release 2017.01.02

Update Readme: Set HOME properly in install command

.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 *2016.12.22*. 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 Issues with outdated version will be rejected.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 **2016.12.22**
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.01.02*. 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 Issues with outdated version will be rejected.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 **2017.01.02**
 
 ### 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 2016.12.22
+[debug] youtube-dl version 2017.01.02
 [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: {}
@@ -50,6 +50,8 @@ $ youtube-dl -v <your command line>
 - Single video: https://youtu.be/BaW_jenozKc
 - Playlist: https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc
 
+Note that **youtube-dl does not support sites dedicated to [copyright infringement](https://github.com/rg3/youtube-dl#can-you-add-support-for-this-anime-video-site-or-site-which-shows-current-movies-for-free)**. In order for site support request to be accepted all provided example URLs should not violate any copyrights.
+
 ---
 
 ### Description of your *issue*, suggested solution and other information

.github/ISSUE_TEMPLATE_tmpl.md

@@ -50,6 +50,8 @@ $ youtube-dl -v <your command line>
 - Single video: https://youtu.be/BaW_jenozKc
 - Playlist: https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc
 
+Note that **youtube-dl does not support sites dedicated to [copyright infringement](https://github.com/rg3/youtube-dl#can-you-add-support-for-this-anime-video-site-or-site-which-shows-current-movies-for-free)**. In order for site support request to be accepted all provided example URLs should not violate any copyrights.
+
 ---
 
 ### Description of your *issue*, suggested solution and other information

AUTHORS

@@ -190,3 +190,4 @@ John Hawkinson
 Rich Leeper
 Zhong Jianxin
 Thor77
+Mattias Wadman

CONTRIBUTING.md

@@ -58,7 +58,7 @@ We are then presented with a very complicated request when the original problem
 
 Some of our users seem to think there is a limit of issues they can or should open. There is no limit of issues they can or should open. While it may seem appealing to be able to dump all your issues into one ticket, that means that someone who solves one of your issues cannot mark the issue as closed. Typically, reporting a bunch of issues leads to the ticket lingering since nobody wants to attack that behemoth, until someone mercifully splits the issue into multiple ones.
 
-In particular, every site support request issue should only pertain to services at one site (generally under a common domain, but always using the same backend technology). Do not request support for vimeo user videos, Whitehouse podcasts, and Google Plus pages in the same issue. Also, make sure that you don't post bug reports alongside feature requests. As a rule of thumb, a feature request does not include outputs of youtube-dl that are not immediately related to the feature at hand. Do not post reports of a network error alongside the request for a new video service.
+In particular, every site support request issue should only pertain to services at one site (generally under a common domain, but always using the same backend technology). Do not request support for vimeo user videos, White house podcasts, and Google Plus pages in the same issue. Also, make sure that you don't post bug reports alongside feature requests. As a rule of thumb, a feature request does not include outputs of youtube-dl that are not immediately related to the feature at hand. Do not post reports of a network error alongside the request for a new video service.
 
 ###  Is anyone going to need the feature?
 
@@ -94,7 +94,7 @@ If you want to create a build of youtube-dl yourself, you'll need
 
 If you want to add support for a new site, first of all **make sure** this site is **not dedicated to [copyright infringement](README.md#can-you-add-support-for-this-anime-video-site-or-site-which-shows-current-movies-for-free)**. youtube-dl does **not support** such sites thus pull requests adding support for them **will be rejected**.
 
-After you have ensured this site is distributing it's content legally, you can follow this quick list (assuming your service is called `yourextractor`):
+After you have ensured this site is distributing its content legally, you can follow this quick list (assuming your service is called `yourextractor`):
 
 1. [Fork this repository](https://github.com/rg3/youtube-dl/fork)
 2. Check out the source code with:
@@ -199,7 +199,7 @@ Assume at this point `meta`'s layout is:
 }
 ```
 
-Assume you want to extract `summary` and put it into the resulting info dict as `description`. Since `description` is an optional metafield you should be ready that this key may be missing from the `meta` dict, so that you should extract it like:
+Assume you want to extract `summary` and put it into the resulting info dict as `description`. Since `description` is an optional meta field you should be ready that this key may be missing from the `meta` dict, so that you should extract it like:
 
 ```python
 description = meta.get('summary')  # correct

ChangeLog

@@ -1,3 +1,31 @@
+version 2017.01.02
+
+Extractors
+* [cctv] Improve extraction (#879, #6753, #8541)
++ [nrktv:episodes] Add support for episodes (#11571)
++ [arkena] Add support for video.arkena.com (#11568)
+
+
+version 2016.12.31
+
+Core
++ Introduce --config-location option for custom configuration files (#6745,
+  #10648)
+
+Extractors
++ [twitch] Add support for player.twitch.tv (#11535, #11537)
++ [videa] Add support for videa.hu (#8181, #11133)
+* [vk] Fix postlive videos extraction
+* [vk] Extract from playerParams (#11555)
+- [freevideo] Remove extractor (#11515)
++ [showroomlive] Add support for showroom-live.com (#11458)
+* [xhamster] Fix duration extraction (#11549)
+* [rtve:live] Fix extraction (#11529)
+* [brightcove:legacy] Improve embeds detection (#11523)
++ [twitch] Add support for rechat messages (#11524)
+* [acast] Fix audio and timestamp extraction (#11521)
+
+
 version 2016.12.22
 
 Core

README.md

@@ -29,7 +29,7 @@ Windows users can [download an .exe file](https://yt-dl.org/latest/youtube-dl.ex
 
 You can also use pip:
 
-    sudo pip install --upgrade youtube-dl
+    sudo -H pip install --upgrade youtube-dl
     
 This command will update youtube-dl if you have already installed it. See the [pypi page](https://pypi.python.org/pypi/youtube_dl) for more information.
 
@@ -44,11 +44,7 @@ Or with [MacPorts](https://www.macports.org/):
 Alternatively, refer to the [developer instructions](#developer-instructions) for how to check out and work with the git repository. For further options, including PGP signatures, see the [youtube-dl Download Page](https://rg3.github.io/youtube-dl/download.html).
 
 # DESCRIPTION
-**youtube-dl** is a command-line program to download videos from
-YouTube.com and a few more sites. It requires the Python interpreter, version
-2.6, 2.7, or 3.2+, and it is not platform specific. It should work on
-your Unix box, on Windows or on Mac OS X. It is released to the public domain,
-which means you can modify it, redistribute it or use it however you like.
+**youtube-dl** is a command-line program to download videos from YouTube.com and a few more sites. It requires the Python interpreter, version 2.6, 2.7, or 3.2+, and it is not platform specific. It should work on your Unix box, on Windows or on Mac OS X. It is released to the public domain, which means you can modify it, redistribute it or use it however you like.
 
     youtube-dl [OPTIONS] URL [URL...]
 
