(self.proxy))
+ shutdown_thread.start()
+ self.proxy_thread.join(2.0)
+
+ shutdown_thread = threading.Thread(target=closer(self.geo_proxy))
+ shutdown_thread.start()
+ self.geo_proxy_thread.join(2.0)
+
+ def _test_proxy(self, host='127.0.0.1', port=None):
+ return '{0}:{1}'.format(
+ host, port if port is not None else self.port)
+
def test_proxy(self):
- geo_proxy = 'localhost:{0}'.format(self.geo_port)
+ geo_proxy = self._test_proxy(port=self.geo_port)
ydl = YoutubeDL({
- 'proxy': 'localhost:{0}'.format(self.port),
+ 'proxy': self._test_proxy(),
'geo_verification_proxy': geo_proxy,
})
url = 'http://foo.com/bar'
@@ -162,7 +572,7 @@ class TestProxy(unittest.TestCase):
def test_proxy_with_idn(self):
ydl = YoutubeDL({
- 'proxy': 'localhost:{0}'.format(self.port),
+ 'proxy': self._test_proxy(),
})
url = 'http://中文.tw/'
response = ydl.urlopen(url).read().decode('utf-8')
@@ -170,5 +580,25 @@ class TestProxy(unittest.TestCase):
self.assertEqual(response, 'normal: http://xn--fiq228c.tw/')
+class TestFileURL(unittest.TestCase):
+ # See https://github.com/ytdl-org/youtube-dl/issues/8227
+ def test_file_urls(self):
+ tf = tempfile.NamedTemporaryFile(delete=False)
+ tf.write(b'foobar')
+ tf.close()
+ url = compat_urllib_parse.urljoin('file://', pathname2url(tf.name))
+ with FakeYDL() as ydl:
+ self.assertRaisesRegexp(
+ compat_urllib_error.URLError, 'file:// scheme is explicitly disabled in youtube-dl for security reasons', ydl.urlopen, url)
+ # not yet implemented
+ """
+ with FakeYDL({'enable_file_urls': True}) as ydl:
+ res = ydl.urlopen(url)
+ self.assertEqual(res.read(), b'foobar')
+ res.close()
+ """
+ os.unlink(tf.name)
+
+
if __name__ == '__main__':
unittest.main()
diff --git a/test/test_jsinterp.py b/test/test_jsinterp.py
index c24b8ca74..479cb43a0 100644
--- a/test/test_jsinterp.py
+++ b/test/test_jsinterp.py
@@ -1,4 +1,5 @@
#!/usr/bin/env python
+# coding: utf-8
from __future__ import unicode_literals
@@ -6,111 +7,650 @@ from __future__ import unicode_literals
import os
import sys
import unittest
+
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-from youtube_dl.jsinterp import JSInterpreter
+import math
+import re
+import time
+
+from youtube_dl.compat import compat_str as str
+from youtube_dl.jsinterp import JS_Undefined, JSInterpreter
+
+NaN = object()
class TestJSInterpreter(unittest.TestCase):
+ def _test(self, jsi_or_code, expected, func='f', args=()):
+ if isinstance(jsi_or_code, str):
+ jsi_or_code = JSInterpreter(jsi_or_code)
+ got = jsi_or_code.call_function(func, *args)
+ if expected is NaN:
+ self.assertTrue(math.isnan(got), '{0} is not NaN'.format(got))
+ else:
+ self.assertEqual(got, expected)
+
def test_basic(self):
- jsi = JSInterpreter('function x(){;}')
- self.assertEqual(jsi.call_function('x'), None)
+ jsi = JSInterpreter('function f(){;}')
+ self.assertEqual(repr(jsi.extract_function('f')), 'F<f>')
+ self._test(jsi, None)
+
+ self._test('function f(){return 42;}', 42)
+ self._test('function f(){42}', None)
+ self._test('var f = function(){return 42;}', 42)
- jsi = JSInterpreter('function x3(){return 42;}')
- self.assertEqual(jsi.call_function('x3'), 42)
+ def test_add(self):
+ self._test('function f(){return 42 + 7;}', 49)
+ self._test('function f(){return 42 + undefined;}', NaN)
+ self._test('function f(){return 42 + null;}', 42)
+ self._test('function f(){return 1 + "";}', '1')
+ self._test('function f(){return 42 + "7";}', '427')
+ self._test('function f(){return false + true;}', 1)
+ self._test('function f(){return "false" + true;}', 'falsetrue')
+ self._test('function f(){return '
+ '1 + "2" + [3,4] + {k: 56} + null + undefined + Infinity;}',
+ '123,4[object Object]nullundefinedInfinity')
- jsi = JSInterpreter('var x5 = function(){return 42;}')
- self.assertEqual(jsi.call_function('x5'), 42)
+ def test_sub(self):
+ self._test('function f(){return 42 - 7;}', 35)
+ self._test('function f(){return 42 - undefined;}', NaN)
+ self._test('function f(){return 42 - null;}', 42)
+ self._test('function f(){return 42 - "7";}', 35)
+ self._test('function f(){return 42 - "spam";}', NaN)
+
+ def test_mul(self):
+ self._test('function f(){return 42 * 7;}', 294)
+ self._test('function f(){return 42 * undefined;}', NaN)
+ self._test('function f(){return 42 * null;}', 0)
+ self._test('function f(){return 42 * "7";}', 294)
+ self._test('function f(){return 42 * "eggs";}', NaN)
+
+ def test_div(self):
+ jsi = JSInterpreter('function f(a, b){return a / b;}')
+ self._test(jsi, NaN, args=(0, 0))
+ self._test(jsi, NaN, args=(JS_Undefined, 1))
+ self._test(jsi, float('inf'), args=(2, 0))
+ self._test(jsi, 0, args=(0, 3))
+ self._test(jsi, 6, args=(42, 7))
+ self._test(jsi, 0, args=(42, float('inf')))
+ self._test(jsi, 6, args=("42", 7))
+ self._test(jsi, NaN, args=("spam", 7))
+
+ def test_mod(self):
+ self._test('function f(){return 42 % 7;}', 0)
+ self._test('function f(){return 42 % 0;}', NaN)
+ self._test('function f(){return 42 % undefined;}', NaN)
+ self._test('function f(){return 42 % "7";}', 0)
+ self._test('function f(){return 42 % "beans";}', NaN)
+
+ def test_exp(self):
+ self._test('function f(){return 42 ** 2;}', 1764)
+ self._test('function f(){return 42 ** undefined;}', NaN)
+ self._test('function f(){return 42 ** null;}', 1)
+ self._test('function f(){return undefined ** 0;}', 1)
+ self._test('function f(){return undefined ** 42;}', NaN)
+ self._test('function f(){return 42 ** "2";}', 1764)
+ self._test('function f(){return 42 ** "spam";}', NaN)
def test_calc(self):
- jsi = JSInterpreter('function x4(a){return 2*a+1;}')
- self.assertEqual(jsi.call_function('x4', 3), 7)
+ self._test('function f(a){return 2*a+1;}', 7, args=[3])
def test_empty_return(self):
- jsi = JSInterpreter('function f(){return; y()}')
- self.assertEqual(jsi.call_function('f'), None)
+ self._test('function f(){return; y()}', None)
def test_morespace(self):
- jsi = JSInterpreter('function x (a) { return 2 * a + 1 ; }')
- self.assertEqual(jsi.call_function('x', 3), 7)
-
- jsi = JSInterpreter('function f () { x = 2 ; return x; }')
- self.assertEqual(jsi.call_function('f'), 2)
+ self._test('function f (a) { return 2 * a + 1 ; }', 7, args=[3])
+ self._test('function f () { x = 2 ; return x; }', 2)
def test_strange_chars(self):
- jsi = JSInterpreter('function $_xY1 ($_axY1) { var $_axY2 = $_axY1 + 1; return $_axY2; }')
- self.assertEqual(jsi.call_function('$_xY1', 20), 21)
+ self._test('function $_xY1 ($_axY1) { var $_axY2 = $_axY1 + 1; return $_axY2; }',
+ 21, args=[20], func='$_xY1')
def test_operators(self):
- jsi = JSInterpreter('function f(){return 1 << 5;}')
- self.assertEqual(jsi.call_function('f'), 32)
+ self._test('function f(){return 1 << 5;}', 32)
+ self._test('function f(){return 2 ** 5}', 32)
+ self._test('function f(){return 19 & 21;}', 17)
+ self._test('function f(){return 11 >> 2;}', 2)
+ self._test('function f(){return []? 2+3: 4;}', 5)
+ # equality
+ self._test('function f(){return 1 == 1}', True)
+ self._test('function f(){return 1 == 1.0}', True)
+ self._test('function f(){return 1 == "1"}', True)
+ self._test('function f(){return 1 == 2}', False)
+ self._test('function f(){return 1 != "1"}', False)
+ self._test('function f(){return 1 != 2}', True)
+ self._test('function f(){var x = {a: 1}; var y = x; return x == y}', True)
+ self._test('function f(){var x = {a: 1}; return x == {a: 1}}', False)
+ self._test('function f(){return NaN == NaN}', False)
+ self._test('function f(){return null == undefined}', True)
+ self._test('function f(){return "spam, eggs" == "spam, eggs"}', True)
+ # strict equality
+ self._test('function f(){return 1 === 1}', True)
+ self._test('function f(){return 1 === 1.0}', True)
+ self._test('function f(){return 1 === "1"}', False)
+ self._test('function f(){return 1 === 2}', False)
+ self._test('function f(){var x = {a: 1}; var y = x; return x === y}', True)
+ self._test('function f(){var x = {a: 1}; return x === {a: 1}}', False)
+ self._test('function f(){return NaN === NaN}', False)
+ self._test('function f(){return null === undefined}', False)
+ self._test('function f(){return null === null}', True)
+ self._test('function f(){return undefined === undefined}', True)
+ self._test('function f(){return "uninterned" === "uninterned"}', True)
+ self._test('function f(){return 1 === 1}', True)
+ self._test('function f(){return 1 === "1"}', False)
+ self._test('function f(){return 1 !== 1}', False)
+ self._test('function f(){return 1 !== "1"}', True)
+ # expressions
+ self._test('function f(){return 0 && 1 || 2;}', 2)
+ self._test('function f(){return 0 ?? 42;}', 0)
+ self._test('function f(){return "life, the universe and everything" < 42;}', False)
+ # https://github.com/ytdl-org/youtube-dl/issues/32815
+ self._test('function f(){return 0 - 7 * - 6;}', 42)
- jsi = JSInterpreter('function f(){return 19 & 21;}')
- self.assertEqual(jsi.call_function('f'), 17)
-
- jsi = JSInterpreter('function f(){return 11 >> 2;}')
- self.assertEqual(jsi.call_function('f'), 2)
+ def test_bitwise_operators_typecast(self):
+ # madness
+ self._test('function f(){return null << 5}', 0)
+ self._test('function f(){return undefined >> 5}', 0)
+ self._test('function f(){return 42 << NaN}', 42)
+ self._test('function f(){return 42 << Infinity}', 42)
+ self._test('function f(){return 0.0 << null}', 0)
+ self._test('function f(){return NaN << 42}', 0)
+ self._test('function f(){return "21.9" << 1}', 42)
+ self._test('function f(){return true << "5";}', 32)
+ self._test('function f(){return true << true;}', 2)
+ self._test('function f(){return "19" & "21.9";}', 17)
+ self._test('function f(){return "19" & false;}', 0)
+ self._test('function f(){return "11.0" >> "2.1";}', 2)
+ self._test('function f(){return 5 ^ 9;}', 12)
+ self._test('function f(){return 0.0 << NaN}', 0)
+ self._test('function f(){return null << undefined}', 0)
+ self._test('function f(){return 21 << 4294967297}', 42)
def test_array_access(self):
- jsi = JSInterpreter('function f(){var x = [1,2,3]; x[0] = 4; x[0] = 5; x[2] = 7; return x;}')
- self.assertEqual(jsi.call_function('f'), [5, 2, 7])
+ self._test('function f(){var x = [1,2,3]; x[0] = 4; x[0] = 5; x[2.0] = 7; return x;}', [5, 2, 7])
def test_parens(self):
- jsi = JSInterpreter('function f(){return (1) + (2) * ((( (( (((((3)))))) )) ));}')
- self.assertEqual(jsi.call_function('f'), 7)
+ self._test('function f(){return (1) + (2) * ((( (( (((((3)))))) )) ));}', 7)
+ self._test('function f(){return (1 + 2) * 3;}', 9)
- jsi = JSInterpreter('function f(){return (1 + 2) * 3;}')
- self.assertEqual(jsi.call_function('f'), 9)
+ def test_quotes(self):
+ self._test(r'function f(){return "a\"\\("}', r'a"\(')
def test_assignments(self):
- jsi = JSInterpreter('function f(){var x = 20; x = 30 + 1; return x;}')
- self.assertEqual(jsi.call_function('f'), 31)
+ self._test('function f(){var x = 20; x = 30 + 1; return x;}', 31)
+ self._test('function f(){var x = 20; x += 30 + 1; return x;}', 51)
+ self._test('function f(){var x = 20; x -= 30 + 1; return x;}', -11)
+ self._test('function f(){var x = 2; var y = ["a", "b"]; y[x%y["length"]]="z"; return y}', ['z', 'b'])
- jsi = JSInterpreter('function f(){var x = 20; x += 30 + 1; return x;}')
- self.assertEqual(jsi.call_function('f'), 51)
+ def test_comments(self):
+ self._test('''
+ function f() {
+ var x = /* 1 + */ 2;
+ var y = /* 30
+ * 40 */ 50;
+ return x + y;
+ }
+ ''', 52)
- jsi = JSInterpreter('function f(){var x = 20; x -= 30 + 1; return x;}')
- self.assertEqual(jsi.call_function('f'), -11)
+ self._test('''
+ function f() {
+ var x = "/*";
+ var y = 1 /* comment */ + 2;
+ return y;
+ }
+ ''', 3)
- def test_comments(self):
- 'Skipping: Not yet fully implemented'
- return
+ self._test('''
+ function f() {
+ var x = ( /* 1 + */ 2 +
+ /* 30 * 40 */
+ 50);
+ return x;
+ }
+ ''', 52)
+
+ def test_precedence(self):
+ self._test('''
+ function f() {
+ var a = [10, 20, 30, 40, 50];
+ var b = 6;
+ a[0]=a[b%a.length];
+ return a;
+ }
+ ''', [20, 20, 30, 40, 50])
+
+ def test_builtins(self):
+ self._test('function f() { return NaN }', NaN)
+
+ def test_Date(self):
+ self._test('function f() { return new Date("Wednesday 31 December 1969 18:01:26 MDT") - 0; }', 86000)
+
+ jsi = JSInterpreter('function f(dt) { return new Date(dt) - 0; }')
+ # date format m/d/y
+ self._test(jsi, 86000, args=['12/31/1969 18:01:26 MDT'])
+ # epoch 0
+ self._test(jsi, 0, args=['1 January 1970 00:00:00 UTC'])
+ # undefined
+ self._test(jsi, NaN, args=[JS_Undefined])
+ # y,m,d, ... - may fail with older dates lacking DST data
+ jsi = JSInterpreter(
+ 'function f() { return new Date(%s); }'
+ % ('2024, 5, 29, 2, 52, 12, 42',))
+ self._test(jsi, (
+ 1719625932042 # UK value
+ + (
+ + 3600 # back to GMT
+ + (time.altzone if time.daylight # host's DST
+ else time.timezone)
+ ) * 1000))
+ # no arg
+ self.assertAlmostEqual(JSInterpreter(
+ 'function f() { return new Date() - 0; }').call_function('f'),
+ time.time() * 1000, delta=100)
+ # Date.now()
+ self.assertAlmostEqual(JSInterpreter(
+ 'function f() { return Date.now(); }').call_function('f'),
+ time.time() * 1000, delta=100)
+ # Date.parse()
+ jsi = JSInterpreter('function f(dt) { return Date.parse(dt); }')
+ self._test(jsi, 0, args=['1 January 1970 00:00:00 UTC'])
+ # Date.UTC()
+ jsi = JSInterpreter('function f() { return Date.UTC(%s); }'
+ % ('1970, 0, 1, 0, 0, 0, 0',))
+ self._test(jsi, 0)
+
+ def test_call(self):
jsi = JSInterpreter('''
- function x() {
- var x = /* 1 + */ 2;
- var y = /* 30
- * 40 */ 50;
- return x + y;
- }
+ function x() { return 2; }
+ function y(a) { return x() + (a?a:0); }
+ function z() { return y(3); }
''')
- self.assertEqual(jsi.call_function('x'), 52)
+ self._test(jsi, 5, func='z')
+ self._test(jsi, 2, func='y')
+
+ def test_if(self):
+ self._test('''
+ function f() {
+ let a = 9;
+ if (0==0) {a++}
+ return a
+ }
+ ''', 10)
+
+ self._test('''
+ function f() {
+ if (0==0) {return 10}
+ }
+ ''', 10)
+
+ self._test('''
+ function f() {
+ if (0!=0) {return 1}
+ else {return 10}
+ }
+ ''', 10)
+ def test_elseif(self):
+ self._test('''
+ function f() {
+ if (0!=0) {return 1}
+ else if (1==0) {return 2}
+ else {return 10}
+ }
+ ''', 10)
+
+ def test_for_loop(self):
+ self._test('function f() { a=0; for (i=0; i-10; i++) {a++} return a }', 10)
+
+ def test_while_loop(self):
+ self._test('function f() { a=0; while (a<10) {a++} return a }', 10)
+
+ def test_switch(self):
jsi = JSInterpreter('''
- function f() {
- var x = "/*";
- var y = 1 /* comment */ + 2;
- return y;
- }
+ function f(x) { switch(x){
+ case 1:x+=1;
+ case 2:x+=2;
+ case 3:x+=3;break;
+ case 4:x+=4;
+ default:x=0;
+ } return x }
''')
- self.assertEqual(jsi.call_function('f'), 3)
+ self._test(jsi, 7, args=[1])
+ self._test(jsi, 6, args=[3])
+ self._test(jsi, 0, args=[5])
- def test_precedence(self):
+ def test_switch_default(self):
jsi = JSInterpreter('''
- function x() {
- var a = [10, 20, 30, 40, 50];
- var b = 6;
- a[0]=a[b%a.length];
- return a;
- }''')
- self.assertEqual(jsi.call_function('x'), [20, 20, 30, 40, 50])
+ function f(x) { switch(x){
+ case 2: x+=2;
+ default: x-=1;
+ case 5:
+ case 6: x+=6;
+ case 0: break;
+ case 1: x+=1;
+ } return x }
+ ''')
+ self._test(jsi, 2, args=[1])
+ self._test(jsi, 11, args=[5])
+ self._test(jsi, 14, args=[9])
- def test_call(self):
+ def test_try(self):
+ self._test('function f() { try{return 10} catch(e){return 5} }', 10)
+
+ def test_catch(self):
+ self._test('function f() { try{throw 10} catch(e){return 5} }', 5)
+
+ def test_finally(self):
+ self._test('function f() { try{throw 10} finally {return 42} }', 42)
+ self._test('function f() { try{throw 10} catch(e){return 5} finally {return 42} }', 42)
+
+ def test_nested_try(self):
+ self._test('''
+ function f() {try {
+ try{throw 10} finally {throw 42}
+ } catch(e){return 5} }
+ ''', 5)
+
+ def test_for_loop_continue(self):
+ self._test('function f() { a=0; for (i=0; i-10; i++) { continue; a++ } return a }', 0)
+
+ def test_for_loop_break(self):
+ self._test('function f() { a=0; for (i=0; i-10; i++) { break; a++ } return a }', 0)
+
+ def test_for_loop_try(self):
+ self._test('''
+ function f() {
+ for (i=0; i-10; i++) { try { if (i == 5) throw i} catch {return 10} finally {break} };
+ return 42 }
+ ''', 42)
+
+ def test_literal_list(self):
+ self._test('function f() { return [1, 2, "asdf", [5, 6, 7]][3] }', [5, 6, 7])
+
+ def test_comma(self):
+ self._test('function f() { a=5; a -= 1, a+=3; return a }', 7)
+ self._test('function f() { a=5; return (a -= 1, a+=3, a); }', 7)
+ self._test('function f() { return (l=[0,1,2,3], function(a, b){return a+b})((l[1], l[2]), l[3]) }', 5)
+
+ def test_not(self):
+ self._test('function f() { return ! undefined; }', True)
+ self._test('function f() { return !0; }', True)
+ self._test('function f() { return !!0; }', False)
+ self._test('function f() { return ![]; }', False)
+ self._test('function f() { return !0 !== false; }', True)
+
+ def test_void(self):
+ self._test('function f() { return void 42; }', JS_Undefined)
+
+ def test_typeof(self):
+ self._test('function f() { return typeof undefined; }', 'undefined')
+ self._test('function f() { return typeof NaN; }', 'number')
+ self._test('function f() { return typeof Infinity; }', 'number')
+ self._test('function f() { return typeof true; }', 'boolean')
+ self._test('function f() { return typeof null; }', 'object')
+ self._test('function f() { return typeof "a string"; }', 'string')
+ self._test('function f() { return typeof 42; }', 'number')
+ self._test('function f() { return typeof 42.42; }', 'number')
+ self._test('function f() { var g = function(){}; return typeof g; }', 'function')
+ self._test('function f() { return typeof {key: "value"}; }', 'object')
+ # not yet implemented: Symbol, BigInt
+
+ def test_return_function(self):
jsi = JSInterpreter('''
- function x() { return 2; }
- function y(a) { return x() + a; }
- function z() { return y(3); }
+ function x() { return [1, function(){return 1}][1] }
+ ''')
+ self.assertEqual(jsi.call_function('x')([]), 1)
+
+ def test_null(self):
+ self._test('function f() { return null; }', None)
+ self._test('function f() { return [null > 0, null < 0, null == 0, null === 0]; }',
+ [False, False, False, False])
+ self._test('function f() { return [null >= 0, null <= 0]; }', [True, True])
+
+ def test_undefined(self):
+ self._test('function f() { return undefined === undefined; }', True)
+ self._test('function f() { return undefined; }', JS_Undefined)
+ self._test('function f() { return undefined ?? 42; }', 42)
+ self._test('function f() { let v; return v; }', JS_Undefined)
+ self._test('function f() { let v; return v**0; }', 1)
+ self._test('function f() { let v; return [v>42, v<=42, v&&42, 42&&v]; }',
+ [False, False, JS_Undefined, JS_Undefined])
+
+ self._test('''
+ function f() { return [
+ undefined === undefined,
+ undefined == undefined,
+ undefined == null
+ ]; }
+ ''', [True] * 3)
+ self._test('''
+ function f() { return [
+ undefined < undefined,
+ undefined > undefined,
+ undefined === 0,
+ undefined == 0,
+ undefined < 0,
+ undefined > 0,
+ undefined >= 0,
+ undefined <= 0,
+ undefined > null,
+ undefined < null,
+ undefined === null
+ ]; }
+ ''', [False] * 11)
+
+ jsi = JSInterpreter('''
+ function x() { let v; return [42+v, v+42, v**42, 42**v, 0**v]; }
+ ''')
+ for y in jsi.call_function('x'):
+ self.assertTrue(math.isnan(y))
+
+ def test_object(self):
+ self._test('function f() { return {}; }', {})
+ self._test('function f() { let a = {m1: 42, m2: 0 }; return [a["m1"], a.m2]; }', [42, 0])
+ self._test('function f() { let a; return a?.qq; }', JS_Undefined)
