Merge remote-tracking branch 'upstream/master' into BlenderCloud-issue-13282

2017-06-14 14:14:57 -05:00 · 2017-06-14 14:14:57 -05:00 · 4f0545b171
commit 4f0545b171
parent d2727c3134 0a268c6e11
16 changed files with 266 additions and 49 deletions
--- a/.github/ISSUE_TEMPLATE.md
+++ b/.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 *2017.06.05*. 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 Issues with outdated version will be rejected.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 **2017.06.05**
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.06.12*. 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 Issues with outdated version will be rejected.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 **2017.06.12**

 ### Before submitting an *issue* make sure you have:
 - [ ] At least skimmed through [README](https://github.com/rg3/youtube-dl/blob/master/README.md) and **most notably** [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
@ -35,7 +35,7 @@ $ youtube-dl -v <your command line>
 [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 2017.06.05
+[debug] youtube-dl version 2017.06.12
 [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: {}
--- a/33
+++ b/33
@ -1,3 +1,36 @@
+version 2017.06.12
+
+Core
+* [utils] Handle compat_HTMLParseError in extract_attributes (#13349)
+ [compat] Introduce compat_HTMLParseError
+* [utils] Improve unified_timestamp
+* [extractor/generic] Ensure format id is unicode string
+* [extractor/common] Return unicode string from _match_id
+ [YoutubeDL] Sanitize more fields (#13313)
+
+Extractors
+ [xfileshare] Add support for rapidvideo.tv (#13348)
+* [xfileshare] Modernize and pass Referer
+ [rutv] Add support for testplayer.vgtrk.com (#13347)
+ [newgrounds] Extract more metadata (#13232)
+ [newgrounds:playlist] Add support for playlists (#10611)
+* [newgrounds] Improve formats and uploader extraction (#13346)
+* [msn] Fix formats extraction
+* [turbo] Ensure format id is string
+* [sexu] Ensure height is int
+* [jove] Ensure comment count is int
+* [golem] Ensure format id is string
+* [gfycat] Ensure filesize is int
+* [foxgay] Ensure height is int
+* [flickr] Ensure format id is string
+* [sohu] Fix numeric fields
+* [safari] Improve authentication detection (#13319)
+* [liveleak] Ensure height is int (#13313)
+* [streamango] Make title optional (#13292)
+* [rtlnl] Improve URL regular expression (#13295)
+* [tvplayer] Fix extraction (#13291)
+
+
 version 2017.06.05

