release 2019.03.09

[ci skip]

.github/ISSUE_TEMPLATE.md

@@ -6,8 +6,8 @@
 
 ---
 
-### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.03.01*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
-- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.03.01**
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2019.03.09*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
+- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2019.03.09**
 
 ### Before submitting an *issue* make sure you have:
 - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
@@ -36,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl
 [debug] User config: []
 [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
 [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
-[debug] youtube-dl version 2019.03.01
+[debug] youtube-dl version 2019.03.09
 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
 [debug] Proxy map: {}

.travis.yml

@@ -9,7 +9,6 @@ python:
   - "3.6"
   - "pypy"
   - "pypy3"
-sudo: false
 env:
   - YTDL_TEST_SET=core
   - YTDL_TEST_SET=download

ChangeLog

@@ -1,3 +1,34 @@
+version 2019.03.09
+
+Core
+* [extractor/common] Use compat_etree_Element
++ [compat] Introduce compat_etree_Element
+* [extractor/common] Fallback url to base URL for DASH formats
+* [extractor/common] Do not fail on invalid data while parsing F4M manifest
+  in non fatal mode
+* [extractor/common] Return MPD manifest as format's url meta field (#20242)
+* [utils] Strip #HttpOnly_ prefix from cookies files (#20219)
+
+Extractors
+* [francetv:site] Relax video id regular expression (#20268)
+* [toutv] Detect invalid login error
+* [toutv] Fix authentication (#20261)
++ [urplay] Extract timestamp (#20235)
++ [openload] Add support for oload.space (#20246)
+* [facebook] Improve uploader extraction (#20250)
+* [bbc] Use compat_etree_Element
+* [crunchyroll] Use compat_etree_Element
+* [npo] Improve ISM extraction
+* [rai] Improve extraction (#20253)
+* [paramountnetwork] Fix mgid extraction (#20241)
+* [libsyn] Improve extraction (#20229)
++ [youtube] Add more invidious instances to URL regular expression (#20228)
+* [spankbang] Fix extraction (#20023)
+* [espn] Extend URL regular expression (#20013)
+* [sixplay] Handle videos with empty assets (#20016)
++ [vimeo] Add support for Vimeo Pro portfolio protected videos (#20070)
+
+
 version 2019.03.01
 
 Core

test/test_YoutubeDLCookieJar.py

@@ -29,6 +29,16 @@ class TestYoutubeDLCookieJar(unittest.TestCase):
             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')
+
 
 if __name__ == '__main__':
     unittest.main()

test/test_compat.py

@@ -13,6 +13,7 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 from youtube_dl.compat import (
     compat_getenv,
     compat_setenv,
+    compat_etree_Element,
     compat_etree_fromstring,
     compat_expanduser,
     compat_shlex_split,
@@ -90,6 +91,12 @@ 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">

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

youtube_dl/compat.py

@@ -2508,6 +2508,15 @@ class _TreeBuilder(etree.TreeBuilder):
         pass
 
 
+try:
+    # xml.etree.ElementTree.Element is a method in Python <=2.6 and
+    # the following will crash with:
+    #  TypeError: isinstance() arg 2 must be a class, type, or tuple of classes and types
+    isinstance(None, xml.etree.ElementTree.Element)
+    from xml.etree.ElementTree import Element as compat_etree_Element
+except TypeError:  # Python <=2.6
+    from xml.etree.ElementTree import _ElementInterface as compat_etree_Element
+
 if sys.version_info[0] >= 3:
     def compat_etree_fromstring(text):
         return etree.XML(text, parser=etree.XMLParser(target=_TreeBuilder()))
@@ -2969,6 +2978,7 @@ __all__ = [
     'compat_cookiejar',
     'compat_cookies',
     'compat_ctypes_WINFUNCTYPE',
+    'compat_etree_Element',
     'compat_etree_fromstring',
     'compat_etree_register_namespace',
     'compat_expanduser',