@@ -84,6 +80,9 @@ which means you can modify it, redistribute it or use it however you like.
                                      configuration in ~/.config/youtube-
                                      dl/config (%APPDATA%/youtube-dl/config.txt
                                      on Windows)
+    --config-location PATH           Location of the configuration file; either
+                                     the path to the config or its containing
+                                     directory.
     --flat-playlist                  Do not extract the videos of a playlist,
                                      only list them.
     --mark-watched                   Mark videos watched (YouTube only)
@@ -187,7 +186,7 @@ which means you can modify it, redistribute it or use it however you like.
                                      of SIZE.
     --playlist-reverse               Download playlist videos in reverse order
     --xattr-set-filesize             Set file xattribute ytdl.filesize with
-                                     expected filesize (experimental)
+                                     expected file size (experimental)
     --hls-prefer-native              Use the native HLS downloader instead of
                                      ffmpeg
     --hls-prefer-ffmpeg              Use ffmpeg instead of the native HLS
@@ -354,7 +353,7 @@ which means you can modify it, redistribute it or use it however you like.
     -u, --username USERNAME          Login with this account ID
     -p, --password PASSWORD          Account password. If this option is left
                                      out, youtube-dl will ask interactively.
-    -2, --twofactor TWOFACTOR        Two-factor auth code
+    -2, --twofactor TWOFACTOR        Two-factor authentication code
     -n, --netrc                      Use .netrc authentication data
     --video-password PASSWORD        Video password (vimeo, smotri, youku)
 
@@ -638,7 +637,7 @@ Also filtering work for comparisons `=` (equals), `!=` (not equals), `^=` (begin
  - `acodec`: Name of the audio codec in use
  - `vcodec`: Name of the video codec in use
  - `container`: Name of the container format
- - `protocol`: The protocol that will be used for the actual download, lower-case. `http`, `https`, `rtsp`, `rtmp`, `rtmpe`, `m3u8`, or `m3u8_native`
+ - `protocol`: The protocol that will be used for the actual download, lower-case (`http`, `https`, `rtsp`, `rtmp`, `rtmpe`, `mms`, `f4m`, `ism`, `m3u8`, or `m3u8_native`)
  - `format_id`: A short description of the format
 
 Note that none of the aforementioned meta fields are guaranteed to be present since this solely depends on the metadata obtained by particular extractor, i.e. the metadata offered by the video hoster.
@@ -744,7 +743,7 @@ Most people asking this question are not aware that youtube-dl now defaults to d
 
 ### I get HTTP error 402 when trying to download a video. What's this?
 
-Apparently YouTube requires you to pass a CAPTCHA test if you download too much. We're [considering to provide a way to let you solve the CAPTCHA](https://github.com/rg3/youtube-dl/issues/154), but at the moment, your best course of action is pointing a webbrowser to the youtube URL, solving the CAPTCHA, and restart youtube-dl.
+Apparently YouTube requires you to pass a CAPTCHA test if you download too much. We're [considering to provide a way to let you solve the CAPTCHA](https://github.com/rg3/youtube-dl/issues/154), but at the moment, your best course of action is pointing a web browser to the youtube URL, solving the CAPTCHA, and restart youtube-dl.
 
 ### Do I need any other programs?
 
@@ -756,7 +755,7 @@ Videos or video formats streamed via RTMP protocol can only be downloaded when [
 
 Once the video is fully downloaded, use any video player, such as [mpv](https://mpv.io/), [vlc](http://www.videolan.org/) or [mplayer](http://www.mplayerhq.hu/).
 
-### I extracted a video URL with `-g`, but it does not play on another machine / in my webbrowser.
+### I extracted a video URL with `-g`, but it does not play on another machine / in my web browser.
 
 It depends a lot on the service. In many cases, requests for the video (to download/play it) must come from the same IP address and with the same cookies and/or HTTP headers. Use the `--cookies` option to write the required cookies into a file, and advise your downloader to read cookies from that file. Some sites also require a common user agent to be used, use `--dump-user-agent` to see the one in use by youtube-dl. You can also get necessary cookies and HTTP headers from JSON output obtained with `--dump-json`.
 
@@ -932,7 +931,7 @@ If you want to create a build of youtube-dl yourself, you'll need
 
 If you want to add support for a new site, first of all **make sure** this site is **not dedicated to [copyright infringement](README.md#can-you-add-support-for-this-anime-video-site-or-site-which-shows-current-movies-for-free)**. youtube-dl does **not support** such sites thus pull requests adding support for them **will be rejected**.
 
-After you have ensured this site is distributing it's content legally, you can follow this quick list (assuming your service is called `yourextractor`):
+After you have ensured this site is distributing its content legally, you can follow this quick list (assuming your service is called `yourextractor`):
 
 1. [Fork this repository](https://github.com/rg3/youtube-dl/fork)
 2. Check out the source code with:
@@ -1037,7 +1036,7 @@ Assume at this point `meta`'s layout is:
 }
 ```
 
-Assume you want to extract `summary` and put it into the resulting info dict as `description`. Since `description` is an optional metafield you should be ready that this key may be missing from the `meta` dict, so that you should extract it like:
+Assume you want to extract `summary` and put it into the resulting info dict as `description`. Since `description` is an optional meta field you should be ready that this key may be missing from the `meta` dict, so that you should extract it like:
 