 Core
--- a/README.md
+++ b/README.md
@ -145,18 +145,18 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
    --max-views COUNT                Do not download any videos with more than
                                     COUNT views
    --match-filter FILTER            Generic video filter. Specify any key (see
-                                     help for -o for a list of available keys)
-                                     to match if the key is present, !key to
-                                     check if the key is not present, key >
-                                     NUMBER (like "comment_count > 12", also
-                                     works with >=, <, <=, !=, =) to compare
-                                     against a number, key = 'LITERAL' (like
-                                     "uploader = 'Mike Smith'", also works with
-                                     !=) to match against a string literal and &
-                                     to require multiple matches. Values which
-                                     are not known are excluded unless you put a
-                                     question mark (?) after the operator. For
-                                     example, to only match videos that have
+                                     the "OUTPUT TEMPLATE" for a list of
+                                     available keys) to match if the key is
+                                     present, !key to check if the key is not
+                                     present, key > NUMBER (like "comment_count
+                                     > 12", also works with >=, <, <=, !=, =) to
+                                     compare against a number, key = 'LITERAL'
+                                     (like "uploader = 'Mike Smith'", also works
+                                     with !=) to match against a string literal
+                                     and & to require multiple matches. Values
+                                     which are not known are excluded unless you
+                                     put a question mark (?) after the operator.
+                                     For example, to only match videos that have
                                     been liked more than 100 times and disliked
                                     less than 50 times (or the dislike
                                     functionality is not available at the given
@ -277,8 +277,8 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
    --get-filename                   Simulate, quiet but print output filename
    --get-format                     Simulate, quiet but print output format
    -j, --dump-json                  Simulate, quiet but print JSON information.
-                                     See --output for a description of available
-                                     keys.
+                                     See the "OUTPUT TEMPLATE" for a description
+                                     of available keys.
    -J, --dump-single-json           Simulate, quiet but print JSON information
                                     for each command-line argument. If the URL
                                     refers to a playlist, dump the whole
--- a/docs/supportedsites.md
+++ b/docs/supportedsites.md
@ -512,6 +512,7 @@
 - **netease:song**: 网易云音乐
 - **Netzkino**
 - **Newgrounds**
+ - **NewgroundsPlaylist**
 - **Newstube**
 - **NextMedia**: 蘋果日報
 - **NextMediaActionNews**: 蘋果日報 - 動新聞
@ -974,7 +975,7 @@
 - **WSJArticle**
 - **XBef**
 - **XboxClips**
- - **XFileShare**: XFileShare based sites: DaClips, FileHoot, GorillaVid, MovPod, PowerWatch, Rapidvideo.ws, TheVideoBee, Vidto, Streamin.To, XVIDSTAGE, Vid ABC, VidBom, vidlo
+ - **XFileShare**: XFileShare based sites: DaClips, FileHoot, GorillaVid, MovPod, PowerWatch, Rapidvideo.ws, TheVideoBee, Vidto, Streamin.To, XVIDSTAGE, Vid ABC, VidBom, vidlo, RapidVideo.TV
 - **XHamster**
 - **XHamsterEmbed**
 - **xiami:album**: 虾米音乐 - 专辑
--- a/test/test_utils.py
+++ b/test/test_utils.py
@ -340,6 +340,7 @@ class TestUtil(unittest.TestCase):
        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)

    def test_determine_ext(self):
        self.assertEqual(determine_ext('http://example.com/foo/bar.mp4/?download'), 'mp4')
@ -915,6 +916,8 @@ 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')
--- a/youtube_dl/compat.py
+++ b/youtube_dl/compat.py
@ -2322,6 +2322,19 @@ try:
 except ImportError:  # Python 2
    from HTMLParser import HTMLParser as compat_HTMLParser

+try:  # Python 2
+    from HTMLParser import HTMLParseError as compat_HTMLParseError
+except ImportError:  # Python <3.4
+    try:
+        from html.parser import HTMLParseError as compat_HTMLParseError
+    except ImportError:  # Python >3.4
+
+        # HTMLParseError has been deprecated in Python 3.3 and removed in
+        # Python 3.5. Introducing dummy exception for Python >3.5 for compatible
+        # and uniform cross-version exceptiong handling
+        class compat_HTMLParseError(Exception):
+            pass
+
 try:
    from subprocess import DEVNULL
    compat_subprocess_get_DEVNULL = lambda: DEVNULL
@ -2882,6 +2895,7 @@ else:


 __all__ = [
+    'compat_HTMLParseError',
    'compat_HTMLParser',
    'compat_HTTPError',
    'compat_basestring',
--- a/youtube_dl/extractor/common.py
+++ b/youtube_dl/extractor/common.py
@ -2328,6 +2328,8 @@ class InfoExtractor(object):
        urls = []
        formats = []
        for source in jwplayer_sources_data:
+            if not isinstance(source, dict):
+                continue
            source_url = self._proto_relative_url(source.get('file'))
            if not source_url:
                continue
--- a/youtube_dl/extractor/corus.py
+++ b/youtube_dl/extractor/corus.py
@ -8,7 +8,16 @@ from ..utils import int_or_none