youtube_dl/extractor/bbc.py

@@ -3,7 +3,6 @@ from __future__ import unicode_literals
 
 import itertools
 import re
-import xml
 
 from .common import InfoExtractor
 from ..utils import (
@@ -23,6 +22,7 @@ from ..utils import (
     urljoin,
 )
 from ..compat import (
+    compat_etree_Element,
     compat_HTTPError,
     compat_urlparse,
 )
@@ -317,7 +317,7 @@ class BBCCoUkIE(InfoExtractor):
                 continue
             captions = self._download_xml(
                 cc_url, programme_id, 'Downloading captions', fatal=False)
-            if not isinstance(captions, xml.etree.ElementTree.Element):
+            if not isinstance(captions, compat_etree_Element):
                 continue
             lang = captions.get('{http://www.w3.org/XML/1998/namespace}lang', 'en')
             subtitles[lang] = [

youtube_dl/extractor/common.py

@@ -17,6 +17,7 @@ import math
 from ..compat import (
     compat_cookiejar,
     compat_cookies,
+    compat_etree_Element,
     compat_etree_fromstring,
     compat_getpass,
     compat_integer_types,
@@ -102,10 +103,23 @@ class InfoExtractor(object):
                     from worst to best quality.
 
                     Potential fields:
-                    * url        Mandatory. The URL of the video file
+                    * url        The mandatory URL representing the media:
+                                   for plain file media - HTTP URL of this file,
+                                   for RTMP - RTMP URL,
+                                   for HLS - URL of the M3U8 media playlist,
+                                   for HDS - URL of the F4M manifest,
+                                   for DASH - URL of the MPD manifest or
+                                              base URL representing the media
+                                              if MPD manifest is parsed from
+                                              a string,
+                                   for MSS - URL of the ISM manifest.
                     * manifest_url
                                  The URL of the manifest file in case of
-                                 fragmented media (DASH, hls, hds)
+                                 fragmented media:
+                                   for HLS - URL of the M3U8 master playlist,
+                                   for HDS - URL of the F4M manifest,
+                                   for DASH - URL of the MPD manifest,
+                                   for MSS - URL of the ISM manifest.
                     * ext        Will be calculated from URL if missing
                     * format     A human-readable description of the format
                                  ("mp4 container with h264/opus").
@@ -788,7 +802,7 @@ class InfoExtractor(object):
             fatal=True, encoding=None, data=None, headers={}, query={},
             expected_status=None):
         """
-        Return a tuple (xml as an xml.etree.ElementTree.Element, URL handle).
+        Return a tuple (xml as an compat_etree_Element, URL handle).
 
         See _download_webpage docstring for arguments specification.
         """
@@ -809,7 +823,7 @@ class InfoExtractor(object):
             transform_source=None, fatal=True, encoding=None,
             data=None, headers={}, query={}, expected_status=None):
         """
-        Return the xml as an xml.etree.ElementTree.Element.
+        Return the xml as an compat_etree_Element.
 
         See _download_webpage docstring for arguments specification.
         """
@@ -1454,6 +1468,9 @@ class InfoExtractor(object):
     def _parse_f4m_formats(self, manifest, manifest_url, video_id, preference=None, f4m_id=None,
                            transform_source=lambda s: fix_xml_ampersands(s).strip(),
                            fatal=True, m3u8_id=None):
+        if not isinstance(manifest, compat_etree_Element) and not fatal:
+            return []
+
         # currently youtube-dl cannot decode the playerVerificationChallenge as Akamai uses Adobe Alchemy
         akamai_pv = manifest.find('{http://ns.adobe.com/f4m/1.0}pv-2.0')
         if akamai_pv is not None and ';' in akamai_pv.text:
@@ -2120,7 +2137,8 @@ class InfoExtractor(object):
                         bandwidth = int_or_none(representation_attrib.get('bandwidth'))
                         f = {
                             'format_id': '%s-%s' % (mpd_id, representation_id) if mpd_id else representation_id,
-                            'url': base_url,
+                            # NB: mpd_url may be empty when MPD manifest is parsed from a string
+                            'url': mpd_url or base_url,
                             'manifest_url': mpd_url,
                             'ext': mimetype2ext(mime_type),
                             'width': int_or_none(representation_attrib.get('width')),