 ```python
 description = meta.get('summary')  # correct
@@ -1149,7 +1148,7 @@ with youtube_dl.YoutubeDL(ydl_opts) as ydl:
     ydl.download(['http://www.youtube.com/watch?v=BaW_jenozKc'])
 ```
 
-Most likely, you'll want to use various options. For a list of options available, have a look at [`youtube_dl/YoutubeDL.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/YoutubeDL.py#L128-L278). For a start, if you want to intercept youtube-dl's output, set a `logger` object.
+Most likely, you'll want to use various options. For a list of options available, have a look at [`youtube_dl/YoutubeDL.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/YoutubeDL.py#L129-L279). For a start, if you want to intercept youtube-dl's output, set a `logger` object.
 
 Here's a more complete example of a program that outputs only errors (and a short message after the download is finished), and downloads/converts the video to an mp3 file:
 
@@ -1252,7 +1251,7 @@ We are then presented with a very complicated request when the original problem
 
 Some of our users seem to think there is a limit of issues they can or should open. There is no limit of issues they can or should open. While it may seem appealing to be able to dump all your issues into one ticket, that means that someone who solves one of your issues cannot mark the issue as closed. Typically, reporting a bunch of issues leads to the ticket lingering since nobody wants to attack that behemoth, until someone mercifully splits the issue into multiple ones.
 
-In particular, every site support request issue should only pertain to services at one site (generally under a common domain, but always using the same backend technology). Do not request support for vimeo user videos, Whitehouse podcasts, and Google Plus pages in the same issue. Also, make sure that you don't post bug reports alongside feature requests. As a rule of thumb, a feature request does not include outputs of youtube-dl that are not immediately related to the feature at hand. Do not post reports of a network error alongside the request for a new video service.
+In particular, every site support request issue should only pertain to services at one site (generally under a common domain, but always using the same backend technology). Do not request support for vimeo user videos, White house podcasts, and Google Plus pages in the same issue. Also, make sure that you don't post bug reports alongside feature requests. As a rule of thumb, a feature request does not include outputs of youtube-dl that are not immediately related to the feature at hand. Do not post reports of a network error alongside the request for a new video service.
 
 ###  Is anyone going to need the feature?
 

devscripts/buildserver.py

@@ -424,8 +424,6 @@ class BuildHTTPRequestHandler(compat_http_server.BaseHTTPRequestHandler):
                     self.send_header('Content-Length', len(msg))
                     self.end_headers()
                     self.wfile.write(msg)
-                except HTTPError as e:
-                    self.send_response(e.code, str(e))
             else:
                 self.send_response(500, 'Unknown build method "%s"' % action)
         else:

docs/supportedsites.md

@@ -132,7 +132,7 @@
  - **cbsnews:livevideo**: CBS News Live Videos
  - **CBSSports**
  - **CCMA**
- - **CCTV**
+ - **CCTV**: 央视网
  - **CDA**
  - **CeskaTelevize**
  - **channel9**: Channel 9
@@ -263,7 +263,6 @@
  - **francetvinfo.fr**
  - **Freesound**
  - **freespeech.org**
- - **FreeVideo**
  - **Funimation**
  - **FunnyOrDie**
  - **Fusion**
@@ -518,6 +517,7 @@
  - **NRKSkole**: NRK Skole
  - **NRKTV**: NRK TV and NRK Radio
  - **NRKTVDirekte**: NRK TV Direkte and NRK Radio Direkte
+ - **NRKTVEpisodes**
  - **ntv.ru**
  - **Nuvid**
  - **NYTimes**
@@ -659,6 +659,7 @@
  - **Shahid**
  - **Shared**: shared.sx
  - **ShareSix**
+ - **ShowRoomLive**
  - **Sina**
  - **SixPlay**
  - **skynewsarabia:article**
@@ -834,6 +835,7 @@
  - **ViceShow**
  - **Vidbit**
  - **Viddler**
+ - **Videa**
  - **video.google:search**: Google Video search
  - **video.mit.edu**
  - **VideoDetective**

youtube_dl/__init__.py

@@ -405,7 +405,7 @@ def _real_main(argv=None):
         'postprocessor_args': postprocessor_args,
         'cn_verification_proxy': opts.cn_verification_proxy,
         'geo_verification_proxy': opts.geo_verification_proxy,
-
+        'config_location': opts.config_location,
     }
 
     with YoutubeDL(ydl_opts) as ydl:

youtube_dl/extractor/acast.py

@@ -8,6 +8,7 @@ from .common import InfoExtractor
 from ..compat import compat_str
 from ..utils import (
     int_or_none,
+    parse_iso8601,
     OnDemandPagedList,
 )
 
@@ -15,18 +16,33 @@ from ..utils import (
 class ACastIE(InfoExtractor):
     IE_NAME = 'acast'
     _VALID_URL = r'https?://(?:www\.)?acast\.com/(?P<channel>[^/]+)/(?P<id>[^/#?]+)'
-    _TEST = {
+    _TESTS = [{
+        # test with one bling
         'url': 'https://www.acast.com/condenasttraveler/-where-are-you-taipei-101-taiwan',
         'md5': 'ada3de5a1e3a2a381327d749854788bb',
         'info_dict': {
             'id': '57de3baa-4bb0-487e-9418-2692c1277a34',
             'ext': 'mp3',
             'title': '"Where Are You?": Taipei 101, Taiwan',
-            'timestamp': 1196172000000,
+            'timestamp': 1196172000,
+            'upload_date': '20071127',
             'description': 'md5:a0b4ef3634e63866b542e5b1199a1a0e',
             'duration': 211,
         }
-    }
+    }, {
+        # test with multiple blings
+        'url': 'https://www.acast.com/sparpodcast/2.raggarmordet-rosterurdetforflutna',
+        'md5': '55c0097badd7095f494c99a172f86501',
+        'info_dict': {
+            'id': '2a92b283-1a75-4ad8-8396-499c641de0d9',
+            'ext': 'mp3',
+            'title': '2. Raggarmordet - Röster ur det förflutna',
+            'timestamp': 1477346700,
+            'upload_date': '20161024',
+            'description': 'md5:4f81f6d8cf2e12ee21a321d8bca32db4',
+            'duration': 2797,
+        }
+    }]
 
     def _real_extract(self, url):
         channel, display_id = re.match(self._VALID_URL, url).groups()
@@ -35,11 +51,11 @@ class ACastIE(InfoExtractor):
         return {
             'id': compat_str(cast_data['id']),
             'display_id': display_id,
-            'url': cast_data['blings'][0]['audio'],
+            'url': [b['audio'] for b in cast_data['blings'] if b['type'] == 'BlingAudio'][0],
             'title': cast_data['name'],
             'description': cast_data.get('description'),
             'thumbnail': cast_data.get('image'),
-            'timestamp': int_or_none(cast_data.get('publishingDate')),
+            'timestamp': parse_iso8601(cast_data.get('publishingDate')),
             'duration': int_or_none(cast_data.get('duration')),
         }
 

youtube_dl/extractor/arkena.py

@@ -4,8 +4,10 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_urlparse
 from ..utils import (
     determine_ext,
+    ExtractorError,
     float_or_none,
     int_or_none,
     mimetype2ext,
@@ -15,7 +17,13 @@ from ..utils import (
 
 
 class ArkenaIE(InfoExtractor):
-    _VALID_URL = r'https?://play\.arkena\.com/(?:config|embed)/avp/v\d/player/media/(?P<id>[^/]+)/[^/]+/(?P<account_id>\d+)'
+    _VALID_URL = r'''(?x)
