release 2016.08.17

And remove a mysterious comma from 115c65793a

.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 *2016.07.09.1*. 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 Issues with outdated version will be rejected.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 **2016.07.09.1**
+### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.08.17*. 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 Issues with outdated version will be rejected.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 **2016.08.17**
 
 ### 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 2016.07.09.1
+[debug] youtube-dl version 2016.08.17
 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
 [debug] Proxy map: {}

.travis.yml

@@ -7,9 +7,6 @@ python:
   - "3.4"
   - "3.5"
 sudo: false
-install:
-  - bash ./devscripts/install_srelay.sh
-  - export PATH=$PATH:$(pwd)/tmp/srelay-0.4.8b6
 script: nosetests test --verbose
 notifications:
   email:

AUTHORS

@@ -177,3 +177,7 @@ Roman Tsiupa
 Artur Krysiak
 Jakub Adam Wieczorek
 Aleksandar Topuzović
+Nehal Patel
+Rob van Bekkum
+Petr Zvoníček
+Pratyush Singh

CONTRIBUTING.md

@@ -46,7 +46,7 @@ Make sure that someone has not already opened the issue you're trying to open. S
 
 ###  Why are existing options not enough?
 
-Before requesting a new feature, please have a quick peek at [the list of supported options](https://github.com/rg3/youtube-dl/blob/master/README.md#synopsis). Many feature requests are for features that actually exist already! Please, absolutely do show off your work in the issue report and detail how the existing similar options do *not* solve your problem.
+Before requesting a new feature, please have a quick peek at [the list of supported options](https://github.com/rg3/youtube-dl/blob/master/README.md#options). Many feature requests are for features that actually exist already! Please, absolutely do show off your work in the issue report and detail how the existing similar options do *not* solve your problem.
 
 ###  Is there enough context in your bug report?
 

ChangeLog

@@ -0,0 +1,423 @@
+version 2016.08.17
+
+Core
++ Add _get_netrc_login_info
+
+Extractors
+* [mofosex] Extract all formats (#10335)
++ [generic] Add support for vbox7 embeds
++ [vbox7] Add support for embed URLs
++ [viafree] Add extractor (#10358)
++ [mtg] Add support for viafree URLs (#10358)
+* [theplatform] Extract all subtitles per language
++ [xvideos] Fix HLS extraction (#10356)
++ [amcnetworks] Add extractor
++ [bbc:playlist] Add support for pagination (#10349)
++ [fxnetworks] Add extractor (#9462)
+* [cbslocal] Fix extraction for SendtoNews-based videos
+* [sendtonews] Fix extraction
+* [jwplatform] Extract video id from JWPlayer data
+- [zippcast] Remove extractor (#10332)
++ [viceland] Add extractor (#8799)
++ [adobepass] Add base extractor for Adobe Pass Authentication
+* [life:embed] Improve extraction
+* [vgtv] Detect geo restricted videos (#10348)
++ [uplynk] Add extractor
+* [xiami] Fix extraction (#10342)
+
+
+version 2016.08.13
+
+Core
+* Show progress for curl external downloader
+* Forward more options to curl external downloader
+
+Extractors
+* [pbs] Fix description extraction
+* [franceculture] Fix extraction (#10324)
+* [pornotube] Fix extraction (#10322)
+* [4tube] Fix metadata extraction (#10321)
+* [imgur] Fix width and height extraction (#10325)
+* [expotv] Improve extraction
++ [vbox7] Fix extraction (#10309)
+- [tapely] Remove extractor (#10323)
+* [muenchentv] Fix extraction (#10313)
++ [24video] Add support for .me and .xxx TLDs
+* [24video] Fix comment count extraction
+* [sunporno] Add support for embed URLs
+* [sunporno] Fix metadata extraction (#10316)
++ [hgtv] Add extractor for hgtv.ca (#3999)
+- [pbs] Remove request to unavailable API
++ [pbs] Add support for high quality HTTP formats
++ [crunchyroll] Add support for HLS formats (#10301)
+
+
+version 2016.08.12
+
+Core
+* Subtitles are now written as is. Newline conversions are disabled. (#10268)
++ Recognize more formats in unified_timestamp
+
+Extractors
+- [goldenmoustache] Remove extractor (#10298)
+* [drtuber] Improve title extraction
+* [drtuber] Make dislike count optional (#10297)
+* [chirbit] Fix extraction (#10296)
+* [francetvinfo] Relax URL regular expression
+* [rtlnl] Relax URL regular expression (#10282)
+* [formula1] Relax URL regular expression (#10283)
+* [wat] Improve extraction (#10281)
+* [ctsnews] Fix extraction
+
+
+version 2016.08.10
+
+Core
+* Make --metadata-from-title non fatal when title does not match the pattern
+* Introduce options for randomized sleep before each download
+  --min-sleep-interval and --max-sleep-interval (#9930)
+* Respect default in _search_json_ld
+
+Extractors
++ [uol] Add extractor for uol.com.br (#4263)
+* [rbmaradio] Fix extraction and extract all formats (#10242)
++ [sonyliv] Add extractor for sonyliv.com (#10258)
+* [aparat] Fix extraction
+* [cwtv] Extract HTTP formats
++ [rozhlas] Add extractor for prehravac.rozhlas.cz (#10253)
+* [kuwo:singer] Fix extraction
+
+
+version 2016.08.07
+
+Core
++ Add support for TV Parental Guidelines ratings in parse_age_limit
++ Add decode_png (#9706)
++ Add support for partOfTVSeries in JSON-LD
+* Lower master M3U8 manifest preference for better format sorting
+
+Extractors
++ [discoverygo] Add extractor (#10245)
+* [flipagram] Make JSON-LD extraction non fatal
+* [generic] Make JSON-LD extraction non fatal
++ [bbc] Add support for morph embeds (#10239)
+* [tnaflixnetworkbase] Improve title extraction
+* [tnaflix] Fix metadata extraction (#10249)
+* [fox] Fix theplatform release URL query
+* [openload] Fix extraction (#9706)
+* [bbc] Skip duplicate manifest URLs
+* [bbc] Improve format code
++ [bbc] Add support for DASH and F4M
+* [bbc] Improve format sorting and listing
+* [bbc] Improve playlist extraction
++ [pokemon] Add extractor (#10093)
++ [condenast] Add fallback scenario for video info extraction
+
+
+version 2016.08.06
+
+Core
+* Add support for JSON-LD root list entries (#10203)
+* Improve unified_timestamp
+* Lower preference of RTSP formats in generic sorting
++ Add support for multiple properties in _og_search_property
+* Improve password hiding from verbose output
+
+Extractors
++ [adultswim] Add support for trailers (#10235)
+* [archiveorg] Improve extraction (#10219)
++ [jwplatform] Add support for playlists
++ [jwplatform] Add support for relative URLs
+* [jwplatform] Improve audio detection
++ [tvplay] Capture and output native error message
++ [tvplay] Extract series metadata
++ [tvplay] Add support for subtitles (#10194)
+* [tvp] Improve extraction (#7799)
+* [cbslocal] Fix timestamp parsing (#10213)
++ [naver] Add support for subtitles (#8096)
+* [naver] Improve extraction
+* [condenast] Improve extraction
+* [engadget] Relax URL regular expression
+* [5min] Fix extraction
++ [nationalgeographic] Add support for Episode Guide
++ [kaltura] Add support for subtitles
+* [kaltura] Optimize network requests
++ [vodplatform] Add extractor for vod-platform.net
+- [gamekings] Remove extractor
+* [limelight] Extract HTTP formats
+* [ntvru] Fix extraction
++ [comedycentral] Re-add :tds and :thedailyshow shortnames
+
+
+version 2016.08.01
+
+Fixed/improved extractors
+- [yandexmusic:track] Adapt to changes in track location JSON (#10193)
+- [bloomberg] Support another form of player (#10187)
+- [limelight] Skip DRM protected videos
+- [safari] Relax regular expressions for URL matching (#10202)
+- [cwtv] Add support for cwtvpr.com (#10196)
+
+
+version 2016.07.30
+
+Fixed/improved extractors
+- [twitch:clips] Sort formats
+- [tv2] Use m3u8_native
+- [tv2:article] Fix video detection (#10188)
+- rtve (#10076)
+- [dailymotion:playlist] Optimize download archive processing (#10180)
+
+
+version 2016.07.28
+
+Fixed/improved extractors
+- shared (#10170)
+- soundcloud (#10179)
+- twitch (#9767)
+
+
+version 2016.07.26.2
+
+Fixed/improved extractors
+- smotri
+- camdemy
+- mtv
+- comedycentral
+- cmt
+- cbc
+- mgtv
+- orf
+
+
+version 2016.07.24
+
+New extractors
+- arkena (#8682)
+- lcp (#8682)
+
+Fixed/improved extractors
+- facebook (#10151)
+- dailymail
+- telegraaf
+- dcn
+- onet
+- tvp
+
+Miscellaneous
+- Support $Time$ in DASH manifests
+
+
+version 2016.07.22
+
+New extractors
+- odatv (#9285)
+
+Fixed/improved extractors
+- bbc
+- youjizz (#10131)
+- youtube (#10140)
+- pornhub (#10138)
+- eporner (#10139)
+
+
+version 2016.07.17
+
+New extractors
+- nintendo (#9986)
+- streamable (#9122)
+
+Fixed/improved extractors
+- ard (#10095)
+- mtv
+- comedycentral (#10101)
+- viki (#10098)
+- spike (#10106)
+
+Miscellaneous
+- Improved twitter player detection (#10090)
+
+
+version 2016.07.16
+
+New extractors
+- ninenow (#5181)
+
+Fixed/improved extractors
+- rtve (#10076)
+- brightcove
+- 3qsdn
+- syfy (#9087, #3820, #2388)
+- youtube (#10083)
+
+Miscellaneous
+- Fix subtitle embedding for video-only and audio-only files (#10081)
+
+
+version 2016.07.13
+
+New extractors
+- rudo
+
+Fixed/improved extractors
+- biobiochiletv
+- tvplay
+- dbtv
+- brightcove
+- tmz
+- youtube (#10059)
+- shahid (#10062)
+- vk
+- ellentv (#10067)
+
+
+version 2016.07.11
+
+New Extractors
+- roosterteeth (#9864)
+
+Fixed/improved extractors
+- miomio (#9605)
+- vuclip
+- youtube
+- vidzi (#10058)
+
+
+version 2016.07.09.2
+
+Fixed/improved extractors
+- vimeo (#1638)
+- facebook (#10048)
+- lynda (#10047)
+- animeondemand
+
+Fixed/improved features
+- Embedding subtitles no longer throws an error with problematic inputs (#9063)
+
+
+version 2016.07.09.1
+
+Fixed/improved extractors
+- youtube
+- ard
+- srmediatek (#9373)
+
+
+version 2016.07.09
+
+New extractors
+- Flipagram (#9898)
+
+Fixed/improved extractors
+- telecinco
+- toutv
+- radiocanada
+- tweakers (#9516)
+- lynda
+- nick (#7542)
+- polskieradio (#10028)
+- le
+- facebook (#9851)
+- mgtv
+- animeondemand (#10031)
+
+Fixed/improved features
+- `--postprocessor-args` and `--downloader-args` now accepts non-ASCII inputs
+  on non-Windows systems
+
+
+version 2016.07.07
+
+New extractors
+- kamcord (#10001)
+
+Fixed/improved extractors
+- spiegel (#10018)
+- metacafe (#8539, #3253)
+- onet (#9950)
+- francetv (#9955)
+- brightcove (#9965)
+- daum (#9972)
+
+
+version 2016.07.06
+
+Fixed/improved extractors
+- youtube (#10007, #10009)
+- xuite
+- stitcher
+- spiegel
+- slideshare
+- sandia
+- rtvnh
+- prosiebensat1
+- onionstudios
+
+
+version 2016.07.05
+
+Fixed/improved extractors
+- brightcove
+- yahoo (#9995)
+- pornhub (#9997)
+- iqiyi
+- kaltura (#5557)
+- la7
+- Changed features
+- Rename --cn-verfication-proxy to --geo-verification-proxy
+Miscellaneous
+- Add script for displaying downloads statistics
+
+
+version 2016.07.03.1
+
+Fixed/improved extractors
+- theplatform
+- aenetworks
+- nationalgeographic
+- hrti (#9482)
+- facebook (#5701)
+- buzzfeed (#5701)
+- rai (#8617, #9157, #9232, #8552, #8551)
+- nationalgeographic (#9991)
+- iqiyi
+
+
+version 2016.07.03
+
+New extractors
+- hrti (#9482)
+
+Fixed/improved extractors
+- vk (#9981)
+- facebook (#9938)
+- xtube (#9953, #9961)
+
+
+version 2016.07.02
+
+New extractors
+- fusion (#9958)
+
+Fixed/improved extractors
+- twitch (#9975)
+- vine (#9970)
+- periscope (#9967)
+- pornhub (#8696)
+
+
+version 2016.07.01
+
+New extractors
+- 9c9media
+- ctvnews (#2156)
+- ctv (#4077)
+
+Fixed/Improved extractors
+- rds
+- meta (#8789)
+- pornhub (#9964)
+- sixplay (#2183)
+
+New features
+- Accept quoted strings across multiple lines (#9940)

Makefile

@@ -94,7 +94,7 @@ _EXTRACTOR_FILES != find youtube_dl/extractor -iname '*.py' -and -not -iname 'la
 youtube_dl/extractor/lazy_extractors.py: devscripts/make_lazy_extractors.py devscripts/lazy_load_template.py $(_EXTRACTOR_FILES)
 	$(PYTHON) devscripts/make_lazy_extractors.py $@
 
-youtube-dl.tar.gz: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish
+youtube-dl.tar.gz: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish ChangeLog
 	@tar -czf youtube-dl.tar.gz --transform "s|^|youtube-dl/|" --owner 0 --group 0 \
 		--exclude '*.DS_Store' \
 		--exclude '*.kate-swp' \
@@ -107,7 +107,7 @@ youtube-dl.tar.gz: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-
 		--exclude 'docs/_build' \
 		-- \
 		bin devscripts test youtube_dl docs \
-		LICENSE README.md README.txt \
+		ChangeLog LICENSE README.md README.txt \
 		Makefile MANIFEST.in youtube-dl.1 youtube-dl.bash-completion \
 		youtube-dl.zsh youtube-dl.fish setup.py \
 		youtube-dl

README.md

@@ -17,7 +17,7 @@ youtube-dl - download videos from youtube.com or other video platforms
 
 To install it right away for all UNIX users (Linux, OS X, etc.), type:
 
-    sudo curl -L https://yt-dl.org/latest/youtube-dl -o /usr/local/bin/youtube-dl
+    sudo curl -L https://yt-dl.org/downloads/latest/youtube-dl -o /usr/local/bin/youtube-dl
     sudo chmod a+rx /usr/local/bin/youtube-dl
 
 If you do not have curl, you can alternatively use a recent wget:
@@ -330,7 +330,15 @@ which means you can modify it, redistribute it or use it however you like.
                                      bidirectional text support. Requires bidiv
                                      or fribidi executable in PATH
     --sleep-interval SECONDS         Number of seconds to sleep before each
-                                     download.
+                                     download when used alone or a lower bound
+                                     of a range for randomized sleep before each
+                                     download (minimum possible number of
+                                     seconds to sleep) when used along with
+                                     --max-sleep-interval.
+    --max-sleep-interval SECONDS     Upper bound of a range for randomized sleep
+                                     before each download (maximum possible
+                                     number of seconds to sleep). Must only be
+                                     used along with --min-sleep-interval.
 
 ## Video Format Options:
     -f, --format FORMAT              Video format code, see the "FORMAT
@@ -1196,7 +1204,7 @@ Make sure that someone has not already opened the issue you're trying to open. S
 
 ###  Why are existing options not enough?
 
-Before requesting a new feature, please have a quick peek at [the list of supported options](https://github.com/rg3/youtube-dl/blob/master/README.md#synopsis). Many feature requests are for features that actually exist already! Please, absolutely do show off your work in the issue report and detail how the existing similar options do *not* solve your problem.
+Before requesting a new feature, please have a quick peek at [the list of supported options](https://github.com/rg3/youtube-dl/blob/master/README.md#options). Many feature requests are for features that actually exist already! Please, absolutely do show off your work in the issue report and detail how the existing similar options do *not* solve your problem.
 
 ###  Is there enough context in your bug report?
 

devscripts/gh-pages/generate-download.py

@@ -15,13 +15,9 @@ data = urllib.request.urlopen(URL).read()
 with open('download.html.in', 'r', encoding='utf-8') as tmplf:
     template = tmplf.read()
 
-md5sum = hashlib.md5(data).hexdigest()
-sha1sum = hashlib.sha1(data).hexdigest()
 sha256sum = hashlib.sha256(data).hexdigest()
 template = template.replace('@PROGRAM_VERSION@', version)
 template = template.replace('@PROGRAM_URL@', URL)
-template = template.replace('@PROGRAM_MD5SUM@', md5sum)
-template = template.replace('@PROGRAM_SHA1SUM@', sha1sum)
 template = template.replace('@PROGRAM_SHA256SUM@', sha256sum)
 template = template.replace('@EXE_URL@', versions_info['versions'][version]['exe'][0])
 template = template.replace('@EXE_SHA256SUM@', versions_info['versions'][version]['exe'][1])

devscripts/install_srelay.sh

@@ -1,8 +0,0 @@
-#!/bin/bash
-
-mkdir -p tmp && cd tmp
-wget -N http://downloads.sourceforge.net/project/socks-relay/socks-relay/srelay-0.4.8/srelay-0.4.8b6.tar.gz
-tar zxvf srelay-0.4.8b6.tar.gz
-cd srelay-0.4.8b6
-./configure
-make

devscripts/prepare_manpage.py

@@ -54,17 +54,21 @@ def filter_options(readme):
 
         if in_options:
             if line.lstrip().startswith('-'):
-                option, description = re.split(r'\s{2,}', line.lstrip())
-                split_option = option.split(' ')
+                split = re.split(r'\s{2,}', line.lstrip())
+                # Description string may start with `-` as well. If there is
+                # only one piece then it's a description bit not an option.
+                if len(split) > 1:
+                    option, description = split
+                    split_option = option.split(' ')
 
-                if not split_option[-1].startswith('-'):  # metavar
-                    option = ' '.join(split_option[:-1] + ['*%s*' % split_option[-1]])
+                    if not split_option[-1].startswith('-'):  # metavar
+                        option = ' '.join(split_option[:-1] + ['*%s*' % split_option[-1]])
 
-                # Pandoc's definition_lists. See http://pandoc.org/README.html
-                # for more information.
-                ret += '\n%s\n:   %s\n' % (option, description)
-            else:
-                ret += line.lstrip() + '\n'
+                    # Pandoc's definition_lists. See http://pandoc.org/README.html
+                    # for more information.
+                    ret += '\n%s\n:   %s\n' % (option, description)
+                    continue
+            ret += line.lstrip() + '\n'
         else:
             ret += line + '\n'
 

devscripts/release.sh

@@ -71,9 +71,12 @@ fi
 /bin/echo -e "\n### Changing version in version.py..."
 sed -i "s/__version__ = '.*'/__version__ = '$version'/" youtube_dl/version.py
 
+/bin/echo -e "\n### Changing version in ChangeLog..."
+sed -i "s/<unreleased>/$version/" ChangeLog
+
 /bin/echo -e "\n### Committing documentation, templates and youtube_dl/version.py..."
 make README.md CONTRIBUTING.md .github/ISSUE_TEMPLATE.md supportedsites
-git add README.md CONTRIBUTING.md .github/ISSUE_TEMPLATE.md docs/supportedsites.md youtube_dl/version.py
+git add README.md CONTRIBUTING.md .github/ISSUE_TEMPLATE.md docs/supportedsites.md youtube_dl/version.py ChangeLog
 git commit $gpg_sign_commits -m "release $version"
 
 /bin/echo -e "\n### Now tagging, signing and pushing..."

devscripts/show-downloads-statistics.py

@@ -1,6 +1,7 @@
 #!/usr/bin/env python
 from __future__ import unicode_literals
 
+import itertools
 import json
 import os
 import re
@@ -21,21 +22,26 @@ def format_size(bytes):
 
 total_bytes = 0
 
-releases = json.loads(compat_urllib_request.urlopen(
-    'https://api.github.com/repos/rg3/youtube-dl/releases').read().decode('utf-8'))
+for page in itertools.count(1):
+    releases = json.loads(compat_urllib_request.urlopen(
+        'https://api.github.com/repos/rg3/youtube-dl/releases?page=%s' % page
+    ).read().decode('utf-8'))
 
-for release in releases:
-    compat_print(release['name'])
-    for asset in release['assets']:
-        asset_name = asset['name']
-        total_bytes += asset['download_count'] * asset['size']
-        if all(not re.match(p, asset_name) for p in (
-                r'^youtube-dl$',
-                r'^youtube-dl-\d{4}\.\d{2}\.\d{2}(?:\.\d+)?\.tar\.gz$',
-                r'^youtube-dl\.exe$')):
-            continue
-        compat_print(
-            ' %s size: %s downloads: %d'
-            % (asset_name, format_size(asset['size']), asset['download_count']))
+    if not releases:
+        break
+
+    for release in releases:
+        compat_print(release['name'])
+        for asset in release['assets']:
+            asset_name = asset['name']
+            total_bytes += asset['download_count'] * asset['size']
+            if all(not re.match(p, asset_name) for p in (
+                    r'^youtube-dl$',
+                    r'^youtube-dl-\d{4}\.\d{2}\.\d{2}(?:\.\d+)?\.tar\.gz$',
+                    r'^youtube-dl\.exe$')):
+                continue
+            compat_print(
+                ' %s size: %s downloads: %d'
+                % (asset_name, format_size(asset['size']), asset['download_count']))
 
 compat_print('total downloads traffic: %s' % format_size(total_bytes))

docs/supportedsites.md

@@ -14,6 +14,7 @@
  - **8tracks**
  - **91porn**
  - **9gag**
+ - **9now.com.au**
  - **abc.net.au**
  - **Abc7News**
  - **abcnews**
@@ -34,6 +35,7 @@
  - **AlJazeera**
  - **Allocine**
  - **AlphaPorno**
+ - **AMCNetworks**
  - **AnimeOnDemand**
  - **anitube.se**
  - **AnySex**
@@ -45,6 +47,7 @@
  - **archive.org**: archive.org videos
  - **ARD**
  - **ARD:mediathek**
+ - **Arkena**
  - **arte.tv**
  - **arte.tv:+7**
  - **arte.tv:cinema**
@@ -140,7 +143,8 @@
  - **CollegeRama**
  - **ComCarCoff**
  - **ComedyCentral**
- - **ComedyCentralShows**: The Daily Show / The Colbert Report
+ - **ComedyCentralShortname**
+ - **ComedyCentralTV**
  - **CondeNast**: Condé Nast media group: Allure, Architectural Digest, Ars Technica, Bon Appétit, Brides, Condé Nast, Condé Nast Traveler, Details, Epicurious, GQ, Glamour, Golf Digest, SELF, Teen Vogue, The New Yorker, Vanity Fair, Vogue, W Magazine, WIRED
  - **Coub**
  - **Cracked**
@@ -179,6 +183,7 @@
  - **DigitallySpeaking**
  - **Digiteka**
  - **Discovery**
+ - **DiscoveryGo**
  - **Dotsub**
  - **DouyuTV**: 斗鱼
  - **DPlay**
@@ -234,7 +239,6 @@
  - **FoxSports**
  - **france2.fr:generation-quoi**
  - **FranceCulture**
- - **FranceCultureEmission**
  - **FranceInter**
  - **francetv**: France 2, 3, 4, 5 and Ô
  - **francetvinfo.fr**
@@ -244,8 +248,8 @@
  - **Funimation**
  - **FunnyOrDie**
  - **Fusion**
+ - **FXNetworks**
  - **GameInformer**
- - **Gamekings**
  - **GameOne**
  - **gameone:playlist**
  - **Gamersyde**
@@ -262,7 +266,6 @@
  - **GloboArticle**
  - **GodTube**
  - **GodTV**
- - **GoldenMoustache**
  - **Golem**
  - **GoogleDrive**
  - **Goshgay**
@@ -275,6 +278,7 @@
  - **HellPorno**
  - **Helsinki**: helsinki.fi
  - **HentaiStigma**
+ - **HGTV**
  - **HistoricFilms**
  - **history:topic**: History.com Topic
  - **hitbox**
@@ -335,6 +339,8 @@
  - **kuwo:song**: 酷我音乐
  - **la7.it**
  - **Laola1Tv**
+ - **Lcp**
+ - **LcpPlay**
  - **Le**: 乐视网
  - **Learnr**
  - **Lecture2Go**
@@ -394,9 +400,9 @@
  - **Moviezine**
  - **MPORA**
  - **MSN**
+ - **mtg**: MTG services
  - **MTV**
  - **mtv.de**
- - **mtviggy.com**
  - **mtvservices:embedded**
  - **MuenchenTV**: münchen.tv
  - **MusicPlayOn**
@@ -412,7 +418,8 @@
  - **MyVidster**
  - **n-tv.de**
  - **natgeo**
- - **natgeo:channel**
+ - **natgeo:episodeguide**
+ - **natgeo:video**
  - **Naver**
  - **NBA**
  - **NBC**
@@ -436,7 +443,6 @@
  - **Newstube**
  - **NextMedia**: 蘋果日報
  - **NextMediaActionNews**: 蘋果日報 - 動新聞
- - **nextmovie.com**
  - **nfb**: National Film Board of Canada
  - **nfl.com**
  - **nhl.com**
@@ -448,6 +454,7 @@
  - **niconico**: ニコニコ動画
  - **NiconicoPlaylist**
  - **NineCNineMedia**
+ - **Nintendo**
  - **njoy**: N-JOY
  - **njoy:embed**
  - **Noco**
@@ -475,6 +482,7 @@
  - **NYTimes**
  - **NYTimesArticle**
  - **ocw.mit.edu**
+ - **OdaTV**
  - **Odnoklassniki**
  - **OktoberfestTV**
  - **on.aol.com**
@@ -513,6 +521,7 @@
  - **plus.google**: Google Plus
  - **pluzz.francetv.fr**
  - **podomatic**
+ - **Pokemon**
  - **PolskieRadio**
  - **PornHd**
  - **PornHub**: PornHub and Thumbzilla
@@ -554,8 +563,10 @@
  - **RICE**
  - **RingTV**
  - **RockstarGames**
+ - **RoosterTeeth**
  - **RottenTomatoes**
  - **Roxwel**
+ - **Rozhlas**
  - **RTBF**
  - **rte**: Raidió Teilifís Éireann TV
  - **rte:radio**: Raidió Teilifís Éireann radio
@@ -566,7 +577,9 @@
  - **rtve.es:alacarta**: RTVE a la carta
  - **rtve.es:infantil**: RTVE infantil
  - **rtve.es:live**: RTVE.es live streams
+ - **rtve.es:television**
  - **RTVNH**
+ - **Rudo**
  - **RUHD**
  - **RulePorn**
  - **rutube**: Rutube videos
@@ -611,6 +624,7 @@
  - **smotri:user**: Smotri.com user videos
  - **Snotr**
  - **Sohu**
+ - **SonyLIV**
  - **soundcloud**
  - **soundcloud:playlist**
  - **soundcloud:search**: Soundcloud search
@@ -641,6 +655,7 @@
  - **stanfordoc**: Stanford Open ClassRoom
  - **Steam**
  - **Stitcher**
+ - **Streamable**
  - **streamcloud.eu**
  - **StreamCZ**
  - **StreetVoice**
@@ -652,7 +667,6 @@
  - **SztvHu**
  - **Tagesschau**
  - **tagesschau:player**
- - **Tapely**
  - **Tass**
  - **TDSLifeway**
  - **teachertube**: teachertube.com videos
@@ -688,6 +702,7 @@
  - **TNAFlix**
  - **TNAFlixNetworkEmbed**
  - **toggle**
+ - **Tosh**: Tosh.0
  - **tou.tv**
  - **Toypics**: Toypics user profile
  - **ToypicsUser**: Toypics user profile
@@ -717,8 +732,8 @@
  - **tvigle**: Интернет-телевидение Tvigle.ru
  - **tvland.com**
  - **tvp**: Telewizja Polska
+ - **tvp:embed**: Telewizja Polska
  - **tvp:series**
- - **TVPlay**: TV3Play and related services
  - **Tweakers**
  - **twitch:chapter**
  - **twitch:clips**
@@ -734,6 +749,9 @@
  - **udemy:course**
  - **UDNEmbed**: 聯合影音
  - **Unistra**
+ - **uol.com.br**
+ - **uplynk**
+ - **uplynk:preplay**
  - **Urort**: NRK P3 Urørt
  - **URPlay**
  - **USAToday**
@@ -751,7 +769,9 @@
  - **VevoPlaylist**
  - **VGTV**: VGTV, BTTV, FTV, Aftenposten and Aftonbladet
  - **vh1.com**
+ - **Viafree**
  - **Vice**
+ - **Viceland**
  - **ViceShow**
  - **Vidbit**
  - **Viddler**
@@ -793,8 +813,10 @@
  - **vine:user**
  - **vk**: VK
  - **vk:uservideos**: VK - User's Videos
+ - **vk:wallpost**
  - **vlive**
  - **Vodlocker**
+ - **VODPlatform**
  - **VoiceRepublic**
  - **VoxMedia**
  - **Vporn**
@@ -871,4 +893,3 @@
  - **ZDFChannel**
  - **zingmp3:album**: mp3.zing.vn albums
  - **zingmp3:song**: mp3.zing.vn songs
- - **ZippCast**

test/test_InfoExtractor.py

@@ -48,6 +48,9 @@ class TestInfoExtractor(unittest.TestCase):
         self.assertEqual(ie._og_search_property('foobar', html), 'Foo')
         self.assertEqual(ie._og_search_property('test1', html), 'foo > < bar')
         self.assertEqual(ie._og_search_property('test2', html), 'foo >//< bar')
+        self.assertEqual(ie._og_search_property(('test0', 'test1'), html), 'foo > < bar')
+        self.assertRaises(RegexNotFoundError, ie._og_search_property, 'test0', html, None, fatal=True)
+        self.assertRaises(RegexNotFoundError, ie._og_search_property, ('test0', 'test00'), html, None, fatal=True)
 
     def test_html_search_meta(self):
         ie = self.ie

test/test_YoutubeDL.py

@@ -335,6 +335,40 @@ class TestFormatSelection(unittest.TestCase):
             downloaded = ydl.downloaded_info_dicts[0]
             self.assertEqual(downloaded['format_id'], f1['format_id'])
 
+    def test_audio_only_extractor_format_selection(self):
+        # For extractors with incomplete formats (all formats are audio-only or
+        # video-only) best and worst should fallback to corresponding best/worst
+        # video-only or audio-only formats (as per
+        # https://github.com/rg3/youtube-dl/pull/5556)
+        formats = [
+            {'format_id': 'low', 'ext': 'mp3', 'preference': 1, 'vcodec': 'none', 'url': TEST_URL},
+            {'format_id': 'high', 'ext': 'mp3', 'preference': 2, 'vcodec': 'none', 'url': TEST_URL},
+        ]
+        info_dict = _make_result(formats)
+
+        ydl = YDL({'format': 'best'})
+        ydl.process_ie_result(info_dict.copy())
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'high')
+
+        ydl = YDL({'format': 'worst'})
+        ydl.process_ie_result(info_dict.copy())
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'low')
+
+    def test_format_not_available(self):
+        formats = [
+            {'format_id': 'regular', 'ext': 'mp4', 'height': 360, 'url': TEST_URL},
+            {'format_id': 'video', 'ext': 'mp4', 'height': 720, 'acodec': 'none', 'url': TEST_URL},
+        ]
+        info_dict = _make_result(formats)
+
+        # This must fail since complete video-audio format does not match filter
+        # and extractor does not provide incomplete only formats (i.e. only
+        # video-only or audio-only).
+        ydl = YDL({'format': 'best[height>360]'})
+        self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy())
+
     def test_invalid_format_specs(self):
         def assert_syntax_error(format_spec):
             ydl = YDL({'format': format_spec})

test/test_all_urls.py

@@ -101,8 +101,6 @@ class TestAllURLsMatching(unittest.TestCase):
         self.assertMatch(':ytsubs', ['youtube:subscriptions'])
         self.assertMatch(':ytsubscriptions', ['youtube:subscriptions'])
         self.assertMatch(':ythistory', ['youtube:history'])
-        self.assertMatch(':thedailyshow', ['ComedyCentralShows'])
-        self.assertMatch(':tds', ['ComedyCentralShows'])
 
     def test_vimeo_matching(self):
         self.assertMatch('https://vimeo.com/channels/tributes', ['vimeo:channel'])

test/test_utils.py

@@ -42,6 +42,7 @@ from youtube_dl.utils import (
     ohdave_rsa_encrypt,
     OnDemandPagedList,
     orderedSet,
+    parse_age_limit,
     parse_duration,
     parse_filesize,
     parse_count,
@@ -81,6 +82,7 @@ from youtube_dl.utils import (
     cli_option,
     cli_valueless_option,
     cli_bool_option,
+    parse_codecs,
 )
 from youtube_dl.compat import (
     compat_chr,
@@ -307,6 +309,7 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(unified_timestamp('25-09-2014'), 1411603200)
         self.assertEqual(unified_timestamp('27.02.2016 17:30'), 1456594200)
         self.assertEqual(unified_timestamp('UNKNOWN DATE FORMAT'), None)
+        self.assertEqual(unified_timestamp('May 16, 2016 11:15 PM'), 1463440500)
 
     def test_determine_ext(self):
         self.assertEqual(determine_ext('http://example.com/foo/bar.mp4/?download'), 'mp4')
@@ -430,6 +433,20 @@ class TestUtil(unittest.TestCase):
             url_basename('http://media.w3.org/2010/05/sintel/trailer.mp4'),
             'trailer.mp4')
 
+    def test_parse_age_limit(self):
+        self.assertEqual(parse_age_limit(None), None)
+        self.assertEqual(parse_age_limit(False), None)
+        self.assertEqual(parse_age_limit('invalid'), None)
+        self.assertEqual(parse_age_limit(0), 0)
+        self.assertEqual(parse_age_limit(18), 18)
+        self.assertEqual(parse_age_limit(21), 21)
+        self.assertEqual(parse_age_limit(22), None)
+        self.assertEqual(parse_age_limit('18'), 18)
+        self.assertEqual(parse_age_limit('18+'), 18)
+        self.assertEqual(parse_age_limit('PG-13'), 13)
+        self.assertEqual(parse_age_limit('TV-14'), 14)
+        self.assertEqual(parse_age_limit('TV-MA'), 17)
+
     def test_parse_duration(self):
         self.assertEqual(parse_duration(None), None)
         self.assertEqual(parse_duration(False), None)
@@ -608,6 +625,29 @@ class TestUtil(unittest.TestCase):
             limit_length('foo bar baz asd', 12).startswith('foo bar'))
         self.assertTrue('...' in limit_length('foo bar baz asd', 12))
 
+    def test_parse_codecs(self):
+        self.assertEqual(parse_codecs(''), {})
+        self.assertEqual(parse_codecs('avc1.77.30, mp4a.40.2'), {
+            'vcodec': 'avc1.77.30',
+            'acodec': 'mp4a.40.2',
+        })
+        self.assertEqual(parse_codecs('mp4a.40.2'), {
+            'vcodec': 'none',
+            'acodec': 'mp4a.40.2',
+        })
+        self.assertEqual(parse_codecs('mp4a.40.5,avc1.42001e'), {
+            'vcodec': 'avc1.42001e',
+            'acodec': 'mp4a.40.5',
+        })
+        self.assertEqual(parse_codecs('avc3.640028'), {
+            'vcodec': 'avc3.640028',
+            'acodec': 'none',
+        })
+        self.assertEqual(parse_codecs(', h264,,newcodec,aac'), {
+            'vcodec': 'h264',
+            'acodec': 'aac',
+        })
+
     def test_escape_rfc3986(self):
         reserved = "!*'();:@&=+$,/?#[]"
         unreserved = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_.~'
@@ -928,6 +968,7 @@ The first line
         self.assertEqual(cli_option({'proxy': '127.0.0.1:3128'}, '--proxy', 'proxy'), ['--proxy', '127.0.0.1:3128'])
         self.assertEqual(cli_option({'proxy': None}, '--proxy', 'proxy'), [])
         self.assertEqual(cli_option({}, '--proxy', 'proxy'), [])
+        self.assertEqual(cli_option({'retries': 10}, '--retries', 'retries'), ['--retries', '10'])
 
     def test_cli_valueless_option(self):
         self.assertEqual(cli_valueless_option(

test/test_verbose_output.py

@@ -0,0 +1,70 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+from __future__ import unicode_literals
+
+import unittest
+
+import sys
+import os
+import subprocess
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+rootDir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+
+
+class TestVerboseOutput(unittest.TestCase):
+    def test_private_info_arg(self):
+        outp = subprocess.Popen(
+            [
+                sys.executable, 'youtube_dl/__main__.py', '-v',
+                '--username', 'johnsmith@gmail.com',
+                '--password', 'secret',
+            ], cwd=rootDir, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+        sout, serr = outp.communicate()
+        self.assertTrue(b'--username' in serr)
+        self.assertTrue(b'johnsmith' not in serr)
+        self.assertTrue(b'--password' in serr)
+        self.assertTrue(b'secret' not in serr)
+
+    def test_private_info_shortarg(self):
+        outp = subprocess.Popen(
+            [
+                sys.executable, 'youtube_dl/__main__.py', '-v',
+                '-u', 'johnsmith@gmail.com',
+                '-p', 'secret',
+            ], cwd=rootDir, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+        sout, serr = outp.communicate()
+        self.assertTrue(b'-u' in serr)
+        self.assertTrue(b'johnsmith' not in serr)
+        self.assertTrue(b'-p' in serr)
+        self.assertTrue(b'secret' not in serr)
+
+    def test_private_info_eq(self):
+        outp = subprocess.Popen(
+            [
+                sys.executable, 'youtube_dl/__main__.py', '-v',
+                '--username=johnsmith@gmail.com',
+                '--password=secret',
+            ], cwd=rootDir, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+        sout, serr = outp.communicate()
+        self.assertTrue(b'--username' in serr)
+        self.assertTrue(b'johnsmith' not in serr)
+        self.assertTrue(b'--password' in serr)
+        self.assertTrue(b'secret' not in serr)
+
+    def test_private_info_shortarg_eq(self):
+        outp = subprocess.Popen(
+            [
+                sys.executable, 'youtube_dl/__main__.py', '-v',
+                '-u=johnsmith@gmail.com',
+                '-p=secret',
+            ], cwd=rootDir, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+        sout, serr = outp.communicate()
+        self.assertTrue(b'-u' in serr)
+        self.assertTrue(b'johnsmith' not in serr)
+        self.assertTrue(b'-p' in serr)
+        self.assertTrue(b'secret' not in serr)
+
+if __name__ == '__main__':
+    unittest.main()

youtube_dl/YoutubeDL.py

@@ -5,6 +5,7 @@ from __future__ import absolute_import, unicode_literals
 
 import collections
 import contextlib
+import copy
 import datetime
 import errno
 import fileinput
@@ -248,7 +249,16 @@ class YoutubeDL(object):
     source_address:    (Experimental) Client-side IP address to bind to.
     call_home:         Boolean, true iff we are allowed to contact the
                        youtube-dl servers for debugging.
-    sleep_interval:    Number of seconds to sleep before each download.
+    sleep_interval:    Number of seconds to sleep before each download when
+                       used alone or a lower bound of a range for randomized
+                       sleep before each download (minimum possible number
+                       of seconds to sleep) when used along with
+                       max_sleep_interval.
+    max_sleep_interval:Upper bound of a range for randomized sleep before each
+                       download (maximum possible number of seconds to sleep).
+                       Must only be used along with sleep_interval.
+                       Actual sleep time will be a random float from range
+                       [sleep_interval; max_sleep_interval].
     listformats:       Print an overview of available video formats and exit.
     list_thumbnails:   Print a table of all thumbnails and exit.
     match_filter:      A function that gets called with the info_dict of
@@ -1051,9 +1061,9 @@ class YoutubeDL(object):
             if isinstance(selector, list):
                 fs = [_build_selector_function(s) for s in selector]
 