youtube_dl/extractor/crunchyroll.py

@@ -3,7 +3,6 @@ from __future__ import unicode_literals
 
 import re
 import json
-import xml.etree.ElementTree as etree
 import zlib
 
 from hashlib import sha1
@@ -12,6 +11,7 @@ from .common import InfoExtractor
 from .vrv import VRVIE
 from ..compat import (
     compat_b64decode,
+    compat_etree_Element,
     compat_etree_fromstring,
     compat_urllib_parse_urlencode,
     compat_urllib_request,
@@ -56,22 +56,11 @@ class CrunchyrollBaseIE(InfoExtractor):
         if username is None:
             return
 
-        self._download_webpage(
-            'https://www.crunchyroll.com/?a=formhandler',
-            None, 'Logging in', 'Wrong login info',
-            data=urlencode_postdata({
-                'formname': 'RpcApiUser_Login',
-                'next_url': 'https://www.crunchyroll.com/acct/membership',
-                'name': username,
-                'password': password,
-            }))
-
-        '''
         login_page = self._download_webpage(
             self._LOGIN_URL, None, 'Downloading login page')
 
         def is_logged(webpage):
-            return '<title>Redirecting' in webpage
+            return 'href="/logout"' in webpage
 
         # Already logged in
         if is_logged(login_page):
@@ -110,7 +99,6 @@ class CrunchyrollBaseIE(InfoExtractor):
             raise ExtractorError('Unable to login: %s' % error, expected=True)
 
         raise ExtractorError('Unable to log in')
-        '''
 
     def _real_initialize(self):
         self._login()
@@ -402,7 +390,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
                 'Downloading subtitles for ' + sub_name, data={
                     'subtitle_script_id': sub_id,
                 })
-            if not isinstance(sub_doc, etree.Element):
+            if not isinstance(sub_doc, compat_etree_Element):
                 continue
             sid = sub_doc.get('id')
             iv = xpath_text(sub_doc, 'iv', 'subtitle iv')
@@ -519,7 +507,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
                         'video_quality': stream_quality,
                         'current_page': url,
                     })
-                if isinstance(streamdata, etree.Element):
+                if isinstance(streamdata, compat_etree_Element):
                     stream_info = streamdata.find('./{default}preload/stream_info')
                     if stream_info is not None:
                         stream_infos.append(stream_info)
@@ -530,7 +518,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
                         'video_format': stream_format,
                         'video_encode_quality': stream_quality,
                     })
-                if isinstance(stream_info, etree.Element):
+                if isinstance(stream_info, compat_etree_Element):
                     stream_infos.append(stream_info)
                 for stream_info in stream_infos:
                     video_encode_id = xpath_text(stream_info, './video_encode_id')
@@ -605,7 +593,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
 
         season = episode = episode_number = duration = thumbnail = None
 
-        if isinstance(metadata, etree.Element):
+        if isinstance(metadata, compat_etree_Element):
             season = xpath_text(metadata, 'series_title')
             episode = xpath_text(metadata, 'episode_title')
             episode_number = int_or_none(xpath_text(metadata, 'episode_number'))

youtube_dl/extractor/espn.py

@@ -29,7 +29,8 @@ class ESPNIE(OnceIE):
                                     (?:
                                         .*?\?.*?\bid=|
                                         /_/id/
-                                    )
+                                    )|
+                                    [^/]+/video/
                                 )
                             )|
                             (?:www\.)espnfc\.(?:com|us)/(?:video/)?[^/]+/\d+/video/
@@ -94,6 +95,9 @@ class ESPNIE(OnceIE):
     }, {
         'url': 'http://www.espnfc.com/english-premier-league/23/video/3324163/premier-league-in-90-seconds-golden-tweets',
         'only_matching': True,
+    }, {
+        'url': 'http://www.espn.com/espnw/video/26066627/arkansas-gibson-completes-hr-cycle-four-innings',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/facebook.py