+                        https?://
+                            (?:
+                                video\.arkena\.com/play2/embed/player\?|
+                                play\.arkena\.com/(?:config|embed)/avp/v\d/player/media/(?P<id>[^/]+)/[^/]+/(?P<account_id>\d+)
+                            )
+                        '''
     _TESTS = [{
         'url': 'https://play.arkena.com/embed/avp/v2/player/media/b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe/1/129411',
         'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
@@ -37,6 +45,9 @@ class ArkenaIE(InfoExtractor):
     }, {
         'url': 'http://play.arkena.com/embed/avp/v1/player/media/327336/darkmatter/131064/',
         'only_matching': True,
+    }, {
+        'url': 'http://video.arkena.com/play2/embed/player?accountId=472718&mediaId=35763b3b-00090078-bf604299&pageStyling=styled',
+        'only_matching': True,
     }]
 
     @staticmethod
@@ -53,6 +64,14 @@ class ArkenaIE(InfoExtractor):
         video_id = mobj.group('id')
         account_id = mobj.group('account_id')
 
+        # Handle http://video.arkena.com/play2/embed/player URL
+        if not video_id:
+            qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
+            video_id = qs.get('mediaId', [None])[0]
+            account_id = qs.get('accountId', [None])[0]
+            if not video_id or not account_id:
+                raise ExtractorError('Invalid URL', expected=True)
+
         playlist = self._download_json(
             'https://play.arkena.com/config/avp/v2/player/media/%s/0/%s/?callbackMethod=_'
             % (video_id, account_id),

youtube_dl/extractor/brightcove.py

@@ -232,13 +232,16 @@ class BrightcoveLegacyIE(InfoExtractor):
         """Return a list of all Brightcove URLs from the webpage """
 
         url_m = re.search(
-            r'<meta\s+property=[\'"]og:video[\'"]\s+content=[\'"](https?://(?:secure|c)\.brightcove.com/[^\'"]+)[\'"]',
-            webpage)
+            r'''(?x)
+                <meta\s+
+                    (?:property|itemprop)=([\'"])(?:og:video|embedURL)\1[^>]+
+                    content=([\'"])(?P<url>https?://(?:secure|c)\.brightcove.com/(?:(?!\2).)+)\2
+            ''', webpage)
         if url_m:
-            url = unescapeHTML(url_m.group(1))
+            url = unescapeHTML(url_m.group('url'))
             # Some sites don't add it, we can't download with this url, for example:
             # http://www.ktvu.com/videos/news/raw-video-caltrain-releases-video-of-man-almost/vCTZdY/
-            if 'playerKey' in url or 'videoId' in url:
+            if 'playerKey' in url or 'videoId' in url or 'idVideo' in url:
                 return [url]
 
         matches = re.findall(
@@ -259,7 +262,7 @@ class BrightcoveLegacyIE(InfoExtractor):
         url, smuggled_data = unsmuggle_url(url, {})
 
         # Change the 'videoId' and others field to '@videoPlayer'
-        url = re.sub(r'(?<=[?&])(videoI(d|D)|bctid)', '%40videoPlayer', url)
+        url = re.sub(r'(?<=[?&])(videoI(d|D)|idVideo|bctid)', '%40videoPlayer', url)
         # Change bckey (used by bcove.me urls) to playerKey
         url = re.sub(r'(?<=[?&])bckey', 'playerKey', url)
         mobj = re.match(self._VALID_URL, url)

youtube_dl/extractor/cctv.py

@@ -4,27 +4,84 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import float_or_none
+from ..compat import compat_str
+from ..utils import (
+    float_or_none,
+    try_get,
+    unified_timestamp,
+)
 
 
 class CCTVIE(InfoExtractor):
-    _VALID_URL = r'''(?x)https?://(?:.+?\.)?
-        (?:
-            cctv\.(?:com|cn)|
-            cntv\.cn
-        )/
-        (?:
-            video/[^/]+/(?P<id>[0-9a-f]{32})|
-            \d{4}/\d{2}/\d{2}/(?P<display_id>VID[0-9A-Za-z]+)
-        )'''
+    IE_DESC = '央视网'
+    _VALID_URL = r'https?://(?:[^/]+)\.(?:cntv|cctv)\.(?:com|cn)/(?:[^/]+/)*?(?P<id>[^/?#&]+?)(?:/index)?(?:\.s?html|[?#&]|$)'
     _TESTS = [{
-        'url': 'http://english.cntv.cn/2016/09/03/VIDEhnkB5y9AgHyIEVphCEz1160903.shtml',
-        'md5': '819c7b49fc3927d529fb4cd555621823',
+        'url': 'http://sports.cntv.cn/2016/02/12/ARTIaBRxv4rTT1yWf1frW2wi160212.shtml',
+        'md5': 'd61ec00a493e09da810bf406a078f691',
         'info_dict': {
-            'id': '454368eb19ad44a1925bf1eb96140a61',
+            'id': '5ecdbeab623f4973b40ff25f18b174e8',
             'ext': 'mp4',
-            'title': 'Portrait of Real Current Life 09/03/2016 Modern Inventors Part 1',
-        }
+            'title': '[NBA]二少联手砍下46分 雷霆主场击败鹈鹕（快讯）',
+            'description': 'md5:7e14a5328dc5eb3d1cd6afbbe0574e95',
+            'duration': 98,
+            'uploader': 'songjunjie',
+            'timestamp': 1455279956,
+            'upload_date': '20160212',
+        },
+    }, {
+        'url': 'http://tv.cctv.com/2016/02/05/VIDEUS7apq3lKrHG9Dncm03B160205.shtml',
+        'info_dict': {
+            'id': 'efc5d49e5b3b4ab2b34f3a502b73d3ae',
+            'ext': 'mp4',
+            'title': '[赛车]“车王”舒马赫恢复情况成谜（快讯）',
+            'description': '2月4日，蒙特泽莫罗透露了关于“车王”舒马赫恢复情况，但情况是否属实遭到了质疑。',
+            'duration': 37,
+            'uploader': 'shujun',
+            'timestamp': 1454677291,
+            'upload_date': '20160205',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://english.cntv.cn/special/four_comprehensives/index.shtml',
+        'info_dict': {
+            'id': '4bb9bb4db7a6471ba85fdeda5af0381e',
+            'ext': 'mp4',
+            'title': 'NHnews008 ANNUAL POLITICAL SEASON',
+            'description': 'Four Comprehensives',
+            'duration': 60,
+            'uploader': 'zhangyunlei',
+            'timestamp': 1425385521,
+            'upload_date': '20150303',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://cctv.cntv.cn/lm/tvseries_russian/yilugesanghua/index.shtml',
+        'info_dict': {
+            'id': 'b15f009ff45c43968b9af583fc2e04b2',
+            'ext': 'mp4',
+            'title': 'Путь，усыпанный космеями Серия 1',
+            'description': 'Путь, усыпанный космеями',
+            'duration': 2645,
+            'uploader': 'renxue',
+            'timestamp': 1477479241,
+            'upload_date': '20161026',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://ent.cntv.cn/2016/01/18/ARTIjprSSJH8DryTVr5Bx8Wb160118.shtml',
+        'only_matching': True,
+    }, {
+        'url': 'http://tv.cntv.cn/video/C39296/e0210d949f113ddfb38d31f00a4e5c44',
+        'only_matching': True,
+    }, {
+        'url': 'http://english.cntv.cn/2016/09/03/VIDEhnkB5y9AgHyIEVphCEz1160903.shtml',
+        'only_matching': True,
     }, {
         'url': 'http://tv.cctv.com/2016/09/07/VIDE5C1FnlX5bUywlrjhxXOV160907.shtml',
         'only_matching': True,
@@ -34,20 +91,63 @@ class CCTVIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        video_id, display_id = re.match(self._VALID_URL, url).groups()
-        if not video_id:
-            webpage = self._download_webpage(url, display_id)
-            video_id = self._search_regex(
-                r'(?:fo\.addVariable\("videoCenterId",\s*|guid\s*=\s*)"([0-9a-f]{32})',
-                webpage, 'video_id')
-        api_data = self._download_json(
-            'http://vdn.apps.cntv.cn/api/getHttpVideoInfo.do?pid=' + video_id, video_id)