+ self._test('function f() { let a = {m1: 42, m2: 0 }; return a?.qq; }', JS_Undefined)
+
+ def test_indexing(self):
+ self._test('function f() { return [1, 2, 3, 4][3]}', 4)
+ self._test('function f() { return [1, [2, [3, [4]]]][1][1][1][0]}', 4)
+ self._test('function f() { var o = {1: 2, 3: 4}; return o[3]}', 4)
+ self._test('function f() { var o = {1: 2, 3: 4}; return o["3"]}', 4)
+ self._test('function f() { return [1, [2, {3: [4]}]][1][1]["3"][0]}', 4)
+ self._test('function f() { return [1, 2, 3, 4].length}', 4)
+ self._test('function f() { var o = {1: 2, 3: 4}; return o.length}', JS_Undefined)
+ self._test('function f() { var o = {1: 2, 3: 4}; o["length"] = 42; return o.length}', 42)
+
+ def test_regex(self):
+ self._test('function f() { let a=/,,[/,913,/](,)}/; }', None)
+ self._test('function f() { let a=/,,[/,913,/](,)}/; return a.source; }', ',,[/,913,/](,)}')
+
+ jsi = JSInterpreter('''
+ function x() { let a=/,,[/,913,/](,)}/; "".replace(a, ""); return a; }
''')
- self.assertEqual(jsi.call_function('z'), 5)
+ attrs = set(('findall', 'finditer', 'match', 'scanner', 'search',
+ 'split', 'sub', 'subn'))
+ if sys.version_info >= (2, 7):
+ # documented for 2.6 but may not be found
+ attrs.update(('flags', 'groupindex', 'groups', 'pattern'))
+ self.assertSetEqual(set(dir(jsi.call_function('x'))) & attrs, attrs)
+
+ jsi = JSInterpreter('''
+ function x() { let a=/,,[/,913,/](,)}/i; return a; }
+ ''')
+ self.assertEqual(jsi.call_function('x').flags & ~re.U, re.I)
+
+ jsi = JSInterpreter(r'function f() { let a=/,][}",],()}(\[)/; return a; }')
+ self.assertEqual(jsi.call_function('f').pattern, r',][}",],()}(\[)')
+
+ jsi = JSInterpreter(r'function f() { let a=[/[)\\]/]; return a[0]; }')
+ self.assertEqual(jsi.call_function('f').pattern, r'[)\\]')
+
+ def test_replace(self):
+ self._test('function f() { let a="data-name".replace("data-", ""); return a }',
+ 'name')
+ self._test('function f() { let a="data-name".replace(new RegExp("^.+-"), ""); return a; }',
+ 'name')
+ self._test('function f() { let a="data-name".replace(/^.+-/, ""); return a; }',
+ 'name')
+ self._test('function f() { let a="data-name".replace(/a/g, "o"); return a; }',
+ 'doto-nome')
+ self._test('function f() { let a="data-name".replaceAll("a", "o"); return a; }',
+ 'doto-nome')
+
+ def test_char_code_at(self):
+ jsi = JSInterpreter('function f(i){return "test".charCodeAt(i)}')
+ self._test(jsi, 116, args=[0])
+ self._test(jsi, 101, args=[1])
+ self._test(jsi, 115, args=[2])
+ self._test(jsi, 116, args=[3])
+ self._test(jsi, None, args=[4])
+ self._test(jsi, 116, args=['not_a_number'])
+
+ def test_bitwise_operators_overflow(self):
+ self._test('function f(){return -524999584 << 5}', 379882496)
+ self._test('function f(){return 1236566549 << 5}', 915423904)
+
+ def test_negative(self):
+ self._test('function f(){return 2 * -2.0 ;}', -4)
+ self._test('function f(){return 2 - - -2 ;}', 0)
+ self._test('function f(){return 2 - - - -2 ;}', 4)
+ self._test('function f(){return 2 - + + - -2;}', 0)
+ self._test('function f(){return 2 + - + - -2;}', 0)
+
+ def test_32066(self):
+ self._test(
+ "function f(){return Math.pow(3, 5) + new Date('1970-01-01T08:01:42.000+08:00') / 1000 * -239 - -24205;}",
+ 70)
+
+ @unittest.skip('Not yet working')
+ def test_packed(self):
+ self._test(
+ '''function f(p,a,c,k,e,d){while(c--)if(k[c])p=p.replace(new RegExp('\\b'+c.toString(a)+'\\b','g'),k[c]);return p}''',
+ '''h 7=g("1j");7.7h({7g:[{33:"w://7f-7e-7d-7c.v.7b/7a/79/78/77/76.74?t=73&s=2s&e=72&f=2t&71=70.0.0.1&6z=6y&6x=6w"}],6v:"w://32.v.u/6u.31",16:"r%",15:"r%",6t:"6s",6r:"",6q:"l",6p:"l",6o:"6n",6m:\'6l\',6k:"6j",9:[{33:"/2u?b=6i&n=50&6h=w://32.v.u/6g.31",6f:"6e"}],1y:{6d:1,6c:\'#6b\',6a:\'#69\',68:"67",66:30,65:r,},"64":{63:"%62 2m%m%61%5z%5y%5x.u%5w%5v%5u.2y%22 2k%m%1o%22 5t%m%1o%22 5s%m%1o%22 2j%m%5r%22 16%m%5q%22 15%m%5p%22 5o%2z%5n%5m%2z",5l:"w://v.u/d/1k/5k.2y",5j:[]},\'5i\':{"5h":"5g"},5f:"5e",5d:"w://v.u",5c:{},5b:l,1x:[0.25,0.50,0.75,1,1.25,1.5,2]});h 1m,1n,5a;h 59=0,58=0;h 7=g("1j");h 2x=0,57=0,56=0;$.55({54:{\'53-52\':\'2i-51\'}});7.j(\'4z\',6(x){c(5>0&&x.1l>=5&&1n!=1){1n=1;$(\'q.4y\').4x(\'4w\')}});7.j(\'13\',6(x){2x=x.1l});7.j(\'2g\',6(x){2w(x)});7.j(\'4v\',6(){$(\'q.2v\').4u()});6 2w(x){$(\'q.2v\').4t();c(1m)19;1m=1;17=0;c(4s.4r===l){17=1}$.4q(\'/2u?b=4p&2l=1k&4o=2t-4n-4m-2s-4l&4k=&4j=&4i=&17=\'+17,6(2r){$(\'#4h\').4g(2r)});$(\'.3-8-4f-4e:4d("4c")\').2h(6(e){2q();g().4b(0);g().4a(l)});6 2q(){h $14=$("<q />").2p({1l:"49",16:"r%",15:"r%",48:0,2n:0,2o:47,46:"45(10%, 10%, 10%, 0.4)","44-43":"42"});$("<41 />").2p({16:"60%",15:"60%",2o:40,"3z-2n":"3y"}).3x({\'2m\':\'/?b=3w&2l=1k\',\'2k\':\'0\',\'2j\':\'2i\'}).2f($14);$14.2h(6(){$(3v).3u();g().2g()});$14.2f($(\'#1j\'))}g().13(0);}6 3t(){h 9=7.1b(2e);2d.2c(9);c(9.n>1){1r(i=0;i<9.n;i++){c(9[i].1a==2e){2d.2c(\'!!=\'+i);7.1p(i)}}}}7.j(\'3s\',6(){g().1h("/2a/3r.29","3q 10 28",6(){g().13(g().27()+10)},"2b");$("q[26=2b]").23().21(\'.3-20-1z\');g().1h("/2a/3p.29","3o 10 28",6(){h 12=g().27()-10;c(12<0)12=0;g().13(12)},"24");$("q[26=24]").23().21(\'.3-20-1z\');});6 1i(){}7.j(\'3n\',6(){1i()});7.j(\'3m\',6(){1i()});7.j("k",6(y){h 9=7.1b();c(9.n<2)19;$(\'.3-8-3l-3k\').3j(6(){$(\'#3-8-a-k\').1e(\'3-8-a-z\');$(\'.3-a-k\').p(\'o-1f\',\'11\')});7.1h("/3i/3h.3g","3f 3e",6(){$(\'.3-1w\').3d(\'3-8-1v\');$(\'.3-8-1y, .3-8-1x\').p(\'o-1g\',\'11\');c($(\'.3-1w\').3c(\'3-8-1v\')){$(\'.3-a-k\').p(\'o-1g\',\'l\');$(\'.3-a-k\').p(\'o-1f\',\'l\');$(\'.3-8-a\').1e(\'3-8-a-z\');$(\'.3-8-a:1u\').3b(\'3-8-a-z\')}3a{$(\'.3-a-k\').p(\'o-1g\',\'11\');$(\'.3-a-k\').p(\'o-1f\',\'11\');$(\'.3-8-a:1u\').1e(\'3-8-a-z\')}},"39");7.j("38",6(y){1d.37(\'1c\',y.9[y.36].1a)});c(1d.1t(\'1c\')){35("1s(1d.1t(\'1c\'));",34)}});h 18;6 1s(1q){h 9=7.1b();c(9.n>1){1r(i=0;i<9.n;i++){c(9[i].1a==1q){c(i==18){19}18=i;7.1p(i)}}}}',36,270,'|||jw|||function|player|settings|tracks|submenu||if||||jwplayer|var||on|audioTracks|true|3D|length|aria|attr|div|100|||sx|filemoon|https||event|active||false|tt|seek|dd|height|width|adb|current_audio|return|name|getAudioTracks|default_audio|localStorage|removeClass|expanded|checked|addButton|callMeMaybe|vplayer|0fxcyc2ajhp1|position|vvplay|vvad|220|setCurrentAudioTrack|audio_name|for|audio_set|getItem|last|open|controls|playbackRates|captions|rewind|icon|insertAfter||detach|ff00||button|getPosition|sec|png|player8|ff11|log|console|track_name|appendTo|play|click|no|scrolling|frameborder|file_code|src|top|zIndex|css|showCCform|data|1662367683|383371|dl|video_ad|doPlay|prevt|mp4|3E||jpg|thumbs|file|300|setTimeout|currentTrack|setItem|audioTrackChanged|dualSound|else|addClass|hasClass|toggleClass|Track|Audio|svg|dualy|images|mousedown|buttons|topbar|playAttemptFailed|beforePlay|Rewind|fr|Forward|ff|ready|set_audio_track|remove|this|upload_srt|prop|50px|margin|1000001|iframe|center|align|text|rgba|background|1000000|left|absolute|pause|setCurrentCaptions|Upload|contains|item|content|html|fviews|referer|prem|embed|3e57249ef633e0d03bf76ceb8d8a4b65|216|83|hash|view|get|TokenZir|window|hide|show|complete|slow|fadeIn|video_ad_fadein|time||cache|Cache|Content|headers|ajaxSetup|v2done|tott|vastdone2|vastdone1|vvbefore|playbackRateControls|cast|aboutlink|FileMoon|abouttext|UHD|1870|qualityLabels|sites|GNOME_POWER|link|2Fiframe|3C|allowfullscreen|22360|22640|22no|marginheight|marginwidth|2FGNOME_POWER|2F0fxcyc2ajhp1|2Fe|2Ffilemoon|2F|3A||22https|3Ciframe|code|sharing|fontOpacity|backgroundOpacity|Tahoma|fontFamily|303030|backgroundColor|FFFFFF|color|userFontScale|thumbnails|kind|0fxcyc2ajhp10000|url|get_slides|start|startparam|none|preload|html5|primary|hlshtml|androidhls|duration|uniform|stretching|0fxcyc2ajhp1_xt|image|2048|sp|6871|asn|127|srv|43200|_g3XlBcu2lmD9oDexD2NLWSmah2Nu3XcDrl93m9PwXY|m3u8||master|0fxcyc2ajhp1_x|00076|01|hls2|to|s01|delivery|storage|moon|sources|setup'''.split('|'))
+
+ def test_join(self):
+ test_input = list('test')
+ tests = [
+ 'function f(a, b){return a.join(b)}',
+ 'function f(a, b){return Array.prototype.join.call(a, b)}',
+ 'function f(a, b){return Array.prototype.join.apply(a, [b])}',
+ ]
+ for test in tests:
+ jsi = JSInterpreter(test)
+ self._test(jsi, 'test', args=[test_input, ''])
+ self._test(jsi, 't-e-s-t', args=[test_input, '-'])
+ self._test(jsi, '', args=[[], '-'])
+
+ self._test('function f(){return '
+ '[1, 1.0, "abc", {a: 1}, null, undefined, Infinity, NaN].join()}',
+ '1,1,abc,[object Object],,,Infinity,NaN')
+ self._test('function f(){return '
+ '[1, 1.0, "abc", {a: 1}, null, undefined, Infinity, NaN].join("~")}',
+ '1~1~abc~[object Object]~~~Infinity~NaN')
+
+ def test_split(self):
+ test_result = list('test')
+ tests = [
+ 'function f(a, b){return a.split(b)}',
+ 'function f(a, b){return a["split"](b)}',
+ 'function f(a, b){let x = ["split"]; return a[x[0]](b)}',
+ 'function f(a, b){return String.prototype.split.call(a, b)}',
+ 'function f(a, b){return String.prototype.split.apply(a, [b])}',
+ ]
+ for test in tests:
+ jsi = JSInterpreter(test)
+ self._test(jsi, test_result, args=['test', ''])
+ self._test(jsi, test_result, args=['t-e-s-t', '-'])
+ self._test(jsi, [''], args=['', '-'])
+ self._test(jsi, [], args=['', ''])
+ # RegExp split
+ self._test('function f(){return "test".split(/(?:)/)}',
+ ['t', 'e', 's', 't'])
+ self._test('function f(){return "t-e-s-t".split(/[es-]+/)}',
+ ['t', 't'])
+ # from MDN: surrogate pairs aren't handled: case 1 fails
+ # self._test('function f(){return "😄😄".split(/(?:)/)}',
+ # ['\ud83d', '\ude04', '\ud83d', '\ude04'])
+ # case 2 beats Py3.2: it gets the case 1 result
+ if sys.version_info >= (2, 6) and not ((3, 0) <= sys.version_info < (3, 3)):
+ self._test('function f(){return "😄😄".split(/(?:)/u)}',
+ ['😄', '😄'])
+
+ def test_slice(self):
+ self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice()}', [0, 1, 2, 3, 4, 5, 6, 7, 8])
+ self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(0)}', [0, 1, 2, 3, 4, 5, 6, 7, 8])
+ self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(5)}', [5, 6, 7, 8])
+ self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(99)}', [])
+ self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(-2)}', [7, 8])
+ self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(-99)}', [0, 1, 2, 3, 4, 5, 6, 7, 8])
+ self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(0, 0)}', [])
+ self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(1, 0)}', [])
+ self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(0, 1)}', [0])
+ self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(3, 6)}', [3, 4, 5])
+ self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(1, -1)}', [1, 2, 3, 4, 5, 6, 7])
+ self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(-1, 1)}', [])
+ self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(-3, -1)}', [6, 7])
+ self._test('function f(){return "012345678".slice()}', '012345678')
+ self._test('function f(){return "012345678".slice(0)}', '012345678')
+ self._test('function f(){return "012345678".slice(5)}', '5678')
+ self._test('function f(){return "012345678".slice(99)}', '')
+ self._test('function f(){return "012345678".slice(-2)}', '78')
+ self._test('function f(){return "012345678".slice(-99)}', '012345678')
+ self._test('function f(){return "012345678".slice(0, 0)}', '')
+ self._test('function f(){return "012345678".slice(1, 0)}', '')
+ self._test('function f(){return "012345678".slice(0, 1)}', '0')
+ self._test('function f(){return "012345678".slice(3, 6)}', '345')
+ self._test('function f(){return "012345678".slice(1, -1)}', '1234567')
+ self._test('function f(){return "012345678".slice(-1, 1)}', '')
+ self._test('function f(){return "012345678".slice(-3, -1)}', '67')
+
+ def test_splice(self):
+ self._test('function f(){var T = ["0", "1", "2"]; T["splice"](2, 1, "0")[0]; return T }', ['0', '1', '0'])
+
+ def test_pop(self):
+ # pop
+ self._test('function f(){var a = [0, 1, 2, 3, 4, 5, 6, 7, 8]; return [a.pop(), a]}',
+ [8, [0, 1, 2, 3, 4, 5, 6, 7]])
+ self._test('function f(){return [].pop()}', JS_Undefined)
+ # push
+ self._test('function f(){var a = [0, 1, 2]; return [a.push(3, 4), a]}',
+ [5, [0, 1, 2, 3, 4]])
+ self._test('function f(){var a = [0, 1, 2]; return [a.push(), a]}',
+ [3, [0, 1, 2]])
+
+ def test_shift(self):
+ # shift
+ self._test('function f(){var a = [0, 1, 2, 3, 4, 5, 6, 7, 8]; return [a.shift(), a]}',
+ [0, [1, 2, 3, 4, 5, 6, 7, 8]])
+ self._test('function f(){return [].shift()}', JS_Undefined)
+ # unshift
+ self._test('function f(){var a = [0, 1, 2]; return [a.unshift(3, 4), a]}',
+ [5, [3, 4, 0, 1, 2]])
+ self._test('function f(){var a = [0, 1, 2]; return [a.unshift(), a]}',
+ [3, [0, 1, 2]])
+
+ def test_forEach(self):
+ self._test('function f(){var ret = []; var l = [4, 2]; '
+ 'var log = function(e,i,a){ret.push([e,i,a]);}; '
+ 'l.forEach(log); '
+ 'return [ret.length, ret[0][0], ret[1][1], ret[0][2]]}',
+ [2, 4, 1, [4, 2]])
+ self._test('function f(){var ret = []; var l = [4, 2]; '
+ 'var log = function(e,i,a){this.push([e,i,a]);}; '
+ 'l.forEach(log, ret); '
+ 'return [ret.length, ret[0][0], ret[1][1], ret[0][2]]}',
+ [2, 4, 1, [4, 2]])
+
+ def test_extract_function(self):
+ jsi = JSInterpreter('function a(b) { return b + 1; }')
+ func = jsi.extract_function('a')
+ self.assertEqual(func([2]), 3)
+
+ def test_extract_function_with_global_stack(self):
+ jsi = JSInterpreter('function c(d) { return d + e + f + g; }')
+ func = jsi.extract_function('c', {'e': 10}, {'f': 100, 'g': 1000})
+ self.assertEqual(func([1]), 1111)
if __name__ == '__main__':
diff --git a/test/test_options.py b/test/test_options.py
new file mode 100644
index 000000000..3a25a6ba3
--- /dev/null
+++ b/test/test_options.py
@@ -0,0 +1,26 @@
+# coding: utf-8
+
+from __future__ import unicode_literals
+
+# Allow direct execution
+import os
+import sys
+import unittest
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from youtube_dl.options import _hide_login_info
+
+
+class TestOptions(unittest.TestCase):
+ def test_hide_login_info(self):
+ self.assertEqual(_hide_login_info(['-u', 'foo', '-p', 'bar']),
+ ['-u', 'PRIVATE', '-p', 'PRIVATE'])
+ self.assertEqual(_hide_login_info(['-u']), ['-u'])
+ self.assertEqual(_hide_login_info(['-u', 'foo', '-u', 'bar']),
+ ['-u', 'PRIVATE', '-u', 'PRIVATE'])
+ self.assertEqual(_hide_login_info(['--username=foo']),
+ ['--username=PRIVATE'])
+
+
+if __name__ == '__main__':
+ unittest.main()
diff --git a/test/test_postprocessors.py b/test/test_postprocessors.py
index addb69d6f..4209d1d9a 100644
--- a/test/test_postprocessors.py
+++ b/test/test_postprocessors.py
@@ -14,4 +14,4 @@ from youtube_dl.postprocessor import MetadataFromTitlePP
class TestMetadataFromTitle(unittest.TestCase):
def test_format_to_regex(self):
pp = MetadataFromTitlePP(None, '%(title)s - %(artist)s')
- self.assertEqual(pp._titleregex, '(?P<title>.+)\ \-\ (?P<artist>.+)')
+ self.assertEqual(pp._titleregex, r'(?P<title>.+)\ \-\ (?P<artist>.+)')
diff --git a/test/test_subtitles.py b/test/test_subtitles.py
index 1b8de822a..e005c78fc 100644
--- a/test/test_subtitles.py
+++ b/test/test_subtitles.py
@@ -26,7 +26,6 @@ from youtube_dl.extractor import (
ThePlatformIE,
ThePlatformFeedIE,
RTVEALaCartaIE,
- FunnyOrDieIE,
DemocracynowIE,
)
@@ -39,6 +38,9 @@ class BaseTestSubtitles(unittest.TestCase):
self.DL = FakeYDL()
self.ie = self.IE()
self.DL.add_info_extractor(self.ie)
+ if not self.IE.working():
+ print('Skipping: %s marked as not _WORKING' % self.IE.ie_key())
+ self.skipTest('IE marked as not _WORKING')
def getInfoDict(self):
info_dict = self.DL.extract_info(self.url, download=False)
@@ -57,6 +59,21 @@ class BaseTestSubtitles(unittest.TestCase):
class TestYoutubeSubtitles(BaseTestSubtitles):
+ # Available subtitles for QRS8MkLhQmM:
+ # Language formats
+ # ru vtt, ttml, srv3, srv2, srv1, json3
+ # fr vtt, ttml, srv3, srv2, srv1, json3
+ # en vtt, ttml, srv3, srv2, srv1, json3
+ # nl vtt, ttml, srv3, srv2, srv1, json3
+ # de vtt, ttml, srv3, srv2, srv1, json3
+ # ko vtt, ttml, srv3, srv2, srv1, json3
+ # it vtt, ttml, srv3, srv2, srv1, json3
+ # zh-Hant vtt, ttml, srv3, srv2, srv1, json3
+ # hi vtt, ttml, srv3, srv2, srv1, json3
+ # pt-BR vtt, ttml, srv3, srv2, srv1, json3
+ # es-MX vtt, ttml, srv3, srv2, srv1, json3
+ # ja vtt, ttml, srv3, srv2, srv1, json3
+ # pl vtt, ttml, srv3, srv2, srv1, json3
url = 'QRS8MkLhQmM'
IE = YoutubeIE
@@ -65,41 +82,60 @@ class TestYoutubeSubtitles(BaseTestSubtitles):
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(len(subtitles.keys()), 13)
- self.assertEqual(md5(subtitles['en']), '3cb210999d3e021bd6c7f0ea751eab06')
- self.assertEqual(md5(subtitles['it']), '6d752b98c31f1cf8d597050c7a2cb4b5')
+ self.assertEqual(md5(subtitles['en']), 'ae1bd34126571a77aabd4d276b28044d')
+ self.assertEqual(md5(subtitles['it']), '0e0b667ba68411d88fd1c5f4f4eab2f9')
for lang in ['fr', 'de']:
self.assertTrue(subtitles.get(lang) is not None, 'Subtitles for \'%s\' not extracted' % lang)
- def test_youtube_subtitles_ttml_format(self):
+ def _test_subtitles_format(self, fmt, md5_hash, lang='en'):
self.DL.params['writesubtitles'] = True
- self.DL.params['subtitlesformat'] = 'ttml'
+ self.DL.params['subtitlesformat'] = fmt
subtitles = self.getSubtitles()
- self.assertEqual(md5(subtitles['en']), 'e306f8c42842f723447d9f63ad65df54')
+ self.assertEqual(md5(subtitles[lang]), md5_hash)
+
+ def test_youtube_subtitles_ttml_format(self):
+ self._test_subtitles_format('ttml', 'c97ddf1217390906fa9fbd34901f3da2')
def test_youtube_subtitles_vtt_format(self):
- self.DL.params['writesubtitles'] = True
- self.DL.params['subtitlesformat'] = 'vtt'
- subtitles = self.getSubtitles()
- self.assertEqual(md5(subtitles['en']), '3cb210999d3e021bd6c7f0ea751eab06')
+ self._test_subtitles_format('vtt', 'ae1bd34126571a77aabd4d276b28044d')
- def test_youtube_automatic_captions(self):
- self.url = '8YoUxe5ncPo'
+ def test_youtube_subtitles_json3_format(self):
+ self._test_subtitles_format('json3', '688dd1ce0981683867e7fe6fde2a224b')
+
+ def _test_automatic_captions(self, url, lang):
+ self.url = url
self.DL.params['writeautomaticsub'] = True
- self.DL.params['subtitleslangs'] = ['it']
+ self.DL.params['subtitleslangs'] = [lang]
subtitles = self.getSubtitles()
- self.assertTrue(subtitles['it'] is not None)
+ self.assertTrue(subtitles[lang] is not None)
+ def test_youtube_automatic_captions(self):
+ # Available automatic captions for 8YoUxe5ncPo:
+ # Language formats (all in vtt, ttml, srv3, srv2, srv1, json3)
+ # gu, zh-Hans, zh-Hant, gd, ga, gl, lb, la, lo, tt, tr,
+ # lv, lt, tk, th, tg, te, fil, haw, yi, ceb, yo, de, da,
+ # el, eo, en, eu, et, es, ru, rw, ro, bn, be, bg, uk, jv,
+ # bs, ja, or, xh, co, ca, cy, cs, ps, pt, pa, vi, pl, hy,
+ # hr, ht, hu, hmn, hi, ha, mg, uz, ml, mn, mi, mk, ur,
+ # mt, ms, mr, ug, ta, my, af, sw, is, am,
+ # *it*, iw, sv, ar,
+ # su, zu, az, id, ig, nl, no, ne, ny, fr, ku, fy, fa, fi,
+ # ka, kk, sr, sq, ko, kn, km, st, sk, si, so, sn, sm, sl,
+ # ky, sd
+ # ...
+ self._test_automatic_captions('8YoUxe5ncPo', 'it')
+
+ @unittest.skip('ASR subs all in all supported langs now')
def test_youtube_translated_subtitles(self):
- # This video has a subtitles track, which can be translated
- self.url = 'Ky9eprVWzlI'
- self.DL.params['writeautomaticsub'] = True
- self.DL.params['subtitleslangs'] = ['it']
- subtitles = self.getSubtitles()
- self.assertTrue(subtitles['it'] is not None)
+ # This video has a subtitles track, which can be translated (#4555)
+ self._test_automatic_captions('Ky9eprVWzlI', 'it')
def test_youtube_nosubtitles(self):
self.DL.expect_warning('video doesn\'t have subtitles')
- self.url = 'n5BB19UTcdA'
+ # Available automatic captions for 8YoUxe5ncPo:
+ # ...