-                def selector_function(formats):
+                def selector_function(ctx):
                     for f in fs:
-                        for format in f(formats):
+                        for format in f(ctx):
                             yield format
                 return selector_function
             elif selector.type == GROUP:
@@ -1061,17 +1071,17 @@ class YoutubeDL(object):
             elif selector.type == PICKFIRST:
                 fs = [_build_selector_function(s) for s in selector.selector]
 
-                def selector_function(formats):
+                def selector_function(ctx):
                     for f in fs:
-                        picked_formats = list(f(formats))
+                        picked_formats = list(f(ctx))
                         if picked_formats:
                             return picked_formats
                     return []
             elif selector.type == SINGLE:
                 format_spec = selector.selector
 
-                def selector_function(formats):
-                    formats = list(formats)
+                def selector_function(ctx):
+                    formats = list(ctx['formats'])
                     if not formats:
                         return
                     if format_spec == 'all':
@@ -1084,9 +1094,10 @@ class YoutubeDL(object):
                             if f.get('vcodec') != 'none' and f.get('acodec') != 'none']
                         if audiovideo_formats:
                             yield audiovideo_formats[format_idx]
-                        # for audio only (soundcloud) or video only (imgur) urls, select the best/worst audio format
-                        elif (all(f.get('acodec') != 'none' for f in formats) or
-                              all(f.get('vcodec') != 'none' for f in formats)):
+                        # for extractors with incomplete formats (audio only (soundcloud)
+                        # or video only (imgur)) we will fallback to best/worst
+                        # {video,audio}-only format
+                        elif ctx['incomplete_formats']:
                             yield formats[format_idx]
                     elif format_spec == 'bestaudio':
                         audio_formats = [
@@ -1160,17 +1171,18 @@ class YoutubeDL(object):
                     }
                 video_selector, audio_selector = map(_build_selector_function, selector.selector)
 
-                def selector_function(formats):
-                    formats = list(formats)
-                    for pair in itertools.product(video_selector(formats), audio_selector(formats)):
+                def selector_function(ctx):
+                    for pair in itertools.product(
+                            video_selector(copy.deepcopy(ctx)), audio_selector(copy.deepcopy(ctx))):
                         yield _merge(pair)
 
             filters = [self._build_format_filter(f) for f in selector.filters]
 
-            def final_selector(formats):
+            def final_selector(ctx):
+                ctx_copy = copy.deepcopy(ctx)
                 for _filter in filters:
-                    formats = list(filter(_filter, formats))
-                return selector_function(formats)
+                    ctx_copy['formats'] = list(filter(_filter, ctx_copy['formats']))
+                return selector_function(ctx_copy)
             return final_selector
 
         stream = io.BytesIO(format_spec.encode('utf-8'))
@@ -1377,7 +1389,34 @@ class YoutubeDL(object):
             req_format_list.append('best')
             req_format = '/'.join(req_format_list)
         format_selector = self.build_format_selector(req_format)
-        formats_to_download = list(format_selector(formats))
+
+        # While in format selection we may need to have an access to the original
+        # format set in order to calculate some metrics or do some processing.
+        # For now we need to be able to guess whether original formats provided
+        # by extractor are incomplete or not (i.e. whether extractor provides only
+        # video-only or audio-only formats) for proper formats selection for
+        # extractors with such incomplete formats (see
+        # https://github.com/rg3/youtube-dl/pull/5556).
+        # Since formats may be filtered during format selection and may not match
+        # the original formats the results may be incorrect. Thus original formats
+        # or pre-calculated metrics should be passed to format selection routines
+        # as well.
+        # We will pass a context object containing all necessary additional data
+        # instead of just formats.
+        # This fixes incorrect format selection issue (see
+        # https://github.com/rg3/youtube-dl/issues/10083).
+        incomplete_formats = (
+            # All formats are video-only or
+            all(f.get('vcodec') != 'none' and f.get('acodec') == 'none' for f in formats) or
+            # all formats are audio-only
+            all(f.get('vcodec') == 'none' and f.get('acodec') != 'none' for f in formats))
+
+        ctx = {
+            'formats': formats,
+            'incomplete_formats': incomplete_formats,
+        }
+
+        formats_to_download = list(format_selector(ctx))
         if not formats_to_download:
             raise ExtractorError('requested format not available',
                                  expected=True)
@@ -1564,7 +1603,9 @@ class YoutubeDL(object):
                         self.to_screen('[info] Video subtitle %s.%s is already_present' % (sub_lang, sub_format))
                     else:
                         self.to_screen('[info] Writing video subtitles to: ' + sub_filename)
-                        with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8') as subfile:
+                        # Use newline='' to prevent conversion of newline characters
+                        # See https://github.com/rg3/youtube-dl/issues/10268
+                        with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8', newline='') as subfile:
                             subfile.write(sub_data)
                 except (OSError, IOError):
                     self.report_error('Cannot write subtitles file ' + sub_filename)

youtube_dl/__init__.py

@@ -145,6 +145,16 @@ def _real_main(argv=None):
         if numeric_limit is None:
             parser.error('invalid max_filesize specified')
         opts.max_filesize = numeric_limit
+    if opts.sleep_interval is not None:
+        if opts.sleep_interval < 0:
+            parser.error('sleep interval must be positive or 0')
+    if opts.max_sleep_interval is not None:
+        if opts.max_sleep_interval < 0:
+            parser.error('max sleep interval must be positive or 0')
+        if opts.max_sleep_interval < opts.sleep_interval:
+            parser.error('max sleep interval must be greater than or equal to min sleep interval')
+    else:
+        opts.max_sleep_interval = opts.sleep_interval
 
     def parse_retries(retries):
         if retries in ('inf', 'infinite'):
@@ -370,6 +380,7 @@ def _real_main(argv=None):
         'source_address': opts.source_address,
         'call_home': opts.call_home,
         'sleep_interval': opts.sleep_interval,
+        'max_sleep_interval': opts.max_sleep_interval,
         'external_downloader': opts.external_downloader,
         'list_thumbnails': opts.list_thumbnails,
         'playlist_items': opts.playlist_items,

youtube_dl/downloader/common.py

@@ -4,6 +4,7 @@ import os
 import re
 import sys
 import time
+import random
 
 from ..compat import compat_os_name
 from ..utils import (
@@ -342,8 +343,11 @@ class FileDownloader(object):
             })
             return True
 
-        sleep_interval = self.params.get('sleep_interval')
-        if sleep_interval:
+        min_sleep_interval = self.params.get('sleep_interval')
+        if min_sleep_interval:
+            max_sleep_interval = self.params.get('max_sleep_interval', min_sleep_interval)
+            print(min_sleep_interval, max_sleep_interval)
+            sleep_interval = random.uniform(min_sleep_interval, max_sleep_interval)
             self.to_screen('[download] Sleeping %s seconds...' % sleep_interval)
             time.sleep(sleep_interval)
 

youtube_dl/downloader/external.py

@@ -96,6 +96,12 @@ class CurlFD(ExternalFD):
         cmd = [self.exe, '--location', '-o', tmpfilename]
         for key, val in info_dict['http_headers'].items():
             cmd += ['--header', '%s: %s' % (key, val)]
+        cmd += self._bool_option('--continue-at', 'continuedl', '-', '0')
+        cmd += self._valueless_option('--silent', 'noprogress')
+        cmd += self._valueless_option('--verbose', 'verbose')
+        cmd += self._option('--limit-rate', 'ratelimit')
+        cmd += self._option('--retry', 'retries')
+        cmd += self._option('--max-filesize', 'max_filesize')
         cmd += self._option('--interface', 'source_address')
         cmd += self._option('--proxy', 'proxy')
         cmd += self._valueless_option('--insecure', 'nocheckcertificate')
@@ -103,6 +109,16 @@ class CurlFD(ExternalFD):
         cmd += ['--', info_dict['url']]
         return cmd
 
+    def _call_downloader(self, tmpfilename, info_dict):
+        cmd = [encodeArgument(a) for a in self._make_cmd(tmpfilename, info_dict)]
+
+        self._debug_cmd(cmd)
+
+        # curl writes the progress to stderr so don't capture it.
+        p = subprocess.Popen(cmd)
+        p.communicate()
+        return p.returncode
+
 
 class AxelFD(ExternalFD):
     AVAILABLE_OPT = '-V'

youtube_dl/downloader/hls.py

@@ -20,6 +20,7 @@ from ..utils import (
     encodeFilename,
     sanitize_open,
     parse_m3u8_attributes,
+    update_url_query,
 )
 
 
@@ -82,6 +83,7 @@ class HlsFD(FragmentFD):
 
         self._prepare_and_start_frag_download(ctx)
 
+        extra_param_to_segment_url = info_dict.get('extra_param_to_segment_url')
         i = 0
         media_sequence = 0
         decrypt_info = {'METHOD': 'NONE'}
@@ -95,6 +97,8 @@ class HlsFD(FragmentFD):
                         if re.match(r'^https?://', line)
                         else compat_urlparse.urljoin(man_url, line))
                     frag_filename = '%s-Frag%d' % (ctx['tmpfilename'], i)
+                    if extra_param_to_segment_url:
+                        frag_url = update_url_query(frag_url, extra_param_to_segment_url)
                     success = ctx['dl'].download(frag_filename, {'url': frag_url})
                     if not success:
                         return False
@@ -120,6 +124,8 @@ class HlsFD(FragmentFD):
                         if not re.match(r'^https?://', decrypt_info['URI']):
                             decrypt_info['URI'] = compat_urlparse.urljoin(
                                 man_url, decrypt_info['URI'])
+                        if extra_param_to_segment_url:
+                            decrypt_info['URI'] = update_url_query(decrypt_info['URI'], extra_param_to_segment_url)
                         decrypt_info['KEY'] = self.ydl.urlopen(decrypt_info['URI']).read()
                 elif line.startswith('#EXT-X-MEDIA-SEQUENCE'):
                     media_sequence = int(line[22:])

youtube_dl/extractor/adobepass.py

@@ -0,0 +1,134 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+
+import re
+import time
+import xml.etree.ElementTree as etree
+
+from .common import InfoExtractor
+from ..utils import (
+    unescapeHTML,
+    urlencode_postdata,
+    unified_timestamp,
+)
+
+
+class AdobePassIE(InfoExtractor):
+    _SERVICE_PROVIDER_TEMPLATE = 'https://sp.auth.adobe.com/adobe-services/%s'
+    _USER_AGENT = 'Mozilla/5.0 (X11; Linux i686; rv:47.0) Gecko/20100101 Firefox/47.0'
+
+    @staticmethod
+    def _get_mvpd_resource(provider_id, title, guid, rating):
+        channel = etree.Element('channel')
+        channel_title = etree.SubElement(channel, 'title')
+        channel_title.text = provider_id
+        item = etree.SubElement(channel, 'item')
+        resource_title = etree.SubElement(item, 'title')
+        resource_title.text = title
+        resource_guid = etree.SubElement(item, 'guid')
+        resource_guid.text = guid
+        resource_rating = etree.SubElement(item, 'media:rating')
+        resource_rating.attrib = {'scheme': 'urn:v-chip'}
+        resource_rating.text = rating
+        return '<rss version="2.0" xmlns:media="http://search.yahoo.com/mrss/">' + etree.tostring(channel).decode() + '</rss>'
+
+    def _extract_mvpd_auth(self, url, video_id, requestor_id, resource):
+        def xml_text(xml_str, tag):
+            return self._search_regex(
+                '<%s>(.+?)</%s>' % (tag, tag), xml_str, tag)
+
+        mvpd_headers = {
+            'ap_42': 'anonymous',
+            'ap_11': 'Linux i686',
+            'ap_z': self._USER_AGENT,
+            'User-Agent': self._USER_AGENT,
+        }
+
+        guid = xml_text(resource, 'guid')
+        requestor_info = self._downloader.cache.load('mvpd', requestor_id) or {}
+        authn_token = requestor_info.get('authn_token')
+        if authn_token:
+            token_expires = unified_timestamp(re.sub(r'[_ ]GMT', '', xml_text(authn_token, 'simpleTokenExpires')))
+            if token_expires and token_expires <= int(time.time()):
+                authn_token = None
+                requestor_info = {}
+        if not authn_token:
+            # TODO add support for other TV Providers
+            mso_id = 'DTV'
+            username, password = self._get_netrc_login_info(mso_id)
+            if not username or not password:
+                return ''
+
+            def post_form(form_page, note, data={}):
+                post_url = self._html_search_regex(r'<form[^>]+action=(["\'])(?P<url>.+?)\1', form_page, 'post url', group='url')
+                return self._download_webpage(
+                    post_url, video_id, note, data=urlencode_postdata(data or self._hidden_inputs(form_page)), headers={
+                        'Content-Type': 'application/x-www-form-urlencoded',
+                    })
+
+            provider_redirect_page = self._download_webpage(
+                self._SERVICE_PROVIDER_TEMPLATE % 'authenticate/saml', video_id,
+                'Downloading Provider Redirect Page', query={
+                    'noflash': 'true',
+                    'mso_id': mso_id,
+                    'requestor_id': requestor_id,
+                    'no_iframe': 'false',
+                    'domain_name': 'adobe.com',
+                    'redirect_url': url,
+                })
+            provider_login_page = post_form(
+                provider_redirect_page, 'Downloading Provider Login Page')
+            mvpd_confirm_page = post_form(provider_login_page, 'Logging in', {
+                'username': username,
+                'password': password,
+            })
+            post_form(mvpd_confirm_page, 'Confirming Login')
+
+            session = self._download_webpage(
+                self._SERVICE_PROVIDER_TEMPLATE % 'session', video_id,
+                'Retrieving Session', data=urlencode_postdata({
+                    '_method': 'GET',
+                    'requestor_id': requestor_id,
+                }), headers=mvpd_headers)
+            if '<pendingLogout' in session:
+                self._downloader.cache.store('mvpd', requestor_id, {})
+                return self._extract_mvpd_auth(url, video_id, requestor_id, resource)
+            authn_token = unescapeHTML(xml_text(session, 'authnToken'))
+            requestor_info['authn_token'] = authn_token
+            self._downloader.cache.store('mvpd', requestor_id, requestor_info)
+
+        authz_token = requestor_info.get(guid)
+        if not authz_token:
+            authorize = self._download_webpage(
+                self._SERVICE_PROVIDER_TEMPLATE % 'authorize', video_id,
+                'Retrieving Authorization Token', data=urlencode_postdata({
+                    'resource_id': resource,
+                    'requestor_id': requestor_id,
+                    'authentication_token': authn_token,
+                    'mso_id': xml_text(authn_token, 'simpleTokenMsoID'),
+                    'userMeta': '1',
+                }), headers=mvpd_headers)
+            if '<pendingLogout' in authorize:
+                self._downloader.cache.store('mvpd', requestor_id, {})
+                return self._extract_mvpd_auth(url, video_id, requestor_id, resource)
+            authz_token = unescapeHTML(xml_text(authorize, 'authzToken'))
+            requestor_info[guid] = authz_token
+            self._downloader.cache.store('mvpd', requestor_id, requestor_info)
+
+        mvpd_headers.update({
+            'ap_19': xml_text(authn_token, 'simpleSamlNameID'),
+            'ap_23': xml_text(authn_token, 'simpleSamlSessionIndex'),
+        })
+
+        short_authorize = self._download_webpage(
+            self._SERVICE_PROVIDER_TEMPLATE % 'shortAuthorize',
+            video_id, 'Retrieving Media Token', data=urlencode_postdata({
+                'authz_token': authz_token,
+                'requestor_id': requestor_id,
+                'session_guid': xml_text(authn_token, 'simpleTokenAuthenticationGuid'),
+                'hashed_guid': 'false',
+            }), headers=mvpd_headers)
+        if '<pendingLogout' in short_authorize:
+            self._downloader.cache.store('mvpd', requestor_id, {})
+            return self._extract_mvpd_auth(url, video_id, requestor_id, resource)
+        return short_authorize

youtube_dl/extractor/adultswim.py

@@ -83,6 +83,20 @@ class AdultSwimIE(InfoExtractor):
             # m3u8 download
             'skip_download': True,
         }
+    }, {
+        # heroMetadata.trailer
+        'url': 'http://www.adultswim.com/videos/decker/inside-decker-a-new-hero/',
+        'info_dict': {
+            'id': 'I0LQFQkaSUaFp8PnAWHhoQ',
+            'ext': 'mp4',
+            'title': 'Decker - Inside Decker: A New Hero',
+            'description': 'md5:c916df071d425d62d70c86d4399d3ee0',
+            'duration': 249.008,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        }
     }]
 
     @staticmethod
@@ -133,20 +147,26 @@ class AdultSwimIE(InfoExtractor):
             if video_info is None:
                 if bootstrapped_data.get('slugged_video', {}).get('slug') == episode_path:
                     video_info = bootstrapped_data['slugged_video']
-                else:
-                    raise ExtractorError('Unable to find video info')
+            if not video_info:
+                video_info = bootstrapped_data.get('heroMetadata', {}).get('trailer').get('video')
+            if not video_info:
+                raise ExtractorError('Unable to find video info')
 
             show = bootstrapped_data['show']
             show_title = show['title']
             stream = video_info.get('stream')
-            clips = [stream] if stream else video_info.get('clips')
-            if not clips:
+            if stream and stream.get('videoPlaybackID'):
+                segment_ids = [stream['videoPlaybackID']]
+            elif video_info.get('clips'):
+                segment_ids = [clip['videoPlaybackID'] for clip in video_info['clips']]
+            elif video_info.get('videoPlaybackID'):
+                segment_ids = [video_info['videoPlaybackID']]
+            else:
                 raise ExtractorError(
                     'This video is only available via cable service provider subscription that'
                     ' is not currently supported. You may want to use --cookies.'
                     if video_info.get('auth') is True else 'Unable to find stream or clips',
                     expected=True)
-            segment_ids = [clip['videoPlaybackID'] for clip in clips]
 
         episode_id = video_info['id']
         episode_title = video_info['title']

youtube_dl/extractor/aenetworks.py

@@ -109,7 +109,10 @@ class AENetworksIE(AENetworksBaseIE):
         info = self._parse_theplatform_metadata(theplatform_metadata)
         if theplatform_metadata.get('AETN$isBehindWall'):
             requestor_id = self._DOMAIN_TO_REQUESTOR_ID[domain]
-            resource = '<rss version="2.0" xmlns:media="http://search.yahoo.com/mrss/"><channel><title>%s</title><item><title>%s</title><guid>%s</guid><media:rating scheme="urn:v-chip">%s</media:rating></item></channel></rss>' % (requestor_id, theplatform_metadata['title'], theplatform_metadata['AETN$PPL_pplProgramId'], theplatform_metadata['ratings'][0]['rating'])
+            resource = self._get_mvpd_resource(
+                requestor_id, theplatform_metadata['title'],
+                theplatform_metadata.get('AETN$PPL_pplProgramId') or theplatform_metadata.get('AETN$PPL_pplProgramId_OLD'),
+                theplatform_metadata['ratings'][0]['rating'])
             query['auth'] = self._extract_mvpd_auth(
                 url, video_id, requestor_id, resource)
         info.update(self._search_json_ld(webpage, video_id, fatal=False))

youtube_dl/extractor/amcnetworks.py

@@ -0,0 +1,91 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .theplatform import ThePlatformIE
+from ..utils import (
+    update_url_query,
+    parse_age_limit,
+    int_or_none,
+)
+
+
+class AMCNetworksIE(ThePlatformIE):
+    _VALID_URL = r'https?://(?:www\.)?(?:amc|bbcamerica|ifc|wetv)\.com/(?:movies/|shows/[^/]+/(?:full-episodes/)?season-\d+/episode-\d+(?:-(?:[^/]+/)?|/))(?P<id>[^/?#]+)'
+    _TESTS = [{
+        'url': 'http://www.ifc.com/shows/maron/season-04/episode-01/step-1',
+        'md5': '',
+        'info_dict': {
+            'id': 's3MX01Nl4vPH',
+            'ext': 'mp4',
+            'title': 'Maron - Season 4 - Step 1',
+            'description': 'In denial about his current situation, Marc is reluctantly convinced by his friends to enter rehab. Starring Marc Maron and Constance Zimmer.',
+            'age_limit': 17,
+            'upload_date': '20160505',
+            'timestamp': 1462468831,
+            'uploader': 'AMCN',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://www.bbcamerica.com/shows/the-hunt/full-episodes/season-1/episode-01-the-hardest-challenge',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.amc.com/shows/preacher/full-episodes/season-01/episode-00/pilot',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.wetv.com/shows/million-dollar-matchmaker/season-01/episode-06-the-dumped-dj-and-shallow-hal',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.ifc.com/movies/chaos',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        query = {
+            'mbr': 'true',
+            'manifest': 'm3u',
+        }
+        media_url = self._search_regex(r'window\.platformLinkURL\s*=\s*[\'"]([^\'"]+)', webpage, 'media url')
+        theplatform_metadata = self._download_theplatform_metadata(self._search_regex(
+            r'https?://link.theplatform.com/s/([^?]+)', media_url, 'theplatform_path'), display_id)
+        info = self._parse_theplatform_metadata(theplatform_metadata)
+        video_id = theplatform_metadata['pid']
+        title = theplatform_metadata['title']
+        rating = theplatform_metadata['ratings'][0]['rating']
+        auth_required = self._search_regex(r'window\.authRequired\s*=\s*(true|false);', webpage, 'auth required')
+        if auth_required == 'true':
+            requestor_id = self._search_regex(r'window\.requestor_id\s*=\s*[\'"]([^\'"]+)', webpage, 'requestor id')
+            resource = self._get_mvpd_resource(requestor_id, title, video_id, rating)
+            query['auth'] = self._extract_mvpd_auth(url, video_id, requestor_id, resource)
+        media_url = update_url_query(media_url, query)
+        formats, subtitles = self._extract_theplatform_smil(media_url, video_id)
+        self._sort_formats(formats)
+        info.update({
+            'id': video_id,
+            'subtitles': subtitles,
+            'formats': formats,
+            'age_limit': parse_age_limit(parse_age_limit(rating)),
+        })
+        ns_keys = theplatform_metadata.get('$xmlns', {}).keys()
+        if ns_keys:
+            ns = list(ns_keys)[0]
+            series = theplatform_metadata.get(ns + '$show')
+            season_number = int_or_none(theplatform_metadata.get(ns + '$season'))
+            episode = theplatform_metadata.get(ns + '$episodeTitle')
+            episode_number = int_or_none(theplatform_metadata.get(ns + '$episode'))
+            if season_number:
+                title = 'Season %d - %s' % (season_number, title)
+            if series:
+                title = '%s - %s' % (series, title)
+            info.update({
+                'title': title,
+                'series': series,
+                'season_number': season_number,
+                'episode': episode,
+                'episode_number': episode_number,
+            })
+        return info

youtube_dl/extractor/animeondemand.py

@@ -203,7 +203,7 @@ class AnimeOnDemandIE(InfoExtractor):
                 'formats': formats,
             }
 
-        def extract_entries(html, video_id, common_info, num):
+        def extract_entries(html, video_id, common_info, num=None):
             info = extract_info(html, video_id, num)
 
             if info['formats']:

youtube_dl/extractor/aol.py

@@ -123,6 +123,10 @@ class AolFeaturesIE(InfoExtractor):
             'title': 'What To Watch - February 17, 2016',
         },
         'add_ie': ['FiveMin'],
+        'params': {
+            # encrypted m3u8 download
+            'skip_download': True,
+        },
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/aparat.py

@@ -1,8 +1,6 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
@@ -15,7 +13,7 @@ class AparatIE(InfoExtractor):
 
     _TEST = {
         'url': 'http://www.aparat.com/v/wP8On',
-        'md5': '6714e0af7e0d875c5a39c4dc4ab46ad1',
+        'md5': '131aca2e14fe7c4dcb3c4877ba300c89',
         'info_dict': {
             'id': 'wP8On',
             'ext': 'mp4',
@@ -31,13 +29,13 @@ class AparatIE(InfoExtractor):
         # Note: There is an easier-to-parse configuration at
         # http://www.aparat.com/video/video/config/videohash/%video_id
         # but the URL in there does not work
-        embed_url = ('http://www.aparat.com/video/video/embed/videohash/' +
-                     video_id + '/vt/frame')
+        embed_url = 'http://www.aparat.com/video/video/embed/vt/frame/showvideo/yes/videohash/' + video_id
         webpage = self._download_webpage(embed_url, video_id)
 
-        video_urls = [video_url.replace('\\/', '/') for video_url in re.findall(
-            r'(?:fileList\[[0-9]+\]\s*=|"file"\s*:)\s*"([^"]+)"', webpage)]
-        for i, video_url in enumerate(video_urls):
+        file_list = self._parse_json(self._search_regex(
+            r'fileList\s*=\s*JSON\.parse\(\'([^\']+)\'\)', webpage, 'file list'), video_id)
+        for i, item in enumerate(file_list[0]):
+            video_url = item['file']
             req = HEADRequest(video_url)
             res = self._request_webpage(
                 req, video_id, note='Testing video URL %d' % i, errnote=False)

youtube_dl/extractor/archiveorg.py

@@ -1,67 +1,65 @@
 from __future__ import unicode_literals
 
-from .common import InfoExtractor
-from ..utils import unified_strdate
+from .jwplatform import JWPlatformBaseIE
+from ..utils import (
+    unified_strdate,
+    clean_html,
+)
 
 
-class ArchiveOrgIE(InfoExtractor):
+class ArchiveOrgIE(JWPlatformBaseIE):
     IE_NAME = 'archive.org'
     IE_DESC = 'archive.org videos'
-    _VALID_URL = r'https?://(?:www\.)?archive\.org/details/(?P<id>[^?/]+)(?:[?].*)?$'
+    _VALID_URL = r'https?://(?:www\.)?archive\.org/(?:details|embed)/(?P<id>[^/?#]+)(?:[?].*)?$'
     _TESTS = [{
         'url': 'http://archive.org/details/XD300-23_68HighlightsAResearchCntAugHumanIntellect',
         'md5': '8af1d4cf447933ed3c7f4871162602db',
         'info_dict': {
             'id': 'XD300-23_68HighlightsAResearchCntAugHumanIntellect',
-            'ext': 'ogv',
+            'ext': 'ogg',
             'title': '1968 Demo - FJCC Conference Presentation Reel #1',
-            'description': 'md5:1780b464abaca9991d8968c877bb53ed',
+            'description': 'md5:da45c349df039f1cc8075268eb1b5c25',
             'upload_date': '19681210',
             'uploader': 'SRI International'
         }
     }, {
         'url': 'https://archive.org/details/Cops1922',
-        'md5': '18f2a19e6d89af8425671da1cf3d4e04',
+        'md5': 'bc73c8ab3838b5a8fc6c6651fa7b58ba',
         'info_dict': {
             'id': 'Cops1922',
-            'ext': 'ogv',
+            'ext': 'mp4',
             'title': 'Buster Keaton\'s "Cops" (1922)',
-            'description': 'md5:70f72ee70882f713d4578725461ffcc3',
+            'description': 'md5:b4544662605877edd99df22f9620d858',
         }
+    }, {
+        'url': 'http://archive.org/embed/XD300-23_68HighlightsAResearchCntAugHumanIntellect',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
+        webpage = self._download_webpage(
+            'http://archive.org/embed/' + video_id, video_id)
+        jwplayer_playlist = self._parse_json(self._search_regex(
+            r"(?s)Play\('[^']+'\s*,\s*(\[.+\])\s*,\s*{.*?}\);",
+            webpage, 'jwplayer playlist'), video_id)
+        info = self._parse_jwplayer_data(
+            {'playlist': jwplayer_playlist}, video_id, base_url=url)
 
-        json_url = url + ('&' if '?' in url else '?') + 'output=json'
-        data = self._download_json(json_url, video_id)
+        def get_optional(metadata, field):
+            return metadata.get(field, [None])[0]
 
-        def get_optional(data_dict, field):
-            return data_dict['metadata'].get(field, [None])[0]
-
-        title = get_optional(data, 'title')
-        description = get_optional(data, 'description')
-        uploader = get_optional(data, 'creator')
-        upload_date = unified_strdate(get_optional(data, 'date'))
-
-        formats = [
-            {
-                'format': fdata['format'],
-                'url': 'http://' + data['server'] + data['dir'] + fn,
-                'file_size': int(fdata['size']),
-            }
-            for fn, fdata in data['files'].items()
-            if 'Video' in fdata['format']]
-
-        self._sort_formats(formats)
-
-        return {
-            '_type': 'video',
-            'id': video_id,
-            'title': title,
-            'formats': formats,
-            'description': description,
-            'uploader': uploader,
-            'upload_date': upload_date,
-            'thumbnail': data.get('misc', {}).get('image'),
-        }
+        metadata = self._download_json(
+            'http://archive.org/details/' + video_id, video_id, query={
+                'output': 'json',
+            })['metadata']
+        info.update({
+            'title': get_optional(metadata, 'title') or info.get('title'),
+            'description': clean_html(get_optional(metadata, 'description')),
+        })
+        if info.get('_type') != 'playlist':
+            info.update({
+                'uploader': get_optional(metadata, 'creator'),
+                'upload_date': unified_strdate(get_optional(metadata, 'date')),
+            })
+        return info

youtube_dl/extractor/ard.py

@@ -20,7 +20,7 @@ from ..compat import compat_etree_fromstring
 
 class ARDMediathekIE(InfoExtractor):
     IE_NAME = 'ARD:mediathek'
-    _VALID_URL = r'^https?://(?:(?:www\.)?ardmediathek\.de|mediathek\.daserste\.de)/(?:.*/)(?P<video_id>[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?'
+    _VALID_URL = r'^https?://(?:(?:www\.)?ardmediathek\.de|mediathek\.(?:daserste|rbb-online)\.de)/(?:.*/)(?P<video_id>[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?'
 
     _TESTS = [{
         'url': 'http://www.ardmediathek.de/tv/Dokumentation-und-Reportage/Ich-liebe-das-Leben-trotzdem/rbb-Fernsehen/Video?documentId=29582122&bcastId=3822114',
@@ -62,6 +62,18 @@ class ARDMediathekIE(InfoExtractor):
     }, {
         'url': 'http://mediathek.daserste.de/sendungen_a-z/328454_anne-will/22429276_vertrauen-ist-gut-spionieren-ist-besser-geht',
         'only_matching': True,
+    }, {
+        # audio
+        'url': 'http://mediathek.rbb-online.de/radio/Hörspiel/Vor-dem-Fest/kulturradio/Audio?documentId=30796318&topRessort=radio&bcastId=9839158',
+        'md5': '4e8f00631aac0395fee17368ac0e9867',
+        'info_dict': {
+            'id': '30796318',
+            'ext': 'mp3',
+            'title': 'Vor dem Fest',
+            'description': 'md5:c0c1c8048514deaed2a73b3a60eecacb',
+            'duration': 3287,
+        },
+        'skip': 'Video is no longer available',
     }]
 
     def _extract_media_info(self, media_info_url, webpage, video_id):

youtube_dl/extractor/arkena.py

@@ -0,0 +1,115 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    determine_ext,
+    float_or_none,
+    int_or_none,
+    mimetype2ext,
+    parse_iso8601,
+    strip_jsonp,
+)
+
+
+class ArkenaIE(InfoExtractor):
+    _VALID_URL = r'https?://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',
+        'info_dict': {
+            'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
+            'ext': 'mp4',
+            'title': 'Big Buck Bunny',
+            'description': 'Royalty free test video',
+            'timestamp': 1432816365,
+            'upload_date': '20150528',
+            'is_live': False,
+        },
+    }, {
+        'url': 'https://play.arkena.com/config/avp/v2/player/media/b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe/1/129411/?callbackMethod=jQuery1111023664739129262213_1469227693893',
+        'only_matching': True,
+    }, {
+        'url': 'http://play.arkena.com/config/avp/v1/player/media/327336/darkmatter/131064/?callbackMethod=jQuery1111002221189684892677_1469227595972',
+        'only_matching': True,
+    }, {
+        'url': 'http://play.arkena.com/embed/avp/v1/player/media/327336/darkmatter/131064/',
+        'only_matching': True,
+    }]
+
+    @staticmethod
+    def _extract_url(webpage):
+        # See https://support.arkena.com/display/PLAY/Ways+to+embed+your+video
+        mobj = re.search(
+            r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//play\.arkena\.com/embed/avp/.+?)\1',
+            webpage)
+        if mobj:
+            return mobj.group('url')
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        account_id = mobj.group('account_id')
+
+        playlist = self._download_json(
+            'https://play.arkena.com/config/avp/v2/player/media/%s/0/%s/?callbackMethod=_'
+            % (video_id, account_id),
+            video_id, transform_source=strip_jsonp)['Playlist'][0]
+
+        media_info = playlist['MediaInfo']
+        title = media_info['Title']
+        media_files = playlist['MediaFiles']
+
+        is_live = False
+        formats = []
+        for kind_case, kind_formats in media_files.items():
+            kind = kind_case.lower()
+            for f in kind_formats:
+                f_url = f.get('Url')
+                if not f_url:
+                    continue
+                is_live = f.get('Live') == 'true'
+                exts = (mimetype2ext(f.get('Type')), determine_ext(f_url, None))
+                if kind == 'm3u8' or 'm3u8' in exts:
+                    formats.extend(self._extract_m3u8_formats(
+                        f_url, video_id, 'mp4',
+                        entry_protocol='m3u8' if is_live else 'm3u8_native',
+                        m3u8_id=kind, fatal=False, live=is_live))
+                elif kind == 'flash' or 'f4m' in exts:
+                    formats.extend(self._extract_f4m_formats(
+                        f_url, video_id, f4m_id=kind, fatal=False))
+                elif kind == 'dash' or 'mpd' in exts:
+                    formats.extend(self._extract_mpd_formats(
+                        f_url, video_id, mpd_id=kind, fatal=False))
+                elif kind == 'silverlight':
+                    # TODO: process when ism is supported (see
+                    # https://github.com/rg3/youtube-dl/issues/8118)
+                    continue
+                else:
+                    tbr = float_or_none(f.get('Bitrate'), 1000)
+                    formats.append({
+                        'url': f_url,
+                        'format_id': '%s-%d' % (kind, tbr) if tbr else kind,
+                        'tbr': tbr,
+                    })
+        self._sort_formats(formats)
+
+        description = media_info.get('Description')
+        video_id = media_info.get('VideoId') or video_id
+        timestamp = parse_iso8601(media_info.get('PublishDate'))
+        thumbnails = [{
+            'url': thumbnail['Url'],
+            'width': int_or_none(thumbnail.get('Size')),
+        } for thumbnail in (media_info.get('Poster') or []) if thumbnail.get('Url')]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'timestamp': timestamp,
+            'is_live': is_live,
+            'thumbnails': thumbnails,
+            'formats': formats,
+        }

youtube_dl/extractor/bbc.py

@@ -2,19 +2,23 @@
 from __future__ import unicode_literals
 
 import re
+import itertools
 
 from .common import InfoExtractor
 from ..utils import (
+    dict_get,
     ExtractorError,
     float_or_none,
     int_or_none,
     parse_duration,
     parse_iso8601,
+    try_get,
     unescapeHTML,
 )
 from ..compat import (
     compat_etree_fromstring,
     compat_HTTPError,
+    compat_urlparse,
 )
 
 
@@ -229,51 +233,6 @@ class BBCCoUkIE(InfoExtractor):
         asx = self._download_xml(connection.get('href'), programme_id, 'Downloading ASX playlist')
         return [ref.get('href') for ref in asx.findall('./Entry/ref')]
 
