release 2013.03.24

Add initial sphinx docs

MANIFEST.in

@@ -3,3 +3,5 @@ include test/*.py
 include test/*.json
 include youtube-dl.bash-completion
 include youtube-dl.1
+recursive-include docs *
+prune docs/_build

README.md

@@ -20,7 +20,7 @@ which means you can modify it, redistribute it or use it however you like.
                                      sure that you have sufficient permissions
                                      (run with sudo if needed)
     -i, --ignore-errors              continue on download errors, for example to
-                                     to skip unavailable videos in a playlist
+                                     skip unavailable videos in a playlist
     --abort-on-error                 Abort downloading of further videos (in the
                                      playlist or the command line) if an error
                                      occurs
@@ -36,6 +36,9 @@ which means you can modify it, redistribute it or use it however you like.
                                      an empty string (--proxy "") for direct
                                      connection
     --no-check-certificate           Suppress HTTPS certificate validation.
+    --prefer-insecure                Use an unencrypted connection to retrieve
+                                     information about the video. (Currently
+                                     supported only for YouTube)
     --cache-dir DIR                  Location in the filesystem where youtube-dl
                                      can store some downloaded information
                                      permanently. By default $XDG_CACHE_HOME
@@ -124,8 +127,12 @@ which means you can modify it, redistribute it or use it however you like.
                                      video id, %(playlist)s for the playlist the
                                      video is in, %(playlist_index)s for the
                                      position in the playlist and %% for a
-                                     literal percent. Use - to output to stdout.
-                                     Can also be used to download to a different
+                                     literal percent. %(height)s and %(width)s
+                                     for the width and height of the video
+                                     format. %(resolution)s for a textual
+                                     description of the resolution of the video
+                                     format. Use - to output to stdout. Can also
+                                     be used to download to a different
                                      directory, for example with -o '/my/downloa
                                      ds/%(uploader)s/%(title)s-%(id)s.%(ext)s' .
     --autonumber-size NUMBER         Specifies the number of digits in
@@ -187,9 +194,9 @@ which means you can modify it, redistribute it or use it however you like.
                                      preference using slashes: "-f 22/17/18".
                                      "-f mp4" and "-f flv" are also supported.
                                      You can also use the special names "best",
-                                     "bestaudio", "worst", and "worstaudio". By
-                                     default, youtube-dl will pick the best
-                                     quality.
+                                     "bestvideo", "bestaudio", "worst",
+                                     "worstvideo" and "worstaudio". By default,
+                                     youtube-dl will pick the best quality.
     --all-formats                    download all available video formats
     --prefer-free-formats            prefer free video formats unless a specific
                                      one is requested
@@ -246,7 +253,7 @@ which means you can modify it, redistribute it or use it however you like.
 
 # CONFIGURATION
 
-You can configure youtube-dl by placing default arguments (such as `--extract-audio --no-mtime` to always extract the audio and not copy the mtime) into `/etc/youtube-dl.conf` and/or `~/.config/youtube-dl.conf`. On Windows, the configuration file locations are `%APPDATA%\youtube-dl\config.txt` and `C:\Users\<Yourname>\youtube-dl.conf`.
+You can configure youtube-dl by placing default arguments (such as `--extract-audio --no-mtime` to always extract the audio and not copy the mtime) into `/etc/youtube-dl.conf` and/or `~/.config/youtube-dl/config`. On Windows, the configuration file locations are `%APPDATA%\youtube-dl\config.txt` and `C:\Users\<Yourname>\youtube-dl.conf`.
 
 # OUTPUT TEMPLATE
 
@@ -281,12 +288,14 @@ Videos can be filtered by their upload date using the options `--date`, `--dateb
  
 Examples:
 
-  $ # Download only the videos uploaded in the last 6 months
-	$ youtube-dl --dateafter now-6months
-  $ # Download only the videos uploaded on January 1, 1970
-	$ youtube-dl --date 19700101
-  $ # will only download the videos uploaded in the 200x decade
-	$ youtube-dl --dateafter 20000101 --datebefore 20091231
+    # Download only the videos uploaded in the last 6 months
+    $ youtube-dl --dateafter now-6months
+
+    # Download only the videos uploaded on January 1, 1970
+    $ youtube-dl --date 19700101
+
+    $ # will only download the videos uploaded in the 200x decade
+    $ youtube-dl --dateafter 20000101 --datebefore 20091231
 
 # FAQ
 
@@ -355,7 +364,7 @@ If you want to create a build of youtube-dl yourself, you'll need
 
 ### Adding support for a new site
 
-If you want to add support for a new site, copy *any* [recently modified](https://github.com/rg3/youtube-dl/commits/master/youtube_dl/extractor) file in `youtube_dl/extractor`, add an import in [`youtube_dl/extractor/__init__.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/__init__.py). Have a look at [`youtube_dl/common/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L38). Don't forget to run the tests with `python test/test_download.py Test_Download.test_YourExtractor`! For a detailed tutorial, refer to [this blog post](http://filippo.io/add-support-for-a-new-video-site-to-youtube-dl/).
+If you want to add support for a new site, copy *any* [recently modified](https://github.com/rg3/youtube-dl/commits/master/youtube_dl/extractor) file in `youtube_dl/extractor`, add an import in [`youtube_dl/extractor/__init__.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/__init__.py). Have a look at [`youtube_dl/common/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L38). Don't forget to run the tests with `python test/test_download.py TestDownload.test_YourExtractor`! For a detailed tutorial, refer to [this blog post](http://filippo.io/add-support-for-a-new-video-site-to-youtube-dl/).
 
 # BUGS
 

devscripts/release.sh

@@ -14,9 +14,9 @@
 
 set -e
 
-skip_tests=false
-if [ "$1" = '--skip-test' ]; then
-    skip_tests=true
+skip_tests=true
+if [ "$1" = '--run-tests' ]; then
+    skip_tests=false
     shift
 fi
 
@@ -70,7 +70,7 @@ RELEASE_FILES="youtube-dl youtube-dl.exe youtube-dl-$version.tar.gz"
 git checkout HEAD -- youtube-dl youtube-dl.exe
 
 /bin/echo -e "\n### Signing and uploading the new binaries to yt-dl.org ..."
-for f in $RELEASE_FILES; do gpg --detach-sig "build/$version/$f"; done
+for f in $RELEASE_FILES; do gpg --passphrase-repeat 5 --detach-sig "build/$version/$f"; done
 scp -r "build/$version" ytdl@yt-dl.org:html/tmp/
 ssh ytdl@yt-dl.org "mv html/tmp/$version html/downloads/"
 ssh ytdl@yt-dl.org "sh html/update_latest.sh $version"
@@ -97,7 +97,7 @@ rm -rf build
 
 make pypi-files
 echo "Uploading to PyPi ..."
-python setup.py sdist upload
+python setup.py sdist bdist_wheel upload
 make clean
 
 /bin/echo -e "\n### DONE!"

docs/.gitignore

@@ -0,0 +1 @@
+_build/

docs/Makefile

@@ -0,0 +1,177 @@
+# Makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line.
+SPHINXOPTS    =
+SPHINXBUILD   = sphinx-build
+PAPER         =
+BUILDDIR      = _build
+
+# User-friendly check for sphinx-build
+ifeq ($(shell which $(SPHINXBUILD) >/dev/null 2>&1; echo $$?), 1)
+$(error The '$(SPHINXBUILD)' command was not found. Make sure you have Sphinx installed, then set the SPHINXBUILD environment variable to point to the full path of the '$(SPHINXBUILD)' executable. Alternatively you can add the directory with the executable to your PATH. If you don't have Sphinx installed, grab it from http://sphinx-doc.org/)
+endif
+
+# Internal variables.
+PAPEROPT_a4     = -D latex_paper_size=a4
+PAPEROPT_letter = -D latex_paper_size=letter
+ALLSPHINXOPTS   = -d $(BUILDDIR)/doctrees $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) .
+# the i18n builder cannot share the environment and doctrees with the others
+I18NSPHINXOPTS  = $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) .
+
+.PHONY: help clean html dirhtml singlehtml pickle json htmlhelp qthelp devhelp epub latex latexpdf text man changes linkcheck doctest gettext
+
+help:
+	@echo "Please use \`make <target>' where <target> is one of"
+	@echo "  html       to make standalone HTML files"
+	@echo "  dirhtml    to make HTML files named index.html in directories"
+	@echo "  singlehtml to make a single large HTML file"
+	@echo "  pickle     to make pickle files"
+	@echo "  json       to make JSON files"
+	@echo "  htmlhelp   to make HTML files and a HTML help project"
+	@echo "  qthelp     to make HTML files and a qthelp project"
+	@echo "  devhelp    to make HTML files and a Devhelp project"
+	@echo "  epub       to make an epub"
+	@echo "  latex      to make LaTeX files, you can set PAPER=a4 or PAPER=letter"
+	@echo "  latexpdf   to make LaTeX files and run them through pdflatex"
+	@echo "  latexpdfja to make LaTeX files and run them through platex/dvipdfmx"
+	@echo "  text       to make text files"
+	@echo "  man        to make manual pages"
+	@echo "  texinfo    to make Texinfo files"
+	@echo "  info       to make Texinfo files and run them through makeinfo"
+	@echo "  gettext    to make PO message catalogs"
+	@echo "  changes    to make an overview of all changed/added/deprecated items"
+	@echo "  xml        to make Docutils-native XML files"
+	@echo "  pseudoxml  to make pseudoxml-XML files for display purposes"
+	@echo "  linkcheck  to check all external links for integrity"
+	@echo "  doctest    to run all doctests embedded in the documentation (if enabled)"
+
+clean:
+	rm -rf $(BUILDDIR)/*
+
+html:
+	$(SPHINXBUILD) -b html $(ALLSPHINXOPTS) $(BUILDDIR)/html
+	@echo
+	@echo "Build finished. The HTML pages are in $(BUILDDIR)/html."
+
+dirhtml:
+	$(SPHINXBUILD) -b dirhtml $(ALLSPHINXOPTS) $(BUILDDIR)/dirhtml
+	@echo
+	@echo "Build finished. The HTML pages are in $(BUILDDIR)/dirhtml."
+
+singlehtml:
+	$(SPHINXBUILD) -b singlehtml $(ALLSPHINXOPTS) $(BUILDDIR)/singlehtml
+	@echo
+	@echo "Build finished. The HTML page is in $(BUILDDIR)/singlehtml."
+
+pickle:
+	$(SPHINXBUILD) -b pickle $(ALLSPHINXOPTS) $(BUILDDIR)/pickle
+	@echo
+	@echo "Build finished; now you can process the pickle files."
+
+json:
+	$(SPHINXBUILD) -b json $(ALLSPHINXOPTS) $(BUILDDIR)/json
+	@echo
+	@echo "Build finished; now you can process the JSON files."
+
+htmlhelp:
+	$(SPHINXBUILD) -b htmlhelp $(ALLSPHINXOPTS) $(BUILDDIR)/htmlhelp
+	@echo
+	@echo "Build finished; now you can run HTML Help Workshop with the" \
+	      ".hhp project file in $(BUILDDIR)/htmlhelp."
+
+qthelp:
+	$(SPHINXBUILD) -b qthelp $(ALLSPHINXOPTS) $(BUILDDIR)/qthelp
+	@echo
+	@echo "Build finished; now you can run "qcollectiongenerator" with the" \
+	      ".qhcp project file in $(BUILDDIR)/qthelp, like this:"
+	@echo "# qcollectiongenerator $(BUILDDIR)/qthelp/youtube-dl.qhcp"
+	@echo "To view the help file:"
+	@echo "# assistant -collectionFile $(BUILDDIR)/qthelp/youtube-dl.qhc"
+
+devhelp:
+	$(SPHINXBUILD) -b devhelp $(ALLSPHINXOPTS) $(BUILDDIR)/devhelp
+	@echo
+	@echo "Build finished."
+	@echo "To view the help file:"
+	@echo "# mkdir -p $$HOME/.local/share/devhelp/youtube-dl"
+	@echo "# ln -s $(BUILDDIR)/devhelp $$HOME/.local/share/devhelp/youtube-dl"
+	@echo "# devhelp"
+
+epub:
+	$(SPHINXBUILD) -b epub $(ALLSPHINXOPTS) $(BUILDDIR)/epub
+	@echo
+	@echo "Build finished. The epub file is in $(BUILDDIR)/epub."
+
+latex:
+	$(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex
+	@echo
+	@echo "Build finished; the LaTeX files are in $(BUILDDIR)/latex."
+	@echo "Run \`make' in that directory to run these through (pdf)latex" \
+	      "(use \`make latexpdf' here to do that automatically)."
+
+latexpdf:
+	$(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex
+	@echo "Running LaTeX files through pdflatex..."
+	$(MAKE) -C $(BUILDDIR)/latex all-pdf
+	@echo "pdflatex finished; the PDF files are in $(BUILDDIR)/latex."
+
+latexpdfja:
+	$(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex
+	@echo "Running LaTeX files through platex and dvipdfmx..."
+	$(MAKE) -C $(BUILDDIR)/latex all-pdf-ja
+	@echo "pdflatex finished; the PDF files are in $(BUILDDIR)/latex."
+
+text:
+	$(SPHINXBUILD) -b text $(ALLSPHINXOPTS) $(BUILDDIR)/text
+	@echo
+	@echo "Build finished. The text files are in $(BUILDDIR)/text."
+
+man:
+	$(SPHINXBUILD) -b man $(ALLSPHINXOPTS) $(BUILDDIR)/man
+	@echo
+	@echo "Build finished. The manual pages are in $(BUILDDIR)/man."
+
+texinfo:
+	$(SPHINXBUILD) -b texinfo $(ALLSPHINXOPTS) $(BUILDDIR)/texinfo
+	@echo
+	@echo "Build finished. The Texinfo files are in $(BUILDDIR)/texinfo."
+	@echo "Run \`make' in that directory to run these through makeinfo" \
+	      "(use \`make info' here to do that automatically)."
+
+info:
+	$(SPHINXBUILD) -b texinfo $(ALLSPHINXOPTS) $(BUILDDIR)/texinfo
+	@echo "Running Texinfo files through makeinfo..."
+	make -C $(BUILDDIR)/texinfo info
+	@echo "makeinfo finished; the Info files are in $(BUILDDIR)/texinfo."
+
+gettext:
+	$(SPHINXBUILD) -b gettext $(I18NSPHINXOPTS) $(BUILDDIR)/locale
+	@echo
+	@echo "Build finished. The message catalogs are in $(BUILDDIR)/locale."
+
+changes:
+	$(SPHINXBUILD) -b changes $(ALLSPHINXOPTS) $(BUILDDIR)/changes
+	@echo
+	@echo "The overview file is in $(BUILDDIR)/changes."
+
+linkcheck:
+	$(SPHINXBUILD) -b linkcheck $(ALLSPHINXOPTS) $(BUILDDIR)/linkcheck
+	@echo
+	@echo "Link check complete; look for any errors in the above output " \
+	      "or in $(BUILDDIR)/linkcheck/output.txt."
+
+doctest:
+	$(SPHINXBUILD) -b doctest $(ALLSPHINXOPTS) $(BUILDDIR)/doctest
+	@echo "Testing of doctests in the sources finished, look at the " \
+	      "results in $(BUILDDIR)/doctest/output.txt."
+
+xml:
+	$(SPHINXBUILD) -b xml $(ALLSPHINXOPTS) $(BUILDDIR)/xml
+	@echo
+	@echo "Build finished. The XML files are in $(BUILDDIR)/xml."
+
+pseudoxml:
+	$(SPHINXBUILD) -b pseudoxml $(ALLSPHINXOPTS) $(BUILDDIR)/pseudoxml
+	@echo
+	@echo "Build finished. The pseudo-XML files are in $(BUILDDIR)/pseudoxml."

docs/conf.py

@@ -0,0 +1,71 @@
+# -*- coding: utf-8 -*-
+#
+# youtube-dl documentation build configuration file, created by
+# sphinx-quickstart on Fri Mar 14 21:05:43 2014.
+#
+# This file is execfile()d with the current directory set to its
+# containing dir.
+#
+# Note that not all possible configuration values are present in this
+# autogenerated file.
+#
+# All configuration values have a default; values that are commented out
+# serve to show the default.
+
+import sys
+import os
+# Allows to import youtube_dl
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+# -- General configuration ------------------------------------------------
+
+# Add any Sphinx extension module names here, as strings. They can be
+# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
+# ones.
+extensions = [
+    'sphinx.ext.autodoc',
+]
+
+# Add any paths that contain templates here, relative to this directory.
+templates_path = ['_templates']
+
+# The suffix of source filenames.
+source_suffix = '.rst'
+
+# The master toctree document.
+master_doc = 'index'
+
+# General information about the project.
+project = u'youtube-dl'
+copyright = u'2014, Ricardo Garcia Gonzalez'
+
+# The version info for the project you're documenting, acts as replacement for
+# |version| and |release|, also used in various other places throughout the
+# built documents.
+#
+# The short X.Y version.
+import youtube_dl
+version = youtube_dl.__version__
+# The full version, including alpha/beta/rc tags.
+release = version
+
+# List of patterns, relative to source directory, that match files and
+# directories to ignore when looking for source files.
+exclude_patterns = ['_build']
+
+# The name of the Pygments (syntax highlighting) style to use.
+pygments_style = 'sphinx'
+
+# -- Options for HTML output ----------------------------------------------
+
+# The theme to use for HTML and HTML Help pages.  See the documentation for
+# a list of builtin themes.
+html_theme = 'default'
+
+# Add any paths that contain custom static files (such as style sheets) here,
+# relative to this directory. They are copied after the builtin static files,
+# so a file named "default.css" will overwrite the builtin "default.css".
+html_static_path = ['_static']
+
+# Output file base name for HTML help builder.
+htmlhelp_basename = 'youtube-dldoc'

docs/index.rst

@@ -0,0 +1,23 @@
+Welcome to youtube-dl's documentation!
+======================================
+
+*youtube-dl* is a command-line program to download videos from YouTube.com and more sites.
+It can also be used in Python code.
+
+Developer guide
+---------------
+
+This section contains information for using *youtube-dl* from Python programs.
+
+.. toctree::
+    :maxdepth: 2
+
+    module_guide
+
+Indices and tables
+==================
+
+* :ref:`genindex`
+* :ref:`modindex`
+* :ref:`search`
+

docs/module_guide.rst

@@ -0,0 +1,67 @@
+Using the ``youtube_dl`` module
+===============================
+
+When using the ``youtube_dl`` module, you start by creating an instance of :class:`YoutubeDL` and adding all the available extractors:
+
+.. code-block:: python
+
+    >>> from youtube_dl import YoutubeDL
+    >>> ydl = YoutubeDL()
+    >>> ydl.add_default_info_extractors()
+
+Extracting video information
+----------------------------
+
+You use the :meth:`YoutubeDL.extract_info` method for getting the video information, which returns a dictionary:
+
+.. code-block:: python
+
+    >>> info = ydl.extract_info('http://www.youtube.com/watch?v=BaW_jenozKc', download=False)
+    [youtube] Setting language
+    [youtube] BaW_jenozKc: Downloading webpage
+    [youtube] BaW_jenozKc: Downloading video info webpage
+    [youtube] BaW_jenozKc: Extracting video information
+    >>> info['title']
+    'youtube-dl test video "\'/\\ä↭𝕐'
+    >>> info['height'], info['width']
+    (720, 1280)
+
+If you want to download or play the video you can get its url:
+
+.. code-block:: python
+
+    >>> info['url']
+    'https://...'
+
+Extracting playlist information
+-------------------------------
+
+The playlist information is extracted in a similar way, but the dictionary is a bit different:
+
+.. code-block:: python
+
+    >>> playlist = ydl.extract_info('http://www.ted.com/playlists/13/open_source_open_world', download=False)
+    [TED] open_source_open_world: Downloading playlist webpage
+    ...
+    >>> playlist['title']
+    'Open-source, open world'
+
+
+
+You can access the videos in the playlist with the ``entries`` field:
+
+.. code-block:: python
+
+    >>> for video in playlist['entries']:
+    ...     print('Video #%d: %s' % (video['playlist_index'], video['title']))
+
+    Video #1: How Arduino is open-sourcing imagination
+    Video #2: The year open data went worldwide
+    Video #3: Massive-scale online collaboration
+    Video #4: The art of asking
+    Video #5: How cognitive surplus will change the world
+    Video #6: The birth of Wikipedia
+    Video #7: Coding a better government
+    Video #8: The era of open innovation
+    Video #9: The currency of the new economy is trust
+

setup.cfg

@@ -0,0 +1,2 @@
+[wheel]
+universal = True

test/helper.py

@@ -9,7 +9,10 @@ import sys
 
 import youtube_dl.extractor
 from youtube_dl import YoutubeDL
-from youtube_dl.utils import preferredencoding
+from youtube_dl.utils import (
+    compat_str,
+    preferredencoding,
+)
 
 
 def get_params(override=None):
@@ -71,7 +74,7 @@ class FakeYDL(YoutubeDL):
             old_report_warning(message)
         self.report_warning = types.MethodType(report_warning, self)
 
-def get_testcases():
+def gettestcases():
     for ie in youtube_dl.extractor.gen_extractors():
         t = getattr(ie, '_TEST', None)
         if t:
@@ -83,3 +86,45 @@ def get_testcases():
 
 
 md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest()
+
+
+def expect_info_dict(self, expected_dict, got_dict):
+    for info_field, expected in expected_dict.items():
+        if isinstance(expected, compat_str) and expected.startswith('re:'):
+            got = got_dict.get(info_field)
+            match_str = expected[len('re:'):]
+            match_rex = re.compile(match_str)
+
+            self.assertTrue(
+                isinstance(got, compat_str) and match_rex.match(got),
+                u'field %s (value: %r) should match %r' % (info_field, got, match_str))
+        elif isinstance(expected, type):
+            got = got_dict.get(info_field)
+            self.assertTrue(isinstance(got, expected),
+                u'Expected type %r, but got value %r of type %r' % (expected, got, type(got)))
+        else:
+            if isinstance(expected, compat_str) and expected.startswith('md5:'):
+                got = 'md5:' + md5(got_dict.get(info_field))
+            else:
+                got = got_dict.get(info_field)
+            self.assertEqual(expected, got,
+                u'invalid value for field %s, expected %r, got %r' % (info_field, expected, got))
+
+    # Check for the presence of mandatory fields
+    for key in ('id', 'url', 'title', 'ext'):
+        self.assertTrue(got_dict.get(key), 'Missing mandatory field %s' % key)
+    # Check for mandatory fields that are automatically set by YoutubeDL
+    for key in ['webpage_url', 'extractor', 'extractor_key']:
+        self.assertTrue(got_dict.get(key), u'Missing field: %s' % key)
+
+    # Are checkable fields missing from the test case definition?
+    test_info_dict = dict((key, value if not isinstance(value, compat_str) or len(value) < 250 else 'md5:' + md5(value))
+        for key, value in got_dict.items()
+        if value and key in ('title', 'description', 'uploader', 'upload_date', 'timestamp', 'uploader_id', 'location'))
+    missing_keys = set(test_info_dict.keys()) - set(expected_dict.keys())
+    if missing_keys:
+        sys.stderr.write(u'\n"info_dict": ' + json.dumps(test_info_dict, ensure_ascii=False, indent=4) + u'\n')
+        self.assertFalse(
+            missing_keys,
+            'Missing keys in test definition: %s' % (
+                ', '.join(sorted(missing_keys))))

test/test_InfoExtractor.py

@@ -0,0 +1,44 @@
+#!/usr/bin/env python
+
+from __future__ import unicode_literals
+
+# Allow direct execution
+import os
+import sys
+import unittest
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from test.helper import FakeYDL
+from youtube_dl.extractor.common import InfoExtractor
+from youtube_dl.extractor import YoutubeIE, get_info_extractor
+
+
+class TestIE(InfoExtractor):
+    pass
+
+
+class TestInfoExtractor(unittest.TestCase):
+    def setUp(self):
+        self.ie = TestIE(FakeYDL())
+
+    def test_ie_key(self):
+        self.assertEqual(get_info_extractor(YoutubeIE.ie_key()), YoutubeIE)
+
+    def test_html_search_regex(self):
+        html = '<p id="foo">Watch this <a href="http://www.youtube.com/watch?v=BaW_jenozKc">video</a></p>'
+        search = lambda re, *args: self.ie._html_search_regex(re, html, *args)
+        self.assertEqual(search(r'<p id="foo">(.+?)</p>', 'foo'), 'Watch this video')
+
+    def test_opengraph(self):
+        ie = self.ie
+        html = '''
+            <meta name="og:title" content='Foo'/>
+            <meta content="Some video's description " name="og:description"/>
+            <meta property='og:image' content='http://domain.com/pic.jpg?key1=val1&amp;key2=val2'/>
+            '''
+        self.assertEqual(ie._og_search_title(html), 'Foo')
+        self.assertEqual(ie._og_search_description(html), 'Some video\'s description ')
+        self.assertEqual(ie._og_search_thumbnail(html), 'http://domain.com/pic.jpg?key1=val1&key2=val2')
+
+if __name__ == '__main__':
+    unittest.main()

test/test_YoutubeDL.py

@@ -182,6 +182,24 @@ class TestFormatSelection(unittest.TestCase):
         downloaded = ydl.downloaded_info_dicts[0]
         self.assertEqual(downloaded['format_id'], 'vid-high')
 