@@ -424,7 +424,7 @@ class FacebookIE(InfoExtractor):
         uploader = clean_html(get_element_by_id(
             'fbPhotoPageAuthorName', webpage)) or self._search_regex(
             r'ownerName\s*:\s*"([^"]+)"', webpage, 'uploader',
-            fatal=False) or self._og_search_title(webpage, fatal=False)
+            default=None) or self._og_search_title(webpage, fatal=False)
         timestamp = int_or_none(self._search_regex(
             r'<abbr[^>]+data-utime=["\'](\d+)', webpage,
             'timestamp', default=None))

youtube_dl/extractor/francetv.py

@@ -215,7 +215,7 @@ class FranceTVSiteIE(FranceTVBaseInfoExtractor):
     _TESTS = [{
         'url': 'https://www.france.tv/france-2/13h15-le-dimanche/140921-les-mysteres-de-jesus.html',
         'info_dict': {
-            'id': '162311093',
+            'id': 'ec217ecc-0733-48cf-ac06-af1347b849d1',
             'ext': 'mp4',
             'title': '13h15, le dimanche... - Les mystères de Jésus',
             'description': 'md5:75efe8d4c0a8205e5904498ffe1e1a42',
@@ -271,7 +271,7 @@ class FranceTVSiteIE(FranceTVBaseInfoExtractor):
 
         catalogue = None
         video_id = self._search_regex(
-            r'(?:data-main-video\s*=|videoId\s*:)\s*(["\'])(?P<id>(?:(?!\1).)+)\1',
+            r'(?:data-main-video\s*=|videoId["\']?\s*[:=])\s*(["\'])(?P<id>(?:(?!\1).)+)\1',
             webpage, 'video id', default=None, group='id')
 
         if not video_id:

youtube_dl/extractor/libsyn.py

@@ -1,12 +1,14 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import json
 import re
 
 from .common import InfoExtractor
 from ..utils import (
+    clean_html,
+    get_element_by_class,
     parse_duration,
+    strip_or_none,
     unified_strdate,
 )
 
@@ -21,7 +23,9 @@ class LibsynIE(InfoExtractor):
             'id': '6385796',
             'ext': 'mp3',
             'title': "Champion Minded - Developing a Growth Mindset",
-            'description': 'In this episode, Allistair talks about the importance of developing a growth mindset, not only in sports, but in life too.',
+            # description fetched using another request:
+            # http://html5-player.libsyn.com/embed/getitemdetails?item_id=6385796
+            # 'description': 'In this episode, Allistair talks about the importance of developing a growth mindset, not only in sports, but in life too.',
             'upload_date': '20180320',
             'thumbnail': 're:^https?://.*',
         },
@@ -38,22 +42,36 @@ class LibsynIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        m = re.match(self._VALID_URL, url)
-        video_id = m.group('id')
-        url = m.group('mainurl')
+        url, video_id = re.match(self._VALID_URL, url).groups()
         webpage = self._download_webpage(url, video_id)
 
-        podcast_title = self._search_regex(
-            r'<h3>([^<]+)</h3>', webpage, 'podcast title', default=None)
-        if podcast_title:
-            podcast_title = podcast_title.strip()
-        episode_title = self._search_regex(
-            r'(?:<div class="episode-title">|<h4>)([^<]+)</', webpage, 'episode title')
-        if episode_title:
-            episode_title = episode_title.strip()
+        data = self._parse_json(self._search_regex(
+            r'var\s+playlistItem\s*=\s*({.+?});',
+            webpage, 'JSON data block'), video_id)
+
+        episode_title = data.get('item_title') or get_element_by_class('episode-title', webpage)
+        if not episode_title:
+            self._search_regex(
+                [r'data-title="([^"]+)"', r'<title>(.+?)</title>'],
+                webpage, 'episode title')
+        episode_title = episode_title.strip()
+
+        podcast_title = strip_or_none(clean_html(self._search_regex(
+            r'<h3>([^<]+)</h3>', webpage, 'podcast title',
+            default=None) or get_element_by_class('podcast-title', webpage)))
 
         title = '%s - %s' % (podcast_title, episode_title) if podcast_title else episode_title
 