-    def _extract_connection(self, connection, programme_id):
-        formats = []
-        kind = connection.get('kind')
-        protocol = connection.get('protocol')
-        supplier = connection.get('supplier')
-        if protocol == 'http':
-            href = connection.get('href')
-            transfer_format = connection.get('transferFormat')
-            # ASX playlist
-            if supplier == 'asx':
-                for i, ref in enumerate(self._extract_asx_playlist(connection, programme_id)):
-                    formats.append({
-                        'url': ref,
-                        'format_id': 'ref%s_%s' % (i, supplier),
-                    })
-            # Skip DASH until supported
-            elif transfer_format == 'dash':
-                pass
-            elif transfer_format == 'hls':
-                formats.extend(self._extract_m3u8_formats(
-                    href, programme_id, ext='mp4', entry_protocol='m3u8_native',
-                    m3u8_id=supplier, fatal=False))
-            # Direct link
-            else:
-                formats.append({
-                    'url': href,
-                    'format_id': supplier or kind or protocol,
-                })
-        elif protocol == 'rtmp':
-            application = connection.get('application', 'ondemand')
-            auth_string = connection.get('authString')
-            identifier = connection.get('identifier')
-            server = connection.get('server')
-            formats.append({
-                'url': '%s://%s/%s?%s' % (protocol, server, application, auth_string),
-                'play_path': identifier,
-                'app': '%s?%s' % (application, auth_string),
-                'page_url': 'http://www.bbc.co.uk',
-                'player_url': 'http://www.bbc.co.uk/emp/releases/iplayer/revisions/617463_618125_4/617463_618125_4_emp.swf',
-                'rtmp_live': False,
-                'ext': 'flv',
-                'format_id': supplier,
-            })
-        return formats
-
     def _extract_items(self, playlist):
         return playlist.findall('./{%s}item' % self._EMP_PLAYLIST_NS)
 
@@ -294,46 +253,6 @@ class BBCCoUkIE(InfoExtractor):
     def _extract_connections(self, media):
         return self._findall_ns(media, './{%s}connection')
 
-    def _extract_video(self, media, programme_id):
-        formats = []
-        vbr = int_or_none(media.get('bitrate'))
-        vcodec = media.get('encoding')
-        service = media.get('service')
-        width = int_or_none(media.get('width'))
-        height = int_or_none(media.get('height'))
-        file_size = int_or_none(media.get('media_file_size'))
-        for connection in self._extract_connections(media):
-            conn_formats = self._extract_connection(connection, programme_id)
-            for format in conn_formats:
-                format.update({
-                    'width': width,
-                    'height': height,
-                    'vbr': vbr,
-                    'vcodec': vcodec,
-                    'filesize': file_size,
-                })
-                if service:
-                    format['format_id'] = '%s_%s' % (service, format['format_id'])
-            formats.extend(conn_formats)
-        return formats
-
-    def _extract_audio(self, media, programme_id):
-        formats = []
-        abr = int_or_none(media.get('bitrate'))
-        acodec = media.get('encoding')
-        service = media.get('service')
-        for connection in self._extract_connections(media):
-            conn_formats = self._extract_connection(connection, programme_id)
-            for format in conn_formats:
-                format.update({
-                    'format_id': '%s_%s' % (service, format['format_id']),
-                    'abr': abr,
-                    'acodec': acodec,
-                    'vcodec': 'none',
-                })
-            formats.extend(conn_formats)
-        return formats
-
     def _get_subtitles(self, media, programme_id):
         subtitles = {}
         for connection in self._extract_connections(media):
@@ -379,13 +298,87 @@ class BBCCoUkIE(InfoExtractor):
     def _process_media_selector(self, media_selection, programme_id):
         formats = []
         subtitles = None
+        urls = []
 
         for media in self._extract_medias(media_selection):
             kind = media.get('kind')
-            if kind == 'audio':
-                formats.extend(self._extract_audio(media, programme_id))
-            elif kind == 'video':
-                formats.extend(self._extract_video(media, programme_id))
+            if kind in ('video', 'audio'):
+                bitrate = int_or_none(media.get('bitrate'))
+                encoding = media.get('encoding')
+                service = media.get('service')
+                width = int_or_none(media.get('width'))
+                height = int_or_none(media.get('height'))
+                file_size = int_or_none(media.get('media_file_size'))
+                for connection in self._extract_connections(media):
+                    href = connection.get('href')
+                    if href in urls:
+                        continue
+                    if href:
+                        urls.append(href)
+                    conn_kind = connection.get('kind')
+                    protocol = connection.get('protocol')
+                    supplier = connection.get('supplier')
+                    transfer_format = connection.get('transferFormat')
+                    format_id = supplier or conn_kind or protocol
+                    if service:
+                        format_id = '%s_%s' % (service, format_id)
+                    # ASX playlist
+                    if supplier == 'asx':
+                        for i, ref in enumerate(self._extract_asx_playlist(connection, programme_id)):
+                            formats.append({
+                                'url': ref,
+                                'format_id': 'ref%s_%s' % (i, format_id),
+                            })
+                    elif transfer_format == 'dash':
+                        formats.extend(self._extract_mpd_formats(
+                            href, programme_id, mpd_id=format_id, fatal=False))
+                    elif transfer_format == 'hls':
+                        formats.extend(self._extract_m3u8_formats(
+                            href, programme_id, ext='mp4', entry_protocol='m3u8_native',
+                            m3u8_id=format_id, fatal=False))
+                    elif transfer_format == 'hds':
+                        formats.extend(self._extract_f4m_formats(
+                            href, programme_id, f4m_id=format_id, fatal=False))
+                    else:
+                        if not service and not supplier and bitrate:
+                            format_id += '-%d' % bitrate
+                        fmt = {
+                            'format_id': format_id,
+                            'filesize': file_size,
+                        }
+                        if kind == 'video':
+                            fmt.update({
+                                'width': width,
+                                'height': height,
+                                'vbr': bitrate,
+                                'vcodec': encoding,
+                            })
+                        else:
+                            fmt.update({
+                                'abr': bitrate,
+                                'acodec': encoding,
+                                'vcodec': 'none',
+                            })
+                        if protocol == 'http':
+                            # Direct link
+                            fmt.update({
+                                'url': href,
+                            })
+                        elif protocol == 'rtmp':
+                            application = connection.get('application', 'ondemand')
+                            auth_string = connection.get('authString')
+                            identifier = connection.get('identifier')
+                            server = connection.get('server')
+                            fmt.update({
+                                'url': '%s://%s/%s?%s' % (protocol, server, application, auth_string),
+                                'play_path': identifier,
+                                'app': '%s?%s' % (application, auth_string),
+                                'page_url': 'http://www.bbc.co.uk',
+                                'player_url': 'http://www.bbc.co.uk/emp/releases/iplayer/revisions/617463_618125_4/617463_618125_4_emp.swf',
+                                'rtmp_live': False,
+                                'ext': 'flv',
+                            })
+                        formats.append(fmt)
             elif kind == 'captions':
                 subtitles = self.extract_subtitles(media, programme_id)
         return formats, subtitles
@@ -590,6 +583,7 @@ class BBCIE(BBCCoUkIE):
             'id': '150615_telabyad_kentin_cogu',
             'ext': 'mp4',
             'title': "YPG: Tel Abyad'ın tamamı kontrolümüzde",
+            'description': 'md5:33a4805a855c9baf7115fcbde57e7025',
             'timestamp': 1434397334,
             'upload_date': '20150615',
         },
@@ -603,6 +597,7 @@ class BBCIE(BBCCoUkIE):
             'id': '150619_video_honduras_militares_hospitales_corrupcion_aw',
             'ext': 'mp4',
             'title': 'Honduras militariza sus hospitales por nuevo escándalo de corrupción',
+            'description': 'md5:1525f17448c4ee262b64b8f0c9ce66c8',
             'timestamp': 1434713142,
             'upload_date': '20150619',
         },
@@ -652,6 +647,23 @@ class BBCIE(BBCCoUkIE):
             # rtmp download
             'skip_download': True,
         }
+    }, {
+        # single video embedded with Morph
+        'url': 'http://www.bbc.co.uk/sport/live/olympics/36895975',
+        'info_dict': {
+            'id': 'p041vhd0',
+            'ext': 'mp4',
+            'title': "Nigeria v Japan - Men's First Round",
+            'description': 'Live coverage of the first round from Group B at the Amazonia Arena.',
+            'duration': 7980,
+            'uploader': 'BBC Sport',
+            'uploader_id': 'bbc_sport',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+        'skip': 'Georestricted to UK',
     }, {
         # single video with playlist.sxml URL in playlist param
         'url': 'http://www.bbc.com/sport/0/football/33653409',
@@ -749,7 +761,7 @@ class BBCIE(BBCCoUkIE):
 
         webpage = self._download_webpage(url, playlist_id)
 
-        json_ld_info = self._search_json_ld(webpage, playlist_id, default=None)
+        json_ld_info = self._search_json_ld(webpage, playlist_id, default={})
         timestamp = json_ld_info.get('timestamp')
 
         playlist_title = json_ld_info.get('title')
@@ -818,8 +830,29 @@ class BBCIE(BBCCoUkIE):
                         # http://www.bbc.com/turkce/multimedya/2015/10/151010_vid_ankara_patlama_ani)
                         playlist = data_playable.get('otherSettings', {}).get('playlist', {})
                         if playlist:
-                            entries.append(self._extract_from_playlist_sxml(
-                                playlist.get('progressiveDownloadUrl'), playlist_id, timestamp))
+                            entry = None
+                            for key in ('streaming', 'progressiveDownload'):
+                                playlist_url = playlist.get('%sUrl' % key)
+                                if not playlist_url:
+                                    continue
+                                try:
+                                    info = self._extract_from_playlist_sxml(
+                                        playlist_url, playlist_id, timestamp)
+                                    if not entry:
+                                        entry = info
+                                    else:
+                                        entry['title'] = info['title']
+                                        entry['formats'].extend(info['formats'])
+                                except Exception as e:
+                                    # Some playlist URL may fail with 500, at the same time
+                                    # the other one may work fine (e.g.
+                                    # http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu)
+                                    if isinstance(e.cause, compat_HTTPError) and e.cause.code == 500:
+                                        continue
+                                    raise
+                            if entry:
+                                self._sort_formats(entry['formats'])
+                                entries.append(entry)
 
         if entries:
             return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)
@@ -852,6 +885,50 @@ class BBCIE(BBCCoUkIE):
                 'subtitles': subtitles,
             }
 
+        # Morph based embed (e.g. http://www.bbc.co.uk/sport/live/olympics/36895975)
+        # There are several setPayload calls may be present but the video
+        # seems to be always related to the first one
+        morph_payload = self._parse_json(
+            self._search_regex(
+                r'Morph\.setPayload\([^,]+,\s*({.+?})\);',
+                webpage, 'morph payload', default='{}'),
+            playlist_id, fatal=False)
+        if morph_payload:
+            components = try_get(morph_payload, lambda x: x['body']['components'], list) or []
+            for component in components:
+                if not isinstance(component, dict):
+                    continue
+                lead_media = try_get(component, lambda x: x['props']['leadMedia'], dict)
+                if not lead_media:
+                    continue
+                identifiers = lead_media.get('identifiers')
+                if not identifiers or not isinstance(identifiers, dict):
+                    continue
+                programme_id = identifiers.get('vpid') or identifiers.get('playablePid')
+                if not programme_id:
+                    continue
+                title = lead_media.get('title') or self._og_search_title(webpage)
+                formats, subtitles = self._download_media_selector(programme_id)
+                self._sort_formats(formats)
+                description = lead_media.get('summary')
+                uploader = lead_media.get('masterBrand')
+                uploader_id = lead_media.get('mid')
+                duration = None
+                duration_d = lead_media.get('duration')
+                if isinstance(duration_d, dict):
+                    duration = parse_duration(dict_get(
+                        duration_d, ('rawDuration', 'formattedDuration', 'spokenDuration')))
+                return {
+                    'id': programme_id,
+                    'title': title,
+                    'description': description,
+                    'duration': duration,
+                    'uploader': uploader,
+                    'uploader_id': uploader_id,
+                    'formats': formats,
+                    'subtitles': subtitles,
+                }
+
         def extract_all(pattern):
             return list(filter(None, map(
                 lambda s: self._parse_json(s, playlist_id, fatal=False),
@@ -869,7 +946,7 @@ class BBCIE(BBCCoUkIE):
             r'setPlaylist\("(%s)"\)' % EMBED_URL, webpage))
         if entries:
             return self.playlist_result(
-                [self.url_result(entry, 'BBCCoUk') for entry in entries],
+                [self.url_result(entry_, 'BBCCoUk') for entry_ in entries],
                 playlist_id, playlist_title, playlist_description)
 
         # Multiple video article (e.g. http://www.bbc.com/news/world-europe-32668511)
@@ -981,27 +1058,43 @@ class BBCCoUkArticleIE(InfoExtractor):
 
 
 class BBCCoUkPlaylistBaseIE(InfoExtractor):
+    def _entries(self, webpage, url, playlist_id):
+        single_page = 'page' in compat_urlparse.parse_qs(
+            compat_urlparse.urlparse(url).query)
+        for page_num in itertools.count(2):
+            for video_id in re.findall(
+                    self._VIDEO_ID_TEMPLATE % BBCCoUkIE._ID_REGEX, webpage):
+                yield self.url_result(
+                    self._URL_TEMPLATE % video_id, BBCCoUkIE.ie_key())
+            if single_page:
+                return
+            next_page = self._search_regex(
+                r'<li[^>]+class=(["\'])pagination_+next\1[^>]*><a[^>]+href=(["\'])(?P<url>(?:(?!\2).)+)\2',
+                webpage, 'next page url', default=None, group='url')
+            if not next_page:
+                break
+            webpage = self._download_webpage(
+                compat_urlparse.urljoin(url, next_page), playlist_id,
+                'Downloading page %d' % page_num, page_num)
+
     def _real_extract(self, url):
         playlist_id = self._match_id(url)
 
         webpage = self._download_webpage(url, playlist_id)
 
-        entries = [
-            self.url_result(self._URL_TEMPLATE % video_id, BBCCoUkIE.ie_key())
-            for video_id in re.findall(
-                self._VIDEO_ID_TEMPLATE % BBCCoUkIE._ID_REGEX, webpage)]
-
         title, description = self._extract_title_and_description(webpage)
 
-        return self.playlist_result(entries, playlist_id, title, description)
+        return self.playlist_result(
+            self._entries(webpage, url, playlist_id),
+            playlist_id, title, description)
 
 
 class BBCCoUkIPlayerPlaylistIE(BBCCoUkPlaylistBaseIE):
     IE_NAME = 'bbc.co.uk:iplayer:playlist'
-    _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/iplayer/episodes/(?P<id>%s)' % BBCCoUkIE._ID_REGEX
+    _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/iplayer/(?:episodes|group)/(?P<id>%s)' % BBCCoUkIE._ID_REGEX
     _URL_TEMPLATE = 'http://www.bbc.co.uk/iplayer/episode/%s'
     _VIDEO_ID_TEMPLATE = r'data-ip-id=["\'](%s)'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.bbc.co.uk/iplayer/episodes/b05rcz9v',
         'info_dict': {
             'id': 'b05rcz9v',
@@ -1009,7 +1102,17 @@ class BBCCoUkIPlayerPlaylistIE(BBCCoUkPlaylistBaseIE):
             'description': 'French thriller serial about a missing teenager.',
         },
         'playlist_mincount': 6,
-    }
+        'skip': 'This programme is not currently available on BBC iPlayer',
+    }, {
+        # Available for over a year unlike 30 days for most other programmes
+        'url': 'http://www.bbc.co.uk/iplayer/group/p02tcc32',
+        'info_dict': {
+            'id': 'p02tcc32',
+            'title': 'Bohemian Icons',
+            'description': 'md5:683e901041b2fe9ba596f2ab04c4dbe7',
+        },
+        'playlist_mincount': 10,
+    }]
 
     def _extract_title_and_description(self, webpage):
         title = self._search_regex(r'<h1>([^<]+)</h1>', webpage, 'title', fatal=False)
@@ -1032,6 +1135,24 @@ class BBCCoUkPlaylistIE(BBCCoUkPlaylistBaseIE):
             'description': 'French thriller serial about a missing teenager.',
         },
         'playlist_mincount': 7,
+    }, {
+        # multipage playlist, explicit page
+        'url': 'http://www.bbc.co.uk/programmes/b00mfl7n/clips?page=1',
+        'info_dict': {
+            'id': 'b00mfl7n',
+            'title': 'Frozen Planet - Clips - BBC One',
+            'description': 'md5:65dcbf591ae628dafe32aa6c4a4a0d8c',
+        },
+        'playlist_mincount': 24,
+    }, {
+        # multipage playlist, all pages
+        'url': 'http://www.bbc.co.uk/programmes/b00mfl7n/clips',
+        'info_dict': {
+            'id': 'b00mfl7n',
+            'title': 'Frozen Planet - Clips - BBC One',
+            'description': 'md5:65dcbf591ae628dafe32aa6c4a4a0d8c',
+        },
+        'playlist_mincount': 142,
     }, {
         'url': 'http://www.bbc.co.uk/programmes/b05rcz9v/broadcasts/2016/06',
         'only_matching': True,

youtube_dl/extractor/bigflix.py

@@ -11,22 +11,13 @@ from ..compat import compat_urllib_parse_unquote
 class BigflixIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?bigflix\.com/.+/(?P<id>[0-9]+)'
     _TESTS = [{
-        'url': 'http://www.bigflix.com/Hindi-movies/Action-movies/Singham-Returns/16537',
-        'md5': 'ec76aa9b1129e2e5b301a474e54fab74',
-        'info_dict': {
-            'id': '16537',
-            'ext': 'mp4',
-            'title': 'Singham Returns',
-            'description': 'md5:3d2ba5815f14911d5cc6a501ae0cf65d',
-        }
-    }, {
         # 2 formats
         'url': 'http://www.bigflix.com/Tamil-movies/Drama-movies/Madarasapatinam/16070',
         'info_dict': {
             'id': '16070',
             'ext': 'mp4',
             'title': 'Madarasapatinam',
-            'description': 'md5:63b9b8ed79189c6f0418c26d9a3452ca',
+            'description': 'md5:9f0470b26a4ba8e824c823b5d95c2f6b',
             'formats': 'mincount:2',
         },
         'params': {

youtube_dl/extractor/bilibili.py

@@ -25,13 +25,13 @@ class BiliBiliIE(InfoExtractor):
 
     _TESTS = [{
         'url': 'http://www.bilibili.tv/video/av1074402/',
-        'md5': '5f7d29e1a2872f3df0cf76b1f87d3788',
+        'md5': '9fa226fe2b8a9a4d5a69b4c6a183417e',
         'info_dict': {
             'id': '1554319',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': '【金坷垃】金泡沫',
             'description': 'md5:ce18c2a2d2193f0df2917d270f2e5923',
-            'duration': 308.067,
+            'duration': 308.315,
             'timestamp': 1398012660,
             'upload_date': '20140420',
             'thumbnail': 're:^https?://.+\.jpg',
@@ -41,73 +41,33 @@ class BiliBiliIE(InfoExtractor):
     }, {
         'url': 'http://www.bilibili.com/video/av1041170/',
         'info_dict': {
-            'id': '1041170',
+            'id': '1507019',
+            'ext': 'mp4',
             'title': '【BD1080P】刀语【诸神&异域】',
             'description': '这是个神奇的故事~每个人不留弹幕不给走哦~切利哦！~',
+            'timestamp': 1396530060,
+            'upload_date': '20140403',
+            'uploader': '枫叶逝去',
+            'uploader_id': '520116',
         },
-        'playlist_count': 9,
     }, {
         'url': 'http://www.bilibili.com/video/av4808130/',
         'info_dict': {
-            'id': '4808130',
+            'id': '7802182',
+            'ext': 'mp4',
             'title': '【长篇】哆啦A梦443【钉铛】',
             'description': '(2016.05.27)来组合客人的脸吧&寻母六千里锭 抱歉，又轮到周日上班现在才到家 封面www.pixiv.net/member_illust.php?mode=medium&illust_id=56912929',
+            'timestamp': 1464564180,
+            'upload_date': '20160529',
+            'uploader': '喜欢拉面',
+            'uploader_id': '151066',
         },
-        'playlist': [{
-            'md5': '55cdadedf3254caaa0d5d27cf20a8f9c',
-            'info_dict': {
-                'id': '4808130_part1',
-                'ext': 'flv',
-                'title': '【长篇】哆啦A梦443【钉铛】',
-                'description': '(2016.05.27)来组合客人的脸吧&寻母六千里锭 抱歉，又轮到周日上班现在才到家 封面www.pixiv.net/member_illust.php?mode=medium&illust_id=56912929',
-                'timestamp': 1464564180,
-                'upload_date': '20160529',
-                'uploader': '喜欢拉面',
-                'uploader_id': '151066',
-            },
-        }, {
-            'md5': '926f9f67d0c482091872fbd8eca7ea3d',
-            'info_dict': {
-                'id': '4808130_part2',
-                'ext': 'flv',
-                'title': '【长篇】哆啦A梦443【钉铛】',
-                'description': '(2016.05.27)来组合客人的脸吧&寻母六千里锭 抱歉，又轮到周日上班现在才到家 封面www.pixiv.net/member_illust.php?mode=medium&illust_id=56912929',
-                'timestamp': 1464564180,
-                'upload_date': '20160529',
-                'uploader': '喜欢拉面',
-                'uploader_id': '151066',
-            },
-        }, {
-            'md5': '4b7b225b968402d7c32348c646f1fd83',
-            'info_dict': {
-                'id': '4808130_part3',
-                'ext': 'flv',
-                'title': '【长篇】哆啦A梦443【钉铛】',
-                'description': '(2016.05.27)来组合客人的脸吧&寻母六千里锭 抱歉，又轮到周日上班现在才到家 封面www.pixiv.net/member_illust.php?mode=medium&illust_id=56912929',
-                'timestamp': 1464564180,
-                'upload_date': '20160529',
-                'uploader': '喜欢拉面',
-                'uploader_id': '151066',
-            },
-        }, {
-            'md5': '7b795e214166501e9141139eea236e91',
-            'info_dict': {
-                'id': '4808130_part4',
-                'ext': 'flv',
-                'title': '【长篇】哆啦A梦443【钉铛】',
-                'description': '(2016.05.27)来组合客人的脸吧&寻母六千里锭 抱歉，又轮到周日上班现在才到家 封面www.pixiv.net/member_illust.php?mode=medium&illust_id=56912929',
-                'timestamp': 1464564180,
-                'upload_date': '20160529',
-                'uploader': '喜欢拉面',
-                'uploader_id': '151066',
-            },
-        }],
     }, {
         # Missing upload time
         'url': 'http://www.bilibili.com/video/av1867637/',
         'info_dict': {
             'id': '2880301',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': '【HDTV】【喜剧】岳父岳母真难当 （2014）【法国票房冠军】',
             'description': '一个信奉天主教的法国旧式传统资产阶级家庭中有四个女儿。三个女儿却分别找了阿拉伯、犹太、中国丈夫，老夫老妻唯独期盼剩下未嫁的小女儿能找一个信奉天主教的法国白人，结果没想到小女儿找了一位非裔黑人……【这次应该不会跳帧了】',
             'uploader': '黑夜为猫',

youtube_dl/extractor/biobiochiletv.py

@@ -2,11 +2,15 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import remove_end
+from ..utils import (
+    ExtractorError,
+    remove_end,
+)
+from .rudo import RudoIE
 
 
 class BioBioChileTVIE(InfoExtractor):
-    _VALID_URL = r'https?://tv\.biobiochile\.cl/notas/(?:[^/]+/)+(?P<id>[^/]+)\.shtml'
+    _VALID_URL = r'https?://(?:tv|www)\.biobiochile\.cl/(?:notas|noticias)/(?:[^/]+/)+(?P<id>[^/]+)\.shtml'
 
     _TESTS = [{
         'url': 'http://tv.biobiochile.cl/notas/2015/10/21/sobre-camaras-y-camarillas-parlamentarias.shtml',
@@ -18,6 +22,7 @@ class BioBioChileTVIE(InfoExtractor):
             'thumbnail': 're:^https?://.*\.jpg$',
             'uploader': 'Fernando Atria',
         },
+        'skip': 'URL expired and redirected to http://www.biobiochile.cl/portada/bbtv/index.html',
     }, {
         # different uploader layout
         'url': 'http://tv.biobiochile.cl/notas/2016/03/18/natalia-valdebenito-repasa-a-diputado-hasbun-paso-a-la-categoria-de-hablar-brutalidades.shtml',
@@ -32,6 +37,16 @@ class BioBioChileTVIE(InfoExtractor):
         'params': {
             'skip_download': True,
         },
+        'skip': 'URL expired and redirected to http://www.biobiochile.cl/portada/bbtv/index.html',
+    }, {
+        'url': 'http://www.biobiochile.cl/noticias/bbtv/comentarios-bio-bio/2016/07/08/edecanes-del-congreso-figuras-decorativas-que-le-cuestan-muy-caro-a-los-chilenos.shtml',
+        'info_dict': {
+            'id': 'edecanes-del-congreso-figuras-decorativas-que-le-cuestan-muy-caro-a-los-chilenos',
+            'ext': 'mp4',
+            'uploader': '(none)',
+            'upload_date': '20160708',
+            'title': 'Edecanes del Congreso: Figuras decorativas que le cuestan muy caro a los chilenos',
+        },
     }, {
         'url': 'http://tv.biobiochile.cl/notas/2015/10/22/ninos-transexuales-de-quien-es-la-decision.shtml',
         'only_matching': True,
@@ -45,42 +60,22 @@ class BioBioChileTVIE(InfoExtractor):
 
         webpage = self._download_webpage(url, video_id)
 
+        rudo_url = RudoIE._extract_url(webpage)
+        if not rudo_url:
+            raise ExtractorError('No videos found')
+
         title = remove_end(self._og_search_title(webpage), ' - BioBioChile TV')
 
-        file_url = self._search_regex(
-            r'loadFWPlayerVideo\([^,]+,\s*(["\'])(?P<url>.+?)\1',
-            webpage, 'file url', group='url')
-
-        base_url = self._search_regex(
-            r'file\s*:\s*(["\'])(?P<url>.+?)\1\s*\+\s*fileURL', webpage,
-            'base url', default='http://unlimited2-cl.digitalproserver.com/bbtv/',
-            group='url')
-
-        formats = self._extract_m3u8_formats(
-            '%s%s/playlist.m3u8' % (base_url, file_url), video_id, 'mp4',
-            entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)
-        f = {
-            'url': '%s%s' % (base_url, file_url),
-            'format_id': 'http',
-            'protocol': 'http',
-            'preference': 1,
-        }
-        if formats:
-            f_copy = formats[-1].copy()
-            f_copy.update(f)
-            f = f_copy
-        formats.append(f)
-        self._sort_formats(formats)
-
         thumbnail = self._og_search_thumbnail(webpage)
         uploader = self._html_search_regex(
-            r'<a[^>]+href=["\']https?://busca\.biobiochile\.cl/author[^>]+>(.+?)</a>',
+            r'<a[^>]+href=["\']https?://(?:busca|www)\.biobiochile\.cl/(?:lista/)?(?:author|autor)[^>]+>(.+?)</a>',
             webpage, 'uploader', fatal=False)
 
         return {
+            '_type': 'url_transparent',
+            'url': rudo_url,
             'id': video_id,
             'title': title,
             'thumbnail': thumbnail,
             'uploader': uploader,
-            'formats': formats,
         }

youtube_dl/extractor/biqle.py

@@ -24,7 +24,8 @@ class BIQLEIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Ребенок в шоке от автоматической мойки',
             'uploader': 'Dmitry Kotov',
-        }
+        },
+        'skip': ' This video was marked as adult.  Embedding adult videos on external sites is prohibited.',
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/bloomberg.py

@@ -1,3 +1,4 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re
@@ -20,6 +21,18 @@ class BloombergIE(InfoExtractor):
         'params': {
             'format': 'best[format_id^=hds]',
         },
+    }, {
+        # video ID in BPlayer(...)
+        'url': 'http://www.bloomberg.com/features/2016-hello-world-new-zealand/',
+        'info_dict': {
+            'id': '938c7e72-3f25-4ddb-8b85-a9be731baa74',
+            'ext': 'flv',
+            'title': 'Meet the Real-Life Tech Wizards of Middle Earth',
+            'description': 'Hello World, Episode 1: New Zealand’s freaky AI babies, robot exoskeletons, and a virtual you.',
+        },
+        'params': {
+            'format': 'best[format_id^=hds]',
+        },
     }, {
         'url': 'http://www.bloomberg.com/news/articles/2015-11-12/five-strange-things-that-have-been-happening-in-financial-markets',
         'only_matching': True,
@@ -33,7 +46,11 @@ class BloombergIE(InfoExtractor):
         webpage = self._download_webpage(url, name)
         video_id = self._search_regex(
             r'["\']bmmrId["\']\s*:\s*(["\'])(?P<url>.+?)\1',
-            webpage, 'id', group='url')
+            webpage, 'id', group='url', default=None)
+        if not video_id:
+            bplayer_data = self._parse_json(self._search_regex(
+                r'BPlayer\(null,\s*({[^;]+})\);', webpage, 'id'), name)
+            video_id = bplayer_data['id']
         title = re.sub(': Video$', '', self._og_search_title(webpage))
 
         embed_info = self._download_json(

youtube_dl/extractor/brightcove.py

@@ -26,6 +26,8 @@ from ..utils import (
     unescapeHTML,
     unsmuggle_url,
     update_url_query,
+    clean_html,
+    mimetype2ext,
 )
 
 
@@ -544,14 +546,16 @@ class BrightcoveNewIE(InfoExtractor):
         formats = []
         for source in json_data.get('sources', []):
             container = source.get('container')
-            source_type = source.get('type')
+            ext = mimetype2ext(source.get('type'))
             src = source.get('src')
-            if source_type == 'application/x-mpegURL' or container == 'M2TS':
+            if ext == 'ism':
+                continue
+            elif ext == 'm3u8' or container == 'M2TS':
                 if not src:
                     continue
                 formats.extend(self._extract_m3u8_formats(
                     src, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
-            elif source_type == 'application/dash+xml':
+            elif ext == 'mpd':
                 if not src:
                     continue
                 formats.extend(self._extract_mpd_formats(src, video_id, 'dash', fatal=False))
@@ -567,7 +571,7 @@ class BrightcoveNewIE(InfoExtractor):
                     'tbr': tbr,
                     'filesize': int_or_none(source.get('size')),
                     'container': container,
-                    'ext': container.lower(),
+                    'ext': ext or container.lower(),
                 }
                 if width == 0 and height == 0:
                     f.update({
@@ -620,7 +624,7 @@ class BrightcoveNewIE(InfoExtractor):
         return {
             'id': video_id,
             'title': title,
-            'description': json_data.get('description'),
+            'description': clean_html(json_data.get('description')),
             'thumbnail': json_data.get('thumbnail') or json_data.get('poster'),
             'duration': float_or_none(json_data.get('duration'), 1000),
             'timestamp': parse_iso8601(json_data.get('published_at')),

youtube_dl/extractor/camdemy.py

@@ -1,7 +1,6 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import datetime
 import re
 
 from .common import InfoExtractor
@@ -10,8 +9,10 @@ from ..compat import (
     compat_urlparse,
 )
 from ..utils import (
-    parse_iso8601,
+    clean_html,
+    parse_duration,
     str_to_int,
+    unified_strdate,
 )
 
 
@@ -26,14 +27,14 @@ class CamdemyIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Ch1-1 Introduction, Signals (02-23-2012)',
             'thumbnail': 're:^https?://.*\.jpg$',
-            'description': '',
             'creator': 'ss11spring',
+            'duration': 1591,
             'upload_date': '20130114',
-            'timestamp': 1358154556,
             'view_count': int,
         }
     }, {
         # With non-empty description
+        # webpage returns "No permission or not login"
         'url': 'http://www.camdemy.com/media/13885',
         'md5': '4576a3bb2581f86c61044822adbd1249',
         'info_dict': {
@@ -41,64 +42,71 @@ class CamdemyIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'EverCam + Camdemy QuickStart',
             'thumbnail': 're:^https?://.*\.jpg$',
-            'description': 'md5:050b62f71ed62928f8a35f1a41e186c9',
+            'description': 'md5:2a9f989c2b153a2342acee579c6e7db6',
             'creator': 'evercam',
-            'upload_date': '20140620',
-            'timestamp': 1403271569,
+            'duration': 318,
         }
     }, {
-        # External source
+        # External source (YouTube)
         'url': 'http://www.camdemy.com/media/14842',
-        'md5': '50e1c3c3aa233d3d7b7daa2fa10b1cf7',
         'info_dict': {
             'id': '2vsYQzNIsJo',
             'ext': 'mp4',
+            'title': 'Excel 2013 Tutorial - How to add Password Protection',
+            'description': 'Excel 2013 Tutorial for Beginners - How to add Password Protection',
             'upload_date': '20130211',
             'uploader': 'Hun Kim',
-            'description': 'Excel 2013 Tutorial for Beginners - How to add Password Protection',
             'uploader_id': 'hunkimtutorials',
-            'title': 'Excel 2013 Tutorial - How to add Password Protection',
-        }
+        },
+        'params': {
+            'skip_download': True,
+        },
     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        page = self._download_webpage(url, video_id)
+
+        webpage = self._download_webpage(url, video_id)
 
         src_from = self._html_search_regex(
-            r"<div class='srcFrom'>Source: <a title='([^']+)'", page,
-            'external source', default=None)
+            r"class=['\"]srcFrom['\"][^>]*>Sources?(?:\s+from)?\s*:\s*<a[^>]+(?:href|title)=(['\"])(?P<url>(?:(?!\1).)+)\1",
+            webpage, 'external source', default=None, group='url')
         if src_from:
             return self.url_result(src_from)
 
         oembed_obj = self._download_json(
             'http://www.camdemy.com/oembed/?format=json&url=' + url, video_id)
 
+        title = oembed_obj['title']
         thumb_url = oembed_obj['thumbnail_url']
         video_folder = compat_urlparse.urljoin(thumb_url, 'video/')
         file_list_doc = self._download_xml(
             compat_urlparse.urljoin(video_folder, 'fileList.xml'),
-            video_id, 'Filelist XML')
+            video_id, 'Downloading filelist XML')
         file_name = file_list_doc.find('./video/item/fileName').text
         video_url = compat_urlparse.urljoin(video_folder, file_name)
 
-        timestamp = parse_iso8601(self._html_search_regex(
-            r"<div class='title'>Posted\s*:</div>\s*<div class='value'>([^<>]+)<",
-            page, 'creation time', fatal=False),
-            delimiter=' ', timezone=datetime.timedelta(hours=8))
-        view_count = str_to_int(self._html_search_regex(
-            r"<div class='title'>Views\s*:</div>\s*<div class='value'>([^<>]+)<",
-            page, 'view count', fatal=False))
+        # Some URLs return "No permission or not login" in a webpage despite being
+        # freely available via oembed JSON URL (e.g. http://www.camdemy.com/media/13885)
+        upload_date = unified_strdate(self._search_regex(
+            r'>published on ([^<]+)<', webpage,
+            'upload date', default=None))
+        view_count = str_to_int(self._search_regex(
+            r'role=["\']viewCnt["\'][^>]*>([\d,.]+) views',
+            webpage, 'view count', default=None))
+        description = self._html_search_meta(
+            'description', webpage, default=None) or clean_html(
+            oembed_obj.get('description'))
 
         return {
             'id': video_id,
             'url': video_url,
-            'title': oembed_obj['title'],
+            'title': title,
             'thumbnail': thumb_url,
-            'description': self._html_search_meta('description', page),
-            'creator': oembed_obj['author_name'],
-            'duration': oembed_obj['duration'],
-            'timestamp': timestamp,
+            'description': description,
+            'creator': oembed_obj.get('author_name'),
+            'duration': parse_duration(oembed_obj.get('duration')),
+            'upload_date': upload_date,
             'view_count': view_count,
         }
 

youtube_dl/extractor/cbc.py

@@ -4,9 +4,11 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_str
 from ..utils import (
     js_to_json,
     smuggle_url,
+    try_get,
 )
 
 
@@ -25,8 +27,22 @@ class CBCIE(InfoExtractor):
             'upload_date': '20160203',
             'uploader': 'CBCC-NEW',
         },
+        'skip': 'Geo-restricted to Canada',
     }, {
-        # with clipId
+        # with clipId, feed available via tpfeed.cbc.ca and feed.theplatform.com
+        'url': 'http://www.cbc.ca/22minutes/videos/22-minutes-update/22-minutes-update-episode-4',
+        'md5': '162adfa070274b144f4fdc3c3b8207db',
+        'info_dict': {
+            'id': '2414435309',
+            'ext': 'mp4',
+            'title': '22 Minutes Update: What Not To Wear Quebec',
+            'description': "This week's latest Canadian top political story is What Not To Wear Quebec.",
+            'upload_date': '20131025',
+            'uploader': 'CBCC-NEW',
+            'timestamp': 1382717907,
+        },
+    }, {
+        # with clipId, feed only available via tpfeed.cbc.ca
         'url': 'http://www.cbc.ca/archives/entry/1978-robin-williams-freestyles-on-90-minutes-live',
         'md5': '0274a90b51a9b4971fe005c63f592f12',
         'info_dict': {
@@ -64,6 +80,7 @@ class CBCIE(InfoExtractor):
                 'uploader': 'CBCC-NEW',
             },
         }],
+        'skip': 'Geo-restricted to Canada',
     }]
 