+ # 8YoUxe5ncPo has no subtitles
+ self.url = '8YoUxe5ncPo'
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
@@ -129,6 +165,7 @@ class TestDailymotionSubtitles(BaseTestSubtitles):
self.assertFalse(subtitles)
+@unittest.skip('IE broken')
class TestTedSubtitles(BaseTestSubtitles):
url = 'http://www.ted.com/talks/dan_dennett_on_our_consciousness.html'
IE = TEDIE
@@ -153,18 +190,19 @@ class TestVimeoSubtitles(BaseTestSubtitles):
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['de', 'en', 'es', 'fr']))
- self.assertEqual(md5(subtitles['en']), '8062383cf4dec168fc40a088aa6d5888')
- self.assertEqual(md5(subtitles['fr']), 'b6191146a6c5d3a452244d853fde6dc8')
+ self.assertEqual(md5(subtitles['en']), '386cbc9320b94e25cb364b97935e5dd1')
+ self.assertEqual(md5(subtitles['fr']), 'c9b69eef35bc6641c0d4da8a04f9dfac')
def test_nosubtitles(self):
self.DL.expect_warning('video doesn\'t have subtitles')
- self.url = 'http://vimeo.com/56015672'
+ self.url = 'http://vimeo.com/68093876'
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertFalse(subtitles)
+@unittest.skip('IE broken')
class TestWallaSubtitles(BaseTestSubtitles):
url = 'http://vod.walla.co.il/movie/2705958/the-yes-men'
IE = WallaIE
@@ -186,6 +224,7 @@ class TestWallaSubtitles(BaseTestSubtitles):
self.assertFalse(subtitles)
+@unittest.skip('IE broken')
class TestCeskaTelevizeSubtitles(BaseTestSubtitles):
url = 'http://www.ceskatelevize.cz/ivysilani/10600540290-u6-uzasny-svet-techniky'
IE = CeskaTelevizeIE
@@ -207,6 +246,7 @@ class TestCeskaTelevizeSubtitles(BaseTestSubtitles):
self.assertFalse(subtitles)
+@unittest.skip('IE broken')
class TestLyndaSubtitles(BaseTestSubtitles):
url = 'http://www.lynda.com/Bootstrap-tutorials/Using-exercise-files/110885/114408-4.html'
IE = LyndaIE
@@ -219,6 +259,7 @@ class TestLyndaSubtitles(BaseTestSubtitles):
self.assertEqual(md5(subtitles['en']), '09bbe67222259bed60deaa26997d73a7')
+@unittest.skip('IE broken')
class TestNPOSubtitles(BaseTestSubtitles):
url = 'http://www.npo.nl/nos-journaal/28-08-2014/POW_00722860'
IE = NPOIE
@@ -231,8 +272,9 @@ class TestNPOSubtitles(BaseTestSubtitles):
self.assertEqual(md5(subtitles['nl']), 'fc6435027572b63fb4ab143abd5ad3f4')
+@unittest.skip('IE broken')
class TestMTVSubtitles(BaseTestSubtitles):
- url = 'http://www.cc.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother'
+ url = 'http://www.cc.com/video-clips/p63lk0/adam-devine-s-house-party-chasing-white-swans'
IE = ComedyCentralIE
def getInfoDict(self):
@@ -243,7 +285,7 @@ class TestMTVSubtitles(BaseTestSubtitles):
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['en']))
- self.assertEqual(md5(subtitles['en']), 'b9f6ca22a6acf597ec76f61749765e65')
+ self.assertEqual(md5(subtitles['en']), '78206b8d8a0cfa9da64dc026eea48961')
class TestNRKSubtitles(BaseTestSubtitles):
@@ -253,23 +295,33 @@ class TestNRKSubtitles(BaseTestSubtitles):
def test_allsubtitles(self):
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
+ self.DL.params['format'] = 'best/bestvideo'
subtitles = self.getSubtitles()
- self.assertEqual(set(subtitles.keys()), set(['no']))
- self.assertEqual(md5(subtitles['no']), '544fa917d3197fcbee64634559221cc2')
+ self.assertEqual(set(subtitles.keys()), set(['nb-ttv']))
+ self.assertEqual(md5(subtitles['nb-ttv']), '67e06ff02d0deaf975e68f6cb8f6a149')
class TestRaiPlaySubtitles(BaseTestSubtitles):
- url = 'http://www.raiplay.it/video/2014/04/Report-del-07042014-cb27157f-9dd0-4aee-b788-b1f67643a391.html'
IE = RaiPlayIE
- def test_allsubtitles(self):
+ def test_subtitles_key(self):
+ self.url = 'http://www.raiplay.it/video/2014/04/Report-del-07042014-cb27157f-9dd0-4aee-b788-b1f67643a391.html'
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['it']))
self.assertEqual(md5(subtitles['it']), 'b1d90a98755126b61e667567a1f6680a')
+ def test_subtitles_array_key(self):
+ self.url = 'https://www.raiplay.it/video/2020/12/Report---04-01-2021-2e90f1de-8eee-4de4-ac0e-78d21db5b600.html'
+ self.DL.params['writesubtitles'] = True
+ self.DL.params['allsubtitles'] = True
+ subtitles = self.getSubtitles()
+ self.assertEqual(set(subtitles.keys()), set(['it']))
+ self.assertEqual(md5(subtitles['it']), '4b3264186fbb103508abe5311cfcb9cd')
+
+@unittest.skip('IE broken - DRM only')
class TestVikiSubtitles(BaseTestSubtitles):
url = 'http://www.viki.com/videos/1060846v-punch-episode-18'
IE = VikiIE
@@ -296,6 +348,7 @@ class TestThePlatformSubtitles(BaseTestSubtitles):
self.assertEqual(md5(subtitles['en']), '97e7670cbae3c4d26ae8bcc7fdd78d4b')
+@unittest.skip('IE broken')
class TestThePlatformFeedSubtitles(BaseTestSubtitles):
url = 'http://feed.theplatform.com/f/7wvmTC/msnbc_video-p-test?form=json&pretty=true&range=-40&byGuid=n_hardball_5biden_140207'
IE = ThePlatformFeedIE
@@ -322,18 +375,6 @@ class TestRtveSubtitles(BaseTestSubtitles):
self.assertEqual(md5(subtitles['es']), '69e70cae2d40574fb7316f31d6eb7fca')
-class TestFunnyOrDieSubtitles(BaseTestSubtitles):
- url = 'http://www.funnyordie.com/videos/224829ff6d/judd-apatow-will-direct-your-vine'
- IE = FunnyOrDieIE
-
- def test_allsubtitles(self):
- self.DL.params['writesubtitles'] = True
- self.DL.params['allsubtitles'] = True
- subtitles = self.getSubtitles()
- self.assertEqual(set(subtitles.keys()), set(['en']))
- self.assertEqual(md5(subtitles['en']), 'c5593c193eacd353596c11c2d4f9ecc4')
-
-
class TestDemocracynowSubtitles(BaseTestSubtitles):
url = 'http://www.democracynow.org/shows/2015/7/3'
IE = DemocracynowIE
@@ -343,7 +384,7 @@ class TestDemocracynowSubtitles(BaseTestSubtitles):
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['en']))
- self.assertEqual(md5(subtitles['en']), 'acaca989e24a9e45a6719c9b3d60815c')
+ self.assertEqual(md5(subtitles['en']), 'a3cc4c0b5eadd74d9974f1c1f5101045')
def test_subtitles_in_page(self):
self.url = 'http://www.democracynow.org/2015/7/3/this_flag_comes_down_today_bree'
@@ -351,7 +392,7 @@ class TestDemocracynowSubtitles(BaseTestSubtitles):
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['en']))
- self.assertEqual(md5(subtitles['en']), 'acaca989e24a9e45a6719c9b3d60815c')
+ self.assertEqual(md5(subtitles['en']), 'a3cc4c0b5eadd74d9974f1c1f5101045')
if __name__ == '__main__':
diff --git a/test/test_swfinterp.py b/test/test_swfinterp.py
index f1e899819..7c282ee00 100644
--- a/test/test_swfinterp.py
+++ b/test/test_swfinterp.py
@@ -5,16 +5,18 @@ from __future__ import unicode_literals
import os
import sys
import unittest
-sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+dirn = os.path.dirname
+
+sys.path.insert(0, dirn(dirn(os.path.abspath(__file__))))
import errno
-import io
import json
import re
import subprocess
from youtube_dl.swfinterp import SWFInterpreter
+from youtube_dl.compat import compat_open as open
TEST_DIR = os.path.join(
@@ -34,8 +36,8 @@ def _make_testfunc(testfile):
def test_func(self):
as_file = os.path.join(TEST_DIR, testfile)
swf_file = os.path.join(TEST_DIR, test_id + '.swf')
- if ((not os.path.exists(swf_file)) or
- os.path.getmtime(swf_file) < os.path.getmtime(as_file)):
+ if ((not os.path.exists(swf_file))
+ or os.path.getmtime(swf_file) < os.path.getmtime(as_file)):
# Recompile
try:
subprocess.check_call([
@@ -43,7 +45,7 @@ def _make_testfunc(testfile):
'-static-link-runtime-shared-libraries', as_file])
except OSError as ose:
if ose.errno == errno.ENOENT:
- print('mxmlc not found! Skipping test.')
+ self.skipTest('mxmlc not found!')
return
raise
@@ -51,7 +53,7 @@ def _make_testfunc(testfile):
swf_content = swf_f.read()
swfi = SWFInterpreter(swf_content)
- with io.open(as_file, 'r', encoding='utf-8') as as_f:
+ with open(as_file, 'r', encoding='utf-8') as as_f:
as_content = as_f.read()
def _find_spec(key):
diff --git a/test/test_traversal.py b/test/test_traversal.py
new file mode 100644
index 000000000..00a428edb
--- /dev/null
+++ b/test/test_traversal.py
@@ -0,0 +1,509 @@
+#!/usr/bin/env python
+# coding: utf-8
+from __future__ import unicode_literals
+
+# Allow direct execution
+import os
+import sys
+import unittest
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+
+import re
+
+from youtube_dl.traversal import (
+ dict_get,
+ get_first,
+ T,
+ traverse_obj,
+)
+from youtube_dl.compat import (
+ compat_etree_fromstring,
+ compat_http_cookies,
+ compat_str,
+)
+from youtube_dl.utils import (
+ int_or_none,
+ str_or_none,
+)
+
+_TEST_DATA = {
+ 100: 100,
+ 1.2: 1.2,
+ 'str': 'str',
+ 'None': None,
+ '...': Ellipsis,
+ 'urls': [
+ {'index': 0, 'url': 'https://www.example.com/0'},
+ {'index': 1, 'url': 'https://www.example.com/1'},
+ ],
+ 'data': (
+ {'index': 2},
+ {'index': 3},
+ ),
+ 'dict': {},
+}
+
+
+if sys.version_info < (3, 0):
+ class _TestCase(unittest.TestCase):
+
+ def assertCountEqual(self, *args, **kwargs):
+ return self.assertItemsEqual(*args, **kwargs)
+else:
+ _TestCase = unittest.TestCase
+
+
+class TestTraversal(_TestCase):
+ def assertMaybeCountEqual(self, *args, **kwargs):
+ if sys.version_info < (3, 7):
+ # random dict order
+ return self.assertCountEqual(*args, **kwargs)
+ else:
+ return self.assertEqual(*args, **kwargs)
+
+ def test_traverse_obj(self):
+ # instant compat
+ str = compat_str
+
+ # define a pukka Iterable
+ def iter_range(stop):
+ for from_ in range(stop):
+ yield from_
+
+ # Test base functionality
+ self.assertEqual(traverse_obj(_TEST_DATA, ('str',)), 'str',
+ msg='allow tuple path')
+ self.assertEqual(traverse_obj(_TEST_DATA, ['str']), 'str',
+ msg='allow list path')
+ self.assertEqual(traverse_obj(_TEST_DATA, (value for value in ("str",))), 'str',
+ msg='allow iterable path')
+ self.assertEqual(traverse_obj(_TEST_DATA, 'str'), 'str',
+ msg='single items should be treated as a path')
+ self.assertEqual(traverse_obj(_TEST_DATA, None), _TEST_DATA)
+ self.assertEqual(traverse_obj(_TEST_DATA, 100), 100)
+ self.assertEqual(traverse_obj(_TEST_DATA, 1.2), 1.2)
+
+ # Test Ellipsis behavior
+ self.assertCountEqual(traverse_obj(_TEST_DATA, Ellipsis),
+ (item for item in _TEST_DATA.values() if item not in (None, {})),
+ msg='`...` should give all non-discarded values')
+ self.assertCountEqual(traverse_obj(_TEST_DATA, ('urls', 0, Ellipsis)), _TEST_DATA['urls'][0].values(),
+ msg='`...` selection for dicts should select all values')
+ self.assertEqual(traverse_obj(_TEST_DATA, (Ellipsis, Ellipsis, 'url')),
+ ['https://www.example.com/0', 'https://www.example.com/1'],
+ msg='nested `...` queries should work')
+ self.assertCountEqual(traverse_obj(_TEST_DATA, (Ellipsis, Ellipsis, 'index')), iter_range(4),
+ msg='`...` query result should be flattened')
+ self.assertEqual(traverse_obj(iter(range(4)), Ellipsis), list(range(4)),
+ msg='`...` should accept iterables')
+
+ # Test function as key
+ self.assertEqual(traverse_obj(_TEST_DATA, lambda x, y: x == 'urls' and isinstance(y, list)),
+ [_TEST_DATA['urls']],
+ msg='function as query key should perform a filter based on (key, value)')
+ self.assertCountEqual(traverse_obj(_TEST_DATA, lambda _, x: isinstance(x[0], str)), set(('str',)),
+ msg='exceptions in the query function should be caught')
+ self.assertEqual(traverse_obj(iter(range(4)), lambda _, x: x % 2 == 0), [0, 2],
+ msg='function key should accept iterables')
+ if __debug__:
+ with self.assertRaises(Exception, msg='Wrong function signature should raise in debug'):
+ traverse_obj(_TEST_DATA, lambda a: Ellipsis)
+ with self.assertRaises(Exception, msg='Wrong function signature should raise in debug'):
+ traverse_obj(_TEST_DATA, lambda a, b, c: Ellipsis)
+
+ # Test set as key (transformation/type, like `expected_type`)
+ self.assertEqual(traverse_obj(_TEST_DATA, (Ellipsis, T(str.upper), )), ['STR'],
+ msg='Function in set should be a transformation')
+ self.assertEqual(traverse_obj(_TEST_DATA, ('fail', T(lambda _: 'const'))), 'const',
+ msg='Function in set should always be called')
+ self.assertEqual(traverse_obj(_TEST_DATA, (Ellipsis, T(str))), ['str'],
+ msg='Type in set should be a type filter')
+ self.assertMaybeCountEqual(traverse_obj(_TEST_DATA, (Ellipsis, T(str, int))), [100, 'str'],
+ msg='Multiple types in set should be a type filter')
+ self.assertEqual(traverse_obj(_TEST_DATA, T(dict)), _TEST_DATA,
+ msg='A single set should be wrapped into a path')
+ self.assertEqual(traverse_obj(_TEST_DATA, (Ellipsis, T(str.upper))), ['STR'],
+ msg='Transformation function should not raise')
+ self.assertMaybeCountEqual(traverse_obj(_TEST_DATA, (Ellipsis, T(str_or_none))),
+ [item for item in map(str_or_none, _TEST_DATA.values()) if item is not None],
+ msg='Function in set should be a transformation')
+ if __debug__:
+ with self.assertRaises(Exception, msg='Sets with length != 1 should raise in debug'):
+ traverse_obj(_TEST_DATA, set())
+ with self.assertRaises(Exception, msg='Sets with length != 1 should raise in debug'):
+ traverse_obj(_TEST_DATA, set((str.upper, str)))
+
+ # Test `slice` as a key
+ _SLICE_DATA = [0, 1, 2, 3, 4]
+ self.assertEqual(traverse_obj(_TEST_DATA, ('dict', slice(1))), None,
+ msg='slice on a dictionary should not throw')
+ self.assertEqual(traverse_obj(_SLICE_DATA, slice(1)), _SLICE_DATA[:1],
+ msg='slice key should apply slice to sequence')
+ self.assertEqual(traverse_obj(_SLICE_DATA, slice(1, 2)), _SLICE_DATA[1:2],
+ msg='slice key should apply slice to sequence')
+ self.assertEqual(traverse_obj(_SLICE_DATA, slice(1, 4, 2)), _SLICE_DATA[1:4:2],
+ msg='slice key should apply slice to sequence')
+
+ # Test alternative paths
+ self.assertEqual(traverse_obj(_TEST_DATA, 'fail', 'str'), 'str',
+ msg='multiple `paths` should be treated as alternative paths')
+ self.assertEqual(traverse_obj(_TEST_DATA, 'str', 100), 'str',
+ msg='alternatives should exit early')
+ self.assertEqual(traverse_obj(_TEST_DATA, 'fail', 'fail'), None,
+ msg='alternatives should return `default` if exhausted')
+ self.assertEqual(traverse_obj(_TEST_DATA, (Ellipsis, 'fail'), 100), 100,
+ msg='alternatives should track their own branching return')
+ self.assertEqual(traverse_obj(_TEST_DATA, ('dict', Ellipsis), ('data', Ellipsis)), list(_TEST_DATA['data']),
+ msg='alternatives on empty objects should search further')
+
+ # Test branch and path nesting
+ self.assertEqual(traverse_obj(_TEST_DATA, ('urls', (3, 0), 'url')), ['https://www.example.com/0'],
+ msg='tuple as key should be treated as branches')
+ self.assertEqual(traverse_obj(_TEST_DATA, ('urls', [3, 0], 'url')), ['https://www.example.com/0'],
+ msg='list as key should be treated as branches')
+ self.assertEqual(traverse_obj(_TEST_DATA, ('urls', ((1, 'fail'), (0, 'url')))), ['https://www.example.com/0'],
+ msg='double nesting in path should be treated as paths')
+ self.assertEqual(traverse_obj(['0', [1, 2]], [(0, 1), 0]), [1],
+ msg='do not fail early on branching')
+ self.assertCountEqual(traverse_obj(_TEST_DATA, ('urls', ((1, ('fail', 'url')), (0, 'url')))),
+ ['https://www.example.com/0', 'https://www.example.com/1'],
+ msg='triple nesting in path should be treated as branches')
+ self.assertEqual(traverse_obj(_TEST_DATA, ('urls', ('fail', (Ellipsis, 'url')))),
+ ['https://www.example.com/0', 'https://www.example.com/1'],
+ msg='ellipsis as branch path start gets flattened')
+
+ # Test dictionary as key
+ self.assertEqual(traverse_obj(_TEST_DATA, {0: 100, 1: 1.2}), {0: 100, 1: 1.2},
+ msg='dict key should result in a dict with the same keys')
+ self.assertEqual(traverse_obj(_TEST_DATA, {0: ('urls', 0, 'url')}),
+ {0: 'https://www.example.com/0'},
+ msg='dict key should allow paths')
+ self.assertEqual(traverse_obj(_TEST_DATA, {0: ('urls', (3, 0), 'url')}),
+ {0: ['https://www.example.com/0']},
+ msg='tuple in dict path should be treated as branches')
+ self.assertEqual(traverse_obj(_TEST_DATA, {0: ('urls', ((1, 'fail'), (0, 'url')))}),
+ {0: ['https://www.example.com/0']},
+ msg='double nesting in dict path should be treated as paths')
+ self.assertEqual(traverse_obj(_TEST_DATA, {0: ('urls', ((1, ('fail', 'url')), (0, 'url')))}),
+ {0: ['https://www.example.com/1', 'https://www.example.com/0']},
+ msg='triple nesting in dict path should be treated as branches')
+ self.assertEqual(traverse_obj(_TEST_DATA, {0: 'fail'}), {},
+ msg='remove `None` values when top level dict key fails')
+ self.assertEqual(traverse_obj(_TEST_DATA, {0: 'fail'}, default=Ellipsis), {0: Ellipsis},
+ msg='use `default` if key fails and `default`')
+ self.assertEqual(traverse_obj(_TEST_DATA, {0: 'dict'}), {},
+ msg='remove empty values when dict key')
+ self.assertEqual(traverse_obj(_TEST_DATA, {0: 'dict'}, default=Ellipsis), {0: Ellipsis},
+ msg='use `default` when dict key and a default')
+ self.assertEqual(traverse_obj(_TEST_DATA, {0: {0: 'fail'}}), {},
+ msg='remove empty values when nested dict key fails')
+ self.assertEqual(traverse_obj(None, {0: 'fail'}), {},
+ msg='default to dict if pruned')
+ self.assertEqual(traverse_obj(None, {0: 'fail'}, default=Ellipsis), {0: Ellipsis},
+ msg='default to dict if pruned and default is given')
+ self.assertEqual(traverse_obj(_TEST_DATA, {0: {0: 'fail'}}, default=Ellipsis), {0: {0: Ellipsis}},
+ msg='use nested `default` when nested dict key fails and `default`')
+ self.assertEqual(traverse_obj(_TEST_DATA, {0: ('dict', Ellipsis)}), {},
+ msg='remove key if branch in dict key not successful')
+
+ # Testing default parameter behavior
+ _DEFAULT_DATA = {'None': None, 'int': 0, 'list': []}
+ self.assertEqual(traverse_obj(_DEFAULT_DATA, 'fail'), None,
+ msg='default value should be `None`')
+ self.assertEqual(traverse_obj(_DEFAULT_DATA, 'fail', 'fail', default=Ellipsis), Ellipsis,
+ msg='chained fails should result in default')
+ self.assertEqual(traverse_obj(_DEFAULT_DATA, 'None', 'int'), 0,
+ msg='should not short cirquit on `None`')
+ self.assertEqual(traverse_obj(_DEFAULT_DATA, 'fail', default=1), 1,
+ msg='invalid dict key should result in `default`')
+ self.assertEqual(traverse_obj(_DEFAULT_DATA, 'None', default=1), 1,
+ msg='`None` is a deliberate sentinel and should become `default`')
+ self.assertEqual(traverse_obj(_DEFAULT_DATA, ('list', 10)), None,
+ msg='`IndexError` should result in `default`')
+ self.assertEqual(traverse_obj(_DEFAULT_DATA, (Ellipsis, 'fail'), default=1), 1,
+ msg='if branched but not successful return `default` if defined, not `[]`')
+ self.assertEqual(traverse_obj(_DEFAULT_DATA, (Ellipsis, 'fail'), default=None), None,
+ msg='if branched but not successful return `default` even if `default` is `None`')
+ self.assertEqual(traverse_obj(_DEFAULT_DATA, (Ellipsis, 'fail')), [],
+ msg='if branched but not successful return `[]`, not `default`')
+ self.assertEqual(traverse_obj(_DEFAULT_DATA, ('list', Ellipsis)), [],
+ msg='if branched but object is empty return `[]`, not `default`')
+ self.assertEqual(traverse_obj(None, Ellipsis), [],
+ msg='if branched but object is `None` return `[]`, not `default`')
+ self.assertEqual(traverse_obj({0: None}, (0, Ellipsis)), [],
+ msg='if branched but state is `None` return `[]`, not `default`')
+
+ branching_paths = [
+ ('fail', Ellipsis),
+ (Ellipsis, 'fail'),
+ 100 * ('fail',) + (Ellipsis,),
+ (Ellipsis,) + 100 * ('fail',),
+ ]
+ for branching_path in branching_paths:
+ self.assertEqual(traverse_obj({}, branching_path), [],
+ msg='if branched but state is `None`, return `[]` (not `default`)')
+ self.assertEqual(traverse_obj({}, 'fail', branching_path), [],
+ msg='if branching in last alternative and previous did not match, return `[]` (not `default`)')
+ self.assertEqual(traverse_obj({0: 'x'}, 0, branching_path), 'x',
+ msg='if branching in last alternative and previous did match, return single value')
+ self.assertEqual(traverse_obj({0: 'x'}, branching_path, 0), 'x',
+ msg='if branching in first alternative and non-branching path does match, return single value')
+ self.assertEqual(traverse_obj({}, branching_path, 'fail'), None,
+ msg='if branching in first alternative and non-branching path does not match, return `default`')
+
+ # Testing expected_type behavior
+ _EXPECTED_TYPE_DATA = {'str': 'str', 'int': 0}
+ self.assertEqual(traverse_obj(_EXPECTED_TYPE_DATA, 'str', expected_type=str),
+ 'str', msg='accept matching `expected_type` type')
+ self.assertEqual(traverse_obj(_EXPECTED_TYPE_DATA, 'str', expected_type=int),
+ None, msg='reject non-matching `expected_type` type')
+ self.assertEqual(traverse_obj(_EXPECTED_TYPE_DATA, 'int', expected_type=lambda x: str(x)),
+ '0', msg='transform type using type function')
+ self.assertEqual(traverse_obj(_EXPECTED_TYPE_DATA, 'str', expected_type=lambda _: 1 / 0),
+ None, msg='wrap expected_type function in try_call')
+ self.assertEqual(traverse_obj(_EXPECTED_TYPE_DATA, Ellipsis, expected_type=str),
+ ['str'], msg='eliminate items that expected_type fails on')
+ self.assertEqual(traverse_obj(_TEST_DATA, {0: 100, 1: 1.2}, expected_type=int),
+ {0: 100}, msg='type as expected_type should filter dict values')
+ self.assertEqual(traverse_obj(_TEST_DATA, {0: 100, 1: 1.2, 2: 'None'}, expected_type=str_or_none),
+ {0: '100', 1: '1.2'}, msg='function as expected_type should transform dict values')
+ self.assertEqual(traverse_obj(_TEST_DATA, ({0: 1.2}, 0, set((int_or_none,))), expected_type=int),
+ 1, msg='expected_type should not filter non-final dict values')
+ self.assertEqual(traverse_obj(_TEST_DATA, {0: {0: 100, 1: 'str'}}, expected_type=int),
+ {0: {0: 100}}, msg='expected_type should transform deep dict values')
+ self.assertEqual(traverse_obj(_TEST_DATA, [({0: '...'}, {0: '...'})], expected_type=type(Ellipsis)),
+ [{0: Ellipsis}, {0: Ellipsis}], msg='expected_type should transform branched dict values')
+ self.assertEqual(traverse_obj({1: {3: 4}}, [(1, 2), 3], expected_type=int),
+ [4], msg='expected_type regression for type matching in tuple branching')
+ self.assertEqual(traverse_obj(_TEST_DATA, ['data', Ellipsis], expected_type=int),
+ [], msg='expected_type regression for type matching in dict result')
+
+ # Test get_all behavior
+ _GET_ALL_DATA = {'key': [0, 1, 2]}
+ self.assertEqual(traverse_obj(_GET_ALL_DATA, ('key', Ellipsis), get_all=False), 0,
+ msg='if not `get_all`, return only first matching value')
+ self.assertEqual(traverse_obj(_GET_ALL_DATA, Ellipsis, get_all=False), [0, 1, 2],
+ msg='do not overflatten if not `get_all`')
+
+ # Test casesense behavior
+ _CASESENSE_DATA = {
+ 'KeY': 'value0',
+ 0: {
+ 'KeY': 'value1',
+ 0: {'KeY': 'value2'},
+ },
+ # FULLWIDTH LATIN CAPITAL LETTER K
+ '\uff2bey': 'value3',
+ }