+        formats = []
+        for k, format_id in (('media_url_libsyn', 'libsyn'), ('media_url', 'main'), ('download_link', 'download')):
+            f_url = data.get(k)
+            if not f_url:
+                continue
+            formats.append({
+                'url': f_url,
+                'format_id': format_id,
+            })
+
         description = self._html_search_regex(
             r'<p\s+id="info_text_body">(.+?)</p>', webpage,
             'description', default=None)
@@ -61,27 +79,15 @@ class LibsynIE(InfoExtractor):
             # Strip non-breaking and normal spaces
             description = description.replace('\u00A0', ' ').strip()
         release_date = unified_strdate(self._search_regex(
-            r'<div class="release_date">Released: ([^<]+)<', webpage, 'release date', fatal=False))
-
-        data_json = self._search_regex(r'var\s+playlistItem\s*=\s*(\{.*?\});\n', webpage, 'JSON data block')
-        data = json.loads(data_json)
-
-        formats = [{
-            'url': data['media_url'],
-            'format_id': 'main',
-        }, {
-            'url': data['media_url_libsyn'],
-            'format_id': 'libsyn',
-        }]
-        thumbnail = data.get('thumbnail_url')
-        duration = parse_duration(data.get('duration'))
+            r'<div class="release_date">Released: ([^<]+)<',
+            webpage, 'release date', default=None) or data.get('release_date'))
 
         return {
             'id': video_id,
             'title': title,
             'description': description,
-            'thumbnail': thumbnail,
+            'thumbnail': data.get('thumbnail_url'),
             'upload_date': release_date,
-            'duration': duration,
+            'duration': parse_duration(data.get('duration')),
             'formats': formats,
         }

youtube_dl/extractor/npo.py

@@ -238,7 +238,7 @@ class NPOIE(NPOBaseIE):
                 formats.extend(self._extract_m3u8_formats(
                     stream_url, video_id, ext='mp4',
                     entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
-            elif '.ism/Manifest' in stream_url:
+            elif re.search(r'\.isml?/Manifest', stream_url):
                 formats.extend(self._extract_ism_formats(
                     stream_url, video_id, ism_id='mss', fatal=False))
             else:

youtube_dl/extractor/openload.py

@@ -249,7 +249,7 @@ class OpenloadIE(InfoExtractor):
                             (?:www\.)?
                             (?:
                                 openload\.(?:co|io|link|pw)|
-                                oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info|pw|live)
+                                oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info|pw|live|space)
                             )
                         )/
                         (?:f|embed)/
@@ -349,6 +349,9 @@ class OpenloadIE(InfoExtractor):
     }, {
         'url': 'https://oload.live/f/-Z58UZ-GR4M',
         'only_matching': True,
+    }, {
+        'url': 'https://oload.space/f/IY4eZSst3u8/',
+        'only_matching': True,
     }]
 
     _USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36'

youtube_dl/extractor/rai.py

@@ -74,11 +74,11 @@ class RaiBaseIE(InfoExtractor):
             if (ext == 'm3u8' and platform != 'mon') or (ext == 'f4m' and platform != 'flash'):
                 continue
 
-            if ext == 'm3u8':
+            if ext == 'm3u8' or 'format=m3u8' in media_url or platform == 'mon':
                 formats.extend(self._extract_m3u8_formats(
                     media_url, video_id, 'mp4', 'm3u8_native',
                     m3u8_id='hls', fatal=False))
-            elif ext == 'f4m':
+            elif ext == 'f4m' or platform == 'flash':
                 manifest_url = update_url_query(
                     media_url.replace('manifest#live_hds.f4m', 'manifest.f4m'),
                     {'hdcore': '3.7.0', 'plugin': 'aasp-3.7.0.39.44'})

