release 2018.07.04

[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 *2018.06.25*. 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 Issues with outdated version will be rejected.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 **2018.06.25**
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.07.04*. 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 Issues with outdated version will be rejected.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 **2018.07.04**
 
 ### 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 2018.06.25
+[debug] youtube-dl version 2018.07.04
 [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: {}

ChangeLog

@@ -1,3 +1,24 @@
+version 2018.07.04
+
+Core
+* [extractor/common] Properly escape % in MPD templates (#16867)
+* [extractor/common] Use source URL as Referer for HTML5 entries (16849)
+* Prefer ffmpeg over avconv by default (#8622)
+
+Extractors
+* [pluralsight] Switch to graphql (#16889, #16895, #16896, #16899)
+* [lynda] Simplify login and improve error capturing (#16891)
++ [go90] Add support for embed URLs (#16873)
+* [go90] Detect geo restriction error and pass geo verification headers
+  (#16874)
+* [vlive] Fix live streams extraction (#16871)
+* [npo] Fix typo (#16872)
++ [mediaset] Add support for new videos and extract all formats (#16568)
+* [dctptv] Restore extraction based on REST API (#16850)
+* [svt] Improve extraction and add support for pages (#16802)
+* [porncom] Fix extraction (#16808)
+
+
 version 2018.06.25
 
 Extractors

README.md

@@ -427,9 +427,9 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
                                      default; fix file if we can, warn
                                      otherwise)
     --prefer-avconv                  Prefer avconv over ffmpeg for running the
-                                     postprocessors (default)
-    --prefer-ffmpeg                  Prefer ffmpeg over avconv for running the
                                      postprocessors
+    --prefer-ffmpeg                  Prefer ffmpeg over avconv for running the
+                                     postprocessors (default)
     --ffmpeg-location PATH           Location of the ffmpeg/avconv binary;
                                      either the path to the binary or its
                                      containing directory.

docs/supportedsites.md

@@ -813,6 +813,7 @@
  - **StretchInternet**
  - **SunPorno**
  - **SVT**
+ - **SVTPage**
  - **SVTPlay**: SVT Play and Öppet arkiv
  - **SVTSeries**
  - **SWRMediathek**

youtube_dl/YoutubeDL.py

@@ -305,8 +305,8 @@ class YoutubeDL(object):
     http_chunk_size.
 
     The following options are used by the post processors:
-    prefer_ffmpeg:     If True, use ffmpeg instead of avconv if both are available,
-                       otherwise prefer avconv.
+    prefer_ffmpeg:     If False, use avconv instead of ffmpeg if both are available,
+                       otherwise prefer ffmpeg.
     postprocessor_args: A list of additional command-line arguments for the
                         postprocessor.
 

youtube_dl/extractor/common.py

@@ -2106,7 +2106,21 @@ class InfoExtractor(object):
                         representation_ms_info = extract_multisegment_info(representation, adaption_set_ms_info)
 
                         def prepare_template(template_name, identifiers):
-                            t = representation_ms_info[template_name]
+                            tmpl = representation_ms_info[template_name]
+                            # First of, % characters outside $...$ templates
+                            # must be escaped by doubling for proper processing
+                            # by % operator string formatting used further (see
+                            # https://github.com/rg3/youtube-dl/issues/16867).
+                            t = ''
+                            in_template = False
+                            for c in tmpl:
+                                t += c
+                                if c == '$':
+                                    in_template = not in_template
+                                elif c == '%' and not in_template:
+                                    t += c
+                            # Next, $...$ templates are translated to their
+                            # %(...) counterparts to be used with % operator
                             t = t.replace('$RepresentationID$', representation_id)
                             t = re.sub(r'\$(%s)\$' % '|'.join(identifiers), r'%(\1)d', t)
                             t = re.sub(r'\$(%s)%%([^$]+)\$' % '|'.join(identifiers), r'%(\1)\2', t)
@@ -2437,6 +2451,8 @@ class InfoExtractor(object):
                         media_info['subtitles'].setdefault(lang, []).append({
                             'url': absolute_url(src),
                         })
+            for f in media_info['formats']:
+                f.setdefault('http_headers', {})['Referer'] = base_url
             if media_info['formats'] or media_info['subtitles']:
                 entries.append(media_info)
         return entries