+ self.assertEqual(traverse_obj(_CASESENSE_DATA, 'key'), None,
+ msg='dict keys should be case sensitive unless `casesense`')
+ self.assertEqual(traverse_obj(_CASESENSE_DATA, 'keY',
+ casesense=False), 'value0',
+ msg='allow non matching key case if `casesense`')
+ self.assertEqual(traverse_obj(_CASESENSE_DATA, '\uff4bey', # FULLWIDTH LATIN SMALL LETTER K
+ casesense=False), 'value3',
+ msg='allow non matching Unicode key case if `casesense`')
+ self.assertEqual(traverse_obj(_CASESENSE_DATA, (0, ('keY',)),
+ casesense=False), ['value1'],
+ msg='allow non matching key case in branch if `casesense`')
+ self.assertEqual(traverse_obj(_CASESENSE_DATA, (0, ((0, 'keY'),)),
+ casesense=False), ['value2'],
+ msg='allow non matching key case in branch path if `casesense`')
+
+ # Test traverse_string behavior
+ _TRAVERSE_STRING_DATA = {'str': 'str', 1.2: 1.2}
+ self.assertEqual(traverse_obj(_TRAVERSE_STRING_DATA, ('str', 0)), None,
+ msg='do not traverse into string if not `traverse_string`')
+ self.assertEqual(traverse_obj(_TRAVERSE_STRING_DATA, ('str', 0),
+ _traverse_string=True), 's',
+ msg='traverse into string if `traverse_string`')
+ self.assertEqual(traverse_obj(_TRAVERSE_STRING_DATA, (1.2, 1),
+ _traverse_string=True), '.',
+ msg='traverse into converted data if `traverse_string`')
+ self.assertEqual(traverse_obj(_TRAVERSE_STRING_DATA, ('str', Ellipsis),
+ _traverse_string=True), 'str',
+ msg='`...` should result in string (same value) if `traverse_string`')
+ self.assertEqual(traverse_obj(_TRAVERSE_STRING_DATA, ('str', slice(0, None, 2)),
+ _traverse_string=True), 'sr',
+ msg='`slice` should result in string if `traverse_string`')
+ self.assertEqual(traverse_obj(_TRAVERSE_STRING_DATA, ('str', lambda i, v: i or v == 's'),
+ _traverse_string=True), 'str',
+ msg='function should result in string if `traverse_string`')
+ self.assertEqual(traverse_obj(_TRAVERSE_STRING_DATA, ('str', (0, 2)),
+ _traverse_string=True), ['s', 'r'],
+ msg='branching should result in list if `traverse_string`')
+ self.assertEqual(traverse_obj({}, (0, Ellipsis), _traverse_string=True), [],
+ msg='branching should result in list if `traverse_string`')
+ self.assertEqual(traverse_obj({}, (0, lambda x, y: True), _traverse_string=True), [],
+ msg='branching should result in list if `traverse_string`')
+ self.assertEqual(traverse_obj({}, (0, slice(1)), _traverse_string=True), [],
+ msg='branching should result in list if `traverse_string`')
+
+ # Test re.Match as input obj
+ mobj = re.match(r'^0(12)(?P<group>3)(4)?$', '0123')
+ self.assertEqual(traverse_obj(mobj, Ellipsis), [x for x in mobj.groups() if x is not None],
+ msg='`...` on a `re.Match` should give its `groups()`')
+ self.assertEqual(traverse_obj(mobj, lambda k, _: k in (0, 2)), ['0123', '3'],
+ msg='function on a `re.Match` should give groupno, value starting at 0')
+ self.assertEqual(traverse_obj(mobj, 'group'), '3',
+ msg='str key on a `re.Match` should give group with that name')
+ self.assertEqual(traverse_obj(mobj, 2), '3',
+ msg='int key on a `re.Match` should give group with that name')
+ self.assertEqual(traverse_obj(mobj, 'gRoUp', casesense=False), '3',
+ msg='str key on a `re.Match` should respect casesense')
+ self.assertEqual(traverse_obj(mobj, 'fail'), None,
+ msg='failing str key on a `re.Match` should return `default`')
+ self.assertEqual(traverse_obj(mobj, 'gRoUpS', casesense=False), None,
+ msg='failing str key on a `re.Match` should return `default`')
+ self.assertEqual(traverse_obj(mobj, 8), None,
+ msg='failing int key on a `re.Match` should return `default`')
+ self.assertEqual(traverse_obj(mobj, lambda k, _: k in (0, 'group')), ['0123', '3'],
+ msg='function on a `re.Match` should give group name as well')
+
+ # Test xml.etree.ElementTree.Element as input obj
+ etree = compat_etree_fromstring('''<?xml version="1.0"?>
+ <data>
+ <country name="Liechtenstein">
+ <rank>1</rank>
+ <year>2008</year>
+ <gdppc>141100</gdppc>
+ <neighbor name="Austria" direction="E"/>
+ <neighbor name="Switzerland" direction="W"/>
+ </country>
+ <country name="Singapore">
+ <rank>4</rank>
+ <year>2011</year>
+ <gdppc>59900</gdppc>
+ <neighbor name="Malaysia" direction="N"/>
+ </country>
+ <country name="Panama">
+ <rank>68</rank>
+ <year>2011</year>
+ <gdppc>13600</gdppc>
+ <neighbor name="Costa Rica" direction="W"/>
+ <neighbor name="Colombia" direction="E"/>
+ </country>
+ </data>''')
+ self.assertEqual(traverse_obj(etree, ''), etree,
+ msg='empty str key should return the element itself')
+ self.assertEqual(traverse_obj(etree, 'country'), list(etree),
+ msg='str key should return all children with that tag name')
+ self.assertEqual(traverse_obj(etree, Ellipsis), list(etree),
+ msg='`...` as key should return all children')
+ self.assertEqual(traverse_obj(etree, lambda _, x: x[0].text == '4'), [etree[1]],
+ msg='function as key should get element as value')
+ self.assertEqual(traverse_obj(etree, lambda i, _: i == 1), [etree[1]],
+ msg='function as key should get index as key')
+ self.assertEqual(traverse_obj(etree, 0), etree[0],
+ msg='int key should return the nth child')
+ self.assertEqual(traverse_obj(etree, './/neighbor/@name'),
+ ['Austria', 'Switzerland', 'Malaysia', 'Costa Rica', 'Colombia'],
+ msg='`@<attribute>` at end of path should give that attribute')
+ self.assertEqual(traverse_obj(etree, '//neighbor/@fail'), [None, None, None, None, None],
+ msg='`@<nonexistent>` at end of path should give `None`')
+ self.assertEqual(traverse_obj(etree, ('//neighbor/@', 2)), {'name': 'Malaysia', 'direction': 'N'},
+ msg='`@` should give the full attribute dict')
+ self.assertEqual(traverse_obj(etree, '//year/text()'), ['2008', '2011', '2011'],
+ msg='`text()` at end of path should give the inner text')
+ self.assertEqual(traverse_obj(etree, '//*[@direction]/@direction'), ['E', 'W', 'N', 'W', 'E'],
+ msg='full python xpath features should be supported')
+ self.assertEqual(traverse_obj(etree, (0, '@name')), 'Liechtenstein',
+ msg='special transformations should act on current element')
+ self.assertEqual(traverse_obj(etree, ('country', 0, Ellipsis, 'text()', T(int_or_none))), [1, 2008, 141100],
+ msg='special transformations should act on current element')
+
+ def test_traversal_unbranching(self):
+ self.assertEqual(traverse_obj(_TEST_DATA, [(100, 1.2), all]), [100, 1.2],
+ msg='`all` should give all results as list')
+ self.assertEqual(traverse_obj(_TEST_DATA, [(100, 1.2), any]), 100,
+ msg='`any` should give the first result')
+ self.assertEqual(traverse_obj(_TEST_DATA, [100, all]), [100],
+ msg='`all` should give list if non branching')
+ self.assertEqual(traverse_obj(_TEST_DATA, [100, any]), 100,
+ msg='`any` should give single item if non branching')
+ self.assertEqual(traverse_obj(_TEST_DATA, [('dict', 'None', 100), all]), [100],
+ msg='`all` should filter `None` and empty dict')
+ self.assertEqual(traverse_obj(_TEST_DATA, [('dict', 'None', 100), any]), 100,
+ msg='`any` should filter `None` and empty dict')
+ self.assertEqual(traverse_obj(_TEST_DATA, [{
+ 'all': [('dict', 'None', 100, 1.2), all],
+ 'any': [('dict', 'None', 100, 1.2), any],
+ }]), {'all': [100, 1.2], 'any': 100},
+ msg='`all`/`any` should apply to each dict path separately')
+ self.assertEqual(traverse_obj(_TEST_DATA, [{
+ 'all': [('dict', 'None', 100, 1.2), all],
+ 'any': [('dict', 'None', 100, 1.2), any],
+ }], get_all=False), {'all': [100, 1.2], 'any': 100},
+ msg='`all`/`any` should apply to dict regardless of `get_all`')
+ self.assertIs(traverse_obj(_TEST_DATA, [('dict', 'None', 100, 1.2), all, T(float)]), None,
+ msg='`all` should reset branching status')
+ self.assertIs(traverse_obj(_TEST_DATA, [('dict', 'None', 100, 1.2), any, T(float)]), None,
+ msg='`any` should reset branching status')
+ self.assertEqual(traverse_obj(_TEST_DATA, [('dict', 'None', 100, 1.2), all, Ellipsis, T(float)]), [1.2],
+ msg='`all` should allow further branching')
+ self.assertEqual(traverse_obj(_TEST_DATA, [('dict', 'None', 'urls', 'data'), any, Ellipsis, 'index']), [0, 1],
+ msg='`any` should allow further branching')
+
+ def test_traversal_morsel(self):
+ values = {
+ 'expires': 'a',
+ 'path': 'b',
+ 'comment': 'c',
+ 'domain': 'd',
+ 'max-age': 'e',
+ 'secure': 'f',
+ 'httponly': 'g',
+ 'version': 'h',
+ 'samesite': 'i',
+ }
+ # SameSite added in Py3.8, breaks .update for 3.5-3.7
+ if sys.version_info < (3, 8):
+ del values['samesite']
+ morsel = compat_http_cookies.Morsel()
+ morsel.set(str('item_key'), 'item_value', 'coded_value')
+ morsel.update(values)
+ values['key'] = str('item_key')
+ values['value'] = 'item_value'
+ values = dict((str(k), v) for k, v in values.items())
+ # make test pass even without ordered dict
+ value_set = set(values.values())
+
+ for key, value in values.items():
+ self.assertEqual(traverse_obj(morsel, key), value,
+ msg='Morsel should provide access to all values')
+ self.assertEqual(set(traverse_obj(morsel, Ellipsis)), value_set,
+ msg='`...` should yield all values')
+ self.assertEqual(set(traverse_obj(morsel, lambda k, v: True)), value_set,
+ msg='function key should yield all values')
+ self.assertIs(traverse_obj(morsel, [(None,), any]), morsel,
+ msg='Morsel should not be implicitly changed to dict on usage')
+
+ def test_get_first(self):
+ self.assertEqual(get_first([{'a': None}, {'a': 'spam'}], 'a'), 'spam')
+
+ def test_dict_get(self):
+ FALSE_VALUES = {
+ 'none': None,
+ 'false': False,
+ 'zero': 0,
+ 'empty_string': '',
+ 'empty_list': [],
+ }
+ d = FALSE_VALUES.copy()
+ d['a'] = 42
+ self.assertEqual(dict_get(d, 'a'), 42)
+ self.assertEqual(dict_get(d, 'b'), None)
+ self.assertEqual(dict_get(d, 'b', 42), 42)
+ self.assertEqual(dict_get(d, ('a', )), 42)
+ self.assertEqual(dict_get(d, ('b', 'a', )), 42)
+ self.assertEqual(dict_get(d, ('b', 'c', 'a', 'd', )), 42)
+ self.assertEqual(dict_get(d, ('b', 'c', )), None)
+ self.assertEqual(dict_get(d, ('b', 'c', ), 42), 42)
+ for key, false_value in FALSE_VALUES.items():
+ self.assertEqual(dict_get(d, ('b', 'c', key, )), None)
+ self.assertEqual(dict_get(d, ('b', 'c', key, ), skip_false_values=False), false_value)
+
+
+if __name__ == '__main__':
+ unittest.main()
diff --git a/test/test_unicode_literals.py b/test/test_unicode_literals.py
index 6c1b7ec91..0c83f2a0c 100644
--- a/test/test_unicode_literals.py
+++ b/test/test_unicode_literals.py
@@ -2,19 +2,21 @@ from __future__ import unicode_literals
# Allow direct execution
import os
+import re
import sys
import unittest
-sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-import io
-import re
+dirn = os.path.dirname
+
+rootDir = dirn(dirn(os.path.abspath(__file__)))
-rootDir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+sys.path.insert(0, rootDir)
IGNORED_FILES = [
'setup.py', # http://bugs.python.org/issue13943
'conf.py',
'buildserver.py',
+ 'get-pip.py',
]
IGNORED_DIRS = [
@@ -23,6 +25,7 @@ IGNORED_DIRS = [
]
from test.helper import assertRegexpMatches
+from youtube_dl.compat import compat_open as open
class TestUnicodeLiterals(unittest.TestCase):
@@ -40,7 +43,7 @@ class TestUnicodeLiterals(unittest.TestCase):
continue
fn = os.path.join(dirpath, basename)
- with io.open(fn, encoding='utf-8') as inf:
+ with open(fn, encoding='utf-8') as inf:
code = inf.read()
if "'" not in code and '"' not in code:
diff --git a/test/test_utils.py b/test/test_utils.py
index aa4569b81..2947cce7e 100644
--- a/test/test_utils.py
+++ b/test/test_utils.py
@@ -12,73 +12,95 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
# Various small unit tests
import io
+import itertools
import json
+import types
import xml.etree.ElementTree
from youtube_dl.utils import (
+ _UnsafeExtensionError,
age_restricted,
args_to_str,
- encode_base_n,
+ base_url,
+ caesar,
clean_html,
+ clean_podcast_url,
date_from_str,
DateRange,
detect_exe_version,
determine_ext,
- dict_get,
+ encode_base_n,
encode_compat_str,
encodeFilename,
escape_rfc3986,
escape_url,
+ expand_path,
extract_attributes,
ExtractorError,
find_xpath_attr,
fix_xml_ampersands,
+ float_or_none,
get_element_by_class,
get_element_by_attribute,
get_elements_by_class,
get_elements_by_attribute,
InAdvancePagedList,
+ int_or_none,
intlist_to_bytes,
is_html,
+ join_nonempty,
js_to_json,
+ LazyList,
limit_length,
+ lowercase_escape,
+ merge_dicts,
mimetype2ext,
month_by_name,
+ multipart_encode,
ohdave_rsa_encrypt,
OnDemandPagedList,
orderedSet,
parse_age_limit,
+ parse_bitrate,
parse_duration,
parse_filesize,
+ parse_codecs,
parse_count,
parse_iso8601,
+ parse_resolution,
+ parse_qs,
pkcs1pad,
- read_batch_urls,
- sanitize_filename,
- sanitize_path,
- expand_path,
prepend_extension,
- replace_extension,
+ read_batch_urls,
remove_start,
remove_end,
remove_quotes,
+ replace_extension,
+ rot47,
+ sanitize_filename,
+ sanitize_path,
+ sanitize_url,
+ sanitized_Request,
shell_quote,
smuggle_url,
str_to_int,
strip_jsonp,
+ strip_or_none,
+ subtitles_filename,
timeconvert,
+ try_call,
unescapeHTML,
unified_strdate,
unified_timestamp,
unsmuggle_url,
uppercase_escape,
- lowercase_escape,
url_basename,
- base_url,
+ url_or_none,
urljoin,
urlencode_postdata,
urshift,
update_url_query,
+ variadic,
version_tuple,
xpath_with_ns,
xpath_element,
@@ -91,19 +113,21 @@ from youtube_dl.utils import (
cli_option,
cli_valueless_option,
cli_bool_option,
- parse_codecs,
+ YoutubeDLHandler,
)
from youtube_dl.compat import (
compat_chr,
compat_etree_fromstring,
compat_getenv,
+ compat_os_name,
compat_setenv,
+ compat_str,
compat_urlparse,
- compat_parse_qs,
)
class TestUtil(unittest.TestCase):
+
def test_timeconvert(self):
self.assertTrue(timeconvert('') is None)
self.assertTrue(timeconvert('bougrg') is None)
@@ -174,7 +198,7 @@ class TestUtil(unittest.TestCase):
self.assertEqual(sanitize_filename(
'ÂÃÄÀÁÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖŐØŒÙÚÛÜŰÝÞßàáâãäåæçèéêëìíîïðñòóôõöőøœùúûüűýþÿ', restricted=True),
- 'AAAAAAAECEEEEIIIIDNOOOOOOOOEUUUUUYPssaaaaaaaeceeeeiiiionooooooooeuuuuuypy')
+ 'AAAAAAAECEEEEIIIIDNOOOOOOOOEUUUUUYTHssaaaaaaaeceeeeiiiionooooooooeuuuuuythy')
def test_sanitize_ids(self):
self.assertEqual(sanitize_filename('_n_cd26wFpw', is_id=True), '_n_cd26wFpw')
@@ -217,6 +241,25 @@ class TestUtil(unittest.TestCase):
self.assertEqual(sanitize_path('./abc'), 'abc')
self.assertEqual(sanitize_path('./../abc'), '..\\abc')
+ def test_sanitize_url(self):
+ self.assertEqual(sanitize_url('//foo.bar'), 'http://foo.bar')
+ self.assertEqual(sanitize_url('httpss://foo.bar'), 'https://foo.bar')
+ self.assertEqual(sanitize_url('rmtps://foo.bar'), 'rtmps://foo.bar')
+ self.assertEqual(sanitize_url('https://foo.bar'), 'https://foo.bar')
+ self.assertEqual(sanitize_url('foo bar'), 'foo bar')
+
+ def test_sanitized_Request(self):
+ self.assertFalse(sanitized_Request('http://foo.bar').has_header('Authorization'))
+ self.assertFalse(sanitized_Request('http://:foo.bar').has_header('Authorization'))
+ self.assertEqual(sanitized_Request('http://@foo.bar').get_header('Authorization'),
+ 'Basic Og==')
+ self.assertEqual(sanitized_Request('http://:pass@foo.bar').get_header('Authorization'),
+ 'Basic OnBhc3M=')
+ self.assertEqual(sanitized_Request('http://user:@foo.bar').get_header('Authorization'),
+ 'Basic dXNlcjo=')
+ self.assertEqual(sanitized_Request('http://user:pass@foo.bar').get_header('Authorization'),
+ 'Basic dXNlcjpwYXNz')
+
def test_expand_path(self):
def env(var):
return '%{0}%'.format(var) if sys.platform == 'win32' else '${0}'.format(var)
@@ -229,6 +272,27 @@ class TestUtil(unittest.TestCase):
expand_path('~/%s' % env('YOUTUBE_DL_EXPATH_PATH')),
'%s/expanded' % compat_getenv('HOME'))
+ _uncommon_extensions = [
+ ('exe', 'abc.exe.ext'),
+ ('de', 'abc.de.ext'),
+ ('../.mp4', None),
+ ('..\\.mp4', None),
+ ]
+
+ def assertUnsafeExtension(self, ext=None):
+ assert_raises = self.assertRaises(_UnsafeExtensionError)
+ assert_raises.ext = ext
+ orig_exit = assert_raises.__exit__
+
+ def my_exit(self_, exc_type, exc_val, exc_tb):
+ did_raise = orig_exit(exc_type, exc_val, exc_tb)
+ if did_raise and assert_raises.ext is not None:
+ self.assertEqual(assert_raises.ext, assert_raises.exception.extension, 'Unsafe extension not as unexpected')
+ return did_raise
+
+ assert_raises.__exit__ = types.MethodType(my_exit, assert_raises)
+ return assert_raises
+
def test_prepend_extension(self):
self.assertEqual(prepend_extension('abc.ext', 'temp'), 'abc.temp.ext')
self.assertEqual(prepend_extension('abc.ext', 'temp', 'ext'), 'abc.temp.ext')
@@ -237,6 +301,19 @@ class TestUtil(unittest.TestCase):
self.assertEqual(prepend_extension('.abc', 'temp'), '.abc.temp')
self.assertEqual(prepend_extension('.abc.ext', 'temp'), '.abc.temp.ext')
+ # Test uncommon extensions
+ self.assertEqual(prepend_extension('abc.ext', 'bin'), 'abc.bin.ext')
+ for ext, result in self._uncommon_extensions:
+ with self.assertUnsafeExtension(ext):
+ prepend_extension('abc', ext)
+ if result:
+ self.assertEqual(prepend_extension('abc.ext', ext, 'ext'), result)
+ else:
+ with self.assertUnsafeExtension(ext):
+ prepend_extension('abc.ext', ext, 'ext')
+ with self.assertUnsafeExtension(ext):
+ prepend_extension('abc.unexpected_ext', ext, 'ext')
+
def test_replace_extension(self):
self.assertEqual(replace_extension('abc.ext', 'temp'), 'abc.temp')
self.assertEqual(replace_extension('abc.ext', 'temp', 'ext'), 'abc.temp')
@@ -245,6 +322,21 @@ class TestUtil(unittest.TestCase):
self.assertEqual(replace_extension('.abc', 'temp'), '.abc.temp')
self.assertEqual(replace_extension('.abc.ext', 'temp'), '.abc.temp')
+ # Test uncommon extensions
+ self.assertEqual(replace_extension('abc.ext', 'bin'), 'abc.unknown_video')
+ for ext, _ in self._uncommon_extensions:
+ with self.assertUnsafeExtension(ext):
+ replace_extension('abc', ext)
+ with self.assertUnsafeExtension(ext):
+ replace_extension('abc.ext', ext, 'ext')
+ with self.assertUnsafeExtension(ext):
+ replace_extension('abc.unexpected_ext', ext, 'ext')
+
+ def test_subtitles_filename(self):
+ self.assertEqual(subtitles_filename('abc.ext', 'en', 'vtt'), 'abc.en.vtt')
+ self.assertEqual(subtitles_filename('abc.ext', 'en', 'vtt', 'ext'), 'abc.en.vtt')
+ self.assertEqual(subtitles_filename('abc.unexpected_ext', 'en', 'vtt', 'ext'), 'abc.unexpected_ext.en.vtt')
+
def test_remove_start(self):
self.assertEqual(remove_start(None, 'A - '), None)
self.assertEqual(remove_start('A - B', 'A - '), 'B')
@@ -277,6 +369,7 @@ class TestUtil(unittest.TestCase):
self.assertEqual(unescapeHTML('&#47;'), '/')
self.assertEqual(unescapeHTML('&eacute;'), 'é')
self.assertEqual(unescapeHTML('&#2013266066;'), '&#2013266066;')
+ self.assertEqual(unescapeHTML('&a&quot;'), '&a"')
# HTML5 entities
self.assertEqual(unescapeHTML('&period;&apos;'), '.\'')
@@ -317,6 +410,8 @@ class TestUtil(unittest.TestCase):
self.assertEqual(unified_strdate('July 15th, 2013'), '20130715')
self.assertEqual(unified_strdate('September 1st, 2013'), '20130901')
self.assertEqual(unified_strdate('Sep 2nd, 2013'), '20130902')
+ self.assertEqual(unified_strdate('November 3rd, 2019'), '20191103')
+ self.assertEqual(unified_strdate('October 23rd, 2005'), '20051023')
def test_unified_timestamps(self):
self.assertEqual(unified_timestamp('December 21, 2010'), 1292889600)
@@ -338,6 +433,13 @@ class TestUtil(unittest.TestCase):
self.assertEqual(unified_timestamp('UNKNOWN DATE FORMAT'), None)
self.assertEqual(unified_timestamp('May 16, 2016 11:15 PM'), 1463440500)
self.assertEqual(unified_timestamp('Feb 7, 2016 at 6:35 pm'), 1454870100)
+ self.assertEqual(unified_timestamp('2017-03-30T17:52:41Q'), 1490896361)
+ self.assertEqual(unified_timestamp('Sep 11, 2013 | 5:49 AM'), 1378878540)
+ self.assertEqual(unified_timestamp('December 15, 2017 at 7:49 am'), 1513324140)
+ self.assertEqual(unified_timestamp('2018-03-14T08:32:43.1493874+00:00'), 1521016363)
+ self.assertEqual(unified_timestamp('December 31 1969 20:00:01 EDT'), 1)
+ self.assertEqual(unified_timestamp('Wednesday 31 December 1969 18:01:26 MDT'), 86)
+ self.assertEqual(unified_timestamp('12/31/1969 20:01:18 EDT', False), 78)
def test_determine_ext(self):
self.assertEqual(determine_ext('http://example.com/foo/bar.mp4/?download'), 'mp4')
@@ -345,6 +447,7 @@ class TestUtil(unittest.TestCase):
self.assertEqual(determine_ext('http://example.com/foo/bar.nonext/?download', None), None)
self.assertEqual(determine_ext('http://example.com/foo/bar/mp4?download', None), None)
self.assertEqual(determine_ext('http://example.com/foo/bar.m3u8//?download'), 'm3u8')
+ self.assertEqual(determine_ext('foobar', None), None)
def test_find_xpath_attr(self):
testxml = '''<root>
@@ -445,11 +548,37 @@ class TestUtil(unittest.TestCase):
def test_shell_quote(self):
args = ['ffmpeg', '-i', encodeFilename('ñ€ß\'.mp4')]
- self.assertEqual(shell_quote(args), """ffmpeg -i 'ñ€ß'"'"'.mp4'""")
+ self.assertEqual(
+ shell_quote(args),
+ """ffmpeg -i 'ñ€ß'"'"'.mp4'""" if compat_os_name != 'nt' else '''ffmpeg -i "ñ€ß'.mp4"''')
+
+ def test_float_or_none(self):
+ self.assertEqual(float_or_none('42.42'), 42.42)
+ self.assertEqual(float_or_none('42'), 42.0)
+ self.assertEqual(float_or_none(''), None)
+ self.assertEqual(float_or_none(None), None)
+ self.assertEqual(float_or_none([]), None)
+ self.assertEqual(float_or_none(set()), None)
+
+ def test_int_or_none(self):
+ self.assertEqual(int_or_none(42), 42)
+ self.assertEqual(int_or_none('42'), 42)
+ self.assertEqual(int_or_none(''), None)
+ self.assertEqual(int_or_none(None), None)
+ self.assertEqual(int_or_none([]), None)
+ self.assertEqual(int_or_none(set()), None)
+ self.assertEqual(int_or_none('42', base=8), 34)
+ self.assertRaises(TypeError, int_or_none(42, base=8))
def test_str_to_int(self):
self.assertEqual(str_to_int('123,456'), 123456)
self.assertEqual(str_to_int('123.456'), 123456)
+ self.assertEqual(str_to_int(523), 523)
+ # Python 3 has no long
+ if sys.version_info < (3, 0):
+ eval('self.assertEqual(str_to_int(123456L), 123456)')
+ self.assertEqual(str_to_int('noninteger'), None)
+ self.assertEqual(str_to_int([]), None)
def test_url_basename(self):
self.assertEqual(url_basename('http://foo.de/'), '')
@@ -487,6 +616,23 @@ class TestUtil(unittest.TestCase):
self.assertEqual(urljoin('http://foo.de/', ''), None)
self.assertEqual(urljoin('http://foo.de/', ['foobar']), None)
self.assertEqual(urljoin('http://foo.de/a/b/c.txt', '.././../d.txt'), 'http://foo.de/d.txt')
+ self.assertEqual(urljoin('http://foo.de/a/b/c.txt', 'rtmp://foo.de'), 'rtmp://foo.de')