+    def test_format_selection_video(self):
+        formats = [
+            {'format_id': 'dash-video-low', 'ext': 'mp4', 'preference': 1, 'acodec': 'none'},
+            {'format_id': 'dash-video-high', 'ext': 'mp4', 'preference': 2, 'acodec': 'none'},
+            {'format_id': 'vid', 'ext': 'mp4', 'preference': 3},
+        ]
+        info_dict = {'formats': formats, 'extractor': 'test'}
+
+        ydl = YDL({'format': 'bestvideo'})
+        ydl.process_ie_result(info_dict.copy())
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'dash-video-high')
+
+        ydl = YDL({'format': 'worstvideo'})
+        ydl.process_ie_result(info_dict.copy())
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'dash-video-low')
+
     def test_youtube_format_selection(self):
         order = [
             '38', '37', '46', '22', '45', '35', '44', '18', '34', '43', '6', '5', '36', '17', '13',

test/test_all_urls.py

@@ -1,5 +1,7 @@
 #!/usr/bin/env python
 
+from __future__ import unicode_literals
+
 # Allow direct execution
 import os
 import sys
@@ -7,12 +9,13 @@ import unittest
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 
-from test.helper import get_testcases
+from test.helper import gettestcases
 
 from youtube_dl.extractor import (
     FacebookIE,
     gen_extractors,
     JustinTVIE,
+    PBSIE,
     YoutubeIE,
 )
 
@@ -29,18 +32,20 @@ class TestAllURLsMatching(unittest.TestCase):
 
     def test_youtube_playlist_matching(self):
         assertPlaylist = lambda url: self.assertMatch(url, ['youtube:playlist'])
-        assertPlaylist(u'ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
-        assertPlaylist(u'UUBABnxM4Ar9ten8Mdjj1j0Q') #585
-        assertPlaylist(u'PL63F0C78739B09958')
-        assertPlaylist(u'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q')
-        assertPlaylist(u'https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
-        assertPlaylist(u'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')
-        assertPlaylist(u'https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012') #668
-        self.assertFalse('youtube:playlist' in self.matching_ies(u'PLtS2H6bU1M'))
+        assertPlaylist('ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
+        assertPlaylist('UUBABnxM4Ar9ten8Mdjj1j0Q') #585
+        assertPlaylist('PL63F0C78739B09958')
+        assertPlaylist('https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q')
+        assertPlaylist('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
+        assertPlaylist('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')
+        assertPlaylist('https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012') #668
+        self.assertFalse('youtube:playlist' in self.matching_ies('PLtS2H6bU1M'))
+        # Top tracks
+        assertPlaylist('https://www.youtube.com/playlist?list=MCUS.20142101')
 
     def test_youtube_matching(self):
-        self.assertTrue(YoutubeIE.suitable(u'PLtS2H6bU1M'))
-        self.assertFalse(YoutubeIE.suitable(u'https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012')) #668
+        self.assertTrue(YoutubeIE.suitable('PLtS2H6bU1M'))
+        self.assertFalse(YoutubeIE.suitable('https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012')) #668
         self.assertMatch('http://youtu.be/BaW_jenozKc', ['youtube'])
         self.assertMatch('http://www.youtube.com/v/BaW_jenozKc', ['youtube'])
         self.assertMatch('https://youtube.googleapis.com/v/BaW_jenozKc', ['youtube'])
@@ -63,6 +68,13 @@ class TestAllURLsMatching(unittest.TestCase):
     def test_youtube_show_matching(self):
         self.assertMatch('http://www.youtube.com/show/airdisasters', ['youtube:show'])
 
+    def test_youtube_truncated(self):
+        self.assertMatch('http://www.youtube.com/watch?', ['youtube:truncated_url'])
+
+    def test_youtube_search_matching(self):
+        self.assertMatch('http://www.youtube.com/results?search_query=making+mustard', ['youtube:search_url'])
+        self.assertMatch('https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', ['youtube:search_url'])
+
     def test_justin_tv_channelid_matching(self):
         self.assertTrue(JustinTVIE.suitable(u"justin.tv/vanillatv"))
         self.assertTrue(JustinTVIE.suitable(u"twitch.tv/vanillatv"))
@@ -80,7 +92,7 @@ class TestAllURLsMatching(unittest.TestCase):
         self.assertTrue(JustinTVIE.suitable(u"http://www.twitch.tv/tsm_theoddone/c/2349361"))
 
     def test_youtube_extract(self):
-        assertExtractId = lambda url, id: self.assertEqual(YoutubeIE()._extract_id(url), id)
+        assertExtractId = lambda url, id: self.assertEqual(YoutubeIE.extract_id(url), id)
         assertExtractId('http://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
         assertExtractId('https://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
         assertExtractId('https://www.youtube.com/watch?feature=player_embedded&v=BaW_jenozKc', 'BaW_jenozKc')
@@ -89,11 +101,11 @@ class TestAllURLsMatching(unittest.TestCase):
         assertExtractId('BaW_jenozKc', 'BaW_jenozKc')
 
     def test_facebook_matching(self):
-        self.assertTrue(FacebookIE.suitable(u'https://www.facebook.com/Shiniknoh#!/photo.php?v=10153317450565268'))
+        self.assertTrue(FacebookIE.suitable('https://www.facebook.com/Shiniknoh#!/photo.php?v=10153317450565268'))
 
     def test_no_duplicates(self):
         ies = gen_extractors()
-        for tc in get_testcases():
+        for tc in gettestcases():
             url = tc['url']
             for ie in ies:
                 if type(ie).__name__ in ('GenericIE', tc['name'] + 'IE'):
@@ -112,6 +124,8 @@ class TestAllURLsMatching(unittest.TestCase):
 
     def test_vimeo_matching(self):
         self.assertMatch('http://vimeo.com/channels/tributes', ['vimeo:channel'])
+        self.assertMatch('http://vimeo.com/channels/31259', ['vimeo:channel'])
+        self.assertMatch('http://vimeo.com/channels/31259/53576664', ['vimeo'])
         self.assertMatch('http://vimeo.com/user7108434', ['vimeo:user'])
         self.assertMatch('http://vimeo.com/user7108434/videos', ['vimeo:user'])
         self.assertMatch('https://vimeo.com/user21297594/review/75524534/3c257a1b5d', ['vimeo:review'])
@@ -124,5 +138,10 @@ class TestAllURLsMatching(unittest.TestCase):
         self.assertMatch('http://tatianamaslanydaily.tumblr.com/post/54196191430/orphan-black-dvd-extra-behind-the-scenes', ['Tumblr'])
         self.assertMatch('http://tatianamaslanydaily.tumblr.com/post/54196191430', ['Tumblr'])
 
+    def test_pbs(self):
+        # https://github.com/rg3/youtube-dl/issues/2350
+        self.assertMatch('http://video.pbs.org/viralplayer/2365173446/', ['PBS'])
+        self.assertMatch('http://video.pbs.org/widget/partnerplayer/980042464/', ['PBS'])
+
 if __name__ == '__main__':
     unittest.main()

test/test_download.py

@@ -8,10 +8,11 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 from test.helper import (
     get_params,
-    get_testcases,
-    try_rm,
+    gettestcases,
+    expect_info_dict,
     md5,
-    report_warning
+    try_rm,
+    report_warning,
 )
 
 
@@ -50,7 +51,7 @@ def _file_md5(fn):
     with open(fn, 'rb') as f:
         return hashlib.md5(f.read()).hexdigest()
 
-defs = get_testcases()
+defs = gettestcases()
 
 
 class TestDownload(unittest.TestCase):
@@ -72,9 +73,7 @@ def generator(test_case):
         if 'playlist' not in test_case:
             info_dict = test_case.get('info_dict', {})
             if not test_case.get('file') and not (info_dict.get('id') and info_dict.get('ext')):
-                print_skipping('The output file cannot be know, the "file" '
-                    'key is missing or the info_dict is incomplete')
-                return
+                raise Exception('Test definition incorrect. The output file cannot be known. Are both \'id\' and \'ext\' keys present?')
         if 'skip' in test_case:
             print_skipping(test_case['skip'])
             return
@@ -136,27 +135,8 @@ def generator(test_case):
                     self.assertEqual(md5_for_file, tc['md5'])
                 with io.open(info_json_fn, encoding='utf-8') as infof:
                     info_dict = json.load(infof)
-                for (info_field, expected) in tc.get('info_dict', {}).items():
-                    if isinstance(expected, compat_str) and expected.startswith('md5:'):
-                        got = 'md5:' + md5(info_dict.get(info_field))
-                    else:
-                        got = info_dict.get(info_field)
-                    self.assertEqual(expected, got,
-                        u'invalid value for field %s, expected %r, got %r' % (info_field, expected, got))
 
-                # If checkable fields are missing from the test case, print the info_dict
-                test_info_dict = dict((key, value if not isinstance(value, compat_str) or len(value) < 250 else 'md5:' + md5(value))
-                    for key, value in info_dict.items()
-                    if value and key in ('title', 'description', 'uploader', 'upload_date', 'uploader_id', 'location'))
-                if not all(key in tc.get('info_dict', {}).keys() for key in test_info_dict.keys()):
-                    sys.stderr.write(u'\n"info_dict": ' + json.dumps(test_info_dict, ensure_ascii=False, indent=4) + u'\n')
-
-                # Check for the presence of mandatory fields
-                for key in ('id', 'url', 'title', 'ext'):
-                    self.assertTrue(key in info_dict.keys() and info_dict[key])
-                # Check for mandatory fields that are automatically set by YoutubeDL
-                for key in ['webpage_url', 'extractor', 'extractor_key']:
-                    self.assertTrue(info_dict.get(key), u'Missing field: %s' % key)
+                expect_info_dict(self, tc.get('info_dict', {}), info_dict)
         finally:
             try_rm_tcs_files()
 

test/test_playlists.py

@@ -9,8 +9,10 @@ import sys
 import unittest
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
-from test.helper import FakeYDL
-
+from test.helper import (
+    expect_info_dict,
+    FakeYDL,
+)
 
 from youtube_dl.extractor import (
     AcademicEarthCourseIE,
@@ -36,6 +38,10 @@ from youtube_dl.extractor import (
     RutubeChannelIE,
     GoogleSearchIE,
     GenericIE,
+    TEDIE,
+    ToypicsUserIE,
+    XTubeUserIE,
+    InstagramUserIE,
 )
 
 
@@ -55,10 +61,10 @@ class TestPlaylists(unittest.TestCase):
     def test_dailymotion_user(self):
         dl = FakeYDL()
         ie = DailymotionUserIE(dl)
-        result = ie.extract('http://www.dailymotion.com/user/generation-quoi/')
+        result = ie.extract('https://www.dailymotion.com/user/nqtv')
         self.assertIsPlaylist(result)
-        self.assertEqual(result['title'], 'Génération Quoi')
-        self.assertTrue(len(result['entries']) >= 26)
+        self.assertEqual(result['title'], 'Rémi Gaillard')
+        self.assertTrue(len(result['entries']) >= 100)
 
     def test_vimeo_channel(self):
         dl = FakeYDL()
@@ -98,7 +104,7 @@ class TestPlaylists(unittest.TestCase):
         result = ie.extract('http://www.ustream.tv/channel/young-americans-for-liberty')
         self.assertIsPlaylist(result)
         self.assertEqual(result['id'], '5124905')
-        self.assertTrue(len(result['entries']) >= 11)
+        self.assertTrue(len(result['entries']) >= 6)
 
     def test_soundcloud_set(self):
         dl = FakeYDL()
@@ -170,12 +176,12 @@ class TestPlaylists(unittest.TestCase):
     def test_AcademicEarthCourse(self):
         dl = FakeYDL()
         ie = AcademicEarthCourseIE(dl)
-        result = ie.extract('http://academicearth.org/courses/building-dynamic-websites/')
+        result = ie.extract('http://academicearth.org/playlists/laws-of-nature/')
         self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], 'building-dynamic-websites')
-        self.assertEqual(result['title'], 'Building Dynamic Websites')
-        self.assertEqual(result['description'], u"Today's websites are increasingly dynamic. Pages are no longer static HTML files but instead generated by scripts and database calls. User interfaces are more seamless, with technologies like Ajax replacing traditional page reloads. This course teaches students how to build dynamic websites with Ajax and with Linux, Apache, MySQL, and PHP (LAMP), one of today's most popular frameworks. Students learn how to set up domain names with DNS, how to structure pages with XHTML and CSS, how to program in JavaScript and PHP, how to configure Apache and MySQL, how to design and query databases with SQL, how to use Ajax with both XML and JSON, and how to build mashups. The course explores issues of security, scalability, and cross-browser support and also discusses enterprise-level deployments of websites, including third-party hosting, virtualization, colocation in data centers, firewalling, and load-balancing.")
-        self.assertEqual(len(result['entries']), 10)
+        self.assertEqual(result['id'], 'laws-of-nature')
+        self.assertEqual(result['title'], 'Laws of Nature')
+        self.assertEqual(result['description'],u'Introduce yourself to the laws of nature with these free online college lectures from Yale, Harvard, and MIT.')# u"Today's websites are increasingly dynamic. Pages are no longer static HTML files but instead generated by scripts and database calls. User interfaces are more seamless, with technologies like Ajax replacing traditional page reloads. This course teaches students how to build dynamic websites with Ajax and with Linux, Apache, MySQL, and PHP (LAMP), one of today's most popular frameworks. Students learn how to set up domain names with DNS, how to structure pages with XHTML and CSS, how to program in JavaScript and PHP, how to configure Apache and MySQL, how to design and query databases with SQL, how to use Ajax with both XML and JSON, and how to build mashups. The course explores issues of security, scalability, and cross-browser support and also discusses enterprise-level deployments of websites, including third-party hosting, virtualization, colocation in data centers, firewalling, and load-balancing.")
+        self.assertEqual(len(result['entries']), 4)
         
     def test_ivi_compilation(self):
         dl = FakeYDL()
@@ -248,7 +254,66 @@ class TestPlaylists(unittest.TestCase):
         self.assertIsPlaylist(result)
         self.assertEqual(result['id'], 'python language')
         self.assertEqual(result['title'], 'python language')
-        self.assertTrue(len(result['entries']) == 15)
+        self.assertEqual(len(result['entries']), 15)
+
+    def test_generic_rss_feed(self):
+        dl = FakeYDL()
+        ie = GenericIE(dl)
+        result = ie.extract('http://phihag.de/2014/youtube-dl/rss.xml')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], 'http://phihag.de/2014/youtube-dl/rss.xml')
+        self.assertEqual(result['title'], 'Zero Punctuation')
+        self.assertTrue(len(result['entries']) > 10)
+
+    def test_ted_playlist(self):
+        dl = FakeYDL()
+        ie = TEDIE(dl)
+        result = ie.extract('http://www.ted.com/playlists/who_are_the_hackers')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], '10')
+        self.assertEqual(result['title'], 'Who are the hackers?')
+        self.assertTrue(len(result['entries']) >= 6)
+
+    def test_toypics_user(self):
+        dl = FakeYDL()
+        ie = ToypicsUserIE(dl)
+        result = ie.extract('http://videos.toypics.net/Mikey')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], 'Mikey')
+        self.assertTrue(len(result['entries']) >= 17)
+
+    def test_xtube_user(self):
+        dl = FakeYDL()
+        ie = XTubeUserIE(dl)
+        result = ie.extract('http://www.xtube.com/community/profile.php?user=greenshowers')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], 'greenshowers')
+        self.assertTrue(len(result['entries']) >= 155)
+
+    def test_InstagramUser(self):
+        dl = FakeYDL()
+        ie = InstagramUserIE(dl)
+        result = ie.extract('http://instagram.com/porsche')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], 'porsche')
+        self.assertTrue(len(result['entries']) >= 2)
+        test_video = next(
+            e for e in result['entries']
+            if e['id'] == '614605558512799803_462752227')
+        dl.add_default_extra_info(test_video, ie, '(irrelevant URL)')
+        dl.process_video_result(test_video, download=False)
+        EXPECTED = {
+            'id': '614605558512799803_462752227',
+            'ext': 'mp4',
+            'title': '#Porsche Intelligent Performance.',
+            'thumbnail': 're:^https?://.*\.jpg',
+            'uploader': 'Porsche',
+            'uploader_id': 'porsche',
+            'timestamp': 1387486713,
+            'upload_date': '20131219',
+        }
+        expect_info_dict(self, EXPECTED, test_video)
+
 
 if __name__ == '__main__':
     unittest.main()

test/test_utils.py

@@ -9,6 +9,7 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 
 # Various small unit tests
+import io
 import xml.etree.ElementTree
 
 #from youtube_dl.utils import htmlentity_transform
@@ -21,16 +22,20 @@ from youtube_dl.utils import (
     orderedSet,
     PagedList,
     parse_duration,
+    read_batch_urls,
     sanitize_filename,
     shell_quote,
     smuggle_url,
     str_to_int,
+    struct_unpack,
     timeconvert,
     unescapeHTML,
     unified_strdate,
     unsmuggle_url,
     url_basename,
+    urlencode_postdata,
     xpath_with_ns,
+    parse_iso8601,
 )
 
 if sys.version_info < (3, 0):
@@ -127,6 +132,7 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(unified_strdate('8/7/2009'), '20090708')
         self.assertEqual(unified_strdate('Dec 14, 2012'), '20121214')
         self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
+        self.assertEqual(unified_strdate('1968-12-10'), '19681210')
 
     def test_find_xpath_attr(self):
         testxml = u'''<root>
@@ -200,7 +206,16 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(parse_duration('1'), 1)
         self.assertEqual(parse_duration('1337:12'), 80232)
         self.assertEqual(parse_duration('9:12:43'), 33163)
+        self.assertEqual(parse_duration('12:00'), 720)
+        self.assertEqual(parse_duration('00:01:01'), 61)
         self.assertEqual(parse_duration('x:y'), None)
+        self.assertEqual(parse_duration('3h11m53s'), 11513)
+        self.assertEqual(parse_duration('62m45s'), 3765)
+        self.assertEqual(parse_duration('6m59s'), 419)
+        self.assertEqual(parse_duration('49s'), 49)
+        self.assertEqual(parse_duration('0h0m0s'), 0)
+        self.assertEqual(parse_duration('0m0s'), 0)
+        self.assertEqual(parse_duration('0s'), 0)
 
     def test_fix_xml_ampersands(self):
         self.assertEqual(
@@ -236,5 +251,26 @@ class TestUtil(unittest.TestCase):
         testPL(5, 2, (2, 99), [2, 3, 4])
         testPL(5, 2, (20, 99), [])
 
+    def test_struct_unpack(self):
+        self.assertEqual(struct_unpack(u'!B', b'\x00'), (0,))
+
+    def test_read_batch_urls(self):
+        f = io.StringIO(u'''\xef\xbb\xbf foo
+            bar\r
+            baz
+            # More after this line\r
+            ; or after this
+            bam''')
+        self.assertEqual(read_batch_urls(f), [u'foo', u'bar', u'baz', u'bam'])
+
+    def test_urlencode_postdata(self):
+        data = urlencode_postdata({'username': 'foo@bar.com', 'password': '1234'})
+        self.assertTrue(isinstance(data, bytes))
+
+    def test_parse_iso8601(self):
+        self.assertEqual(parse_iso8601('2014-03-23T23:04:26+0100'), 1395612266)
+        self.assertEqual(parse_iso8601('2014-03-23T22:04:26+0000'), 1395612266)
+        self.assertEqual(parse_iso8601('2014-03-23T22:04:26Z'), 1395612266)
+
 if __name__ == '__main__':
     unittest.main()

test/test_youtube_lists.py

@@ -16,6 +16,7 @@ from youtube_dl.extractor import (
     YoutubeChannelIE,
     YoutubeShowIE,
     YoutubeTopListIE,
+    YoutubeSearchURLIE,
 )
 
 
@@ -30,7 +31,7 @@ class TestYoutubeLists(unittest.TestCase):
         result = ie.extract('https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re')
         self.assertIsPlaylist(result)
         self.assertEqual(result['title'], 'ytdl test PL')
-        ytie_results = [YoutubeIE()._extract_id(url['url']) for url in result['entries']]
+        ytie_results = [YoutubeIE().extract_id(url['url']) for url in result['entries']]
         self.assertEqual(ytie_results, [ 'bV9L5Ht9LgY', 'FXxLjLQi3Fg', 'tU3Bgo5qJZE'])
 
     def test_youtube_playlist_noplaylist(self):
@@ -39,7 +40,7 @@ class TestYoutubeLists(unittest.TestCase):
         ie = YoutubePlaylistIE(dl)
         result = ie.extract('https://www.youtube.com/watch?v=FXxLjLQi3Fg&list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re')
         self.assertEqual(result['_type'], 'url')
-        self.assertEqual(YoutubeIE()._extract_id(result['url']), 'FXxLjLQi3Fg')
+        self.assertEqual(YoutubeIE().extract_id(result['url']), 'FXxLjLQi3Fg')
 
     def test_issue_673(self):
         dl = FakeYDL()
@@ -59,7 +60,7 @@ class TestYoutubeLists(unittest.TestCase):
         dl = FakeYDL()
         ie = YoutubePlaylistIE(dl)
         result = ie.extract('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')
-        ytie_results = [YoutubeIE()._extract_id(url['url']) for url in result['entries']]
+        ytie_results = [YoutubeIE().extract_id(url['url']) for url in result['entries']]
         self.assertFalse('pElCt5oNDuI' in ytie_results)
         self.assertFalse('KdPEApIVdWM' in ytie_results)
         
@@ -76,9 +77,9 @@ class TestYoutubeLists(unittest.TestCase):
         # TODO find a > 100 (paginating?) videos course
         result = ie.extract('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
         entries = result['entries']
-        self.assertEqual(YoutubeIE()._extract_id(entries[0]['url']), 'j9WZyLZCBzs')
+        self.assertEqual(YoutubeIE().extract_id(entries[0]['url']), 'j9WZyLZCBzs')
         self.assertEqual(len(entries), 25)
-        self.assertEqual(YoutubeIE()._extract_id(entries[-1]['url']), 'rYefUsYuEp0')
+        self.assertEqual(YoutubeIE().extract_id(entries[-1]['url']), 'rYefUsYuEp0')
 
     def test_youtube_channel(self):
         dl = FakeYDL()
@@ -117,6 +118,15 @@ class TestYoutubeLists(unittest.TestCase):
         original_video = entries[0]
         self.assertEqual(original_video['id'], 'rjFaenf1T-Y')
 
+    def test_youtube_toptracks(self):
+        print('Skipping: The playlist page gives error 500')
+        return
+        dl = FakeYDL()
+        ie = YoutubePlaylistIE(dl)
+        result = ie.extract('https://www.youtube.com/playlist?list=MCUS')
+        entries = result['entries']
+        self.assertEqual(len(entries), 100)
+
     def test_youtube_toplist(self):
         dl = FakeYDL()
         ie = YoutubeTopListIE(dl)
@@ -124,5 +134,14 @@ class TestYoutubeLists(unittest.TestCase):
         entries = result['entries']
         self.assertTrue(len(entries) >= 5)
 