youtube_dl/extractor/dctp.py

@@ -5,13 +5,15 @@ from .common import InfoExtractor
 from ..compat import compat_str
 from ..utils import (
     float_or_none,
-    unified_strdate,
+    int_or_none,
+    unified_timestamp,
 )
 
 
 class DctpTvIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?dctp\.tv/(?:#/)?filme/(?P<id>[^/?#&]+)'
-    _TEST = {
+    _TESTS = [{
+        # 4x3
         'url': 'http://www.dctp.tv/filme/videoinstallation-fuer-eine-kaufhausfassade/',
         'info_dict': {
             'id': '95eaa4f33dad413aa17b4ee613cccc6c',
@@ -19,31 +21,49 @@ class DctpTvIE(InfoExtractor):
             'ext': 'flv',
             'title': 'Videoinstallation für eine Kaufhausfassade',
             'description': 'Kurzfilm',
-            'upload_date': '20110407',
             'thumbnail': r're:^https?://.*\.jpg$',
             'duration': 71.24,
+            'timestamp': 1302172322,
+            'upload_date': '20110407',
         },
         'params': {
             # rtmp download
             'skip_download': True,
         },
-    }
+    }, {
+        # 16x9
+        'url': 'http://www.dctp.tv/filme/sind-youtuber-die-besseren-lehrer/',
+        'only_matching': True,
+    }]
+
+    _BASE_URL = 'http://dctp-ivms2-restapi.s3.amazonaws.com'
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
 
-        webpage = self._download_webpage(url, display_id)
+        version = self._download_json(
+            '%s/version.json' % self._BASE_URL, display_id,
+            'Downloading version JSON')
 
-        video_id = self._html_search_meta(
-            'DC.identifier', webpage, 'video id',
-            default=None) or self._search_regex(
-            r'id=["\']uuid[^>]+>([^<]+)<', webpage, 'video id')
+        restapi_base = '%s/%s/restapi' % (
+            self._BASE_URL, version['version_name'])
 
-        title = self._og_search_title(webpage)
+        info = self._download_json(
+            '%s/slugs/%s.json' % (restapi_base, display_id), display_id,
+            'Downloading video info JSON')
+
+        media = self._download_json(
+            '%s/media/%s.json' % (restapi_base, compat_str(info['object_id'])),
+            display_id, 'Downloading media JSON')
+
+        uuid = media['uuid']
+        title = media['title']
+        ratio = '16x9' if media.get('is_wide') else '4x3'
+        play_path = 'mp4:%s_dctp_0500_%s.m4v' % (uuid, ratio)
 
         servers = self._download_json(
             'http://www.dctp.tv/streaming_servers/', display_id,
-            note='Downloading server list', fatal=False)
+            note='Downloading server list JSON', fatal=False)
 
         if servers:
             endpoint = next(
@@ -60,27 +80,35 @@ class DctpTvIE(InfoExtractor):
         formats = [{
             'url': endpoint,
             'app': app,
-            'play_path': 'mp4:%s_dctp_0500_4x3.m4v' % video_id,
+            'play_path': play_path,
             'page_url': url,
-            'player_url': 'http://svm-prod-dctptv-static.s3.amazonaws.com/dctptv-relaunch2012-109.swf',
+            'player_url': 'http://svm-prod-dctptv-static.s3.amazonaws.com/dctptv-relaunch2012-110.swf',
             'ext': 'flv',
         }]
 
-        description = self._html_search_meta('DC.description', webpage)
-        upload_date = unified_strdate(
-            self._html_search_meta('DC.date.created', webpage))
-        thumbnail = self._og_search_thumbnail(webpage)
-        duration = float_or_none(self._search_regex(
-            r'id=["\']duration_in_ms[^+]>(\d+)', webpage, 'duration',
-            default=None), scale=1000)
+        thumbnails = []
+        images = media.get('images')
+        if isinstance(images, list):
+            for image in images:
+                if not isinstance(image, dict):
+                    continue
+                image_url = image.get('url')
+                if not image_url or not isinstance(image_url, compat_str):
+                    continue
+                thumbnails.append({
+                    'url': image_url,
+                    'width': int_or_none(image.get('width')),
+                    'height': int_or_none(image.get('height')),
+                })
 