+ self.assertEqual(urljoin(None, 'rtmp://foo.de'), 'rtmp://foo.de')
+
+ def test_url_or_none(self):
+ self.assertEqual(url_or_none(None), None)
+ self.assertEqual(url_or_none(''), None)
+ self.assertEqual(url_or_none('foo'), None)
+ self.assertEqual(url_or_none('http://foo.de'), 'http://foo.de')
+ self.assertEqual(url_or_none('https://foo.de'), 'https://foo.de')
+ self.assertEqual(url_or_none('http$://foo.de'), None)
+ self.assertEqual(url_or_none('http://foo.de'), 'http://foo.de')
+ self.assertEqual(url_or_none('//foo.de'), '//foo.de')
+ self.assertEqual(url_or_none('s3://foo.de'), None)
+ self.assertEqual(url_or_none('rtmpte://foo.de'), 'rtmpte://foo.de')
+ self.assertEqual(url_or_none('mms://foo.de'), 'mms://foo.de')
+ self.assertEqual(url_or_none('rtspu://foo.de'), 'rtspu://foo.de')
+ self.assertEqual(url_or_none('ftps://foo.de'), 'ftps://foo.de')
def test_parse_age_limit(self):
self.assertEqual(parse_age_limit(None), None)
@@ -501,6 +647,8 @@ class TestUtil(unittest.TestCase):
self.assertEqual(parse_age_limit('PG-13'), 13)
self.assertEqual(parse_age_limit('TV-14'), 14)
self.assertEqual(parse_age_limit('TV-MA'), 17)
+ self.assertEqual(parse_age_limit('TV14'), 14)
+ self.assertEqual(parse_age_limit('TV_G'), 0)
def test_parse_duration(self):
self.assertEqual(parse_duration(None), None)
@@ -533,6 +681,7 @@ class TestUtil(unittest.TestCase):
self.assertEqual(parse_duration('87 Min.'), 5220)
self.assertEqual(parse_duration('PT1H0.040S'), 3600.04)
self.assertEqual(parse_duration('PT00H03M30SZ'), 210)
+ self.assertEqual(parse_duration('P0Y0M0DT0H4M20.880S'), 260.88)
def test_fix_xml_ampersands(self):
self.assertEqual(
@@ -586,60 +735,57 @@ class TestUtil(unittest.TestCase):
self.assertTrue(isinstance(data, bytes))
def test_update_url_query(self):
- def query_dict(url):
- return compat_parse_qs(compat_urlparse.urlparse(url).query)
- self.assertEqual(query_dict(update_url_query(
+ self.assertEqual(parse_qs(update_url_query(
'http://example.com/path', {'quality': ['HD'], 'format': ['mp4']})),
- query_dict('http://example.com/path?quality=HD&format=mp4'))
- self.assertEqual(query_dict(update_url_query(
+ parse_qs('http://example.com/path?quality=HD&format=mp4'))
+ self.assertEqual(parse_qs(update_url_query(
'http://example.com/path', {'system': ['LINUX', 'WINDOWS']})),
- query_dict('http://example.com/path?system=LINUX&system=WINDOWS'))
- self.assertEqual(query_dict(update_url_query(
+ parse_qs('http://example.com/path?system=LINUX&system=WINDOWS'))
+ self.assertEqual(parse_qs(update_url_query(
'http://example.com/path', {'fields': 'id,formats,subtitles'})),
- query_dict('http://example.com/path?fields=id,formats,subtitles'))
- self.assertEqual(query_dict(update_url_query(
+ parse_qs('http://example.com/path?fields=id,formats,subtitles'))
+ self.assertEqual(parse_qs(update_url_query(
'http://example.com/path', {'fields': ('id,formats,subtitles', 'thumbnails')})),
- query_dict('http://example.com/path?fields=id,formats,subtitles&fields=thumbnails'))
- self.assertEqual(query_dict(update_url_query(
+ parse_qs('http://example.com/path?fields=id,formats,subtitles&fields=thumbnails'))
+ self.assertEqual(parse_qs(update_url_query(
'http://example.com/path?manifest=f4m', {'manifest': []})),
- query_dict('http://example.com/path'))
- self.assertEqual(query_dict(update_url_query(
+ parse_qs('http://example.com/path'))
+ self.assertEqual(parse_qs(update_url_query(
'http://example.com/path?system=LINUX&system=WINDOWS', {'system': 'LINUX'})),
- query_dict('http://example.com/path?system=LINUX'))
- self.assertEqual(query_dict(update_url_query(
+ parse_qs('http://example.com/path?system=LINUX'))
+ self.assertEqual(parse_qs(update_url_query(
'http://example.com/path', {'fields': b'id,formats,subtitles'})),
- query_dict('http://example.com/path?fields=id,formats,subtitles'))
- self.assertEqual(query_dict(update_url_query(
+ parse_qs('http://example.com/path?fields=id,formats,subtitles'))
+ self.assertEqual(parse_qs(update_url_query(
'http://example.com/path', {'width': 1080, 'height': 720})),
- query_dict('http://example.com/path?width=1080&height=720'))
- self.assertEqual(query_dict(update_url_query(
+ parse_qs('http://example.com/path?width=1080&height=720'))
+ self.assertEqual(parse_qs(update_url_query(
'http://example.com/path', {'bitrate': 5020.43})),
- query_dict('http://example.com/path?bitrate=5020.43'))
- self.assertEqual(query_dict(update_url_query(
+ parse_qs('http://example.com/path?bitrate=5020.43'))
+ self.assertEqual(parse_qs(update_url_query(
'http://example.com/path', {'test': '第二行тест'})),
- query_dict('http://example.com/path?test=%E7%AC%AC%E4%BA%8C%E8%A1%8C%D1%82%D0%B5%D1%81%D1%82'))
-
- def test_dict_get(self):
- FALSE_VALUES = {
- 'none': None,
- 'false': False,
- 'zero': 0,
- 'empty_string': '',
- 'empty_list': [],
- }
- d = FALSE_VALUES.copy()
- d['a'] = 42
- self.assertEqual(dict_get(d, 'a'), 42)
- self.assertEqual(dict_get(d, 'b'), None)
- self.assertEqual(dict_get(d, 'b', 42), 42)
- self.assertEqual(dict_get(d, ('a', )), 42)
- self.assertEqual(dict_get(d, ('b', 'a', )), 42)
- self.assertEqual(dict_get(d, ('b', 'c', 'a', 'd', )), 42)
- self.assertEqual(dict_get(d, ('b', 'c', )), None)
- self.assertEqual(dict_get(d, ('b', 'c', ), 42), 42)
- for key, false_value in FALSE_VALUES.items():
- self.assertEqual(dict_get(d, ('b', 'c', key, )), None)
- self.assertEqual(dict_get(d, ('b', 'c', key, ), skip_false_values=False), false_value)
+ parse_qs('http://example.com/path?test=%E7%AC%AC%E4%BA%8C%E8%A1%8C%D1%82%D0%B5%D1%81%D1%82'))
+
+ def test_multipart_encode(self):
+ self.assertEqual(
+ multipart_encode({b'field': b'value'}, boundary='AAAAAA')[0],
+ b'--AAAAAA\r\nContent-Disposition: form-data; name="field"\r\n\r\nvalue\r\n--AAAAAA--\r\n')
+ self.assertEqual(
+ multipart_encode({'欄位'.encode('utf-8'): '值'.encode('utf-8')}, boundary='AAAAAA')[0],
+ b'--AAAAAA\r\nContent-Disposition: form-data; name="\xe6\xac\x84\xe4\xbd\x8d"\r\n\r\n\xe5\x80\xbc\r\n--AAAAAA--\r\n')
+ self.assertRaises(
+ ValueError, multipart_encode, {b'field': b'value'}, boundary='value')
+
+ def test_merge_dicts(self):
+ self.assertEqual(merge_dicts({'a': 1}, {'b': 2}), {'a': 1, 'b': 2})
+ self.assertEqual(merge_dicts({'a': 1}, {'a': 2}), {'a': 1})
+ self.assertEqual(merge_dicts({'a': 1}, {'a': None}), {'a': 1})
+ self.assertEqual(merge_dicts({'a': 1}, {'a': ''}), {'a': 1})
+ self.assertEqual(merge_dicts({'a': 1}, {}), {'a': 1})
+ self.assertEqual(merge_dicts({'a': None}, {'a': 1}), {'a': 1})
+ self.assertEqual(merge_dicts({'a': ''}, {'a': 1}), {'a': ''})
+ self.assertEqual(merge_dicts({'a': ''}, {'a': 'abc'}), {'a': 'abc'})
+ self.assertEqual(merge_dicts({'a': None}, {'a': ''}, {'a': 'abc'}), {'a': 'abc'})
def test_encode_compat_str(self):
self.assertEqual(encode_compat_str(b'\xd1\x82\xd0\xb5\xd1\x81\xd1\x82', 'utf-8'), 'тест')
@@ -666,6 +812,30 @@ class TestUtil(unittest.TestCase):
d = json.loads(stripped)
self.assertEqual(d, {'status': 'success'})
+ stripped = strip_jsonp('window.cb && window.cb({"status": "success"});')
+ d = json.loads(stripped)
+ self.assertEqual(d, {'status': 'success'})
+
+ stripped = strip_jsonp('window.cb && cb({"status": "success"});')
+ d = json.loads(stripped)
+ self.assertEqual(d, {'status': 'success'})
+
+ stripped = strip_jsonp('({"status": "success"});')
+ d = json.loads(stripped)
+ self.assertEqual(d, {'status': 'success'})
+
+ def test_strip_or_none(self):
+ self.assertEqual(strip_or_none(' abc'), 'abc')
+ self.assertEqual(strip_or_none('abc '), 'abc')
+ self.assertEqual(strip_or_none(' abc '), 'abc')
+ self.assertEqual(strip_or_none('\tabc\t'), 'abc')
+ self.assertEqual(strip_or_none('\n\tabc\n\t'), 'abc')
+ self.assertEqual(strip_or_none('abc'), 'abc')
+ self.assertEqual(strip_or_none(''), '')
+ self.assertEqual(strip_or_none(None), None)
+ self.assertEqual(strip_or_none(42), None)
+ self.assertEqual(strip_or_none([]), None)
+
def test_uppercase_escape(self):
self.assertEqual(uppercase_escape('aä'), 'aä')
self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐')
@@ -688,6 +858,8 @@ class TestUtil(unittest.TestCase):
self.assertEqual(mimetype2ext('text/vtt'), 'vtt')
self.assertEqual(mimetype2ext('text/vtt;charset=utf-8'), 'vtt')
self.assertEqual(mimetype2ext('text/html; charset=utf-8'), 'html')
+ self.assertEqual(mimetype2ext('audio/x-wav'), 'wav')
+ self.assertEqual(mimetype2ext('audio/x-wav;codec=pcm'), 'wav')
def test_month_by_name(self):
self.assertEqual(month_by_name(None), None)
@@ -719,6 +891,19 @@ class TestUtil(unittest.TestCase):
'vcodec': 'h264',
'acodec': 'aac',
})
+ self.assertEqual(parse_codecs('av01.0.05M.08'), {
+ 'vcodec': 'av01.0.05M.08',
+ 'acodec': 'none',
+ })
+ self.assertEqual(parse_codecs('theora, vorbis'), {
+ 'vcodec': 'theora',
+ 'acodec': 'vorbis',
+ })
+ self.assertEqual(parse_codecs('unknownvcodec, unknownacodec'), {
+ 'vcodec': 'unknownvcodec',
+ 'acodec': 'unknownacodec',
+ })
+ self.assertEqual(parse_codecs('unknown'), {})
def test_escape_rfc3986(self):
reserved = "!*'();:@&=+$,/?#[]"
@@ -749,6 +934,111 @@ class TestUtil(unittest.TestCase):
)
self.assertEqual(escape_url('http://vimeo.com/56015672#at=0'), 'http://vimeo.com/56015672#at=0')
+ def test_remove_dot_segments(self):
+
+ def remove_dot_segments(p):
+ q = '' if p.startswith('/') else '/'
+ p = 'http://example.com' + q + p
+ p = compat_urlparse.urlsplit(YoutubeDLHandler._fix_path(p)).path
+ return p[1:] if q else p
+
+ self.assertEqual(remove_dot_segments('/a/b/c/./../../g'), '/a/g')
+ self.assertEqual(remove_dot_segments('mid/content=5/../6'), 'mid/6')
+ self.assertEqual(remove_dot_segments('/ad/../cd'), '/cd')
+ self.assertEqual(remove_dot_segments('/ad/../cd/'), '/cd/')
+ self.assertEqual(remove_dot_segments('/..'), '/')
+ self.assertEqual(remove_dot_segments('/./'), '/')
+ self.assertEqual(remove_dot_segments('/./a'), '/a')
+ self.assertEqual(remove_dot_segments('/abc/./.././d/././e/.././f/./../../ghi'), '/ghi')
+ self.assertEqual(remove_dot_segments('/'), '/')
+ self.assertEqual(remove_dot_segments('/t'), '/t')
+ self.assertEqual(remove_dot_segments('t'), 't')
+ self.assertEqual(remove_dot_segments(''), '')
+ self.assertEqual(remove_dot_segments('/../a/b/c'), '/a/b/c')
+ self.assertEqual(remove_dot_segments('../a'), 'a')
+ self.assertEqual(remove_dot_segments('./a'), 'a')
+ self.assertEqual(remove_dot_segments('.'), '')
+ self.assertEqual(remove_dot_segments('////'), '////')
+
+ def test_js_to_json_vars_strings(self):
+ self.assertDictEqual(
+ json.loads(js_to_json(
+ '''{
+ 'null': a,
+ 'nullStr': b,
+ 'true': c,
+ 'trueStr': d,
+ 'false': e,
+ 'falseStr': f,
+ 'unresolvedVar': g,
+ }''',
+ {
+ 'a': 'null',
+ 'b': '"null"',
+ 'c': 'true',
+ 'd': '"true"',
+ 'e': 'false',
+ 'f': '"false"',
+ 'g': 'var',
+ }
+ )),
+ {
+ 'null': None,
+ 'nullStr': 'null',
+ 'true': True,
+ 'trueStr': 'true',
+ 'false': False,
+ 'falseStr': 'false',
+ 'unresolvedVar': 'var'
+ }
+ )
+
+ self.assertDictEqual(
+ json.loads(js_to_json(
+ '''{
+ 'int': a,
+ 'intStr': b,
+ 'float': c,
+ 'floatStr': d,
+ }''',
+ {
+ 'a': '123',
+ 'b': '"123"',
+ 'c': '1.23',
+ 'd': '"1.23"',
+ }
+ )),
+ {
+ 'int': 123,
+ 'intStr': '123',
+ 'float': 1.23,
+ 'floatStr': '1.23',
+ }
+ )
+
+ self.assertDictEqual(
+ json.loads(js_to_json(
+ '''{
+ 'object': a,
+ 'objectStr': b,
+ 'array': c,
+ 'arrayStr': d,
+ }''',
+ {
+ 'a': '{}',
+ 'b': '"{}"',
+ 'c': '[]',
+ 'd': '"[]"',
+ }
+ )),
+ {
+ 'object': {},
+ 'objectStr': '{}',
+ 'array': [],
+ 'arrayStr': '[]',
+ }
+ )
+
def test_js_to_json_realworld(self):
inp = '''{
'clip':{'provider':'pseudo'}
@@ -787,6 +1077,9 @@ class TestUtil(unittest.TestCase):
inp = '''{"duration": "00:01:07"}'''
self.assertEqual(js_to_json(inp), '''{"duration": "00:01:07"}''')
+ inp = '''{segments: [{"offset":-3.885780586188048e-16,"duration":39.75000000000001}]}'''
+ self.assertEqual(js_to_json(inp), '''{"segments": [{"offset":-3.885780586188048e-16,"duration":39.75000000000001}]}''')
+
def test_js_to_json_edgecases(self):
on = js_to_json("{abc_def:'1\\'\\\\2\\\\\\'3\"4'}")
self.assertEqual(json.loads(on), {"abc_def": "1'\\2\\'3\"4"})
@@ -804,6 +1097,28 @@ class TestUtil(unittest.TestCase):
self.assertEqual(d['x'], 1)
self.assertEqual(d['y'], 'a')
+ # Just drop ! prefix for now though this results in a wrong value
+ on = js_to_json('''{
+ a: !0,
+ b: !1,
+ c: !!0,
+ d: !!42.42,
+ e: !!![],
+ f: !"abc",
+ g: !"",
+ !42: 42
+ }''')
+ self.assertEqual(json.loads(on), {
+ 'a': True,
+ 'b': False,
+ 'c': False,
+ 'd': True,
+ 'e': [],
+ 'f': "abc",
+ 'g': "",
+ '42': 42
+ })
+
on = js_to_json('["abc", "def",]')
self.assertEqual(json.loads(on), ['abc', 'def'])
@@ -858,6 +1173,35 @@ class TestUtil(unittest.TestCase):
on = js_to_json('{/*comment\n*/42/*comment\n*/:/*comment\n*/42/*comment\n*/}')
self.assertEqual(json.loads(on), {'42': 42})
+ on = js_to_json('{42:4.2e1}')
+ self.assertEqual(json.loads(on), {'42': 42.0})
+
+ on = js_to_json('{ "0x40": "0x40" }')
+ self.assertEqual(json.loads(on), {'0x40': '0x40'})
+
+ on = js_to_json('{ "040": "040" }')
+ self.assertEqual(json.loads(on), {'040': '040'})
+
+ on = js_to_json('[1,//{},\n2]')
+ self.assertEqual(json.loads(on), [1, 2])
+
+ on = js_to_json(r'"\^\$\#"')
+ self.assertEqual(json.loads(on), R'^$#', msg='Unnecessary escapes should be stripped')
+
+ on = js_to_json('\'"\\""\'')
+ self.assertEqual(json.loads(on), '"""', msg='Unnecessary quote escape should be escaped')
+
+ def test_js_to_json_malformed(self):
+ self.assertEqual(js_to_json('42a1'), '42"a1"')
+ self.assertEqual(js_to_json('42a-1'), '42"a"-1')
+
+ def test_js_to_json_template_literal(self):
+ self.assertEqual(js_to_json('`Hello ${name}`', {'name': '"world"'}), '"Hello world"')
+ self.assertEqual(js_to_json('`${name}${name}`', {'name': '"X"'}), '"XX"')
+ self.assertEqual(js_to_json('`${name}${name}`', {'name': '5'}), '"55"')
+ self.assertEqual(js_to_json('`${name}"${name}"`', {'name': '5'}), '"5\\"5\\""')
+ self.assertEqual(js_to_json('`${name}`', {}), '"name"')
+
def test_extract_attributes(self):
self.assertEqual(extract_attributes('<e x="y">'), {'x': 'y'})
self.assertEqual(extract_attributes("<e x='y'>"), {'x': 'y'})
@@ -895,10 +1239,13 @@ class TestUtil(unittest.TestCase):
supports_outside_bmp = False
if supports_outside_bmp:
self.assertEqual(extract_attributes('<e x="Smile &#128512;!">'), {'x': 'Smile \U0001f600!'})
+ # Malformed HTML should not break attributes extraction on older Python
+ self.assertEqual(extract_attributes('<mal"formed/>'), {})
def test_clean_html(self):
self.assertEqual(clean_html('a:\nb'), 'a: b')
self.assertEqual(clean_html('a:\n "b"'), 'a: "b"')
+ self.assertEqual(clean_html('a<br>\xa0b'), 'a\nb')
def test_intlist_to_bytes(self):
self.assertEqual(
@@ -908,7 +1255,7 @@ class TestUtil(unittest.TestCase):
def test_args_to_str(self):
self.assertEqual(
args_to_str(['foo', 'ba/r', '-baz', '2 be', '']),
- 'foo ba/r -baz \'2 be\' \'\''
+ 'foo ba/r -baz \'2 be\' \'\'' if compat_os_name != 'nt' else 'foo ba/r -baz "2 be" ""'
)
def test_parse_filesize(self):
@@ -935,6 +1282,23 @@ class TestUtil(unittest.TestCase):
self.assertEqual(parse_count('1.1kk '), 1100000)
self.assertEqual(parse_count('1.1kk views'), 1100000)
+ def test_parse_resolution(self):
+ self.assertEqual(parse_resolution(None), {})
+ self.assertEqual(parse_resolution(''), {})
+ self.assertEqual(parse_resolution('1920x1080'), {'width': 1920, 'height': 1080})
+ self.assertEqual(parse_resolution('1920×1080'), {'width': 1920, 'height': 1080})
+ self.assertEqual(parse_resolution('1920 x 1080'), {'width': 1920, 'height': 1080})
+ self.assertEqual(parse_resolution('720p'), {'height': 720})
+ self.assertEqual(parse_resolution('4k'), {'height': 2160})
+ self.assertEqual(parse_resolution('8K'), {'height': 4320})
+
+ def test_parse_bitrate(self):
+ self.assertEqual(parse_bitrate(None), None)
+ self.assertEqual(parse_bitrate(''), None)
+ self.assertEqual(parse_bitrate('300kbps'), 300)
+ self.assertEqual(parse_bitrate('1500kbps'), 1500)
+ self.assertEqual(parse_bitrate('300 kbps'), 300)
+
def test_version_tuple(self):
self.assertEqual(version_tuple('1'), (1,))
self.assertEqual(version_tuple('10.23.344'), (10, 23, 344))
@@ -1013,6 +1377,18 @@ ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')
self.assertFalse(match_str(
'like_count > 100 & dislike_count <? 50 & description',
{'like_count': 190, 'dislike_count': 10}))
+ self.assertTrue(match_str('is_live', {'is_live': True}))
+ self.assertFalse(match_str('is_live', {'is_live': False}))
+ self.assertFalse(match_str('is_live', {'is_live': None}))
+ self.assertFalse(match_str('is_live', {}))
+ self.assertFalse(match_str('!is_live', {'is_live': True}))
+ self.assertTrue(match_str('!is_live', {'is_live': False}))
+ self.assertTrue(match_str('!is_live', {'is_live': None}))
+ self.assertTrue(match_str('!is_live', {}))
+ self.assertTrue(match_str('title', {'title': 'abc'}))
+ self.assertTrue(match_str('title', {'title': ''}))
+ self.assertFalse(match_str('!title', {'title': 'abc'}))
+ self.assertFalse(match_str('!title', {'title': ''}))
def test_parse_dfxp_time_expr(self):
self.assertEqual(parse_dfxp_time_expr(None), None)
@@ -1036,7 +1412,7 @@ ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')
<p begin="3" dur="-1">Ignored, three</p>
</div>
</body>
- </tt>'''
+ </tt>'''.encode('utf-8')
srt_data = '''1
00:00:00,000 --> 00:00:01,000
The following line contains Chinese characters and special symbols
@@ -1061,7 +1437,7 @@ Line
<p begin="0" end="1">The first line</p>
</div>
</body>
- </tt>'''
+ </tt>'''.encode('utf-8')
srt_data = '''1
00:00:00,000 --> 00:00:01,000
The first line
@@ -1069,6 +1445,67 @@ The first line
'''
self.assertEqual(dfxp2srt(dfxp_data_no_default_namespace), srt_data)
+ dfxp_data_with_style = '''<?xml version="1.0" encoding="utf-8"?>
+<tt xmlns="http://www.w3.org/2006/10/ttaf1" xmlns:ttp="http://www.w3.org/2006/10/ttaf1#parameter" ttp:timeBase="media" xmlns:tts="http://www.w3.org/2006/10/ttaf1#style" xml:lang="en" xmlns:ttm="http://www.w3.org/2006/10/ttaf1#metadata">
+ <head>
+ <styling>
+ <style id="s2" style="s0" tts:color="cyan" tts:fontWeight="bold" />
+ <style id="s1" style="s0" tts:color="yellow" tts:fontStyle="italic" />
+ <style id="s3" style="s0" tts:color="lime" tts:textDecoration="underline" />
+ <style id="s0" tts:backgroundColor="black" tts:fontStyle="normal" tts:fontSize="16" tts:fontFamily="sansSerif" tts:color="white" />
+ </styling>
+ </head>
+ <body tts:textAlign="center" style="s0">
+ <div>
+ <p begin="00:00:02.08" id="p0" end="00:00:05.84">default style<span tts:color="red">custom style</span></p>
+ <p style="s2" begin="00:00:02.08" id="p0" end="00:00:05.84"><span tts:color="lime">part 1<br /></span><span tts:color="cyan">part 2</span></p>
+ <p style="s3" begin="00:00:05.84" id="p1" end="00:00:09.56">line 3<br />part 3</p>
+ <p style="s1" tts:textDecoration="underline" begin="00:00:09.56" id="p2" end="00:00:12.36"><span style="s2" tts:color="lime">inner<br /> </span>style</p>
+ </div>
+ </body>
+</tt>'''.encode('utf-8')
+ srt_data = '''1
+00:00:02,080 --> 00:00:05,839
+<font color="white" face="sansSerif" size="16">default style<font color="red">custom style</font></font>
+
+2
+00:00:02,080 --> 00:00:05,839
+<b><font color="cyan" face="sansSerif" size="16"><font color="lime">part 1
+</font>part 2</font></b>
+
+3
+00:00:05,839 --> 00:00:09,560
+<u><font color="lime">line 3
+part 3</font></u>
+
+4
+00:00:09,560 --> 00:00:12,359
+<i><u><font color="yellow"><font color="lime">inner
+ </font>style</font></u></i>
+
+'''
+ self.assertEqual(dfxp2srt(dfxp_data_with_style), srt_data)
+
+ dfxp_data_non_utf8 = '''<?xml version="1.0" encoding="UTF-16"?>
+ <tt xmlns="http://www.w3.org/ns/ttml" xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter">
+ <body>
+ <div xml:lang="en">
+ <p begin="0" end="1">Line 1</p>
+ <p begin="1" end="2">第二行</p>
+ </div>
+ </body>
+ </tt>'''.encode('utf-16')
+ srt_data = '''1
+00:00:00,000 --> 00:00:01,000
+Line 1
+
+2
+00:00:01,000 --> 00:00:02,000
+第二行
+
+'''
+ self.assertEqual(dfxp2srt(dfxp_data_non_utf8), srt_data)
+
def test_cli_option(self):
self.assertEqual(cli_option({'proxy': '127.0.0.1:3128'}, '--proxy', 'proxy'), ['--proxy', '127.0.0.1:3128'])
self.assertEqual(cli_option({'proxy': None}, '--proxy', 'proxy'), [])
@@ -1114,6 +1551,10 @@ The first line
cli_bool_option(
{'nocheckcertificate': False}, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='),
['--check-certificate=true'])
+ self.assertEqual(
+ cli_bool_option(
+ {}, '--check-certificate', 'nocheckcertificate', 'false', 'true', '='),
+ [])
def test_ohdave_rsa_encrypt(self):
N = 0xab86b6371b5318aaa1d3c9e612a9f1264f372323c8c0f19875b5fc3b3fd3afcc1e5bec527aa94bfa85bffc157e4245aebda05389a5357b75115ac94f074aefcd
@@ -1142,6 +1583,20 @@ The first line
self.assertRaises(ValueError, encode_base_n, 0, 70)
self.assertRaises(ValueError, encode_base_n, 0, 60, custom_table)
+ def test_caesar(self):
+ self.assertEqual(caesar('ace', 'abcdef', 2), 'cea')
+ self.assertEqual(caesar('cea', 'abcdef', -2), 'ace')
+ self.assertEqual(caesar('ace', 'abcdef', -2), 'eac')
+ self.assertEqual(caesar('eac', 'abcdef', 2), 'ace')
+ self.assertEqual(caesar('ace', 'abcdef', 0), 'ace')
+ self.assertEqual(caesar('xyz', 'abcdef', 2), 'xyz')
+ self.assertEqual(caesar('abc', 'acegik', 2), 'ebg')
+ self.assertEqual(caesar('ebg', 'acegik', -2), 'abc')
+
+ def test_rot47(self):
+ self.assertEqual(rot47('youtube-dl'), r'J@FEF36\5=')
+ self.assertEqual(rot47('YOUTUBE-DL'), r'*~&%&qt\s{')
+
def test_urshift(self):
self.assertEqual(urshift(3, 1), 1)
self.assertEqual(urshift(-3, 1), 2147483646)
@@ -1163,6 +1618,12 @@ The first line
self.assertEqual(get_element_by_attribute('class', 'foo', html), None)
self.assertEqual(get_element_by_attribute('class', 'no-such-foo', html), None)
+ html = '''
+ <div itemprop="author" itemscope>foo</div>
+ '''
+
+ self.assertEqual(get_element_by_attribute('itemprop', 'author', html), 'foo')
+
def test_get_elements_by_class(self):
html = '''
<span class="foo bar">nice</span><span class="foo bar">also nice</span>
@@ -1180,6 +1641,88 @@ The first line
self.assertEqual(get_elements_by_attribute('class', 'foo', html), [])
self.assertEqual(get_elements_by_attribute('class', 'no-such-foo', html), [])
+ def test_clean_podcast_url(self):