youtube_dl/extractor/sixplay.py

@@ -61,7 +61,8 @@ class SixPlayIE(InfoExtractor):
         quality_key = qualities(['lq', 'sd', 'hq', 'hd'])
         formats = []
         subtitles = {}
-        for asset in clip_data['assets']:
+        assets = clip_data.get('assets') or []
+        for asset in assets:
             asset_url = asset.get('full_physical_path')
             protocol = asset.get('protocol')
             if not asset_url or protocol == 'primetime' or asset.get('type') == 'usp_hlsfp_h264' or asset_url in urls:

youtube_dl/extractor/spankbang.py

@@ -9,6 +9,8 @@ from ..utils import (
     parse_duration,
     parse_resolution,
     str_to_int,
+    url_or_none,
+    urlencode_postdata,
 )
 
 
@@ -64,16 +66,49 @@ class SpankBangIE(InfoExtractor):
                 'Video %s is not available' % video_id, expected=True)
 
         formats = []
-        for mobj in re.finditer(
-                r'stream_url_(?P<id>[^\s=]+)\s*=\s*(["\'])(?P<url>(?:(?!\2).)+)\2',
-                webpage):
-            format_id, format_url = mobj.group('id', 'url')
+
+        def extract_format(format_id, format_url):
+            f_url = url_or_none(format_url)
+            if not f_url:
+                return
             f = parse_resolution(format_id)
             f.update({
-                'url': format_url,
+                'url': f_url,
                 'format_id': format_id,
             })
             formats.append(f)
+
+        STREAM_URL_PREFIX = 'stream_url_'
+
+        for mobj in re.finditer(
+                r'%s(?P<id>[^\s=]+)\s*=\s*(["\'])(?P<url>(?:(?!\2).)+)\2'
+                % STREAM_URL_PREFIX, webpage):
+            extract_format(mobj.group('id', 'url'))
+
+        if not formats:
+            stream_key = self._search_regex(
+                r'data-streamkey\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
+                webpage, 'stream key', group='value')
+
+            sb_csrf_session = self._get_cookies(
+                'https://spankbang.com')['sb_csrf_session'].value
+
+            stream = self._download_json(
+                'https://spankbang.com/api/videos/stream', video_id,
+                'Downloading stream JSON', data=urlencode_postdata({
+                    'id': stream_key,
+                    'data': 0,
+                    'sb_csrf_session': sb_csrf_session,
+                }), headers={
+                    'Referer': url,
+                    'X-CSRFToken': sb_csrf_session,
+                })
+
+            for format_id, format_url in stream.items():
+                if format_id.startswith(STREAM_URL_PREFIX):
+                    extract_format(
+                        format_id[len(STREAM_URL_PREFIX):], format_url)
+
         self._sort_formats(formats)
 
         title = self._html_search_regex(

youtube_dl/extractor/spike.py

@@ -46,8 +46,12 @@ class ParamountNetworkIE(MTVServicesInfoExtractor):
     _GEO_COUNTRIES = ['US']
 
     def _extract_mgid(self, webpage):
-        cs = self._parse_json(self._search_regex(
+        root_data = self._parse_json(self._search_regex(
             r'window\.__DATA__\s*=\s*({.+})',
-            webpage, 'data'), None)['children']
-        c = next(c for c in cs if c.get('type') == 'VideoPlayer')
+            webpage, 'data'), None)
+
+        def find_sub_data(data, data_type):
+            return next(c for c in data['children'] if c.get('type') == data_type)
+
+        c = find_sub_data(find_sub_data(root_data, 'MainContainer'), 'VideoPlayer')
         return c['props']['media']['video']['config']['uri']

youtube_dl/extractor/toutv.py

@@ -1,14 +1,14 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
+import json
 
 from .radiocanada import RadioCanadaIE
+from ..compat import compat_HTTPError
 from ..utils import (
-    extract_attributes,
+    ExtractorError,
     int_or_none,
     merge_dicts,
-    urlencode_postdata,
 )
 