         return {
-            'id': video_id,
-            'title': title,
-            'formats': formats,
+            'id': uuid,
             'display_id': display_id,
-            'description': description,
-            'upload_date': upload_date,
-            'thumbnail': thumbnail,
-            'duration': duration,
+            'title': title,
+            'alt_title': media.get('subtitle'),
+            'description': media.get('description') or media.get('teaser'),
+            'timestamp': unified_timestamp(media.get('created')),
+            'duration': float_or_none(media.get('duration_in_ms'), scale=1000),
+            'thumbnails': thumbnails,
+            'formats': formats,
         }

youtube_dl/extractor/extractors.py

@@ -1040,6 +1040,7 @@ from .stretchinternet import StretchInternetIE
 from .sunporno import SunPornoIE
 from .svt import (
     SVTIE,
+    SVTPageIE,
     SVTPlayIE,
     SVTSeriesIE,
 )

youtube_dl/extractor/generic.py

@@ -1395,17 +1395,6 @@ class GenericIE(InfoExtractor):
                 'skip_download': True,
             },
         },
-        # SVT embed
-        {
-            'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
-            'info_dict': {
-                'id': '2900353',
-                'ext': 'flv',
-                'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
-                'duration': 27,
-                'age_limit': 0,
-            },
-        },
         # Crooks and Liars embed
         {
             'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',

youtube_dl/extractor/go90.py

@@ -4,6 +4,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_HTTPError
 from ..utils import (
     determine_ext,
     ExtractorError,
@@ -14,8 +15,8 @@ from ..utils import (
 
 
 class Go90IE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?go90\.com/videos/(?P<id>[0-9a-zA-Z]+)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?go90\.com/(?:videos|embed)/(?P<id>[0-9a-zA-Z]+)'
+    _TESTS = [{
         'url': 'https://www.go90.com/videos/84BUqjLpf9D',
         'md5': 'efa7670dbbbf21a7b07b360652b24a32',
         'info_dict': {
@@ -27,15 +28,31 @@ class Go90IE(InfoExtractor):
             'upload_date': '20170411',
             'age_limit': 14,
         }
-    }
+    }, {
+        'url': 'https://www.go90.com/embed/261MflWkD3N',
+        'only_matching': True,
+    }]
+    _GEO_BYPASS = False
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        video_data = self._download_json(
-            'https://www.go90.com/api/view/items/' + video_id,
-            video_id, headers={
+
+        try:
+            headers = self.geo_verification_headers()
+            headers.update({
                 'Content-Type': 'application/json; charset=utf-8',
-            }, data=b'{"client":"web","device_type":"pc"}')
+            })
+            video_data = self._download_json(
+                'https://www.go90.com/api/view/items/' + video_id, video_id,
+                headers=headers, data=b'{"client":"web","device_type":"pc"}')
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400:
+                message = self._parse_json(e.cause.read().decode(), None)['error']['message']
+                if 'region unavailable' in message:
+                    self.raise_geo_restricted(countries=['US'])
+                raise ExtractorError(message, expected=True)
+            raise
+
         if video_data.get('requires_drm'):
             raise ExtractorError('This video is DRM protected.', expected=True)
         main_video_asset = video_data['main_video_asset']

youtube_dl/extractor/lynda.py

@@ -4,7 +4,6 @@ import re
 
 from .common import InfoExtractor
 from ..compat import (
-    compat_HTTPError,
     compat_str,
     compat_urlparse,
 )
@@ -44,21 +43,15 @@ class LyndaBaseIE(InfoExtractor):
         form_data = self._hidden_inputs(form_html)
         form_data.update(extra_form_data)
 
-        try:
-            response = self._download_json(
-                action_url, None, note,
-                data=urlencode_postdata(form_data),
-                headers={
-                    'Referer': referrer_url,
-                    'X-Requested-With': 'XMLHttpRequest',
-                })
-        except ExtractorError as e:
-            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 500:
-                response = self._parse_json(e.cause.read().decode('utf-8'), None)
-                self._check_error(response, ('email', 'password'))
-            raise
+        response = self._download_json(
+            action_url, None, note,
+            data=urlencode_postdata(form_data),
+            headers={
+                'Referer': referrer_url,
+                'X-Requested-With': 'XMLHttpRequest',
+            }, expected_status=(418, 500, ))
 