 class CorusIE(ThePlatformFeedIE):
-    _VALID_URL = r'https?://(?:www\.)?(?P<domain>(?:globaltv|etcanada)\.com|(?:hgtv|foodnetwork|slice)\.ca)/(?:video/|(?:[^/]+/)+(?:videos/[a-z0-9-]+-|video\.html\?.*?\bv=))(?P<id>\d+)'
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:www\.)?
+                        (?P<domain>
+                            (?:globaltv|etcanada)\.com|
+                            (?:hgtv|foodnetwork|slice|history|showcase)\.ca
+                        )
+                        /(?:video/|(?:[^/]+/)+(?:videos/[a-z0-9-]+-|video\.html\?.*?\bv=))
+                        (?P<id>\d+)
+                    '''
    _TESTS = [{
        'url': 'http://www.hgtv.ca/shows/bryan-inc/videos/movie-night-popcorn-with-bryan-870923331648/',
        'md5': '05dcbca777bf1e58c2acbb57168ad3a6',
@ -27,6 +36,12 @@ class CorusIE(ThePlatformFeedIE):
    }, {
        'url': 'http://etcanada.com/video/873675331955/meet-the-survivor-game-changers-castaways-part-2/',
        'only_matching': True,
+    }, {
+        'url': 'http://www.history.ca/the-world-without-canada/video/full-episodes/natural-resources/video.html?v=955054659646#video',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.showcase.ca/eyewitness/video/eyewitness++106/video.html?v=955070531919&p=1&s=da#video',
+        'only_matching': True,
    }]

    _TP_FEEDS = {
@ -50,6 +65,14 @@ class CorusIE(ThePlatformFeedIE):
            'feed_id': '5tUJLgV2YNJ5',
            'account_id': 2414427935,
        },
+        'history': {
+            'feed_id': 'tQFx_TyyEq4J',
+            'account_id': 2369613659,
+        },
+        'showcase': {
+            'feed_id': '9H6qyshBZU3E',
+            'account_id': 2414426607,
+        },
    }

    def _real_extract(self, url):
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@ -637,7 +637,10 @@ from .neteasemusic import (
    NetEaseMusicProgramIE,
    NetEaseMusicDjRadioIE,
 )
-from .newgrounds import NewgroundsIE
+from .newgrounds import (
+    NewgroundsIE,
+    NewgroundsPlaylistIE,
+)
 from .newstube import NewstubeIE
 from .nextmedia import (
    NextMediaIE,
--- a/youtube_dl/extractor/msn.py
+++ b/youtube_dl/extractor/msn.py
@ -68,10 +68,6 @@ class MSNIE(InfoExtractor):
            format_url = file_.get('url')
            if not format_url:
                continue
-            ext = determine_ext(format_url)
-            if ext == 'ism':
-                formats.extend(self._extract_ism_formats(
-                    format_url + '/Manifest', display_id, 'mss', fatal=False))
            if 'm3u8' in format_url:
                # m3u8_native should not be used here until
                # https://github.com/rg3/youtube-dl/issues/9913 is fixed
@ -79,6 +75,9 @@ class MSNIE(InfoExtractor):
                    format_url, display_id, 'mp4',
                    m3u8_id='hls', fatal=False)
                formats.extend(m3u8_formats)
+            elif determine_ext(format_url) == 'ism':
+                formats.extend(self._extract_ism_formats(
+                    format_url + '/Manifest', display_id, 'mss', fatal=False))
            else:
                formats.append({
                    'url': format_url,
--- a/youtube_dl/extractor/newgrounds.py
+++ b/youtube_dl/extractor/newgrounds.py
@ -1,6 +1,15 @@
 from __future__ import unicode_literals