     @classmethod
@@ -81,9 +98,15 @@ class CBCIE(InfoExtractor):
             media_id = player_info.get('mediaId')
             if not media_id:
                 clip_id = player_info['clipId']
-                media_id = self._download_json(
-                    'http://feed.theplatform.com/f/h9dtGB/punlNGjMlc1F?fields=id&byContent=byReleases%3DbyId%253D' + clip_id,
-                    clip_id)['entries'][0]['id'].split('/')[-1]
+                feed = self._download_json(
+                    'http://tpfeed.cbc.ca/f/ExhSPC/vms_5akSXx4Ng_Zn?byCustomValue={:mpsReleases}{%s}' % clip_id,
+                    clip_id, fatal=False)
+                if feed:
+                    media_id = try_get(feed, lambda x: x['entries'][0]['guid'], compat_str)
+                if not media_id:
+                    media_id = self._download_json(
+                        'http://feed.theplatform.com/f/h9dtGB/punlNGjMlc1F?fields=id&byContent=byReleases%3DbyId%253D' + clip_id,
+                        clip_id)['entries'][0]['id'].split('/')[-1]
             return self.url_result('cbcplayer:%s' % media_id, 'CBCPlayer', media_id)
         else:
             entries = [self.url_result('cbcplayer:%s' % media_id, 'CBCPlayer', media_id) for media_id in re.findall(r'<iframe[^>]+src="[^"]+?mediaId=(\d+)"', webpage)]
@@ -104,6 +127,7 @@ class CBCPlayerIE(InfoExtractor):
             'upload_date': '20160210',
             'uploader': 'CBCC-NEW',
         },
+        'skip': 'Geo-restricted to Canada',
     }, {
         # Redirected from http://www.cbc.ca/player/AudioMobile/All%20in%20a%20Weekend%20Montreal/ID/2657632011/
         'url': 'http://www.cbc.ca/player/play/2657631896',

youtube_dl/extractor/cbslocal.py

@@ -1,12 +1,10 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import calendar
-import datetime
-
 from .anvato import AnvatoIE
 from .sendtonews import SendtoNewsIE
 from ..compat import compat_urlparse
+from ..utils import unified_timestamp
 
 
 class CBSLocalIE(AnvatoIE):
@@ -43,13 +41,8 @@ class CBSLocalIE(AnvatoIE):
         'url': 'http://cleveland.cbslocal.com/2016/05/16/indians-score-season-high-15-runs-in-blowout-win-over-reds-rapid-reaction/',
         'info_dict': {
             'id': 'GxfCe0Zo7D-175909-5588',
-            'ext': 'mp4',
-            'title': 'Recap: CLE 15, CIN 6',
-            'description': '5/16/16: Indians\' bats explode for 15 runs in a win',
-            'upload_date': '20160516',
-            'timestamp': 1463433840,
-            'duration': 49,
         },
+        'playlist_count': 9,
         'params': {
             # m3u8 download
             'skip_download': True,
@@ -62,19 +55,15 @@ class CBSLocalIE(AnvatoIE):
 
         sendtonews_url = SendtoNewsIE._extract_url(webpage)
         if sendtonews_url:
-            info_dict = {
-                '_type': 'url_transparent',
-                'url': compat_urlparse.urljoin(url, sendtonews_url),
-            }
-        else:
-            info_dict = self._extract_anvato_videos(webpage, display_id)
+            return self.url_result(
+                compat_urlparse.urljoin(url, sendtonews_url),
+                ie=SendtoNewsIE.ie_key())
+
+        info_dict = self._extract_anvato_videos(webpage, display_id)
 
         time_str = self._html_search_regex(
             r'class="entry-date">([^<]+)<', webpage, 'released date', fatal=False)
-        timestamp = None
-        if time_str:
-            timestamp = calendar.timegm(datetime.datetime.strptime(
-                time_str, '%b %d, %Y %I:%M %p').timetuple())
+        timestamp = unified_timestamp(time_str)
 
         info_dict.update({
             'display_id': display_id,

youtube_dl/extractor/cbsnews.py

@@ -26,6 +26,7 @@ class CBSNewsIE(CBSBaseIE):
                 # rtmp download
                 'skip_download': True,
             },
+            'skip': 'Subscribers only',
         },
         {
             'url': 'http://www.cbsnews.com/videos/fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack/',
@@ -69,6 +70,7 @@ class CBSNewsLiveVideoIE(InfoExtractor):
     IE_DESC = 'CBS News Live Videos'
     _VALID_URL = r'https?://(?:www\.)?cbsnews\.com/live/video/(?P<id>[\da-z_-]+)'
 
+    # Live videos get deleted soon. See http://www.cbsnews.com/live/ for the latest examples
     _TEST = {
         'url': 'http://www.cbsnews.com/live/video/clinton-sanders-prepare-to-face-off-in-nh/',
         'info_dict': {
@@ -77,6 +79,7 @@ class CBSNewsLiveVideoIE(InfoExtractor):
             'title': 'Clinton, Sanders Prepare To Face Off In NH',
             'duration': 334,
         },
+        'skip': 'Video gone',
     }
 
     def _real_extract(self, url):

youtube_dl/extractor/chaturbate.py

@@ -17,7 +17,8 @@ class ChaturbateIE(InfoExtractor):
         },
         'params': {
             'skip_download': True,
-        }
+        },
+        'skip': 'Room is offline',
     }, {
         'url': 'https://en.chaturbate.com/siswet19/',
         'only_matching': True,

youtube_dl/extractor/chirbit.py

@@ -1,30 +1,33 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import base64
+
 from .common import InfoExtractor
-from ..utils import (
-    parse_duration,
-    int_or_none,
-)
+from ..utils import parse_duration
 
 
 class ChirbitIE(InfoExtractor):
     IE_NAME = 'chirbit'
     _VALID_URL = r'https?://(?:www\.)?chirb\.it/(?:(?:wp|pl)/|fb_chirbit_player\.swf\?key=)?(?P<id>[\da-zA-Z]+)'
     _TESTS = [{
-        'url': 'http://chirb.it/PrIPv5',
-        'md5': '9847b0dad6ac3e074568bf2cfb197de8',
+        'url': 'http://chirb.it/be2abG',
         'info_dict': {
-            'id': 'PrIPv5',
+            'id': 'be2abG',
             'ext': 'mp3',
-            'title': 'Фасадстрой',
-            'duration': 52,
-            'view_count': int,
-            'comment_count': int,
+            'title': 'md5:f542ea253f5255240be4da375c6a5d7e',
+            'description': 'md5:f24a4e22a71763e32da5fed59e47c770',
+            'duration': 306,
+        },
+        'params': {
+            'skip_download': True,
         }
     }, {
         'url': 'https://chirb.it/fb_chirbit_player.swf?key=PrIPv5',
         'only_matching': True,
+    }, {
+        'url': 'https://chirb.it/wp/MN58c2',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -33,27 +36,30 @@ class ChirbitIE(InfoExtractor):
         webpage = self._download_webpage(
             'http://chirb.it/%s' % audio_id, audio_id)
 
-        audio_url = self._search_regex(
-            r'"setFile"\s*,\s*"([^"]+)"', webpage, 'audio url')
+        data_fd = self._search_regex(
+            r'data-fd=(["\'])(?P<url>(?:(?!\1).)+)\1',
+            webpage, 'data fd', group='url')
+
+        # Reverse engineered from https://chirb.it/js/chirbit.player.js (look
+        # for soundURL)
+        audio_url = base64.b64decode(
+            data_fd[::-1].encode('ascii')).decode('utf-8')
 
         title = self._search_regex(
-            r'itemprop="name">([^<]+)', webpage, 'title')
-        duration = parse_duration(self._html_search_meta(
-            'duration', webpage, 'duration', fatal=False))
-        view_count = int_or_none(self._search_regex(
-            r'itemprop="playCount"\s*>(\d+)', webpage,
-            'listen count', fatal=False))
-        comment_count = int_or_none(self._search_regex(
-            r'>(\d+) Comments?:', webpage,
-            'comment count', fatal=False))
+            r'class=["\']chirbit-title["\'][^>]*>([^<]+)', webpage, 'title')
+        description = self._search_regex(
+            r'<h3>Description</h3>\s*<pre[^>]*>([^<]+)</pre>',
+            webpage, 'description', default=None)
+        duration = parse_duration(self._search_regex(
+            r'class=["\']c-length["\'][^>]*>([^<]+)',
+            webpage, 'duration', fatal=False))
 
         return {
             'id': audio_id,
             'url': audio_url,
             'title': title,
+            'description': description,
             'duration': duration,
-            'view_count': view_count,
-            'comment_count': comment_count,
         }
 
 

youtube_dl/extractor/cliphunter.py

@@ -23,7 +23,7 @@ class CliphunterIE(InfoExtractor):
         (?P<id>[0-9]+)/
         (?P<seo>.+?)(?:$|[#\?])
     '''
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.cliphunter.com/w/1012420/Fun_Jynx_Maze_solo',
         'md5': 'b7c9bbd4eb3a226ab91093714dcaa480',
         'info_dict': {
@@ -32,8 +32,19 @@ class CliphunterIE(InfoExtractor):
             'title': 'Fun Jynx Maze solo',
             'thumbnail': 're:^https?://.*\.jpg$',
             'age_limit': 18,
-        }
-    }
+        },
+        'skip': 'Video gone',
+    }, {
+        'url': 'http://www.cliphunter.com/w/2019449/ShesNew__My_booty_girlfriend_Victoria_Paradices_pussy_filled_with_jizz',
+        'md5': '55a723c67bfc6da6b0cfa00d55da8a27',
+        'info_dict': {
+            'id': '2019449',
+            'ext': 'mp4',
+            'title': 'ShesNew - My booty girlfriend, Victoria Paradice\'s pussy filled with jizz',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'age_limit': 18,
+        },
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)

youtube_dl/extractor/cloudy.py

@@ -6,7 +6,6 @@ import re
 from .common import InfoExtractor
 from ..compat import (
     compat_parse_qs,
-    compat_urllib_parse_urlencode,
     compat_HTTPError,
 )
 from ..utils import (
@@ -17,37 +16,26 @@ from ..utils import (
 
 
 class CloudyIE(InfoExtractor):
-    _IE_DESC = 'cloudy.ec and videoraj.ch'
+    _IE_DESC = 'cloudy.ec'
     _VALID_URL = r'''(?x)
-        https?://(?:www\.)?(?P<host>cloudy\.ec|videoraj\.(?:ch|to))/
+        https?://(?:www\.)?cloudy\.ec/
         (?:v/|embed\.php\?id=)
         (?P<id>[A-Za-z0-9]+)
         '''
-    _EMBED_URL = 'http://www.%s/embed.php?id=%s'
-    _API_URL = 'http://www.%s/api/player.api.php?%s'
+    _EMBED_URL = 'http://www.cloudy.ec/embed.php?id=%s'
+    _API_URL = 'http://www.cloudy.ec/api/player.api.php'
     _MAX_TRIES = 2
-    _TESTS = [
-        {
-            'url': 'https://www.cloudy.ec/v/af511e2527aac',
-            'md5': '5cb253ace826a42f35b4740539bedf07',
-            'info_dict': {
-                'id': 'af511e2527aac',
-                'ext': 'flv',
-                'title': 'Funny Cats and Animals Compilation june 2013',
-            }
-        },
-        {
-            'url': 'http://www.videoraj.to/v/47f399fd8bb60',
-            'md5': '7d0f8799d91efd4eda26587421c3c3b0',
-            'info_dict': {
-                'id': '47f399fd8bb60',
-                'ext': 'flv',
-                'title': 'Burning a New iPhone 5 with Gasoline - Will it Survive?',
-            }
+    _TEST = {
+        'url': 'https://www.cloudy.ec/v/af511e2527aac',
+        'md5': '5cb253ace826a42f35b4740539bedf07',
+        'info_dict': {
+            'id': 'af511e2527aac',
+            'ext': 'flv',
+            'title': 'Funny Cats and Animals Compilation june 2013',
         }
-    ]
+    }
 
-    def _extract_video(self, video_host, video_id, file_key, error_url=None, try_num=0):
+    def _extract_video(self, video_id, file_key, error_url=None, try_num=0):
 
         if try_num > self._MAX_TRIES - 1:
             raise ExtractorError('Unable to extract video URL', expected=True)
@@ -64,9 +52,8 @@ class CloudyIE(InfoExtractor):
                 'errorUrl': error_url,
             })
 
-        data_url = self._API_URL % (video_host, compat_urllib_parse_urlencode(form))
         player_data = self._download_webpage(
-            data_url, video_id, 'Downloading player data')
+            self._API_URL, video_id, 'Downloading player data', query=form)
         data = compat_parse_qs(player_data)
 
         try_num += 1
@@ -88,7 +75,7 @@ class CloudyIE(InfoExtractor):
             except ExtractorError as e:
                 if isinstance(e.cause, compat_HTTPError) and e.cause.code in [404, 410]:
                     self.report_warning('Invalid video URL, requesting another', video_id)
-                    return self._extract_video(video_host, video_id, file_key, video_url, try_num)
+                    return self._extract_video(video_id, file_key, video_url, try_num)
 
         return {
             'id': video_id,
@@ -98,14 +85,13 @@ class CloudyIE(InfoExtractor):
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        video_host = mobj.group('host')
         video_id = mobj.group('id')
 
-        url = self._EMBED_URL % (video_host, video_id)
+        url = self._EMBED_URL % video_id
         webpage = self._download_webpage(url, video_id)
 
         file_key = self._search_regex(
             [r'key\s*:\s*"([^"]+)"', r'filekey\s*=\s*"([^"]+)"'],
             webpage, 'file_key')
 
-        return self._extract_video(video_host, video_id, file_key)
+        return self._extract_video(video_id, file_key)

youtube_dl/extractor/cmt.py

@@ -1,5 +1,7 @@
 from __future__ import unicode_literals
+
 from .mtv import MTVIE
+from ..utils import ExtractorError
 
 
 class CMTIE(MTVIE):
@@ -16,7 +18,27 @@ class CMTIE(MTVIE):
             'title': 'Garth Brooks - "The Call (featuring Trisha Yearwood)"',
             'description': 'Blame It All On My Roots',
         },
+        'skip': 'Video not available',
+    }, {
+        'url': 'http://www.cmt.com/videos/misc/1504699/still-the-king-ep-109-in-3-minutes.jhtml#id=1739908',
+        'md5': 'e61a801ca4a183a466c08bd98dccbb1c',
+        'info_dict': {
+            'id': '1504699',
+            'ext': 'mp4',
+            'title': 'Still The King Ep. 109 in 3 Minutes',
+            'description': 'Relive or catch up with Still The King by watching this recap of season 1, episode 9. New episodes Sundays 9/8c.',
+            'timestamp': 1469421000.0,
+            'upload_date': '20160725',
+        },
     }, {
         'url': 'http://www.cmt.com/shows/party-down-south/party-down-south-ep-407-gone-girl/1738172/playlist/#id=1738172',
         'only_matching': True,
     }]
+
+    @classmethod
+    def _transform_rtmp_url(cls, rtmp_video_url):
+        if 'error_not_available.swf' in rtmp_video_url:
+            raise ExtractorError(
+                '%s said: video is not available' % cls.IE_NAME, expected=True)
+
+        return super(CMTIE, cls)._transform_rtmp_url(rtmp_video_url)

youtube_dl/extractor/comedycentral.py

@@ -1,17 +1,7 @@
 from __future__ import unicode_literals
 
-import re
-
 from .mtv import MTVServicesInfoExtractor
-from ..compat import (
-    compat_str,
-    compat_urllib_parse_urlencode,
-)
-from ..utils import (
-    ExtractorError,
-    float_or_none,
-    unified_strdate,
-)
+from .common import InfoExtractor
 
 
 class ComedyCentralIE(MTVServicesInfoExtractor):
@@ -26,8 +16,10 @@ class ComedyCentralIE(MTVServicesInfoExtractor):
         'info_dict': {
             'id': 'cef0cbb3-e776-4bc9-b62e-8016deccb354',
             'ext': 'mp4',
-            'title': 'CC:Stand-Up|Greg Fitzsimmons: Life on Stage|Uncensored - Too Good of a Mother',
+            'title': 'CC:Stand-Up|August 18, 2013|1|0101|Uncensored - Too Good of a Mother',
             'description': 'After a certain point, breastfeeding becomes c**kblocking.',
+            'timestamp': 1376798400,
+            'upload_date': '20130818',
         },
     }, {
         'url': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/interviews/6yx39d/exclusive-rand-paul-extended-interview',
@@ -35,241 +27,92 @@ class ComedyCentralIE(MTVServicesInfoExtractor):
     }]
 
 
-class ComedyCentralShowsIE(MTVServicesInfoExtractor):
-    IE_DESC = 'The Daily Show / The Colbert Report'
-    # urls can be abbreviations like :thedailyshow
-    # urls for episodes like:
-    # or urls for clips like: http://www.thedailyshow.com/watch/mon-december-10-2012/any-given-gun-day
-    #                     or: http://www.colbertnation.com/the-colbert-report-videos/421667/november-29-2012/moon-shattering-news
-    #                     or: http://www.colbertnation.com/the-colbert-report-collections/422008/festival-of-lights/79524
-    _VALID_URL = r'''(?x)^(:(?P<shortname>tds|thedailyshow)
-                      |https?://(:www\.)?
-                          (?P<showname>thedailyshow|thecolbertreport|tosh)\.(?:cc\.)?com/
-                         ((?:full-)?episodes/(?:[0-9a-z]{6}/)?(?P<episode>.*)|
-                          (?P<clip>
-                              (?:(?:guests/[^/]+|videos|video-(?:clips|playlists)|special-editions|news-team/[^/]+)/[^/]+/(?P<videotitle>[^/?#]+))
-                              |(the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?))
-                              |(watch/(?P<date>[^/]*)/(?P<tdstitle>.*))
-                          )|
-                          (?P<interview>
-                              extended-interviews/(?P<interID>[0-9a-z]+)/
-                              (?:playlist_tds_extended_)?(?P<interview_title>[^/?#]*?)
-                              (?:/[^/?#]?|[?#]|$))))
-                     '''
+class ToshIE(MTVServicesInfoExtractor):
+    IE_DESC = 'Tosh.0'
+    _VALID_URL = r'^https?://tosh\.cc\.com/video-(?:clips|collections)/[^/]+/(?P<videotitle>[^/?#]+)'
+    _FEED_URL = 'http://tosh.cc.com/feeds/mrss'
+
     _TESTS = [{
-        'url': 'http://thedailyshow.cc.com/watch/thu-december-13-2012/kristen-stewart',
-        'md5': '4e2f5cb088a83cd8cdb7756132f9739d',
-        'info_dict': {
-            'id': 'ab9ab3e7-5a98-4dbe-8b21-551dc0523d55',
-            'ext': 'mp4',
-            'upload_date': '20121213',
-            'description': 'Kristen Stewart learns to let loose in "On the Road."',
-            'uploader': 'thedailyshow',
-            'title': 'thedailyshow kristen-stewart part 1',
-        }
-    }, {
-        'url': 'http://thedailyshow.cc.com/extended-interviews/b6364d/sarah-chayes-extended-interview',
-        'info_dict': {
-            'id': 'sarah-chayes-extended-interview',
-            'description': 'Carnegie Endowment Senior Associate Sarah Chayes discusses how corrupt institutions function throughout the world in her book "Thieves of State: Why Corruption Threatens Global Security."',
-            'title': 'thedailyshow Sarah Chayes Extended Interview',
-        },
-        'playlist': [
-            {
-                'info_dict': {
-                    'id': '0baad492-cbec-4ec1-9e50-ad91c291127f',
-                    'ext': 'mp4',
-                    'upload_date': '20150129',
-                    'description': 'Carnegie Endowment Senior Associate Sarah Chayes discusses how corrupt institutions function throughout the world in her book "Thieves of State: Why Corruption Threatens Global Security."',
-                    'uploader': 'thedailyshow',
-                    'title': 'thedailyshow sarah-chayes-extended-interview part 1',
-                },
-            },
-            {
-                'info_dict': {
-                    'id': '1e4fb91b-8ce7-4277-bd7c-98c9f1bbd283',
-                    'ext': 'mp4',
-                    'upload_date': '20150129',
-                    'description': 'Carnegie Endowment Senior Associate Sarah Chayes discusses how corrupt institutions function throughout the world in her book "Thieves of State: Why Corruption Threatens Global Security."',
-                    'uploader': 'thedailyshow',
-                    'title': 'thedailyshow sarah-chayes-extended-interview part 2',
-                },
-            },
-        ],
-        'params': {
-            'skip_download': True,
-        },
-    }, {
-        'url': 'http://thedailyshow.cc.com/extended-interviews/xm3fnq/andrew-napolitano-extended-interview',
-        'only_matching': True,
-    }, {
-        'url': 'http://thecolbertreport.cc.com/videos/29w6fx/-realhumanpraise-for-fox-news',
-        'only_matching': True,
-    }, {
-        'url': 'http://thecolbertreport.cc.com/videos/gh6urb/neil-degrasse-tyson-pt--1?xrs=eml_col_031114',
-        'only_matching': True,
-    }, {
-        'url': 'http://thedailyshow.cc.com/guests/michael-lewis/3efna8/exclusive---michael-lewis-extended-interview-pt--3',
-        'only_matching': True,
-    }, {
-        'url': 'http://thedailyshow.cc.com/episodes/sy7yv0/april-8--2014---denis-leary',
-        'only_matching': True,
-    }, {
-        'url': 'http://thecolbertreport.cc.com/episodes/8ase07/april-8--2014---jane-goodall',
-        'only_matching': True,
-    }, {
-        'url': 'http://thedailyshow.cc.com/video-playlists/npde3s/the-daily-show-19088-highlights',
-        'only_matching': True,
-    }, {
-        'url': 'http://thedailyshow.cc.com/video-playlists/t6d9sg/the-daily-show-20038-highlights/be3cwo',
-        'only_matching': True,
-    }, {
-        'url': 'http://thedailyshow.cc.com/special-editions/2l8fdb/special-edition---a-look-back-at-food',
-        'only_matching': True,
-    }, {
-        'url': 'http://thedailyshow.cc.com/news-team/michael-che/7wnfel/we-need-to-talk-about-israel',
-        'only_matching': True,
-    }, {
         'url': 'http://tosh.cc.com/video-clips/68g93d/twitter-users-share-summer-plans',
+        'info_dict': {
+            'description': 'Tosh asked fans to share their summer plans.',
+            'title': 'Twitter Users Share Summer Plans',
+        },
+        'playlist': [{
+            'md5': 'f269e88114c1805bb6d7653fecea9e06',
+            'info_dict': {
+                'id': '90498ec2-ed00-11e0-aca6-0026b9414f30',
+                'ext': 'mp4',
+                'title': 'Tosh.0|June 9, 2077|2|211|Twitter Users Share Summer Plans',
+                'description': 'Tosh asked fans to share their summer plans.',
+                'thumbnail': 're:^https?://.*\.jpg',
+                # It's really reported to be published on year 2077
+                'upload_date': '20770610',
+                'timestamp': 3390510600,
+                'subtitles': {
+                    'en': 'mincount:3',
+                },
+            },
+        }]
+    }, {
+        'url': 'http://tosh.cc.com/video-collections/x2iz7k/just-plain-foul/m5q4fp',
         'only_matching': True,
     }]
 
-    _available_formats = ['3500', '2200', '1700', '1200', '750', '400']
+    @classmethod
+    def _transform_rtmp_url(cls, rtmp_video_url):
+        new_urls = super(ToshIE, cls)._transform_rtmp_url(rtmp_video_url)
+        new_urls['rtmp'] = rtmp_video_url.replace('viacomccstrm', 'viacommtvstrm')
+        return new_urls
 
-    _video_extensions = {
-        '3500': 'mp4',
-        '2200': 'mp4',
-        '1700': 'mp4',
-        '1200': 'mp4',
-        '750': 'mp4',
-        '400': 'mp4',
-    }
-    _video_dimensions = {
-        '3500': (1280, 720),
-        '2200': (960, 540),
-        '1700': (768, 432),
-        '1200': (640, 360),
-        '750': (512, 288),
-        '400': (384, 216),
-    }
+
+class ComedyCentralTVIE(MTVServicesInfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?comedycentral\.tv/(?:staffeln|shows)/(?P<id>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'http://www.comedycentral.tv/staffeln/7436-the-mindy-project-staffel-4',
+        'info_dict': {
+            'id': 'local_playlist-f99b626bdfe13568579a',
+            'ext': 'flv',
+            'title': 'Episode_the-mindy-project_shows_season-4_episode-3_full-episode_part1',
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://www.comedycentral.tv/shows/1074-workaholics',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.comedycentral.tv/shows/1727-the-mindy-project/bonus',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
+        video_id = self._match_id(url)
 
-        if mobj.group('shortname'):
-            return self.url_result('http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes')
+        webpage = self._download_webpage(url, video_id)
 
-        if mobj.group('clip'):
-            if mobj.group('videotitle'):
-                epTitle = mobj.group('videotitle')
-            elif mobj.group('showname') == 'thedailyshow':
-                epTitle = mobj.group('tdstitle')
-            else:
-                epTitle = mobj.group('cntitle')
-            dlNewest = False
-        elif mobj.group('interview'):
-            epTitle = mobj.group('interview_title')
-            dlNewest = False
-        else:
-            dlNewest = not mobj.group('episode')
-            if dlNewest:
-                epTitle = mobj.group('showname')
-            else:
-                epTitle = mobj.group('episode')
-        show_name = mobj.group('showname')
+        mrss_url = self._search_regex(
+            r'data-mrss=(["\'])(?P<url>(?:(?!\1).)+)\1',
+            webpage, 'mrss url', group='url')
 
-        webpage, htmlHandle = self._download_webpage_handle(url, epTitle)
-        if dlNewest:
-            url = htmlHandle.geturl()
-            mobj = re.match(self._VALID_URL, url, re.VERBOSE)
-            if mobj is None:
-                raise ExtractorError('Invalid redirected URL: ' + url)
-            if mobj.group('episode') == '':
-                raise ExtractorError('Redirected URL is still not specific: ' + url)
-            epTitle = (mobj.group('episode') or mobj.group('videotitle')).rpartition('/')[-1]
+        return self._get_videos_info_from_url(mrss_url, video_id)
 
-        mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*(?:episode|video).*?:.*?))"', webpage)
-        if len(mMovieParams) == 0:
-            # The Colbert Report embeds the information in a without
-            # a URL prefix; so extract the alternate reference
-            # and then add the URL prefix manually.
 
-            altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video|playlist).*?:.*?)"', webpage)
-            if len(altMovieParams) == 0:
-                raise ExtractorError('unable to find Flash URL in webpage ' + url)
-            else:
-                mMovieParams = [('http://media.mtvnservices.com/' + altMovieParams[0], altMovieParams[0])]
+class ComedyCentralShortnameIE(InfoExtractor):
+    _VALID_URL = r'^:(?P<id>tds|thedailyshow)$'
+    _TESTS = [{
+        'url': ':tds',
+        'only_matching': True,
+    }, {
+        'url': ':thedailyshow',
+        'only_matching': True,
+    }]
 
-        uri = mMovieParams[0][1]
-        # Correct cc.com in uri
-        uri = re.sub(r'(episode:[^.]+)(\.cc)?\.com', r'\1.com', uri)
-
-        index_url = 'http://%s.cc.com/feeds/mrss?%s' % (show_name, compat_urllib_parse_urlencode({'uri': uri}))
-        idoc = self._download_xml(
-            index_url, epTitle,
-            'Downloading show index', 'Unable to download episode index')
-
-        title = idoc.find('./channel/title').text
-        description = idoc.find('./channel/description').text
-
-        entries = []
-        item_els = idoc.findall('.//item')
-        for part_num, itemEl in enumerate(item_els):
-            upload_date = unified_strdate(itemEl.findall('./pubDate')[0].text)
-            thumbnail = itemEl.find('.//{http://search.yahoo.com/mrss/}thumbnail').attrib.get('url')
-
-            content = itemEl.find('.//{http://search.yahoo.com/mrss/}content')
-            duration = float_or_none(content.attrib.get('duration'))
-            mediagen_url = content.attrib['url']
-            guid = itemEl.find('./guid').text.rpartition(':')[-1]
-
-            cdoc = self._download_xml(
-                mediagen_url, epTitle,
-                'Downloading configuration for segment %d / %d' % (part_num + 1, len(item_els)))
-
-            turls = []
-            for rendition in cdoc.findall('.//rendition'):
-                finfo = (rendition.attrib['bitrate'], rendition.findall('./src')[0].text)
-                turls.append(finfo)
-
-            formats = []
-            for format, rtmp_video_url in turls:
-                w, h = self._video_dimensions.get(format, (None, None))
-                formats.append({
-                    'format_id': 'vhttp-%s' % format,
-                    'url': self._transform_rtmp_url(rtmp_video_url),
-                    'ext': self._video_extensions.get(format, 'mp4'),
-                    'height': h,
-                    'width': w,
-                })
-                formats.append({
-                    'format_id': 'rtmp-%s' % format,
-                    'url': rtmp_video_url.replace('viacomccstrm', 'viacommtvstrm'),
-                    'ext': self._video_extensions.get(format, 'mp4'),
-                    'height': h,
-                    'width': w,
-                })
-                self._sort_formats(formats)
-
-            subtitles = self._extract_subtitles(cdoc, guid)
-
-            virtual_id = show_name + ' ' + epTitle + ' part ' + compat_str(part_num + 1)
-            entries.append({
-                'id': guid,
-                'title': virtual_id,
-                'formats': formats,
-                'uploader': show_name,
-                'upload_date': upload_date,
-                'duration': duration,
-                'thumbnail': thumbnail,
-                'description': description,
-                'subtitles': subtitles,
-            })
-
-        return {
-            '_type': 'playlist',
-            'id': epTitle,
-            'entries': entries,
-            'title': show_name + ' ' + title,
-            'description': description,
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        shortcut_map = {
+            'tds': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes',
+            'thedailyshow': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes',
         }
+        return self.url_result(shortcut_map[video_id])

youtube_dl/extractor/common.py

@@ -55,6 +55,8 @@ from ..utils import (
     update_Request,
     update_url_query,
     parse_m3u8_attributes,
+    extract_attributes,
+    parse_codecs,
 )
 
 
@@ -660,6 +662,24 @@ class InfoExtractor(object):
         else:
             return res
 
+    def _get_netrc_login_info(self, netrc_machine=None):
+        username = None
+        password = None
+        netrc_machine = netrc_machine or self._NETRC_MACHINE
+
+        if self._downloader.params.get('usenetrc', False):
+            try:
+                info = netrc.netrc().authenticators(netrc_machine)
+                if info is not None:
+                    username = info[0]
+                    password = info[2]
+                else:
+                    raise netrc.NetrcParseError('No authenticators for %s' % netrc_machine)
+            except (IOError, netrc.NetrcParseError) as err:
+                self._downloader.report_warning('parsing .netrc: %s' % error_to_compat_str(err))
+
+        return (username, password)
+
     def _get_login_info(self):
         """
         Get the login info as (username, password)
@@ -677,16 +697,8 @@ class InfoExtractor(object):
         if downloader_params.get('username') is not None:
             username = downloader_params['username']
             password = downloader_params['password']
-        elif downloader_params.get('usenetrc', False):
-            try:
-                info = netrc.netrc().authenticators(self._NETRC_MACHINE)
-                if info is not None:
-                    username = info[0]
-                    password = info[2]
-                else:
-                    raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
-            except (IOError, netrc.NetrcParseError) as err:
-                self._downloader.report_warning('parsing .netrc: %s' % error_to_compat_str(err))
+        else:
+            username, password = self._get_netrc_login_info()
 
         return (username, password)
 
@@ -725,9 +737,14 @@ class InfoExtractor(object):
                     [^>]+?content=(["\'])(?P<content>.*?)\2''' % re.escape(prop)
 
     def _og_search_property(self, prop, html, name=None, **kargs):
+        if not isinstance(prop, (list, tuple)):
+            prop = [prop]
         if name is None:
-            name = 'OpenGraph %s' % prop
-        escaped = self._search_regex(self._og_regexes(prop), html, name, flags=re.DOTALL, **kargs)
+            name = 'OpenGraph %s' % prop[0]
+        og_regexes = []
+        for p in prop:
+            og_regexes.extend(self._og_regexes(p))
+        escaped = self._search_regex(og_regexes, html, name, flags=re.DOTALL, **kargs)
         if escaped is None:
             return None
         return unescapeHTML(escaped)
@@ -809,11 +826,14 @@ class InfoExtractor(object):
         json_ld = self._search_regex(
             r'(?s)<script[^>]+type=(["\'])application/ld\+json\1[^>]*>(?P<json_ld>.+?)</script>',
             html, 'JSON-LD', group='json_ld', **kwargs)
+        default = kwargs.get('default', NO_DEFAULT)
         if not json_ld:
-            return {}
-        return self._json_ld(
-            json_ld, video_id, fatal=kwargs.get('fatal', True),
-            expected_type=expected_type)
+            return default if default is not NO_DEFAULT else {}
+        # JSON-LD may be malformed and thus `fatal` should be respected.
+        # At the same time `default` may be passed that assumes `fatal=False`
+        # for _search_regex. Let's simulate the same behavior here as well.
+        fatal = kwargs.get('fatal', True) if default == NO_DEFAULT else False
+        return self._json_ld(json_ld, video_id, fatal=fatal, expected_type=expected_type)
 
     def _json_ld(self, json_ld, video_id, fatal=True, expected_type=None):
         if isinstance(json_ld, compat_str):
@@ -821,41 +841,47 @@ class InfoExtractor(object):
         if not json_ld:
             return {}
         info = {}
-        if json_ld.get('@context') == 'http://schema.org':
-            item_type = json_ld.get('@type')
-            if expected_type is not None and expected_type != item_type:
-                return info
-            if item_type == 'TVEpisode':
-                info.update({
-                    'episode': unescapeHTML(json_ld.get('name')),
-                    'episode_number': int_or_none(json_ld.get('episodeNumber')),
-                    'description': unescapeHTML(json_ld.get('description')),
-                })
-                part_of_season = json_ld.get('partOfSeason')
-                if isinstance(part_of_season, dict) and part_of_season.get('@type') == 'TVSeason':
-                    info['season_number'] = int_or_none(part_of_season.get('seasonNumber'))
-                part_of_series = json_ld.get('partOfSeries')
-                if isinstance(part_of_series, dict) and part_of_series.get('@type') == 'TVSeries':
-                    info['series'] = unescapeHTML(part_of_series.get('name'))
-            elif item_type == 'Article':
-                info.update({
-                    'timestamp': parse_iso8601(json_ld.get('datePublished')),
-                    'title': unescapeHTML(json_ld.get('headline')),
-                    'description': unescapeHTML(json_ld.get('articleBody')),
-                })
-            elif item_type == 'VideoObject':
-                info.update({
-                    'url': json_ld.get('contentUrl'),
-                    'title': unescapeHTML(json_ld.get('name')),
-                    'description': unescapeHTML(json_ld.get('description')),
-                    'thumbnail': json_ld.get('thumbnailUrl'),
-                    'duration': parse_duration(json_ld.get('duration')),
-                    'timestamp': unified_timestamp(json_ld.get('uploadDate')),
-                    'filesize': float_or_none(json_ld.get('contentSize')),
-                    'tbr': int_or_none(json_ld.get('bitrate')),
-                    'width': int_or_none(json_ld.get('width')),
-                    'height': int_or_none(json_ld.get('height')),
-                })
+        if not isinstance(json_ld, (list, tuple, dict)):
+            return info
+        if isinstance(json_ld, dict):
+            json_ld = [json_ld]
+        for e in json_ld:
+            if e.get('@context') == 'http://schema.org':
+                item_type = e.get('@type')
+                if expected_type is not None and expected_type != item_type:
+                    return info
+                if item_type == 'TVEpisode':
+                    info.update({
+                        'episode': unescapeHTML(e.get('name')),
+                        'episode_number': int_or_none(e.get('episodeNumber')),
+                        'description': unescapeHTML(e.get('description')),
+                    })
+                    part_of_season = e.get('partOfSeason')
+                    if isinstance(part_of_season, dict) and part_of_season.get('@type') == 'TVSeason':
+                        info['season_number'] = int_or_none(part_of_season.get('seasonNumber'))
+                    part_of_series = e.get('partOfSeries') or e.get('partOfTVSeries')
+                    if isinstance(part_of_series, dict) and part_of_series.get('@type') == 'TVSeries':
+                        info['series'] = unescapeHTML(part_of_series.get('name'))
+                elif item_type == 'Article':
+                    info.update({
+                        'timestamp': parse_iso8601(e.get('datePublished')),
+                        'title': unescapeHTML(e.get('headline')),
+                        'description': unescapeHTML(e.get('articleBody')),
+                    })
+                elif item_type == 'VideoObject':
+                    info.update({
+                        'url': e.get('contentUrl'),
+                        'title': unescapeHTML(e.get('name')),
+                        'description': unescapeHTML(e.get('description')),
+                        'thumbnail': e.get('thumbnailUrl'),
+                        'duration': parse_duration(e.get('duration')),
+                        'timestamp': unified_timestamp(e.get('uploadDate')),
+                        'filesize': float_or_none(e.get('contentSize')),
+                        'tbr': int_or_none(e.get('bitrate')),
+                        'width': int_or_none(e.get('width')),
+                        'height': int_or_none(e.get('height')),
+                    })
+                break
         return dict((k, v) for k, v in info.items() if v is not None)
 
     @staticmethod
@@ -909,7 +935,8 @@ class InfoExtractor(object):
                 if f.get('ext') in ['f4f', 'f4m']:  # Not yet supported
                     preference -= 0.5
 