-        self._check_error(response, 'ErrorMessage')
+        self._check_error(response, ('email', 'password', 'ErrorMessage'))
 
         return response, action_url
 

youtube_dl/extractor/mediaset.py

@@ -42,6 +42,22 @@ class MediasetIE(InfoExtractor):
             'categories': ['reality'],
         },
         'expected_warnings': ['is not a supported codec'],
+    }, {
+        'url': 'http://www.video.mediaset.it/video/matrix/full_chiambretti/puntata-del-25-maggio_846685.html',
+        'md5': '1276f966ac423d16ba255ce867de073e',
+        'info_dict': {
+            'id': '846685',
+            'ext': 'mp4',
+            'title': 'Puntata del 25 maggio',
+            'description': 'md5:ee2e456e3eb1dba5e814596655bb5296',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 6565,
+            'creator': 'mediaset',
+            'upload_date': '20180525',
+            'series': 'Matrix',
+            'categories': ['infotainment'],
+        },
+        'expected_warnings': ['HTTP Error 403: Forbidden'],
     }, {
         # clip
         'url': 'http://www.video.mediaset.it/video/gogglebox/clip/un-grande-classico-della-commedia-sexy_661680.html',
@@ -70,16 +86,33 @@ class MediasetIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
+        video = self._download_json(
+            'https://www.video.mediaset.it/html/metainfo.sjson',
+            video_id, 'Downloading media info', query={
+                'id': video_id
+            })['video']
+
+        title = video['title']
+        media_id = video.get('guid') or video_id
+
         video_list = self._download_json(
-            'http://cdnsel01.mediaset.net/GetCdn.aspx',
+            'http://cdnsel01.mediaset.net/GetCdn2018.aspx',
             video_id, 'Downloading video CDN JSON', query={
-                'streamid': video_id,
+                'streamid': media_id,
                 'format': 'json',
             })['videoList']
 
         formats = []
         for format_url in video_list:
-            if '.ism' in format_url:
+            ext = determine_ext(format_url)
+            if ext == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    format_url, video_id, 'mp4', entry_protocol='m3u8_native',
+                    m3u8_id='hls', fatal=False))
+            elif ext == 'mpd':
+                formats.extend(self._extract_mpd_formats(
+                    format_url, video_id, mpd_id='dash', fatal=False))
+            elif ext == 'ism' or '.ism' in format_url:
                 formats.extend(self._extract_ism_formats(
                     format_url, video_id, ism_id='mss', fatal=False))
             else:
@@ -89,30 +122,23 @@ class MediasetIE(InfoExtractor):
                 })
         self._sort_formats(formats)
 
-        mediainfo = self._download_json(
-            'http://plr.video.mediaset.it/html/metainfo.sjson',
-            video_id, 'Downloading video info JSON', query={
-                'id': video_id,
-            })['video']
-
-        title = mediainfo['title']
-
         creator = try_get(
-            mediainfo, lambda x: x['brand-info']['publisher'], compat_str)
+            video, lambda x: x['brand-info']['publisher'], compat_str)
         category = try_get(
-            mediainfo, lambda x: x['brand-info']['category'], compat_str)
+            video, lambda x: x['brand-info']['category'], compat_str)
         categories = [category] if category else None
 
         return {
             'id': video_id,
             'title': title,
-            'description': mediainfo.get('short-description'),
-            'thumbnail': mediainfo.get('thumbnail'),
-            'duration': parse_duration(mediainfo.get('duration')),
+            'description': video.get('short-description'),
+            'thumbnail': video.get('thumbnail'),
+            'duration': parse_duration(video.get('duration')),
             'creator': creator,
-            'upload_date': unified_strdate(mediainfo.get('production-date')),
-            'webpage_url': mediainfo.get('url'),
-            'series': mediainfo.get('brand-value'),
+            'upload_date': unified_strdate(video.get('production-date')),
+            'webpage_url': video.get('url'),
+            'series': video.get('brand-value'),
+            'season': video.get('season'),
             'categories': categories,
             'formats': formats,
         }

youtube_dl/extractor/npo.py

@@ -282,7 +282,7 @@ class NPOIE(NPOBaseIE):
                 video_url = stream_info.get('url')
             if not video_url or video_url in urls:
                 continue
-            urls.add(item_url)
+            urls.add(video_url)
             if determine_ext(video_url) == 'm3u8':
                 formats.extend(self._extract_m3u8_formats(
                     video_url, video_id, ext='mp4',

youtube_dl/extractor/pluralsight.py

@@ -27,6 +27,60 @@ from ..utils import (
 class PluralsightBaseIE(InfoExtractor):
     _API_BASE = 'https://app.pluralsight.com'
 