+import re
+
 from .common import InfoExtractor
+from ..utils import (
+    extract_attributes,
+    int_or_none,
+    parse_duration,
+    parse_filesize,
+    unified_timestamp,
+)


 class NewgroundsIE(InfoExtractor):
@ -13,7 +22,10 @@ class NewgroundsIE(InfoExtractor):
            'ext': 'mp3',
            'title': 'B7 - BusMode',
            'uploader': 'Burn7',
-        }
+            'timestamp': 1378878540,
+            'upload_date': '20130911',
+            'duration': 143,
+        },
    }, {
        'url': 'https://www.newgrounds.com/portal/view/673111',
        'md5': '3394735822aab2478c31b1004fe5e5bc',
@ -22,25 +34,133 @@ class NewgroundsIE(InfoExtractor):
            'ext': 'mp4',
            'title': 'Dancin',
            'uploader': 'Squirrelman82',
+            'timestamp': 1460256780,
+            'upload_date': '20160410',
+        },
+    }, {
+        # source format unavailable, additional mp4 formats
+        'url': 'http://www.newgrounds.com/portal/view/689400',
+        'info_dict': {
+            'id': '689400',
+            'ext': 'mp4',
+            'title': 'ZTV News Episode 8',
+            'uploader': 'BennettTheSage',
+            'timestamp': 1487965140,
+            'upload_date': '20170224',
+        },
+        'params': {
+            'skip_download': True,
        },
    }]

    def _real_extract(self, url):
        media_id = self._match_id(url)
+
        webpage = self._download_webpage(url, media_id)

        title = self._html_search_regex(
            r'<title>([^>]+)</title>', webpage, 'title')

-        uploader = self._html_search_regex(
-            r'Author\s*<a[^>]+>([^<]+)', webpage, 'uploader', fatal=False)
+        media_url = self._parse_json(self._search_regex(
+            r'"url"\s*:\s*("[^"]+"),', webpage, ''), media_id)

-        music_url = self._parse_json(self._search_regex(
-            r'"url":("[^"]+"),', webpage, ''), media_id)
+        formats = [{
+            'url': media_url,
+            'format_id': 'source',
+            'quality': 1,
+        }]
+
+        max_resolution = int_or_none(self._search_regex(
+            r'max_resolution["\']\s*:\s*(\d+)', webpage, 'max resolution',
+            default=None))
+        if max_resolution:
+            url_base = media_url.rpartition('.')[0]
+            for resolution in (360, 720, 1080):
+                if resolution > max_resolution:
+                    break
+                formats.append({
+                    'url': '%s.%dp.mp4' % (url_base, resolution),
+                    'format_id': '%dp' % resolution,
+                    'height': resolution,
+                })
+
+        self._check_formats(formats, media_id)
+        self._sort_formats(formats)
+
+        uploader = self._search_regex(
+            r'(?:Author|Writer)\s*<a[^>]+>([^<]+)', webpage, 'uploader',
+            fatal=False)
+
+        timestamp = unified_timestamp(self._search_regex(
+            r'<dt>Uploaded</dt>\s*<dd>([^<]+)', webpage, 'timestamp',
+            default=None))
+        duration = parse_duration(self._search_regex(
+            r'<dd>Song\s*</dd><dd>.+?</dd><dd>([^<]+)', webpage, 'duration',
+            default=None))
+
+        filesize_approx = parse_filesize(self._html_search_regex(
+            r'<dd>Song\s*</dd><dd>(.+?)</dd>', webpage, 'filesize',
+            default=None))
+        if len(formats) == 1:
+            formats[0]['filesize_approx'] = filesize_approx
+
+        if '<dd>Song' in webpage:
+            formats[0]['vcodec'] = 'none'