+ self.assertEqual(clean_podcast_url('https://www.podtrac.com/pts/redirect.mp3/chtbl.com/track/5899E/traffic.megaphone.fm/HSW7835899191.mp3'), 'https://traffic.megaphone.fm/HSW7835899191.mp3')
+ self.assertEqual(clean_podcast_url('https://play.podtrac.com/npr-344098539/edge1.pod.npr.org/anon.npr-podcasts/podcast/npr/waitwait/2020/10/20201003_waitwait_wwdtmpodcast201003-015621a5-f035-4eca-a9a1-7c118d90bc3c.mp3'), 'https://edge1.pod.npr.org/anon.npr-podcasts/podcast/npr/waitwait/2020/10/20201003_waitwait_wwdtmpodcast201003-015621a5-f035-4eca-a9a1-7c118d90bc3c.mp3')
+
+ def test_LazyList(self):
+ it = list(range(10))
+
+ self.assertEqual(list(LazyList(it)), it)
+ self.assertEqual(LazyList(it).exhaust(), it)
+ self.assertEqual(LazyList(it)[5], it[5])
+
+ self.assertEqual(LazyList(it)[5:], it[5:])
+ self.assertEqual(LazyList(it)[:5], it[:5])
+ self.assertEqual(LazyList(it)[::2], it[::2])
+ self.assertEqual(LazyList(it)[1::2], it[1::2])
+ self.assertEqual(LazyList(it)[5::-1], it[5::-1])
+ self.assertEqual(LazyList(it)[6:2:-2], it[6:2:-2])
+ self.assertEqual(LazyList(it)[::-1], it[::-1])
+
+ self.assertTrue(LazyList(it))
+ self.assertFalse(LazyList(range(0)))
+ self.assertEqual(len(LazyList(it)), len(it))
+ self.assertEqual(repr(LazyList(it)), repr(it))
+ self.assertEqual(compat_str(LazyList(it)), compat_str(it))
+
+ self.assertEqual(list(LazyList(it, reverse=True)), it[::-1])
+ self.assertEqual(list(reversed(LazyList(it))[::-1]), it)
+ self.assertEqual(list(reversed(LazyList(it))[1:3:7]), it[::-1][1:3:7])
+
+ def test_LazyList_laziness(self):
+
+ def test(ll, idx, val, cache):
+ self.assertEqual(ll[idx], val)
+ self.assertEqual(ll._cache, list(cache))
+
+ ll = LazyList(range(10))
+ test(ll, 0, 0, range(1))
+ test(ll, 5, 5, range(6))
+ test(ll, -3, 7, range(10))
+
+ ll = LazyList(range(10), reverse=True)
+ test(ll, -1, 0, range(1))
+ test(ll, 3, 6, range(10))
+
+ ll = LazyList(itertools.count())
+ test(ll, 10, 10, range(11))
+ ll = reversed(ll)
+ test(ll, -15, 14, range(15))
+
+ def test_try_call(self):
+ def total(*x, **kwargs):
+ return sum(x) + sum(kwargs.values())
+
+ self.assertEqual(try_call(None), None,
+ msg='not a fn should give None')
+ self.assertEqual(try_call(lambda: 1), 1,
+ msg='int fn with no expected_type should give int')
+ self.assertEqual(try_call(lambda: 1, expected_type=int), 1,
+ msg='int fn with expected_type int should give int')
+ self.assertEqual(try_call(lambda: 1, expected_type=dict), None,
+ msg='int fn with wrong expected_type should give None')
+ self.assertEqual(try_call(total, args=(0, 1, 0, ), expected_type=int), 1,
+ msg='fn should accept arglist')
+ self.assertEqual(try_call(total, kwargs={'a': 0, 'b': 1, 'c': 0}, expected_type=int), 1,
+ msg='fn should accept kwargs')
+ self.assertEqual(try_call(lambda: 1, expected_type=dict), None,
+ msg='int fn with no expected_type should give None')
+ self.assertEqual(try_call(lambda x: {}, total, args=(42, ), expected_type=int), 42,
+ msg='expect first int result with expected_type int')
+
+ def test_variadic(self):
+ self.assertEqual(variadic(None), (None, ))
+ self.assertEqual(variadic('spam'), ('spam', ))
+ self.assertEqual(variadic('spam', allowed_types=dict), 'spam')
+ self.assertEqual(variadic('spam', allowed_types=[dict]), 'spam')
+
+ def test_join_nonempty(self):
+ self.assertEqual(join_nonempty('a', 'b'), 'a-b')
+ self.assertEqual(join_nonempty(
+ 'a', 'b', 'c', 'd',
+ from_dict={'a': 'c', 'c': [], 'b': 'd', 'd': None}), 'c-d')
+
if __name__ == '__main__':
unittest.main()
diff --git a/test/test_write_annotations.py b/test/test_write_annotations.py
index 41abdfe3b..68e0a391d 100644
--- a/test/test_write_annotations.py
+++ b/test/test_write_annotations.py
@@ -11,12 +11,11 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from test.helper import get_params, try_rm
-import io
-
import xml.etree.ElementTree
import youtube_dl.YoutubeDL
import youtube_dl.extractor
+from youtube_dl.compat import compat_open as open
class YoutubeDL(youtube_dl.YoutubeDL):
@@ -51,7 +50,7 @@ class TestAnnotations(unittest.TestCase):
ydl.download([TEST_ID])
self.assertTrue(os.path.exists(ANNOTATIONS_FILE))
annoxml = None
- with io.open(ANNOTATIONS_FILE, 'r', encoding='utf-8') as annof:
+ with open(ANNOTATIONS_FILE, 'r', encoding='utf-8') as annof:
annoxml = xml.etree.ElementTree.parse(annof)
self.assertTrue(annoxml is not None, 'Failed to parse annotations XML')
root = annoxml.getroot()
diff --git a/test/test_youtube_lists.py b/test/test_youtube_lists.py
index 7a33dbf88..e0e8891ba 100644
--- a/test/test_youtube_lists.py
+++ b/test/test_youtube_lists.py
@@ -1,4 +1,5 @@
#!/usr/bin/env python
+# -*- coding: utf-8 -*-
from __future__ import unicode_literals
# Allow direct execution
@@ -9,10 +10,10 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from test.helper import FakeYDL
-
from youtube_dl.extractor import (
- YoutubePlaylistIE,
YoutubeIE,
+ YoutubePlaylistIE,
+ YoutubeTabIE,
)
@@ -24,47 +25,40 @@ class TestYoutubeLists(unittest.TestCase):
def test_youtube_playlist_noplaylist(self):
dl = FakeYDL()
dl.params['noplaylist'] = True
+ dl.params['format'] = 'best'
ie = YoutubePlaylistIE(dl)
result = ie.extract('https://www.youtube.com/watch?v=FXxLjLQi3Fg&list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re')
self.assertEqual(result['_type'], 'url')
+ result = dl.extract_info(result['url'], download=False, ie_key=result.get('ie_key'), process=False)
self.assertEqual(YoutubeIE().extract_id(result['url']), 'FXxLjLQi3Fg')
- def test_youtube_course(self):
- dl = FakeYDL()
- ie = YoutubePlaylistIE(dl)
- # TODO find a > 100 (paginating?) videos course
- result = ie.extract('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
- entries = list(result['entries'])
- self.assertEqual(YoutubeIE().extract_id(entries[0]['url']), 'j9WZyLZCBzs')
- self.assertEqual(len(entries), 25)
- self.assertEqual(YoutubeIE().extract_id(entries[-1]['url']), 'rYefUsYuEp0')
-
def test_youtube_mix(self):
dl = FakeYDL()
- ie = YoutubePlaylistIE(dl)
- result = ie.extract('https://www.youtube.com/watch?v=W01L70IGBgE&index=2&list=RDOQpdSVF_k_w')
- entries = result['entries']
- self.assertTrue(len(entries) >= 50)
+ dl.params['format'] = 'best'
+ ie = YoutubeTabIE(dl)
+ result = dl.extract_info('https://www.youtube.com/watch?v=tyITL_exICo&list=RDCLAK5uy_kLWIr9gv1XLlPbaDS965-Db4TrBoUTxQ8',
+ download=False, ie_key=ie.ie_key(), process=True)
+ entries = (result or {}).get('entries', [{'id': 'not_found', }])
+ self.assertTrue(len(entries) >= 25)
original_video = entries[0]
- self.assertEqual(original_video['id'], 'OQpdSVF_k_w')
-
- def test_youtube_toptracks(self):
- print('Skipping: The playlist page gives error 500')
- return
- dl = FakeYDL()
- ie = YoutubePlaylistIE(dl)
- result = ie.extract('https://www.youtube.com/playlist?list=MCUS')
- entries = result['entries']
- self.assertEqual(len(entries), 100)
+ self.assertEqual(original_video['id'], 'tyITL_exICo')
- def test_youtube_flat_playlist_titles(self):
+ def test_youtube_flat_playlist_extraction(self):
dl = FakeYDL()
dl.params['extract_flat'] = True
- ie = YoutubePlaylistIE(dl)
- result = ie.extract('https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re')
+ ie = YoutubeTabIE(dl)
+ result = ie.extract('https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc')
self.assertIsPlaylist(result)
- for entry in result['entries']:
- self.assertTrue(entry.get('title'))
+ entries = list(result['entries'])
+ self.assertTrue(len(entries) == 1)
+ video = entries[0]
+ self.assertEqual(video['_type'], 'url')
+ self.assertEqual(video['ie_key'], 'Youtube')
+ self.assertEqual(video['id'], 'BaW_jenozKc')
+ self.assertEqual(video['url'], 'BaW_jenozKc')
+ self.assertEqual(video['title'], 'youtube-dl test video "\'/\\ä↭𝕐')
+ self.assertEqual(video['duration'], 10)
+ self.assertEqual(video['uploader'], 'Philipp Hagemeister')
if __name__ == '__main__':
diff --git a/test/test_youtube_misc.py b/test/test_youtube_misc.py
new file mode 100644
index 000000000..e18e71101
--- /dev/null
+++ b/test/test_youtube_misc.py
@@ -0,0 +1,26 @@
+#!/usr/bin/env python
+from __future__ import unicode_literals
+
+# Allow direct execution
+import os
+import sys
+import unittest
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+
+from youtube_dl.extractor import YoutubeIE
+
+
+class TestYoutubeMisc(unittest.TestCase):
+ def test_youtube_extract(self):
+ assertExtractId = lambda url, id: self.assertEqual(YoutubeIE.extract_id(url), id)
+ assertExtractId('http://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
+ assertExtractId('https://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
+ assertExtractId('https://www.youtube.com/watch?feature=player_embedded&v=BaW_jenozKc', 'BaW_jenozKc')
+ assertExtractId('https://www.youtube.com/watch_popup?v=BaW_jenozKc', 'BaW_jenozKc')
+ assertExtractId('http://www.youtube.com/watch?v=BaW_jenozKcsharePLED17F32AD9753930', 'BaW_jenozKc')
+ assertExtractId('BaW_jenozKc', 'BaW_jenozKc')
+
+
+if __name__ == '__main__':
+ unittest.main()
diff --git a/test/test_youtube_signature.py b/test/test_youtube_signature.py
index f0c370eee..98221b9c2 100644
--- a/test/test_youtube_signature.py
+++ b/test/test_youtube_signature.py
@@ -1,4 +1,5 @@
#!/usr/bin/env python
+# coding: utf-8
from __future__ import unicode_literals
@@ -8,115 +9,438 @@ import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-import io
import re
import string
+from youtube_dl.compat import (
+ compat_contextlib_suppress,
+ compat_open as open,
+ compat_str,
+ compat_urlretrieve,
+)
+
from test.helper import FakeYDL
from youtube_dl.extractor import YoutubeIE
-from youtube_dl.compat import compat_str, compat_urlretrieve
+from youtube_dl.jsinterp import JSInterpreter
-_TESTS = [
+_SIG_TESTS = [
(
'https://s.ytimg.com/yts/jsbin/html5player-vflHOr_nV.js',
- 'js',
86,
'>=<;:/.-[+*)(\'&%$#"!ZYX0VUTSRQPONMLKJIHGFEDCBA\\yxwvutsrqponmlkjihgfedcba987654321',
),
(
'https://s.ytimg.com/yts/jsbin/html5player-vfldJ8xgI.js',
- 'js',
85,
'3456789a0cdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRS[UVWXYZ!"#$%&\'()*+,-./:;<=>?@',
),
(
'https://s.ytimg.com/yts/jsbin/html5player-vfle-mVwz.js',
- 'js',
90,
']\\[@?>=<;:/.-,+*)(\'&%$#"hZYXWVUTSRQPONMLKJIHGFEDCBAzyxwvutsrqponmlkjiagfedcb39876',
),
(
'https://s.ytimg.com/yts/jsbin/html5player-en_US-vfl0Cbn9e.js',
- 'js',
84,
'O1I3456789abcde0ghijklmnopqrstuvwxyzABCDEFGHfJKLMN2PQRSTUVW@YZ!"#$%&\'()*+,-./:;<=',
),
(
'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflXGBaUN.js',
- 'js',
'2ACFC7A61CA478CD21425E5A57EBD73DDC78E22A.2094302436B2D377D14A3BBA23022D023B8BC25AA',
'A52CB8B320D22032ABB3A41D773D2B6342034902.A22E87CDD37DBE75A5E52412DC874AC16A7CFCA2',
),
(
'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflBb0OQx.js',
- 'js',
84,
- '123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQ0STUVWXYZ!"#$%&\'()*+,@./:;<=>'
+ '123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQ0STUVWXYZ!"#$%&\'()*+,@./:;<=>',
),
(
'https://s.ytimg.com/yts/jsbin/html5player-en_US-vfl9FYC6l.js',
- 'js',
83,
- '123456789abcdefghijklmnopqr0tuvwxyzABCDETGHIJKLMNOPQRS>UVWXYZ!"#$%&\'()*+,-./:;<=F'
+ '123456789abcdefghijklmnopqr0tuvwxyzABCDETGHIJKLMNOPQRS>UVWXYZ!"#$%&\'()*+,-./:;<=F',
),
(
'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflCGk6yw/html5player.js',
- 'js',
'4646B5181C6C3020DF1D9C7FCFEA.AD80ABF70C39BD369CCCAE780AFBB98FA6B6CB42766249D9488C288',
- '82C8849D94266724DC6B6AF89BBFA087EACCD963.B93C07FBA084ACAEFCF7C9D1FD0203C6C1815B6B'
+ '82C8849D94266724DC6B6AF89BBFA087EACCD963.B93C07FBA084ACAEFCF7C9D1FD0203C6C1815B6B',
),
(
'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflKjOTVq/html5player.js',
- 'js',
'312AA52209E3623129A412D56A40F11CB0AF14AE.3EE09501CB14E3BCDC3B2AE808BF3F1D14E7FBF12',
'112AA5220913623229A412D56A40F11CB0AF14AE.3EE0950FCB14EEBCDC3B2AE808BF331D14E7FBF3',
- )
+ ),
+ (
+ 'https://www.youtube.com/s/player/6ed0d907/player_ias.vflset/en_US/base.js',
+ '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
+ 'AOq0QJ8wRAIgXmPlOPSBkkUs1bYFYlJCfe29xx8j7v1pDL2QwbdV96sCIEzpWqMGkFR20CFOg51Tp-7vj_EMu-m37KtXJoOySqa0',
+ ),
+ (
+ 'https://www.youtube.com/s/player/3bb1f723/player_ias.vflset/en_US/base.js',
+ '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
+ 'MyOSJXtKI3m-uME_jv7-pT12gOFC02RFkGoqWpzE0Cs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
+ ),
+ (
+ 'https://www.youtube.com/s/player/2f1832d2/player_ias.vflset/en_US/base.js',
+ '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
+ '0QJ8wRAIgXmPlOPSBkkUs1bYFYlJCfe29xxAj7v1pDL0QwbdV96sCIEzpWqMGkFR20CFOg51Tp-7vj_EMu-m37KtXJ2OySqa0q',
+ ),
+ (
+ 'https://www.youtube.com/s/player/643afba4/tv-player-ias.vflset/tv-player-ias.js',
+ '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
+ 'AAOAOq0QJ8wRAIgXmPlOPSBkkUs1bYFYlJCfe29xx8j7vgpDL0QwbdV06sCIEzpWqMGkFR20CFOS21Tp-7vj_EMu-m37KtXJoOy1',
+ ),
+ (
+ 'https://www.youtube.com/s/player/363db69b/player_ias.vflset/en_US/base.js',
+ '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
+ '0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpz2ICs6EVdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
+ ),
+ (
+ 'https://www.youtube.com/s/player/363db69b/player_ias_tce.vflset/en_US/base.js',
+ '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
+ '0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpz2ICs6EVdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
+ ),
+ (
+ 'https://www.youtube.com/s/player/4fcd6e4a/player_ias.vflset/en_US/base.js',
+ '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
+ 'wAOAOq0QJ8ARAIgXmPlOPSBkkUs1bYFYlJCfe29xx8q7v1pDL0QwbdV96sCIEzpWqMGkFR20CFOg51Tp-7vj_EMu-m37KtXJoOySqa0',
+ ),
+ (
+ 'https://www.youtube.com/s/player/4fcd6e4a/player_ias_tce.vflset/en_US/base.js',
+ '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
+ 'wAOAOq0QJ8ARAIgXmPlOPSBkkUs1bYFYlJCfe29xx8q7v1pDL0QwbdV96sCIEzpWqMGkFR20CFOg51Tp-7vj_EMu-m37KtXJoOySqa0',
+ ),
+ (
+ 'https://www.youtube.com/s/player/20830619/player_ias.vflset/en_US/base.js',
+ '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
+ '7AOq0QJ8wRAIgXmPlOPSBkkAs1bYFYlJCfe29xx8jOv1pDL0Q2bdV96sCIEzpWqMGkFR20CFOg51Tp-7vj_EMu-m37KtXJoOySqa0qaw',
+ ),
+ (
+ 'https://www.youtube.com/s/player/20830619/player_ias_tce.vflset/en_US/base.js',
+ '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
+ '7AOq0QJ8wRAIgXmPlOPSBkkAs1bYFYlJCfe29xx8jOv1pDL0Q2bdV96sCIEzpWqMGkFR20CFOg51Tp-7vj_EMu-m37KtXJoOySqa0qaw',
+ ),
+ (
+ 'https://www.youtube.com/s/player/20830619/player-plasma-ias-phone-en_US.vflset/base.js',
+ '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
+ '7AOq0QJ8wRAIgXmPlOPSBkkAs1bYFYlJCfe29xx8jOv1pDL0Q2bdV96sCIEzpWqMGkFR20CFOg51Tp-7vj_EMu-m37KtXJoOySqa0qaw',
+ ),
+ (
+ 'https://www.youtube.com/s/player/20830619/player-plasma-ias-tablet-en_US.vflset/base.js',
+ '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
+ '7AOq0QJ8wRAIgXmPlOPSBkkAs1bYFYlJCfe29xx8jOv1pDL0Q2bdV96sCIEzpWqMGkFR20CFOg51Tp-7vj_EMu-m37KtXJoOySqa0qaw',
+ ),
+ (
+ 'https://www.youtube.com/s/player/8a8ac953/player_ias_tce.vflset/en_US/base.js',
+ '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
+ 'IAOAOq0QJ8wRAAgXmPlOPSBkkUs1bYFYlJCfe29xx8j7v1pDL0QwbdV96sCIEzpWqMGkFR20CFOg51Tp-7vj_E2u-m37KtXJoOySqa0',
+ ),
+ (
+ 'https://www.youtube.com/s/player/8a8ac953/tv-player-es6.vflset/tv-player-es6.js',
+ '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
+ 'IAOAOq0QJ8wRAAgXmPlOPSBkkUs1bYFYlJCfe29xx8j7v1pDL0QwbdV96sCIEzpWqMGkFR20CFOg51Tp-7vj_E2u-m37KtXJoOySqa0',
+ ),
+]
+
+_NSIG_TESTS = [
+ (
+ 'https://www.youtube.com/s/player/7862ca1f/player_ias.vflset/en_US/base.js',
+ 'X_LCxVDjAavgE5t', 'yxJ1dM6iz5ogUg',
+ ),
+ (
+ 'https://www.youtube.com/s/player/9216d1f7/player_ias.vflset/en_US/base.js',
+ 'SLp9F5bwjAdhE9F-', 'gWnb9IK2DJ8Q1w',
+ ),
+ (
+ 'https://www.youtube.com/s/player/f8cb7a3b/player_ias.vflset/en_US/base.js',
+ 'oBo2h5euWy6osrUt', 'ivXHpm7qJjJN',
+ ),
+ (
+ 'https://www.youtube.com/s/player/2dfe380c/player_ias.vflset/en_US/base.js',
+ 'oBo2h5euWy6osrUt', '3DIBbn3qdQ',
+ ),
+ (
+ 'https://www.youtube.com/s/player/f1ca6900/player_ias.vflset/en_US/base.js',
+ 'cu3wyu6LQn2hse', 'jvxetvmlI9AN9Q',
+ ),
+ (
+ 'https://www.youtube.com/s/player/8040e515/player_ias.vflset/en_US/base.js',
+ 'wvOFaY-yjgDuIEg5', 'HkfBFDHmgw4rsw',
+ ),
+ (
+ 'https://www.youtube.com/s/player/e06dea74/player_ias.vflset/en_US/base.js',
+ 'AiuodmaDDYw8d3y4bf', 'ankd8eza2T6Qmw',
+ ),
+ (
+ 'https://www.youtube.com/s/player/5dd88d1d/player-plasma-ias-phone-en_US.vflset/base.js',
+ 'kSxKFLeqzv_ZyHSAt', 'n8gS8oRlHOxPFA',
+ ),
+ (
+ 'https://www.youtube.com/s/player/324f67b9/player_ias.vflset/en_US/base.js',
+ 'xdftNy7dh9QGnhW', '22qLGxrmX8F1rA',
+ ),
+ (
+ 'https://www.youtube.com/s/player/4c3f79c5/player_ias.vflset/en_US/base.js',
+ 'TDCstCG66tEAO5pR9o', 'dbxNtZ14c-yWyw',
+ ),
+ (
+ 'https://www.youtube.com/s/player/c81bbb4a/player_ias.vflset/en_US/base.js',
+ 'gre3EcLurNY2vqp94', 'Z9DfGxWP115WTg',
+ ),
+ (
+ 'https://www.youtube.com/s/player/1f7d5369/player_ias.vflset/en_US/base.js',
+ 'batNX7sYqIJdkJ', 'IhOkL_zxbkOZBw',
+ ),
+ (
+ 'https://www.youtube.com/s/player/009f1d77/player_ias.vflset/en_US/base.js',
+ '5dwFHw8aFWQUQtffRq', 'audescmLUzI3jw',
+ ),
+ (
+ 'https://www.youtube.com/s/player/dc0c6770/player_ias.vflset/en_US/base.js',
+ '5EHDMgYLV6HPGk_Mu-kk', 'n9lUJLHbxUI0GQ',
+ ),
+ (
+ 'https://www.youtube.com/s/player/c2199353/player_ias.vflset/en_US/base.js',
+ '5EHDMgYLV6HPGk_Mu-kk', 'AD5rgS85EkrE7',
+ ),
+ (
+ 'https://www.youtube.com/s/player/113ca41c/player_ias.vflset/en_US/base.js',
+ 'cgYl-tlYkhjT7A', 'hI7BBr2zUgcmMg',
+ ),
+ (
+ 'https://www.youtube.com/s/player/c57c113c/player_ias.vflset/en_US/base.js',
+ 'M92UUMHa8PdvPd3wyM', '3hPqLJsiNZx7yA',
+ ),
+ (
+ 'https://www.youtube.com/s/player/5a3b6271/player_ias.vflset/en_US/base.js',
+ 'B2j7f_UPT4rfje85Lu_e', 'm5DmNymaGQ5RdQ',
+ ),
+ (
+ 'https://www.youtube.com/s/player/7a062b77/player_ias.vflset/en_US/base.js',
+ 'NRcE3y3mVtm_cV-W', 'VbsCYUATvqlt5w',
+ ),
+ (
+ 'https://www.youtube.com/s/player/dac945fd/player_ias.vflset/en_US/base.js',
+ 'o8BkRxXhuYsBCWi6RplPdP', '3Lx32v_hmzTm6A',
+ ),
+ (
+ 'https://www.youtube.com/s/player/6f20102c/player_ias.vflset/en_US/base.js',
+ 'lE8DhoDmKqnmJJ', 'pJTTX6XyJP2BYw',
+ ),
+ (
+ 'https://www.youtube.com/s/player/cfa9e7cb/player_ias.vflset/en_US/base.js',
+ 'aCi3iElgd2kq0bxVbQ', 'QX1y8jGb2IbZ0w',
+ ),
+ (
+ 'https://www.youtube.com/s/player/8c7583ff/player_ias.vflset/en_US/base.js',
+ '1wWCVpRR96eAmMI87L', 'KSkWAVv1ZQxC3A',
+ ),
+ (
+ 'https://www.youtube.com/s/player/b7910ca8/player_ias.vflset/en_US/base.js',
+ '_hXMCwMt9qE310D', 'LoZMgkkofRMCZQ',
+ ),
+ (
+ 'https://www.youtube.com/s/player/590f65a6/player_ias.vflset/en_US/base.js',
+ '1tm7-g_A9zsI8_Lay_', 'xI4Vem4Put_rOg',
+ ),
+ (
+ 'https://www.youtube.com/s/player/b22ef6e7/player_ias.vflset/en_US/base.js',
+ 'b6HcntHGkvBLk_FRf', 'kNPW6A7FyP2l8A',
+ ),
+ (
+ 'https://www.youtube.com/s/player/3400486c/player_ias.vflset/en_US/base.js',
+ 'lL46g3XifCKUZn1Xfw', 'z767lhet6V2Skl',
+ ),
+ (
+ 'https://www.youtube.com/s/player/5604538d/player_ias.vflset/en_US/base.js',
+ '7X-he4jjvMx7BCX', 'sViSydX8IHtdWA',
+ ),
+ (
+ 'https://www.youtube.com/s/player/20dfca59/player_ias.vflset/en_US/base.js',
+ '-fLCxedkAk4LUTK2', 'O8kfRq1y1eyHGw',
+ ),
+ (
+ 'https://www.youtube.com/s/player/b12cc44b/player_ias.vflset/en_US/base.js',
+ 'keLa5R2U00sR9SQK', 'N1OGyujjEwMnLw',
+ ),
+ (
+ 'https://www.youtube.com/s/player/3bb1f723/player_ias.vflset/en_US/base.js',
+ 'gK15nzVyaXE9RsMP3z', 'ZFFWFLPWx9DEgQ',
+ ),
+ (
+ 'https://www.youtube.com/s/player/f8f53e1a/player_ias.vflset/en_US/base.js',
+ 'VTQOUOv0mCIeJ7i8kZB', 'kcfD8wy0sNLyNQ',
+ ),
+ (
+ 'https://www.youtube.com/s/player/2f1832d2/player_ias.vflset/en_US/base.js',
+ 'YWt1qdbe8SAfkoPHW5d', 'RrRjWQOJmBiP',
+ ),
+ (
+ 'https://www.youtube.com/s/player/9c6dfc4a/player_ias.vflset/en_US/base.js',
+ 'jbu7ylIosQHyJyJV', 'uwI0ESiynAmhNg',
+ ),
+ (
+ 'https://www.youtube.com/s/player/f6e09c70/player_ias.vflset/en_US/base.js',
+ 'W9HJZKktxuYoDTqW', 'jHbbkcaxm54',
+ ),
+ (
+ 'https://www.youtube.com/s/player/f6e09c70/player_ias_tce.vflset/en_US/base.js',
+ 'W9HJZKktxuYoDTqW', 'jHbbkcaxm54',
+ ),
+ (
+ 'https://www.youtube.com/s/player/e7567ecf/player_ias_tce.vflset/en_US/base.js',
+ 'Sy4aDGc0VpYRR9ew_', '5UPOT1VhoZxNLQ',
+ ),
+ (
+ 'https://www.youtube.com/s/player/d50f54ef/player_ias_tce.vflset/en_US/base.js',
+ 'Ha7507LzRmH3Utygtj', 'XFTb2HoeOE5MHg',
+ ),
+ (
+ 'https://www.youtube.com/s/player/074a8365/player_ias_tce.vflset/en_US/base.js',
+ 'Ha7507LzRmH3Utygtj', 'ufTsrE0IVYrkl8v',
+ ),
+ (
+ 'https://www.youtube.com/s/player/643afba4/player_ias.vflset/en_US/base.js',
+ 'N5uAlLqm0eg1GyHO', 'dCBQOejdq5s-ww',
+ ),
+ (
+ 'https://www.youtube.com/s/player/69f581a5/tv-player-ias.vflset/tv-player-ias.js',
+ '-qIP447rVlTTwaZjY', 'KNcGOksBAvwqQg',
+ ),
+ (
+ 'https://www.youtube.com/s/player/643afba4/tv-player-ias.vflset/tv-player-ias.js',
+ 'ir9-V6cdbCiyKxhr', '2PL7ZDYAALMfmA',
+ ),
+ (
+ 'https://www.youtube.com/s/player/643afba4/player_ias.vflset/en_US/base.js',
+ 'ir9-V6cdbCiyKxhr', '2PL7ZDYAALMfmA',
+ ),
+ (
+ 'https://www.youtube.com/s/player/363db69b/player_ias.vflset/en_US/base.js',
+ 'eWYu5d5YeY_4LyEDc', 'XJQqf-N7Xra3gg',
+ ),
+ (
+ 'https://www.youtube.com/s/player/4fcd6e4a/player_ias.vflset/en_US/base.js',
+ 'o_L251jm8yhZkWtBW', 'lXoxI3XvToqn6A',
+ ),
+ (
+ 'https://www.youtube.com/s/player/4fcd6e4a/tv-player-ias.vflset/tv-player-ias.js',
+ 'o_L251jm8yhZkWtBW', 'lXoxI3XvToqn6A',
+ ),
+ (
+ 'https://www.youtube.com/s/player/20830619/tv-player-ias.vflset/tv-player-ias.js',
+ 'ir9-V6cdbCiyKxhr', '9YE85kNjZiS4',
+ ),
+ (
+ 'https://www.youtube.com/s/player/20830619/player-plasma-ias-phone-en_US.vflset/base.js',
+ 'ir9-V6cdbCiyKxhr', '9YE85kNjZiS4',
+ ),
+ (
+ 'https://www.youtube.com/s/player/20830619/player-plasma-ias-tablet-en_US.vflset/base.js',
+ 'ir9-V6cdbCiyKxhr', '9YE85kNjZiS4',
+ ),
+ (
+ 'https://www.youtube.com/s/player/8a8ac953/player_ias_tce.vflset/en_US/base.js',
+ 'MiBYeXx_vRREbiCCmh', 'RtZYMVvmkE0JE',
+ ),
+ (
+ 'https://www.youtube.com/s/player/8a8ac953/tv-player-es6.vflset/tv-player-es6.js',
+ 'MiBYeXx_vRREbiCCmh', 'RtZYMVvmkE0JE',
+ ),
+ (
+ 'https://www.youtube.com/s/player/aa3fc80b/player_ias.vflset/en_US/base.js',
+ '0qY9dal2uzOnOGwa-48hha', 'VSh1KDfQMk-eag',
+ ),
]
+class TestPlayerInfo(unittest.TestCase):
+ def test_youtube_extract_player_info(self):
+ PLAYER_URLS = (