-            proto_preference = 0 if determine_protocol(f) in ['http', 'https'] else -0.1
+            protocol = f.get('protocol') or determine_protocol(f)
+            proto_preference = 0 if protocol in ['http', 'https'] else (-0.5 if protocol == 'rtsp' else -0.1)
 
             if f.get('vcodec') == 'none':  # audio only
                 preference -= 50
@@ -1126,7 +1153,7 @@ class InfoExtractor(object):
             'url': m3u8_url,
             'ext': ext,
             'protocol': 'm3u8',
-            'preference': preference - 1 if preference else -1,
+            'preference': preference - 100 if preference else -100,
             'resolution': 'multiple',
             'format_note': 'Quality selection URL',
         }
@@ -1205,6 +1232,7 @@ class InfoExtractor(object):
                     'url': format_url(line.strip()),
                     'tbr': tbr,
                     'ext': ext,
+                    'fps': float_or_none(last_info.get('FRAME-RATE')),
                     'protocol': entry_protocol,
                     'preference': preference,
                 }
@@ -1213,24 +1241,17 @@ class InfoExtractor(object):
                     width_str, height_str = resolution.split('x')
                     f['width'] = int(width_str)
                     f['height'] = int(height_str)
-                codecs = last_info.get('CODECS')
-                if codecs:
-                    vcodec, acodec = [None] * 2
-                    va_codecs = codecs.split(',')
-                    if len(va_codecs) == 1:
-                        # Audio only entries usually come with single codec and
-                        # no resolution. For more robustness we also check it to
-                        # be mp4 audio.
-                        if not resolution and va_codecs[0].startswith('mp4a'):
-                            vcodec, acodec = 'none', va_codecs[0]
-                        else:
-                            vcodec = va_codecs[0]
-                    else:
-                        vcodec, acodec = va_codecs[:2]
+                # Unified Streaming Platform
+                mobj = re.search(
+                    r'audio.*?(?:%3D|=)(\d+)(?:-video.*?(?:%3D|=)(\d+))?', f['url'])
+                if mobj:
+                    abr, vbr = mobj.groups()
+                    abr, vbr = float_or_none(abr, 1000), float_or_none(vbr, 1000)
                     f.update({
-                        'acodec': acodec,
-                        'vcodec': vcodec,
+                        'vbr': vbr,
+                        'abr': abr,
                     })
+                f.update(parse_codecs(last_info.get('CODECS')))
                 if last_media is not None:
                     f['m3u8_media'] = last_media
                     last_media = None
@@ -1485,6 +1506,13 @@ class InfoExtractor(object):
             compat_etree_fromstring(mpd.encode('utf-8')), mpd_id, mpd_base_url, formats_dict=formats_dict)
 
     def _parse_mpd_formats(self, mpd_doc, mpd_id=None, mpd_base_url='', formats_dict={}):
+        """
+        Parse formats from MPD manifest.
+        References:
+         1. MPEG-DASH Standard, ISO/IEC 23009-1:2014(E),
+            http://standards.iso.org/ittf/PubliclyAvailableStandards/c065274_ISO_IEC_23009-1_2014.zip
+         2. https://en.wikipedia.org/wiki/Dynamic_Adaptive_Streaming_over_HTTP
+        """
         if mpd_doc.get('type') == 'dynamic':
             return []
 
@@ -1517,8 +1545,16 @@ class InfoExtractor(object):
                         s_e = segment_timeline.findall(_add_ns('S'))
                         if s_e:
                             ms_info['total_number'] = 0
+                            ms_info['s'] = []
                             for s in s_e:
-                                ms_info['total_number'] += 1 + int(s.get('r', '0'))
+                                r = int(s.get('r', 0))
+                                ms_info['total_number'] += 1 + r
+                                ms_info['s'].append({
+                                    't': int(s.get('t', 0)),
+                                    # @d is mandatory (see [1, 5.3.9.6.2, Table 17, page 60])
+                                    'd': int(s.attrib['d']),
+                                    'r': r,
+                                })
                     else:
                         timescale = segment_template.get('timescale')
                         if timescale:
@@ -1555,7 +1591,7 @@ class InfoExtractor(object):
                         continue
                     representation_attrib = adaptation_set.attrib.copy()
                     representation_attrib.update(representation.attrib)
-                    # According to page 41 of ISO/IEC 29001-1:2014, @mimeType is mandatory
+                    # According to [1, 5.3.7.2, Table 9, page 41], @mimeType is mandatory
                     mime_type = representation_attrib['mimeType']
                     content_type = mime_type.split('/')[0]
                     if content_type == 'text':
@@ -1599,16 +1635,40 @@ class InfoExtractor(object):
                                 representation_ms_info['total_number'] = int(math.ceil(float(period_duration) / segment_duration))
                             media_template = representation_ms_info['media_template']
                             media_template = media_template.replace('$RepresentationID$', representation_id)
-                            media_template = re.sub(r'\$(Number|Bandwidth)\$', r'%(\1)d', media_template)
-                            media_template = re.sub(r'\$(Number|Bandwidth)%([^$]+)\$', r'%(\1)\2', media_template)
+                            media_template = re.sub(r'\$(Number|Bandwidth|Time)\$', r'%(\1)d', media_template)
+                            media_template = re.sub(r'\$(Number|Bandwidth|Time)%([^$]+)\$', r'%(\1)\2', media_template)
                             media_template.replace('$$', '$')
-                            representation_ms_info['segment_urls'] = [
-                                media_template % {
-                                    'Number': segment_number,
-                                    'Bandwidth': representation_attrib.get('bandwidth')}
-                                for segment_number in range(
-                                    representation_ms_info['start_number'],
-                                    representation_ms_info['total_number'] + representation_ms_info['start_number'])]
+
+                            # As per [1, 5.3.9.4.4, Table 16, page 55] $Number$ and $Time$
+                            # can't be used at the same time
+                            if '%(Number' in media_template:
+                                representation_ms_info['segment_urls'] = [
+                                    media_template % {
+                                        'Number': segment_number,
+                                        'Bandwidth': representation_attrib.get('bandwidth'),
+                                    }
+                                    for segment_number in range(
+                                        representation_ms_info['start_number'],
+                                        representation_ms_info['total_number'] + representation_ms_info['start_number'])]
+                            else:
+                                representation_ms_info['segment_urls'] = []
+                                segment_time = 0
+
+                                def add_segment_url():
+                                    representation_ms_info['segment_urls'].append(
+                                        media_template % {
+                                            'Time': segment_time,
+                                            'Bandwidth': representation_attrib.get('bandwidth'),
+                                        }
+                                    )
+
+                                for num, s in enumerate(representation_ms_info['s']):
+                                    segment_time = s.get('t') or segment_time
+                                    add_segment_url()
+                                    for r in range(s.get('r', 0)):
+                                        segment_time += s['d']
+                                        add_segment_url()
+                                    segment_time += s['d']
                         if 'segment_urls' in representation_ms_info:
                             f.update({
                                 'segment_urls': representation_ms_info['segment_urls'],
@@ -1635,6 +1695,62 @@ class InfoExtractor(object):
                         self.report_warning('Unknown MIME type %s in DASH manifest' % mime_type)
         return formats
 
+    def _parse_html5_media_entries(self, base_url, webpage):
+        def absolute_url(video_url):
+            return compat_urlparse.urljoin(base_url, video_url)
+
+        def parse_content_type(content_type):
+            if not content_type:
+                return {}
+            ctr = re.search(r'(?P<mimetype>[^/]+/[^;]+)(?:;\s*codecs="?(?P<codecs>[^"]+))?', content_type)
+            if ctr:
+                mimetype, codecs = ctr.groups()
+                f = parse_codecs(codecs)
+                f['ext'] = mimetype2ext(mimetype)
+                return f
+            return {}
+
+        entries = []
+        for media_tag, media_type, media_content in re.findall(r'(?s)(<(?P<tag>video|audio)[^>]*>)(.*?)</(?P=tag)>', webpage):
+            media_info = {
+                'formats': [],
+                'subtitles': {},
+            }
+            media_attributes = extract_attributes(media_tag)
+            src = media_attributes.get('src')
+            if src:
+                media_info['formats'].append({
+                    'url': absolute_url(src),
+                    'vcodec': 'none' if media_type == 'audio' else None,
+                })
+            media_info['thumbnail'] = media_attributes.get('poster')
+            if media_content:
+                for source_tag in re.findall(r'<source[^>]+>', media_content):
+                    source_attributes = extract_attributes(source_tag)
+                    src = source_attributes.get('src')
+                    if not src:
+                        continue
+                    f = parse_content_type(source_attributes.get('type'))
+                    f.update({
+                        'url': absolute_url(src),
+                        'vcodec': 'none' if media_type == 'audio' else None,
+                    })
+                    media_info['formats'].append(f)
+                for track_tag in re.findall(r'<track[^>]+>', media_content):
+                    track_attributes = extract_attributes(track_tag)
+                    kind = track_attributes.get('kind')
+                    if not kind or kind == 'subtitles':
+                        src = track_attributes.get('src')
+                        if not src:
+                            continue
+                        lang = track_attributes.get('srclang') or track_attributes.get('lang') or track_attributes.get('label')
+                        media_info['subtitles'].setdefault(lang, []).append({
+                            'url': absolute_url(src),
+                        })
+            if media_info['formats']:
+                entries.append(media_info)
+        return entries
+
     def _live_title(self, name):
         """ Generate the title for a live video """
         now = datetime.datetime.now()
@@ -1695,7 +1811,7 @@ class InfoExtractor(object):
 
         any_restricted = False
         for tc in self.get_testcases(include_onlymatching=False):
-            if 'playlist' in tc:
+            if tc.get('playlist', []):
                 tc = tc['playlist'][0]
             is_restricted = age_restricted(
                 tc.get('info_dict', {}).get('age_limit'), age_limit)

youtube_dl/extractor/condenast.py

@@ -5,13 +5,17 @@ import re
 
 from .common import InfoExtractor
 from ..compat import (
-    compat_urllib_parse_urlencode,
     compat_urllib_parse_urlparse,
     compat_urlparse,
 )
 from ..utils import (
     orderedSet,
     remove_end,
+    extract_attributes,
+    mimetype2ext,
+    determine_ext,
+    int_or_none,
+    parse_iso8601,
 )
 
 
@@ -58,6 +62,9 @@ class CondeNastIE(InfoExtractor):
             'ext': 'mp4',
             'title': '3D Printed Speakers Lit With LED',
             'description': 'Check out these beautiful 3D printed LED speakers.  You can\'t actually buy them, but LumiGeek is working on a board that will let you make you\'re own.',
+            'uploader': 'wired',
+            'upload_date': '20130314',
+            'timestamp': 1363219200,
         }
     }, {
         # JS embed
@@ -67,70 +74,93 @@ class CondeNastIE(InfoExtractor):
             'id': '55f9cf8b61646d1acf00000c',
             'ext': 'mp4',
             'title': '3D printed TSA Travel Sentry keys really do open TSA locks',
+            'uploader': 'arstechnica',
+            'upload_date': '20150916',
+            'timestamp': 1442434955,
         }
     }]
 
     def _extract_series(self, url, webpage):
-        title = self._html_search_regex(r'<div class="cne-series-info">.*?<h1>(.+?)</h1>',
-                                        webpage, 'series title', flags=re.DOTALL)
+        title = self._html_search_regex(
+            r'(?s)<div class="cne-series-info">.*?<h1>(.+?)</h1>',
+            webpage, 'series title')
         url_object = compat_urllib_parse_urlparse(url)
         base_url = '%s://%s' % (url_object.scheme, url_object.netloc)
-        m_paths = re.finditer(r'<p class="cne-thumb-title">.*?<a href="(/watch/.+?)["\?]',
-                              webpage, flags=re.DOTALL)
+        m_paths = re.finditer(
+            r'(?s)<p class="cne-thumb-title">.*?<a href="(/watch/.+?)["\?]', webpage)
         paths = orderedSet(m.group(1) for m in m_paths)
         build_url = lambda path: compat_urlparse.urljoin(base_url, path)
         entries = [self.url_result(build_url(path), 'CondeNast') for path in paths]
         return self.playlist_result(entries, playlist_title=title)
 
     def _extract_video(self, webpage, url_type):
-        if url_type != 'embed':
-            description = self._html_search_regex(
-                [
-                    r'<div class="cne-video-description">(.+?)</div>',
-                    r'<div class="video-post-content">(.+?)</div>',
-                ],
-                webpage, 'description', fatal=False, flags=re.DOTALL)
+        query = {}
+        params = self._search_regex(
+            r'(?s)var params = {(.+?)}[;,]', webpage, 'player params', default=None)
+        if params:
+            query.update({
+                'videoId': self._search_regex(r'videoId: [\'"](.+?)[\'"]', params, 'video id'),
+                'playerId': self._search_regex(r'playerId: [\'"](.+?)[\'"]', params, 'player id'),
+                'target': self._search_regex(r'target: [\'"](.+?)[\'"]', params, 'target'),
+            })
         else:
-            description = None
-        params = self._search_regex(r'var params = {(.+?)}[;,]', webpage,
-                                    'player params', flags=re.DOTALL)
-        video_id = self._search_regex(r'videoId: [\'"](.+?)[\'"]', params, 'video id')
-        player_id = self._search_regex(r'playerId: [\'"](.+?)[\'"]', params, 'player id')
-        target = self._search_regex(r'target: [\'"](.+?)[\'"]', params, 'target')
-        data = compat_urllib_parse_urlencode({'videoId': video_id,
-                                              'playerId': player_id,
-                                              'target': target,
-                                              })
-        base_info_url = self._search_regex(r'url = [\'"](.+?)[\'"][,;]',
-                                           webpage, 'base info url',
-                                           default='http://player.cnevids.com/player/loader.js?')
-        info_url = base_info_url + data
-        info_page = self._download_webpage(info_url, video_id,
-                                           'Downloading video info')
-        video_info = self._search_regex(r'var\s+video\s*=\s*({.+?});', info_page, 'video info')
-        video_info = self._parse_json(video_info, video_id)
+            params = extract_attributes(self._search_regex(
+                r'(<[^>]+data-js="video-player"[^>]+>)',
+                webpage, 'player params element'))
+            query.update({
+                'videoId': params['data-video'],
+                'playerId': params['data-player'],
+                'target': params['id'],
+            })
+        video_id = query['videoId']
+        video_info = None
+        info_page = self._download_webpage(
+            'http://player.cnevids.com/player/video.js',
+            video_id, 'Downloading video info', query=query, fatal=False)
+        if info_page:
+            video_info = self._parse_json(self._search_regex(
+                r'loadCallback\(({.+})\)', info_page, 'video info'), video_id)['video']
+        else:
+            info_page = self._download_webpage(
+                'http://player.cnevids.com/player/loader.js',
+                video_id, 'Downloading loader info', query=query)
+            video_info = self._parse_json(self._search_regex(
+                r'var\s+video\s*=\s*({.+?});', info_page, 'video info'), video_id)
+        title = video_info['title']
 
-        formats = [{
-            'format_id': '%s-%s' % (fdata['type'].split('/')[-1], fdata['quality']),
-            'url': fdata['src'],
-            'ext': fdata['type'].split('/')[-1],
-            'quality': 1 if fdata['quality'] == 'high' else 0,
-        } for fdata in video_info['sources'][0]]
+        formats = []
+        for fdata in video_info.get('sources', [{}])[0]:
+            src = fdata.get('src')
+            if not src:
+                continue
+            ext = mimetype2ext(fdata.get('type')) or determine_ext(src)
+            quality = fdata.get('quality')
+            formats.append({
+                'format_id': ext + ('-%s' % quality if quality else ''),
+                'url': src,
+                'ext': ext,
+                'quality': 1 if quality == 'high' else 0,
+            })
         self._sort_formats(formats)
 
-        return {
+        info = self._search_json_ld(
+            webpage, video_id, fatal=False) if url_type != 'embed' else {}
+        info.update({
             'id': video_id,
             'formats': formats,
-            'title': video_info['title'],
-            'thumbnail': video_info['poster_frame'],
-            'description': description,
-        }
+            'title': title,
+            'thumbnail': video_info.get('poster_frame'),
+            'uploader': video_info.get('brand'),
+            'duration': int_or_none(video_info.get('duration')),
+            'tags': video_info.get('tags'),
+            'series': video_info.get('series_title'),
+            'season': video_info.get('season_title'),
+            'timestamp': parse_iso8601(video_info.get('premiere_date')),
+        })
+        return info
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        site = mobj.group('site')
-        url_type = mobj.group('type')
-        item_id = mobj.group('id')
+        site, url_type, item_id = re.match(self._VALID_URL, url).groups()
 
         # Convert JS embed to regular embed
         if url_type == 'embedjs':

youtube_dl/extractor/crunchyroll.py

@@ -114,6 +114,21 @@ class CrunchyrollIE(CrunchyrollBaseIE):
             # rtmp
             'skip_download': True,
         },
+    }, {
+        'url': 'http://www.crunchyroll.com/rezero-starting-life-in-another-world-/episode-5-the-morning-of-our-promise-is-still-distant-702409',
+        'info_dict': {
+            'id': '702409',
+            'ext': 'mp4',
+            'title': 'Re:ZERO -Starting Life in Another World- Episode 5 – The Morning of Our Promise Is Still Distant',
+            'description': 'md5:97664de1ab24bbf77a9c01918cb7dca9',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'uploader': 'TV TOKYO',
+            'upload_date': '20160508',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
     }, {
         'url': 'http://www.crunchyroll.fr/girl-friend-beta/episode-11-goodbye-la-mode-661697',
         'only_matching': True,
@@ -336,9 +351,18 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
             if video_encode_id in video_encode_ids:
                 continue
             video_encode_ids.append(video_encode_id)
+
+            video_file = xpath_text(stream_info, './file')
+            if not video_file:
+                continue
+            if video_file.startswith('http'):
+                formats.extend(self._extract_m3u8_formats(
+                    video_file, video_id, 'mp4', entry_protocol='m3u8_native',
+                    m3u8_id='hls', fatal=False))
+                continue
+
             video_url = xpath_text(stream_info, './host')
-            video_play_path = xpath_text(stream_info, './file')
-            if not video_url or not video_play_path:
+            if not video_url:
                 continue
             metadata = stream_info.find('./metadata')
             format_info = {
@@ -353,7 +377,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
                 parsed_video_url = compat_urlparse.urlparse(video_url)
                 direct_video_url = compat_urlparse.urlunparse(parsed_video_url._replace(
                     netloc='v.lvlt.crcdn.net',
-                    path='%s/%s' % (remove_end(parsed_video_url.path, '/'), video_play_path.split(':')[-1])))
+                    path='%s/%s' % (remove_end(parsed_video_url.path, '/'), video_file.split(':')[-1])))
                 if self._is_valid_url(direct_video_url, video_id, video_format):
                     format_info.update({
                         'url': direct_video_url,
@@ -363,7 +387,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
 
             format_info.update({
                 'url': video_url,
-                'play_path': video_play_path,
+                'play_path': video_file,
                 'ext': 'flv',
             })
             formats.append(format_info)

youtube_dl/extractor/cspan.py

@@ -51,8 +51,11 @@ class CSpanIE(InfoExtractor):
         'url': 'http://www.c-span.org/video/?104517-1/immigration-reforms-needed-protect-skilled-american-workers',
         'info_dict': {
             'id': 'judiciary031715',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': 'Immigration Reforms Needed to Protect Skilled American Workers',
+        },
+        'params': {
+            'skip_download': True,  # m3u8 downloads
         }
     }]
 

youtube_dl/extractor/ctsnews.py

@@ -1,13 +1,12 @@
-# -*- coding: utf-8 -*-
+# coding: utf-8
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import parse_iso8601, ExtractorError
+from ..utils import unified_timestamp
 
 
 class CtsNewsIE(InfoExtractor):
     IE_DESC = '華視新聞'
-    # https connection failed (Connection reset)
     _VALID_URL = r'https?://news\.cts\.com\.tw/[a-z]+/[a-z]+/\d+/(?P<id>\d+)\.html'
     _TESTS = [{
         'url': 'http://news.cts.com.tw/cts/international/201501/201501291578109.html',
@@ -16,7 +15,7 @@ class CtsNewsIE(InfoExtractor):
             'id': '201501291578109',
             'ext': 'mp4',
             'title': '以色列.真主黨交火 3人死亡',
-            'description': 'md5:95e9b295c898b7ff294f09d450178d7d',
+            'description': '以色列和黎巴嫩真主黨，爆發五年最嚴重衝突，雙方砲轟交火，兩名以軍死亡，還有一名西班牙籍的聯合國維和人...',
             'timestamp': 1422528540,
             'upload_date': '20150129',
         }
@@ -28,7 +27,7 @@ class CtsNewsIE(InfoExtractor):
             'id': '201309031304098',
             'ext': 'mp4',
             'title': '韓國31歲童顏男 貌如十多歲小孩',
-            'description': 'md5:f183feeba3752b683827aab71adad584',
+            'description': '越有年紀的人，越希望看起來年輕一點，而南韓卻有一位31歲的男子，看起來像是11、12歲的小孩，身...',
             'thumbnail': 're:^https?://.*\.jpg$',
             'timestamp': 1378205880,
             'upload_date': '20130903',
@@ -36,8 +35,7 @@ class CtsNewsIE(InfoExtractor):
     }, {
         # With Youtube embedded video
         'url': 'http://news.cts.com.tw/cts/money/201501/201501291578003.html',
-        'md5': '1d842c771dc94c8c3bca5af2cc1db9c5',
-        'add_ie': ['Youtube'],
+        'md5': 'e4726b2ccd70ba2c319865e28f0a91d1',
         'info_dict': {
             'id': 'OVbfO7d0_hQ',
             'ext': 'mp4',
@@ -47,42 +45,37 @@ class CtsNewsIE(InfoExtractor):
             'upload_date': '20150128',
             'uploader_id': 'TBSCTS',
             'uploader': '中華電視公司',
-        }
+        },
+        'add_ie': ['Youtube'],
     }]
 
     def _real_extract(self, url):
         news_id = self._match_id(url)
         page = self._download_webpage(url, news_id)
 
-        if self._search_regex(r'(CTSPlayer2)', page, 'CTSPlayer2 identifier', default=None):
-            feed_url = self._html_search_regex(
-                r'(http://news\.cts\.com\.tw/action/mp4feed\.php\?news_id=\d+)',
-                page, 'feed url')
-            video_url = self._download_webpage(
-                feed_url, news_id, note='Fetching feed')
+        news_id = self._hidden_inputs(page).get('get_id')
+
+        if news_id:
+            mp4_feed = self._download_json(
+                'http://news.cts.com.tw/action/test_mp4feed.php',
+                news_id, note='Fetching feed', query={'news_id': news_id})
+            video_url = mp4_feed['source_url']
         else:
             self.to_screen('Not CTSPlayer video, trying Youtube...')
             youtube_url = self._search_regex(
-                r'src="(//www\.youtube\.com/embed/[^"]+)"', page, 'youtube url',
-                default=None)
-            if not youtube_url:
-                raise ExtractorError('The news includes no videos!', expected=True)
+                r'src="(//www\.youtube\.com/embed/[^"]+)"', page, 'youtube url')
 
-            return {
-                '_type': 'url',
-                'url': youtube_url,
-                'ie_key': 'Youtube',
-            }
+            return self.url_result(youtube_url, ie='Youtube')
 
         description = self._html_search_meta('description', page)
-        title = self._html_search_meta('title', page)
+        title = self._html_search_meta('title', page, fatal=True)
         thumbnail = self._html_search_meta('image', page)
 
         datetime_str = self._html_search_regex(
-            r'(\d{4}/\d{2}/\d{2} \d{2}:\d{2})', page, 'date and time')
-        # Transform into ISO 8601 format with timezone info
-        datetime_str = datetime_str.replace('/', '-') + ':00+0800'
-        timestamp = parse_iso8601(datetime_str, delimiter=' ')
+            r'(\d{4}/\d{2}/\d{2} \d{2}:\d{2})', page, 'date and time', fatal=False)
+        timestamp = None
+        if datetime_str:
+            timestamp = unified_timestamp(datetime_str) - 8 * 3600
 
         return {
             'id': news_id,

youtube_dl/extractor/cwtv.py

@@ -9,7 +9,7 @@ from ..utils import (
 
 
 class CWTVIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?cw(?:tv|seed)\.com/(?:shows/)?(?:[^/]+/){2}\?.*\bplay=(?P<id>[a-z0-9]{8}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{12})'
+    _VALID_URL = r'https?://(?:www\.)?cw(?:tv(?:pr)?|seed)\.com/(?:shows/)?(?:[^/]+/)+[^?]*\?.*\b(?:play|watch)=(?P<id>[a-z0-9]{8}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{12})'
     _TESTS = [{
         'url': 'http://cwtv.com/shows/arrow/legends-of-yesterday/?play=6b15e985-9345-4f60-baf8-56e96be57c63',
         'info_dict': {
@@ -28,7 +28,8 @@ class CWTVIE(InfoExtractor):
         'params': {
             # m3u8 download
             'skip_download': True,
-        }
+        },
+        'skip': 'redirect to http://cwtv.com/shows/arrow/',
     }, {
         'url': 'http://www.cwseed.com/shows/whose-line-is-it-anyway/jeff-davis-4/?play=24282b12-ead2-42f2-95ad-26770c2c6088',
         'info_dict': {
@@ -44,22 +45,43 @@ class CWTVIE(InfoExtractor):
             'upload_date': '20151006',
             'timestamp': 1444107300,
         },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
-        }
     }, {
         'url': 'http://cwtv.com/thecw/chroniclesofcisco/?play=8adebe35-f447-465f-ab52-e863506ff6d6',
         'only_matching': True,
+    }, {
+        'url': 'http://cwtvpr.com/the-cw/video?watch=9eee3f60-ef4e-440b-b3b2-49428ac9c54e',
+        'only_matching': True,
+    }, {
+        'url': 'http://cwtv.com/shows/arrow/legends-of-yesterday/?watch=6b15e985-9345-4f60-baf8-56e96be57c63',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        video_data = self._download_json(
-            'http://metaframe.digitalsmiths.tv/v2/CWtv/assets/%s/partner/132?format=json' % video_id, video_id)
-
-        formats = self._extract_m3u8_formats(
-            video_data['videos']['variantplaylist']['uri'], video_id, 'mp4')
+        video_data = None
+        formats = []
+        for partner in (154, 213):
+            vdata = self._download_json(
+                'http://metaframe.digitalsmiths.tv/v2/CWtv/assets/%s/partner/%d?format=json' % (video_id, partner), video_id, fatal=False)
+            if not vdata:
+                continue
+            video_data = vdata
+            for quality, quality_data in vdata.get('videos', {}).items():
+                quality_url = quality_data.get('uri')
+                if not quality_url:
+                    continue
+                if quality == 'variantplaylist':
+                    formats.extend(self._extract_m3u8_formats(
+                        quality_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
+                else:
+                    tbr = int_or_none(quality_data.get('bitrate'))
+                    format_id = 'http' + ('-%d' % tbr if tbr else '')
+                    if self._is_valid_url(quality_url, video_id, format_id):
+                        formats.append({
+                            'format_id': format_id,
+                            'url': quality_url,
+                            'tbr': tbr,
+                        })
         self._sort_formats(formats)
 
         thumbnails = [{

youtube_dl/extractor/dailymail.py

@@ -5,19 +5,20 @@ from .common import InfoExtractor
 from ..utils import (
     int_or_none,
     determine_protocol,
+    unescapeHTML,
 )
 
 
 class DailyMailIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?dailymail\.co\.uk/video/[^/]+/video-(?P<id>[0-9]+)'
     _TEST = {
-        'url': 'http://www.dailymail.co.uk/video/sciencetech/video-1288527/Turn-video-impressionist-masterpiece.html',
-        'md5': '2f639d446394f53f3a33658b518b6615',
+        'url': 'http://www.dailymail.co.uk/video/tvshowbiz/video-1295863/The-Mountain-appears-sparkling-water-ad-Heavy-Bubbles.html',
+        'md5': 'f6129624562251f628296c3a9ffde124',
         'info_dict': {
-            'id': '1288527',
+            'id': '1295863',
             'ext': 'mp4',
-            'title': 'Turn any video into an impressionist masterpiece',
-            'description': 'md5:88ddbcb504367987b2708bb38677c9d2',
+            'title': 'The Mountain appears in sparkling water ad for \'Heavy Bubbles\'',
+            'description': 'md5:a93d74b6da172dd5dc4d973e0b766a84',
         }
     }
 
@@ -26,7 +27,7 @@ class DailyMailIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
         video_data = self._parse_json(self._search_regex(
             r"data-opts='({.+?})'", webpage, 'video data'), video_id)
-        title = video_data['title']
+        title = unescapeHTML(video_data['title'])
         video_sources = self._download_json(video_data.get(
             'sources', {}).get('url') or 'http://www.dailymail.co.uk/api/player/%s/video-sources.json' % video_id, video_id)
 
@@ -55,7 +56,7 @@ class DailyMailIE(InfoExtractor):
         return {
             'id': video_id,
             'title': title,
-            'description': video_data.get('descr'),
+            'description': unescapeHTML(video_data.get('descr')),
             'thumbnail': video_data.get('poster') or video_data.get('thumbnail'),
             'formats': formats,
         }

youtube_dl/extractor/dailymotion.py

@@ -331,7 +331,9 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
 
             for video_id in re.findall(r'data-xid="(.+?)"', webpage):
                 if video_id not in video_ids:
-                    yield self.url_result('http://www.dailymotion.com/video/%s' % video_id, 'Dailymotion')
+                    yield self.url_result(
+                        'http://www.dailymotion.com/video/%s' % video_id,
+                        DailymotionIE.ie_key(), video_id)
                     video_ids.add(video_id)
 
             if re.search(self._MORE_PAGES_INDICATOR, webpage) is None:

youtube_dl/extractor/dbtv.py

@@ -4,78 +4,47 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_str
-from ..utils import (
-    float_or_none,
-    int_or_none,
-    clean_html,
-)
 
 
 class DBTVIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?dbtv\.no/(?:(?:lazyplayer|player)/)?(?P<id>[0-9]+)(?:#(?P<display_id>.+))?'
+    _VALID_URL = r'https?://(?:www\.)?dbtv\.no/(?:[^/]+/)?(?P<id>[0-9]+)(?:#(?P<display_id>.+))?'
     _TESTS = [{
         'url': 'http://dbtv.no/3649835190001#Skulle_teste_ut_fornøyelsespark,_men_kollegaen_var_bare_opptatt_av_bikinikroppen',
-        'md5': 'b89953ed25dacb6edb3ef6c6f430f8bc',
+        'md5': '2e24f67936517b143a234b4cadf792ec',
         'info_dict': {
-            'id': '33100',
+            'id': '3649835190001',
             'display_id': 'Skulle_teste_ut_fornøyelsespark,_men_kollegaen_var_bare_opptatt_av_bikinikroppen',
             'ext': 'mp4',
             'title': 'Skulle teste ut fornøyelsespark, men kollegaen var bare opptatt av bikinikroppen',
             'description': 'md5:1504a54606c4dde3e4e61fc97aa857e0',
-            'thumbnail': 're:https?://.*\.jpg$',
-            'timestamp': 1404039863.438,
+            'thumbnail': 're:https?://.*\.jpg',
+            'timestamp': 1404039863,
             'upload_date': '20140629',
             'duration': 69.544,
-            'view_count': int,
-            'categories': list,
-        }
+            'uploader_id': '1027729757001',
+        },
+        'add_ie': ['BrightcoveNew']
     }, {
         'url': 'http://dbtv.no/3649835190001',
         'only_matching': True,
     }, {
         'url': 'http://www.dbtv.no/lazyplayer/4631135248001',
         'only_matching': True,
+    }, {
+        'url': 'http://dbtv.no/vice/5000634109001',
+        'only_matching': True,
+    }, {
+        'url': 'http://dbtv.no/filmtrailer/3359293614001',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        display_id = mobj.group('display_id') or video_id
-
-        data = self._download_json(
-            'http://api.dbtv.no/discovery/%s' % video_id, display_id)
-
-        video = data['playlist'][0]
-
-        formats = [{
-            'url': f['URL'],
-            'vcodec': f.get('container'),
-            'width': int_or_none(f.get('width')),
-            'height': int_or_none(f.get('height')),
-            'vbr': float_or_none(f.get('rate'), 1000),
-            'filesize': int_or_none(f.get('size')),
-        } for f in video['renditions'] if 'URL' in f]
-
-        if not formats:
-            for url_key, format_id in [('URL', 'mp4'), ('HLSURL', 'hls')]:
-                if url_key in video:
-                    formats.append({
-                        'url': video[url_key],
-                        'format_id': format_id,
-                    })
-
-        self._sort_formats(formats)
+        video_id, display_id = re.match(self._VALID_URL, url).groups()
 
         return {
-            'id': compat_str(video['id']),
+            '_type': 'url_transparent',
+            'url': 'http://players.brightcove.net/1027729757001/default_default/index.html?videoId=%s' % video_id,
+            'id': video_id,
             'display_id': display_id,
-            'title': video['title'],
-            'description': clean_html(video['desc']),
-            'thumbnail': video.get('splash') or video.get('thumb'),
-            'timestamp': float_or_none(video.get('publishedAt'), 1000),
-            'duration': float_or_none(video.get('length'), 1000),
-            'view_count': int_or_none(video.get('views')),
-            'categories': video.get('tags'),
-            'formats': formats,
+            'ie_key': 'BrightcoveNew',
         }

youtube_dl/extractor/dcn.py

@@ -62,11 +62,9 @@ class DCNBaseIE(InfoExtractor):
                 r'file\s*:\s*"https?(://[^"]+)/playlist.m3u8',
                 r'<a[^>]+href="rtsp(://[^"]+)"'
             ], webpage, 'format url')
-        # TODO: Current DASH formats are broken - $Time$ pattern in
-        # <SegmentTemplate> not implemented yet
-        # formats.extend(self._extract_mpd_formats(
-        #     format_url_base + '/manifest.mpd',
-        #     video_id, mpd_id='dash', fatal=False))
+        formats.extend(self._extract_mpd_formats(
+            format_url_base + '/manifest.mpd',
+            video_id, mpd_id='dash', fatal=False))
         formats.extend(self._extract_m3u8_formats(
             format_url_base + '/playlist.m3u8', video_id, 'mp4',
             m3u8_entry_protocol, m3u8_id='hls', fatal=False))

youtube_dl/extractor/discoverygo.py

@@ -0,0 +1,98 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    extract_attributes,
+    int_or_none,
+    parse_age_limit,
+    unescapeHTML,
+)
+
+
+class DiscoveryGoIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?discoverygo\.com/(?:[^/]+/)*(?P<id>[^/?#&]+)'
+    _TEST = {
+        'url': 'https://www.discoverygo.com/love-at-first-kiss/kiss-first-ask-questions-later/',
+        'info_dict': {
+            'id': '57a33c536b66d1cd0345eeb1',
+            'ext': 'mp4',
+            'title': 'Kiss First, Ask Questions Later!',
+            'description': 'md5:fe923ba34050eae468bffae10831cb22',
+            'duration': 2579,
+            'series': 'Love at First Kiss',
+            'season_number': 1,
+            'episode_number': 1,
+            'age_limit': 14,
+        },
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        container = extract_attributes(
+            self._search_regex(
+                r'(<div[^>]+class=["\']video-player-container[^>]+>)',
+                webpage, 'video container'))
+
+        video = self._parse_json(
+            unescapeHTML(container.get('data-video') or container.get('data-json')),
+            display_id)
+
+        title = video['name']
+
+        stream = video['stream']
+        STREAM_URL_SUFFIX = 'streamUrl'
+        formats = []
+        for stream_kind in ('', 'hds'):
+            suffix = STREAM_URL_SUFFIX.capitalize() if stream_kind else STREAM_URL_SUFFIX
+            stream_url = stream.get('%s%s' % (stream_kind, suffix))
+            if not stream_url:
+                continue
+            if stream_kind == '':
+                formats.extend(self._extract_m3u8_formats(
+                    stream_url, display_id, 'mp4', entry_protocol='m3u8_native',
+                    m3u8_id='hls', fatal=False))
+            elif stream_kind == 'hds':
+                formats.extend(self._extract_f4m_formats(
+                    stream_url, display_id, f4m_id=stream_kind, fatal=False))
+        self._sort_formats(formats)
+
+        video_id = video.get('id') or display_id
+        description = video.get('description', {}).get('detailed')
+        duration = int_or_none(video.get('duration'))
+
+        series = video.get('show', {}).get('name')
+        season_number = int_or_none(video.get('season', {}).get('number'))
+        episode_number = int_or_none(video.get('episodeNumber'))
+
+        tags = video.get('tags')
+        age_limit = parse_age_limit(video.get('parental', {}).get('rating'))
+
+        subtitles = {}
+        captions = stream.get('captions')
+        if isinstance(captions, list):
+            for caption in captions:
+                subtitle_url = caption.get('fileUrl')
+                if (not subtitle_url or not isinstance(subtitle_url, compat_str) or
+                        not subtitle_url.startswith('http')):
+                    continue
+                lang = caption.get('fileLang', 'en')
+                subtitles.setdefault(lang, []).append({'url': subtitle_url})
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'description': description,
+            'duration': duration,
+            'series': series,
+            'season_number': season_number,
+            'episode_number': episode_number,
+            'tags': tags,
+            'age_limit': age_limit,
+            'formats': formats,
+            'subtitles': subtitles,
+        }

youtube_dl/extractor/dreisat.py

@@ -17,8 +17,12 @@ class DreiSatIE(ZDFIE):
                 'ext': 'mp4',
                 'title': 'Waidmannsheil',
                 'description': 'md5:cce00ca1d70e21425e72c86a98a56817',
-                'uploader': '3sat',
+                'uploader': 'SCHWEIZWEIT',
+                'uploader_id': '100000210',
                 'upload_date': '20140913'
+            },
+            'params': {
+                'skip_download': True,  # m3u8 downloads
             }
         },
         {

youtube_dl/extractor/drtuber.py

@@ -3,7 +3,10 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import str_to_int
+from ..utils import (
+    NO_DEFAULT,
+    str_to_int,
+)
 
 
 class DrTuberIE(InfoExtractor):
@@ -17,7 +20,6 @@ class DrTuberIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'hot perky blonde naked golf',
             'like_count': int,
-            'dislike_count': int,
             'comment_count': int,
             'categories': ['Babe', 'Blonde', 'Erotic', 'Outdoor', 'Softcore', 'Solo'],
             'thumbnail': 're:https?://.*\.jpg$',
@@ -36,25 +38,29 @@ class DrTuberIE(InfoExtractor):
             r'<source src="([^"]+)"', webpage, 'video URL')
 
         title = self._html_search_regex(
-            [r'<p[^>]+class="title_substrate">([^<]+)</p>', r'<title>([^<]+) - \d+'],
+            (r'class="title_watch"[^>]*><p>([^<]+)<',
+             r'<p[^>]+class="title_substrate">([^<]+)</p>',
+             r'<title>([^<]+) - \d+'),
             webpage, 'title')
 
         thumbnail = self._html_search_regex(
             r'poster="([^"]+)"',
             webpage, 'thumbnail', fatal=False)
 