        return {
            'id': media_id,
            'title': title,
-            'url': music_url,
            'uploader': uploader,
+            'timestamp': timestamp,
+            'duration': duration,
+            'formats': formats,
        }
+
+
+class NewgroundsPlaylistIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?newgrounds\.com/(?:collection|[^/]+/search/[^/]+)/(?P<id>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'https://www.newgrounds.com/collection/cats',
+        'info_dict': {
+            'id': 'cats',
+            'title': 'Cats',
+        },
+        'playlist_mincount': 46,
+    }, {
+        'url': 'http://www.newgrounds.com/portal/search/author/ZONE-SAMA',
+        'info_dict': {
+            'id': 'ZONE-SAMA',
+            'title': 'Portal Search: ZONE-SAMA',
+        },
+        'playlist_mincount': 47,
+    }, {
+        'url': 'http://www.newgrounds.com/audio/search/title/cats',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, playlist_id)
+
+        title = self._search_regex(
+            r'<title>([^>]+)</title>', webpage, 'title', default=None)
+
+        # cut left menu
+        webpage = self._search_regex(
+            r'(?s)<div[^>]+\bclass=["\']column wide(.+)',
+            webpage, 'wide column', default=webpage)
+
+        entries = []
+        for a, path, media_id in re.findall(
+                r'(<a[^>]+\bhref=["\']/?((?:portal/view|audio/listen)/(\d+))[^>]+>)',
+                webpage):
+            a_class = extract_attributes(a).get('class')
+            if a_class not in ('item-portalsubmission', 'item-audiosubmission'):
+                continue
+            entries.append(
+                self.url_result(
+                    'https://www.newgrounds.com/%s' % path,
+                    ie=NewgroundsIE.ie_key(), video_id=media_id))
+
+        return self.playlist_result(entries, playlist_id, title)
--- a/youtube_dl/extractor/npo.py
+++ b/youtube_dl/extractor/npo.py
@ -35,7 +35,7 @@ class NPOIE(NPOBaseIE):
                        https?://
                            (?:www\.)?
                            (?:
-                                npo\.nl/(?!live|radio)(?:[^/]+/){2}|
+                                npo\.nl/(?!(?:live|radio)/)(?:[^/]+/){2}|
                                ntr\.nl/(?:[^/]+/){2,}|
                                omroepwnl\.nl/video/fragment/[^/]+__|
                                zapp\.nl/[^/]+/[^/]+/
@ -150,6 +150,9 @@ class NPOIE(NPOBaseIE):
        # live stream
        'url': 'npo:LI_NL1_4188102',
        'only_matching': True,
+    }, {
+        'url': 'http://www.npo.nl/radio-gaga/13-06-2017/BNN_101383373',
+        'only_matching': True,
    }]

    def _real_extract(self, url):
--- a/youtube_dl/extractor/rutv.py
+++ b/youtube_dl/extractor/rutv.py
@ -13,11 +13,15 @@ from ..utils import (
 class RUTVIE(InfoExtractor):
    IE_DESC = 'RUTV.RU'
    _VALID_URL = r'''(?x)
-        https?://player\.(?:rutv\.ru|vgtrk\.com)/
-            (?P<path>flash\d+v/container\.swf\?id=
-            |iframe/(?P<type>swf|video|live)/id/
-            |index/iframe/cast_id/)
-            (?P<id>\d+)'''
+                    https?://
+                        (?:test)?player\.(?:rutv\.ru|vgtrk\.com)/
+                        (?P<path>
+                            flash\d+v/container\.swf\?id=|
+                            iframe/(?P<type>swf|video|live)/id/|
+                            index/iframe/cast_id/
+                        )
+                        (?P<id>\d+)
+                    '''

    _TESTS = [
        {
@ -99,17 +103,21 @@ class RUTVIE(InfoExtractor):
                'skip_download': True,
            },
        },
+        {
+            'url': 'https://testplayer.vgtrk.com/iframe/live/id/19201/showZoomBtn/false/isPlay/true/',
+            'only_matching': True,
+        },
    ]