-        m3u8_url = re.sub(r'maxbr=\d+&?', '', api_data['hls_url'])
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        video_id = self._search_regex(
+            [r'var\s+guid\s*=\s*["\']([\da-fA-F]+)',
+             r'videoCenterId["\']\s*,\s*["\']([\da-fA-F]+)',
+             r'"changePlayer\s*\(\s*["\']([\da-fA-F]+)',
+             r'"load[Vv]ideo\s*\(\s*["\']([\da-fA-F]+)'],
+            webpage, 'video id')
+
+        data = self._download_json(
+            'http://vdn.apps.cntv.cn/api/getHttpVideoInfo.do', video_id,
+            query={
+                'pid': video_id,
+                'url': url,
+                'idl': 32,
+                'idlr': 32,
+                'modifyed': 'false',
+            })
+
+        title = data['title']
+
+        formats = []
+
+        video = data.get('video')
+        if isinstance(video, dict):
+            for quality, chapters_key in enumerate(('lowChapters', 'chapters')):
+                video_url = try_get(
+                    video, lambda x: x[chapters_key][0]['url'], compat_str)
+                if video_url:
+                    formats.append({
+                        'url': video_url,
+                        'format_id': 'http',
+                        'quality': quality,
+                        'preference': -1,
+                    })
+
+        hls_url = try_get(data, lambda x: x['hls_url'], compat_str)
+        if hls_url:
+            hls_url = re.sub(r'maxbr=\d+&?', '', hls_url)
+            formats.extend(self._extract_m3u8_formats(
+                hls_url, video_id, 'mp4', entry_protocol='m3u8_native',
+                m3u8_id='hls', fatal=False))
+
+        self._sort_formats(formats)
+
+        uploader = data.get('editer_name')
+        description = self._html_search_meta('description', webpage)
+        timestamp = unified_timestamp(data.get('f_pgmtime'))
+        duration = float_or_none(try_get(video, lambda x: x['totalLength']))
 
         return {
             'id': video_id,
-            'title': api_data['title'],
-            'formats': self._extract_m3u8_formats(
-                m3u8_url, video_id, 'mp4', 'm3u8_native', fatal=False),
-            'duration': float_or_none(api_data.get('video', {}).get('totalLength')),
+            'title': title,
+            'description': description,
+            'uploader': uploader,
+            'timestamp': timestamp,
+            'duration': duration,
+            'formats': formats,
         }

youtube_dl/extractor/common.py

@@ -189,9 +189,10 @@ class InfoExtractor(object):
     uploader_url:   Full URL to a personal webpage of the video uploader.
     location:       Physical location where the video was filmed.
     subtitles:      The available subtitles as a dictionary in the format
-                    {language: subformats}. "subformats" is a list sorted from
-                    lower to higher preference, each element is a dictionary
-                    with the "ext" entry and one of:
+                    {tag: subformats}. "tag" is usually a language code, and
+                    "subformats" is a list sorted from lower to higher
+                    preference, each element is a dictionary with the "ext"
+                    entry and one of:
                         * "data": The subtitles file contents
                         * "url": A URL pointing to the subtitles file
                     "ext" will be calculated from URL if missing

youtube_dl/extractor/extractors.py

@@ -320,7 +320,6 @@ from .francetv import (
 )
 from .freesound import FreesoundIE
 from .freespeech import FreespeechIE
-from .freevideo import FreeVideoIE
 from .funimation import FunimationIE
 from .funnyordie import FunnyOrDieIE
 from .fusion import FusionIE
@@ -656,6 +655,7 @@ from .nrk import (
     NRKSkoleIE,
     NRKTVIE,
     NRKTVDirekteIE,
+    NRKTVEpisodesIE,
 )
 from .ntvde import NTVDeIE
 from .ntvru import NTVRuIE
@@ -825,6 +825,7 @@ from .shared import (
     VivoIE,
 )
 from .sharesix import ShareSixIE
+from .showroomlive import ShowRoomLiveIE
 from .sina import SinaIE
 from .sixplay import SixPlayIE
 from .skynewsarabia import (
@@ -1064,6 +1065,7 @@ from .vice import (
 from .viceland import VicelandIE
 from .vidbit import VidbitIE
 from .viddler import ViddlerIE
+from .videa import VideaIE
 from .videodetective import VideoDetectiveIE
 from .videofyme import VideofyMeIE
 from .videomega import VideoMegaIE

youtube_dl/extractor/freevideo.py

@@ -1,38 +0,0 @@
-from __future__ import unicode_literals
-
-from .common import InfoExtractor
-from ..utils import ExtractorError
-
-
-class FreeVideoIE(InfoExtractor):
-    _VALID_URL = r'^https?://www.freevideo.cz/vase-videa/(?P<id>[^.]+)\.html(?:$|[?#])'
-
-    _TEST = {
-        'url': 'http://www.freevideo.cz/vase-videa/vysukany-zadecek-22033.html',
-        'info_dict': {
-            'id': 'vysukany-zadecek-22033',
-            'ext': 'mp4',
-            'title': 'vysukany-zadecek-22033',
-            'age_limit': 18,
-        },
-        'skip': 'Blocked outside .cz',
-    }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage, handle = self._download_webpage_handle(url, video_id)
-        if '//www.czechav.com/' in handle.geturl():
-            raise ExtractorError(
-                'Access to freevideo is blocked from your location',
-                expected=True)
-
-        video_url = self._search_regex(
-            r'\s+url: "(http://[a-z0-9-]+.cdn.freevideo.cz/stream/.*?/video.mp4)"',
-            webpage, 'video URL')
-
-        return {
-            'id': video_id,
-            'url': video_url,
-            'title': video_id,
-            'age_limit': 18,
-        }

youtube_dl/extractor/generic.py

@@ -76,6 +76,7 @@ from .soundcloud import SoundcloudIE
 from .vbox7 import Vbox7IE
 from .dbtv import DBTVIE
 from .piksel import PikselIE
+from .videa import VideaIE
 
 
 class GenericIE(InfoExtractor):
@@ -344,10 +345,10 @@ class GenericIE(InfoExtractor):
             },
             'skip': 'There is a limit of 200 free downloads / month for the test song',
         },
-        # embedded brightcove video
-        # it also tests brightcove videos that need to set the 'Referer' in the
-        # http requests
         {
+            # embedded brightcove video
+            # it also tests brightcove videos that need to set the 'Referer'
+            # in the http requests
             'add_ie': ['BrightcoveLegacy'],
             'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
             'info_dict': {
@@ -361,6 +362,24 @@ class GenericIE(InfoExtractor):
                 'skip_download': True,
             },
         },
+        {
+            # embedded with itemprop embedURL and video id spelled as `idVideo`
+            'add_id': ['BrightcoveLegacy'],
+            'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
+            'info_dict': {
+                'id': '5255628253001',
+                'ext': 'mp4',
+                'title': 'md5:37c519b1128915607601e75a87995fc0',
+                'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
+                'uploader': 'BFM BUSINESS',
+                'uploader_id': '876450612001',
+                'timestamp': 1482255315,
+                'upload_date': '20161220',