+    _GRAPHQL_EP = '%s/player/api/graphql' % _API_BASE
+    _GRAPHQL_HEADERS = {
+        'Content-Type': 'application/json;charset=UTF-8',
+    }
+    _GRAPHQL_COURSE_TMPL = '''
+query BootstrapPlayer {
+  rpc {
+    bootstrapPlayer {
+      profile {
+        firstName
+        lastName
+        email
+        username
+        userHandle
+        authed
+        isAuthed
+        plan
+      }
+      course(courseId: "%s") {
+        name
+        title
+        courseHasCaptions
+        translationLanguages {
+          code
+          name
+        }
+        supportsWideScreenVideoFormats
+        timestamp
+        modules {
+          name
+          title
+          duration
+          formattedDuration
+          author
+          authorized
+          clips {
+            authorized
+            clipId
+            duration
+            formattedDuration
+            id
+            index
+            moduleIndex
+            moduleTitle
+            name
+            title
+            watched
+          }
+        }
+      }
+    }
+  }
+}'''
+
     def _download_course(self, course_id, url, display_id):
         try:
             return self._download_course_rpc(course_id, url, display_id)
@@ -39,20 +93,14 @@ class PluralsightBaseIE(InfoExtractor):
 
     def _download_course_rpc(self, course_id, url, display_id):
         response = self._download_json(
-            '%s/player/functions/rpc' % self._API_BASE, display_id,
-            'Downloading course JSON',
-            data=json.dumps({
-                'fn': 'bootstrapPlayer',
-                'payload': {
-                    'courseId': course_id,
-                },
-            }).encode('utf-8'),
-            headers={
-                'Content-Type': 'application/json;charset=utf-8',
-                'Referer': url,
-            })
+            self._GRAPHQL_EP, display_id, data=json.dumps({
+                'query': self._GRAPHQL_COURSE_TMPL % course_id,
+                'variables': {}
+            }).encode('utf-8'), headers=self._GRAPHQL_HEADERS)
 
-        course = try_get(response, lambda x: x['payload']['course'], dict)
+        course = try_get(
+            response, lambda x: x['data']['rpc']['bootstrapPlayer']['course'],
+            dict)
         if course:
             return course
 
@@ -90,6 +138,28 @@ class PluralsightIE(PluralsightBaseIE):
         'only_matching': True,
     }]
 
+    GRAPHQL_VIEWCLIP_TMPL = '''
+query viewClip {
+  viewClip(input: {
+    author: "%(author)s",
+    clipIndex: %(clipIndex)d,
+    courseName: "%(courseName)s",
+    includeCaptions: %(includeCaptions)s,
+    locale: "%(locale)s",
+    mediaType: "%(mediaType)s",
+    moduleName: "%(moduleName)s",
+    quality: "%(quality)s"
+  }) {
+    urls {
+      url
+      cdn
+      rank
+      source
+    },
+    status
+  }
+}'''
+
     def _real_initialize(self):
         self._login()
 