    @classmethod
    def _extract_url(cls, webpage):
        mobj = re.search(
-            r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.(?:rutv\.ru|vgtrk\.com)/(?:iframe/(?:swf|video|live)/id|index/iframe/cast_id)/.+?)\1', webpage)
+            r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:test)?player\.(?:rutv\.ru|vgtrk\.com)/(?:iframe/(?:swf|video|live)/id|index/iframe/cast_id)/.+?)\1', webpage)
        if mobj:
            return mobj.group('url')

        mobj = re.search(
-            r'<meta[^>]+?property=(["\'])og:video\1[^>]+?content=(["\'])(?P<url>https?://player\.(?:rutv\.ru|vgtrk\.com)/flash\d+v/container\.swf\?id=.+?\2)',
+            r'<meta[^>]+?property=(["\'])og:video\1[^>]+?content=(["\'])(?P<url>https?://(?:test)?player\.(?:rutv\.ru|vgtrk\.com)/flash\d+v/container\.swf\?id=.+?\2)',
            webpage)
        if mobj:
            return mobj.group('url')
--- a/youtube_dl/extractor/xfileshare.py
+++ b/youtube_dl/extractor/xfileshare.py
@ -10,7 +10,6 @@ from ..utils import (
    ExtractorError,
    int_or_none,
    NO_DEFAULT,
-    sanitized_Request,
    urlencode_postdata,
 )

@ -30,6 +29,7 @@ class XFileShareIE(InfoExtractor):
        (r'vidabc\.com', 'Vid ABC'),
        (r'vidbom\.com', 'VidBom'),
        (r'vidlo\.us', 'vidlo'),
+        (r'rapidvideo\.(?:cool|org)', 'RapidVideo.TV'),
    )

    IE_DESC = 'XFileShare based sites: %s' % ', '.join(list(zip(*_SITES))[1])
@ -109,6 +109,9 @@ class XFileShareIE(InfoExtractor):
        'params': {
            'skip_download': True,
        },
+    }, {
+        'url': 'http://www.rapidvideo.cool/b667kprndr8w',
+        'only_matching': True,
    }]

    def _real_extract(self, url):
@ -130,12 +133,12 @@ class XFileShareIE(InfoExtractor):
            if countdown:
                self._sleep(countdown, video_id)

-            post = urlencode_postdata(fields)
-
-            req = sanitized_Request(url, post)
-            req.add_header('Content-type', 'application/x-www-form-urlencoded')
-
-            webpage = self._download_webpage(req, video_id, 'Downloading video page')
+            webpage = self._download_webpage(
+                url, video_id, 'Downloading video page',
+                data=urlencode_postdata(fields), headers={
+                    'Referer': url,
+                    'Content-type': 'application/x-www-form-urlencoded',
+                })

        title = (self._search_regex(
            (r'style="z-index: [0-9]+;">([^<]+)</span>',
--- a/youtube_dl/utils.py
+++ b/youtube_dl/utils.py
@ -36,6 +36,7 @@ import xml.etree.ElementTree
 import zlib

 from .compat import (
+    compat_HTMLParseError,
    compat_HTMLParser,
    compat_basestring,
    compat_chr,
@ -409,8 +410,12 @@ def extract_attributes(html_element):
    but the cases in the unit test will work for all of 2.6, 2.7, 3.2-3.5.
    """
    parser = HTMLAttributeParser()
-    parser.feed(html_element)
-    parser.close()
+    try:
+        parser.feed(html_element)
+        parser.close()
+    # Older Python may throw HTMLParseError in case of malformed HTML
+    except compat_HTMLParseError:
+        pass
    return parser.attrs


@ -1179,7 +1184,7 @@ def unified_timestamp(date_str, day_first=True):
    if date_str is None:
        return None

-    date_str = date_str.replace(',', ' ')
+    date_str = re.sub(r'[,|]', '', date_str)

    pm_delta = 12 if re.search(r'(?i)PM', date_str) else 0
    timezone, date_str = extract_timezone(date_str)
--- a/youtube_dl/version.py
+++ b/youtube_dl/version.py
@ -1,3 +1,3 @@
 from __future__ import unicode_literals

-__version__ = '2017.06.05'
+__version__ = '2017.06.12'