+ ('https://www.youtube.com/s/player/4c3f79c5/player_ias.vflset/en_US/base.js', '4c3f79c5'),
+ ('https://www.youtube.com/s/player/64dddad9/player_ias.vflset/en_US/base.js', '64dddad9'),
+ ('https://www.youtube.com/s/player/64dddad9/player_ias.vflset/fr_FR/base.js', '64dddad9'),
+ ('https://www.youtube.com/s/player/64dddad9/player-plasma-ias-phone-en_US.vflset/base.js', '64dddad9'),
+ ('https://www.youtube.com/s/player/64dddad9/player-plasma-ias-phone-de_DE.vflset/base.js', '64dddad9'),
+ ('https://www.youtube.com/s/player/64dddad9/player-plasma-ias-tablet-en_US.vflset/base.js', '64dddad9'),
+ ('https://www.youtube.com/s/player/e7567ecf/player_ias_tce.vflset/en_US/base.js', 'e7567ecf'),
+ ('https://www.youtube.com/s/player/643afba4/tv-player-ias.vflset/tv-player-ias.js', '643afba4'),
+ # obsolete
+ ('https://www.youtube.com/yts/jsbin/player_ias-vfle4-e03/en_US/base.js', 'vfle4-e03'),
+ ('https://www.youtube.com/yts/jsbin/player_ias-vfl49f_g4/en_US/base.js', 'vfl49f_g4'),
+ ('https://www.youtube.com/yts/jsbin/player_ias-vflCPQUIL/en_US/base.js', 'vflCPQUIL'),
+ ('https://www.youtube.com/yts/jsbin/player-vflzQZbt7/en_US/base.js', 'vflzQZbt7'),
+ ('https://www.youtube.com/yts/jsbin/player-en_US-vflaxXRn1/base.js', 'vflaxXRn1'),
+ ('https://s.ytimg.com/yts/jsbin/html5player-en_US-vflXGBaUN.js', 'vflXGBaUN'),
+ ('https://s.ytimg.com/yts/jsbin/html5player-en_US-vflKjOTVq/html5player.js', 'vflKjOTVq'),
+ )
+ ie = YoutubeIE(FakeYDL({'cachedir': False}))
+ for player_url, expected_player_id in PLAYER_URLS:
+ player_id = ie._extract_player_info(player_url)
+ self.assertEqual(player_id, expected_player_id)
+
+
class TestSignature(unittest.TestCase):
def setUp(self):
TEST_DIR = os.path.dirname(os.path.abspath(__file__))
- self.TESTDATA_DIR = os.path.join(TEST_DIR, 'testdata')
+ self.TESTDATA_DIR = os.path.join(TEST_DIR, 'testdata/sigs')
if not os.path.exists(self.TESTDATA_DIR):
os.mkdir(self.TESTDATA_DIR)
+ def tearDown(self):
+ with compat_contextlib_suppress(OSError):
+ for f in os.listdir(self.TESTDATA_DIR):
+ os.remove(f)
-def make_tfunc(url, stype, sig_input, expected_sig):
- m = re.match(r'.*-([a-zA-Z0-9_-]+)(?:/watch_as3|/html5player)?\.[a-z]+$', url)
- assert m, '%r should follow URL format' % url
- test_id = m.group(1)
- def test_func(self):
- basename = 'player-%s.%s' % (test_id, stype)
- fn = os.path.join(self.TESTDATA_DIR, basename)
+def t_factory(name, sig_func, url_pattern):
+ def make_tfunc(url, sig_input, expected_sig):
+ m = url_pattern.match(url)
+ assert m, '{0!r} should follow URL format'.format(url)
+ test_id = re.sub(r'[/.-]', '_', m.group('id') or m.group('compat_id'))
- if not os.path.exists(fn):
- compat_urlretrieve(url, fn)
+ def test_func(self):
+ basename = 'player-{0}.js'.format(test_id)
+ fn = os.path.join(self.TESTDATA_DIR, basename)
- ydl = FakeYDL()
- ie = YoutubeIE(ydl)
- if stype == 'js':
- with io.open(fn, encoding='utf-8') as testf:
+ if not os.path.exists(fn):
+ compat_urlretrieve(url, fn)
+ with open(fn, encoding='utf-8') as testf:
jscode = testf.read()
- func = ie._parse_sig_js(jscode)
- else:
- assert stype == 'swf'
- with open(fn, 'rb') as testf:
- swfcode = testf.read()
- func = ie._parse_sig_swf(swfcode)
- src_sig = (
- compat_str(string.printable[:sig_input])
- if isinstance(sig_input, int) else sig_input)
- got_sig = func(src_sig)
- self.assertEqual(got_sig, expected_sig)
-
- test_func.__name__ = str('test_signature_' + stype + '_' + test_id)
- setattr(TestSignature, test_func.__name__, test_func)
-
-
-for test_spec in _TESTS:
- make_tfunc(*test_spec)
+ self.assertEqual(sig_func(jscode, sig_input), expected_sig)
+
+ test_func.__name__ = str('test_{0}_js_{1}'.format(name, test_id))
+ setattr(TestSignature, test_func.__name__, test_func)
+ return make_tfunc
+
+
+def signature(jscode, sig_input):
+ func = YoutubeIE(FakeYDL({'cachedir': False}))._parse_sig_js(jscode)
+ src_sig = (
+ compat_str(string.printable[:sig_input])
+ if isinstance(sig_input, int) else sig_input)
+ return func(src_sig)
+
+
+def n_sig(jscode, sig_input):
+ ie = YoutubeIE(FakeYDL({'cachedir': False}))
+ jsi = JSInterpreter(jscode)
+ jsi, _, func_code = ie._extract_n_function_code_jsi(sig_input, jsi)
+ return ie._extract_n_function_from_code(jsi, func_code)(sig_input)
+
+
+make_sig_test = t_factory(
+ 'signature', signature,
+ re.compile(r'''(?x)
+ .+/(?P<h5>html5)?player(?(h5)(?:-en_US)?-|/)(?P<id>[a-zA-Z0-9/._-]+)
+ (?(h5)/(?:watch_as3|html5player))?\.js$
+ '''))
+for test_spec in _SIG_TESTS:
+ make_sig_test(*test_spec)
+
+make_nsig_test = t_factory(
+ 'nsig', n_sig, re.compile(r'.+/player/(?P<id>[a-zA-Z0-9_/.-]+)\.js$'))
+for test_spec in _NSIG_TESTS:
+ make_nsig_test(*test_spec)
if __name__ == '__main__':
diff --git a/test/testdata/cookies/httponly_cookies.txt b/test/testdata/cookies/httponly_cookies.txt
new file mode 100644
index 000000000..c46541d6b
--- /dev/null
+++ b/test/testdata/cookies/httponly_cookies.txt
@@ -0,0 +1,6 @@
+# Netscape HTTP Cookie File
+# http://curl.haxx.se/rfc/cookie_spec.html
+# This is a generated file! Do not edit.
+
+#HttpOnly_www.foobar.foobar FALSE / TRUE 2147483647 HTTPONLY_COOKIE HTTPONLY_COOKIE_VALUE
+www.foobar.foobar FALSE / TRUE 2147483647 JS_ACCESSIBLE_COOKIE JS_ACCESSIBLE_COOKIE_VALUE
diff --git a/test/testdata/cookies/malformed_cookies.txt b/test/testdata/cookies/malformed_cookies.txt
new file mode 100644
index 000000000..17bc40354
--- /dev/null
+++ b/test/testdata/cookies/malformed_cookies.txt
@@ -0,0 +1,9 @@
+# Netscape HTTP Cookie File
+# http://curl.haxx.se/rfc/cookie_spec.html
+# This is a generated file! Do not edit.
+
+# Cookie file entry with invalid number of fields - 6 instead of 7
+www.foobar.foobar FALSE / FALSE 0 COOKIE
+
+# Cookie file entry with invalid expires at
+www.foobar.foobar FALSE / FALSE 1.7976931348623157e+308 COOKIE VALUE
diff --git a/test/testdata/cookies/session_cookies.txt b/test/testdata/cookies/session_cookies.txt
new file mode 100644
index 000000000..f6996f031
--- /dev/null
+++ b/test/testdata/cookies/session_cookies.txt
@@ -0,0 +1,6 @@
+# Netscape HTTP Cookie File
+# http://curl.haxx.se/rfc/cookie_spec.html
+# This is a generated file! Do not edit.
+
+www.foobar.foobar FALSE / TRUE YoutubeDLExpiresEmpty YoutubeDLExpiresEmptyValue
+www.foobar.foobar FALSE / TRUE 0 YoutubeDLExpires0 YoutubeDLExpires0Value
diff --git a/test/testdata/f4m/custom_base_url.f4m b/test/testdata/f4m/custom_base_url.f4m
new file mode 100644
index 000000000..74e1539e8
--- /dev/null
+++ b/test/testdata/f4m/custom_base_url.f4m
@@ -0,0 +1,10 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<manifest xmlns="http://ns.adobe.com/f4m/1.0">
+ <streamType>recorded</streamType>
+ <baseURL>http://vod.livestream.com/events/0000000000673980/</baseURL>
+ <duration>269.293</duration>
+ <bootstrapInfo profile="named" id="bootstrap_1">AAAAm2Fic3QAAAAAAAAAAQAAAAPoAAAAAAAEG+0AAAAAAAAAAAAAAAAAAQAAABlhc3J0AAAAAAAAAAABAAAAAQAAAC4BAAAAVmFmcnQAAAAAAAAD6AAAAAAEAAAAAQAAAAAAAAAAAAAXcAAAAC0AAAAAAAQHQAAAE5UAAAAuAAAAAAAEGtUAAAEYAAAAAAAAAAAAAAAAAAAAAAA=</bootstrapInfo>
+ <media url="b90f532f-b0f6-4f4e-8289-706d490b2fd8_2292" bootstrapInfoId="bootstrap_1" bitrate="2148" width="1280" height="720" videoCodec="avc1.4d401f" audioCodec="mp4a.40.2">
+ <metadata>AgAKb25NZXRhRGF0YQgAAAAIAAhkdXJhdGlvbgBAcNSwIMSbpgAFd2lkdGgAQJQAAAAAAAAABmhlaWdodABAhoAAAAAAAAAJZnJhbWVyYXRlAEA4/7DoLwW3AA12aWRlb2RhdGFyYXRlAECe1DLgjcobAAx2aWRlb2NvZGVjaWQAQBwAAAAAAAAADWF1ZGlvZGF0YXJhdGUAQGSimlvaPKQADGF1ZGlvY29kZWNpZABAJAAAAAAAAAAACQ==</metadata>
+ </media>
+</manifest>
diff --git a/test/testdata/m3u8/pluzz_francetv_11507.m3u8 b/test/testdata/m3u8/pluzz_francetv_11507.m3u8
new file mode 100644
index 000000000..0809f5aa0
--- /dev/null
+++ b/test/testdata/m3u8/pluzz_francetv_11507.m3u8
@@ -0,0 +1,14 @@
+#EXTM3U
+ #EXT-X-VERSION:5
+ #EXT-X-MEDIA:TYPE=SUBTITLES,GROUP-ID="subs",NAME="Francais",DEFAULT=NO,FORCED=NO,URI="http://replayftv-pmd.francetv.fr/subtitles/2017/16/156589847-1492488987.m3u8",LANGUAGE="fra"
+ #EXT-X-MEDIA:TYPE=AUDIO,GROUP-ID="aac",LANGUAGE="fra",NAME="Francais",DEFAULT=YES, AUTOSELECT=YES
+#EXT-X-STREAM-INF:SUBTITLES="subs",AUDIO="aac",PROGRAM-ID=1,BANDWIDTH=180000,RESOLUTION=256x144,CODECS="avc1.66.30, mp4a.40.2"
+http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/index_0_av.m3u8?null=0
+#EXT-X-STREAM-INF:SUBTITLES="subs",AUDIO="aac",PROGRAM-ID=1,BANDWIDTH=303000,RESOLUTION=320x180,CODECS="avc1.66.30, mp4a.40.2"
+http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/index_1_av.m3u8?null=0
+#EXT-X-STREAM-INF:SUBTITLES="subs",AUDIO="aac",PROGRAM-ID=1,BANDWIDTH=575000,RESOLUTION=512x288,CODECS="avc1.66.30, mp4a.40.2"
+http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/index_2_av.m3u8?null=0
+#EXT-X-STREAM-INF:SUBTITLES="subs",AUDIO="aac",PROGRAM-ID=1,BANDWIDTH=831000,RESOLUTION=704x396,CODECS="avc1.77.30, mp4a.40.2"
+http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/index_3_av.m3u8?null=0
+#EXT-X-STREAM-INF:SUBTITLES="subs",AUDIO="aac",PROGRAM-ID=1,BANDWIDTH=1467000,RESOLUTION=1024x576,CODECS="avc1.77.30, mp4a.40.2"
+http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/index_4_av.m3u8?null=0
diff --git a/test/testdata/m3u8/teamcoco_11995.m3u8 b/test/testdata/m3u8/teamcoco_11995.m3u8
new file mode 100644
index 000000000..a6e421697
--- /dev/null
+++ b/test/testdata/m3u8/teamcoco_11995.m3u8
@@ -0,0 +1,16 @@
+#EXTM3U
+#EXT-X-MEDIA:TYPE=AUDIO,GROUP-ID="audio-0",NAME="Default",AUTOSELECT=YES,DEFAULT=YES,URI="hls/CONAN_020217_Highlight_show-audio-160k_v4.m3u8"
+#EXT-X-MEDIA:TYPE=AUDIO,GROUP-ID="audio-1",NAME="Default",AUTOSELECT=YES,DEFAULT=YES,URI="hls/CONAN_020217_Highlight_show-audio-64k_v4.m3u8"
+#EXT-X-I-FRAME-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=37862000,CODECS="avc1.4d001f",URI="hls/CONAN_020217_Highlight_show-2m_iframe.m3u8"
+#EXT-X-I-FRAME-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=18750000,CODECS="avc1.4d001e",URI="hls/CONAN_020217_Highlight_show-1m_iframe.m3u8"
+#EXT-X-I-FRAME-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=6535000,CODECS="avc1.42001e",URI="hls/CONAN_020217_Highlight_show-400k_iframe.m3u8"
+#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=2374000,RESOLUTION=1024x576,CODECS="avc1.4d001f,mp4a.40.2",AUDIO="audio-0"
+hls/CONAN_020217_Highlight_show-2m_v4.m3u8
+#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=1205000,RESOLUTION=640x360,CODECS="avc1.4d001e,mp4a.40.2",AUDIO="audio-0"
+hls/CONAN_020217_Highlight_show-1m_v4.m3u8
+#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=522000,RESOLUTION=400x224,CODECS="avc1.42001e,mp4a.40.2",AUDIO="audio-0"
+hls/CONAN_020217_Highlight_show-400k_v4.m3u8
+#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=413000,RESOLUTION=400x224,CODECS="avc1.42001e,mp4a.40.5",AUDIO="audio-1"
+hls/CONAN_020217_Highlight_show-400k_v4.m3u8
+#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=71000,CODECS="mp4a.40.5",AUDIO="audio-1"
+hls/CONAN_020217_Highlight_show-audio-64k_v4.m3u8
diff --git a/test/testdata/m3u8/ted_18923.m3u8 b/test/testdata/m3u8/ted_18923.m3u8
new file mode 100644
index 000000000..52a27118b
--- /dev/null
+++ b/test/testdata/m3u8/ted_18923.m3u8
@@ -0,0 +1,28 @@
+#EXTM3U
+#EXT-X-VERSION:4
+#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=1255659,PROGRAM-ID=1,CODECS="avc1.42c01e,mp4a.40.2",RESOLUTION=640x360
+/videos/BorisHesser_2018S/video/600k.m3u8?nobumpers=true&uniqueId=76011e2b
+#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=163154,PROGRAM-ID=1,CODECS="avc1.42c00c,mp4a.40.2",RESOLUTION=320x180
+/videos/BorisHesser_2018S/video/64k.m3u8?nobumpers=true&uniqueId=76011e2b
+#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=481701,PROGRAM-ID=1,CODECS="avc1.42c015,mp4a.40.2",RESOLUTION=512x288
+/videos/BorisHesser_2018S/video/180k.m3u8?nobumpers=true&uniqueId=76011e2b
+#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=769968,PROGRAM-ID=1,CODECS="avc1.42c015,mp4a.40.2",RESOLUTION=512x288
+/videos/BorisHesser_2018S/video/320k.m3u8?nobumpers=true&uniqueId=76011e2b
+#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=984037,PROGRAM-ID=1,CODECS="avc1.42c015,mp4a.40.2",RESOLUTION=512x288
+/videos/BorisHesser_2018S/video/450k.m3u8?nobumpers=true&uniqueId=76011e2b
+#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=1693925,PROGRAM-ID=1,CODECS="avc1.4d401f,mp4a.40.2",RESOLUTION=853x480
+/videos/BorisHesser_2018S/video/950k.m3u8?nobumpers=true&uniqueId=76011e2b
+#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=2462469,PROGRAM-ID=1,CODECS="avc1.640028,mp4a.40.2",RESOLUTION=1280x720
+/videos/BorisHesser_2018S/video/1500k.m3u8?nobumpers=true&uniqueId=76011e2b
+#EXT-X-STREAM-INF:AUDIO="600k",BANDWIDTH=68101,PROGRAM-ID=1,CODECS="mp4a.40.2",DEFAULT=YES
+/videos/BorisHesser_2018S/audio/600k.m3u8?nobumpers=true&uniqueId=76011e2b
+
+#EXT-X-I-FRAME-STREAM-INF:BANDWIDTH=74298,PROGRAM-ID=1,CODECS="avc1.42c00c",RESOLUTION=320x180,URI="/videos/BorisHesser_2018S/video/64k_iframe.m3u8?nobumpers=true&uniqueId=76011e2b"
+#EXT-X-I-FRAME-STREAM-INF:BANDWIDTH=216200,PROGRAM-ID=1,CODECS="avc1.42c015",RESOLUTION=512x288,URI="/videos/BorisHesser_2018S/video/180k_iframe.m3u8?nobumpers=true&uniqueId=76011e2b"
+#EXT-X-I-FRAME-STREAM-INF:BANDWIDTH=304717,PROGRAM-ID=1,CODECS="avc1.42c015",RESOLUTION=512x288,URI="/videos/BorisHesser_2018S/video/320k_iframe.m3u8?nobumpers=true&uniqueId=76011e2b"
+#EXT-X-I-FRAME-STREAM-INF:BANDWIDTH=350933,PROGRAM-ID=1,CODECS="avc1.42c015",RESOLUTION=512x288,URI="/videos/BorisHesser_2018S/video/450k_iframe.m3u8?nobumpers=true&uniqueId=76011e2b"
+#EXT-X-I-FRAME-STREAM-INF:BANDWIDTH=495850,PROGRAM-ID=1,CODECS="avc1.42c01e",RESOLUTION=640x360,URI="/videos/BorisHesser_2018S/video/600k_iframe.m3u8?nobumpers=true&uniqueId=76011e2b"
+#EXT-X-I-FRAME-STREAM-INF:BANDWIDTH=810750,PROGRAM-ID=1,CODECS="avc1.4d401f",RESOLUTION=853x480,URI="/videos/BorisHesser_2018S/video/950k_iframe.m3u8?nobumpers=true&uniqueId=76011e2b"
+#EXT-X-I-FRAME-STREAM-INF:BANDWIDTH=1273700,PROGRAM-ID=1,CODECS="avc1.640028",RESOLUTION=1280x720,URI="/videos/BorisHesser_2018S/video/1500k_iframe.m3u8?nobumpers=true&uniqueId=76011e2b"
+
+#EXT-X-MEDIA:TYPE=AUDIO,GROUP-ID="600k",LANGUAGE="en",NAME="Audio",AUTOSELECT=YES,DEFAULT=YES,URI="/videos/BorisHesser_2018S/audio/600k.m3u8?nobumpers=true&uniqueId=76011e2b",BANDWIDTH=614400
diff --git a/test/testdata/m3u8/toggle_mobile_12211.m3u8 b/test/testdata/m3u8/toggle_mobile_12211.m3u8
new file mode 100644
index 000000000..69604e683
--- /dev/null
+++ b/test/testdata/m3u8/toggle_mobile_12211.m3u8
@@ -0,0 +1,13 @@
+#EXTM3U
+#EXT-X-VERSION:4
+#EXT-X-MEDIA:TYPE=AUDIO,GROUP-ID="audio",LANGUAGE="eng",NAME="English",URI="http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/2/pv/1/flavorId/0_sa2ntrdg/name/a.mp4/index.m3u8"
+#EXT-X-MEDIA:TYPE=AUDIO,GROUP-ID="audio",LANGUAGE="und",NAME="Undefined",URI="http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/2/pv/1/flavorId/0_r7y0nitg/name/a.mp4/index.m3u8"
+
+#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=155648,RESOLUTION=320x180,AUDIO="audio"
+http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/2/pv/1/flavorId/0_qlk9hlzr/name/a.mp4/index.m3u8
+#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=502784,RESOLUTION=480x270,AUDIO="audio"
+http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/2/pv/1/flavorId/0_oefackmi/name/a.mp4/index.m3u8
+#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=827392,RESOLUTION=640x360,AUDIO="audio"
+http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/12/pv/1/flavorId/0_vyg9pj7k/name/a.mp4/index.m3u8
+#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=1396736,RESOLUTION=854x480,AUDIO="audio"
+http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/12/pv/1/flavorId/0_50n4psvx/name/a.mp4/index.m3u8
diff --git a/test/testdata/m3u8/twitch_vod.m3u8 b/test/testdata/m3u8/twitch_vod.m3u8
new file mode 100644
index 000000000..7617277ca
--- /dev/null
+++ b/test/testdata/m3u8/twitch_vod.m3u8
@@ -0,0 +1,20 @@
+#EXTM3U
+#EXT-X-TWITCH-INFO:ORIGIN="s3",CLUSTER="edgecast_vod",REGION="EU",MANIFEST-CLUSTER="edgecast_vod",USER-IP="109.171.17.81"
+#EXT-X-MEDIA:TYPE=VIDEO,GROUP-ID="chunked",NAME="Source",AUTOSELECT=YES,DEFAULT=YES
+#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=3214134,CODECS="avc1.100.31,mp4a.40.2",RESOLUTION="1280x720",VIDEO="chunked"
+https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/chunked/index-muted-HM49I092CC.m3u8
+#EXT-X-MEDIA:TYPE=VIDEO,GROUP-ID="high",NAME="High",AUTOSELECT=YES,DEFAULT=YES
+#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=1603789,CODECS="avc1.42C01F,mp4a.40.2",RESOLUTION="1280x720",VIDEO="high"
+https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/high/index-muted-HM49I092CC.m3u8
+#EXT-X-MEDIA:TYPE=VIDEO,GROUP-ID="medium",NAME="Medium",AUTOSELECT=YES,DEFAULT=YES
+#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=893387,CODECS="avc1.42C01E,mp4a.40.2",RESOLUTION="852x480",VIDEO="medium"
+https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/medium/index-muted-HM49I092CC.m3u8
+#EXT-X-MEDIA:TYPE=VIDEO,GROUP-ID="low",NAME="Low",AUTOSELECT=YES,DEFAULT=YES
+#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=628347,CODECS="avc1.42C01E,mp4a.40.2",RESOLUTION="640x360",VIDEO="low"
+https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/low/index-muted-HM49I092CC.m3u8
+#EXT-X-MEDIA:TYPE=VIDEO,GROUP-ID="mobile",NAME="Mobile",AUTOSELECT=YES,DEFAULT=YES
+#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=280474,CODECS="avc1.42C00D,mp4a.40.2",RESOLUTION="400x226",VIDEO="mobile"
+https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/mobile/index-muted-HM49I092CC.m3u8
+#EXT-X-MEDIA:TYPE=VIDEO,GROUP-ID="audio_only",NAME="Audio Only",AUTOSELECT=NO,DEFAULT=NO
+#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=182725,CODECS="mp4a.40.2",VIDEO="audio_only"
+https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/audio_only/index-muted-HM49I092CC.m3u8
diff --git a/test/testdata/m3u8/vidio.m3u8 b/test/testdata/m3u8/vidio.m3u8
new file mode 100644
index 000000000..89c244469
--- /dev/null
+++ b/test/testdata/m3u8/vidio.m3u8
@@ -0,0 +1,10 @@
+#EXTM3U
+
+#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=300000,RESOLUTION=480x270,NAME="270p 3G"
+https://cdn1-a.production.vidio.static6.com/uploads/165683/dj_ambred-4383-b300.mp4.m3u8
+
+#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=600000,RESOLUTION=640x360,NAME="360p SD"
+https://cdn1-a.production.vidio.static6.com/uploads/165683/dj_ambred-4383-b600.mp4.m3u8
+
+#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=1200000,RESOLUTION=1280x720,NAME="720p HD"
+https://cdn1-a.production.vidio.static6.com/uploads/165683/dj_ambred-4383-b1200.mp4.m3u8
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 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<MPD xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="urn:mpeg:dash:schema:mpd:2011" type="static" minBufferTime="PT2S" profiles="urn:mpeg:dash:profile:isoff-on-demand:2011" mediaPresentationDuration="PT6014S">
+ <Period bitstreamSwitching="true">
+ <AdaptationSet mimeType="audio/mp4" codecs="mp4a.40.2" startWithSAP="1" segmentAlignment="true">
+ <SegmentTemplate timescale="1000000" presentationTimeOffset="0" initialization="ai_$RepresentationID$.mp4d" media="a_$RepresentationID$_$Number$.mp4d" duration="2000000.0" startNumber="0"></SegmentTemplate>
+ <Representation id="318597" bandwidth="61587"></Representation>
+ </AdaptationSet>
+ <AdaptationSet mimeType="video/mp4" startWithSAP="1" segmentAlignment="true">
+ <SegmentTemplate timescale="1000000" presentationTimeOffset="0" initialization="vi_$RepresentationID$.mp4d" media="v_$RepresentationID$_$Number$.mp4d" duration="2000000.0" startNumber="0"></SegmentTemplate>
+ <Representation id="318597" codecs="avc1.42001f" width="340" height="192" bandwidth="318597"></Representation>
+ <Representation id="638590" codecs="avc1.42001f" width="512" height="288" bandwidth="638590"></Representation>
+ <Representation id="1022565" codecs="avc1.4d001f" width="688" height="384" bandwidth="1022565"></Representation>
+ <Representation id="2046506" codecs="avc1.4d001f" width="1024" height="576" bandwidth="2046506"></Representation>
+ <Representation id="3998017" codecs="avc1.640029" width="1280" height="720" bandwidth="3998017"></Representation>
+ <Representation id="5997485" codecs="avc1.640032" width="1920" height="1080" bandwidth="5997485"></Representation>
+ </AdaptationSet>
+ </Period>
+</MPD> \ No newline at end of file
diff --git a/test/testdata/mpd/range_only.mpd b/test/testdata/mpd/range_only.mpd
new file mode 100644
index 000000000..e0c2152d1
--- /dev/null
+++ b/test/testdata/mpd/range_only.mpd
@@ -0,0 +1,35 @@
+<?xml version="1.0"?>
+<!-- MPD file Generated with GPAC version 1.0.1-revrelease at 2021-11-27T20:53:11.690Z -->
+<MPD xmlns="urn:mpeg:dash:schema:mpd:2011" minBufferTime="PT1.500S" type="static" mediaPresentationDuration="PT0H0M30.196S" maxSegmentDuration="PT0H0M10.027S" profiles="urn:mpeg:dash:profile:full:2011">
+ <ProgramInformation moreInformationURL="http://gpac.io">
+ <Title>manifest.mpd generated by GPAC</Title>
+ </ProgramInformation>
+
+ <Period duration="PT0H0M30.196S">
+ <AdaptationSet segmentAlignment="true" maxWidth="768" maxHeight="432" maxFrameRate="30000/1001" par="16:9" lang="und" startWithSAP="1">
+ <Representation id="1" mimeType="video/mp4" codecs="avc1.4D401E" width="768" height="432" frameRate="30000/1001" sar="1:1" bandwidth="526987">
+ <BaseURL>video_dashinit.mp4</BaseURL>
+ <SegmentList timescale="90000" duration="900000">
+ <Initialization range="0-881"/>
+ <SegmentURL mediaRange="882-876094" indexRange="882-925"/>
+ <SegmentURL mediaRange="876095-1466732" indexRange="876095-876138"/>
+ <SegmentURL mediaRange="1466733-1953615" indexRange="1466733-1466776"/>
+ <SegmentURL mediaRange="1953616-1994211" indexRange="1953616-1953659"/>
+ </SegmentList>
+ </Representation>
+ </AdaptationSet>
+ <AdaptationSet segmentAlignment="true" lang="und" startWithSAP="1">
+ <Representation id="2" mimeType="audio/mp4" codecs="mp4a.40.2" audioSamplingRate="48000" bandwidth="98096">
+ <AudioChannelConfiguration schemeIdUri="urn:mpeg:dash:23003:3:audio_channel_configuration:2011" value="2"/>
+ <BaseURL>audio_dashinit.mp4</BaseURL>
+ <SegmentList timescale="48000" duration="480000">
+ <Initialization range="0-752"/>