@@ -277,7 +347,7 @@ class PluralsightIE(PluralsightBaseIE):
                 f = QUALITIES[quality].copy()
                 clip_post = {
                     'author': author,
-                    'includeCaptions': False,
+                    'includeCaptions': 'false',
                     'clipIndex': int(clip_idx),
                     'courseName': course_name,
                     'locale': 'en',
@@ -286,11 +356,23 @@ class PluralsightIE(PluralsightBaseIE):
                     'quality': '%dx%d' % (f['width'], f['height']),
                 }
                 format_id = '%s-%s' % (ext, quality)
-                viewclip = self._download_json(
-                    '%s/video/clips/viewclip' % self._API_BASE, display_id,
-                    'Downloading %s viewclip JSON' % format_id, fatal=False,
-                    data=json.dumps(clip_post).encode('utf-8'),
-                    headers={'Content-Type': 'application/json;charset=utf-8'})
+
+                try:
+                    viewclip = self._download_json(
+                        self._GRAPHQL_EP, display_id,
+                        'Downloading %s viewclip graphql' % format_id,
+                        data=json.dumps({
+                            'query': self.GRAPHQL_VIEWCLIP_TMPL % clip_post,
+                            'variables': {}
+                        }).encode('utf-8'),
+                        headers=self._GRAPHQL_HEADERS)['data']['viewClip']
+                except ExtractorError:
+                    # Still works but most likely will go soon
+                    viewclip = self._download_json(
+                        '%s/video/clips/viewclip' % self._API_BASE, display_id,
+                        'Downloading %s viewclip JSON' % format_id, fatal=False,
+                        data=json.dumps(clip_post).encode('utf-8'),
+                        headers={'Content-Type': 'application/json;charset=utf-8'})
 
                 # Pluralsight tracks multiple sequential calls to ViewClip API and start
                 # to return 429 HTTP errors after some time (see

youtube_dl/extractor/porncom.py

@@ -43,7 +43,8 @@ class PornComIE(InfoExtractor):
 
         config = self._parse_json(
             self._search_regex(
-                r'=\s*({.+?})\s*,\s*[\da-zA-Z_]+\s*=',
+                (r'=\s*({.+?})\s*;\s*v1ar\b',
+                 r'=\s*({.+?})\s*,\s*[\da-zA-Z_]+\s*='),
                 webpage, 'config', default='{}'),
             display_id, transform_source=js_to_json, fatal=False)
 
@@ -69,7 +70,7 @@ class PornComIE(InfoExtractor):
                 'height': int(height),
                 'filesize_approx': parse_filesize(filesize),
             } for format_url, height, filesize in re.findall(
-                r'<a[^>]+href="(/download/[^"]+)">MPEG4 (\d+)p<span[^>]*>(\d+\s+[a-zA-Z]+)<',
+                r'<a[^>]+href="(/download/[^"]+)">[^<]*?(\d+)p<span[^>]*>(\d+\s*[a-zA-Z]+)<',
                 webpage)]
             thumbnail = None
             duration = None

youtube_dl/extractor/svt.py

@@ -12,6 +12,8 @@ from ..utils import (
     determine_ext,
     dict_get,
     int_or_none,
+    orderedSet,
+    strip_or_none,
     try_get,
     urljoin,
     compat_str,
@@ -137,7 +139,12 @@ class SVTPlayBaseIE(SVTBaseIE):
 
 class SVTPlayIE(SVTPlayBaseIE):
     IE_DESC = 'SVT Play and Öppet arkiv'
-    _VALID_URL = r'https?://(?:www\.)?(?:svtplay|oppetarkiv)\.se/(?:video|klipp|kanaler)/(?P<id>[^/?#&]+)'
+    _VALID_URL = r'''(?x)
+                    (?:
+                        svt:(?P<svt_id>[^/?#&]+)|
+                        https?://(?:www\.)?(?:svtplay|oppetarkiv)\.se/(?:video|klipp|kanaler)/(?P<id>[^/?#&]+)
+                    )
+                    '''
     _TESTS = [{
         'url': 'http://www.svtplay.se/video/5996901/flygplan-till-haile-selassie/flygplan-till-haile-selassie-2',
         'md5': '2b6704fe4a28801e1a098bbf3c5ac611',
@@ -164,10 +171,40 @@ class SVTPlayIE(SVTPlayBaseIE):
     }, {
         'url': 'https://www.svtplay.se/kanaler/svt1',
         'only_matching': True,
+    }, {
+        'url': 'svt:1376446-003A',
+        'only_matching': True,
+    }, {
+        'url': 'svt:14278044',
+        'only_matching': True,
     }]
 