 
@@ -38,47 +38,30 @@ class TouTvIE(RadioCanadaIE):
         'url': 'https://ici.tou.tv/l-age-adulte/S01C501',
         'only_matching': True,
     }]
+    _CLIENT_KEY = '4dd36440-09d5-4468-8923-b6d91174ad36'
 
     def _real_initialize(self):
         email, password = self._get_login_info()
         if email is None:
             return
-        login_webpage = self._download_webpage(
-            'https://services.radio-canada.ca/auth/oauth/v2/authorize',
-            None, 'Downloading login page', query={
-                'client_id': '4dd36440-09d5-4468-8923-b6d91174ad36',
-                'redirect_uri': 'https://ici.tou.tv/logincallback',
-                'response_type': 'token',
-                'scope': 'id.write media-validation.read',
-                'state': '/',
-            })
-
-        def extract_form_url_and_data(wp, default_form_url, form_spec_re=''):
-            form, form_elem = re.search(
-                r'(?s)((<form[^>]+?%s[^>]*?>).+?</form>)' % form_spec_re, wp).groups()
-            form_data = self._hidden_inputs(form)
-            form_url = extract_attributes(form_elem).get('action') or default_form_url
-            return form_url, form_data
-
-        post_url, form_data = extract_form_url_and_data(
-            login_webpage,
-            'https://services.radio-canada.ca/auth/oauth/v2/authorize/login',
-            r'(?:id|name)="Form-login"')
-        form_data.update({
-            'login-email': email,
-            'login-password': password,
-        })
-        consent_webpage = self._download_webpage(
-            post_url, None, 'Logging in', data=urlencode_postdata(form_data))
-        post_url, form_data = extract_form_url_and_data(
-            consent_webpage,
-            'https://services.radio-canada.ca/auth/oauth/v2/authorize/consent')
-        _, urlh = self._download_webpage_handle(
-            post_url, None, 'Following Redirection',
-            data=urlencode_postdata(form_data))
-        self._access_token = self._search_regex(
-            r'access_token=([\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})',
-            urlh.geturl(), 'access token')
+        try:
+            self._access_token = self._download_json(
+                'https://services.radio-canada.ca/toutv/profiling/accounts/login',
+                None, 'Logging in', data=json.dumps({
+                    'ClientId': self._CLIENT_KEY,
+                    'ClientSecret': '34026772-244b-49b6-8b06-317b30ac9a20',
+                    'Email': email,
+                    'Password': password,
+                    'Scope': 'id.write media-validation.read',
+                }).encode(), headers={
+                    'Authorization': 'client-key ' + self._CLIENT_KEY,
+                    'Content-Type': 'application/json;charset=utf-8',
+                })['access_token']
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
+                error = self._parse_json(e.cause.read().decode(), None)['Message']
+                raise ExtractorError(error, expected=True)
+            raise
         self._claims = self._call_api('validation/v2/getClaims')['claims']
 
     def _real_extract(self, url):

youtube_dl/extractor/urplay.py

@@ -2,18 +2,31 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from ..utils import unified_timestamp
 
 
 class URPlayIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?ur(?:play|skola)\.se/(?:program|Produkter)/(?P<id>[0-9]+)'
     _TESTS = [{
-        'url': 'http://urplay.se/program/190031-tripp-trapp-trad-sovkudde',
-        'md5': 'ad5f0de86f16ca4c8062cd103959a9eb',
+        'url': 'https://urplay.se/program/203704-ur-samtiden-livet-universum-och-rymdens-markliga-musik-om-vetenskap-kritiskt-tankande-och-motstand',
+        'md5': 'ff5b0c89928f8083c74bbd5099c9292d',
+        'info_dict': {
+            'id': '203704',
+            'ext': 'mp4',
+            'title': 'UR Samtiden - Livet, universum och rymdens märkliga musik : Om vetenskap, kritiskt tänkande och motstånd',
+            'description': 'md5:5344508a52aa78c1ced6c1b8b9e44e9a',
+            'timestamp': 1513512768,
+            'upload_date': '20171217',
+        },
+    }, {
+        'url': 'https://urskola.se/Produkter/190031-Tripp-Trapp-Trad-Sovkudde',
         'info_dict': {
             'id': '190031',
             'ext': 'mp4',
             'title': 'Tripp, Trapp, Träd : Sovkudde',
             'description': 'md5:b86bffdae04a7e9379d1d7e5947df1d1',
+            'timestamp': 1440093600,
+            'upload_date': '20150820',
         },
     }, {
         'url': 'http://urskola.se/Produkter/155794-Smasagor-meankieli-Grodan-i-vida-varlden',
@@ -51,6 +64,7 @@ class URPlayIE(InfoExtractor):
             'title': urplayer_data['title'],
             'description': self._og_search_description(webpage),
             'thumbnail': urplayer_data.get('image'),
+            'timestamp': unified_timestamp(self._html_search_meta(('uploadDate', 'schema:uploadDate'), webpage, 'timestamp')),
             'series': urplayer_data.get('series_title'),
             'subtitles': subtitles,
             'formats': formats,