+    def test_youtube_search_url(self):
+        dl = FakeYDL()
+        ie = YoutubeSearchURLIE(dl)
+        result = ie.extract('https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video')
+        entries = result['entries']
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['title'], 'youtube-dl test video')
+        self.assertTrue(len(entries) >= 5)
+
 if __name__ == '__main__':
     unittest.main()

youtube_dl/InfoExtractors.py

@@ -1,4 +0,0 @@
-# Legacy file for backwards compatibility, use youtube_dl.extractor instead!
-
-from .extractor.common import InfoExtractor, SearchInfoExtractor
-from .extractor import gen_extractors, get_info_extractor

youtube_dl/YoutubeDL.py

@@ -4,6 +4,7 @@
 from __future__ import absolute_import, unicode_literals
 
 import collections
+import datetime
 import errno
 import io
 import json
@@ -147,6 +148,8 @@ class YoutubeDL(object):
                        again.
     cookiefile:        File name where cookies should be read from and dumped to.
     nocheckcertificate:Do not verify SSL certificates
+    prefer_insecure:   Use HTTP instead of HTTPS to retrieve information.
+                       At the moment, this is only supported by YouTube.
     proxy:             URL of the proxy server to use
     socket_timeout:    Time to wait for unresponsive hosts, in seconds
     bidi_workaround:   Work around buggy terminals without bidirectional text
@@ -370,12 +373,15 @@ class YoutubeDL(object):
         Print the message to stderr, it will be prefixed with 'WARNING:'
         If stderr is a tty file the 'WARNING:' will be colored
         '''
-        if self._err_file.isatty() and os.name != 'nt':
-            _msg_header = '\033[0;33mWARNING:\033[0m'
+        if self.params.get('logger') is not None:
+            self.params['logger'].warning(message)
         else:
-            _msg_header = 'WARNING:'
-        warning_message = '%s %s' % (_msg_header, message)
-        self.to_stderr(warning_message)
+            if self._err_file.isatty() and os.name != 'nt':
+                _msg_header = '\033[0;33mWARNING:\033[0m'
+            else:
+                _msg_header = 'WARNING:'
+            warning_message = '%s %s' % (_msg_header, message)
+            self.to_stderr(warning_message)
 
     def report_error(self, message, tb=None):
         '''
@@ -409,6 +415,13 @@ class YoutubeDL(object):
             template_dict['autonumber'] = autonumber_templ % self._num_downloads
             if template_dict.get('playlist_index') is not None:
                 template_dict['playlist_index'] = '%05d' % template_dict['playlist_index']
+            if template_dict.get('resolution') is None:
+                if template_dict.get('width') and template_dict.get('height'):
+                    template_dict['resolution'] = '%dx%d' % (template_dict['width'], template_dict['height'])
+                elif template_dict.get('height'):
+                    template_dict['resolution'] = '%sp' % template_dict['height']
+                elif template_dict.get('width'):
+                    template_dict['resolution'] = '?x%d' % template_dict['width']
 
             sanitize = lambda k, v: sanitize_filename(
                 compat_str(v),
@@ -499,13 +512,7 @@ class YoutubeDL(object):
                         '_type': 'compat_list',
                         'entries': ie_result,
                     }
-                self.add_extra_info(ie_result,
-                    {
-                        'extractor': ie.IE_NAME,
-                        'webpage_url': url,
-                        'webpage_url_basename': url_basename(url),
-                        'extractor_key': ie.ie_key(),
-                    })
+                self.add_default_extra_info(ie_result, ie, url)
                 if process:
                     return self.process_ie_result(ie_result, download, extra_info)
                 else:
@@ -522,7 +529,15 @@ class YoutubeDL(object):
                 else:
                     raise
         else:
-            self.report_error('no suitable InfoExtractor: %s' % url)
+            self.report_error('no suitable InfoExtractor for URL %s' % url)
+
+    def add_default_extra_info(self, ie_result, ie, url):
+        self.add_extra_info(ie_result, {
+            'extractor': ie.IE_NAME,
+            'webpage_url': url,
+            'webpage_url_basename': url_basename(url),
+            'extractor_key': ie.ie_key(),
+        })
 
     def process_ie_result(self, ie_result, download=True, extra_info={}):
         """
@@ -656,6 +671,18 @@ class YoutubeDL(object):
                 if f.get('vcodec') == 'none']
             if audio_formats:
                 return audio_formats[0]
+        elif format_spec == 'bestvideo':
+            video_formats = [
+                f for f in available_formats
+                if f.get('acodec') == 'none']
+            if video_formats:
+                return video_formats[-1]
+        elif format_spec == 'worstvideo':
+            video_formats = [
+                f for f in available_formats
+                if f.get('acodec') == 'none']
+            if video_formats:
+                return video_formats[0]
         else:
             extensions = ['mp4', 'flv', 'webm', '3gp']
             if format_spec in extensions:
@@ -675,6 +702,14 @@ class YoutubeDL(object):
             info_dict['playlist'] = None
             info_dict['playlist_index'] = None
 
+        if 'display_id' not in info_dict and 'id' in info_dict:
+            info_dict['display_id'] = info_dict['id']
+
+        if info_dict.get('upload_date') is None and info_dict.get('timestamp') is not None:
+            upload_date = datetime.datetime.utcfromtimestamp(
+                info_dict['timestamp'])
+            info_dict['upload_date'] = upload_date.strftime('%Y%m%d')
+
         # This extractors handle format selection themselves
         if info_dict['extractor'] in ['Youku']:
             if download:
@@ -688,8 +723,11 @@ class YoutubeDL(object):
         else:
             formats = info_dict['formats']
 
+        if not formats:
+            raise ExtractorError('No video formats found!')
+
         # We check that all the formats have the format and format_id fields
-        for (i, format) in enumerate(formats):
+        for i, format in enumerate(formats):
             if format.get('format_id') is None:
                 format['format_id'] = compat_str(i)
             if format.get('format') is None:
@@ -908,7 +946,7 @@ class YoutubeDL(object):
                     self.to_screen('[%s] %s: Downloading thumbnail ...' %
                                    (info_dict['extractor'], info_dict['id']))
                     try:
-                        uf = compat_urllib_request.urlopen(info_dict['thumbnail'])
+                        uf = self.urlopen(info_dict['thumbnail'])
                         with open(thumb_filename, 'wb') as thumbf:
                             shutil.copyfileobj(uf, thumbf)
                         self.to_screen('[%s] %s: Writing thumbnail to: %s' %
@@ -1154,7 +1192,7 @@ class YoutubeDL(object):
 
     def urlopen(self, req):
         """ Start an HTTP download """
-        return self._opener.open(req)
+        return self._opener.open(req, timeout=self._socket_timeout)
 
     def print_debug_header(self):
         if not self.params.get('verbose'):
@@ -1185,7 +1223,7 @@ class YoutubeDL(object):
 
     def _setup_opener(self):
         timeout_val = self.params.get('socket_timeout')
-        timeout = 600 if timeout_val is None else float(timeout_val)
+        self._socket_timeout = 600 if timeout_val is None else float(timeout_val)
 
         opts_cookiefile = self.params.get('cookiefile')
         opts_proxy = self.params.get('proxy')
@@ -1223,7 +1261,3 @@ class YoutubeDL(object):
         # (See https://github.com/rg3/youtube-dl/issues/1309 for details)
         opener.addheaders = []
         self._opener = opener
-
-        # TODO remove this global modification
-        compat_urllib_request.install_opener(opener)
-        socket.setdefaulttimeout(timeout)

youtube_dl/__init__.py

@@ -41,12 +41,22 @@ __authors__  = (
     'Chris Gahan',
     'Saimadhav Heblikar',
     'Mike Col',
+    'Oleg Prutz',
+    'pulpe',
+    'Andreas Schmitz',
+    'Michael Kaiser',
+    'Niklas Laxström',
+    'David Triendl',
+    'Anthony Weems',
+    'David Wagner',
+    'Juan C. Olivares',
+    'Mattias Harrysson',
 )
 
 __license__ = 'Public Domain'
 
 import codecs
-import getpass
+import io
 import locale
 import optparse
 import os
@@ -57,6 +67,7 @@ import sys
 
 
 from .utils import (
+    compat_getpass,
     compat_print,
     DateRange,
     decodeOption,
@@ -65,6 +76,7 @@ from .utils import (
     get_cachedir,
     MaxDownloadsReached,
     preferredencoding,
+    read_batch_urls,
     SameFileError,
     setproctitle,
     std_headers,
@@ -203,7 +215,7 @@ def parseOpts(overrideArguments=None):
     general.add_option('-U', '--update',
             action='store_true', dest='update_self', help='update this program to latest version. Make sure that you have sufficient permissions (run with sudo if needed)')
     general.add_option('-i', '--ignore-errors',
-            action='store_true', dest='ignoreerrors', help='continue on download errors, for example to to skip unavailable videos in a playlist', default=False)
+            action='store_true', dest='ignoreerrors', help='continue on download errors, for example to skip unavailable videos in a playlist', default=False)
     general.add_option('--abort-on-error',
             action='store_false', dest='ignoreerrors',
             help='Abort downloading of further videos (in the playlist or the command line) if an error occurs')
@@ -225,6 +237,9 @@ def parseOpts(overrideArguments=None):
         '--proxy', dest='proxy', default=None, metavar='URL',
         help='Use the specified HTTP/HTTPS proxy. Pass in an empty string (--proxy "") for direct connection')
     general.add_option('--no-check-certificate', action='store_true', dest='no_check_certificate', default=False, help='Suppress HTTPS certificate validation.')
+    general.add_option(
+        '--prefer-insecure', action='store_true', dest='prefer_insecure',
+        help='Use an unencrypted connection to retrieve information about the video. (Currently supported only for YouTube)')
     general.add_option(
         '--cache-dir', dest='cachedir', default=get_cachedir(), metavar='DIR',
         help='Location in the filesystem where youtube-dl can store some downloaded information permanently. By default $XDG_CACHE_HOME/youtube-dl or ~/.cache/youtube-dl . At the moment, only YouTube player files (for videos with obfuscated signatures) are cached, but that may change.')
@@ -245,7 +260,6 @@ def parseOpts(overrideArguments=None):
         action='store_true',
         help='Do not read configuration files. When given in the global configuration file /etc/youtube-dl.conf: do not read the user configuration in ~/.config/youtube-dl.conf (%APPDATA%/youtube-dl/config.txt on Windows)')
 
-
     selection.add_option(
         '--playlist-start',
         dest='playliststart', metavar='NUMBER', default=1, type=int,
@@ -304,7 +318,7 @@ def parseOpts(overrideArguments=None):
 
     video_format.add_option('-f', '--format',
             action='store', dest='format', metavar='FORMAT', default=None,
-            help='video format code, specify the order of preference using slashes: "-f 22/17/18". "-f mp4" and "-f flv" are also supported. You can also use the special names "best", "bestaudio", "worst", and "worstaudio". By default, youtube-dl will pick the best quality.')
+            help='video format code, specify the order of preference using slashes: "-f 22/17/18". "-f mp4" and "-f flv" are also supported. You can also use the special names "best", "bestvideo", "bestaudio", "worst", "worstvideo" and "worstaudio". By default, youtube-dl will pick the best quality.')
     video_format.add_option('--all-formats',
             action='store_const', dest='format', help='download all available video formats', const='all')
     video_format.add_option('--prefer-free-formats',
@@ -419,6 +433,8 @@ def parseOpts(overrideArguments=None):
                   '%(extractor)s for the provider (youtube, metacafe, etc), '
                   '%(id)s for the video id, %(playlist)s for the playlist the video is in, '
                   '%(playlist_index)s for the position in the playlist and %% for a literal percent. '
+                  '%(height)s and %(width)s for the width and height of the video format. '
+                  '%(resolution)s for a textual description of the resolution of the video format. '
                   'Use - to output to stdout. Can also be used to download to a different directory, '
                   'for example with -o \'/my/downloads/%(uploader)s/%(title)s-%(id)s.%(ext)s\' .'))
     filesystem.add_option('--autonumber-size',
@@ -546,21 +562,19 @@ def _real_main(argv=None):
         sys.exit(0)
 
     # Batch file verification
-    batchurls = []
+    batch_urls = []
     if opts.batchfile is not None:
         try:
             if opts.batchfile == '-':
                 batchfd = sys.stdin
             else:
-                batchfd = open(opts.batchfile, 'r')
-            batchurls = batchfd.readlines()
-            batchurls = [x.strip() for x in batchurls]
-            batchurls = [x for x in batchurls if len(x) > 0 and not re.search(r'^[#/;]', x)]
+                batchfd = io.open(opts.batchfile, 'r', encoding='utf-8', errors='ignore')
+            batch_urls = read_batch_urls(batchfd)
             if opts.verbose:
-                write_string(u'[debug] Batch file urls: ' + repr(batchurls) + u'\n')
+                write_string(u'[debug] Batch file urls: ' + repr(batch_urls) + u'\n')
         except IOError:
             sys.exit(u'ERROR: batch file could not be read')
-    all_urls = batchurls + args
+    all_urls = batch_urls + args
     all_urls = [url.strip() for url in all_urls]
     _enc = preferredencoding()
     all_urls = [url.decode(_enc, 'ignore') if isinstance(url, bytes) else url for url in all_urls]
@@ -599,7 +613,7 @@ def _real_main(argv=None):
     if opts.usetitle and opts.useid:
         parser.error(u'using title conflicts with using video ID')
     if opts.username is not None and opts.password is None:
-        opts.password = getpass.getpass(u'Type account password and press return:')
+        opts.password = compat_getpass(u'Type account password and press [Return]: ')
     if opts.ratelimit is not None:
         numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
         if numeric_limit is None:
@@ -744,6 +758,7 @@ def _real_main(argv=None):
         'download_archive': download_archive_fn,
         'cookiefile': opts.cookiefile,
         'nocheckcertificate': opts.no_check_certificate,
+        'prefer_insecure': opts.prefer_insecure,
         'proxy': opts.proxy,
         'socket_timeout': opts.socket_timeout,
         'bidi_workaround': opts.bidi_workaround,

youtube_dl/downloader/__init__.py

@@ -5,6 +5,7 @@ from .hls import HlsFD
 from .http import HttpFD
 from .mplayer import MplayerFD
 from .rtmp import RtmpFD
+from .f4m import F4mFD
 
 from ..utils import (
     determine_ext,
@@ -22,5 +23,7 @@ def get_suitable_downloader(info_dict):
         return HlsFD
     if url.startswith('mms') or url.startswith('rtsp'):
         return MplayerFD
+    if determine_ext(url) == 'f4m':
+        return F4mFD
     else:
         return HttpFD

youtube_dl/downloader/f4m.py

@@ -0,0 +1,314 @@
+from __future__ import unicode_literals
+
+import base64
+import io
+import itertools
+import os
+import time
+import xml.etree.ElementTree as etree
+
+from .common import FileDownloader
+from .http import HttpFD
+from ..utils import (
+    struct_pack,
+    struct_unpack,
+    compat_urlparse,
+    format_bytes,
+    encodeFilename,
+    sanitize_open,
+)
+
+
+class FlvReader(io.BytesIO):
+    """
+    Reader for Flv files
+    The file format is documented in https://www.adobe.com/devnet/f4v.html
+    """
+
+    # Utility functions for reading numbers and strings
+    def read_unsigned_long_long(self):
+        return struct_unpack('!Q', self.read(8))[0]
+
+    def read_unsigned_int(self):
+        return struct_unpack('!I', self.read(4))[0]
+
+    def read_unsigned_char(self):
+        return struct_unpack('!B', self.read(1))[0]
+
+    def read_string(self):
+        res = b''
+        while True:
+            char = self.read(1)
+            if char == b'\x00':
+                break
+            res += char
+        return res
+
+    def read_box_info(self):
+        """
+        Read a box and return the info as a tuple: (box_size, box_type, box_data)
+        """
+        real_size = size = self.read_unsigned_int()
+        box_type = self.read(4)
+        header_end = 8
+        if size == 1:
+            real_size = self.read_unsigned_long_long()
+            header_end = 16
+        return real_size, box_type, self.read(real_size-header_end)
+
+    def read_asrt(self):
+        # version
+        self.read_unsigned_char()
+        # flags
+        self.read(3)
+        quality_entry_count = self.read_unsigned_char()
+        # QualityEntryCount
+        for i in range(quality_entry_count):
+            self.read_string()
+
+        segment_run_count = self.read_unsigned_int()
+        segments = []
+        for i in range(segment_run_count):
+            first_segment = self.read_unsigned_int()
+            fragments_per_segment = self.read_unsigned_int()
+            segments.append((first_segment, fragments_per_segment))
+
+        return {
+            'segment_run': segments,
+        }
+
+    def read_afrt(self):
+        # version
+        self.read_unsigned_char()
+        # flags
+        self.read(3)
+        # time scale
+        self.read_unsigned_int()
+
+        quality_entry_count = self.read_unsigned_char()
+        # QualitySegmentUrlModifiers
+        for i in range(quality_entry_count):
+            self.read_string()
+
+        fragments_count = self.read_unsigned_int()
+        fragments = []
+        for i in range(fragments_count):
+            first = self.read_unsigned_int()
+            first_ts = self.read_unsigned_long_long()
+            duration = self.read_unsigned_int()
+            if duration == 0:
+                discontinuity_indicator = self.read_unsigned_char()
+            else:
+                discontinuity_indicator = None
+            fragments.append({
+                'first': first,
+                'ts': first_ts,
+                'duration': duration,
+                'discontinuity_indicator': discontinuity_indicator,
+            })
+
+        return {
+            'fragments': fragments,
+        }
+
+    def read_abst(self):
+        # version
+        self.read_unsigned_char()
+        # flags
+        self.read(3)
+
+        self.read_unsigned_int()  # BootstrapinfoVersion
+        # Profile,Live,Update,Reserved
+        self.read(1)
+        # time scale
+        self.read_unsigned_int()
+        # CurrentMediaTime
+        self.read_unsigned_long_long()
+        # SmpteTimeCodeOffset
+        self.read_unsigned_long_long()
+
+        self.read_string()  # MovieIdentifier
+        server_count = self.read_unsigned_char()
+        # ServerEntryTable
+        for i in range(server_count):
+            self.read_string()
+        quality_count = self.read_unsigned_char()
+        # QualityEntryTable
+        for i in range(quality_count):
+            self.read_string()
+        # DrmData
+        self.read_string()
+        # MetaData
+        self.read_string()
+
+        segments_count = self.read_unsigned_char()
+        segments = []
+        for i in range(segments_count):
+            box_size, box_type, box_data = self.read_box_info()
+            assert box_type == b'asrt'
+            segment = FlvReader(box_data).read_asrt()
+            segments.append(segment)
+        fragments_run_count = self.read_unsigned_char()
+        fragments = []
+        for i in range(fragments_run_count):
+            box_size, box_type, box_data = self.read_box_info()
+            assert box_type == b'afrt'
+            fragments.append(FlvReader(box_data).read_afrt())
+
+        return {
+            'segments': segments,
+            'fragments': fragments,
+        }
+
+    def read_bootstrap_info(self):
+        total_size, box_type, box_data = self.read_box_info()
+        assert box_type == b'abst'
+        return FlvReader(box_data).read_abst()
+
+
+def read_bootstrap_info(bootstrap_bytes):
+    return FlvReader(bootstrap_bytes).read_bootstrap_info()
+
+
+def build_fragments_list(boot_info):
+    """ Return a list of (segment, fragment) for each fragment in the video """
+    res = []
+    segment_run_table = boot_info['segments'][0]
+    # I've only found videos with one segment
+    segment_run_entry = segment_run_table['segment_run'][0]
+    n_frags = segment_run_entry[1]
+    fragment_run_entry_table = boot_info['fragments'][0]['fragments']
+    first_frag_number = fragment_run_entry_table[0]['first']
+    for (i, frag_number) in zip(range(1, n_frags+1), itertools.count(first_frag_number)):
+        res.append((1, frag_number))
+    return res
+
+
+def write_flv_header(stream, metadata):
+    """Writes the FLV header and the metadata to stream"""
+    # FLV header
+    stream.write(b'FLV\x01')
+    stream.write(b'\x05')
+    stream.write(b'\x00\x00\x00\x09')
+    # FLV File body
+    stream.write(b'\x00\x00\x00\x00')
+    # FLVTAG
+    # Script data
+    stream.write(b'\x12')
+    # Size of the metadata with 3 bytes
+    stream.write(struct_pack('!L', len(metadata))[1:])
+    stream.write(b'\x00\x00\x00\x00\x00\x00\x00')
+    stream.write(metadata)
+    # Magic numbers extracted from the output files produced by AdobeHDS.php
+    #(https://github.com/K-S-V/Scripts)
+    stream.write(b'\x00\x00\x01\x73')
+
+
+def _add_ns(prop):
+    return '{http://ns.adobe.com/f4m/1.0}%s' % prop
+
+
+class HttpQuietDownloader(HttpFD):
+    def to_screen(self, *args, **kargs):
+        pass
+
+
+class F4mFD(FileDownloader):
+    """
+    A downloader for f4m manifests or AdobeHDS.
+    """
+
+    def real_download(self, filename, info_dict):
+        man_url = info_dict['url']
+        self.to_screen('[download] Downloading f4m manifest')
+        manifest = self.ydl.urlopen(man_url).read()
+        self.report_destination(filename)
+        http_dl = HttpQuietDownloader(self.ydl,
+            {
+                'continuedl': True,
+                'quiet': True,
+                'noprogress': True,
+                'test': self.params.get('test', False),
+            })
+
+        doc = etree.fromstring(manifest)
+        formats = [(int(f.attrib.get('bitrate', -1)), f) for f in doc.findall(_add_ns('media'))]
+        formats = sorted(formats, key=lambda f: f[0])
+        rate, media = formats[-1]
+        base_url = compat_urlparse.urljoin(man_url, media.attrib['url'])
+        bootstrap = base64.b64decode(doc.find(_add_ns('bootstrapInfo')).text)
+        metadata = base64.b64decode(media.find(_add_ns('metadata')).text)
+        boot_info = read_bootstrap_info(bootstrap)
+        fragments_list = build_fragments_list(boot_info)
+        if self.params.get('test', False):
+            # We only download the first fragment
+            fragments_list = fragments_list[:1]
+        total_frags = len(fragments_list)
+
+        tmpfilename = self.temp_name(filename)
+        (dest_stream, tmpfilename) = sanitize_open(tmpfilename, 'wb')
+        write_flv_header(dest_stream, metadata)
+
+        # This dict stores the download progress, it's updated by the progress
+        # hook
+        state = {
+            'downloaded_bytes': 0,
+            'frag_counter': 0,
+        }
+        start = time.time()
+
+        def frag_progress_hook(status):
+            frag_total_bytes = status.get('total_bytes', 0)
+            estimated_size = (state['downloaded_bytes'] +
+                (total_frags - state['frag_counter']) * frag_total_bytes)
+            if status['status'] == 'finished':
+                state['downloaded_bytes'] += frag_total_bytes
+                state['frag_counter'] += 1
+                progress = self.calc_percent(state['frag_counter'], total_frags)
+                byte_counter = state['downloaded_bytes']
+            else:
+                frag_downloaded_bytes = status['downloaded_bytes']
+                byte_counter = state['downloaded_bytes'] + frag_downloaded_bytes
+                frag_progress = self.calc_percent(frag_downloaded_bytes,
+                    frag_total_bytes)
+                progress = self.calc_percent(state['frag_counter'], total_frags)
+                progress += frag_progress / float(total_frags)
+
+            eta = self.calc_eta(start, time.time(), estimated_size, byte_counter)
+            self.report_progress(progress, format_bytes(estimated_size),
+                status.get('speed'), eta)
+        http_dl.add_progress_hook(frag_progress_hook)
+
+        frags_filenames = []
+        for (seg_i, frag_i) in fragments_list:
+            name = 'Seg%d-Frag%d' % (seg_i, frag_i)
+            url = base_url + name
+            frag_filename = '%s-%s' % (tmpfilename, name)
+            success = http_dl.download(frag_filename, {'url': url})
+            if not success:
+                return False
+            with open(frag_filename, 'rb') as down:
+                down_data = down.read()
+                reader = FlvReader(down_data)
+                while True:
+                    _, box_type, box_data = reader.read_box_info()
+                    if box_type == b'mdat':
+                        dest_stream.write(box_data)
+                        break
+            frags_filenames.append(frag_filename)
+
+        self.report_finish(format_bytes(state['downloaded_bytes']), time.time() - start)
+
+        self.try_rename(tmpfilename, filename)
+        for frag_file in frags_filenames:
+            os.remove(frag_file)
+
+        fsize = os.path.getsize(encodeFilename(filename))
+        self._hook_progress({
+            'downloaded_bytes': fsize,
+            'total_bytes': fsize,
+            'filename': filename,
+            'status': 'finished',
+        })
+
+        return True

youtube_dl/downloader/http.py

@@ -49,7 +49,7 @@ class HttpFD(FileDownloader):
         while count <= retries:
             # Establish connection
             try:
-                data = compat_urllib_request.urlopen(request)
+                data = self.ydl.urlopen(request)
                 break
             except (compat_urllib_error.HTTPError, ) as err:
                 if (err.code < 500 or err.code >= 600) and err.code != 416:
@@ -59,7 +59,7 @@ class HttpFD(FileDownloader):
                     # Unable to resume (requested range not satisfiable)
                     try:
                         # Open the connection again without the range header
-                        data = compat_urllib_request.urlopen(basic_request)
+                        data = self.ydl.urlopen(basic_request)
                         content_length = data.info()['Content-Length']
                     except (compat_urllib_error.HTTPError, ) as err:
                         if err.code < 500 or err.code >= 600:
@@ -85,6 +85,7 @@ class HttpFD(FileDownloader):
                         else:
                             # The length does not match, we start the download over
                             self.report_unable_to_resume()
+                            resume_len = 0
                             open_mode = 'wb'
                             break
             # Retry

youtube_dl/downloader/rtmp.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import os
 import re
 import subprocess
@@ -22,7 +24,7 @@ class RtmpFD(FileDownloader):
             proc_stderr_closed = False
             while not proc_stderr_closed:
                 # read line from stderr
-                line = u''
+                line = ''
                 while True:
                     char = proc.stderr.read(1)
                     if not char:
@@ -46,7 +48,7 @@ class RtmpFD(FileDownloader):
                     data_len = None
                     if percent > 0:
                         data_len = int(downloaded_data_len * 100 / percent)
-                    data_len_str = u'~' + format_bytes(data_len)
+                    data_len_str = '~' + format_bytes(data_len)
                     self.report_progress(percent, data_len_str, speed, eta)
                     cursor_in_new_line = False
                     self._hook_progress({
@@ -76,19 +78,21 @@ class RtmpFD(FileDownloader):
                         })
                     elif self.params.get('verbose', False):
                         if not cursor_in_new_line:
-                            self.to_screen(u'')
+                            self.to_screen('')
                         cursor_in_new_line = True
-                        self.to_screen(u'[rtmpdump] '+line)
+                        self.to_screen('[rtmpdump] '+line)
             proc.wait()
             if not cursor_in_new_line:
-                self.to_screen(u'')
+                self.to_screen('')
             return proc.returncode
 
         url = info_dict['url']
         player_url = info_dict.get('player_url', None)
         page_url = info_dict.get('page_url', None)
+        app = info_dict.get('app', None)
         play_path = info_dict.get('play_path', None)
         tc_url = info_dict.get('tc_url', None)
+        flash_version = info_dict.get('flash_version', None)
         live = info_dict.get('rtmp_live', False)
         conn = info_dict.get('rtmp_conn', None)
 