+    def _adjust_title(self, info):
+        if info['is_live']:
+            info['title'] = self._live_title(info['title'])
+
+    def _extract_by_video_id(self, video_id, webpage=None):
+        data = self._download_json(
+            'https://api.svt.se/videoplayer-api/video/%s' % video_id,
+            video_id, headers=self.geo_verification_headers())
+        info_dict = self._extract_video(data, video_id)
+        if not info_dict.get('title'):
+            title = dict_get(info_dict, ('episode', 'series'))
+            if not title and webpage:
+                title = re.sub(
+                    r'\s*\|\s*.+?$', '', self._og_search_title(webpage))
+            if not title:
+                title = video_id
+            info_dict['title'] = title
+        self._adjust_title(info_dict)
+        return info_dict
+
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        mobj = re.match(self._VALID_URL, url)
+        video_id, svt_id = mobj.group('id', 'svt_id')
+
+        if svt_id:
+            return self._extract_by_video_id(svt_id)
 
         webpage = self._download_webpage(url, video_id)
 
@@ -179,10 +216,6 @@ class SVTPlayIE(SVTPlayBaseIE):
 
         thumbnail = self._og_search_thumbnail(webpage)
 
-        def adjust_title(info):
-            if info['is_live']:
-                info['title'] = self._live_title(info['title'])
-
         if data:
             video_info = try_get(
                 data, lambda x: x['context']['dispatcher']['stores']['VideoTitlePageStore']['data']['video'],
@@ -193,24 +226,14 @@ class SVTPlayIE(SVTPlayBaseIE):
                     'title': data['context']['dispatcher']['stores']['MetaStore']['title'],
                     'thumbnail': thumbnail,
                 })
-                adjust_title(info_dict)
+                self._adjust_title(info_dict)
                 return info_dict
 
-        video_id = self._search_regex(
+        svt_id = self._search_regex(
             r'<video[^>]+data-video-id=["\']([\da-zA-Z-]+)',
-            webpage, 'video id', default=None)
+            webpage, 'video id')
 
-        if video_id:
-            data = self._download_json(
-                'https://api.svt.se/videoplayer-api/video/%s' % video_id,
-                video_id, headers=self.geo_verification_headers())
-            info_dict = self._extract_video(data, video_id)
-            if not info_dict.get('title'):
-                info_dict['title'] = re.sub(
-                    r'\s*\|\s*.+?$', '',
-                    info_dict.get('episode') or self._og_search_title(webpage))
-            adjust_title(info_dict)
-            return info_dict
+        return self._extract_by_video_id(svt_id, webpage)
 
 
 class SVTSeriesIE(SVTPlayBaseIE):
@@ -292,3 +315,57 @@ class SVTSeriesIE(SVTPlayBaseIE):
 
         return self.playlist_result(
             entries, series_id, title, metadata.get('description'))
+
+
+class SVTPageIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?svt\.se/(?:[^/]+/)*(?P<id>[^/?&#]+)'
+    _TESTS = [{
+        'url': 'https://www.svt.se/sport/oseedat/guide-sommartraningen-du-kan-gora-var-och-nar-du-vill',
+        'info_dict': {
+            'id': 'guide-sommartraningen-du-kan-gora-var-och-nar-du-vill',
+            'title': 'GUIDE: Sommarträning du kan göra var och när du vill',
+        },
+        'playlist_count': 7,
+    }, {
+        'url': 'https://www.svt.se/nyheter/inrikes/ebba-busch-thor-kd-har-delvis-ratt-om-no-go-zoner',
+        'info_dict': {
+            'id': 'ebba-busch-thor-kd-har-delvis-ratt-om-no-go-zoner',
+            'title': 'Ebba Busch Thor har bara delvis rätt om ”no-go-zoner”',
+        },
+        'playlist_count': 1,
+    }, {
+        # only programTitle
+        'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
+        'info_dict': {
+            'id': '2900353',
+            'ext': 'mp4',
+            'title': 'Stjärnorna skojar till det - under SVT-intervjun',
+            'duration': 27,
+            'age_limit': 0,
+        },
+    }, {
+        'url': 'https://www.svt.se/nyheter/lokalt/vast/svt-testar-tar-nagon-upp-skrapet-1',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.svt.se/vader/manadskronikor/maj2018',
+        'only_matching': True,
+    }]
+
+    @classmethod
+    def suitable(cls, url):
+        return False if SVTIE.suitable(url) else super(SVTPageIE, cls).suitable(url)
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, playlist_id)
+
+        entries = [
+            self.url_result(
+                'svt:%s' % video_id, ie=SVTPlayIE.ie_key(), video_id=video_id)
+            for video_id in orderedSet(re.findall(
+                r'data-video-id=["\'](\d+)', webpage))]
+
+        title = strip_or_none(self._og_search_title(webpage, default=None))
+
+        return self.playlist_result(entries, playlist_id, title)