-        def extract_count(id_, name):
+        def extract_count(id_, name, default=NO_DEFAULT):
             return str_to_int(self._html_search_regex(
                 r'<span[^>]+(?:class|id)="%s"[^>]*>([\d,\.]+)</span>' % id_,
-                webpage, '%s count' % name, fatal=False))
+                webpage, '%s count' % name, default=default, fatal=False))
 
         like_count = extract_count('rate_likes', 'like')
-        dislike_count = extract_count('rate_dislikes', 'dislike')
+        dislike_count = extract_count('rate_dislikes', 'dislike', default=None)
         comment_count = extract_count('comments_count', 'comment')
 
         cats_str = self._search_regex(
-            r'<div[^>]+class="categories_list">(.+?)</div>', webpage, 'categories', fatal=False)
-        categories = [] if not cats_str else re.findall(r'<a title="([^"]+)"', cats_str)
+            r'<div[^>]+class="categories_list">(.+?)</div>',
+            webpage, 'categories', fatal=False)
+        categories = [] if not cats_str else re.findall(
+            r'<a title="([^"]+)"', cats_str)
 
         return {
             'id': video_id,

youtube_dl/extractor/ellentv.py

@@ -6,12 +6,13 @@ import json
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
+    NO_DEFAULT,
 )
 
 
 class EllenTVIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?(?:ellentv|ellentube)\.com/videos/(?P<id>[a-z0-9_-]+)'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.ellentv.com/videos/0-ipq1gsai/',
         'md5': '4294cf98bc165f218aaa0b89e0fd8042',
         'info_dict': {
@@ -22,24 +23,47 @@ class EllenTVIE(InfoExtractor):
             'timestamp': 1428035648,
             'upload_date': '20150403',
             'uploader_id': 'batchUser',
-        }
-    }
+        },
+    }, {
+        # not available via http://widgets.ellentube.com/
+        'url': 'http://www.ellentv.com/videos/1-szkgu2m2/',
+        'info_dict': {
+            'id': '1_szkgu2m2',
+            'ext': 'flv',
+            'title': "Ellen's Amazingly Talented Audience",
+            'description': 'md5:86ff1e376ff0d717d7171590e273f0a5',
+            'timestamp': 1255140900,
+            'upload_date': '20091010',
+            'uploader_id': 'ellenkaltura@gmail.com',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        webpage = self._download_webpage(
-            'http://widgets.ellentube.com/videos/%s' % video_id,
-            video_id)
+        URLS = ('http://widgets.ellentube.com/videos/%s' % video_id, url)
 
-        partner_id = self._search_regex(
-            r"var\s+partnerId\s*=\s*'([^']+)", webpage, 'partner id')
+        for num, url_ in enumerate(URLS, 1):
+            webpage = self._download_webpage(
+                url_, video_id, fatal=num == len(URLS))
 
-        kaltura_id = self._search_regex(
-            [r'id="kaltura_player_([^"]+)"',
-             r"_wb_entry_id\s*:\s*'([^']+)",
-             r'data-kaltura-entry-id="([^"]+)'],
-            webpage, 'kaltura id')
+            default = NO_DEFAULT if num == len(URLS) else None
+
+            partner_id = self._search_regex(
+                r"var\s+partnerId\s*=\s*'([^']+)", webpage, 'partner id',
+                default=default)
+
+            kaltura_id = self._search_regex(
+                [r'id="kaltura_player_([^"]+)"',
+                 r"_wb_entry_id\s*:\s*'([^']+)",
+                 r'data-kaltura-entry-id="([^"]+)'],
+                webpage, 'kaltura id', default=default)
+
+            if partner_id and kaltura_id:
+                break
 
         return self.url_result('kaltura:%s:%s' % (partner_id, kaltura_id), 'Kaltura')
 

youtube_dl/extractor/engadget.py

@@ -4,9 +4,10 @@ from .common import InfoExtractor
 
 
 class EngadgetIE(InfoExtractor):
-    _VALID_URL = r'https?://www.engadget.com/video/(?P<id>\d+)'
+    _VALID_URL = r'https?://www.engadget.com/video/(?P<id>[^/?#]+)'
 
-    _TEST = {
+    _TESTS = [{
+        # video with 5min ID
         'url': 'http://www.engadget.com/video/518153925/',
         'md5': 'c6820d4828a5064447a4d9fc73f312c9',
         'info_dict': {
@@ -15,8 +16,12 @@ class EngadgetIE(InfoExtractor):
             'title': 'Samsung Galaxy Tab Pro 8.4 Review',
         },
         'add_ie': ['FiveMin'],
-    }
+    }, {
+        # video with vidible ID
+        'url': 'https://www.engadget.com/video/57a28462134aa15a39f0421a/',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        return self.url_result('5min:%s' % video_id)
+        return self.url_result('aol-video:%s' % video_id)

youtube_dl/extractor/eporner.py

@@ -4,19 +4,23 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_str
 from ..utils import (
+    encode_base_n,
+    ExtractorError,
+    int_or_none,
     parse_duration,
     str_to_int,
 )
 
 
 class EpornerIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?eporner\.com/hd-porn/(?P<id>\w+)/(?P<display_id>[\w-]+)'
+    _VALID_URL = r'https?://(?:www\.)?eporner\.com/hd-porn/(?P<id>\w+)(?:/(?P<display_id>[\w-]+))?'
     _TESTS = [{
         'url': 'http://www.eporner.com/hd-porn/95008/Infamous-Tiffany-Teen-Strip-Tease-Video/',
         'md5': '39d486f046212d8e1b911c52ab4691f8',
         'info_dict': {
-            'id': '95008',
+            'id': 'qlDUmNsj6VS',
             'display_id': 'Infamous-Tiffany-Teen-Strip-Tease-Video',
             'ext': 'mp4',
             'title': 'Infamous Tiffany Teen Strip Tease Video',
@@ -28,34 +32,72 @@ class EpornerIE(InfoExtractor):
         # New (May 2016) URL layout
         'url': 'http://www.eporner.com/hd-porn/3YRUtzMcWn0/Star-Wars-XXX-Parody/',
         'only_matching': True,
+    }, {
+        'url': 'http://www.eporner.com/hd-porn/3YRUtzMcWn0',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
-        display_id = mobj.group('display_id')
+        display_id = mobj.group('display_id') or video_id
 
-        webpage = self._download_webpage(url, display_id)
-        title = self._html_search_regex(
-            r'<title>(.*?) - EPORNER', webpage, 'title')
+        webpage, urlh = self._download_webpage_handle(url, display_id)
 
-        redirect_url = 'http://www.eporner.com/config5/%s' % video_id
-        player_code = self._download_webpage(
-            redirect_url, display_id, note='Downloading player config')
+        video_id = self._match_id(compat_str(urlh.geturl()))
 
-        sources = self._search_regex(
-            r'(?s)sources\s*:\s*\[\s*({.+?})\s*\]', player_code, 'sources')
+        hash = self._search_regex(
+            r'hash\s*:\s*["\']([\da-f]{32})', webpage, 'hash')
+
+        title = self._og_search_title(webpage, default=None) or self._html_search_regex(
+            r'<title>(.+?) - EPORNER', webpage, 'title')
+
+        # Reverse engineered from vjs.js
+        def calc_hash(s):
+            return ''.join((encode_base_n(int(s[lb:lb + 8], 16), 36) for lb in range(0, 32, 8)))
+
+        video = self._download_json(
+            'http://www.eporner.com/xhr/video/%s' % video_id,
+            display_id, note='Downloading video JSON',
+            query={
+                'hash': calc_hash(hash),
+                'device': 'generic',
+                'domain': 'www.eporner.com',
+                'fallback': 'false',
+            })
+
+        if video.get('available') is False:
+            raise ExtractorError(
+                '%s said: %s' % (self.IE_NAME, video['message']), expected=True)
+
+        sources = video['sources']
 
         formats = []
-        for video_url, format_id in re.findall(r'file\s*:\s*"([^"]+)",\s*label\s*:\s*"([^"]+)"', sources):
-            fmt = {
-                'url': video_url,
-                'format_id': format_id,
-            }
-            m = re.search(r'^(\d+)', format_id)
-            if m:
-                fmt['height'] = int(m.group(1))
-            formats.append(fmt)
+        for kind, formats_dict in sources.items():
+            if not isinstance(formats_dict, dict):
+                continue
+            for format_id, format_dict in formats_dict.items():
+                if not isinstance(format_dict, dict):
+                    continue
+                src = format_dict.get('src')
+                if not isinstance(src, compat_str) or not src.startswith('http'):
+                    continue
+                if kind == 'hls':
+                    formats.extend(self._extract_m3u8_formats(
+                        src, display_id, 'mp4', entry_protocol='m3u8_native',
+                        m3u8_id=kind, fatal=False))
+                else:
+                    height = int_or_none(self._search_regex(
+                        r'(\d+)[pP]', format_id, 'height', default=None))
+                    fps = int_or_none(self._search_regex(
+                        r'(\d+)fps', format_id, 'fps', default=None))
+
+                    formats.append({
+                        'url': src,
+                        'format_id': format_id,
+                        'height': height,
+                        'fps': fps,
+                    })
         self._sort_formats(formats)
 
         duration = parse_duration(self._html_search_meta('duration', webpage))

youtube_dl/extractor/expotv.py

@@ -1,7 +1,5 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 from ..utils import (
     int_or_none,
@@ -12,23 +10,22 @@ from ..utils import (
 class ExpoTVIE(InfoExtractor):
     _VALID_URL = r'https?://www\.expotv\.com/videos/[^?#]*/(?P<id>[0-9]+)($|[?#])'
     _TEST = {
-        'url': 'http://www.expotv.com/videos/reviews/1/24/LinneCardscom/17561',
-        'md5': '2985e6d7a392b2f7a05e0ca350fe41d0',
+        'url': 'http://www.expotv.com/videos/reviews/3/40/NYX-Butter-lipstick/667916',
+        'md5': 'fe1d728c3a813ff78f595bc8b7a707a8',
         'info_dict': {
-            'id': '17561',
+            'id': '667916',
             'ext': 'mp4',
-            'upload_date': '20060212',
-            'title': 'My Favorite Online Scrapbook Store',
-            'view_count': int,
-            'description': 'You\'ll find most everything you need at this virtual store front.',
-            'uploader': 'Anna T.',
+            'title': 'NYX Butter Lipstick Little Susie',
+            'description': 'Goes on like butter, but looks better!',
             'thumbnail': 're:^https?://.*\.jpg$',
+            'uploader': 'Stephanie S.',
+            'upload_date': '20150520',
+            'view_count': int,
         }
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
         player_key = self._search_regex(
@@ -66,7 +63,7 @@ class ExpoTVIE(InfoExtractor):
             fatal=False)
         upload_date = unified_strdate(self._search_regex(
             r'<h5>Reviewed on ([0-9/.]+)</h5>', webpage, 'upload date',
-            fatal=False))
+            fatal=False), day_first=False)
 
         return {
             'id': video_id,

youtube_dl/extractor/extractors.py

@@ -29,6 +29,7 @@ from .aftonbladet import AftonbladetIE
 from .airmozilla import AirMozillaIE
 from .aljazeera import AlJazeeraIE
 from .alphaporno import AlphaPornoIE
+from .amcnetworks import AMCNetworksIE
 from .animeondemand import AnimeOnDemandIE
 from .anitube import AnitubeIE
 from .anysex import AnySexIE
@@ -44,6 +45,7 @@ from .appletrailers import (
     AppleTrailersSectionIE,
 )
 from .archiveorg import ArchiveOrgIE
+from .arkena import ArkenaIE
 from .ard import (
     ARDIE,
     ARDMediathekIE,
@@ -156,7 +158,12 @@ from .cnn import (
 )
 from .coub import CoubIE
 from .collegerama import CollegeRamaIE
-from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE
+from .comedycentral import (
+    ComedyCentralIE,
+    ComedyCentralShortnameIE,
+    ComedyCentralTVIE,
+    ToshIE,
+)
 from .comcarcoff import ComCarCoffIE
 from .commonmistakes import CommonMistakesIE, UnicodeBOMIE
 from .commonprotocols import RtmpIE
@@ -215,6 +222,7 @@ from .dvtv import DVTVIE
 from .dumpert import DumpertIE
 from .defense import DefenseGouvFrIE
 from .discovery import DiscoveryIE
+from .discoverygo import DiscoveryGoIE
 from .dispeak import DigitallySpeakingIE
 from .dropbox import DropboxIE
 from .dw import (
@@ -265,10 +273,7 @@ from .fox import FOXIE
 from .foxgay import FoxgayIE
 from .foxnews import FoxNewsIE
 from .foxsports import FoxSportsIE
-from .franceculture import (
-    FranceCultureIE,
-    FranceCultureEmissionIE,
-)
+from .franceculture import FranceCultureIE
 from .franceinter import FranceInterIE
 from .francetv import (
     PluzzIE,
@@ -283,8 +288,8 @@ from .freevideo import FreeVideoIE
 from .funimation import FunimationIE
 from .funnyordie import FunnyOrDieIE
 from .fusion import FusionIE
+from .fxnetworks import FXNetworksIE
 from .gameinformer import GameInformerIE
-from .gamekings import GamekingsIE
 from .gameone import (
     GameOneIE,
     GameOnePlaylistIE,
@@ -305,7 +310,6 @@ from .globo import (
 )
 from .godtube import GodTubeIE
 from .godtv import GodTVIE
-from .goldenmoustache import GoldenMoustacheIE
 from .golem import GolemIE
 from .googledrive import GoogleDriveIE
 from .googleplus import GooglePlusIE
@@ -320,6 +324,7 @@ from .heise import HeiseIE
 from .hellporno import HellPornoIE
 from .helsinki import HelsinkiIE
 from .hentaistigma import HentaiStigmaIE
+from .hgtv import HGTVIE
 from .historicfilms import HistoricFilmsIE
 from .hitbox import HitboxIE, HitboxLiveIE
 from .hornbunny import HornBunnyIE
@@ -393,6 +398,10 @@ from .kuwo import (
 )
 from .la7 import LA7IE
 from .laola1tv import Laola1TvIE
+from .lcp import (
+    LcpPlayIE,
+    LcpIE,
+)
 from .learnr import LearnrIE
 from .lecture2go import Lecture2GoIE
 from .lemonde import LemondeIE
@@ -471,7 +480,6 @@ from .msn import MSNIE
 from .mtv import (
     MTVIE,
     MTVServicesEmbeddedIE,
-    MTVIggyIE,
     MTVDEIE,
 )
 from .muenchentv import MuenchenTVIE
@@ -483,8 +491,9 @@ from .myvi import MyviIE
 from .myvideo import MyVideoIE
 from .myvidster import MyVidsterIE
 from .nationalgeographic import (
+    NationalGeographicVideoIE,
     NationalGeographicIE,
-    NationalGeographicChannelIE,
+    NationalGeographicEpisodeGuideIE,
 )
 from .naver import NaverIE
 from .nba import NBAIE
@@ -521,7 +530,6 @@ from .nextmedia import (
     NextMediaActionNewsIE,
     AppleDailyIE,
 )
-from .nextmovie import NextMovieIE
 from .nfb import NFBIE
 from .nfl import NFLIE
 from .nhl import (
@@ -537,6 +545,8 @@ from .nick import (
 from .niconico import NiconicoIE, NiconicoPlaylistIE
 from .ninecninemedia import NineCNineMediaIE
 from .ninegag import NineGagIE
+from .ninenow import NineNowIE
+from .nintendo import NintendoIE
 from .noco import NocoIE
 from .normalboots import NormalbootsIE
 from .nosvideo import NosVideoIE
@@ -581,6 +591,7 @@ from .nytimes import (
     NYTimesArticleIE,
 )
 from .nuvid import NuvidIE
+from .odatv import OdaTVIE
 from .odnoklassniki import OdnoklassnikiIE
 from .oktoberfesttv import OktoberfestTVIE
 from .onet import (
@@ -625,6 +636,7 @@ from .pluralsight import (
     PluralsightCourseIE,
 )
 from .podomatic import PodomaticIE
+from .pokemon import PokemonIE
 from .polskieradio import PolskieRadioIE
 from .porn91 import Porn91IE
 from .pornhd import PornHdIE
@@ -680,16 +692,19 @@ from .rice import RICEIE
 from .ringtv import RingTVIE
 from .ro220 import Ro220IE
 from .rockstargames import RockstarGamesIE
+from .roosterteeth import RoosterTeethIE
 from .rottentomatoes import RottenTomatoesIE
 from .roxwel import RoxwelIE
+from .rozhlas import RozhlasIE
 from .rtbf import RTBFIE
 from .rte import RteIE, RteRadioIE
 from .rtlnl import RtlNlIE
 from .rtl2 import RTL2IE
 from .rtp import RTPIE
 from .rts import RTSIE
-from .rtve import RTVEALaCartaIE, RTVELiveIE, RTVEInfantilIE
+from .rtve import RTVEALaCartaIE, RTVELiveIE, RTVEInfantilIE, RTVELiveIE, RTVETelevisionIE
 from .rtvnh import RTVNHIE
+from .rudo import RudoIE
 from .ruhd import RUHDIE
 from .ruleporn import RulePornIE
 from .rutube import (
@@ -740,6 +755,7 @@ from .smotri import (
 )
 from .snotr import SnotrIE
 from .sohu import SohuIE
+from .sonyliv import SonyLIVIE
 from .soundcloud import (
     SoundcloudIE,
     SoundcloudSetIE,
@@ -779,6 +795,7 @@ from .srmediathek import SRMediathekIE
 from .ssa import SSAIE
 from .stanfordoc import StanfordOpenClassroomIE
 from .steam import SteamIE
+from .streamable import StreamableIE
 from .streamcloud import StreamcloudIE
 from .streamcz import StreamCZIE
 from .streetvoice import StreetVoiceIE
@@ -794,7 +811,6 @@ from .tagesschau import (
     TagesschauPlayerIE,
     TagesschauIE,
 )
-from .tapely import TapelyIE
 from .tass import TassIE
 from .tdslifeway import TDSLifewayIE
 from .teachertube import (
@@ -878,10 +894,14 @@ from .tvc import (
 from .tvigle import TvigleIE
 from .tvland import TVLandIE
 from .tvp import (
+    TVPEmbedIE,
     TVPIE,
     TVPSeriesIE,
 )
-from .tvplay import TVPlayIE
+from .tvplay import (
+    TVPlayIE,
+    ViafreeIE,
+)
 from .tweakers import TweakersIE
 from .twentyfourvideo import TwentyFourVideoIE
 from .twentymin import TwentyMinutenIE
@@ -910,6 +930,11 @@ from .udemy import (
 from .udn import UDNEmbedIE
 from .digiteka import DigitekaIE
 from .unistra import UnistraIE
+from .uol import UOLIE
+from .uplynk import (
+    UplynkIE,
+    UplynkPreplayIE,
+)
 from .urort import UrortIE
 from .urplay import URPlayIE
 from .usatoday import USATodayIE
@@ -938,6 +963,7 @@ from .vice import (
     ViceIE,
     ViceShowIE,
 )
+from .viceland import VicelandIE
 from .vidbit import VidbitIE
 from .viddler import ViddlerIE
 from .videodetective import VideoDetectiveIE
@@ -987,9 +1013,11 @@ from .viki import (
 from .vk import (
     VKIE,
     VKUserVideosIE,
+    VKWallPostIE,
 )
 from .vlive import VLiveIE
 from .vodlocker import VodlockerIE
+from .vodplatform import VODPlatformIE
 from .voicerepublic import VoiceRepublicIE
 from .voxmedia import VoxMediaIE
 from .vporn import VpornIE
@@ -1086,4 +1114,3 @@ from .zingmp3 import (
     ZingMp3SongIE,
     ZingMp3AlbumIE,
 )
-from .zippcast import ZippCastIE

youtube_dl/extractor/extremetube.py

@@ -1,22 +1,17 @@
 from __future__ import unicode_literals
 
-import re
-
-from .common import InfoExtractor
-from ..utils import (
-    int_or_none,
-    sanitized_Request,
-    str_to_int,
-)
+from ..utils import str_to_int
+from .keezmovies import KeezMoviesIE
 
 
-class ExtremeTubeIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?extremetube\.com/(?:[^/]+/)?video/(?P<id>[^/#?&]+)'
+class ExtremeTubeIE(KeezMoviesIE):
+    _VALID_URL = r'https?://(?:www\.)?extremetube\.com/(?:[^/]+/)?video/(?:(?P<display_id>[^/]+)-)(?P<id>\d+)'
     _TESTS = [{
         'url': 'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431',
-        'md5': '344d0c6d50e2f16b06e49ca011d8ac69',
+        'md5': '1fb9228f5e3332ec8c057d6ac36f33e0',
         'info_dict': {
-            'id': 'music-video-14-british-euro-brit-european-cumshots-swallow-652431',
+            'id': '652431',
+            'display_id': 'music-video-14-british-euro-brit-european-cumshots-swallow',
             'ext': 'mp4',
             'title': 'Music Video 14 british euro brit european cumshots swallow',
             'uploader': 'unknown',
@@ -35,58 +30,22 @@ class ExtremeTubeIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        webpage, info = self._extract_info(url)
 
-        req = sanitized_Request(url)
-        req.add_header('Cookie', 'age_verified=1')
-        webpage = self._download_webpage(req, video_id)
+        if not info['title']:
+            info['title'] = self._search_regex(
+                r'<h1[^>]+title="([^"]+)"[^>]*>', webpage, 'title')
 
-        video_title = self._html_search_regex(
-            r'<h1 [^>]*?title="([^"]+)"[^>]*>', webpage, 'title')
         uploader = self._html_search_regex(
             r'Uploaded by:\s*</strong>\s*(.+?)\s*</div>',
             webpage, 'uploader', fatal=False)
-        view_count = str_to_int(self._html_search_regex(
+        view_count = str_to_int(self._search_regex(
             r'Views:\s*</strong>\s*<span>([\d,\.]+)</span>',
             webpage, 'view count', fatal=False))
 
-        flash_vars = self._parse_json(
-            self._search_regex(
-                r'var\s+flashvars\s*=\s*({.+?});', webpage, 'flash vars'),
-            video_id)
-
-        formats = []
-        for quality_key, video_url in flash_vars.items():
-            height = int_or_none(self._search_regex(
-                r'quality_(\d+)[pP]$', quality_key, 'height', default=None))
-            if not height:
-                continue
-            f = {
-                'url': video_url,
-            }
-            mobj = re.search(
-                r'/(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+', video_url)
-            if mobj:
-                height = int(mobj.group('height'))
-                bitrate = int(mobj.group('bitrate'))
-                f.update({
-                    'format_id': '%dp-%dk' % (height, bitrate),
-                    'height': height,
-                    'tbr': bitrate,
-                })
-            else:
-                f.update({
-                    'format_id': '%dp' % height,
-                    'height': height,
-                })
-            formats.append(f)
-        self._sort_formats(formats)
-
-        return {
-            'id': video_id,
-            'title': video_title,
-            'formats': formats,
+        info.update({
             'uploader': uploader,
             'view_count': view_count,
-            'age_limit': 18,
-        }
+        })
+
+        return info

youtube_dl/extractor/facebook.py

@@ -27,7 +27,7 @@ class FacebookIE(InfoExtractor):
     _VALID_URL = r'''(?x)
                 (?:
                     https?://
-                        (?:\w+\.)?facebook\.com/
+                        (?:[\w-]+\.)?facebook\.com/
                         (?:[^#]*?\#!/)?
                         (?:
                             (?:
@@ -127,6 +127,9 @@ class FacebookIE(InfoExtractor):
     }, {
         'url': 'https://www.facebook.com/groups/164828000315060/permalink/764967300301124/',
         'only_matching': True,
+    }, {
+        'url': 'https://zh-hk.facebook.com/peoplespower/videos/1135894589806027/',
+        'only_matching': True,
     }]
 
     @staticmethod
@@ -231,11 +234,13 @@ class FacebookIE(InfoExtractor):
                     continue
                 if isinstance(f, dict):
                     f = [f]
-                if isinstance(f, list):
+                if not isinstance(f, list):
                     continue
                 if f[0].get('video_id') == video_id:
                     video_data = video_data_candidate
                     break
+            if video_data:
+                break
 
         def video_data_list2dict(video_data):
             ret = {}

youtube_dl/extractor/fivemin.py

@@ -1,24 +1,11 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
-from ..compat import (
-    compat_parse_qs,
-    compat_urllib_parse_urlencode,
-    compat_urllib_parse_urlparse,
-    compat_urlparse,
-)
-from ..utils import (
-    ExtractorError,
-    parse_duration,
-    replace_extension,
-)
 
 
 class FiveMinIE(InfoExtractor):
     IE_NAME = '5min'
-    _VALID_URL = r'(?:5min:(?P<id>\d+)(?::(?P<sid>\d+))?|https?://[^/]*?5min\.com/Scripts/PlayerSeed\.js\?(?P<query>.*))'
+    _VALID_URL = r'(?:5min:|https?://(?:[^/]*?5min\.com/|delivery\.vidible\.tv/aol)(?:(?:Scripts/PlayerSeed\.js|playerseed/?)?\?.*?playList=)?)(?P<id>\d+)'
 
     _TESTS = [
         {
@@ -29,8 +16,16 @@ class FiveMinIE(InfoExtractor):
                 'id': '518013791',
                 'ext': 'mp4',
                 'title': 'iPad Mini with Retina Display Review',
+                'description': 'iPad mini with Retina Display review',
                 'duration': 177,
+                'uploader': 'engadget',
+                'upload_date': '20131115',
+                'timestamp': 1384515288,
             },
+            'params': {
+                # m3u8 download
+                'skip_download': True,
+            }
         },
         {
             # From http://on.aol.com/video/how-to-make-a-next-level-fruit-salad-518086247
@@ -44,108 +39,16 @@ class FiveMinIE(InfoExtractor):
             },
             'skip': 'no longer available',
         },
+        {
+            'url': 'http://embed.5min.com/518726732/',
+            'only_matching': True,
+        },
+        {
+            'url': 'http://delivery.vidible.tv/aol?playList=518013791',
+            'only_matching': True,
+        }
     ]
-    _ERRORS = {
-        'ErrorVideoNotExist': 'We\'re sorry, but the video you are trying to watch does not exist.',
-        'ErrorVideoNoLongerAvailable': 'We\'re sorry, but the video you are trying to watch is no longer available.',
-        'ErrorVideoRejected': 'We\'re sorry, but the video you are trying to watch has been removed.',
-        'ErrorVideoUserNotGeo': 'We\'re sorry, but the video you are trying to watch cannot be viewed from your current location.',
-        'ErrorVideoLibraryRestriction': 'We\'re sorry, but the video you are trying to watch is currently unavailable for viewing at this domain.',
-        'ErrorExposurePermission': 'We\'re sorry, but the video you are trying to watch is currently unavailable for viewing at this domain.',
-    }
-    _QUALITIES = {
-        1: {
-            'width': 640,
-            'height': 360,
-        },
-        2: {
-            'width': 854,
-            'height': 480,
-        },
-        4: {
-            'width': 1280,
-            'height': 720,
-        },
-        8: {
-            'width': 1920,
-            'height': 1080,
-        },
-        16: {
-            'width': 640,
-            'height': 360,
-        },
-        32: {
-            'width': 854,
-            'height': 480,
-        },
-        64: {
-            'width': 1280,
-            'height': 720,
-        },
-        128: {
-            'width': 640,
-            'height': 360,
-        },
-    }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        sid = mobj.group('sid')
-
-        if mobj.group('query'):
-            qs = compat_parse_qs(mobj.group('query'))
-            if not qs.get('playList'):
-                raise ExtractorError('Invalid URL', expected=True)
-            video_id = qs['playList'][0]
-            if qs.get('sid'):
-                sid = qs['sid'][0]
-
-        embed_url = 'https://embed.5min.com/playerseed/?playList=%s' % video_id
-        if not sid:
-            embed_page = self._download_webpage(embed_url, video_id,
-                                                'Downloading embed page')
-            sid = self._search_regex(r'sid=(\d+)', embed_page, 'sid')
-
-        response = self._download_json(
-            'https://syn.5min.com/handlers/SenseHandler.ashx?' +
-            compat_urllib_parse_urlencode({
-                'func': 'GetResults',
-                'playlist': video_id,
-                'sid': sid,
-                'isPlayerSeed': 'true',
-                'url': embed_url,
-            }),
-            video_id)
-        if not response['success']:
-            raise ExtractorError(
-                '%s said: %s' % (
-                    self.IE_NAME,
-                    self._ERRORS.get(response['errorMessage'], response['errorMessage'])),
-                expected=True)
-        info = response['binding'][0]
-
-        formats = []
-        parsed_video_url = compat_urllib_parse_urlparse(compat_parse_qs(
-            compat_urllib_parse_urlparse(info['EmbededURL']).query)['videoUrl'][0])
-        for rendition in info['Renditions']:
-            if rendition['RenditionType'] == 'aac' or rendition['RenditionType'] == 'm3u8':
-                continue
-            else:
-                rendition_url = compat_urlparse.urlunparse(parsed_video_url._replace(path=replace_extension(parsed_video_url.path.replace('//', '/%s/' % rendition['ID']), rendition['RenditionType'])))
-                quality = self._QUALITIES.get(rendition['ID'], {})
-                formats.append({
-                    'format_id': '%s-%d' % (rendition['RenditionType'], rendition['ID']),
-                    'url': rendition_url,
-                    'width': quality.get('width'),
-                    'height': quality.get('height'),
-                })
-        self._sort_formats(formats)
-
-        return {
-            'id': video_id,
-            'title': info['Title'],
-            'thumbnail': info.get('ThumbURL'),
-            'duration': parse_duration(info.get('Duration')),
-            'formats': formats,
-        }
+        video_id = self._match_id(url)
+        return self.url_result('aol-video:%s' % video_id)

youtube_dl/extractor/flipagram.py

@@ -48,7 +48,7 @@ class FlipagramIE(InfoExtractor):
         flipagram = video_data['flipagram']
         video = flipagram['video']
 
-        json_ld = self._search_json_ld(webpage, video_id, default=False)
+        json_ld = self._search_json_ld(webpage, video_id, default={})
         title = json_ld.get('title') or flipagram['captionText']
         description = json_ld.get('description') or flipagram.get('captionText')
 

youtube_dl/extractor/formula1.py

@@ -5,8 +5,8 @@ from .common import InfoExtractor
 
 
 class Formula1IE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?formula1\.com/content/fom-website/en/video/\d{4}/\d{1,2}/(?P<id>.+?)\.html'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?formula1\.com/(?:content/fom-website/)?en/video/\d{4}/\d{1,2}/(?P<id>.+?)\.html'
+    _TESTS = [{
         'url': 'http://www.formula1.com/content/fom-website/en/video/2016/5/Race_highlights_-_Spain_2016.html',
         'md5': '8c79e54be72078b26b89e0e111c0502b',
         'info_dict': {
@@ -15,7 +15,10 @@ class Formula1IE(InfoExtractor):
             'title': 'Race highlights - Spain 2016',
         },
         'add_ie': ['Ooyala'],
-    }
+    }, {
+        'url': 'http://www.formula1.com/en/video/2016/5/Race_highlights_-_Spain_2016.html',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         display_id = self._match_id(url)

youtube_dl/extractor/fourtube.py

@@ -43,14 +43,14 @@ class FourTubeIE(InfoExtractor):
             'uploadDate', webpage))
         thumbnail = self._html_search_meta('thumbnailUrl', webpage)
         uploader_id = self._html_search_regex(
-            r'<a class="img-avatar" href="[^"]+/channels/([^/"]+)" title="Go to [^"]+ page">',
+            r'<a class="item-to-subscribe" href="[^"]+/channels/([^/"]+)" title="Go to [^"]+ page">',
             webpage, 'uploader id', fatal=False)
         uploader = self._html_search_regex(
-            r'<a class="img-avatar" href="[^"]+/channels/[^/"]+" title="Go to ([^"]+) page">',
+            r'<a class="item-to-subscribe" href="[^"]+/channels/[^/"]+" title="Go to ([^"]+) page">',
             webpage, 'uploader', fatal=False)
 
         categories_html = self._search_regex(
-            r'(?s)><i class="icon icon-tag"></i>\s*Categories / Tags\s*.*?<ul class="list">(.*?)</ul>',
+            r'(?s)><i class="icon icon-tag"></i>\s*Categories / Tags\s*.*?<ul class="[^"]*?list[^"]*?">(.*?)</ul>',
             webpage, 'categories', fatal=False)
         categories = None
         if categories_html:
@@ -59,10 +59,10 @@ class FourTubeIE(InfoExtractor):
                     r'(?s)<li><a.*?>(.*?)</a>', categories_html)]
 
         view_count = str_to_int(self._search_regex(
-            r'<meta itemprop="interactionCount" content="UserPlays:([0-9,]+)">',
+            r'<meta[^>]+itemprop="interactionCount"[^>]+content="UserPlays:([0-9,]+)">',
             webpage, 'view count', fatal=False))
         like_count = str_to_int(self._search_regex(
-            r'<meta itemprop="interactionCount" content="UserLikes:([0-9,]+)">',
+            r'<meta[^>]+itemprop="interactionCount"[^>]+content="UserLikes:([0-9,]+)">',
             webpage, 'like count', fatal=False))
         duration = parse_duration(self._html_search_meta('duration', webpage))
 

youtube_dl/extractor/fox.py

@@ -2,7 +2,10 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import smuggle_url
+from ..utils import (
+    smuggle_url,
+    update_url_query,
+)
 
 
 class FOXIE(InfoExtractor):
@@ -29,11 +32,12 @@ class FOXIE(InfoExtractor):
 
         release_url = self._parse_json(self._search_regex(
             r'"fox_pdk_player"\s*:\s*({[^}]+?})', webpage, 'fox_pdk_player'),
-            video_id)['release_url'] + '&switch=http'
+            video_id)['release_url']
 
         return {
             '_type': 'url_transparent',
             'ie_key': 'ThePlatform',
-            'url': smuggle_url(release_url, {'force_smil_url': True}),
+            'url': smuggle_url(update_url_query(
+                release_url, {'switch': 'http'}), {'force_smil_url': True}),
             'id': video_id,
         }

youtube_dl/extractor/franceculture.py

@@ -2,104 +2,56 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..compat import (
-    compat_urlparse,
-)
 from ..utils import (
     determine_ext,
-    int_or_none,
-    ExtractorError,
+    unified_strdate,
 )
 
 
 class FranceCultureIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?franceculture\.fr/player/reecouter\?play=(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?franceculture\.fr/emissions/(?:[^/]+/)*(?P<id>[^/?#&]+)'
     _TEST = {
-        'url': 'http://www.franceculture.fr/player/reecouter?play=4795174',
+        'url': 'http://www.franceculture.fr/emissions/carnet-nomade/rendez-vous-au-pays-des-geeks',
         'info_dict': {
-            'id': '4795174',
+            'id': 'rendez-vous-au-pays-des-geeks',
+            'display_id': 'rendez-vous-au-pays-des-geeks',
             'ext': 'mp3',
             'title': 'Rendez-vous au pays des geeks',
-            'alt_title': 'Carnet nomade | 13-14',
-            'vcodec': 'none',
+            'thumbnail': 're:^https?://.*\\.jpg$',
             'upload_date': '20140301',
-            'thumbnail': r're:^http://static\.franceculture\.fr/.*/images/player/Carnet-nomade\.jpg$',
-            'description': 'startswith:Avec :Jean-Baptiste Péretié pour son documentaire sur Arte "La revanche',
-            'timestamp': 1393700400,
+            'vcodec': 'none',
         }
     }
 
-    def _extract_from_player(self, url, video_id):
-        webpage = self._download_webpage(url, video_id)
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
 