+            },
+            'params': {
+                'skip_download': True,
+            },
+        },
         {
             # https://github.com/rg3/youtube-dl/issues/2253
             'url': 'http://bcove.me/i6nfkrc3',
@@ -1404,6 +1423,15 @@ class GenericIE(InfoExtractor):
             },
             'playlist_mincount': 3,
         },
+        {
+            # Videa embeds
+            'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
+            'info_dict': {
+                'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
+                'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
+            },
+            'playlist_mincount': 2,
+        },
         # {
         #     # TODO: find another test
         #     # http://schema.org/VideoObject
@@ -2340,6 +2368,11 @@ class GenericIE(InfoExtractor):
         if dbtv_urls:
             return _playlist_from_matches(dbtv_urls, ie=DBTVIE.ie_key())
 
+        # Look for Videa embeds
+        videa_urls = VideaIE._extract_urls(webpage)
+        if videa_urls:
+            return _playlist_from_matches(videa_urls, ie=VideaIE.ie_key())
+
         # Looking for http://schema.org/VideoObject
         json_ld = self._search_json_ld(
             webpage, video_id, default={}, expected_type='VideoObject')

youtube_dl/extractor/nrk.py

@@ -207,7 +207,15 @@ class NRKIE(NRKBaseIE):
 
 class NRKTVIE(NRKBaseIE):
     IE_DESC = 'NRK TV and NRK Radio'
-    _VALID_URL = r'https?://(?:tv|radio)\.nrk(?:super)?\.no/(?:serie/[^/]+|program)/(?P<id>[a-zA-Z]{4}\d{8})(?:/\d{2}-\d{2}-\d{4})?(?:#del=(?P<part_id>\d+))?'
+    _EPISODE_RE = r'(?P<id>[a-zA-Z]{4}\d{8})'
+    _VALID_URL = r'''(?x)
+                        https?://
+                            (?:tv|radio)\.nrk(?:super)?\.no/
+                            (?:serie/[^/]+|program)/
+                            (?![Ee]pisodes)%s
+                            (?:/\d{2}-\d{2}-\d{4})?
+                            (?:\#del=(?P<part_id>\d+))?
+                    ''' % _EPISODE_RE
     _API_HOST = 'psapi-we.nrk.no'
 
     _TESTS = [{
@@ -286,9 +294,30 @@ class NRKTVDirekteIE(NRKTVIE):
     }]
 
 
-class NRKPlaylistIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?nrk\.no/(?!video|skole)(?:[^/]+/)+(?P<id>[^/]+)'
+class NRKPlaylistBaseIE(InfoExtractor):
+    def _extract_description(self, webpage):
+        pass
 
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, playlist_id)
+
+        entries = [
+            self.url_result('nrk:%s' % video_id, NRKIE.ie_key())
+            for video_id in re.findall(self._ITEM_RE, webpage)
+        ]
+
+        playlist_title = self. _extract_title(webpage)
+        playlist_description = self._extract_description(webpage)
+
+        return self.playlist_result(
+            entries, playlist_id, playlist_title, playlist_description)
+
+
+class NRKPlaylistIE(NRKPlaylistBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?nrk\.no/(?!video|skole)(?:[^/]+/)+(?P<id>[^/]+)'
+    _ITEM_RE = r'class="[^"]*\brich\b[^"]*"[^>]+data-video-id="([^"]+)"'
     _TESTS = [{
         'url': 'http://www.nrk.no/troms/gjenopplev-den-historiske-solformorkelsen-1.12270763',
         'info_dict': {
@@ -307,23 +336,28 @@ class NRKPlaylistIE(InfoExtractor):
         'playlist_count': 5,
     }]
 
-    def _real_extract(self, url):
-        playlist_id = self._match_id(url)
+    def _extract_title(self, webpage):
+        return self._og_search_title(webpage, fatal=False)
 
-        webpage = self._download_webpage(url, playlist_id)
+    def _extract_description(self, webpage):
+        return self._og_search_description(webpage)
 
-        entries = [
-            self.url_result('nrk:%s' % video_id, 'NRK')
-            for video_id in re.findall(
-                r'class="[^"]*\brich\b[^"]*"[^>]+data-video-id="([^"]+)"',
-                webpage)
-        ]
 
-        playlist_title = self._og_search_title(webpage)
-        playlist_description = self._og_search_description(webpage)
+class NRKTVEpisodesIE(NRKPlaylistBaseIE):
+    _VALID_URL = r'https?://tv\.nrk\.no/program/[Ee]pisodes/[^/]+/(?P<id>\d+)'
+    _ITEM_RE = r'data-episode=["\']%s' % NRKTVIE._EPISODE_RE
+    _TESTS = [{
+        'url': 'https://tv.nrk.no/program/episodes/nytt-paa-nytt/69031',
+        'info_dict': {
+            'id': '69031',
+            'title': 'Nytt på nytt, sesong: 201210',
+        },
+        'playlist_count': 4,
+    }]
 
-        return self.playlist_result(
-            entries, playlist_id, playlist_title, playlist_description)
+    def _extract_title(self, webpage):
+        return self._html_search_regex(
+            r'<h1>([^<]+)</h1>', webpage, 'title', fatal=False)
 
 
 class NRKSkoleIE(InfoExtractor):

youtube_dl/extractor/rtve.py

@@ -209,7 +209,10 @@ class RTVELiveIE(InfoExtractor):
         title += ' ' + time.strftime('%Y-%m-%dZ%H%M%S', start_time)
 
         vidplayer_id = self._search_regex(
-            r'playerId=player([0-9]+)', webpage, 'internal video ID')
+            (r'playerId=player([0-9]+)',
+             r'class=["\'].*?\blive_mod\b.*?["\'][^>]+data-assetid=["\'](\d+)',
+             r'data-id=["\'](\d+)'),
+            webpage, 'internal video ID')
         png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/amonet/videos/%s.png' % vidplayer_id
         png = self._download_webpage(png_url, video_id, 'Downloading url information')
         m3u8_url = _decrypt_url(png)

youtube_dl/extractor/showroomlive.py

@@ -0,0 +1,84 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    urljoin,
+)
+
+
+class ShowRoomLiveIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?showroom-live\.com/(?!onlive|timetable|event|campaign|news|ranking|room)(?P<id>[^/?#&]+)'
+    _TEST = {
+        'url': 'https://www.showroom-live.com/48_Nana_Okada',
+        'only_matching': True,
+    }
+
+    def _real_extract(self, url):
+        broadcaster_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, broadcaster_id)
+
+        room_id = self._search_regex(
+            (r'SrGlobal\.roomId\s*=\s*(\d+)',
+             r'(?:profile|room)\?room_id\=(\d+)'), webpage, 'room_id')
+
+        room = self._download_json(
+            urljoin(url, '/api/room/profile?room_id=%s' % room_id),
+            broadcaster_id)
+
+        is_live = room.get('is_onlive')
+        if is_live is not True:
+            raise ExtractorError('%s is offline' % broadcaster_id, expected=True)
+
+        uploader = room.get('performer_name') or broadcaster_id
+        title = room.get('room_name') or room.get('main_name') or uploader
+
+        streaming_url_list = self._download_json(
+            urljoin(url, '/api/live/streaming_url?room_id=%s' % room_id),
+            broadcaster_id)['streaming_url_list']
+
+        formats = []
+        for stream in streaming_url_list:
+            stream_url = stream.get('url')
+            if not stream_url:
+                continue
+            stream_type = stream.get('type')
+            if stream_type == 'hls':
+                m3u8_formats = self._extract_m3u8_formats(
+                    stream_url, broadcaster_id, ext='mp4', m3u8_id='hls',
+                    live=True)
+                for f in m3u8_formats:
+                    f['quality'] = int_or_none(stream.get('quality', 100))