youtube_dl/extractor/vlive.py

@@ -57,7 +57,7 @@ class VLiveIE(InfoExtractor):
         video_id = self._match_id(url)
 
         webpage = self._download_webpage(
-            'http://www.vlive.tv/video/%s' % video_id, video_id)
+            'https://www.vlive.tv/video/%s' % video_id, video_id)
 
         VIDEO_PARAMS_RE = r'\bvlive\.video\.init\(([^)]+)'
         VIDEO_PARAMS_FIELD = 'video params'
@@ -108,11 +108,11 @@ class VLiveIE(InfoExtractor):
 
     def _live(self, video_id, webpage):
         init_page = self._download_webpage(
-            'http://www.vlive.tv/video/init/view',
+            'https://www.vlive.tv/video/init/view',
             video_id, note='Downloading live webpage',
             data=urlencode_postdata({'videoSeq': video_id}),
             headers={
-                'Referer': 'http://www.vlive.tv/video/%s' % video_id,
+                'Referer': 'https://www.vlive.tv/video/%s' % video_id,
                 'Content-Type': 'application/x-www-form-urlencoded'
             })
 

youtube_dl/options.py

@@ -841,11 +841,11 @@ def parseOpts(overrideArguments=None):
     postproc.add_option(
         '--prefer-avconv',
         action='store_false', dest='prefer_ffmpeg',
-        help='Prefer avconv over ffmpeg for running the postprocessors (default)')
+        help='Prefer avconv over ffmpeg for running the postprocessors')
     postproc.add_option(
         '--prefer-ffmpeg',
         action='store_true', dest='prefer_ffmpeg',
-        help='Prefer ffmpeg over avconv for running the postprocessors')
+        help='Prefer ffmpeg over avconv for running the postprocessors (default)')
     postproc.add_option(
         '--ffmpeg-location', '--avconv-location', metavar='PATH',
         dest='ffmpeg_location',

youtube_dl/postprocessor/ffmpeg.py

@@ -77,7 +77,7 @@ class FFmpegPostProcessor(PostProcessor):
 
     def _determine_executables(self):
         programs = ['avprobe', 'avconv', 'ffmpeg', 'ffprobe']
-        prefer_ffmpeg = False
+        prefer_ffmpeg = True
 
         self.basename = None
         self.probe_basename = None
@@ -85,7 +85,7 @@ class FFmpegPostProcessor(PostProcessor):
         self._paths = None
         self._versions = None
         if self._downloader:
-            prefer_ffmpeg = self._downloader.params.get('prefer_ffmpeg', False)
+            prefer_ffmpeg = self._downloader.params.get('prefer_ffmpeg', True)
             location = self._downloader.params.get('ffmpeg_location')
             if location is not None:
                 if not os.path.exists(location):
@@ -117,19 +117,19 @@ class FFmpegPostProcessor(PostProcessor):
                 (p, get_exe_version(p, args=['-version'])) for p in programs)
             self._paths = dict((p, p) for p in programs)
 
-        if prefer_ffmpeg:
-            prefs = ('ffmpeg', 'avconv')
-        else:
+        if prefer_ffmpeg is False:
             prefs = ('avconv', 'ffmpeg')
+        else:
+            prefs = ('ffmpeg', 'avconv')
         for p in prefs:
             if self._versions[p]:
                 self.basename = p
                 break
 
-        if prefer_ffmpeg:
-            prefs = ('ffprobe', 'avprobe')
-        else:
+        if prefer_ffmpeg is False:
             prefs = ('avprobe', 'ffprobe')
+        else:
+            prefs = ('ffprobe', 'avprobe')
         for p in prefs:
             if self._versions[p]:
                 self.probe_basename = p

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2018.06.25'
+__version__ = '2018.07.04'