@@ -100,7 +104,7 @@ class RtmpFD(FileDownloader):
         try:
             subprocess.call(['rtmpdump', '-h'], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
         except (OSError, IOError):
-            self.report_error(u'RTMP download detected but "rtmpdump" could not be run')
+            self.report_error('RTMP download detected but "rtmpdump" could not be run')
             return False
 
         # Download using rtmpdump. rtmpdump returns exit code 2 when
@@ -111,17 +115,21 @@ class RtmpFD(FileDownloader):
             basic_args += ['--swfVfy', player_url]
         if page_url is not None:
             basic_args += ['--pageUrl', page_url]
+        if app is not None:
+            basic_args += ['--app', app]
         if play_path is not None:
             basic_args += ['--playpath', play_path]
         if tc_url is not None:
             basic_args += ['--tcUrl', url]
         if test:
             basic_args += ['--stop', '1']
+        if flash_version is not None:
+            basic_args += ['--flashVer', flash_version]
         if live:
             basic_args += ['--live']
         if conn:
             basic_args += ['--conn', conn]
-        args = basic_args + [[], ['--resume', '--skip', '1']][self.params.get('continuedl', False)]
+        args = basic_args + [[], ['--resume', '--skip', '1']][not live and self.params.get('continuedl', False)]
 
         if sys.platform == 'win32' and sys.version_info < (3, 0):
             # Windows subprocess module does not actually support Unicode
@@ -144,26 +152,35 @@ class RtmpFD(FileDownloader):
                 shell_quote = lambda args: ' '.join(map(pipes.quote, str_args))
             except ImportError:
                 shell_quote = repr
-            self.to_screen(u'[debug] rtmpdump command line: ' + shell_quote(str_args))
+            self.to_screen('[debug] rtmpdump command line: ' + shell_quote(str_args))
+
+        RD_SUCCESS = 0
+        RD_FAILED = 1
+        RD_INCOMPLETE = 2
+        RD_NO_CONNECT = 3
 
         retval = run_rtmpdump(args)
 
-        while (retval == 2 or retval == 1) and not test:
+        if retval == RD_NO_CONNECT:
+            self.report_error('[rtmpdump] Could not connect to RTMP server.')
+            return False
+
+        while (retval == RD_INCOMPLETE or retval == RD_FAILED) and not test and not live:
             prevsize = os.path.getsize(encodeFilename(tmpfilename))
-            self.to_screen(u'[rtmpdump] %s bytes' % prevsize)
+            self.to_screen('[rtmpdump] %s bytes' % prevsize)
             time.sleep(5.0) # This seems to be needed
-            retval = run_rtmpdump(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1])
+            retval = run_rtmpdump(basic_args + ['-e'] + [[], ['-k', '1']][retval == RD_FAILED])
             cursize = os.path.getsize(encodeFilename(tmpfilename))
-            if prevsize == cursize and retval == 1:
+            if prevsize == cursize and retval == RD_FAILED:
                 break
              # Some rtmp streams seem abort after ~ 99.8%. Don't complain for those
-            if prevsize == cursize and retval == 2 and cursize > 1024:
-                self.to_screen(u'[rtmpdump] Could not download the whole video. This can happen for some advertisements.')
-                retval = 0
+            if prevsize == cursize and retval == RD_INCOMPLETE and cursize > 1024:
+                self.to_screen('[rtmpdump] Could not download the whole video. This can happen for some advertisements.')
+                retval = RD_SUCCESS
                 break
-        if retval == 0 or (test and retval == 2):
+        if retval == RD_SUCCESS or (test and retval == RD_INCOMPLETE):
             fsize = os.path.getsize(encodeFilename(tmpfilename))
-            self.to_screen(u'[rtmpdump] %s bytes' % fsize)
+            self.to_screen('[rtmpdump] %s bytes' % fsize)
             self.try_rename(tmpfilename, filename)
             self._hook_progress({
                 'downloaded_bytes': fsize,
@@ -173,6 +190,6 @@ class RtmpFD(FileDownloader):
             })
             return True
         else:
-            self.to_stderr(u"\n")
-            self.report_error(u'rtmpdump exited with code %d' % retval)
+            self.to_stderr('\n')
+            self.report_error('rtmpdump exited with code %d' % retval)
             return False

youtube_dl/extractor/__init__.py

@@ -1,6 +1,8 @@
 from .academicearth import AcademicEarthCourseIE
 from .addanime import AddAnimeIE
+from .aftonbladet import AftonbladetIE
 from .anitube import AnitubeIE
+from .aol import AolIE
 from .aparat import AparatIE
 from .appletrailers import AppleTrailersIE
 from .archiveorg import ArchiveOrgIE
@@ -9,28 +11,37 @@ from .arte import (
     ArteTvIE,
     ArteTVPlus7IE,
     ArteTVCreativeIE,
+    ArteTVConcertIE,
     ArteTVFutureIE,
     ArteTVDDCIE,
 )
 from .auengine import AUEngineIE
 from .bambuser import BambuserIE, BambuserChannelIE
 from .bandcamp import BandcampIE, BandcampAlbumIE
+from .bbccouk import BBCCoUkIE
 from .blinkx import BlinkxIE
 from .bliptv import BlipTVIE, BlipTVUserIE
 from .bloomberg import BloombergIE
+from .br import BRIE
 from .breakcom import BreakIE
 from .brightcove import BrightcoveIE
 from .c56 import C56IE
+from .canal13cl import Canal13clIE
 from .canalplus import CanalplusIE
 from .canalc2 import Canalc2IE
 from .cbs import CBSIE
+from .ceskatelevize import CeskaTelevizeIE
 from .channel9 import Channel9IE
+from .chilloutzone import ChilloutzoneIE
 from .cinemassacre import CinemassacreIE
 from .clipfish import ClipfishIE
 from .cliphunter import CliphunterIE
 from .clipsyndicate import ClipsyndicateIE
 from .cmt import CMTIE
-from .cnn import CNNIE
+from .cnn import (
+    CNNIE,
+    CNNBlogsIE,
+)
 from .collegehumor import CollegeHumorIE
 from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE
 from .condenast import CondeNastIE
@@ -44,7 +55,6 @@ from .dailymotion import (
     DailymotionUserIE,
 )
 from .daum import DaumIE
-from .depositfiles import DepositFilesIE
 from .dotsub import DotsubIE
 from .dreisat import DreiSatIE
 from .defense import DefenseGouvFrIE
@@ -55,6 +65,7 @@ from .ehow import EHowIE
 from .eighttracks import EightTracksIE
 from .eitb import EitbIE
 from .elpais import ElPaisIE
+from .engadget import EngadgetIE
 from .escapist import EscapistIE
 from .everyonesmixtape import EveryonesMixtapeIE
 from .exfm import ExfmIE
@@ -62,11 +73,14 @@ from .extremetube import ExtremeTubeIE
 from .facebook import FacebookIE
 from .faz import FazIE
 from .firstpost import FirstpostIE
+from .firsttv import FirstTVIE
+from .fivemin import FiveMinIE
 from .fktv import (
     FKTVIE,
     FKTVPosteckeIE,
 )
 from .flickr import FlickrIE
+from .fourtube import FourTubeIE
 from .franceinter import FranceInterIE
 from .francetv import (
     PluzzIE,
@@ -81,10 +95,12 @@ from .funnyordie import FunnyOrDieIE
 from .gamekings import GamekingsIE
 from .gamespot import GameSpotIE
 from .gametrailers import GametrailersIE
+from .gdcvault import GDCVaultIE
 from .generic import GenericIE
 from .googleplus import GooglePlusIE
 from .googlesearch import GoogleSearchIE
 from .hark import HarkIE
+from .helsinki import HelsinkiIE
 from .hotnewhiphop import HotNewHipHopIE
 from .howcast import HowcastIE
 from .huffpost import HuffPostIE
@@ -96,13 +112,14 @@ from .imdb import (
 )
 from .ina import InaIE
 from .infoq import InfoQIE
-from .instagram import InstagramIE
+from .instagram import InstagramIE, InstagramUserIE
 from .internetvideoarchive import InternetVideoArchiveIE
 from .iprima import IPrimaIE
 from .ivi import (
     IviIE,
     IviCompilationIE
 )
+from .jadorecettepub import JadoreCettePubIE
 from .jeuxvideo import JeuxVideoIE
 from .jukebox import JukeboxIE
 from .justintv import JustinTVIE
@@ -112,6 +129,7 @@ from .keezmovies import KeezMoviesIE
 from .khanacademy import KhanAcademyIE
 from .kickstarter import KickStarterIE
 from .keek import KeekIE
+from .kontrtube import KontrTubeIE
 from .la7 import LA7IE
 from .lifenews import LifeNewsIE
 from .liveleak import LiveLeakIE
@@ -122,11 +140,12 @@ from .lynda import (
 )
 from .m6 import M6IE
 from .macgamestore import MacGameStoreIE
+from .mailru import MailRuIE
 from .malemotion import MalemotionIE
 from .mdr import MDRIE
 from .metacafe import MetacafeIE
 from .metacritic import MetacriticIE
-from .mit import TechTVMITIE, MITIE
+from .mit import TechTVMITIE, MITIE, OCWMITIE
 from .mixcloud import MixcloudIE
 from .mpora import MporaIE
 from .mofosex import MofosexIE
@@ -141,24 +160,32 @@ from .myspass import MySpassIE
 from .myvideo import MyVideoIE
 from .naver import NaverIE
 from .nba import NBAIE
-from .nbc import NBCNewsIE
+from .nbc import (
+    NBCIE,
+    NBCNewsIE,
+)
+from .ndr import NDRIE
 from .ndtv import NDTVIE
 from .newgrounds import NewgroundsIE
+from .nfb import NFBIE
 from .nhl import NHLIE, NHLVideocenterIE
 from .niconico import NiconicoIE
 from .ninegag import NineGagIE
 from .normalboots import NormalbootsIE
-from .novamov import NovamovIE
+from .novamov import NovaMovIE
 from .nowness import NownessIE
 from .nowvideo import NowVideoIE
 from .ooyala import OoyalaIE
 from .orf import ORFIE
+from .parliamentliveuk import ParliamentLiveUKIE
 from .pbs import PBSIE
 from .photobucket import PhotobucketIE
+from .playvid import PlayvidIE
 from .podomatic import PodomaticIE
 from .pornhd import PornHdIE
 from .pornhub import PornHubIE
 from .pornotube import PornotubeIE
+from .prosiebensat1 import ProSiebenSat1IE
 from .pyvideo import PyvideoIE
 from .radiofrance import RadioFranceIE
 from .rbmaradio import RBMARadioIE
@@ -168,12 +195,15 @@ from .ro220 import Ro220IE
 from .rottentomatoes import RottenTomatoesIE
 from .roxwel import RoxwelIE
 from .rtlnow import RTLnowIE
+from .rts import RTSIE
 from .rutube import (
     RutubeIE,
     RutubeChannelIE,
     RutubeMovieIE,
     RutubePersonIE,
 )
+from .rutv import RUTVIE
+from .savefrom import SaveFromIE
 from .servingsys import ServingSysIE
 from .sina import SinaIE
 from .slashdot import SlashdotIE
@@ -198,31 +228,44 @@ from .stanfordoc import StanfordOpenClassroomIE
 from .statigram import StatigramIE
 from .steam import SteamIE
 from .streamcloud import StreamcloudIE
+from .streamcz import StreamCZIE
+from .syfy import SyfyIE
 from .sztvhu import SztvHuIE
 from .teamcoco import TeamcocoIE
 from .techtalks import TechTalksIE
 from .ted import TEDIE
+from .testurl import TestURLIE
 from .tf1 import TF1IE
 from .theplatform import ThePlatformIE
 from .thisav import ThisAVIE
 from .tinypic import TinyPicIE
 from .toutv import TouTvIE
+from .toypics import ToypicsUserIE, ToypicsIE
 from .traileraddict import TrailerAddictIE
 from .trilulilu import TriluliluIE
+from .trutube import TruTubeIE
 from .tube8 import Tube8IE
 from .tudou import TudouIE
 from .tumblr import TumblrIE
 from .tutv import TutvIE
+from .tvigle import TvigleIE
 from .tvp import TvpIE
+from .udemy import (
+    UdemyIE,
+    UdemyCourseIE
+)
 from .unistra import UnistraIE
 from .ustream import UstreamIE, UstreamChannelIE
 from .vbox7 import Vbox7IE
 from .veehd import VeeHDIE
 from .veoh import VeohIE
+from .vesti import VestiIE
 from .vevo import VevoIE
 from .vice import ViceIE
 from .viddler import ViddlerIE
+from .videobam import VideoBamIE
 from .videodetective import VideoDetectiveIE
+from .videolecturesnet import VideoLecturesNetIE
 from .videofyme import VideofyMeIE
 from .videopremium import VideoPremiumIE
 from .vimeo import (
@@ -238,14 +281,16 @@ from .viki import VikiIE
 from .vk import VKIE
 from .vube import VubeIE
 from .wat import WatIE
+from .wdr import WDRIE
 from .weibo import WeiboIE
 from .wimp import WimpIE
 from .wistia import WistiaIE
 from .worldstarhiphop import WorldStarHipHopIE
+from .xbef import XBefIE
 from .xhamster import XHamsterIE
 from .xnxx import XNXXIE
 from .xvideos import XVideosIE
-from .xtube import XTubeIE
+from .xtube import XTubeUserIE, XTubeIE
 from .yahoo import (
     YahooIE,
     YahooNewsIE,
@@ -256,19 +301,20 @@ from .youku import YoukuIE
 from .youporn import YouPornIE
 from .youtube import (
     YoutubeIE,
-    YoutubePlaylistIE,
-    YoutubeSearchIE,
-    YoutubeSearchDateIE,
-    YoutubeUserIE,
     YoutubeChannelIE,
-    YoutubeShowIE,
-    YoutubeSubscriptionsIE,
-    YoutubeRecommendedIE,
-    YoutubeTruncatedURLIE,
-    YoutubeWatchLaterIE,
     YoutubeFavouritesIE,
     YoutubeHistoryIE,
+    YoutubePlaylistIE,
+    YoutubeRecommendedIE,
+    YoutubeSearchDateIE,
+    YoutubeSearchIE,
+    YoutubeSearchURLIE,
+    YoutubeShowIE,
+    YoutubeSubscriptionsIE,
     YoutubeTopListIE,
+    YoutubeTruncatedURLIE,
+    YoutubeUserIE,
+    YoutubeWatchLaterIE,
 )
 from .zdf import ZDFIE
 

youtube_dl/extractor/academicearth.py

@@ -5,7 +5,7 @@ from .common import InfoExtractor
 
 
 class AcademicEarthCourseIE(InfoExtractor):
-    _VALID_URL = r'^https?://(?:www\.)?academicearth\.org/(?:courses|playlists)/(?P<id>[^?#/]+)'
+    _VALID_URL = r'^https?://(?:www\.)?academicearth\.org/playlists/(?P<id>[^?#/]+)'
     IE_NAME = 'AcademicEarth:Course'
 
     def _real_extract(self, url):
@@ -14,12 +14,12 @@ class AcademicEarthCourseIE(InfoExtractor):
 
         webpage = self._download_webpage(url, playlist_id)
         title = self._html_search_regex(
-            r'<h1 class="playlist-name">(.*?)</h1>', webpage, u'title')
+            r'<h1 class="playlist-name"[^>]*?>(.*?)</h1>', webpage, u'title')
         description = self._html_search_regex(
-            r'<p class="excerpt">(.*?)</p>',
+            r'<p class="excerpt"[^>]*?>(.*?)</p>',
             webpage, u'description', fatal=False)
         urls = re.findall(
-            r'<h3 class="lecture-title"><a target="_blank" href="([^"]+)">',
+            r'<li class="lecture-preview">\s*?<a target="_blank" href="([^"]+)">',
             webpage)
         entries = [self.url_result(u) for u in urls]
 

youtube_dl/extractor/aftonbladet.py

@@ -0,0 +1,69 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import datetime
+import re
+
+from .common import InfoExtractor
+
+
+class AftonbladetIE(InfoExtractor):
+    _VALID_URL = r'^http://tv\.aftonbladet\.se/webbtv.+?(?P<video_id>article[0-9]+)\.ab(?:$|[?#])'
+    _TEST = {
+        'url': 'http://tv.aftonbladet.se/webbtv/nyheter/vetenskap/rymden/article36015.ab',
+        'info_dict': {
+            'id': 'article36015',
+            'ext': 'mp4',
+            'title': 'Vulkanutbrott i rymden - nu släpper NASA bilderna',
+            'description': 'Jupiters måne mest aktiv av alla himlakroppar',
+            'upload_date': '20140306',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.search(self._VALID_URL, url)
+
+        video_id = mobj.group('video_id')
+        webpage = self._download_webpage(url, video_id)
+
+        # find internal video meta data
+        META_URL = 'http://aftonbladet-play.drlib.aptoma.no/video/%s.json'
+        internal_meta_id = self._html_search_regex(
+            r'data-aptomaId="([\w\d]+)"', webpage, 'internal_meta_id')
+        internal_meta_url = META_URL % internal_meta_id
+        internal_meta_json = self._download_json(
+            internal_meta_url, video_id, 'Downloading video meta data')
+
+        # find internal video formats
+        FORMATS_URL = 'http://aftonbladet-play.videodata.drvideo.aptoma.no/actions/video/?id=%s'
+        internal_video_id = internal_meta_json['videoId']
+        internal_formats_url = FORMATS_URL % internal_video_id
+        internal_formats_json = self._download_json(
+            internal_formats_url, video_id, 'Downloading video formats')
+
+        formats = []
+        for fmt in internal_formats_json['formats']['http']['pseudostreaming']['mp4']:
+            p = fmt['paths'][0]
+            formats.append({
+                'url': 'http://%s:%d/%s/%s' % (p['address'], p['port'], p['path'], p['filename']),
+                'ext': 'mp4',
+                'width': fmt['width'],
+                'height': fmt['height'],
+                'tbr': fmt['bitrate'],
+                'protocol': 'http',
+            })
+        self._sort_formats(formats)
+
+        timestamp = datetime.datetime.fromtimestamp(internal_meta_json['timePublished'])
+        upload_date = timestamp.strftime('%Y%m%d')
+
+        return {
+            'id': video_id,
+            'title': internal_meta_json['title'],
+            'formats': formats,
+            'thumbnail': internal_meta_json['imageUrl'],
+            'description': internal_meta_json['shortPreamble'],
+            'upload_date': upload_date,
+            'duration': internal_meta_json['duration'],
+            'view_count': internal_meta_json['views'],
+        }

youtube_dl/extractor/aol.py

@@ -0,0 +1,28 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from .fivemin import FiveMinIE
+
+
+class AolIE(InfoExtractor):
+    IE_NAME = 'on.aol.com'
+    _VALID_URL = r'http://on\.aol\.com/video/.*-(?P<id>\d+)($|\?)'
+
+    _TEST = {
+        'url': 'http://on.aol.com/video/u-s--official-warns-of-largest-ever-irs-phone-scam-518167793?icid=OnHomepageC2Wide_MustSee_Img',
+        'md5': '18ef68f48740e86ae94b98da815eec42',
+        'info_dict': {
+            'id': '518167793',
+            'ext': 'mp4',
+            'title': 'U.S. Official Warns Of \'Largest Ever\' IRS Phone Scam',
+        },
+        'add_ie': ['FiveMin'],
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        self.to_screen('Downloading 5min.com video %s' % video_id)
+        return FiveMinIE._build_result(video_id)

youtube_dl/extractor/arte.py

@@ -72,18 +72,22 @@ class ArteTvIE(InfoExtractor):
             return self._extract_liveweb(url, name, lang)
 
         if re.search(self._LIVE_URL, url) is not None:
-            raise ExtractorError(u'Arte live streams are not yet supported, sorry')
+            raise ExtractorError('Arte live streams are not yet supported, sorry')
             # self.extractLiveStream(url)
             # return
 
+        raise ExtractorError('No video found')
+
     def _extract_video(self, url, video_id, lang):
         """Extract from videos.arte.tv"""
         ref_xml_url = url.replace('/videos/', '/do_delegate/videos/')
         ref_xml_url = ref_xml_url.replace('.html', ',view,asPlayerXml.xml')
-        ref_xml_doc = self._download_xml(ref_xml_url, video_id, note=u'Downloading metadata')
+        ref_xml_doc = self._download_xml(
+            ref_xml_url, video_id, note='Downloading metadata')
         config_node = find_xpath_attr(ref_xml_doc, './/video', 'lang', lang)
         config_xml_url = config_node.attrib['ref']
-        config_xml = self._download_webpage(config_xml_url, video_id, note=u'Downloading configuration')
+        config_xml = self._download_webpage(
+            config_xml_url, video_id, note='Downloading configuration')
 
         video_urls = list(re.finditer(r'<url quality="(?P<quality>.*?)">(?P<url>.*?)</url>', config_xml))
         def _key(m):
@@ -127,7 +131,7 @@ class ArteTvIE(InfoExtractor):
 
 class ArteTVPlus7IE(InfoExtractor):
     IE_NAME = 'arte.tv:+7'
-    _VALID_URL = r'https?://www\.arte.tv/guide/(?P<lang>fr|de)/(?:(?:sendungen|emissions)/)?(?P<id>.*?)/(?P<name>.*?)(\?.*)?'
+    _VALID_URL = r'https?://(?:www\.)?arte\.tv/guide/(?P<lang>fr|de)/(?:(?:sendungen|emissions)/)?(?P<id>.*?)/(?P<name>.*?)(\?.*)?'
 