+                formats.extend(m3u8_formats)
+            elif stream_type == 'rtmp':
+                stream_name = stream.get('stream_name')
+                if not stream_name:
+                    continue
+                formats.append({
+                    'url': stream_url,
+                    'play_path': stream_name,
+                    'page_url': url,
+                    'player_url': 'https://www.showroom-live.com/assets/swf/v3/ShowRoomLive.swf',
+                    'rtmp_live': True,
+                    'ext': 'flv',
+                    'format_id': 'rtmp',
+                    'format_note': stream.get('label'),
+                    'quality': int_or_none(stream.get('quality', 100)),
+                })
+        self._sort_formats(formats)
+
+        return {
+            'id': compat_str(room.get('live_id') or broadcaster_id),
+            'title': self._live_title(title),
+            'description': room.get('description'),
+            'timestamp': int_or_none(room.get('current_live_started_at')),
+            'uploader': uploader,
+            'uploader_id': broadcaster_id,
+            'view_count': int_or_none(room.get('view_num')),
+            'formats': formats,
+            'is_live': True,
+        }

youtube_dl/extractor/twitch.py

@@ -22,6 +22,7 @@ from ..utils import (
     orderedSet,
     parse_duration,
     parse_iso8601,
+    update_url_query,
     urlencode_postdata,
 )
 
@@ -205,7 +206,14 @@ class TwitchChapterIE(TwitchItemBaseIE):
 
 class TwitchVodIE(TwitchItemBaseIE):
     IE_NAME = 'twitch:vod'
-    _VALID_URL = r'%s/[^/]+/v/(?P<id>\d+)' % TwitchBaseIE._VALID_URL_BASE
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:
+                            (?:www\.)?twitch\.tv/[^/]+/v/|
+                            player\.twitch\.tv/\?.*?\bvideo=v
+                        )
+                        (?P<id>\d+)
+                    '''
     _ITEM_TYPE = 'vod'
     _ITEM_SHORTCUT = 'v'
 
@@ -248,6 +256,9 @@ class TwitchVodIE(TwitchItemBaseIE):
             'skip_download': True,
         },
         'skip': 'HTTP Error 404: Not Found',
+    }, {
+        'url': 'http://player.twitch.tv/?t=5m10s&video=v6528877',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -279,6 +290,18 @@ class TwitchVodIE(TwitchItemBaseIE):
         if 't' in query:
             info['start_time'] = parse_duration(query['t'][0])
 
+        if info.get('timestamp') is not None:
+            info['subtitles'] = {
+                'rechat': [{
+                    'url': update_url_query(
+                        'https://rechat.twitch.tv/rechat-messages', {
+                            'video_id': 'v%s' % item_id,
+                            'start': info['timestamp'],
+                        }),
+                    'ext': 'json',
+                }],
+            }
+
         return info
 
 

youtube_dl/extractor/videa.py

@@ -0,0 +1,97 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    mimetype2ext,
+    parse_codecs,
+    xpath_element,
+    xpath_text,
+)
+
+
+class VideaIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+                    https?://
+                        videa\.hu/
+                        (?:
+                            videok/(?:[^/]+/)*[^?#&]+-|
+                            player\?.*?\bv=|
+                            player/v/
+                        )
+                        (?P<id>[^?#&]+)
+                    '''
+    _TESTS = [{
+        'url': 'http://videa.hu/videok/allatok/az-orult-kigyasz-285-kigyot-kigyo-8YfIAjxwWGwT8HVQ',
+        'md5': '97a7af41faeaffd9f1fc864a7c7e7603',
+        'info_dict': {
+            'id': '8YfIAjxwWGwT8HVQ',
+            'ext': 'mp4',
+            'title': 'Az őrült kígyász 285 kígyót enged szabadon',
+            'thumbnail': 'http://videa.hu/static/still/1.4.1.1007274.1204470.3',
+            'duration': 21,
+        },
+    }, {
+        'url': 'http://videa.hu/videok/origo/jarmuvek/supercars-elozes-jAHDWfWSJH5XuFhH',
+        'only_matching': True,
+    }, {
+        'url': 'http://videa.hu/player?v=8YfIAjxwWGwT8HVQ',
+        'only_matching': True,
+    }, {
+        'url': 'http://videa.hu/player/v/8YfIAjxwWGwT8HVQ?autoplay=1',
+        'only_matching': True,
+    }]
+
+    @staticmethod
+    def _extract_urls(webpage):
+        return [url for _, url in re.findall(
+            r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//videa\.hu/player\?.*?\bv=.+?)\1',
+            webpage)]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        info = self._download_xml(
+            'http://videa.hu/videaplayer_get_xml.php', video_id,
+            query={'v': video_id})
+
+        video = xpath_element(info, './/video', 'video', fatal=True)
+        sources = xpath_element(info, './/video_sources', 'sources', fatal=True)
+
+        title = xpath_text(video, './title', fatal=True)
+
+        formats = []
+        for source in sources.findall('./video_source'):
+            source_url = source.text
+            if not source_url:
+                continue
+            f = parse_codecs(source.get('codecs'))
+            f.update({
+                'url': source_url,
+                'ext': mimetype2ext(source.get('mimetype')) or 'mp4',
+                'format_id': source.get('name'),
+                'width': int_or_none(source.get('width')),
+                'height': int_or_none(source.get('height')),
+            })
+            formats.append(f)
+        self._sort_formats(formats)
+
+        thumbnail = xpath_text(video, './poster_src')
+        duration = int_or_none(xpath_text(video, './duration'))
+
+        age_limit = None
+        is_adult = xpath_text(video, './is_adult_content', default=None)
+        if is_adult:
+            age_limit = 18 if is_adult == '1' else 0
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'age_limit': age_limit,
+            'formats': formats,
+        }

youtube_dl/extractor/vk.py

@@ -245,7 +245,7 @@ class VKIE(VKBaseIE):
             },
         },
         {
-            # finished live stream, live_mp4
+            # finished live stream, postlive_mp4
             'url': 'https://vk.com/videos-387766?z=video-387766_456242764%2Fpl_-387766_-2',
             'md5': '90d22d051fccbbe9becfccc615be6791',
             'info_dict': {
@@ -258,7 +258,7 @@ class VKIE(VKBaseIE):
             },
         },
         {
-            # live stream, hls and rtmp links,most likely already finished live
+            # live stream, hls and rtmp links, most likely already finished live
             # stream by the time you are reading this comment
             'url': 'https://vk.com/video-140332_456239111',
             'only_matching': True,
@@ -378,12 +378,24 @@ class VKIE(VKBaseIE):
         if not data:
             data = self._parse_json(
                 self._search_regex(
-                    r'<!json>\s*({.+?})\s*<!>', info_page, 'json'),
-                video_id)['player']['params'][0]
+                    r'<!json>\s*({.+?})\s*<!>', info_page, 'json', default='{}'),
+                video_id)
+            if data:
+                data = data['player']['params'][0]
+
+        if not data:
+            data = self._parse_json(
+                self._search_regex(