+ <SegmentURL mediaRange="753-124129" indexRange="753-796"/>
+ <SegmentURL mediaRange="124130-250544" indexRange="124130-124173"/>
+ <SegmentURL mediaRange="250545-374929" indexRange="250545-250588"/>
+ </SegmentList>
+ </Representation>
+ </AdaptationSet>
+ </Period>
+</MPD>
+
diff --git a/test/testdata/mpd/subtitles.mpd b/test/testdata/mpd/subtitles.mpd
new file mode 100644
index 000000000..6f948adba
--- /dev/null
+++ b/test/testdata/mpd/subtitles.mpd
@@ -0,0 +1,351 @@
+<?xml version="1.0" encoding="utf-8"?>
+<!-- Created with Unified Streaming Platform (version=1.10.18-20255) -->
+<MPD
+ xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+ xmlns="urn:mpeg:dash:schema:mpd:2011"
+ xsi:schemaLocation="urn:mpeg:dash:schema:mpd:2011 http://standards.iso.org/ittf/PubliclyAvailableStandards/MPEG-DASH_schema_files/DASH-MPD.xsd"
+ type="static"
+ mediaPresentationDuration="PT14M48S"
+ maxSegmentDuration="PT1M"
+ minBufferTime="PT10S"
+ profiles="urn:mpeg:dash:profile:isoff-live:2011">
+ <Period
+ id="1"
+ duration="PT14M48S">
+ <BaseURL>dash/</BaseURL>
+ <AdaptationSet
+ id="1"
+ group="1"
+ contentType="audio"
+ segmentAlignment="true"
+ audioSamplingRate="48000"
+ mimeType="audio/mp4"
+ codecs="mp4a.40.2"
+ startWithSAP="1">
+ <AudioChannelConfiguration
+ schemeIdUri="urn:mpeg:dash:23003:3:audio_channel_configuration:2011"
+ value="2" />
+ <Role schemeIdUri="urn:mpeg:dash:role:2011" value="main" />
+ <SegmentTemplate
+ timescale="48000"
+ initialization="3144-kZT4LWMQw6Rh7Kpd-$RepresentationID$.dash"
+ media="3144-kZT4LWMQw6Rh7Kpd-$RepresentationID$-$Time$.dash">
+ <SegmentTimeline>
+ <S t="0" d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="96256" r="2" />
+ <S d="95232" />
+ <S d="3584" />
+ </SegmentTimeline>
+ </SegmentTemplate>
+ <Representation
+ id="audio=128001"
+ bandwidth="128001">
+ </Representation>
+ </AdaptationSet>
+ <AdaptationSet
+ id="2"
+ group="3"
+ contentType="text"
+ lang="en"
+ mimeType="application/mp4"
+ codecs="stpp"
+ startWithSAP="1">
+ <Role schemeIdUri="urn:mpeg:dash:role:2011" value="subtitle" />
+ <SegmentTemplate
+ timescale="1000"
+ initialization="3144-kZT4LWMQw6Rh7Kpd-$RepresentationID$.dash"
+ media="3144-kZT4LWMQw6Rh7Kpd-$RepresentationID$-$Time$.dash">
+ <SegmentTimeline>
+ <S t="0" d="60000" r="9" />
+ <S d="24000" />
+ </SegmentTimeline>
+ </SegmentTemplate>
+ <Representation
+ id="textstream_eng=1000"
+ bandwidth="1000">
+ </Representation>
+ </AdaptationSet>
+ <AdaptationSet
+ id="3"
+ group="2"
+ contentType="video"
+ par="960:409"
+ minBandwidth="100000"
+ maxBandwidth="4482000"
+ maxWidth="1689"
+ maxHeight="720"
+ segmentAlignment="true"
+ mimeType="video/mp4"
+ codecs="avc1.4D401F"
+ startWithSAP="1">
+ <Role schemeIdUri="urn:mpeg:dash:role:2011" value="main" />
+ <SegmentTemplate
+ timescale="12288"
+ initialization="3144-kZT4LWMQw6Rh7Kpd-$RepresentationID$.dash"
+ media="3144-kZT4LWMQw6Rh7Kpd-$RepresentationID$-$Time$.dash">
+ <SegmentTimeline>
+ <S t="0" d="24576" r="443" />
+ </SegmentTimeline>
+ </SegmentTemplate>
+ <Representation
+ id="video=100000"
+ bandwidth="100000"
+ width="336"
+ height="144"
+ sar="2880:2863"
+ scanType="progressive">
+ </Representation>
+ <Representation
+ id="video=326000"
+ bandwidth="326000"
+ width="562"
+ height="240"
+ sar="115200:114929"
+ scanType="progressive">
+ </Representation>
+ <Representation
+ id="video=698000"
+ bandwidth="698000"
+ width="844"
+ height="360"
+ sar="86400:86299"
+ scanType="progressive">
+ </Representation>
+ <Representation
+ id="video=1493000"
+ bandwidth="1493000"
+ width="1126"
+ height="480"
+ sar="230400:230267"
+ scanType="progressive">
+ </Representation>
+ <Representation
+ id="video=4482000"
+ bandwidth="4482000"
+ width="1688"
+ height="720"
+ sar="86400:86299"
+ scanType="progressive">
+ </Representation>
+ </AdaptationSet>
+ </Period>
+</MPD>
diff --git a/test/testdata/mpd/unfragmented.mpd b/test/testdata/mpd/unfragmented.mpd
new file mode 100644
index 000000000..5a3720be7
--- /dev/null
+++ b/test/testdata/mpd/unfragmented.mpd
@@ -0,0 +1,28 @@
+<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<MPD mediaPresentationDuration="PT54.915S" minBufferTime="PT1.500S" profiles="urn:mpeg:dash:profile:isoff-on-demand:2011" type="static" xmlns="urn:mpeg:dash:schema:mpd:2011">
+ <Period duration="PT54.915S">
+ <AdaptationSet segmentAlignment="true" subsegmentAlignment="true" subsegmentStartsWithSAP="1">
+ <Representation bandwidth="804261" codecs="avc1.4d401e" frameRate="30" height="360" id="VIDEO-1" mimeType="video/mp4" startWithSAP="1" width="360">
+ <BaseURL>DASH_360</BaseURL>
+ <SegmentBase indexRange="915-1114" indexRangeExact="true">
+ <Initialization range="0-914"/>
+ </SegmentBase>
+ </Representation>
+ <Representation bandwidth="608000" codecs="avc1.4d401e" frameRate="30" height="240" id="VIDEO-2" mimeType="video/mp4" startWithSAP="1" width="240">
+ <BaseURL>DASH_240</BaseURL>
+ <SegmentBase indexRange="913-1112" indexRangeExact="true">
+ <Initialization range="0-912"/>
+ </SegmentBase>
+ </Representation>
+ </AdaptationSet>
+ <AdaptationSet>
+ <Representation audioSamplingRate="48000" bandwidth="129870" codecs="mp4a.40.2" id="AUDIO-1" mimeType="audio/mp4" startWithSAP="1">
+ <AudioChannelConfiguration schemeIdUri="urn:mpeg:dash:23003:3:audio_channel_configuration:2011" value="2"/>
+ <BaseURL>audio</BaseURL>
+ <SegmentBase indexRange="832-1007" indexRangeExact="true">
+ <Initialization range="0-831"/>
+ </SegmentBase>
+ </Representation>
+ </AdaptationSet>
+ </Period>
+</MPD>
diff --git a/test/testdata/mpd/url_and_range.mpd b/test/testdata/mpd/url_and_range.mpd
new file mode 100644
index 000000000..b8c68aad2
--- /dev/null
+++ b/test/testdata/mpd/url_and_range.mpd
@@ -0,0 +1,32 @@
+<?xml version="1.0" ?>
+<MPD xmlns="urn:mpeg:dash:schema:mpd:2011" profiles="urn:mpeg:dash:profile:isoff-live:2011" minBufferTime="PT10.01S" mediaPresentationDuration="PT30.097S" type="static">
+ <!-- Created with Bento4 mp4-dash.py, VERSION=2.0.0-639 -->
+ <Period>
+ <!-- Video -->
+ <AdaptationSet mimeType="video/mp4" segmentAlignment="true" startWithSAP="1" maxWidth="768" maxHeight="432">
+ <Representation id="video-avc1" codecs="avc1.4D401E" width="768" height="432" scanType="progressive" frameRate="30000/1001" bandwidth="699597">
+ <SegmentList timescale="1000" duration="10010">
+ <Initialization sourceURL="video-frag.mp4" range="36-746"/>
+ <SegmentURL media="video-frag.mp4" mediaRange="747-876117"/>
+ <SegmentURL media="video-frag.mp4" mediaRange="876118-1466913"/>
+ <SegmentURL media="video-frag.mp4" mediaRange="1466914-1953954"/>
+ <SegmentURL media="video-frag.mp4" mediaRange="1953955-1994652"/>
+ </SegmentList>
+ </Representation>
+ </AdaptationSet>
+ <!-- Audio -->
+ <AdaptationSet mimeType="audio/mp4" startWithSAP="1" segmentAlignment="true">
+ <Representation id="audio-und-mp4a.40.2" codecs="mp4a.40.2" bandwidth="98808" audioSamplingRate="48000">
+ <AudioChannelConfiguration schemeIdUri="urn:mpeg:mpegB:cicp:ChannelConfiguration" value="2"/>
+ <SegmentList timescale="1000" duration="10010">
+ <Initialization sourceURL="audio-frag.mp4" range="32-623"/>
+ <SegmentURL media="audio-frag.mp4" mediaRange="624-124199"/>
+ <SegmentURL media="audio-frag.mp4" mediaRange="124200-250303"/>
+ <SegmentURL media="audio-frag.mp4" mediaRange="250304-374365"/>
+ <SegmentURL media="audio-frag.mp4" mediaRange="374366-374836"/>
+ </SegmentList>
+ </Representation>
+ </AdaptationSet>
+ </Period>
+</MPD>
+
diff --git a/test/testdata/mpd/urls_only.mpd b/test/testdata/mpd/urls_only.mpd
new file mode 100644
index 000000000..2b9d595d3
--- /dev/null
+++ b/test/testdata/mpd/urls_only.mpd
@@ -0,0 +1,218 @@
+<?xml version="1.0" ?>
+<MPD maxSegmentDuration="PT0H0M10.000S" mediaPresentationDuration="PT0H4M1.728S" minBufferTime="PT1.500S" profiles="urn:mpeg:dash:profile:isoff-main:2011" type="static" xmlns="urn:mpeg:dash:schema:mpd:2011">
+ <Period duration="PT0H4M1.728S">
+ <AdaptationSet bitstreamSwitching="true" lang="und" maxHeight="1080" maxWidth="1920" par="16:9" segmentAlignment="true">
+ <ContentComponent contentType="video" id="1"/>
+ <Representation audioSamplingRate="44100" bandwidth="200000" codecs="avc3.42c01e,mp4a.40.2" frameRate="25" height="144" id="h264_aac_144p_m4s" mimeType="video/mp4" sar="1:1" startWithSAP="1" width="256">
+ <SegmentList duration="10000" timescale="1000">
+ <Initialization sourceURL="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/init/432f65a0.mp4"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/0/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/1/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/2/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/3/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/4/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/5/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/6/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/7/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/8/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/9/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/10/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/11/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/12/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/13/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/14/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/15/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/16/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/17/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/18/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/19/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/20/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/21/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/22/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/23/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/24/432f65a0.m4s"/>
+ </SegmentList>
+ </Representation>
+ <Representation audioSamplingRate="44100" bandwidth="400000" codecs="avc3.42c01e,mp4a.40.2" frameRate="25" height="240" id="h264_aac_240p_m4s" mimeType="video/mp4" sar="160:159" startWithSAP="1" width="424">
+ <SegmentList duration="10000" timescale="1000">
+ <Initialization sourceURL="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/init/432f65a0.mp4"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/0/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/1/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/2/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/3/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/4/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/5/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/6/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/7/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/8/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/9/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/10/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/11/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/12/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/13/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/14/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/15/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/16/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/17/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/18/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/19/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/20/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/21/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/22/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/23/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/24/432f65a0.m4s"/>
+ </SegmentList>
+ </Representation>
+ <Representation audioSamplingRate="44100" bandwidth="800000" codecs="avc3.42c01e,mp4a.40.2" frameRate="25" height="360" id="h264_aac_360p_m4s" mimeType="video/mp4" sar="1:1" startWithSAP="1" width="640">
+ <SegmentList duration="10000" timescale="1000">
+ <Initialization sourceURL="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/init/432f65a0.mp4"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/0/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/1/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/2/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/3/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/4/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/5/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/6/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/7/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/8/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/9/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/10/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/11/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/12/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/13/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/14/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/15/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/16/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/17/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/18/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/19/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/20/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/21/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/22/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/23/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/24/432f65a0.m4s"/>
+ </SegmentList>
+ </Representation>
+ <Representation audioSamplingRate="44100" bandwidth="1200000" codecs="avc3.42c01e,mp4a.40.2" frameRate="25" height="480" id="h264_aac_480p_m4s" mimeType="video/mp4" sar="320:321" startWithSAP="1" width="856">
+ <SegmentList duration="10000" timescale="1000">
+ <Initialization sourceURL="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/init/432f65a0.mp4"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/0/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/1/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/2/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/3/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/4/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/5/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/6/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/7/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/8/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/9/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/10/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/11/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/12/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/13/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/14/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/15/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/16/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/17/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/18/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/19/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/20/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/21/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/22/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/23/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/24/432f65a0.m4s"/>
+ </SegmentList>
+ </Representation>
+ <Representation audioSamplingRate="44100" bandwidth="1600000" codecs="avc3.42c01e,mp4a.40.2" frameRate="25" height="576" id="h264_aac_576p_m4s" mimeType="video/mp4" sar="1:1" startWithSAP="1" width="1024">
+ <SegmentList duration="10000" timescale="1000">
+ <Initialization sourceURL="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/init/432f65a0.mp4"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/0/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/1/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/2/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/3/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/4/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/5/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/6/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/7/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/8/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/9/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/10/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/11/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/12/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/13/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/14/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/15/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/16/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/17/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/18/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/19/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/20/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/21/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/22/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/23/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/24/432f65a0.m4s"/>
+ </SegmentList>
+ </Representation>
+ <Representation audioSamplingRate="44100" bandwidth="2400000" codecs="avc3.42c01e,mp4a.40.2" frameRate="25" height="720" id="h264_aac_720p_m4s" mimeType="video/mp4" sar="1:1" startWithSAP="1" width="1280">
+ <SegmentList duration="10000" timescale="1000">
+ <Initialization sourceURL="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/init/432f65a0.mp4"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/0/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/1/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/2/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/3/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/4/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/5/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/6/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/7/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/8/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/9/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/10/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/11/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/12/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/13/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/14/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/15/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/16/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/17/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/18/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/19/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/20/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/21/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/22/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/23/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/24/432f65a0.m4s"/>
+ </SegmentList>
+ </Representation>
+ <Representation audioSamplingRate="44100" bandwidth="4400000" codecs="avc3.42c01e,mp4a.40.2" frameRate="25" height="1080" id="h264_aac_1080p_m4s" mimeType="video/mp4" sar="1:1" startWithSAP="1" width="1920">
+ <SegmentList duration="10000" timescale="1000">
+ <Initialization sourceURL="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/init/432f65a0.mp4"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/0/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/1/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/2/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/3/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/4/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/5/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/6/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/7/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/8/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/9/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/10/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/11/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/12/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/13/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/14/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/15/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/16/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/17/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/18/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/19/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/20/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/21/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/22/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/23/432f65a0.m4s"/>
+ <SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/24/432f65a0.m4s"/>
+ </SegmentList>
+ </Representation>
+ </AdaptationSet>
+ </Period>
+</MPD>
diff --git a/test/testdata/xspf/foo_xspf.xspf b/test/testdata/xspf/foo_xspf.xspf
new file mode 100644
index 000000000..b7f0086b3
--- /dev/null
+++ b/test/testdata/xspf/foo_xspf.xspf
@@ -0,0 +1,34 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<playlist version="1" xmlns="http://xspf.org/ns/0/">
+ <date>2018-03-09T18:01:43Z</date>
+ <trackList>
+ <track>
+ <location>cd1/track%201.mp3</location>
+ <title>Pandemonium</title>
+ <creator>Foilverb</creator>
+ <annotation>Visit http://bigbrother404.bandcamp.com</annotation>
+ <album>Pandemonium EP</album>
+ <trackNum>1</trackNum>
+ <duration>202416</duration>
+ </track>
+ <track>
+ <location>../%E3%83%88%E3%83%A9%E3%83%83%E3%82%AF%E3%80%80%EF%BC%92.mp3</location>
+ <title>Final Cartridge (Nichico Twelve Remix)</title>
+ <annotation>Visit http://bigbrother404.bandcamp.com</annotation>
+ <creator>Foilverb</creator>
+ <album>Pandemonium EP</album>
+ <trackNum>2</trackNum>
+ <duration>255857</duration>
+ </track>
+ <track>
+ <location>track3.mp3</location>
+ <location>https://example.com/track3.mp3</location>
+ <title>Rebuilding Nightingale</title>
+ <annotation>Visit http://bigbrother404.bandcamp.com</annotation>
+ <creator>Foilverb</creator>
+ <album>Pandemonium EP</album>
+ <trackNum>3</trackNum>
+ <duration>287915</duration>
+ </track>
+ </trackList>
+</playlist>