     @classmethod
     def _extract_url_info(cls, url):
@@ -198,6 +202,8 @@ class ArteTVPlus7IE(InfoExtractor):
                     re.match(r'VO-ST(F|A)', f.get('versionCode', '')) is None,
                     # The version with sourds/mal subtitles has also lower relevance
                     re.match(r'VO?(F|A)-STM\1', f.get('versionCode', '')) is None,
+                    # Prefer http downloads over m3u8
+                    0 if f['url'].endswith('m3u8') else 1,
                 )
         formats = sorted(formats, key=sort_key)
         def _format(format_info):
@@ -238,8 +244,9 @@ class ArteTVCreativeIE(ArteTVPlus7IE):
 
     _TEST = {
         'url': 'http://creative.arte.tv/de/magazin/agentur-amateur-corporate-design',
-        'file': '050489-002.mp4',
         'info_dict': {
+            'id': '050489-002',
+            'ext': 'mp4',
             'title': 'Agentur Amateur / Agence Amateur #2 : Corporate Design',
         },
     }
@@ -251,8 +258,9 @@ class ArteTVFutureIE(ArteTVPlus7IE):
 
     _TEST = {
         'url': 'http://future.arte.tv/fr/sujet/info-sciences#article-anchor-7081',
-        'file': '050940-003.mp4',
         'info_dict': {
+            'id': '050940-003',
+            'ext': 'mp4',
             'title': 'Les champignons au secours de la planète',
         },
     }
@@ -266,7 +274,7 @@ class ArteTVFutureIE(ArteTVPlus7IE):
 
 class ArteTVDDCIE(ArteTVPlus7IE):
     IE_NAME = 'arte.tv:ddc'
-    _VALID_URL = r'http?://ddc\.arte\.tv/(?P<lang>emission|folge)/(?P<id>.+)'
+    _VALID_URL = r'https?://ddc\.arte\.tv/(?P<lang>emission|folge)/(?P<id>.+)'
 
     def _real_extract(self, url):
         video_id, lang = self._extract_url_info(url)
@@ -280,3 +288,20 @@ class ArteTVDDCIE(ArteTVPlus7IE):
         javascriptPlayerGenerator = self._download_webpage(script_url, video_id, 'Download javascript player generator')
         json_url = self._search_regex(r"json_url=(.*)&rendering_place.*", javascriptPlayerGenerator, 'json url')
         return self._extract_from_json_url(json_url, video_id, lang)
+
+
+class ArteTVConcertIE(ArteTVPlus7IE):
+    IE_NAME = 'arte.tv:concert'
+    _VALID_URL = r'https?://concert\.arte\.tv/(?P<lang>de|fr)/(?P<id>.+)'
+
+    _TEST = {
+        'url': 'http://concert.arte.tv/de/notwist-im-pariser-konzertclub-divan-du-monde',
+        'md5': '9ea035b7bd69696b67aa2ccaaa218161',
+        'info_dict': {
+            'id': '186',
+            'ext': 'mp4',
+            'title': 'The Notwist im Pariser Konzertclub "Divan du Monde"',
+            'upload_date': '20140128',
+            'description': 'md5:486eb08f991552ade77439fe6d82c305',
+        },
+    }

youtube_dl/extractor/bbccouk.py

@@ -0,0 +1,223 @@
+from __future__ import unicode_literals
+
+import re
+
+from .subtitles import SubtitlesInfoExtractor
+from ..utils import ExtractorError
+
+
+class BBCCoUkIE(SubtitlesInfoExtractor):
+    IE_NAME = 'bbc.co.uk'
+    IE_DESC = 'BBC iPlayer'
+    _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:programmes|iplayer/episode)/(?P<id>[\da-z]{8})'
+
+    _TESTS = [
+        {
+            'url': 'http://www.bbc.co.uk/programmes/b039g8p7',
+            'info_dict': {
+                'id': 'b039d07m',
+                'ext': 'flv',
+                'title': 'Kaleidoscope: Leonard Cohen',
+                'description': 'md5:db4755d7a665ae72343779f7dacb402c',
+                'duration': 1740,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            }
+        },
+        {
+            'url': 'http://www.bbc.co.uk/iplayer/episode/b00yng5w/The_Man_in_Black_Series_3_The_Printed_Name/',
+            'info_dict': {
+                'id': 'b00yng1d',
+                'ext': 'flv',
+                'title': 'The Man in Black: Series 3: The Printed Name',
+                'description': "Mark Gatiss introduces Nicholas Pierpan's chilling tale of a writer's devilish pact with a mysterious man. Stars Ewan Bailey.",
+                'duration': 1800,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+            'skip': 'Episode is no longer available on BBC iPlayer Radio',
+        },
+        {
+            'url': 'http://www.bbc.co.uk/iplayer/episode/b03vhd1f/The_Voice_UK_Series_3_Blind_Auditions_5/',
+            'info_dict': {
+                'id': 'b00yng1d',
+                'ext': 'flv',
+                'title': 'The Voice UK: Series 3: Blind Auditions 5',
+                'description': "Emma Willis and Marvin Humes present the fifth set of blind auditions in the singing competition, as the coaches continue to build their teams based on voice alone.",
+                'duration': 5100,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+            'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only',
+        }
+    ]
+
+    def _extract_asx_playlist(self, connection, programme_id):
+        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 = []
+        protocol = connection.get('protocol')
+        supplier = connection.get('supplier')
+        if protocol == 'http':
+            href = connection.get('href')
+            # 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),
+                    })
+            # Direct link
+            else:
+                formats.append({
+                    'url': href,
+                    'format_id': supplier,
+                })
+        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('./{http://bbc.co.uk/2008/emp/playlist}item')
+
+    def _extract_medias(self, media_selection):
+        return media_selection.findall('./{http://bbc.co.uk/2008/mp/mediaselection}media')
+
+    def _extract_connections(self, media):
+        return media.findall('./{http://bbc.co.uk/2008/mp/mediaselection}connection')
+
+    def _extract_video(self, media, programme_id):
+        formats = []
+        vbr = int(media.get('bitrate'))
+        vcodec = media.get('encoding')
+        service = media.get('service')
+        width = int(media.get('width'))
+        height = int(media.get('height'))
+        file_size = int(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({
+                    'format_id': '%s_%s' % (service, format['format_id']),
+                    'width': width,
+                    'height': height,
+                    'vbr': vbr,
+                    'vcodec': vcodec,
+                    'filesize': file_size,
+                })
+            formats.extend(conn_formats)
+        return formats
+
+    def _extract_audio(self, media, programme_id):
+        formats = []
+        abr = int(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,
+                })
+            formats.extend(conn_formats)
+        return formats
+
+    def _extract_captions(self, media, programme_id):
+        subtitles = {}
+        for connection in self._extract_connections(media):
+            captions = self._download_xml(connection.get('href'), programme_id, 'Downloading captions')
+            lang = captions.get('{http://www.w3.org/XML/1998/namespace}lang', 'en')
+            ps = captions.findall('./{0}body/{0}div/{0}p'.format('{http://www.w3.org/2006/10/ttaf1}'))
+            srt = ''
+            for pos, p in enumerate(ps):
+                srt += '%s\r\n%s --> %s\r\n%s\r\n\r\n' % (str(pos), p.get('begin'), p.get('end'),
+                                                          p.text.strip() if p.text is not None else '')
+            subtitles[lang] = srt
+        return subtitles
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        group_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, group_id, 'Downloading video page')
+        if re.search(r'id="emp-error" class="notinuk">', webpage):
+            raise ExtractorError('Currently BBC iPlayer TV programmes are available to play in the UK only',
+                expected=True)
+
+        playlist = self._download_xml('http://www.bbc.co.uk/iplayer/playlist/%s' % group_id, group_id,
+            'Downloading playlist XML')
+
+        no_items = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}noItems')
+        if no_items is not None:
+            reason = no_items.get('reason')
+            if reason == 'preAvailability':
+                msg = 'Episode %s is not yet available' % group_id
+            elif reason == 'postAvailability':
+                msg = 'Episode %s is no longer available' % group_id
+            else:
+                msg = 'Episode %s is not available: %s' % (group_id, reason)
+            raise ExtractorError(msg, expected=True)
+
+        formats = []
+        subtitles = None
+
+        for item in self._extract_items(playlist):
+            kind = item.get('kind')
+            if kind != 'programme' and kind != 'radioProgramme':
+                continue
+            title = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}title').text
+            description = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}summary').text
+
+            programme_id = item.get('identifier')
+            duration = int(item.get('duration'))
+
+            media_selection = self._download_xml(
+                'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s'  % programme_id,
+                programme_id, 'Downloading media selection XML')
+
+            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))
+                elif kind == 'captions':
+                    subtitles = self._extract_captions(media, programme_id)
+
+        if self._downloader.params.get('listsubtitles', False):
+            self._list_available_subtitles(programme_id, subtitles)
+            return
+
+        self._sort_formats(formats)
+
+        return {
+            'id': programme_id,
+            'title': title,
+            'description': description,
+            'duration': duration,
+            'formats': formats,
+            'subtitles': subtitles,
+        }

youtube_dl/extractor/bloomberg.py

@@ -24,5 +24,7 @@ class BloombergIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         name = mobj.group('name')
         webpage = self._download_webpage(url, name)
-        ooyala_url = self._twitter_search_player(webpage)
-        return self.url_result(ooyala_url, OoyalaIE.ie_key())
+        embed_code = self._search_regex(
+            r'<source src="https?://[^/]+/[^/]+/[^/]+/([^/]+)', webpage,
+            'embed code')
+        return OoyalaIE._build_url_result(embed_code)

youtube_dl/extractor/br.py

@@ -0,0 +1,99 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+
+class BRIE(InfoExtractor):
+    IE_DESC = "Bayerischer Rundfunk Mediathek"
+    _VALID_URL = r"^https?://(?:www\.)?br\.de/mediathek/video/(?:sendungen/)?(?:[a-z0-9\-/]+/)?(?P<id>[a-z0-9\-]+)\.html$"
+    _BASE_URL = "http://www.br.de"
+
+    _TESTS = [
+        {
+            "url": "http://www.br.de/mediathek/video/anselm-gruen-114.html",
+            "md5": "c4f83cf0f023ba5875aba0bf46860df2",
+            "info_dict": {
+                "id": "2c8d81c5-6fb7-4a74-88d4-e768e5856532",
+                "ext": "mp4",
+                "title": "Feiern und Verzichten",
+                "description": "Anselm Grün: Feiern und Verzichten",
+                "uploader": "BR/Birgit Baier",
+                "upload_date": "20140301"
+            }
+        },
+        {
+            "url": "http://www.br.de/mediathek/video/sendungen/unter-unserem-himmel/unter-unserem-himmel-alpen-ueber-den-pass-100.html",
+            "md5": "ab451b09d861dbed7d7cc9ab0be19ebe",
+            "info_dict": {
+                "id": "2c060e69-3a27-4e13-b0f0-668fac17d812",
+                "ext": "mp4",
+                "title": "Über den Pass",
+                "description": "Die Eroberung der Alpen: Über den Pass",
+                "uploader": None,
+                "upload_date": None
+            }
+        }
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        display_id = mobj.group('id')
+        page = self._download_webpage(url, display_id)
+        xml_url = self._search_regex(
+            r"return BRavFramework\.register\(BRavFramework\('avPlayer_(?:[a-f0-9-]{36})'\)\.setup\({dataURL:'(/mediathek/video/[a-z0-9/~_.-]+)'}\)\);", page, "XMLURL")
+        xml = self._download_xml(self._BASE_URL + xml_url, None)
+
+        videos = []
+        for xml_video in xml.findall("video"):
+            video = {
+                "id": xml_video.get("externalId"),
+                "title": xml_video.find("title").text,
+                "formats": self._extract_formats(xml_video.find("assets")),
+                "thumbnails": self._extract_thumbnails(xml_video.find("teaserImage/variants")),
+                "description": " ".join(xml_video.find("shareTitle").text.splitlines()),
+                "webpage_url": xml_video.find("permalink").text
+            }
+            if xml_video.find("author").text:
+                video["uploader"] = xml_video.find("author").text
+            if xml_video.find("broadcastDate").text:
+                video["upload_date"] =  "".join(reversed(xml_video.find("broadcastDate").text.split(".")))
+            videos.append(video)
+
+        if len(videos) > 1:
+            self._downloader.report_warning(
+                'found multiple videos; please '
+                'report this with the video URL to http://yt-dl.org/bug')
+        if not videos:
+            raise ExtractorError('No video entries found')
+        return videos[0]
+
+    def _extract_formats(self, assets):
+        formats = [{
+            "url": asset.find("downloadUrl").text,
+            "ext": asset.find("mediaType").text,
+            "format_id": asset.get("type"),
+            "width": int(asset.find("frameWidth").text),
+            "height": int(asset.find("frameHeight").text),
+            "tbr": int(asset.find("bitrateVideo").text),
+            "abr": int(asset.find("bitrateAudio").text),
+            "vcodec": asset.find("codecVideo").text,
+            "container": asset.find("mediaType").text,
+            "filesize": int(asset.find("size").text),
+        } for asset in assets.findall("asset")
+            if asset.find("downloadUrl") is not None]
+
+        self._sort_formats(formats)
+        return formats
+
+    def _extract_thumbnails(self, variants):
+        thumbnails = [{
+            "url": self._BASE_URL + variant.find("url").text,
+            "width": int(variant.find("width").text),
+            "height": int(variant.find("height").text),
+        } for variant in variants.findall("variant")]
+        thumbnails.sort(key=lambda x: x["width"] * x["height"], reverse=True)
+        return thumbnails

youtube_dl/extractor/breakcom.py

@@ -1,18 +1,20 @@
+from __future__ import unicode_literals
+
 import re
 import json
 
 from .common import InfoExtractor
-from ..utils import determine_ext
 
 
 class BreakIE(InfoExtractor):
-    _VALID_URL = r'(?:http://)?(?:www\.)?break\.com/video/([^/]+)'
+    _VALID_URL = r'http://(?:www\.)?break\.com/video/([^/]+)'
     _TEST = {
-        u'url': u'http://www.break.com/video/when-girls-act-like-guys-2468056',
-        u'file': u'2468056.mp4',
-        u'md5': u'a3513fb1547fba4fb6cfac1bffc6c46b',
-        u'info_dict': {
-            u"title": u"When Girls Act Like D-Bags"
+        'url': 'http://www.break.com/video/when-girls-act-like-guys-2468056',
+        'md5': 'a3513fb1547fba4fb6cfac1bffc6c46b',
+        'info_dict': {
+            'id': '2468056',
+            'ext': 'mp4',
+            'title': 'When Girls Act Like D-Bags',
         }
     }
 
@@ -21,18 +23,17 @@ class BreakIE(InfoExtractor):
         video_id = mobj.group(1).split("-")[-1]
         embed_url = 'http://www.break.com/embed/%s' % video_id
         webpage = self._download_webpage(embed_url, video_id)
-        info_json = self._search_regex(r'var embedVars = ({.*?});', webpage,
-                                       u'info json', flags=re.DOTALL)
+        info_json = self._search_regex(r'var embedVars = ({.*})\s*?</script>',
+            webpage, 'info json', flags=re.DOTALL)
         info = json.loads(info_json)
         video_url = info['videoUri']
         m_youtube = re.search(r'(https?://www\.youtube\.com/watch\?v=.*)', video_url)
         if m_youtube is not None:
             return self.url_result(m_youtube.group(1), 'Youtube')
         final_url = video_url + '?' + info['AuthToken']
-        return [{
-            'id':        video_id,
-            'url':       final_url,
-            'ext':       determine_ext(final_url),
-            'title':     info['contentName'],
+        return {
+            'id': video_id,
+            'url': final_url,
+            'title': info['contentName'],
             'thumbnail': info['thumbUri'],
-        }]
+        }

youtube_dl/extractor/brightcove.py

@@ -17,6 +17,7 @@ from ..utils import (
 
     ExtractorError,
     unsmuggle_url,
+    unescapeHTML,
 )
 
 
@@ -139,7 +140,7 @@ class BrightcoveIE(InfoExtractor):
 
         url_m = re.search(r'<meta\s+property="og:video"\s+content="(http://c.brightcove.com/[^"]+)"', webpage)
         if url_m:
-            return [url_m.group(1)]
+            return [unescapeHTML(url_m.group(1))]
 
         matches = re.findall(
             r'''(?sx)<object

youtube_dl/extractor/canal13cl.py

@@ -0,0 +1,48 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class Canal13clIE(InfoExtractor):
+    _VALID_URL = r'^http://(?:www\.)?13\.cl/(?:[^/?#]+/)*(?P<id>[^/?#]+)'
+    _TEST = {
+        'url': 'http://www.13.cl/t13/nacional/el-circulo-de-hierro-de-michelle-bachelet-en-su-regreso-a-la-moneda',
+        'md5': '4cb1fa38adcad8fea88487a078831755',
+        'info_dict': {
+            'id': '1403022125',
+            'display_id': 'el-circulo-de-hierro-de-michelle-bachelet-en-su-regreso-a-la-moneda',
+            'ext': 'mp4',
+            'title': 'El "círculo de hierro" de Michelle Bachelet en su regreso a La Moneda',
+            'description': '(Foto: Agencia Uno) En nueve días más, Michelle Bachelet va a asumir por segunda vez como presidenta de la República. Entre aquellos que la acompañarán hay caras que se repiten y otras que se consolidan en su entorno de colaboradores más cercanos.',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        display_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, display_id)
+
+        title = self._html_search_meta(
+            'twitter:title', webpage, 'title', fatal=True)
+        description = self._html_search_meta(
+            'twitter:description', webpage, 'description')
+        url = self._html_search_regex(
+            r'articuloVideo = \"(.*?)\"', webpage, 'url')
+        real_id = self._search_regex(
+            r'[^0-9]([0-9]{7,})[^0-9]', url, 'id', default=display_id)
+        thumbnail = self._html_search_regex(
+            r'articuloImagen = \"(.*?)\"', webpage, 'thumbnail')
+
+        return {
+            'id': real_id,
+            'display_id': display_id,
+            'url': url,
+            'title': title,
+            'description': description,
+            'ext': 'mp4',
+            'thumbnail': thumbnail,
+        }

youtube_dl/extractor/canalc2.py

@@ -1,4 +1,6 @@
 # coding: utf-8
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -9,11 +11,12 @@ class Canalc2IE(InfoExtractor):
     _VALID_URL = r'http://.*?\.canalc2\.tv/video\.asp\?.*?idVideo=(?P<id>\d+)'
 
     _TEST = {
-        u'url': u'http://www.canalc2.tv/video.asp?idVideo=12163&voir=oui',
-        u'file': u'12163.mp4',
-        u'md5': u'060158428b650f896c542dfbb3d6487f',
-        u'info_dict': {
-            u'title': u'Terrasses du Numérique'
+        'url': 'http://www.canalc2.tv/video.asp?idVideo=12163&voir=oui',
+        'md5': '060158428b650f896c542dfbb3d6487f',
+        'info_dict': {
+            'id': '12163',
+            'ext': 'mp4',
+            'title': 'Terrasses du Numérique'
         }
     }
 
@@ -28,10 +31,11 @@ class Canalc2IE(InfoExtractor):
         video_url = 'http://vod-flash.u-strasbg.fr:8080/' + file_name
 
         title = self._html_search_regex(
-            r'class="evenement8">(.*?)</a>', webpage, u'title')
-        
-        return {'id': video_id,
-                'ext': 'mp4',
-                'url': video_url,
-                'title': title,
-                }
+            r'class="evenement8">(.*?)</a>', webpage, 'title')
+
+        return {
+            'id': video_id,
+            'ext': 'mp4',
+            'url': video_url,
+            'title': title,
+        }

youtube_dl/extractor/ceskatelevize.py

@@ -0,0 +1,126 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_request,
+    compat_urllib_parse,
+    compat_urllib_parse_urlparse,
+    ExtractorError,
+)
+
+
+class CeskaTelevizeIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.ceskatelevize\.cz/(porady|ivysilani)/(.+/)?(?P<id>[^?#]+)'
+
+    _TESTS = [
+        {
+            'url': 'http://www.ceskatelevize.cz/ivysilani/10532695142-prvni-republika/213512120230004-spanelska-chripka',
+            'info_dict': {
+                'id': '213512120230004',
+                'ext': 'flv',
+                'title': 'První republika: Španělská chřipka',
+                'duration': 3107.4,
+            },
+            'params': {
+                'skip_download': True,  # requires rtmpdump
+            },
+            'skip': 'Works only from Czech Republic.',
+        },
+        {
+            'url': 'http://www.ceskatelevize.cz/ivysilani/1030584952-tsatsiki-maminka-a-policajt',
+            'info_dict': {
+                'id': '20138143440',
+                'ext': 'flv',
+                'title': 'Tsatsiki, maminka a policajt',
+                'duration': 6754.1,
+            },
+            'params': {
+                'skip_download': True,  # requires rtmpdump
+            },
+            'skip': 'Works only from Czech Republic.',
+        },
+        {
+            'url': 'http://www.ceskatelevize.cz/ivysilani/10532695142-prvni-republika/bonus/14716-zpevacka-z-duparny-bobina',
+            'info_dict': {
+                'id': '14716',
+                'ext': 'flv',
+                'title': 'První republika: Zpěvačka z Dupárny Bobina',
+                'duration': 90,
+            },
+            'params': {
+                'skip_download': True,  # requires rtmpdump
+            },
+        },
+    ]
+
+    def _real_extract(self, url):
+        url = url.replace('/porady/', '/ivysilani/').replace('/video/', '')
+
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+
+        NOT_AVAILABLE_STRING = 'This content is not available at your territory due to limited copyright.'
+        if '%s</p>' % NOT_AVAILABLE_STRING in webpage:
+            raise ExtractorError(NOT_AVAILABLE_STRING, expected=True)
+
+        typ = self._html_search_regex(r'getPlaylistUrl\(\[\{"type":"(.+?)","id":".+?"\}\],', webpage, 'type')
+        episode_id = self._html_search_regex(r'getPlaylistUrl\(\[\{"type":".+?","id":"(.+?)"\}\],', webpage, 'episode_id')
+
+        data = {
+            'playlist[0][type]': typ,
+            'playlist[0][id]': episode_id,
+            'requestUrl': compat_urllib_parse_urlparse(url).path,
+            'requestSource': 'iVysilani',
+        }
+
+        req = compat_urllib_request.Request('http://www.ceskatelevize.cz/ivysilani/ajax/get-playlist-url',
+                                            data=compat_urllib_parse.urlencode(data))
+
+        req.add_header('Content-type', 'application/x-www-form-urlencoded')
+        req.add_header('x-addr', '127.0.0.1')
+        req.add_header('X-Requested-With', 'XMLHttpRequest')
+        req.add_header('Referer', url)
+
+        playlistpage = self._download_json(req, video_id)
+
+        req = compat_urllib_request.Request(compat_urllib_parse.unquote(playlistpage['url']))
+        req.add_header('Referer', url)
+
+        playlist = self._download_xml(req, video_id)
+        
+        formats = []
+        for i in playlist.find('smilRoot/body'):
+            if 'AD' not in i.attrib['id']:
+                base_url = i.attrib['base']
+                parsedurl = compat_urllib_parse_urlparse(base_url)
+                duration = i.attrib['duration']
+
+                for video in i.findall('video'):
+                    if video.attrib['label'] != 'AD':
+                        format_id = video.attrib['label']
+                        play_path = video.attrib['src']
+                        vbr = int(video.attrib['system-bitrate'])
+
+                        formats.append({
+                            'format_id': format_id,
+                            'url': base_url,
+                            'vbr': vbr,
+                            'play_path': play_path,
+                            'app': parsedurl.path[1:] + '?' + parsedurl.query,
+                            'rtmp_live': True,
+                            'ext': 'flv',
+                        })
+
+        self._sort_formats(formats)
+
+        return {
+            'id': episode_id,
+            'title': self._html_search_regex(r'<title>(.+?) — iVysílání — Česká televize</title>', webpage, 'title'),
+            'duration': float(duration),
+            'formats': formats,
+        }

youtube_dl/extractor/channel9.py

@@ -15,14 +15,15 @@ class Channel9IE(InfoExtractor):
     '''
     IE_DESC = 'Channel 9'
     IE_NAME = 'channel9'
-    _VALID_URL = r'^https?://(?:www\.)?channel9\.msdn\.com/(?P<contentpath>.+)/?'
+    _VALID_URL = r'https?://(?:www\.)?channel9\.msdn\.com/(?P<contentpath>.+)/?'
 