-        video_path = self._search_regex(
-            r'<a id="player".*?href="([^"]+)"', webpage, 'video path')
-        video_url = compat_urlparse.urljoin(url, video_path)
-        timestamp = int_or_none(self._search_regex(
-            r'<a id="player".*?data-date="([0-9]+)"',
+        webpage = self._download_webpage(url, display_id)
+
+        video_url = self._search_regex(
+            r'(?s)<div[^>]+class="[^"]*?title-zone-diffusion[^"]*?"[^>]*>.*?<a[^>]+href="([^"]+)"',
+            webpage, 'video path')
+
+        title = self._og_search_title(webpage)
+
+        upload_date = unified_strdate(self._search_regex(
+            '(?s)<div[^>]+class="date"[^>]*>.*?<span[^>]+class="inner"[^>]*>([^<]+)<',
             webpage, 'upload date', fatal=False))
         thumbnail = self._search_regex(
-            r'<a id="player".*?>\s+<img src="([^"]+)"',
+            r'(?s)<figure[^>]+itemtype="https://schema.org/ImageObject"[^>]*>.*?<img[^>]+data-pagespeed-(?:lazy|high-res)-src="([^"]+)"',
             webpage, 'thumbnail', fatal=False)
-
-        display_id = self._search_regex(
-            r'<span class="path-diffusion">emission-(.*?)</span>', webpage, 'display_id')
-
-        title = self._html_search_regex(
-            r'<span class="title-diffusion">(.*?)</span>', webpage, 'title')
-        alt_title = self._html_search_regex(
-            r'<span class="title">(.*?)</span>',
-            webpage, 'alt_title', fatal=False)
-        description = self._html_search_regex(
-            r'<span class="description">(.*?)</span>',
-            webpage, 'description', fatal=False)
-
         uploader = self._html_search_regex(
             r'(?s)<div id="emission".*?<span class="author">(.*?)</span>',
             webpage, 'uploader', default=None)
         vcodec = 'none' if determine_ext(video_url.lower()) == 'mp3' else None
 
         return {
-            'id': video_id,
+            'id': display_id,
+            'display_id': display_id,
             'url': video_url,
+            'title': title,
+            'thumbnail': thumbnail,
             'vcodec': vcodec,
             'uploader': uploader,
-            'timestamp': timestamp,
-            'title': title,
-            'alt_title': alt_title,
-            'thumbnail': thumbnail,
-            'description': description,
-            'display_id': display_id,
+            'upload_date': upload_date,
         }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        return self._extract_from_player(url, video_id)
-
-
-class FranceCultureEmissionIE(FranceCultureIE):
-    _VALID_URL = r'https?://(?:www\.)?franceculture\.fr/emission-(?P<id>[^?#]+)'
-    _TEST = {
-        'url': 'http://www.franceculture.fr/emission-les-carnets-de-la-creation-jean-gabriel-periot-cineaste-2015-10-13',
-        'info_dict': {
-            'title': 'Jean-Gabriel Périot, cinéaste',
-            'alt_title': 'Les Carnets de la création',
-            'id': '5093239',
-            'display_id': 'les-carnets-de-la-creation-jean-gabriel-periot-cineaste-2015-10-13',
-            'ext': 'mp3',
-            'timestamp': 1444762500,
-            'upload_date': '20151013',
-            'description': 'startswith:Aujourd\'hui dans "Les carnets de la création", le cinéaste',
-        },
-    }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
-        video_path = self._html_search_regex(
-            r'<a class="rf-player-open".*?href="([^"]+)"', webpage, 'video path', 'no_path_player')
-        if video_path == 'no_path_player':
-            raise ExtractorError('no player : no sound in this page.', expected=True)
-        new_id = self._search_regex('play=(?P<id>[0-9]+)', video_path, 'new_id', group='id')
-        video_url = compat_urlparse.urljoin(url, video_path)
-        return self._extract_from_player(video_url, new_id)

youtube_dl/extractor/francetv.py

@@ -131,7 +131,7 @@ class PluzzIE(FranceTVBaseInfoExtractor):
 
 class FranceTvInfoIE(FranceTVBaseInfoExtractor):
     IE_NAME = 'francetvinfo.fr'
-    _VALID_URL = r'https?://(?:www|mobile|france3-regions)\.francetvinfo\.fr/.*/(?P<title>.+)\.html'
+    _VALID_URL = r'https?://(?:www|mobile|france3-regions)\.francetvinfo\.fr/(?:[^/]+/)*(?P<title>[^/?#&.]+)'
 
     _TESTS = [{
         'url': 'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html',
@@ -206,6 +206,9 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor):
             'uploader_id': 'x2q2ez',
         },
         'add_ie': ['Dailymotion'],
+    }, {
+        'url': 'http://france3-regions.francetvinfo.fr/limousin/emissions/jt-1213-limousin',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/fxnetworks.py

@@ -0,0 +1,70 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .adobepass import AdobePassIE
+from ..utils import (
+    update_url_query,
+    extract_attributes,
+    parse_age_limit,
+    smuggle_url,
+)
+
+
+class FXNetworksIE(AdobePassIE):
+    _VALID_URL = r'https?://(?:www\.)?(?:fxnetworks|simpsonsworld)\.com/video/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'http://www.fxnetworks.com/video/719841347694',
+        'md5': '1447d4722e42ebca19e5232ab93abb22',
+        'info_dict': {
+            'id': '719841347694',
+            'ext': 'mp4',
+            'title': 'Vanpage',
+            'description': 'F*ck settling down. You\'re the Worst returns for an all new season August 31st on FXX.',
+            'age_limit': 14,
+            'uploader': 'NEWA-FNG-FX',
+            'upload_date': '20160706',
+            'timestamp': 1467844741,
+        },
+        'add_ie': ['ThePlatform'],
+    }, {
+        'url': 'http://www.simpsonsworld.com/video/716094019682',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        if 'The content you are trying to access is not available in your region.' in webpage:
+            self.raise_geo_restricted()
+        video_data = extract_attributes(self._search_regex(
+            r'(<a.+?rel="http://link\.theplatform\.com/s/.+?</a>)', webpage, 'video data'))
+        player_type = self._search_regex(r'playerType\s*=\s*[\'"]([^\'"]+)', webpage, 'player type', default=None)
+        release_url = video_data['rel']
+        title = video_data['data-title']
+        rating = video_data.get('data-rating')
+        query = {
+            'mbr': 'true',
+        }
+        if player_type == 'movies':
+            query.update({
+                'manifest': 'm3u',
+            })
+        else:
+            query.update({
+                'switch': 'http',
+            })
+        if video_data.get('data-req-auth') == '1':
+            resource = self._get_mvpd_resource(
+                video_data['data-channel'], title,
+                video_data.get('data-guid'), rating)
+            query['auth'] = self._extract_mvpd_auth(url, video_id, 'fx', resource)
+
+        return {
+            '_type': 'url_transparent',
+            'id': video_id,
+            'title': title,
+            'url': smuggle_url(update_url_query(release_url, query), {'force_smil_url': True}),
+            'thumbnail': video_data.get('data-large-thumb'),
+            'age_limit': parse_age_limit(rating),
+            'ie_key': 'ThePlatform',
+        }

youtube_dl/extractor/gamekings.py

@@ -1,76 +0,0 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
-from .common import InfoExtractor
-from ..utils import (
-    xpath_text,
-    xpath_with_ns,
-)
-from .youtube import YoutubeIE
-
-
-class GamekingsIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.gamekings\.nl/(?:videos|nieuws)/(?P<id>[^/]+)'
-    _TESTS = [{
-        # YouTube embed video
-        'url': 'http://www.gamekings.nl/videos/phoenix-wright-ace-attorney-dual-destinies-review/',
-        'md5': '5208d3a17adeaef829a7861887cb9029',
-        'info_dict': {
-            'id': 'HkSQKetlGOU',
-            'ext': 'mp4',
-            'title': 'Phoenix Wright: Ace Attorney - Dual Destinies Review',
-            'description': 'md5:db88c0e7f47e9ea50df3271b9dc72e1d',
-            'thumbnail': 're:^https?://.*\.jpg$',
-            'uploader_id': 'UCJugRGo4STYMeFr5RoOShtQ',
-            'uploader': 'Gamekings Vault',
-            'upload_date': '20151123',
-        },
-        'add_ie': ['Youtube'],
-    }, {
-        # vimeo video
-        'url': 'http://www.gamekings.nl/videos/the-legend-of-zelda-majoras-mask/',
-        'md5': '12bf04dfd238e70058046937657ea68d',
-        'info_dict': {
-            'id': 'the-legend-of-zelda-majoras-mask',
-            'ext': 'mp4',
-            'title': 'The Legend of Zelda: Majora’s Mask',
-            'description': 'md5:9917825fe0e9f4057601fe1e38860de3',
-            'thumbnail': 're:^https?://.*\.jpg$',
-        },
-    }, {
-        'url': 'http://www.gamekings.nl/nieuws/gamekings-extra-shelly-en-david-bereiden-zich-voor-op-de-livestream/',
-        'only_matching': True,
-    }]
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, video_id)
-
-        playlist_id = self._search_regex(
-            r'gogoVideo\([^,]+,\s*"([^"]+)', webpage, 'playlist id')
-
-        # Check if a YouTube embed is used
-        if YoutubeIE.suitable(playlist_id):
-            return self.url_result(playlist_id, ie='Youtube')
-
-        playlist = self._download_xml(
-            'http://www.gamekings.tv/wp-content/themes/gk2010/rss_playlist.php?id=%s' % playlist_id,
-            video_id)
-
-        NS_MAP = {
-            'jwplayer': 'http://rss.jwpcdn.com/'
-        }
-
-        item = playlist.find('./channel/item')
-
-        thumbnail = xpath_text(item, xpath_with_ns('./jwplayer:image', NS_MAP), 'thumbnail')
-        video_url = item.find(xpath_with_ns('./jwplayer:source', NS_MAP)).get('file')
-
-        return {
-            'id': video_id,
-            'url': video_url,
-            'title': self._og_search_title(webpage),
-            'description': self._og_search_description(webpage),
-            'thumbnail': thumbnail,
-        }

youtube_dl/extractor/gamespot.py

@@ -28,10 +28,13 @@ class GameSpotIE(OnceIE):
         'url': 'http://www.gamespot.com/videos/the-witcher-3-wild-hunt-xbox-one-now-playing/2300-6424837/',
         'info_dict': {
             'id': 'gs-2300-6424837',
-            'ext': 'flv',
-            'title': 'The Witcher 3: Wild Hunt [Xbox ONE]  - Now Playing',
+            'ext': 'mp4',
+            'title': 'Now Playing - The Witcher 3: Wild Hunt',
             'description': 'Join us as we take a look at the early hours of The Witcher 3: Wild Hunt and more.',
         },
+        'params': {
+            'skip_download': True,  # m3u8 downloads
+        },
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/generic.py

@@ -62,6 +62,7 @@ from .videomore import VideomoreIE
 from .googledrive import GoogleDriveIE
 from .jwplatform import JWPlatformIE
 from .digiteka import DigitekaIE
+from .arkena import ArkenaIE
 from .instagram import InstagramIE
 from .liveleak import LiveLeakIE
 from .threeqsdn import ThreeQSDNIE
@@ -70,6 +71,8 @@ from .vessel import VesselIE
 from .kaltura import KalturaIE
 from .eagleplatform import EaglePlatformIE
 from .facebook import FacebookIE
+from .soundcloud import SoundcloudIE
+from .vbox7 import Vbox7IE
 
 
 class GenericIE(InfoExtractor):
@@ -473,7 +476,7 @@ class GenericIE(InfoExtractor):
             'url': 'http://www.vestifinance.ru/articles/25753',
             'info_dict': {
                 'id': '25753',
-                'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
+                'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
             },
             'playlist': [{
                 'info_dict': {
@@ -640,6 +643,8 @@ class GenericIE(InfoExtractor):
                 'ext': 'mp4',
                 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
                 'description': 'Two valets share their love for movie star Liam Neesons.',
+                'timestamp': 1349922600,
+                'upload_date': '20121011',
             },
         },
         # YouTube embed via <data-embed-url="">
@@ -781,6 +786,15 @@ class GenericIE(InfoExtractor):
                 'upload_date': '20141029',
             }
         },
+        # Soundcloud multiple embeds
+        {
+            'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
+            'info_dict': {
+                'id': '52809',
+                'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance  | TAB + AUDIO',
+            },
+            'playlist_mincount': 7,
+        },
         # Livestream embed
         {
             'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
@@ -856,6 +870,7 @@ class GenericIE(InfoExtractor):
                 'description': 'md5:601cb790edd05908957dae8aaa866465',
                 'upload_date': '20150220',
             },
+            'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
         },
         # jwplayer YouTube
         {
@@ -1249,6 +1264,20 @@ class GenericIE(InfoExtractor):
                 'uploader': 'www.hudl.com',
             },
         },
+        # twitter:player:stream embed
+        {
+            'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
+            'info_dict': {
+                'id': 'master',
+                'ext': 'mp4',
+                'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
+                'uploader': 'www.rtl.be',
+            },
+            'params': {
+                # m3u8 downloads
+                'skip_download': True,
+            },
+        },
         # twitter:player embed
         {
             'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
@@ -1313,6 +1342,50 @@ class GenericIE(InfoExtractor):
             },
             'add_ie': ['Kaltura'],
         },
+        {
+            # Non-standard Vimeo embed
+            'url': 'https://openclassrooms.com/courses/understanding-the-web',
+            'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
+            'info_dict': {
+                'id': '148867247',
+                'ext': 'mp4',
+                'title': 'Understanding the web - Teaser',
+                'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
+                'upload_date': '20151214',
+                'uploader': 'OpenClassrooms',
+                'uploader_id': 'openclassrooms',
+            },
+            'add_ie': ['Vimeo'],
+        },
+        {
+            'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
+            'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
+            'info_dict': {
+                'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
+                'ext': 'mp4',
+                'title': 'Big Buck Bunny',
+                'description': 'Royalty free test video',
+                'timestamp': 1432816365,
+                'upload_date': '20150528',
+                'is_live': False,
+            },
+            'params': {
+                'skip_download': True,
+            },
+            'add_ie': [ArkenaIE.ie_key()],
+        },
+        {
+            'url': 'http://nova.bg/news/view/2016/08/16/156543/%D0%BD%D0%B0-%D0%BA%D0%BE%D1%81%D1%8A%D0%BC-%D0%BE%D1%82-%D0%B2%D0%B7%D1%80%D0%B8%D0%B2-%D0%BE%D1%82%D1%86%D0%B5%D0%BF%D0%B8%D1%85%D0%B0-%D1%86%D1%8F%D0%BB-%D0%BA%D0%B2%D0%B0%D1%80%D1%82%D0%B0%D0%BB-%D0%B7%D0%B0%D1%80%D0%B0%D0%B4%D0%B8-%D0%B8%D0%B7%D1%82%D0%B8%D1%87%D0%B0%D0%BD%D0%B5-%D0%BD%D0%B0-%D0%B3%D0%B0%D0%B7-%D0%B2-%D0%BF%D0%BB%D0%BE%D0%B2%D0%B4%D0%B8%D0%B2/',
+            'info_dict': {
+                'id': '1c7141f46c',
+                'ext': 'mp4',
+                'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
+            },
+            'params': {
+                'skip_download': True,
+            },
+            'add_ie': [Vbox7IE.ie_key()],
+        },
         # {
         #     # TODO: find another test
         #     # http://schema.org/VideoObject
@@ -1949,12 +2022,9 @@ class GenericIE(InfoExtractor):
             return self.url_result(myvi_url)
 
         # Look for embedded soundcloud player
-        mobj = re.search(
-            r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
-            webpage)
-        if mobj is not None:
-            url = unescapeHTML(mobj.group('url'))
-            return self.url_result(url)
+        soundcloud_urls = SoundcloudIE._extract_urls(webpage)
+        if soundcloud_urls:
+            return _playlist_from_matches(soundcloud_urls, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
 
         # Look for embedded mtvservices player
         mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
@@ -2117,6 +2187,11 @@ class GenericIE(InfoExtractor):
         if digiteka_url:
             return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
 
+        # Look for Arkena embeds
+        arkena_url = ArkenaIE._extract_url(webpage)
+        if arkena_url:
+            return self.url_result(arkena_url, ArkenaIE.ie_key())
+
         # Look for Limelight embeds
         mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
         if mobj:
@@ -2145,6 +2220,14 @@ class GenericIE(InfoExtractor):
             return self.url_result(
                 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
 
+        # Look for VODPlatform embeds
+        mobj = re.search(
+            r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vod-platform\.net/embed/[^/?#]+)',
+            webpage)
+        if mobj is not None:
+            return self.url_result(
+                self._proto_relative_url(unescapeHTML(mobj.group(1))), 'VODPlatform')
+
         # Look for Instagram embeds
         instagram_embed_url = InstagramIE._extract_embed_url(webpage)
         if instagram_embed_url is not None:
@@ -2169,15 +2252,15 @@ class GenericIE(InfoExtractor):
                 'uploader': video_uploader,
             }
 
-        # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser
-        embed_url = self._html_search_meta('twitter:player', webpage, default=None)
-        if embed_url:
-            return self.url_result(embed_url)
+        # Look for VBOX7 embeds
+        vbox7_url = Vbox7IE._extract_url(webpage)
+        if vbox7_url:
+            return self.url_result(vbox7_url, Vbox7IE.ie_key())
 
         # Looking for http://schema.org/VideoObject
         json_ld = self._search_json_ld(
-            webpage, video_id, default=None, expected_type='VideoObject')
-        if json_ld and json_ld.get('url'):
+            webpage, video_id, default={}, expected_type='VideoObject')
+        if json_ld.get('url'):
             info_dict.update({
                 'title': video_title or info_dict['title'],
                 'description': video_description,
@@ -2230,6 +2313,9 @@ class GenericIE(InfoExtractor):
                 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
         if not found:
             # Try to find twitter cards info
+            # twitter:player:stream should be checked before twitter:player since
+            # it is expected to contain a raw stream (see
+            # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
             found = filter_video(re.findall(
                 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
         if not found:
@@ -2263,6 +2349,15 @@ class GenericIE(InfoExtractor):
                     '_type': 'url',
                     'url': new_url,
                 }
+
+        if not found:
+            # twitter:player is a https URL to iframe player that may or may not
+            # be supported by youtube-dl thus this is checked the very last (see
+            # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
+            embed_url = self._html_search_meta('twitter:player', webpage, default=None)
+            if embed_url:
+                return self.url_result(embed_url)
+
         if not found:
             raise UnsupportedError(url)
 

youtube_dl/extractor/goldenmoustache.py

@@ -1,48 +0,0 @@
-from __future__ import unicode_literals
-
-from .common import InfoExtractor
-
-
-class GoldenMoustacheIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?goldenmoustache\.com/(?P<display_id>[\w-]+)-(?P<id>\d+)'
-    _TESTS = [{
-        'url': 'http://www.goldenmoustache.com/suricate-le-poker-3700/',
-        'md5': '0f904432fa07da5054d6c8beb5efb51a',
-        'info_dict': {
-            'id': '3700',
-            'ext': 'mp4',
-            'title': 'Suricate - Le Poker',
-            'description': 'md5:3d1f242f44f8c8cb0a106f1fd08e5dc9',
-            'thumbnail': 're:^https?://.*\.jpg$',
-        }
-    }, {
-        'url': 'http://www.goldenmoustache.com/le-lab-tout-effacer-mc-fly-et-carlito-55249/',
-        'md5': '27f0c50fb4dd5f01dc9082fc67cd5700',
-        'info_dict': {
-            'id': '55249',
-            'ext': 'mp4',
-            'title': 'Le LAB - Tout Effacer (Mc Fly et Carlito)',
-            'description': 'md5:9b7fbf11023fb2250bd4b185e3de3b2a',
-            'thumbnail': 're:^https?://.*\.(?:png|jpg)$',
-        }
-    }]
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
-
-        video_url = self._html_search_regex(
-            r'data-src-type="mp4" data-src="([^"]+)"', webpage, 'video URL')
-        title = self._html_search_regex(
-            r'<title>(.*?)(?: - Golden Moustache)?</title>', webpage, 'title')
-        thumbnail = self._og_search_thumbnail(webpage)
-        description = self._og_search_description(webpage)
-
-        return {
-            'id': video_id,
-            'url': video_url,
-            'ext': 'mp4',
-            'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
-        }

youtube_dl/extractor/hgtv.py

@@ -0,0 +1,48 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    js_to_json,
+    smuggle_url,
+)
+
+
+class HGTVIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?hgtv\.ca/[^/]+/video/(?P<id>[^/]+)/video.html'
+    _TEST = {
+        'url': 'http://www.hgtv.ca/homefree/video/overnight-success/video.html?v=738081859718&p=1&s=da#video',
+        'md5': '',
+        'info_dict': {
+            'id': 'aFH__I_5FBOX',
+            'ext': 'mp4',
+            'title': 'Overnight Success',
+            'description': 'After weeks of hard work, high stakes, breakdowns and pep talks, the final 2 contestants compete to win the ultimate dream.',
+            'uploader': 'SHWM-NEW',
+            'timestamp': 1470320034,
+            'upload_date': '20160804',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        embed_vars = self._parse_json(self._search_regex(
+            r'(?s)embed_vars\s*=\s*({.*?});',
+            webpage, 'embed vars'), display_id, js_to_json)
+        return {
+            '_type': 'url_transparent',
+            'url': smuggle_url(
+                'http://link.theplatform.com/s/dtjsEC/%s?mbr=true&manifest=m3u' % embed_vars['pid'], {
+                    'force_smil_url': True
+                }),
+            'series': embed_vars.get('show'),
+            'season_number': int_or_none(embed_vars.get('season')),
+            'episode_number': int_or_none(embed_vars.get('episode')),
+            'ie_key': 'ThePlatform',
+        }

youtube_dl/extractor/imgur.py

@@ -50,12 +50,10 @@ class ImgurIE(InfoExtractor):
         webpage = self._download_webpage(
             compat_urlparse.urljoin(url, video_id), video_id)
 
-        width = int_or_none(self._search_regex(
-            r'<param name="width" value="([0-9]+)"',
-            webpage, 'width', fatal=False))
-        height = int_or_none(self._search_regex(
-            r'<param name="height" value="([0-9]+)"',
-            webpage, 'height', fatal=False))
+        width = int_or_none(self._og_search_property(
+            'video:width', webpage, default=None))
+        height = int_or_none(self._og_search_property(
+            'video:height', webpage, default=None))
 
         video_elements = self._search_regex(
             r'(?s)<div class="video-elements">(.*?)</div>',

youtube_dl/extractor/instagram.py

@@ -36,7 +36,6 @@ class InstagramIE(InfoExtractor):
         'info_dict': {
             'id': 'BA-pQFBG8HZ',
             'ext': 'mp4',
-            'uploader_id': 'britneyspears',
             'title': 'Video by britneyspears',
             'thumbnail': 're:^https?://.*\.jpg',
             'timestamp': 1453760977,

youtube_dl/extractor/jwplatform.py

@@ -4,10 +4,12 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_urlparse
 from ..utils import (
     determine_ext,
     float_or_none,
     int_or_none,
+    mimetype2ext,
 )
 
 
@@ -28,74 +30,86 @@ class JWPlatformBaseIE(InfoExtractor):
         return self._parse_jwplayer_data(
             jwplayer_data, video_id, *args, **kwargs)
 
-    def _parse_jwplayer_data(self, jwplayer_data, video_id, require_title=True, m3u8_id=None, rtmp_params=None):
+    def _parse_jwplayer_data(self, jwplayer_data, video_id=None, require_title=True, m3u8_id=None, rtmp_params=None, base_url=None):
         # JWPlayer backward compatibility: flattened playlists
         # https://github.com/jwplayer/jwplayer/blob/v7.4.3/src/js/api/config.js#L81-L96
         if 'playlist' not in jwplayer_data:
             jwplayer_data = {'playlist': [jwplayer_data]}
 
-        video_data = jwplayer_data['playlist'][0]
+        entries = []
+        for video_data in jwplayer_data['playlist']:
+            # JWPlayer backward compatibility: flattened sources
+            # https://github.com/jwplayer/jwplayer/blob/v7.4.3/src/js/playlist/item.js#L29-L35
+            if 'sources' not in video_data:
+                video_data['sources'] = [video_data]
 
-        # JWPlayer backward compatibility: flattened sources
-        # https://github.com/jwplayer/jwplayer/blob/v7.4.3/src/js/playlist/item.js#L29-L35
-        if 'sources' not in video_data:
-            video_data['sources'] = [video_data]
+            this_video_id = video_id or video_data['mediaid']
 
-        formats = []
-        for source in video_data['sources']:
-            source_url = self._proto_relative_url(source['file'])
-            source_type = source.get('type') or ''
-            if source_type in ('application/vnd.apple.mpegurl', 'hls') or determine_ext(source_url) == 'm3u8':
-                formats.extend(self._extract_m3u8_formats(
-                    source_url, video_id, 'mp4', 'm3u8_native', m3u8_id=m3u8_id, fatal=False))
-            elif source_type.startswith('audio'):
-                formats.append({
-                    'url': source_url,
-                    'vcodec': 'none',
-                })
-            else:
-                a_format = {
-                    'url': source_url,
-                    'width': int_or_none(source.get('width')),
-                    'height': int_or_none(source.get('height')),
-                }
-                if source_url.startswith('rtmp'):
-                    a_format['ext'] = 'flv',
-
-                    # See com/longtailvideo/jwplayer/media/RTMPMediaProvider.as
-                    # of jwplayer.flash.swf
-                    rtmp_url_parts = re.split(
-                        r'((?:mp4|mp3|flv):)', source_url, 1)
-                    if len(rtmp_url_parts) == 3:
-                        rtmp_url, prefix, play_path = rtmp_url_parts
-                        a_format.update({
-                            'url': rtmp_url,
-                            'play_path': prefix + play_path,
-                        })
-                    if rtmp_params:
-                        a_format.update(rtmp_params)
-                formats.append(a_format)
-        self._sort_formats(formats)
-
-        subtitles = {}
-        tracks = video_data.get('tracks')
-        if tracks and isinstance(tracks, list):
-            for track in tracks:
-                if track.get('file') and track.get('kind') == 'captions':
-                    subtitles.setdefault(track.get('label') or 'en', []).append({
-                        'url': self._proto_relative_url(track['file'])
+            formats = []
+            for source in video_data['sources']:
+                source_url = self._proto_relative_url(source['file'])
+                if base_url:
+                    source_url = compat_urlparse.urljoin(base_url, source_url)
+                source_type = source.get('type') or ''
+                ext = mimetype2ext(source_type) or determine_ext(source_url)
+                if source_type == 'hls' or ext == 'm3u8':
+                    formats.extend(self._extract_m3u8_formats(
+                        source_url, this_video_id, 'mp4', 'm3u8_native', m3u8_id=m3u8_id, fatal=False))
+                # https://github.com/jwplayer/jwplayer/blob/master/src/js/providers/default.js#L67
+                elif source_type.startswith('audio') or ext in ('oga', 'aac', 'mp3', 'mpeg', 'vorbis'):
+                    formats.append({
+                        'url': source_url,
+                        'vcodec': 'none',
+                        'ext': ext,
                     })
+                else:
+                    a_format = {
+                        'url': source_url,
+                        'width': int_or_none(source.get('width')),
+                        'height': int_or_none(source.get('height')),
+                        'ext': ext,
+                    }
+                    if source_url.startswith('rtmp'):
+                        a_format['ext'] = 'flv'
 
-        return {
-            'id': video_id,
-            'title': video_data['title'] if require_title else video_data.get('title'),
-            'description': video_data.get('description'),
-            'thumbnail': self._proto_relative_url(video_data.get('image')),
-            'timestamp': int_or_none(video_data.get('pubdate')),
-            'duration': float_or_none(jwplayer_data.get('duration')),
-            'subtitles': subtitles,
-            'formats': formats,
-        }
+                        # See com/longtailvideo/jwplayer/media/RTMPMediaProvider.as
+                        # of jwplayer.flash.swf
+                        rtmp_url_parts = re.split(
+                            r'((?:mp4|mp3|flv):)', source_url, 1)
+                        if len(rtmp_url_parts) == 3:
+                            rtmp_url, prefix, play_path = rtmp_url_parts
+                            a_format.update({
+                                'url': rtmp_url,
+                                'play_path': prefix + play_path,
+                            })
+                        if rtmp_params:
+                            a_format.update(rtmp_params)
+                    formats.append(a_format)
+            self._sort_formats(formats)
+
+            subtitles = {}
+            tracks = video_data.get('tracks')
+            if tracks and isinstance(tracks, list):
+                for track in tracks:
+                    if track.get('file') and track.get('kind') == 'captions':
+                        subtitles.setdefault(track.get('label') or 'en', []).append({
+                            'url': self._proto_relative_url(track['file'])
+                        })
+
+            entries.append({
+                'id': this_video_id,
+                'title': video_data['title'] if require_title else video_data.get('title'),
+                'description': video_data.get('description'),
+                'thumbnail': self._proto_relative_url(video_data.get('image')),
+                'timestamp': int_or_none(video_data.get('pubdate')),
+                'duration': float_or_none(jwplayer_data.get('duration')),
+                'subtitles': subtitles,
+                'formats': formats,
+            })
+        if len(entries) == 1:
+            return entries[0]
+        else:
+            return self.playlist_result(entries)
 
 
 class JWPlatformIE(JWPlatformBaseIE):

youtube_dl/extractor/kaltura.py

@@ -62,6 +62,11 @@ class KalturaIE(InfoExtractor):
         {
             'url': 'https://cdnapisec.kaltura.com/html5/html5lib/v2.30.2/mwEmbedFrame.php/p/1337/uiconf_id/20540612/entry_id/1_sf5ovm7u?wid=_243342',
             'only_matching': True,
+        },
+        {
+            # video with subtitles
+            'url': 'kaltura:111032:1_cw786r8q',
+            'only_matching': True,
         }
     ]
 
@@ -130,7 +135,6 @@ class KalturaIE(InfoExtractor):
             video_id, actions, service_url, note='Downloading Kaltura signature')['ks']
 
     def _get_video_info(self, video_id, partner_id, service_url=None):
-        signature = self._get_kaltura_signature(video_id, partner_id, service_url)
         actions = [
             {
                 'action': 'null',
@@ -138,18 +142,30 @@ class KalturaIE(InfoExtractor):
                 'clientTag': 'kdp:v3.8.5',
                 'format': 1,  # JSON, 2 = XML, 3 = PHP
                 'service': 'multirequest',
-                'ks': signature,
+            },
+            {
+                'expiry': 86400,
+                'service': 'session',
+                'action': 'startWidgetSession',
+                'widgetId': '_%s' % partner_id,
             },
             {
                 'action': 'get',
                 'entryId': video_id,
                 'service': 'baseentry',
-                'version': '-1',
+                'ks': '{1:result:ks}',
             },
             {
                 'action': 'getbyentryid',
                 'entryId': video_id,
                 'service': 'flavorAsset',
+                'ks': '{1:result:ks}',
+            },
+            {
+                'action': 'list',
+                'filter:entryIdEqual': video_id,
+                'service': 'caption_captionasset',
+                'ks': '{1:result:ks}',
             },
         ]
         return self._kaltura_api_call(
@@ -161,8 +177,9 @@ class KalturaIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         partner_id, entry_id = mobj.group('partner_id', 'id')
         ks = None
+        captions = None
         if partner_id and entry_id:
-            info, flavor_assets = self._get_video_info(entry_id, partner_id, smuggled_data.get('service_url'))
+            _, info, flavor_assets, captions = self._get_video_info(entry_id, partner_id, smuggled_data.get('service_url'))
         else:
             path, query = mobj.group('path', 'query')
             if not path and not query:
@@ -181,7 +198,7 @@ class KalturaIE(InfoExtractor):
                 raise ExtractorError('Invalid URL', expected=True)
             if 'entry_id' in params:
                 entry_id = params['entry_id'][0]
-                info, flavor_assets = self._get_video_info(entry_id, partner_id)
+                _, info, flavor_assets, captions = self._get_video_info(entry_id, partner_id)
             elif 'uiconf_id' in params and 'flashvars[referenceId]' in params:
                 reference_id = params['flashvars[referenceId]'][0]
                 webpage = self._download_webpage(url, reference_id)
@@ -217,7 +234,7 @@ class KalturaIE(InfoExtractor):
         formats = []
         for f in flavor_assets:
             # Continue if asset is not ready
-            if f['status'] != 2:
+            if f.get('status') != 2:
                 continue
             video_url = sign_url(
                 '%s/flavorId/%s' % (data_url, f['id']))
@@ -240,13 +257,24 @@ class KalturaIE(InfoExtractor):
                 m3u8_url, entry_id, 'mp4', 'm3u8_native',
                 m3u8_id='hls', fatal=False))
 
-        self._check_formats(formats, entry_id)
         self._sort_formats(formats)
 
+        subtitles = {}
+        if captions:
+            for caption in captions.get('objects', []):
+                # Continue if caption is not ready
+                if f.get('status') != 2:
+                    continue
+                subtitles.setdefault(caption.get('languageCode') or caption.get('language'), []).append({
+                    'url': '%s/api_v3/service/caption_captionasset/action/serve/captionAssetId/%s' % (self._SERVICE_URL, caption['id']),
+                    'ext': caption.get('fileExt'),
+                })
+
         return {
             'id': entry_id,
             'title': info['name'],
             'formats': formats,
+            'subtitles': subtitles,
             'description': clean_html(info.get('description')),
             'thumbnail': info.get('thumbnailUrl'),
             'duration': info.get('duration'),

youtube_dl/extractor/keezmovies.py

@@ -3,64 +3,124 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..aes import aes_decrypt_text
+from ..compat import (
+    compat_str,
+    compat_urllib_parse_unquote,
+)
 from ..utils import (
-    sanitized_Request,
-    url_basename,
+    determine_ext,
+    ExtractorError,
+    int_or_none,
+    str_to_int,
+    strip_or_none,
 )
 
 
 class KeezMoviesIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?keezmovies\.com/video/.+?(?P<id>[0-9]+)(?:[/?&]|$)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?keezmovies\.com/video/(?:(?P<display_id>[^/]+)-)?(?P<id>\d+)'
+    _TESTS = [{
         'url': 'http://www.keezmovies.com/video/petite-asian-lady-mai-playing-in-bathtub-1214711',
         'md5': '1c1e75d22ffa53320f45eeb07bc4cdc0',
         'info_dict': {
             'id': '1214711',
+            'display_id': 'petite-asian-lady-mai-playing-in-bathtub',
             'ext': 'mp4',
             'title': 'Petite Asian Lady Mai Playing In Bathtub',
-            'age_limit': 18,
             'thumbnail': 're:^https?://.*\.jpg$',
+            'view_count': int,
+            'age_limit': 18,
         }
-    }
+    }, {
+        'url': 'http://www.keezmovies.com/video/1214711',
+        'only_matching': True,
+    }]
 
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
+    def _extract_info(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        display_id = mobj.group('display_id') or video_id
 
-        req = sanitized_Request(url)
-        req.add_header('Cookie', 'age_verified=1')
-        webpage = self._download_webpage(req, video_id)
-
-        # embedded video
-        mobj = re.search(r'href="([^"]+)"></iframe>', webpage)
-        if mobj:
-            embedded_url = mobj.group(1)
-            return self.url_result(embedded_url)
-
-        video_title = self._html_search_regex(
-            r'<h1 [^>]*>([^<]+)', webpage, 'title')
-        flashvars = self._parse_json(self._search_regex(
-            r'var\s+flashvars\s*=\s*([^;]+);', webpage, 'flashvars'), video_id)
+        webpage = self._download_webpage(
+            url, display_id, headers={'Cookie': 'age_verified=1'})
 
         formats = []
-        for height in (180, 240, 480):
-            if flashvars.get('quality_%dp' % height):
-                video_url = flashvars['quality_%dp' % height]
-                a_format = {
-                    'url': video_url,
-                    'height': height,
-                    'format_id': '%dp' % height,
-                }
-                filename_parts = url_basename(video_url).split('_')
-                if len(filename_parts) >= 2 and re.match(r'\d+[Kk]', filename_parts[1]):
-                    a_format['tbr'] = int(filename_parts[1][:-1])
-                formats.append(a_format)
+        format_urls = set()
 
-        age_limit = self._rta_search(webpage)
+        title = None
+        thumbnail = None
+        duration = None
+        encrypted = False
 