+                    r'var\s+playerParams\s*=\s*({.+?})\s*;\s*\n', info_page,
+                    'player params'),
+                video_id)['params'][0]
 
         title = unescapeHTML(data['md_title'])
 
-        if data.get('live') == 2:
+        # 2 = live
+        # 3 = post live (finished live)
+        is_live = data.get('live') == 2
+        if is_live:
             title = self._live_title(title)
 
         timestamp = unified_timestamp(self._html_search_regex(
@@ -398,7 +410,8 @@ class VKIE(VKBaseIE):
         for format_id, format_url in data.items():
             if not isinstance(format_url, compat_str) or not format_url.startswith(('http', '//', 'rtmp')):
                 continue
-            if format_id.startswith(('url', 'cache')) or format_id in ('extra_data', 'live_mp4'):
+            if (format_id.startswith(('url', 'cache')) or
+                    format_id in ('extra_data', 'live_mp4', 'postlive_mp4')):
                 height = int_or_none(self._search_regex(
                     r'^(?:url|cache)(\d+)', format_id, 'height', default=None))
                 formats.append({
@@ -408,8 +421,9 @@ class VKIE(VKBaseIE):
                 })
             elif format_id == 'hls':
                 formats.extend(self._extract_m3u8_formats(
-                    format_url, video_id, 'mp4', m3u8_id=format_id,
-                    fatal=False, live=True))
+                    format_url, video_id, 'mp4',
+                    entry_protocol='m3u8' if is_live else 'm3u8_native',
+                    m3u8_id=format_id, fatal=False, live=is_live))
             elif format_id == 'rtmp':
                 formats.append({
                     'format_id': format_id,
@@ -427,6 +441,7 @@ class VKIE(VKBaseIE):
             'duration': data.get('duration'),
             'timestamp': timestamp,
             'view_count': view_count,
+            'is_live': is_live,
         }
 
 

youtube_dl/extractor/xhamster.py

@@ -5,8 +5,8 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     dict_get,
-    float_or_none,
     int_or_none,
+    parse_duration,
     unified_strdate,
 )
 
@@ -22,7 +22,7 @@ class XHamsterIE(InfoExtractor):
             'title': 'FemaleAgent Shy beauty takes the bait',
             'upload_date': '20121014',
             'uploader': 'Ruseful2011',
-            'duration': 893.52,
+            'duration': 893,
             'age_limit': 18,
         },
     }, {
@@ -33,7 +33,7 @@ class XHamsterIE(InfoExtractor):
             'title': 'Britney Spears  Sexy Booty',
             'upload_date': '20130914',
             'uploader': 'jojo747400',
-            'duration': 200.48,
+            'duration': 200,
             'age_limit': 18,
         },
         'params': {
@@ -48,7 +48,7 @@ class XHamsterIE(InfoExtractor):
             'title': '....',
             'upload_date': '20160208',
             'uploader': 'parejafree',
-            'duration': 72.0,
+            'duration': 72,
             'age_limit': 18,
         },
         'params': {
@@ -101,9 +101,9 @@ class XHamsterIE(InfoExtractor):
              r'''<video[^>]+poster=(?P<q>["'])(?P<thumbnail>.+?)(?P=q)[^>]*>'''],
             webpage, 'thumbnail', fatal=False, group='thumbnail')
 
-        duration = float_or_none(self._search_regex(
-            r'(["\'])duration\1\s*:\s*(["\'])(?P<duration>.+?)\2',
-            webpage, 'duration', fatal=False, group='duration'))
+        duration = parse_duration(self._search_regex(
+            r'Runtime:\s*</span>\s*([\d:]+)', webpage,
+            'duration', fatal=False))
 
         view_count = int_or_none(self._search_regex(
             r'content=["\']User(?:View|Play)s:(\d+)',

youtube_dl/options.py

@@ -178,6 +178,10 @@ def parseOpts(overrideArguments=None):
         'When given in the global configuration file /etc/youtube-dl.conf: '
         'Do not read the user configuration in ~/.config/youtube-dl/config '
         '(%APPDATA%/youtube-dl/config.txt on Windows)')
+    general.add_option(
+        '--config-location',
+        dest='config_location', metavar='PATH',
+        help='Location of the configuration file; either the path to the config or its containing directory.')
     general.add_option(
         '--flat-playlist',
         action='store_const', dest='extract_flat', const='in_playlist',
@@ -341,7 +345,7 @@ def parseOpts(overrideArguments=None):
     authentication.add_option(
         '-2', '--twofactor',
         dest='twofactor', metavar='TWOFACTOR',
-        help='Two-factor auth code')
+        help='Two-factor authentication code')
     authentication.add_option(
         '-n', '--netrc',
         action='store_true', dest='usenetrc', default=False,
@@ -469,7 +473,7 @@ def parseOpts(overrideArguments=None):
     downloader.add_option(
         '--xattr-set-filesize',
         dest='xattr_set_filesize', action='store_true',
-        help='Set file xattribute ytdl.filesize with expected filesize (experimental)')
+        help='Set file xattribute ytdl.filesize with expected file size (experimental)')
     downloader.add_option(
         '--hls-prefer-native',
         dest='hls_prefer_native', action='store_true', default=None,
@@ -845,22 +849,32 @@ def parseOpts(overrideArguments=None):
             return conf
 
         command_line_conf = compat_conf(sys.argv[1:])
+        opts, args = parser.parse_args(command_line_conf)
 
-        if '--ignore-config' in command_line_conf:
-            system_conf = []
-            user_conf = []
+        system_conf = user_conf = custom_conf = []
+
+        if '--config-location' in command_line_conf:
+            location = compat_expanduser(opts.config_location)
+            if os.path.isdir(location):
+                location = os.path.join(location, 'youtube-dl.conf')
+            if not os.path.exists(location):
+                parser.error('config-location %s does not exist.' % location)
+            custom_conf = _readOptions(location)
+        elif '--ignore-config' in command_line_conf:
+            pass
         else:
             system_conf = _readOptions('/etc/youtube-dl.conf')
-            if '--ignore-config' in system_conf:
-                user_conf = []
-            else:
+            if '--ignore-config' not in system_conf:
                 user_conf = _readUserConf()
-        argv = system_conf + user_conf + command_line_conf
 
+        argv = system_conf + user_conf + command_line_conf
         opts, args = parser.parse_args(argv)
         if opts.verbose:
-            write_string('[debug] System config: ' + repr(_hide_login_info(system_conf)) + '\n')
-            write_string('[debug] User config: ' + repr(_hide_login_info(user_conf)) + '\n')
-            write_string('[debug] Command-line args: ' + repr(_hide_login_info(command_line_conf)) + '\n')
+            for conf_label, conf in (
+                    ('System config', system_conf),
+                    ('User config', user_conf),
+                    ('Custom config', custom_conf),
+                    ('Command-line args', command_line_conf)):
+                write_string('[debug] %s: %s\n' % (conf_label, repr(_hide_login_info(conf))))
 
     return parser, opts, args

youtube_dl/version.py

@@ -1,3 +1,3 @@
 from __future__ import unicode_literals
 
-__version__ = '2016.12.22'
+__version__ = '2017.01.02'