     _TESTS = [
         {
             'url': 'http://channel9.msdn.com/Events/TechEd/Australia/2013/KOS002',
-            'file': 'Events_TechEd_Australia_2013_KOS002.mp4',
             'md5': 'bbd75296ba47916b754e73c3a4bbdf10',
             'info_dict': {
+                'id': 'Events/TechEd/Australia/2013/KOS002',
+                'ext': 'mp4',
                 'title': 'Developer Kick-Off Session: Stuff We Love',
                 'description': 'md5:c08d72240b7c87fcecafe2692f80e35f',
                 'duration': 4576,
@@ -35,9 +36,10 @@ class Channel9IE(InfoExtractor):
         },
         {
             'url': 'http://channel9.msdn.com/posts/Self-service-BI-with-Power-BI-nuclear-testing',
-            'file': 'posts_Self-service-BI-with-Power-BI-nuclear-testing.mp4',
             'md5': 'b43ee4529d111bc37ba7ee4f34813e68',
             'info_dict': {
+                'id': 'posts/Self-service-BI-with-Power-BI-nuclear-testing',
+                'ext': 'mp4',
                 'title': 'Self-service BI with Power BI - nuclear testing',
                 'description': 'md5:d1e6ecaafa7fb52a2cacdf9599829f5b',
                 'duration': 1540,

youtube_dl/extractor/chilloutzone.py

@@ -0,0 +1,97 @@
+from __future__ import unicode_literals
+
+import re
+import base64
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    ExtractorError
+)
+
+
+class ChilloutzoneIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?chilloutzone\.net/video/(?P<id>[\w|-]+)\.html'
+    _TESTS = [{
+        'url': 'http://www.chilloutzone.net/video/enemene-meck-alle-katzen-weg.html',
+        'md5': 'a76f3457e813ea0037e5244f509e66d1',
+        'info_dict': {
+            'id': 'enemene-meck-alle-katzen-weg',
+            'ext': 'mp4',
+            'title': 'Enemene Meck - Alle Katzen weg',
+            'description': 'Ist das der Umkehrschluss des Niesenden Panda-Babys?',
+        },
+    }, {
+        'note': 'Video hosted at YouTube',
+        'url': 'http://www.chilloutzone.net/video/eine-sekunde-bevor.html',
+        'info_dict': {
+            'id': '1YVQaAgHyRU',
+            'ext': 'mp4',
+            'title': '16 Photos Taken 1 Second Before Disaster',
+            'description': 'md5:58a8fcf6a459fe0a08f54140f0ad1814',
+            'uploader': 'BuzzFeedVideo',
+            'uploader_id': 'BuzzFeedVideo',
+            'upload_date': '20131105',
+        },
+    }, {
+        'note': 'Video hosted at Vimeo',
+        'url': 'http://www.chilloutzone.net/video/icon-blending.html',
+        'md5': '2645c678b8dc4fefcc0e1b60db18dac1',
+        'info_dict': {
+            'id': '85523671',
+            'ext': 'mp4',
+            'title': 'The Sunday Times - Icons',
+            'description': 'md5:3e1c0dc6047498d6728dcdaad0891762',
+            'uploader': 'Us',
+            'uploader_id': 'usfilms',
+            'upload_date': '20140131'
+        },
+    }]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+
+        base64_video_info = self._html_search_regex(
+            r'var cozVidData = "(.+?)";', webpage, 'video data')
+        decoded_video_info = base64.b64decode(base64_video_info).decode("utf-8")
+        video_info_dict = json.loads(decoded_video_info)
+
+        # get video information from dict
+        video_url = video_info_dict['mediaUrl']
+        description = clean_html(video_info_dict.get('description'))
+        title = video_info_dict['title']
+        native_platform = video_info_dict['nativePlatform']
+        native_video_id = video_info_dict['nativeVideoId']
+        source_priority = video_info_dict['sourcePriority']
+
+        # If nativePlatform is None a fallback mechanism is used (i.e. youtube embed)
+        if native_platform is None:
+            youtube_url = self._html_search_regex(
+                r'<iframe.* src="((?:https?:)?//(?:[^.]+\.)?youtube\.com/.+?)"',
+                webpage, 'fallback video URL', default=None)
+            if youtube_url is not None:
+                return self.url_result(youtube_url, ie='Youtube')
+
+        # Non Fallback: Decide to use native source (e.g. youtube or vimeo) or
+        # the own CDN
+        if source_priority == 'native':
+            if native_platform == 'youtube':
+                return self.url_result(native_video_id, ie='Youtube')
+            if native_platform == 'vimeo':
+                return self.url_result(
+                    'http://vimeo.com/' + native_video_id, ie='Vimeo')
+
+        if not video_url:
+            raise ExtractorError('No video found')
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'ext': 'mp4',
+            'title': title,
+            'description': description,
+        }

youtube_dl/extractor/cinemassacre.py

@@ -1,4 +1,5 @@
 # encoding: utf-8
+from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
@@ -8,73 +9,63 @@ from ..utils import (
 
 
 class CinemassacreIE(InfoExtractor):
-    _VALID_URL = r'(?:http://)?(?:www\.)?(?P<url>cinemassacre\.com/(?P<date_Y>[0-9]{4})/(?P<date_m>[0-9]{2})/(?P<date_d>[0-9]{2})/.+?)(?:[/?].*)?'
-    _TESTS = [{
-        u'url': u'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/',
-        u'file': u'19911.flv',
-        u'info_dict': {
-            u'upload_date': u'20121110',
-            u'title': u'“Angry Video Game Nerd: The Movie” – Trailer',
-            u'description': u'md5:fb87405fcb42a331742a0dce2708560b',
+    _VALID_URL = r'http://(?:www\.)?cinemassacre\.com/(?P<date_Y>[0-9]{4})/(?P<date_m>[0-9]{2})/(?P<date_d>[0-9]{2})/.+?'
+    _TESTS = [
+        {
+            'url': 'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/',
+            'file': '19911.mp4',
+            'md5': 'fde81fbafaee331785f58cd6c0d46190',
+            'info_dict': {
+                'upload_date': '20121110',
+                'title': '“Angry Video Game Nerd: The Movie” – Trailer',
+                'description': 'md5:fb87405fcb42a331742a0dce2708560b',
+            },
         },
-        u'params': {
-            # rtmp download
-            u'skip_download': True,
-        },
-    },
-    {
-        u'url': u'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940',
-        u'file': u'521be8ef82b16.flv',
-        u'info_dict': {
-            u'upload_date': u'20131002',
-            u'title': u'The Mummy’s Hand (1940)',
-        },
-        u'params': {
-            # rtmp download
-            u'skip_download': True,
-        },
-    }]
+        {
+            'url': 'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940',
+            'file': '521be8ef82b16.mp4',
+            'md5': 'd72f10cd39eac4215048f62ab477a511',
+            'info_dict': {
+                'upload_date': '20131002',
+                'title': 'The Mummy’s Hand (1940)',
+            },
+        }
+    ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
 
-        webpage_url = u'http://' + mobj.group('url')
-        webpage = self._download_webpage(webpage_url, None) # Don't know video id yet
+        webpage = self._download_webpage(url, None)  # Don't know video id yet
         video_date = mobj.group('date_Y') + mobj.group('date_m') + mobj.group('date_d')
         mobj = re.search(r'src="(?P<embed_url>http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?id=(?:Cinemassacre-)?(?P<video_id>.+?))"', webpage)
         if not mobj:
-            raise ExtractorError(u'Can\'t extract embed url and video id')
-        playerdata_url = mobj.group(u'embed_url')
-        video_id = mobj.group(u'video_id')
+            raise ExtractorError('Can\'t extract embed url and video id')
+        playerdata_url = mobj.group('embed_url')
+        video_id = mobj.group('video_id')
 
         video_title = self._html_search_regex(r'<title>(?P<title>.+?)\|',
-            webpage, u'title')
+            webpage, 'title')
         video_description = self._html_search_regex(r'<div class="entry-content">(?P<description>.+?)</div>',
-            webpage, u'description', flags=re.DOTALL, fatal=False)
+            webpage, 'description', flags=re.DOTALL, fatal=False)
         if len(video_description) == 0:
             video_description = None
 
         playerdata = self._download_webpage(playerdata_url, video_id)
-        url = self._html_search_regex(r'\'streamer\': \'(?P<url>[^\']+)\'', playerdata, u'url')
 
-        sd_file = self._html_search_regex(r'\'file\': \'(?P<sd_file>[^\']+)\'', playerdata, u'sd_file')
-        hd_file = self._html_search_regex(r'\'?file\'?: "(?P<hd_file>[^"]+)"', playerdata, u'hd_file')
-        video_thumbnail = self._html_search_regex(r'\'image\': \'(?P<thumbnail>[^\']+)\'', playerdata, u'thumbnail', fatal=False)
+        sd_url = self._html_search_regex(r'file: \'(?P<sd_file>[^\']+)\', label: \'SD\'', playerdata, 'sd_file')
+        hd_url = self._html_search_regex(r'file: \'(?P<hd_file>[^\']+)\', label: \'HD\'', playerdata, 'hd_file')
+        video_thumbnail = self._html_search_regex(r'image: \'(?P<thumbnail>[^\']+)\'', playerdata, 'thumbnail', fatal=False)
 
         formats = [
             {
-                'url': url,
-                'play_path': 'mp4:' + sd_file,
-                'rtmp_live': True, # workaround
-                'ext': 'flv',
+                'url': sd_url,
+                'ext': 'mp4',
                 'format': 'sd',
                 'format_id': 'sd',
             },
             {
-                'url': url,
-                'play_path': 'mp4:' + hd_file,
-                'rtmp_live': True, # workaround
-                'ext': 'flv',
+                'url': hd_url,
+                'ext': 'mp4',
                 'format': 'hd',
                 'format_id': 'hd',
             },

youtube_dl/extractor/cnn.py

@@ -6,6 +6,7 @@ from .common import InfoExtractor
 from ..utils import (
     int_or_none,
     parse_duration,
+    url_basename,
 )
 
 
@@ -98,3 +99,28 @@ class CNNIE(InfoExtractor):
             'duration': duration,
             'upload_date': upload_date,
         }
+
+
+class CNNBlogsIE(InfoExtractor):
+    _VALID_URL = r'https?://[^\.]+\.blogs\.cnn\.com/.+'
+    _TEST = {
+        'url': 'http://reliablesources.blogs.cnn.com/2014/02/09/criminalizing-journalism/',
+        'md5': '3e56f97b0b6ffb4b79f4ea0749551084',
+        'info_dict': {
+            'id': 'bestoftv/2014/02/09/criminalizing-journalism.cnn',
+            'ext': 'mp4',
+            'title': 'Criminalizing journalism?',
+            'description': 'Glenn Greenwald responds to comments made this week on Capitol Hill that journalists could be criminal accessories.',
+            'upload_date': '20140209',
+        },
+        'add_ie': ['CNN'],
+    }
+
+    def _real_extract(self, url):
+        webpage = self._download_webpage(url, url_basename(url))
+        cnn_url = self._html_search_regex(r'data-url="(.+?)"', webpage, 'cnn url')
+        return {
+            '_type': 'url',
+            'url': cnn_url,
+            'ie_key': CNNIE.ie_key(),
+        }

youtube_dl/extractor/collegehumor.py

@@ -17,8 +17,9 @@ class CollegeHumorIE(InfoExtractor):
             'id': '6902724',
             'ext': 'mp4',
             'title': 'Comic-Con Cosplay Catastrophe',
-            'description': 'Fans get creative this year',
+            'description': "Fans get creative this year at San Diego.  Too creative.  And yes, that's really Joss Whedon.",
             'age_limit': 13,
+            'duration': 187,
         },
     },
     {
@@ -28,22 +29,22 @@ class CollegeHumorIE(InfoExtractor):
             'id': '3505939',
             'ext': 'mp4',
             'title': 'Font Conference',
-            'description': 'This video wasn\'t long enough,',
+            'description': "This video wasn't long enough, so we made it double-spaced.",
             'age_limit': 10,
             'duration': 179,
         },
     },
     # embedded youtube video
     {
-        'url': 'http://www.collegehumor.com/embed/6950457',
+        'url': 'http://www.collegehumor.com/embed/6950306',
         'info_dict': {
-            'id': 'W5gMp3ZjYg4',
+            'id': 'Z-bao9fg6Yc',
             'ext': 'mp4',
-            'title': 'Funny Dogs Protecting Babies Compilation 2014 [NEW HD]',
-            'uploader': 'Funnyplox TV',
-            'uploader_id': 'funnyploxtv',
-            'description': 'md5:11812366244110c3523968aa74f02521',
-            'upload_date': '20140128',
+            'title': 'Young Americans Think President John F. Kennedy Died THIS MORNING IN A CAR ACCIDENT!!!',
+            'uploader': 'Mark Dice',
+            'uploader_id': 'MarkDice',
+            'description': 'md5:62c3dab9351fac7bb44b53b69511d87f',
+            'upload_date': '20140127',
         },
         'params': {
             'skip_download': True,
@@ -87,6 +88,7 @@ class CollegeHumorIE(InfoExtractor):
         self._sort_formats(formats)
 
         duration = int_or_none(vdata.get('duration'), 1000)
+        like_count = int_or_none(vdata.get('likes'))
 
         return {
             'id': video_id,
@@ -96,4 +98,5 @@ class CollegeHumorIE(InfoExtractor):
             'formats': formats,
             'age_limit': age_limit,
             'duration': duration,
+            'like_count': like_count,
         }

youtube_dl/extractor/comedycentral.py

@@ -14,7 +14,7 @@ from ..utils import (
 
 
 class ComedyCentralIE(MTVServicesInfoExtractor):
-    _VALID_URL = r'''(?x)https?://(?:www\.)?comedycentral\.com/
+    _VALID_URL = r'''(?x)https?://(?:www\.)?(comedycentral|cc)\.com/
         (video-clips|episodes|cc-studios|video-collections)
         /(?P<title>.*)'''
     _FEED_URL = 'http://comedycentral.com/feeds/mrss/'

youtube_dl/extractor/common.py

@@ -74,7 +74,7 @@ class InfoExtractor(object):
                                  "http", "https", "rtsp", "rtmp", "m3u8" or so.
                     * preference Order number of this format. If this field is
                                  present and not None, the formats get sorted
-                                 by this field.
+                                 by this field, regardless of all other values.
                                  -1 for default (order by other properties),
                                  -2 or smaller for less than default.
                     * quality    Order number of the video quality of this
@@ -88,12 +88,18 @@ class InfoExtractor(object):
 
     The following fields are optional:
 
+    display_id      An alternative identifier for the video, not necessarily
+                    unique, but available before title. Typically, id is
+                    something like "4234987", title "Dancing naked mole rats",
+                    and display_id "dancing-naked-mole-rats"
     thumbnails:     A list of dictionaries (with the entries "resolution" and
                     "url") for the varying thumbnails
     thumbnail:      Full URL to a video thumbnail image.
     description:    One-line video description.
     uploader:       Full name of the video uploader.
+    timestamp:      UNIX timestamp of the moment the video became available.
     upload_date:    Video upload date (YYYYMMDD).
+                    If not explicitly set, calculated from timestamp.
     uploader_id:    Nickname or id of the video uploader.
     location:       Physical location of the video.
     subtitles:      The subtitle file contents as a dictionary in the format
@@ -114,9 +120,6 @@ class InfoExtractor(object):
     _real_extract() methods and define a _VALID_URL regexp.
     Probably, they should also be added to the list of extractors.
 
-    _real_extract() must return a *list* of information dictionaries as
-    described above.
-
     Finally, the _WORKING attribute should be set to False for broken IEs
     in order to warn the users and skip the tests.
     """
@@ -271,8 +274,11 @@ class InfoExtractor(object):
 
     def _download_json(self, url_or_request, video_id,
                        note=u'Downloading JSON metadata',
-                       errnote=u'Unable to download JSON metadata'):
+                       errnote=u'Unable to download JSON metadata',
+                       transform_source=None):
         json_string = self._download_webpage(url_or_request, video_id, note, errnote)
+        if transform_source:
+            json_string = transform_source(json_string)
         try:
             return json.loads(json_string)
         except ValueError as ve:
@@ -429,14 +435,14 @@ class InfoExtractor(object):
         if secure: regexes = self._og_regexes('video:secure_url') + regexes
         return self._html_search_regex(regexes, html, name, **kargs)
 
-    def _html_search_meta(self, name, html, display_name=None):
+    def _html_search_meta(self, name, html, display_name=None, fatal=False):
         if display_name is None:
             display_name = name
         return self._html_search_regex(
             r'''(?ix)<meta
                     (?=[^>]+(?:itemprop|name|property)=["\']%s["\'])
                     [^>]+content=["\']([^"\']+)["\']''' % re.escape(name),
-            html, display_name, fatal=False)
+            html, display_name, fatal=fatal)
 
     def _dc_search_uploader(self, html):
         return self._html_search_meta('dc.creator', html, 'uploader')

youtube_dl/extractor/crunchyroll.py

@@ -1,7 +1,11 @@
 # encoding: utf-8
 from __future__ import unicode_literals
 
-import re, base64, zlib
+import re
+import json
+import base64
+import zlib
+
 from hashlib import sha1
 from math import pow, sqrt, floor
 from .common import InfoExtractor
@@ -19,13 +23,15 @@ from ..aes import (
     inc,
 )
 
+
 class CrunchyrollIE(InfoExtractor):
-    _VALID_URL = r'(?:https?://)?(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?:[^/]*/[^/?&]*?|media/\?id=)(?P<video_id>[0-9]+))(?:[/?&]|$)'
-    _TESTS = [{
+    _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?:[^/]*/[^/?&]*?|media/\?id=)(?P<video_id>[0-9]+))(?:[/?&]|$)'
+    _TEST = {
         'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
-        'file': '645513.flv',
         #'md5': 'b1639fd6ddfaa43788c85f6d1dddd412',
         'info_dict': {
+            'id': '645513',
+            'ext': 'flv',
             'title': 'Wanna be the Strongest in the World Episode 1 – An Idol-Wrestler is Born!',
             'description': 'md5:2d17137920c64f2f49981a7797d275ef',
             'thumbnail': 'http://img1.ak.crunchyroll.com/i/spire1-tmb/20c6b5e10f1a47b10516877d3c039cae1380951166_full.jpg',
@@ -36,7 +42,7 @@ class CrunchyrollIE(InfoExtractor):
             # rtmp
             'skip_download': True,
         },
-    }]
+    }
 
     _FORMAT_IDS = {
         '360': ('60', '106'),
@@ -68,7 +74,7 @@ class CrunchyrollIE(InfoExtractor):
             shaHash = bytes_to_intlist(sha1(prefix + str(num4).encode('ascii')).digest())
             # Extend 160 Bit hash to 256 Bit
             return shaHash + [0] * 12
-        
+
         key = obfuscate_key(id)
         class Counter:
             __value = iv
@@ -80,9 +86,8 @@ class CrunchyrollIE(InfoExtractor):
         return zlib.decompress(decrypted_data)
 
     def _convert_subtitles_to_srt(self, subtitles):
-        i=1
         output = ''
-        for start, end, text in re.findall(r'<event [^>]*?start="([^"]+)" [^>]*?end="([^"]+)" [^>]*?text="([^"]+)"[^>]*?>', subtitles):
+        for i, (start, end, text) in enumerate(re.findall(r'<event [^>]*?start="([^"]+)" [^>]*?end="([^"]+)" [^>]*?text="([^"]+)"[^>]*?>', subtitles), 1):
             start = start.replace('.', ',')
             end = end.replace('.', ',')
             text = clean_html(text)
@@ -90,7 +95,6 @@ class CrunchyrollIE(InfoExtractor):
             if not text:
                 continue
             output += '%d\n%s --> %s\n%s\n\n' % (i, start, end, text)
-            i+=1
         return output
 
     def _real_extract(self,url):
@@ -108,6 +112,12 @@ class CrunchyrollIE(InfoExtractor):
         if note_m:
             raise ExtractorError(note_m)
 
+        mobj = re.search(r'Page\.messaging_box_controller\.addItems\(\[(?P<msg>{.+?})\]\)', webpage)
+        if mobj:
+            msg = json.loads(mobj.group('msg'))
+            if msg.get('type') == 'error':
+                raise ExtractorError('crunchyroll returned error: %s' % msg['message_body'], expected=True)
+
         video_title = self._html_search_regex(r'<h1[^>]*>(.+?)</h1>', webpage, 'video_title', flags=re.DOTALL)
         video_title = re.sub(r' {2,}', ' ', video_title)
         video_description = self._html_search_regex(r'"description":"([^"]+)', webpage, 'video_description', default='')
@@ -123,7 +133,7 @@ class CrunchyrollIE(InfoExtractor):
         playerdata_req.data = compat_urllib_parse.urlencode({'current_page': webpage_url})
         playerdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
         playerdata = self._download_webpage(playerdata_req, video_id, note='Downloading media info')
-        
+
         stream_id = self._search_regex(r'<media_id>([^<]+)', playerdata, 'stream_id')
         video_thumbnail = self._search_regex(r'<episode_image_url>([^<]+)', playerdata, 'thumbnail', fatal=False)
 
@@ -161,7 +171,7 @@ class CrunchyrollIE(InfoExtractor):
             data = base64.b64decode(data)
 
             subtitle = self._decrypt_subtitles(data, iv, id).decode('utf-8')
-            lang_code = self._search_regex(r'lang_code=\'([^\']+)', subtitle, 'subtitle_lang_code', fatal=False)
+            lang_code = self._search_regex(r'lang_code=["\']([^"\']+)', subtitle, 'subtitle_lang_code', fatal=False)
             if not lang_code:
                 continue
             subtitles[lang_code] = self._convert_subtitles_to_srt(subtitle)

youtube_dl/extractor/cspan.py

@@ -10,9 +10,9 @@ from ..utils import (
 
 
 class CSpanIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?c-span\.org/video/\?(?P<id>\d+)'
+    _VALID_URL = r'http://(?:www\.)?c-span\.org/video/\?(?P<id>[0-9a-f]+)'
     IE_DESC = 'C-SPAN'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.c-span.org/video/?313572-1/HolderonV',
         'md5': '8e44ce11f0f725527daccc453f553eb0',
         'info_dict': {
@@ -22,13 +22,24 @@ class CSpanIE(InfoExtractor):
             'description': 'Attorney General Eric Holder spoke to reporters following the Supreme Court decision in Shelby County v. Holder in which the court ruled that the preclearance provisions of the Voting Rights Act could not be enforced until Congress established new guidelines for review.',
         },
         'skip': 'Regularly fails on travis, for unknown reasons',
-    }
+    }, {
+        'url': 'http://www.c-span.org/video/?c4486943/cspan-international-health-care-models',
+        # For whatever reason, the served video alternates between
+        # two different ones
+        #'md5': 'dbb0f047376d457f2ab8b3929cbb2d0c',
+        'info_dict': {
+            'id': '340723',
+            'ext': 'mp4',
+            'title': 'International Health Care Models',
+            'description': 'md5:7a985a2d595dba00af3d9c9f0783c967',
+        }
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         page_id = mobj.group('id')
         webpage = self._download_webpage(url, page_id)
-        video_id = self._search_regex(r'data-progid=\'(\d+)\'>', webpage, 'video id')
+        video_id = self._search_regex(r'progid=\'?([0-9]+)\'?>', webpage, 'video id')
 
         description = self._html_search_regex(
             [

youtube_dl/extractor/dailymotion.py

@@ -12,6 +12,7 @@ from ..utils import (
     get_element_by_id,
     orderedSet,
     str_to_int,
+    int_or_none,
 