-        return {
+        def extract_format(format_url, height=None):
+            if not isinstance(format_url, compat_str) or not format_url.startswith('http'):
+                return
+            if format_url in format_urls:
+                return
+            format_urls.add(format_url)
+            tbr = int_or_none(self._search_regex(
+                r'[/_](\d+)[kK][/_]', format_url, 'tbr', default=None))
+            if not height:
+                height = int_or_none(self._search_regex(
+                    r'[/_](\d+)[pP][/_]', format_url, 'height', default=None))
+            if encrypted:
+                format_url = aes_decrypt_text(
+                    video_url, title, 32).decode('utf-8')
+            formats.append({
+                'url': format_url,
+                'format_id': '%dp' % height if height else None,
+                'height': height,
+                'tbr': tbr,
+            })
+
+        flashvars = self._parse_json(
+            self._search_regex(
+                r'flashvars\s*=\s*({.+?});', webpage,
+                'flashvars', default='{}'),
+            display_id, fatal=False)
+
+        if flashvars:
+            title = flashvars.get('video_title')
+            thumbnail = flashvars.get('image_url')
+            duration = int_or_none(flashvars.get('video_duration'))
+            encrypted = flashvars.get('encrypted') is True
+            for key, value in flashvars.items():
+                mobj = re.search(r'quality_(\d+)[pP]', key)
+                if mobj:
+                    extract_format(value, int(mobj.group(1)))
+            video_url = flashvars.get('video_url')
+            if video_url and determine_ext(video_url, None):
+                extract_format(video_url)
+
+        video_url = self._html_search_regex(
+            r'flashvars\.video_url\s*=\s*(["\'])(?P<url>http.+?)\1',
+            webpage, 'video url', default=None, group='url')
+        if video_url:
+            extract_format(compat_urllib_parse_unquote(video_url))
+
+        if not formats:
+            if 'title="This video is no longer available"' in webpage:
+                raise ExtractorError(
+                    'Video %s is no longer available' % video_id, expected=True)
+
+        self._sort_formats(formats)
+
+        if not title:
+            title = self._html_search_regex(
+                r'<h1[^>]*>([^<]+)', webpage, 'title')
+
+        return webpage, {
             'id': video_id,
-            'title': video_title,
+            'display_id': display_id,
+            'title': strip_or_none(title),
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'age_limit': 18,
             'formats': formats,
-            'age_limit': age_limit,
-            'thumbnail': flashvars.get('image_url')
         }
+
+    def _real_extract(self, url):
+        webpage, info = self._extract_info(url)
+        info['view_count'] = str_to_int(self._search_regex(
+            r'<b>([\d,.]+)</b> Views?', webpage, 'view count', fatal=False))
+        return info

youtube_dl/extractor/kuwo.py

@@ -4,6 +4,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_urlparse
 from ..utils import (
     get_element_by_id,
     clean_html,
@@ -242,8 +243,9 @@ class KuwoSingerIE(InfoExtractor):
                 query={'artistId': artist_id, 'pn': page_num, 'rn': self.PAGE_SIZE})
 
             return [
-                self.url_result(song_url, 'Kuwo') for song_url in re.findall(
-                    r'<div[^>]+class="name"><a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+)',
+                self.url_result(compat_urlparse.urljoin(url, song_url), 'Kuwo')
+                for song_url in re.findall(
+                    r'<div[^>]+class="name"><a[^>]+href="(/yinyue/\d+)',
                     webpage)
             ]
 

youtube_dl/extractor/lcp.py

@@ -0,0 +1,90 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from .arkena import ArkenaIE
+
+
+class LcpPlayIE(ArkenaIE):
+    _VALID_URL = r'https?://play\.lcp\.fr/embed/(?P<id>[^/]+)/(?P<account_id>[^/]+)/[^/]+/[^/]+'
+    _TESTS = [{
+        'url': 'http://play.lcp.fr/embed/327336/131064/darkmatter/0',
+        'md5': 'b8bd9298542929c06c1c15788b1f277a',
+        'info_dict': {
+            'id': '327336',
+            'ext': 'mp4',
+            'title': '327336',
+            'timestamp': 1456391602,
+            'upload_date': '20160225',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }]
+
+
+class LcpIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?lcp\.fr/(?:[^/]+/)*(?P<id>[^/]+)'
+
+    _TESTS = [{
+        # arkena embed
+        'url': 'http://www.lcp.fr/la-politique-en-video/schwartzenberg-prg-preconise-francois-hollande-de-participer-une-primaire',
+        'md5': 'b8bd9298542929c06c1c15788b1f277a',
+        'info_dict': {
+            'id': 'd56d03e9',
+            'ext': 'mp4',
+            'title': 'Schwartzenberg (PRG) préconise à François Hollande de participer à une primaire à gauche',
+            'description': 'md5:96ad55009548da9dea19f4120c6c16a8',
+            'timestamp': 1456488895,
+            'upload_date': '20160226',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        # dailymotion live stream
+        'url': 'http://www.lcp.fr/le-direct',
+        'info_dict': {
+            'id': 'xji3qy',
+            'ext': 'mp4',
+            'title': 'La Chaine Parlementaire (LCP), Live TNT',
+            'description': 'md5:5c69593f2de0f38bd9a949f2c95e870b',
+            'uploader': 'LCP',
+            'uploader_id': 'xbz33d',
+            'timestamp': 1308923058,
+            'upload_date': '20110624',
+        },
+        'params': {
+            # m3u8 live stream
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://www.lcp.fr/emissions/277792-les-volontaires',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        play_url = self._search_regex(
+            r'<iframe[^>]+src=(["\'])(?P<url>%s?(?:(?!\1).)*)\1' % LcpPlayIE._VALID_URL,
+            webpage, 'play iframe', default=None, group='url')
+
+        if not play_url:
+            return self.url_result(url, 'Generic')
+
+        title = self._og_search_title(webpage, default=None) or self._html_search_meta(
+            'twitter:title', webpage, fatal=True)
+        description = self._html_search_meta(
+            ('description', 'twitter:description'), webpage)
+
+        return {
+            '_type': 'url_transparent',
+            'ie_key': LcpPlayIE.ie_key(),
+            'url': play_url,
+            'display_id': display_id,
+            'title': title,
+            'description': description,
+        }

youtube_dl/extractor/lifenews.py

@@ -4,7 +4,10 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_urlparse
+from ..compat import (
+    compat_str,
+    compat_urlparse,
+)
 from ..utils import (
     determine_ext,
     ExtractorError,
@@ -96,7 +99,7 @@ class LifeNewsIE(InfoExtractor):
             r'<video[^>]+><source[^>]+src=["\'](.+?)["\']', webpage)
 
         iframe_links = re.findall(
-            r'<iframe[^>]+src=["\']((?:https?:)?//embed\.life\.ru/embed/.+?)["\']',
+            r'<iframe[^>]+src=["\']((?:https?:)?//embed\.life\.ru/(?:embed|video)/.+?)["\']',
             webpage)
 
         if not video_urls and not iframe_links:
@@ -164,9 +167,9 @@ class LifeNewsIE(InfoExtractor):
 
 class LifeEmbedIE(InfoExtractor):
     IE_NAME = 'life:embed'
-    _VALID_URL = r'https?://embed\.life\.ru/embed/(?P<id>[\da-f]{32})'
+    _VALID_URL = r'https?://embed\.life\.ru/(?:embed|video)/(?P<id>[\da-f]{32})'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://embed.life.ru/embed/e50c2dec2867350528e2574c899b8291',
         'md5': 'b889715c9e49cb1981281d0e5458fbbe',
         'info_dict': {
@@ -175,30 +178,57 @@ class LifeEmbedIE(InfoExtractor):
             'title': 'e50c2dec2867350528e2574c899b8291',
             'thumbnail': 're:http://.*\.jpg',
         }
-    }
+    }, {
+        # with 1080p
+        'url': 'https://embed.life.ru/video/e50c2dec2867350528e2574c899b8291',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
 
+        thumbnail = None
         formats = []
-        for video_url in re.findall(r'"file"\s*:\s*"([^"]+)', webpage):
-            video_url = compat_urlparse.urljoin(url, video_url)
-            ext = determine_ext(video_url)
-            if ext == 'm3u8':
-                formats.extend(self._extract_m3u8_formats(
-                    video_url, video_id, 'mp4',
-                    entry_protocol='m3u8_native', m3u8_id='m3u8'))
-            else:
-                formats.append({
-                    'url': video_url,
-                    'format_id': ext,
-                    'preference': 1,
-                })
+
+        def extract_m3u8(manifest_url):
+            formats.extend(self._extract_m3u8_formats(
+                manifest_url, video_id, 'mp4',
+                entry_protocol='m3u8_native', m3u8_id='m3u8'))
+
+        def extract_original(original_url):
+            formats.append({
+                'url': original_url,
+                'format_id': determine_ext(original_url, None),
+                'preference': 1,
+            })
+
+        playlist = self._parse_json(
+            self._search_regex(
+                r'options\s*=\s*({.+?});', webpage, 'options', default='{}'),
+            video_id).get('playlist', {})
+        if playlist:
+            master = playlist.get('master')
+            if isinstance(master, compat_str) and determine_ext(master) == 'm3u8':
+                extract_m3u8(compat_urlparse.urljoin(url, master))
+            original = playlist.get('original')
+            if isinstance(original, compat_str):
+                extract_original(original)
+            thumbnail = playlist.get('image')
+
+        # Old rendition fallback
+        if not formats:
+            for video_url in re.findall(r'"file"\s*:\s*"([^"]+)', webpage):
+                video_url = compat_urlparse.urljoin(url, video_url)
+                if determine_ext(video_url) == 'm3u8':
+                    extract_m3u8(video_url)
+                else:
+                    extract_original(video_url)
+
         self._sort_formats(formats)
 
-        thumbnail = self._search_regex(
+        thumbnail = thumbnail or self._search_regex(
             r'"image"\s*:\s*"([^"]+)', webpage, 'thumbnail', default=None)
 
         return {

youtube_dl/extractor/limelight.py

@@ -37,11 +37,12 @@ class LimelightBaseIE(InfoExtractor):
 
         for stream in streams:
             stream_url = stream.get('url')
-            if not stream_url:
+            if not stream_url or stream.get('drmProtected'):
                 continue
-            if '.f4m' in stream_url:
+            ext = determine_ext(stream_url)
+            if ext == 'f4m':
                 formats.extend(self._extract_f4m_formats(
-                    stream_url, video_id, fatal=False))
+                    stream_url, video_id, f4m_id='hds', fatal=False))
             else:
                 fmt = {
                     'url': stream_url,
@@ -50,13 +51,19 @@ class LimelightBaseIE(InfoExtractor):
                     'fps': float_or_none(stream.get('videoFrameRate')),
                     'width': int_or_none(stream.get('videoWidthInPixels')),
                     'height': int_or_none(stream.get('videoHeightInPixels')),
-                    'ext': determine_ext(stream_url)
+                    'ext': ext,
                 }
-                rtmp = re.search(r'^(?P<url>rtmpe?://[^/]+/(?P<app>.+))/(?P<playpath>mp4:.+)$', stream_url)
+                rtmp = re.search(r'^(?P<url>rtmpe?://(?P<host>[^/]+)/(?P<app>.+))/(?P<playpath>mp4:.+)$', stream_url)
                 if rtmp:
                     format_id = 'rtmp'
                     if stream.get('videoBitRate'):
                         format_id += '-%d' % int_or_none(stream['videoBitRate'])
+                    http_fmt = fmt.copy()
+                    http_fmt.update({
+                        'url': 'http://%s/%s' % (rtmp.group('host').replace('csl.', 'cpl.'), rtmp.group('playpath')[4:]),
+                        'format_id': format_id.replace('rtmp', 'http'),
+                    })
+                    formats.append(http_fmt)
                     fmt.update({
                         'url': rtmp.group('url'),
                         'play_path': rtmp.group('playpath'),
@@ -68,18 +75,23 @@ class LimelightBaseIE(InfoExtractor):
 
         for mobile_url in mobile_urls:
             media_url = mobile_url.get('mobileUrl')
-            if not media_url:
-                continue
             format_id = mobile_url.get('targetMediaPlatform')
-            if determine_ext(media_url) == 'm3u8':
+            if not media_url or format_id == 'Widevine':
+                continue
+            ext = determine_ext(media_url)
+            if ext == 'm3u8':
                 formats.extend(self._extract_m3u8_formats(
                     media_url, video_id, 'mp4', 'm3u8_native',
                     m3u8_id=format_id, fatal=False))
+            elif ext == 'f4m':
+                formats.extend(self._extract_f4m_formats(
+                    stream_url, video_id, f4m_id=format_id, fatal=False))
             else:
                 formats.append({
                     'url': media_url,
                     'format_id': format_id,
                     'preference': -1,
+                    'ext': ext,
                 })
 
         self._sort_formats(formats)
@@ -145,7 +157,7 @@ class LimelightMediaIE(LimelightBaseIE):
         'url': 'http://link.videoplatform.limelight.com/media/?mediaId=3ffd040b522b4485b6d84effc750cd86',
         'info_dict': {
             'id': '3ffd040b522b4485b6d84effc750cd86',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': 'HaP and the HB Prince Trailer',
             'description': 'md5:8005b944181778e313d95c1237ddb640',
             'thumbnail': 're:^https?://.*\.jpeg$',
@@ -154,27 +166,23 @@ class LimelightMediaIE(LimelightBaseIE):
             'upload_date': '20090604',
         },
         'params': {
-            # rtmp download
+            # m3u8 download
             'skip_download': True,
         },
     }, {
         # video with subtitles
         'url': 'limelight:media:a3e00274d4564ec4a9b29b9466432335',
+        'md5': '2fa3bad9ac321e23860ca23bc2c69e3d',
         'info_dict': {
             'id': 'a3e00274d4564ec4a9b29b9466432335',
-            'ext': 'flv',
+            'ext': 'mp4',
             'title': '3Play Media Overview Video',
-            'description': '',
             'thumbnail': 're:^https?://.*\.jpeg$',
             'duration': 78.101,
             'timestamp': 1338929955,
             'upload_date': '20120605',
             'subtitles': 'mincount:9',
         },
-        'params': {
-            # rtmp download
-            'skip_download': True,
-        },
     }, {
         'url': 'https://assets.delvenetworks.com/player/loader.swf?mediaId=8018a574f08d416e95ceaccae4ba0452',
         'only_matching': True,

youtube_dl/extractor/lynda.py

@@ -100,7 +100,7 @@ class LyndaIE(LyndaBaseIE):
 
     _TESTS = [{
         'url': 'http://www.lynda.com/Bootstrap-tutorials/Using-exercise-files/110885/114408-4.html',
-        'md5': '679734f6786145da3546585de9a356be',
+        # md5 is unstable
         'info_dict': {
             'id': '114408',
             'ext': 'mp4',

youtube_dl/extractor/mgtv.py

@@ -9,7 +9,7 @@ class MGTVIE(InfoExtractor):
     _VALID_URL = r'https?://www\.mgtv\.com/v/(?:[^/]+/)*(?P<id>\d+)\.html'
     IE_DESC = '芒果TV'
 
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.mgtv.com/v/1/290525/f/3116640.html',
         'md5': '1bdadcf760a0b90946ca68ee9a2db41a',
         'info_dict': {
@@ -20,7 +20,11 @@ class MGTVIE(InfoExtractor):
             'duration': 7461,
             'thumbnail': 're:^https?://.*\.jpg$',
         },
-    }
+    }, {
+        # no tbr extracted from stream_url
+        'url': 'http://www.mgtv.com/v/1/1/f/3324755.html',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
@@ -41,7 +45,8 @@ class MGTVIE(InfoExtractor):
             def extract_format(stream_url, format_id, idx, query={}):
                 format_info = self._download_json(
                     stream_url, video_id,
-                    note='Download video info for format %s' % format_id or '#%d' % idx, query=query)
+                    note='Download video info for format %s' % (format_id or '#%d' % idx),
+                    query=query)
                 return {
                     'format_id': format_id,
                     'url': format_info['info'],

youtube_dl/extractor/miomio.py

@@ -4,6 +4,7 @@ from __future__ import unicode_literals
 import random
 
 from .common import InfoExtractor
+from ..compat import compat_urlparse
 from ..utils import (
     xpath_text,
     int_or_none,
@@ -18,13 +19,16 @@ class MioMioIE(InfoExtractor):
     _TESTS = [{
         # "type=video" in flashvars
         'url': 'http://www.miomio.tv/watch/cc88912/',
-        'md5': '317a5f7f6b544ce8419b784ca8edae65',
         'info_dict': {
             'id': '88912',
             'ext': 'flv',
             'title': '【SKY】字幕 铠武昭和VS平成 假面骑士大战FEAT战队 魔星字幕组 字幕',
             'duration': 5923,
         },
+        'params': {
+            # The server provides broken file
+            'skip_download': True,
+        }
     }, {
         'url': 'http://www.miomio.tv/watch/cc184024/',
         'info_dict': {
@@ -32,7 +36,7 @@ class MioMioIE(InfoExtractor):
             'title': '《动漫同人插画绘制》',
         },
         'playlist_mincount': 86,
-        'skip': 'This video takes time too long for retrieving the URL',
+        'skip': 'Unable to load videos',
     }, {
         'url': 'http://www.miomio.tv/watch/cc173113/',
         'info_dict': {
@@ -40,20 +44,23 @@ class MioMioIE(InfoExtractor):
             'title': 'The New Macbook 2015 上手试玩与简评'
         },
         'playlist_mincount': 2,
+        'skip': 'Unable to load videos',
+    }, {
+        # new 'h5' player
+        'url': 'http://www.miomio.tv/watch/cc273295/',
+        'md5': '',
+        'info_dict': {
+            'id': '273295',
+            'ext': 'mp4',
+            'title': 'アウト×デラックス 20160526',
+        },
+        'params': {
+            # intermittent HTTP 500
+            'skip_download': True,
+        },
     }]
 
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
-
-        title = self._html_search_meta(
-            'description', webpage, 'title', fatal=True)
-
-        mioplayer_path = self._search_regex(
-            r'src="(/mioplayer/[^"]+)"', webpage, 'ref_path')
-
-        http_headers = {'Referer': 'http://www.miomio.tv%s' % mioplayer_path}
-
+    def _extract_mioplayer(self, webpage, video_id, title, http_headers):
         xml_config = self._search_regex(
             r'flashvars="type=(?:sina|video)&(.+?)&',
             webpage, 'xml config')
@@ -92,10 +99,34 @@ class MioMioIE(InfoExtractor):
                 'http_headers': http_headers,
             })
 
+        return entries
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._html_search_meta(
+            'description', webpage, 'title', fatal=True)
+
+        mioplayer_path = self._search_regex(
+            r'src="(/mioplayer(?:_h5)?/[^"]+)"', webpage, 'ref_path')
+
+        if '_h5' in mioplayer_path:
+            player_url = compat_urlparse.urljoin(url, mioplayer_path)
+            player_webpage = self._download_webpage(
+                player_url, video_id,
+                note='Downloading player webpage', headers={'Referer': url})
+            entries = self._parse_html5_media_entries(player_url, player_webpage)
+            http_headers = {'Referer': player_url}
+        else:
+            http_headers = {'Referer': 'http://www.miomio.tv%s' % mioplayer_path}
+            entries = self._extract_mioplayer(webpage, video_id, title, http_headers)
+
         if len(entries) == 1:
             segment = entries[0]
             segment['id'] = video_id
             segment['title'] = title
+            segment['http_headers'] = http_headers
             return segment
 
         return {

youtube_dl/extractor/mofosex.py

@@ -1,53 +1,56 @@
 from __future__ import unicode_literals
 
-import os
-import re
-
-from .common import InfoExtractor
-from ..compat import (
-    compat_urllib_parse_unquote,
-    compat_urllib_parse_urlparse,
+from ..utils import (
+    int_or_none,
+    str_to_int,
+    unified_strdate,
 )
-from ..utils import sanitized_Request
+from .keezmovies import KeezMoviesIE
 
 
-class MofosexIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?(?P<url>mofosex\.com/videos/(?P<id>[0-9]+)/.*?\.html)'
-    _TEST = {
-        'url': 'http://www.mofosex.com/videos/5018/japanese-teen-music-video.html',
-        'md5': '1b2eb47ac33cc75d4a80e3026b613c5a',
+class MofosexIE(KeezMoviesIE):
+    _VALID_URL = r'https?://(?:www\.)?mofosex\.com/videos/(?P<id>\d+)/(?P<display_id>[^/?#&.]+)\.html'
+    _TESTS = [{
+        'url': 'http://www.mofosex.com/videos/318131/amateur-teen-playing-and-masturbating-318131.html',
+        'md5': '39a15853632b7b2e5679f92f69b78e91',
         'info_dict': {
-            'id': '5018',
+            'id': '318131',
+            'display_id': 'amateur-teen-playing-and-masturbating-318131',
             'ext': 'mp4',
-            'title': 'Japanese Teen Music Video',
+            'title': 'amateur teen playing and masturbating',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'upload_date': '20121114',
+            'view_count': int,
+            'like_count': int,
+            'dislike_count': int,
             'age_limit': 18,
         }
-    }
+    }, {
+        # This video is no longer available
+        'url': 'http://www.mofosex.com/videos/5018/japanese-teen-music-video.html',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        url = 'http://www.' + mobj.group('url')
+        webpage, info = self._extract_info(url)
 
-        req = sanitized_Request(url)
-        req.add_header('Cookie', 'age_verified=1')
-        webpage = self._download_webpage(req, video_id)
+        view_count = str_to_int(self._search_regex(
+            r'VIEWS:</span>\s*([\d,.]+)', webpage, 'view count', fatal=False))
+        like_count = int_or_none(self._search_regex(
+            r'id=["\']amountLikes["\'][^>]*>(\d+)', webpage,
+            'like count', fatal=False))
+        dislike_count = int_or_none(self._search_regex(
+            r'id=["\']amountDislikes["\'][^>]*>(\d+)', webpage,
+            'like count', fatal=False))
+        upload_date = unified_strdate(self._html_search_regex(
+            r'Added:</span>([^<]+)', webpage, 'upload date', fatal=False))
 
-        video_title = self._html_search_regex(r'<h1>(.+?)<', webpage, 'title')
-        video_url = compat_urllib_parse_unquote(self._html_search_regex(r'flashvars.video_url = \'([^\']+)', webpage, 'video_url'))
-        path = compat_urllib_parse_urlparse(video_url).path
-        extension = os.path.splitext(path)[1][1:]
-        format = path.split('/')[5].split('_')[:2]
-        format = '-'.join(format)
+        info.update({
+            'view_count': view_count,
+            'like_count': like_count,
+            'dislike_count': dislike_count,
+            'upload_date': upload_date,
+            'thumbnail': self._og_search_thumbnail(webpage),
+        })
 
-        age_limit = self._rta_search(webpage)
-
-        return {
-            'id': video_id,
-            'title': video_title,
-            'url': video_url,
-            'ext': extension,
-            'format': format,
-            'format_id': format,
-            'age_limit': age_limit,
-        }
+        return info

youtube_dl/extractor/mtv.py

@@ -15,6 +15,8 @@ from ..utils import (
     float_or_none,
     HEADRequest,
     sanitized_Request,
+    strip_or_none,
+    timeconvert,
     unescapeHTML,
     url_basename,
     RegexNotFoundError,
@@ -35,13 +37,13 @@ class MTVServicesInfoExtractor(InfoExtractor):
         return uri.split(':')[-1]
 
     # This was originally implemented for ComedyCentral, but it also works here
-    @staticmethod
-    def _transform_rtmp_url(rtmp_video_url):
+    @classmethod
+    def _transform_rtmp_url(cls, rtmp_video_url):
         m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp\..+?/.*)$', rtmp_video_url)
         if not m:
-            return rtmp_video_url
+            return {'rtmp': rtmp_video_url}
         base = 'http://viacommtvstrmfs.fplive.net/'
-        return base + m.group('finalid')
+        return {'http': base + m.group('finalid')}
 
     def _get_feed_url(self, uri):
         return self._FEED_URL
@@ -85,14 +87,14 @@ class MTVServicesInfoExtractor(InfoExtractor):
                 rtmp_video_url = rendition.find('./src').text
                 if rtmp_video_url.endswith('siteunavail.png'):
                     continue
-                new_url = self._transform_rtmp_url(rtmp_video_url)
-                formats.append({
+                new_urls = self._transform_rtmp_url(rtmp_video_url)
+                formats.extend([{
                     'ext': 'flv' if new_url.startswith('rtmp') else ext,
                     'url': new_url,
-                    'format_id': rendition.get('bitrate'),
+                    'format_id': '-'.join(filter(None, [kind, rendition.get('bitrate')])),
                     'width': int(rendition.get('width')),
                     'height': int(rendition.get('height')),
-                })
+                } for kind, new_url in new_urls.items()])
             except (KeyError, TypeError):
                 raise ExtractorError('Invalid rendition field.')
         self._sort_formats(formats)
@@ -133,7 +135,9 @@ class MTVServicesInfoExtractor(InfoExtractor):
             message += item.text
             raise ExtractorError(message, expected=True)
 
-        description = xpath_text(itemdoc, 'description')
+        description = strip_or_none(xpath_text(itemdoc, 'description'))
+
+        timestamp = timeconvert(xpath_text(itemdoc, 'pubDate'))
 
         title_el = None
         if title_el is None:
@@ -167,6 +171,7 @@ class MTVServicesInfoExtractor(InfoExtractor):
             'thumbnail': self._get_thumbnail_url(uri, itemdoc),
             'description': description,
             'duration': float_or_none(content_el.attrib.get('duration')),
+            'timestamp': timestamp,
         }
 
     def _get_feed_query(self, uri):
@@ -185,8 +190,13 @@ class MTVServicesInfoExtractor(InfoExtractor):
         idoc = self._download_xml(
             url, video_id,
             'Downloading info', transform_source=fix_xml_ampersands)
+
+        title = xpath_text(idoc, './channel/title')
+        description = xpath_text(idoc, './channel/description')
+
         return self.playlist_result(
-            [self._get_video_info(item) for item in idoc.findall('.//item')])
+            [self._get_video_info(item) for item in idoc.findall('.//item')],
+            playlist_title=title, playlist_description=description)
 
     def _extract_mgid(self, webpage):
         try:
@@ -232,6 +242,8 @@ class MTVServicesEmbeddedIE(MTVServicesInfoExtractor):
             'ext': 'mp4',
             'title': 'Peter Dinklage Sums Up \'Game Of Thrones\' In 45 Seconds',
             'description': '"Sexy sexy sexy, stabby stabby stabby, beautiful language," says Peter Dinklage as he tries summarizing "Game of Thrones" in under a minute.',
+            'timestamp': 1400126400,
+            'upload_date': '20140515',
         },
     }
 
@@ -274,6 +286,8 @@ class MTVIE(MTVServicesInfoExtractor):
                 'ext': 'mp4',
                 'title': 'Taylor Swift - "Ours (VH1 Storytellers)"',
                 'description': 'Album: Taylor Swift performs "Ours" for VH1 Storytellers at Harvey Mudd College.',
+                'timestamp': 1352610000,
+                'upload_date': '20121111',
             },
         },
     ]
@@ -300,20 +314,6 @@ class MTVIE(MTVServicesInfoExtractor):
         return self._get_videos_info(uri)
 
 
-class MTVIggyIE(MTVServicesInfoExtractor):
-    IE_NAME = 'mtviggy.com'
-    _VALID_URL = r'https?://www\.mtviggy\.com/videos/.+'
-    _TEST = {
-        'url': 'http://www.mtviggy.com/videos/arcade-fire-behind-the-scenes-at-the-biggest-music-experiment-yet/',
-        'info_dict': {
-            'id': '984696',
-            'ext': 'mp4',
-            'title': 'Arcade Fire: Behind the Scenes at the Biggest Music Experiment Yet',
-        }
-    }
-    _FEED_URL = 'http://all.mtvworldverticals.com/feed-xml/'
-
-
 class MTVDEIE(MTVServicesInfoExtractor):
     IE_NAME = 'mtv.de'
     _VALID_URL = r'https?://(?:www\.)?mtv\.de/(?:artists|shows|news)/(?:[^/]+/)*(?P<id>\d+)-[^/#?]+/*(?:[#?].*)?$'
@@ -321,7 +321,7 @@ class MTVDEIE(MTVServicesInfoExtractor):
         'url': 'http://www.mtv.de/artists/10571-cro/videos/61131-traum',
         'info_dict': {
             'id': 'music_video-a50bc5f0b3aa4b3190aa',
-            'ext': 'mp4',
+            'ext': 'flv',
             'title': 'MusicVideo_cro-traum',
             'description': 'Cro - Traum',
         },
@@ -329,20 +329,21 @@ class MTVDEIE(MTVServicesInfoExtractor):
             # rtmp download
             'skip_download': True,
         },
+        'skip': 'Blocked at Travis CI',
     }, {
         # mediagen URL without query (e.g. http://videos.mtvnn.com/mediagen/e865da714c166d18d6f80893195fcb97)
         'url': 'http://www.mtv.de/shows/933-teen-mom-2/staffeln/5353/folgen/63565-enthullungen',
         'info_dict': {
             'id': 'local_playlist-f5ae778b9832cc837189',
-            'ext': 'mp4',
+            'ext': 'flv',
             'title': 'Episode_teen-mom-2_shows_season-5_episode-1_full-episode_part1',
         },
         'params': {
             # rtmp download
             'skip_download': True,
         },
+        'skip': 'Blocked at Travis CI',
     }, {
-        # single video in pagePlaylist with different id
         'url': 'http://www.mtv.de/news/77491-mtv-movies-spotlight-pixels-teil-3',
         'info_dict': {
             'id': 'local_playlist-4e760566473c4c8c5344',
@@ -354,6 +355,7 @@ class MTVDEIE(MTVServicesInfoExtractor):
             # rtmp download
             'skip_download': True,
         },
+        'skip': 'Das Video kann zur Zeit nicht abgespielt werden.',
     }]
 
     def _real_extract(self, url):
@@ -366,11 +368,14 @@ class MTVDEIE(MTVServicesInfoExtractor):
                 r'window\.pagePlaylist\s*=\s*(\[.+?\]);\n', webpage, 'page playlist'),
             video_id)
 
+        def _mrss_url(item):
+            return item['mrss'] + item.get('mrssvars', '')
+
         # news pages contain single video in playlist with different id
         if len(playlist) == 1:
-            return self._get_videos_info_from_url(playlist[0]['mrss'], video_id)
+            return self._get_videos_info_from_url(_mrss_url(playlist[0]), video_id)
 
         for item in playlist:
             item_id = item.get('id')
             if item_id and compat_str(item_id) == video_id:
-                return self._get_videos_info_from_url(item['mrss'], video_id)
+                return self._get_videos_info_from_url(_mrss_url(item), video_id)

youtube_dl/extractor/muenchentv.py

@@ -36,7 +36,7 @@ class MuenchenTVIE(InfoExtractor):
         title = self._live_title(self._og_search_title(webpage))
 
         data_js = self._search_regex(
-            r'(?s)\nplaylist:\s*(\[.*?}\]),related:',
+            r'(?s)\nplaylist:\s*(\[.*?}\]),',
             webpage, 'playlist configuration')
         data_json = js_to_json(data_js)
         data = json.loads(data_json)[0]

youtube_dl/extractor/nationalgeographic.py

@@ -1,16 +1,19 @@
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
-from .theplatform import ThePlatformIE
+from .adobepass import AdobePassIE
 from ..utils import (
     smuggle_url,
     url_basename,
     update_url_query,
+    get_element_by_class,
 )
 
 
-class NationalGeographicIE(InfoExtractor):
-    IE_NAME = 'natgeo'
+class NationalGeographicVideoIE(InfoExtractor):
+    IE_NAME = 'natgeo:video'
     _VALID_URL = r'https?://video\.nationalgeographic\.com/.*?'
 
     _TESTS = [
@@ -62,16 +65,16 @@ class NationalGeographicIE(InfoExtractor):
         }
 
 
-class NationalGeographicChannelIE(ThePlatformIE):
-    IE_NAME = 'natgeo:channel'
-    _VALID_URL = r'https?://channel\.nationalgeographic\.com/(?:wild/)?[^/]+/videos/(?P<id>[^/?]+)'
+class NationalGeographicIE(AdobePassIE):
+    IE_NAME = 'natgeo'
+    _VALID_URL = r'https?://channel\.nationalgeographic\.com/(?:wild/)?[^/]+/(?:videos|episodes)/(?P<id>[^/?]+)'
 
     _TESTS = [
         {
             'url': 'http://channel.nationalgeographic.com/the-story-of-god-with-morgan-freeman/videos/uncovering-a-universal-knowledge/',
             'md5': '518c9aa655686cf81493af5cc21e2a04',
             'info_dict': {
-                'id': 'nB5vIAfmyllm',
+                'id': 'vKInpacll2pC',
                 'ext': 'mp4',
                 'title': 'Uncovering a Universal Knowledge',
                 'description': 'md5:1a89148475bf931b3661fcd6ddb2ae3a',
@@ -85,7 +88,7 @@ class NationalGeographicChannelIE(ThePlatformIE):
             'url': 'http://channel.nationalgeographic.com/wild/destination-wild/videos/the-stunning-red-bird-of-paradise/',
             'md5': 'c4912f656b4cbe58f3e000c489360989',
             'info_dict': {
-                'id': '3TmMv9OvGwIR',
+                'id': 'Pok5lWCkiEFA',
                 'ext': 'mp4',
                 'title': 'The Stunning Red Bird of Paradise',
                 'description': 'md5:7bc8cd1da29686be4d17ad1230f0140c',
@@ -95,6 +98,10 @@ class NationalGeographicChannelIE(ThePlatformIE):
             },
             'add_ie': ['ThePlatform'],
         },
+        {
+            'url': 'http://channel.nationalgeographic.com/the-story-of-god-with-morgan-freeman/episodes/the-power-of-miracles/',
+            'only_matching': True,
+        }
     ]
 
     def _real_extract(self, url):
@@ -112,7 +119,7 @@ class NationalGeographicChannelIE(ThePlatformIE):
             auth_resource_id = self._search_regex(
                 r"video_auth_resourceId\s*=\s*'([^']+)'",
                 webpage, 'auth resource id')
-            query['auth'] = self._extract_mvpd_auth(url, display_id, 'natgeo', auth_resource_id) or ''
+            query['auth'] = self._extract_mvpd_auth(url, display_id, 'natgeo', auth_resource_id)
 
         return {
             '_type': 'url_transparent',
@@ -122,3 +129,40 @@ class NationalGeographicChannelIE(ThePlatformIE):
                 {'force_smil_url': True}),
             'display_id': display_id,
         }
+
+
+class NationalGeographicEpisodeGuideIE(InfoExtractor):
+    IE_NAME = 'natgeo:episodeguide'
+    _VALID_URL = r'https?://channel\.nationalgeographic\.com/(?:wild/)?(?P<id>[^/]+)/episode-guide'
+    _TESTS = [
+        {
+            'url': 'http://channel.nationalgeographic.com/the-story-of-god-with-morgan-freeman/episode-guide/',
+            'info_dict': {
+                'id': 'the-story-of-god-with-morgan-freeman-season-1',
+                'title': 'The Story of God with Morgan Freeman - Season 1',
+            },
+            'playlist_mincount': 6,
+        },
+        {
+            'url': 'http://channel.nationalgeographic.com/underworld-inc/episode-guide/?s=2',
+            'info_dict': {
+                'id': 'underworld-inc-season-2',
+                'title': 'Underworld, Inc. - Season 2',
+            },
+            'playlist_mincount': 7,
+        },
+    ]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        show = get_element_by_class('show', webpage)
+        selected_season = self._search_regex(
+            r'<div[^>]+class="select-seasons[^"]*".*?<a[^>]*>(.*?)</a>',
+            webpage, 'selected season')
+        entries = [
+            self.url_result(self._proto_relative_url(entry_url), 'NationalGeographic')
+            for entry_url in re.findall('(?s)<div[^>]+class="col-inner"[^>]*?>.*?<a[^>]+href="([^"]+)"', webpage)]
+        return self.playlist_result(
+            entries, '%s-%s' % (display_id, selected_season.lower().replace(' ', '-')),
+            '%s - %s' % (show, selected_season))

youtube_dl/extractor/naver.py

@@ -4,12 +4,10 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import (
-    compat_urllib_parse_urlencode,
-    compat_urlparse,
-)
 from ..utils import (
     ExtractorError,
+    int_or_none,
+    update_url_query,
 )
 
 
@@ -51,48 +49,74 @@ class NaverIE(InfoExtractor):
             if error:
                 raise ExtractorError(error, expected=True)
             raise ExtractorError('couldn\'t extract vid and key')
-        vid = m_id.group(1)
-        key = m_id.group(2)
-        query = compat_urllib_parse_urlencode({'vid': vid, 'inKey': key, })
-        query_urls = compat_urllib_parse_urlencode({
-            'masterVid': vid,
-            'protocol': 'p2p',
-            'inKey': key,
-        })
-        info = self._download_xml(
-            'http://serviceapi.rmcnmv.naver.com/flash/videoInfo.nhn?' + query,
-            video_id, 'Downloading video info')
-        urls = self._download_xml(
-            'http://serviceapi.rmcnmv.naver.com/flash/playableEncodingOption.nhn?' + query_urls,
-            video_id, 'Downloading video formats info')
-
+        video_data = self._download_json(
+            'http://play.rmcnmv.naver.com/vod/play/v2.0/' + m_id.group(1),
+            video_id, query={
+                'key': m_id.group(2),
+            })
+        meta = video_data['meta']
+        title = meta['subject']
         formats = []
-        for format_el in urls.findall('EncodingOptions/EncodingOption'):
-            domain = format_el.find('Domain').text
-            uri = format_el.find('uri').text
-            f = {
-                'url': compat_urlparse.urljoin(domain, uri),
-                'ext': 'mp4',
-                'width': int(format_el.find('width').text),
-                'height': int(format_el.find('height').text),
-            }
-            if domain.startswith('rtmp'):
-                # urlparse does not support custom schemes
-                # https://bugs.python.org/issue18828
-                f.update({
-                    'url': domain + uri,
-                    'ext': 'flv',
-                    'rtmp_protocol': '1',  # rtmpt
+
+        def extract_formats(streams, stream_type, query={}):
+            for stream in streams:
+                stream_url = stream.get('source')
+                if not stream_url:
+                    continue
+                stream_url = update_url_query(stream_url, query)
+                encoding_option = stream.get('encodingOption', {})
+                bitrate = stream.get('bitrate', {})
+                formats.append({
+                    'format_id': '%s_%s' % (stream.get('type') or stream_type, encoding_option.get('id') or encoding_option.get('name')),
+                    'url': stream_url,
+                    'width': int_or_none(encoding_option.get('width')),
+                    'height': int_or_none(encoding_option.get('height')),
+                    'vbr': int_or_none(bitrate.get('video')),
+                    'abr': int_or_none(bitrate.get('audio')),
+                    'filesize': int_or_none(stream.get('size')),
+                    'protocol': 'm3u8_native' if stream_type == 'HLS' else None,
                 })
-            formats.append(f)
+
+        extract_formats(video_data.get('videos', {}).get('list', []), 'H264')
+        for stream_set in video_data.get('streams', []):
+            query = {}
+            for param in stream_set.get('keys', []):
+                query[param['name']] = param['value']
+            stream_type = stream_set.get('type')
+            videos = stream_set.get('videos')
+            if videos:
+                extract_formats(videos, stream_type, query)
+            elif stream_type == 'HLS':
+                stream_url = stream_set.get('source')
+                if not stream_url:
+                    continue
+                formats.extend(self._extract_m3u8_formats(
+                    update_url_query(stream_url, query), video_id,
+                    'mp4', 'm3u8_native', m3u8_id=stream_type, fatal=False))
         self._sort_formats(formats)
 
+        subtitles = {}
+        for caption in video_data.get('captions', {}).get('list', []):
+            caption_url = caption.get('source')
+            if not caption_url:
+                continue
+            subtitles.setdefault(caption.get('language') or caption.get('locale'), []).append({
+                'url': caption_url,
+            })
+
+        upload_date = self._search_regex(
+            r'<span[^>]+class="date".*?(\d{4}\.\d{2}\.\d{2})',
+            webpage, 'upload date', fatal=False)
+        if upload_date:
+            upload_date = upload_date.replace('.', '')
+
         return {
             'id': video_id,
-            'title': info.find('Subject').text,
+            'title': title,
             'formats': formats,
+            'subtitles': subtitles,
             'description': self._og_search_description(webpage),
-            'thumbnail': self._og_search_thumbnail(webpage),
-            'upload_date': info.find('WriteDate').text.replace('.', ''),
-            'view_count': int(info.find('PlayCount').text),
+            'thumbnail': meta.get('cover', {}).get('source') or self._og_search_thumbnail(webpage),
+            'view_count': int_or_none(meta.get('count')),
+            'upload_date': upload_date,
         }