youtube_dl/extractor/vimeo.py

@@ -502,7 +502,11 @@ class VimeoIE(VimeoBaseInfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
         orig_url = url
-        if mobj.group('pro') or mobj.group('player'):
+        if mobj.group('pro'):
+            # some videos require portfolio_id to be present in player url
+            # https://github.com/rg3/youtube-dl/issues/20070
+            url = self._extract_url(url, self._download_webpage(url, video_id))
+        elif mobj.group('player'):
             url = 'https://player.vimeo.com/video/' + video_id
         elif any(p in url for p in ('play_redirect_hls', 'moogaloop.swf')):
             url = 'https://vimeo.com/' + video_id

youtube_dl/extractor/youtube.py

@@ -352,6 +352,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                             (?:www\.)?yourepeat\.com/|
                             tube\.majestyc\.net/|
                             (?:www\.)?invidio\.us/|
+                            (?:www\.)?invidious\.snopyta\.org/|
+                            (?:www\.)?invidious\.kabi\.tk/|
+                            (?:www\.)?vid\.wxzm\.sx/|
                             youtube\.googleapis\.com/)                        # the various hostnames, with wildcard subdomains
                          (?:.*?\#/)?                                          # handle anchor (#/) redirect urls
                          (?:                                                  # the various things that can precede the ID:

youtube_dl/utils.py

@@ -1141,6 +1141,8 @@ class YoutubeDLHTTPSHandler(compat_urllib_request.HTTPSHandler):
 
 
 class YoutubeDLCookieJar(compat_cookiejar.MozillaCookieJar):
+    _HTTPONLY_PREFIX = '#HttpOnly_'
+
     def save(self, filename=None, ignore_discard=False, ignore_expires=False):
         # Store session cookies with `expires` set to 0 instead of an empty
         # string
@@ -1150,7 +1152,21 @@ class YoutubeDLCookieJar(compat_cookiejar.MozillaCookieJar):
         compat_cookiejar.MozillaCookieJar.save(self, filename, ignore_discard, ignore_expires)
 
     def load(self, filename=None, ignore_discard=False, ignore_expires=False):
-        compat_cookiejar.MozillaCookieJar.load(self, filename, ignore_discard, ignore_expires)
+        """Load cookies from a file."""
+        if filename is None:
+            if self.filename is not None:
+                filename = self.filename
+            else:
+                raise ValueError(compat_cookiejar.MISSING_FILENAME_TEXT)
+
+        cf = io.StringIO()
+        with open(filename) as f:
+            for line in f:
+                if line.startswith(self._HTTPONLY_PREFIX):
+                    line = line[len(self._HTTPONLY_PREFIX):]
+                cf.write(compat_str(line))
+        cf.seek(0)
+        self._really_load(cf, filename, ignore_discard, ignore_expires)
         # Session cookies are denoted by either `expires` field set to
         # an empty string or 0. MozillaCookieJar only recognizes the former
         # (see [1]). So we need force the latter to be recognized as session

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2019.03.01'
+__version__ = '2019.03.09'