     ExtractorError,
 )
@@ -124,7 +125,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
             if video_url is not None:
                 m_size = re.search(r'H264-(\d+)x(\d+)', video_url)
                 if m_size is not None:
-                    width, height = m_size.group(1), m_size.group(2)
+                    width, height = map(int_or_none, (m_size.group(1), m_size.group(2)))
                 else:
                     width, height = None, None
                 formats.append({

youtube_dl/extractor/daum.py

@@ -1,25 +1,28 @@
 # encoding: utf-8
+
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
 from ..utils import (
     compat_urllib_parse,
-    determine_ext,
 )
 
 
 class DaumIE(InfoExtractor):
     _VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/.*?clipid=(?P<id>\d+)'
-    IE_NAME = u'daum.net'
+    IE_NAME = 'daum.net'
 
     _TEST = {
-        u'url': u'http://tvpot.daum.net/clip/ClipView.do?clipid=52554690',
-        u'file': u'52554690.mp4',
-        u'info_dict': {
-            u'title': u'DOTA 2GETHER 시즌2 6회 - 2부',
-            u'description': u'DOTA 2GETHER 시즌2 6회 - 2부',
-            u'upload_date': u'20130831',
-            u'duration': 3868,
+        'url': 'http://tvpot.daum.net/clip/ClipView.do?clipid=52554690',
+        'info_dict': {
+            'id': '52554690',
+            'ext': 'mp4',
+            'title': 'DOTA 2GETHER 시즌2 6회 - 2부',
+            'description': 'DOTA 2GETHER 시즌2 6회 - 2부',
+            'upload_date': '20130831',
+            'duration': 3868,
         },
     }
 
@@ -30,14 +33,14 @@ class DaumIE(InfoExtractor):
         webpage = self._download_webpage(canonical_url, video_id)
         full_id = self._search_regex(
             r'<iframe src="http://videofarm.daum.net/controller/video/viewer/Video.html\?.*?vid=(.+?)[&"]',
-            webpage, u'full id')
+            webpage, 'full id')
         query = compat_urllib_parse.urlencode({'vid': full_id})
         info = self._download_xml(
             'http://tvpot.daum.net/clip/ClipInfoXml.do?' + query, video_id,
-            u'Downloading video info')
+            'Downloading video info')
         urls = self._download_xml(
             'http://videofarm.daum.net/controller/api/open/v1_2/MovieData.apixml?' + query,
-            video_id, u'Downloading video formats info')
+            video_id, 'Downloading video formats info')
 
         self.to_screen(u'%s: Getting video urls' % video_id)
         formats = []
@@ -53,7 +56,6 @@ class DaumIE(InfoExtractor):
             format_url = url_doc.find('result/url').text
             formats.append({
                 'url': format_url,
-                'ext': determine_ext(format_url),
                 'format_id': profile,
             })
 

youtube_dl/extractor/depositfiles.py

@@ -1,60 +0,0 @@
-import re
-import os
-import socket
-
-from .common import InfoExtractor
-from ..utils import (
-    compat_http_client,
-    compat_str,
-    compat_urllib_error,
-    compat_urllib_parse,
-    compat_urllib_request,
-
-    ExtractorError,
-)
-
-
-class DepositFilesIE(InfoExtractor):
-    """Information extractor for depositfiles.com"""
-
-    _VALID_URL = r'(?:http://)?(?:\w+\.)?depositfiles\.com/(?:../(?#locale))?files/(.+)'
-
-    def _real_extract(self, url):
-        file_id = url.split('/')[-1]
-        # Rebuild url in english locale
-        url = 'http://depositfiles.com/en/files/' + file_id
-
-        # Retrieve file webpage with 'Free download' button pressed
-        free_download_indication = {'gateway_result' : '1'}
-        request = compat_urllib_request.Request(url, compat_urllib_parse.urlencode(free_download_indication))
-        try:
-            self.report_download_webpage(file_id)
-            webpage = compat_urllib_request.urlopen(request).read()
-        except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
-            raise ExtractorError(u'Unable to retrieve file webpage: %s' % compat_str(err))
-
-        # Search for the real file URL
-        mobj = re.search(r'<form action="(http://fileshare.+?)"', webpage)
-        if (mobj is None) or (mobj.group(1) is None):
-            # Try to figure out reason of the error.
-            mobj = re.search(r'<strong>(Attention.*?)</strong>', webpage, re.DOTALL)
-            if (mobj is not None) and (mobj.group(1) is not None):
-                restriction_message = re.sub('\s+', ' ', mobj.group(1)).strip()
-                raise ExtractorError(u'%s' % restriction_message)
-            else:
-                raise ExtractorError(u'Unable to extract download URL from: %s' % url)
-
-        file_url = mobj.group(1)
-        file_extension = os.path.splitext(file_url)[1][1:]
-
-        # Search for file title
-        file_title = self._search_regex(r'<b title="(.*?)">', webpage, u'title')
-
-        return [{
-            'id':       file_id.decode('utf-8'),
-            'url':      file_url.decode('utf-8'),
-            'uploader': None,
-            'upload_date':  None,
-            'title':    file_title,
-            'ext':      file_extension.decode('utf-8'),
-        }]

youtube_dl/extractor/dotsub.py

@@ -1,41 +1,42 @@
+from __future__ import unicode_literals
+
 import re
-import json
 import time
 
 from .common import InfoExtractor
 
 
 class DotsubIE(InfoExtractor):
-    _VALID_URL = r'(?:http://)?(?:www\.)?dotsub\.com/view/([^/]+)'
+    _VALID_URL = r'http://(?:www\.)?dotsub\.com/view/(?P<id>[^/]+)'
     _TEST = {
-        u'url': u'http://dotsub.com/view/aed3b8b2-1889-4df5-ae63-ad85f5572f27',
-        u'file': u'aed3b8b2-1889-4df5-ae63-ad85f5572f27.flv',
-        u'md5': u'0914d4d69605090f623b7ac329fea66e',
-        u'info_dict': {
-            u"title": u"Pyramids of Waste (2010), AKA The Lightbulb Conspiracy - Planned obsolescence documentary",
-            u"uploader": u"4v4l0n42",
-            u'description': u'Pyramids of Waste (2010) also known as "The lightbulb conspiracy" is a documentary about how our economic system based on consumerism  and planned obsolescence is breaking our planet down.\r\n\r\nSolutions to this can be found at:\r\nhttp://robotswillstealyourjob.com\r\nhttp://www.federicopistono.org\r\n\r\nhttp://opensourceecology.org\r\nhttp://thezeitgeistmovement.com',
-            u'thumbnail': u'http://dotsub.com/media/aed3b8b2-1889-4df5-ae63-ad85f5572f27/p',
-            u'upload_date': u'20101213',
+        'url': 'http://dotsub.com/view/aed3b8b2-1889-4df5-ae63-ad85f5572f27',
+        'md5': '0914d4d69605090f623b7ac329fea66e',
+        'info_dict': {
+            'id': 'aed3b8b2-1889-4df5-ae63-ad85f5572f27',
+            'ext': 'flv',
+            'title': 'Pyramids of Waste (2010), AKA The Lightbulb Conspiracy - Planned obsolescence documentary',
+            'uploader': '4v4l0n42',
+            'description': 'Pyramids of Waste (2010) also known as "The lightbulb conspiracy" is a documentary about how our economic system based on consumerism  and planned obsolescence is breaking our planet down.\r\n\r\nSolutions to this can be found at:\r\nhttp://robotswillstealyourjob.com\r\nhttp://www.federicopistono.org\r\n\r\nhttp://opensourceecology.org\r\nhttp://thezeitgeistmovement.com',
+            'thumbnail': 'http://dotsub.com/media/aed3b8b2-1889-4df5-ae63-ad85f5572f27/p',
+            'upload_date': '20101213',
         }
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group(1)
-        info_url = "https://dotsub.com/api/media/%s/metadata" %(video_id)
-        webpage = self._download_webpage(info_url, video_id)
-        info = json.loads(webpage)
+        video_id = mobj.group('id')
+        info_url = "https://dotsub.com/api/media/%s/metadata" % video_id
+        info = self._download_json(info_url, video_id)
         date = time.gmtime(info['dateCreated']/1000) # The timestamp is in miliseconds
 
-        return [{
-            'id':          video_id,
-            'url':         info['mediaURI'],
-            'ext':         'flv',
-            'title':       info['title'],
-            'thumbnail':   info['screenshotURI'],
+        return {
+            'id': video_id,
+            'url': info['mediaURI'],
+            'ext': 'flv',
+            'title': info['title'],
+            'thumbnail': info['screenshotURI'],
             'description': info['description'],
-            'uploader':    info['user'],
-            'view_count':  info['numberOfViews'],
-            'upload_date': u'%04i%02i%02i' % (date.tm_year, date.tm_mon, date.tm_mday),
-        }]
+            'uploader': info['user'],
+            'view_count': info['numberOfViews'],
+            'upload_date': '%04i%02i%02i' % (date.tm_year, date.tm_mon, date.tm_mday),
+        }

youtube_dl/extractor/dropbox.py

@@ -10,11 +10,12 @@ from .common import InfoExtractor
 class DropboxIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?dropbox[.]com/s/(?P<id>[a-zA-Z0-9]{15})/(?P<title>[^?#]*)'
     _TEST = {
-        'url': 'https://www.dropbox.com/s/mcnzehi9wo55th4/20131219_085616.mp4',
-        'file': 'mcnzehi9wo55th4.mp4',
-        'md5': 'f6d65b1b326e82fd7ab7720bea3dacae',
+        'url': 'https://www.dropbox.com/s/0qr9sai2veej4f8/THE_DOCTOR_GAMES.mp4',
+        'md5': '8ae17c51172fb7f93bdd6a214cc8c896',
         'info_dict': {
-            'title': '20131219_085616'
+            'id': '0qr9sai2veej4f8',
+            'ext': 'mp4',
+            'title': 'THE_DOCTOR_GAMES'
         }
     }
 

youtube_dl/extractor/elpais.py

@@ -9,7 +9,7 @@ from ..utils import unified_strdate
 
 class ElPaisIE(InfoExtractor):
     _VALID_URL = r'https?://(?:[^.]+\.)?elpais\.com/.*/(?P<id>[^/#?]+)\.html(?:$|[?#])'
-    IE_DESCR = 'El País'
+    IE_DESC = 'El País'
 
     _TEST = {
         'url': 'http://blogs.elpais.com/la-voz-de-inaki/2014/02/tiempo-nuevo-recetas-viejas.html',

youtube_dl/extractor/engadget.py

@@ -0,0 +1,43 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from .fivemin import FiveMinIE
+from ..utils import (
+    url_basename,
+)
+
+
+class EngadgetIE(InfoExtractor):
+    _VALID_URL = r'''(?x)https?://www.engadget.com/
+        (?:video/5min/(?P<id>\d+)|
+            [\d/]+/.*?)
+        '''
+
+    _TEST = {
+        'url': 'http://www.engadget.com/video/5min/518153925/',
+        'md5': 'c6820d4828a5064447a4d9fc73f312c9',
+        'info_dict': {
+            'id': '518153925',
+            'ext': 'mp4',
+            'title': 'Samsung Galaxy Tab Pro 8.4 Review',
+        },
+        'add_ie': ['FiveMin'],
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        if video_id is not None:
+            return FiveMinIE._build_result(video_id)
+        else:
+            title = url_basename(url)
+            webpage = self._download_webpage(url, title)
+            ids = re.findall(r'<iframe[^>]+?playList=(\d+)', webpage)
+            return {
+                '_type': 'playlist',
+                'title': title,
+                'entries': [FiveMinIE._build_result(id) for id in ids]
+            }

youtube_dl/extractor/escapist.py

@@ -1,9 +1,9 @@
-import json
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
 from ..utils import (
-    compat_str,
     compat_urllib_parse,
 
     ExtractorError,
@@ -11,70 +11,68 @@ from ..utils import (
 
 
 class EscapistIE(InfoExtractor):
-    _VALID_URL = r'^https?://?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$'
+    _VALID_URL = r'^https?://?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<id>[0-9]+)-'
     _TEST = {
-        u'url': u'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate',
-        u'file': u'6618-Breaking-Down-Baldurs-Gate.mp4',
-        u'md5': u'ab3a706c681efca53f0a35f1415cf0d1',
-        u'info_dict': {
-            u"description": u"Baldur's Gate: Original, Modded or Enhanced Edition? I'll break down what you can expect from the new Baldur's Gate: Enhanced Edition.", 
-            u"uploader": u"the-escapist-presents", 
-            u"title": u"Breaking Down Baldur's Gate"
+        'url': 'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate',
+        'md5': 'ab3a706c681efca53f0a35f1415cf0d1',
+        'info_dict': {
+            'id': '6618',
+            'ext': 'mp4',
+            'description': "Baldur's Gate: Original, Modded or Enhanced Edition? I'll break down what you can expect from the new Baldur's Gate: Enhanced Edition.",
+            'uploader': 'the-escapist-presents',
+            'title': "Breaking Down Baldur's Gate",
         }
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         showName = mobj.group('showname')
-        videoId = mobj.group('episode')
+        video_id = mobj.group('id')
 
-        self.report_extraction(videoId)
-        webpage = self._download_webpage(url, videoId)
+        self.report_extraction(video_id)
+        webpage = self._download_webpage(url, video_id)
 
         videoDesc = self._html_search_regex(
             r'<meta name="description" content="([^"]*)"',
-            webpage, u'description', fatal=False)
+            webpage, 'description', fatal=False)
 
         playerUrl = self._og_search_video_url(webpage, name=u'player URL')
 
         title = self._html_search_regex(
             r'<meta name="title" content="([^"]*)"',
-            webpage, u'title').split(' : ')[-1]
+            webpage, 'title').split(' : ')[-1]
 
-        configUrl = self._search_regex('config=(.*)$', playerUrl, u'config URL')
+        configUrl = self._search_regex('config=(.*)$', playerUrl, 'config URL')
         configUrl = compat_urllib_parse.unquote(configUrl)
 
         formats = []
 
-        def _add_format(name, cfgurl):
-            configJSON = self._download_webpage(
-                cfgurl, videoId,
-                u'Downloading ' + name + ' configuration',
-                u'Unable to download ' + name + ' configuration')
+        def _add_format(name, cfgurl, quality):
+            config = self._download_json(
+                cfgurl, video_id,
+                'Downloading ' + name + ' configuration',
+                'Unable to download ' + name + ' configuration',
+                transform_source=lambda s: s.replace("'", '"'))
 
-            # Technically, it's JavaScript, not JSON
-            configJSON = configJSON.replace("'", '"')
-
-            try:
-                config = json.loads(configJSON)
-            except (ValueError,) as err:
-                raise ExtractorError(u'Invalid JSON in configuration file: ' + compat_str(err))
             playlist = config['playlist']
             formats.append({
                 'url': playlist[1]['url'],
                 'format_id': name,
+                'quality': quality,
             })
 
-        _add_format(u'normal', configUrl)
+        _add_format('normal', configUrl, quality=0)
         hq_url = (configUrl +
                   ('&hq=1' if '?' in configUrl else configUrl + '?hq=1'))
         try:
-            _add_format(u'hq', hq_url)
+            _add_format('hq', hq_url, quality=1)
         except ExtractorError:
             pass  # That's fine, we'll just use normal quality
 
+        self._sort_formats(formats)
+
         return {
-            'id': videoId,
+            'id': video_id,
             'formats': formats,
             'uploader': showName,
             'title': title,

youtube_dl/extractor/exfm.py

@@ -1,56 +1,58 @@
+from __future__ import unicode_literals
+
 import re
-import json
 
 from .common import InfoExtractor
 
 
 class ExfmIE(InfoExtractor):
-    IE_NAME = u'exfm'
-    IE_DESC = u'ex.fm'
-    _VALID_URL = r'(?:http://)?(?:www\.)?ex\.fm/song/([^/]+)'
-    _SOUNDCLOUD_URL = r'(?:http://)?(?:www\.)?api\.soundcloud\.com/tracks/([^/]+)/stream'
+    IE_NAME = 'exfm'
+    IE_DESC = 'ex.fm'
+    _VALID_URL = r'http://(?:www\.)?ex\.fm/song/(?P<id>[^/]+)'
+    _SOUNDCLOUD_URL = r'http://(?:www\.)?api\.soundcloud\.com/tracks/([^/]+)/stream'
     _TESTS = [
         {
-            u'url': u'http://ex.fm/song/eh359',
-            u'file': u'44216187.mp3',
-            u'md5': u'e45513df5631e6d760970b14cc0c11e7',
-            u'info_dict': {
-                u"title": u"Test House \"Love Is Not Enough\" (Extended Mix) DeadJournalist Exclusive",
-                u"uploader": u"deadjournalist",
-                u'upload_date': u'20120424',
-                u'description': u'Test House \"Love Is Not Enough\" (Extended Mix) DeadJournalist Exclusive',
+            'url': 'http://ex.fm/song/eh359',
+            'md5': 'e45513df5631e6d760970b14cc0c11e7',
+            'info_dict': {
+                'id': '44216187',
+                'ext': 'mp3',
+                'title': 'Test House "Love Is Not Enough" (Extended Mix) DeadJournalist Exclusive',
+                'uploader': 'deadjournalist',
+                'upload_date': '20120424',
+                'description': 'Test House \"Love Is Not Enough\" (Extended Mix) DeadJournalist Exclusive',
             },
-            u'note': u'Soundcloud song',
-            u'skip': u'The site is down too often',
+            'note': 'Soundcloud song',
+            'skip': 'The site is down too often',
         },
         {
-            u'url': u'http://ex.fm/song/wddt8',
-            u'file': u'wddt8.mp3',
-            u'md5': u'966bd70741ac5b8570d8e45bfaed3643',
-            u'info_dict': {
-                u'title': u'Safe and Sound',
-                u'uploader': u'Capital Cities',
+            'url': 'http://ex.fm/song/wddt8',
+            'md5': '966bd70741ac5b8570d8e45bfaed3643',
+            'info_dict': {
+                'id': 'wddt8',
+                'ext': 'mp3',
+                'title': 'Safe and Sound',
+                'uploader': 'Capital Cities',
             },
-            u'skip': u'The site is down too often',
+            'skip': 'The site is down too often',
         },
     ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        song_id = mobj.group(1)
-        info_url = "http://ex.fm/api/v3/song/%s" %(song_id)
-        webpage = self._download_webpage(info_url, song_id)
-        info = json.loads(webpage)
-        song_url = info['song']['url']
+        song_id = mobj.group('id')
+        info_url = "http://ex.fm/api/v3/song/%s" % song_id
+        info = self._download_json(info_url, song_id)['song']
+        song_url = info['url']
         if re.match(self._SOUNDCLOUD_URL, song_url) is not None:
             self.to_screen('Soundcloud song detected')
-            return self.url_result(song_url.replace('/stream',''), 'Soundcloud')
-        return [{
-            'id':          song_id,
-            'url':         song_url,
-            'ext':         'mp3',
-            'title':       info['song']['title'],
-            'thumbnail':   info['song']['image']['large'],
-            'uploader':    info['song']['artist'],
-            'view_count':  info['song']['loved_count'],
-        }]
+            return self.url_result(song_url.replace('/stream', ''), 'Soundcloud')
+        return {
+            'id': song_id,
+            'url': song_url,
+            'ext': 'mp3',
+            'title': info['title'],
+            'thumbnail': info['image']['large'],
+            'uploader': info['artist'],
+            'view_count': info['loved_count'],
+        }

youtube_dl/extractor/facebook.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import json
 import re
 import socket
@@ -9,16 +11,15 @@ from ..utils import (
     compat_urllib_error,
     compat_urllib_parse,
     compat_urllib_request,
+    urlencode_postdata,
 
     ExtractorError,
 )
 
 
 class FacebookIE(InfoExtractor):
-    """Information Extractor for Facebook"""
-
     _VALID_URL = r'''(?x)
-        (?:https?://)?(?:\w+\.)?facebook\.com/
+        https?://(?:\w+\.)?facebook\.com/
         (?:[^#?]*\#!/)?
         (?:video/video\.php|photo\.php|video/embed)\?(?:.*?)
         (?:v|video_id)=(?P<id>[0-9]+)
@@ -26,21 +27,18 @@ class FacebookIE(InfoExtractor):
     _LOGIN_URL = 'https://www.facebook.com/login.php?next=http%3A%2F%2Ffacebook.com%2Fhome.php&login_attempt=1'
     _CHECKPOINT_URL = 'https://www.facebook.com/checkpoint/?next=http%3A%2F%2Ffacebook.com%2Fhome.php&_fb_noscript=1'
     _NETRC_MACHINE = 'facebook'
-    IE_NAME = u'facebook'
+    IE_NAME = 'facebook'
     _TEST = {
-        u'url': u'https://www.facebook.com/photo.php?v=120708114770723',
-        u'file': u'120708114770723.mp4',
-        u'md5': u'48975a41ccc4b7a581abd68651c1a5a8',
-        u'info_dict': {
-            u"duration": 279,
-            u"title": u"PEOPLE ARE AWESOME 2013"
+        'url': 'https://www.facebook.com/photo.php?v=120708114770723',
+        'md5': '48975a41ccc4b7a581abd68651c1a5a8',
+        'info_dict': {
+            'id': '120708114770723',
+            'ext': 'mp4',
+            'duration': 279,
+            'title': 'PEOPLE ARE AWESOME 2013',
         }
     }
 
-    def report_login(self):
-        """Report attempt to log in."""
-        self.to_screen(u'Logging in')
-
     def _login(self):
         (useremail, password) = self._get_login_info()
         if useremail is None:
@@ -48,11 +46,13 @@ class FacebookIE(InfoExtractor):
 
         login_page_req = compat_urllib_request.Request(self._LOGIN_URL)
         login_page_req.add_header('Cookie', 'locale=en_US')
-        self.report_login()
-        login_page = self._download_webpage(login_page_req, None, note=False,
-            errnote=u'Unable to download login page')
-        lsd = self._search_regex(r'"lsd":"(\w*?)"', login_page, u'lsd')
-        lgnrnd = self._search_regex(r'name="lgnrnd" value="([^"]*?)"', login_page, u'lgnrnd')
+        login_page = self._download_webpage(login_page_req, None,
+            note='Downloading login page',
+            errnote='Unable to download login page')
+        lsd = self._search_regex(
+            r'<input type="hidden" name="lsd" value="([^"]*)"',
+            login_page, 'lsd')
+        lgnrnd = self._search_regex(r'name="lgnrnd" value="([^"]*?)"', login_page, 'lgnrnd')
 
         login_form = {
             'email': useremail,
@@ -65,27 +65,29 @@ class FacebookIE(InfoExtractor):
             'timezone': '-60',
             'trynum': '1',
             }
-        request = compat_urllib_request.Request(self._LOGIN_URL, compat_urllib_parse.urlencode(login_form))
+        request = compat_urllib_request.Request(self._LOGIN_URL, urlencode_postdata(login_form))
         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
         try:
-            login_results = compat_urllib_request.urlopen(request).read()
+            login_results = self._download_webpage(request, None,
+                note='Logging in', errnote='unable to fetch login page')
             if re.search(r'<form(.*)name="login"(.*)</form>', login_results) is not None:
-                self._downloader.report_warning(u'unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.')
+                self._downloader.report_warning('unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.')
                 return
 
             check_form = {
-                'fb_dtsg': self._search_regex(r'"fb_dtsg":"(.*?)"', login_results, u'fb_dtsg'),
-                'nh': self._search_regex(r'name="nh" value="(\w*?)"', login_results, u'nh'),
+                'fb_dtsg': self._search_regex(r'name="fb_dtsg" value="(.+?)"', login_results, 'fb_dtsg'),
+                'nh': self._search_regex(r'name="nh" value="(\w*?)"', login_results, 'nh'),
                 'name_action_selected': 'dont_save',
-                'submit[Continue]': self._search_regex(r'<input value="(.*?)" name="submit\[Continue\]"', login_results, u'continue'),
+                'submit[Continue]': self._search_regex(r'<button[^>]+value="(.*?)"[^>]+name="submit\[Continue\]"', login_results, 'continue'),
             }
-            check_req = compat_urllib_request.Request(self._CHECKPOINT_URL, compat_urllib_parse.urlencode(check_form))
+            check_req = compat_urllib_request.Request(self._CHECKPOINT_URL, urlencode_postdata(check_form))
             check_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
-            check_response = compat_urllib_request.urlopen(check_req).read()
+            check_response = self._download_webpage(check_req, None,
+                note='Confirming login')
             if re.search(r'id="checkpointSubmitButton"', check_response) is not None:
-                self._downloader.report_warning(u'Unable to confirm login, you have to login in your brower and authorize the login.')
+                self._downloader.report_warning('Unable to confirm login, you have to login in your brower and authorize the login.')
         except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
-            self._downloader.report_warning(u'unable to log in: %s' % compat_str(err))
+            self._downloader.report_warning('unable to log in: %s' % compat_str(err))
             return
 
     def _real_initialize(self):
@@ -93,8 +95,6 @@ class FacebookIE(InfoExtractor):
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError(u'Invalid URL: %s' % url)
         video_id = mobj.group('id')
 
         url = 'https://www.facebook.com/video/video.php?v=%s' % video_id
@@ -107,10 +107,10 @@ class FacebookIE(InfoExtractor):
             m_msg = re.search(r'class="[^"]*uiInterstitialContent[^"]*"><div>(.*?)</div>', webpage)
             if m_msg is not None:
                 raise ExtractorError(
-                    u'The video is not available, Facebook said: "%s"' % m_msg.group(1),
+                    'The video is not available, Facebook said: "%s"' % m_msg.group(1),
                     expected=True)
             else:
-                raise ExtractorError(u'Cannot parse data')
+                raise ExtractorError('Cannot parse data')
         data = dict(json.loads(m.group(1)))
         params_raw = compat_urllib_parse.unquote(data['params'])
         params = json.loads(params_raw)
@@ -119,19 +119,15 @@ class FacebookIE(InfoExtractor):
         if not video_url:
             video_url = video_data['sd_src']
         if not video_url:
-            raise ExtractorError(u'Cannot find video URL')
-        video_duration = int(video_data['video_duration'])
-        thumbnail = video_data['thumbnail_src']
+            raise ExtractorError('Cannot find video URL')
 
         video_title = self._html_search_regex(
-            r'<h2 class="uiHeaderTitle">([^<]*)</h2>', webpage, u'title')
+            r'<h2 class="uiHeaderTitle">([^<]*)</h2>', webpage, 'title')
 
-        info = {
+        return {
             'id': video_id,
             'title': video_title,
             'url': video_url,
-            'ext': 'mp4',
-            'duration': video_duration,
-            'thumbnail': thumbnail,
+            'duration': int(video_data['video_duration']),
+            'thumbnail': video_data['thumbnail_src'],
         }
-        return [info]

youtube_dl/extractor/firsttv.py

@@ -0,0 +1,60 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import int_or_none
+
+
+class FirstTVIE(InfoExtractor):
+    IE_NAME = 'firsttv'
+    IE_DESC = 'Видеоархив - Первый канал'
+    _VALID_URL = r'http://(?:www\.)?1tv\.ru/videoarchive/(?P<id>\d+)'
+
+    _TEST = {
+        'url': 'http://www.1tv.ru/videoarchive/73390',
+        'md5': '3de6390cf0cca4a5eae1d1d83895e5ad',
+        'info_dict': {
+            'id': '73390',
+            'ext': 'mp4',
+            'title': 'Олимпийские канатные дороги',
+            'description': 'md5:cc730d2bf4215463e37fff6a1e277b13',
+            'thumbnail': 'http://img1.1tv.ru/imgsize640x360/PR20140210114657.JPG',
+            'duration': 149,
+        },
+        'skip': 'Only works from Russia',
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id, 'Downloading page')
+
+        video_url = self._html_search_regex(
+            r'''(?s)jwplayer\('flashvideoportal_1'\)\.setup\({.*?'file': '([^']+)'.*?}\);''', webpage, 'video URL')
+
+        title = self._html_search_regex(
+            r'<div class="tv_translation">\s*<h1><a href="[^"]+">([^<]*)</a>', webpage, 'title')
+        description = self._html_search_regex(
+            r'<div class="descr">\s*<div>&nbsp;</div>\s*<p>([^<]*)</p></div>', webpage, 'description', fatal=False)
+
+        thumbnail = self._og_search_thumbnail(webpage)
+        duration = self._og_search_property('video:duration', webpage, 'video duration', fatal=False)
+
+        like_count = self._html_search_regex(r'title="Понравилось".*?/></label> \[(\d+)\]',
+            webpage, 'like count', fatal=False)
+        dislike_count = self._html_search_regex(r'title="Не понравилось".*?/></label> \[(\d+)\]',
+            webpage, 'dislike count', fatal=False)
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'thumbnail': thumbnail,
+            'title': title,
+            'description': description,
+            'duration': int_or_none(duration),
+            'like_count': int_or_none(like_count),
+            'dislike_count': int_or_none(dislike_count),
+        }

youtube_dl/extractor/fivemin.py

@@ -0,0 +1,56 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_str,
+)
+
+
+class FiveMinIE(InfoExtractor):
+    IE_NAME = '5min'
+    _VALID_URL = r'''(?x)
+        (?:https?://[^/]*?5min\.com/Scripts/PlayerSeed\.js\?(.*?&)?playList=|
+            5min:)
+        (?P<id>\d+)
+        '''
+
+    _TEST = {
+        # From http://www.engadget.com/2013/11/15/ipad-mini-retina-display-review/
+        'url': 'http://pshared.5min.com/Scripts/PlayerSeed.js?sid=281&width=560&height=345&playList=518013791',
+        'md5': '4f7b0b79bf1a470e5004f7112385941d',
+        'info_dict': {
+            'id': '518013791',
+            'ext': 'mp4',
+            'title': 'iPad Mini with Retina Display Review',
+        },
+    }
+
+    @classmethod
+    def _build_result(cls, video_id):
+        return cls.url_result('5min:%s' % video_id, cls.ie_key())
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        info = self._download_json(
+            'https://syn.5min.com/handlers/SenseHandler.ashx?func=GetResults&'
+            'playlist=%s&url=https' % video_id,
+            video_id)['binding'][0]
+
+        second_id = compat_str(int(video_id[:-2]) + 1)
+        formats = []
+        for quality, height in [(1, 320), (2, 480), (4, 720), (8, 1080)]:
+            if any(r['ID'] == quality for r in info['Renditions']):
+                formats.append({
+                    'format_id': compat_str(quality),
+                    'url': 'http://avideos.5min.com/%s/%s/%s_%s.mp4' % (second_id[-3:], second_id, video_id, quality),
+                    'height': height,
+                })
+
+        return {
+            'id': video_id,
+            'title': info['Title'],
+            'formats': formats,
+        }

youtube_dl/extractor/fourtube.py

@@ -0,0 +1,95 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_request,
+    unified_strdate,
+    str_to_int,
+    parse_duration,
+    clean_html,
+)
+
+
+class FourTubeIE(InfoExtractor):
+    IE_NAME = '4tube'
+    _VALID_URL = r'https?://(?:www\.)?4tube\.com/videos/(?P<id>\d+)'
+
+    _TEST = {
+        'url': 'http://www.4tube.com/videos/209733/hot-babe-holly-michaels-gets-her-ass-stuffed-by-black',
+        'md5': '6516c8ac63b03de06bc8eac14362db4f',
+        'info_dict': {
+            'id': '209733',
+            'ext': 'mp4',
+            'title': 'Hot Babe Holly Michaels gets her ass stuffed by black',
+            'uploader': 'WCP Club',
+            'uploader_id': 'wcp-club',
+            'upload_date': '20131031',
+            'duration': 583,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+
+        video_id = mobj.group('id')
+        webpage_url = 'http://www.4tube.com/videos/' + video_id
+        webpage = self._download_webpage(webpage_url, video_id)
+
+        self.report_extraction(video_id)
+
+        playlist_json = self._html_search_regex(r'var playerConfigPlaylist\s+=\s+([^;]+)', webpage, 'Playlist')
+        media_id = self._search_regex(r'idMedia:\s*(\d+)', playlist_json, 'Media Id')
+        sources = self._search_regex(r'sources:\s*\[([^\]]*)\]', playlist_json, 'Sources').split(',')
+        title = self._search_regex(r'title:\s*"([^"]*)', playlist_json, 'Title')
+        thumbnail_url = self._search_regex(r'image:\s*"([^"]*)', playlist_json, 'Thumbnail', fatal=False)
+
+        uploader_str = self._search_regex(r'<span>Uploaded by</span>(.*?)<span>', webpage, 'uploader', fatal=False)
+        mobj = re.search(r'<a href="/sites/(?P<id>[^"]+)"><strong>(?P<name>[^<]+)</strong></a>', uploader_str)
+        (uploader, uploader_id) = (mobj.group('name'), mobj.group('id')) if mobj else (clean_html(uploader_str), None)
+
+        upload_date = None
+        view_count = None
+        duration = None
+        description = self._html_search_meta('description', webpage, 'description')
+        if description:
+            upload_date = self._search_regex(r'Published Date: (\d{2} [a-zA-Z]{3} \d{4})', description, 'upload date',
+                fatal=False)
+            if upload_date:
+                upload_date = unified_strdate(upload_date)
+            view_count = self._search_regex(r'Views: ([\d,\.]+)', description, 'view count', fatal=False)
+            if view_count:
+                view_count = str_to_int(view_count)
+            duration = parse_duration(self._search_regex(r'Length: (\d+m\d+s)', description, 'duration', fatal=False))
+
+        token_url = "http://tkn.4tube.com/{0}/desktop/{1}".format(media_id, "+".join(sources))
+        headers = {
+                b'Content-Type': b'application/x-www-form-urlencoded',
+                b'Origin': b'http://www.4tube.com',
+                }
+        token_req = compat_urllib_request.Request(token_url, b'{}', headers)
+        tokens = self._download_json(token_req, video_id)
+
+        formats = [{
+            'url': tokens[format]['token'],
+            'format_id': format + 'p',
+            'resolution': format + 'p',
+            'quality': int(format),
+            } for format in sources]
+
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'thumbnail': thumbnail_url,
+            'uploader': uploader,
+            'uploader_id': uploader_id,
+            'upload_date': upload_date,
+            'view_count': view_count,
+            'duration': duration,
+            'age_limit': 18,
+            'webpage_url': webpage_url,
+        }

youtube_dl/extractor/francetv.py

@@ -184,6 +184,7 @@ class GenerationQuoiIE(InfoExtractor):
             # It uses Dailymotion
             'skip_download': True,
         },
+        'skip': 'Only available from France',
     }
 
     def _real_extract(self, url):

youtube_dl/extractor/freesound.py

@@ -1,18 +1,21 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
-from ..utils import determine_ext
+
 
 class FreesoundIE(InfoExtractor):
-    _VALID_URL = r'(?:https?://)?(?:www\.)?freesound\.org/people/([^/]+)/sounds/(?P<id>[^/]+)'
+    _VALID_URL = r'https?://(?:www\.)?freesound\.org/people/([^/]+)/sounds/(?P<id>[^/]+)'
     _TEST = {
-        u'url': u'http://www.freesound.org/people/miklovan/sounds/194503/',
-        u'file': u'194503.mp3',
-        u'md5': u'12280ceb42c81f19a515c745eae07650',
-        u'info_dict': {
-            u"title": u"gulls in the city.wav",
-            u"uploader" : u"miklovan",
-            u'description': u'the sounds of seagulls in the city',
+        'url': 'http://www.freesound.org/people/miklovan/sounds/194503/',
+        'md5': '12280ceb42c81f19a515c745eae07650',
+        'info_dict': {
+            'id': '194503',
+            'ext': 'mp3',
+            'title': 'gulls in the city.wav',
+            'uploader': 'miklovan',
+            'description': 'the sounds of seagulls in the city',
         }
     }
 
@@ -20,17 +23,17 @@ class FreesoundIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         music_id = mobj.group('id')
         webpage = self._download_webpage(url, music_id)
-        title = self._html_search_regex(r'<div id="single_sample_header">.*?<a href="#">(.+?)</a>',
-                                webpage, 'music title', flags=re.DOTALL)
-        music_url = self._og_search_property('audio', webpage, 'music url')
-        description = self._html_search_regex(r'<div id="sound_description">(.*?)</div>',
-                                webpage, 'description', fatal=False, flags=re.DOTALL)
+        title = self._html_search_regex(
+            r'<div id="single_sample_header">.*?<a href="#">(.+?)</a>',
+            webpage, 'music title', flags=re.DOTALL)
+        description = self._html_search_regex(
+            r'<div id="sound_description">(.*?)</div>', webpage, 'description',
+            fatal=False, flags=re.DOTALL)
 
-        return [{
-            'id':       music_id,
-            'title':    title,            
-            'url':      music_url,
+        return {
+            'id': music_id,
+            'title': title,
+            'url': self._og_search_property('audio', webpage, 'music url'),
             'uploader': self._og_search_property('audio:artist', webpage, 'music uploader'),
-            'ext':      determine_ext(music_url),
             'description': description,
-        }]
+        }

youtube_dl/extractor/funnyordie.py

@@ -1,12 +1,13 @@
 from __future__ import unicode_literals
 
+import json
 import re
 
 from .common import InfoExtractor
 
 
 class FunnyOrDieIE(InfoExtractor):
-    _VALID_URL = r'^(?:https?://)?(?:www\.)?funnyordie\.com/videos/(?P<id>[0-9a-f]+)/.*$'
+    _VALID_URL = r'https?://(?:www\.)?funnyordie\.com/(?P<type>embed|videos)/(?P<id>[0-9a-f]+)(?:$|[?#/])'
     _TEST = {
         'url': 'http://www.funnyordie.com/videos/0732f586d7/heart-shaped-box-literal-video-version',
         'file': '0732f586d7.mp4',
@@ -30,10 +31,23 @@ class FunnyOrDieIE(InfoExtractor):
             [r'type="video/mp4" src="(.*?)"', r'src="([^>]*?)" type=\'video/mp4\''],
             webpage, 'video URL', flags=re.DOTALL)
 
+        if mobj.group('type') == 'embed':
+            post_json = self._search_regex(
+                r'fb_post\s*=\s*(\{.*?\});', webpage, 'post details')
+            post = json.loads(post_json)
+            title = post['name']
+            description = post.get('description')
+            thumbnail = post.get('picture')
+        else:
+            title = self._og_search_title(webpage)
+            description = self._og_search_description(webpage)
+            thumbnail = None
+
         return {
             'id': video_id,
             'url': video_url,
             'ext': 'mp4',
-            'title': self._og_search_title(webpage),
-            'description': self._og_search_description(webpage),
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
         }

youtube_dl/extractor/gamekings.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -6,13 +8,14 @@ from .common import InfoExtractor
 class GamekingsIE(InfoExtractor):
     _VALID_URL = r'http://www\.gamekings\.tv/videos/(?P<name>[0-9a-z\-]+)'
     _TEST = {
-        u"url": u"http://www.gamekings.tv/videos/phoenix-wright-ace-attorney-dual-destinies-review/",
-        u'file': u'20130811.mp4',
+        'url': 'http://www.gamekings.tv/videos/phoenix-wright-ace-attorney-dual-destinies-review/',
         # MD5 is flaky, seems to change regularly
-        #u'md5': u'2f32b1f7b80fdc5cb616efb4f387f8a3',
+        # 'md5': '2f32b1f7b80fdc5cb616efb4f387f8a3',
         u'info_dict': {
-            u"title": u"Phoenix Wright: Ace Attorney \u2013 Dual Destinies Review",
-            u"description": u"Melle en Steven hebben voor de review een week in de rechtbank doorbracht met Phoenix Wright: Ace Attorney - Dual Destinies.",
+            'id': '20130811',
+            'ext': 'mp4',
+            'title': 'Phoenix Wright: Ace Attorney \u2013 Dual Destinies Review',
+            'description': 'md5:632e61a9f97d700e83f43d77ddafb6a4',
         }
     }
 

youtube_dl/extractor/gametrailers.py

@@ -7,10 +7,11 @@ class GametrailersIE(MTVServicesInfoExtractor):
     _VALID_URL = r'http://www\.gametrailers\.com/(?P<type>videos|reviews|full-episodes)/(?P<id>.*?)/(?P<title>.*)'
     _TEST = {
         'url': 'http://www.gametrailers.com/videos/zbvr8i/mirror-s-edge-2-e3-2013--debut-trailer',
-        'file': '70e9a5d7-cf25-4a10-9104-6f3e7342ae0d.mp4',
         'md5': '4c8e67681a0ea7ec241e8c09b3ea8cf7',
         'info_dict': {
-            'title': 'Mirror\'s Edge 2|E3 2013: Debut Trailer',
+            'id': '70e9a5d7-cf25-4a10-9104-6f3e7342ae0d',
+            'ext': 'mp4',
+            'title': 'E3 2013: Debut Trailer',
             'description': 'Faith is back!  Check out the World Premiere trailer for Mirror\'s Edge 2 straight from the EA Press Conference at E3 2013!',
         },
     }

youtube_dl/extractor/gdcvault.py

@@ -0,0 +1,134 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_parse,
+    compat_urllib_request,
+)
+
+class GDCVaultIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?gdcvault\.com/play/(?P<id>\d+)/(?P<name>(\w|-)+)'
+    _TESTS = [
+        {
+            'url': 'http://www.gdcvault.com/play/1019721/Doki-Doki-Universe-Sweet-Simple',
+            'md5': '7ce8388f544c88b7ac11c7ab1b593704',
+            'info_dict': {
+                'id': '1019721',
+                'ext': 'mp4',
+                'title': 'Doki-Doki Universe: Sweet, Simple and Genuine (GDC Next 10)'
+            }
+        },
+        {
+            'url': 'http://www.gdcvault.com/play/1015683/Embracing-the-Dark-Art-of',
+            'info_dict': {
+                'id': '1015683',
+                'ext': 'flv',
+                'title': 'Embracing the Dark Art of Mathematical Modeling in AI'
+            },
+            'params': {
+                'skip_download': True,  # Requires rtmpdump
+            }
+        },
+    ]
+
+    def _parse_mp4(self, xml_description):
+        video_formats = []
+        mp4_video = xml_description.find('./metadata/mp4video')
+        if mp4_video is None:
+            return None
+
+        mobj = re.match(r'(?P<root>https?://.*?/).*', mp4_video.text)
+        video_root = mobj.group('root')
+        formats = xml_description.findall('./metadata/MBRVideos/MBRVideo')
+        for format in formats:
+            mobj = re.match(r'mp4\:(?P<path>.*)', format.find('streamName').text)
+            url = video_root + mobj.group('path')
+            vbr = format.find('bitrate').text
+            video_formats.append({
+                'url': url,
+                'vbr': int(vbr),
+            })
+        return video_formats
+
+    def _parse_flv(self, xml_description):
+        video_formats = []
+        akami_url = xml_description.find('./metadata/akamaiHost').text
+        slide_video_path = xml_description.find('./metadata/slideVideo').text
+        video_formats.append({
+            'url': 'rtmp://' + akami_url + '/' + slide_video_path,
+            'format_note': 'slide deck video',
+            'quality': -2,
+            'preference': -2,
+            'format_id': 'slides',
+        })
+        speaker_video_path = xml_description.find('./metadata/speakerVideo').text
+        video_formats.append({
+            'url': 'rtmp://' + akami_url + '/' + speaker_video_path,
+            'format_note': 'speaker video',
+            'quality': -1,
+            'preference': -1,
+            'format_id': 'speaker',
+        })
+        return video_formats
+
+    def _login(self, webpage_url, video_id):
+        (username, password) = self._get_login_info()
+        if username is None or password is None:
+            self.report_warning('It looks like ' + webpage_url + ' requires a login. Try specifying a username and password and try again.')
+            return None
+
+        mobj = re.match(r'(?P<root_url>https?://.*?/).*', webpage_url)
+        login_url = mobj.group('root_url') + 'api/login.php'
+        logout_url = mobj.group('root_url') + 'logout'
+
+        login_form = {
+            'email': username,
+            'password': password,
+        }
+
+        request = compat_urllib_request.Request(login_url, compat_urllib_parse.urlencode(login_form))
+        request.add_header('Content-Type', 'application/x-www-form-urlencoded')
+        self._download_webpage(request, video_id, 'Logging in')
+        start_page = self._download_webpage(webpage_url, video_id, 'Getting authenticated video page')
+        self._download_webpage(logout_url, video_id, 'Logging out')
+
+        return start_page
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+
+        video_id = mobj.group('id')
+        webpage_url = 'http://www.gdcvault.com/play/' + video_id
+        start_page = self._download_webpage(webpage_url, video_id)
+
+        xml_root = self._html_search_regex(r'<iframe src="(?P<xml_root>.*?)player.html.*?".*?</iframe>', start_page, 'xml root', None, False)
+
+        if xml_root is None:
+            # Probably need to authenticate
+            start_page = self._login(webpage_url, video_id)
+            if start_page is None:
+                self.report_warning('Could not login.')
+            else:
+                # Grab the url from the authenticated page
+                xml_root = self._html_search_regex(r'<iframe src="(?P<xml_root>.*?)player.html.*?".*?</iframe>', start_page, 'xml root')
+
+        xml_name = self._html_search_regex(r'<iframe src=".*?\?xml=(?P<xml_file>.+?\.xml).*?".*?</iframe>', start_page, 'xml filename', None, False)
+        if xml_name is None:
+            # Fallback to the older format
+            xml_name = self._html_search_regex(r'<iframe src=".*?\?xmlURL=xml/(?P<xml_file>.+?\.xml).*?".*?</iframe>', start_page, 'xml filename')
+
+        xml_decription_url = xml_root + 'xml/' + xml_name
+        xml_description = self._download_xml(xml_decription_url, video_id)
+
+        video_title = xml_description.find('./metadata/title').text
+        video_formats = self._parse_mp4(xml_description)
+        if video_formats is None:
+            video_formats = self._parse_flv(xml_description)
+
+        return {
+            'id': video_id,
+            'title': video_title,
+            'formats': video_formats,
+        }

youtube_dl/extractor/generic.py

@@ -12,9 +12,11 @@ from ..utils import (
     compat_urllib_parse,
     compat_urllib_request,
     compat_urlparse,
+    compat_xml_parse_error,
 
     ExtractorError,
     HEADRequest,
+    parse_xml,
     smuggle_url,
     unescapeHTML,
     unified_strdate,
@@ -22,6 +24,7 @@ from ..utils import (
 )
 from .brightcove import BrightcoveIE
 from .ooyala import OoyalaIE
+from .rutv import RUTVIE
 
 
 class GenericIE(InfoExtractor):
@@ -81,10 +84,10 @@ class GenericIE(InfoExtractor):
         # Direct link to a video
         {
             'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
-            'file': 'trailer.mp4',
             'md5': '67d406c2bcb6af27fa886f31aa934bbe',
             'info_dict': {
                 'id': 'trailer',
+                'ext': 'mp4',
                 'title': 'trailer',
                 'upload_date': '20100513',
             }
@@ -92,7 +95,6 @@ class GenericIE(InfoExtractor):
         # ooyala video
         {
             'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
-            'file': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ.mp4',
             'md5': '5644c6ca5d5782c1d0d350dad9bd840c',
             'info_dict': {
                 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
@@ -100,6 +102,101 @@ class GenericIE(InfoExtractor):
                 'title': '2cc213299525360.mov',  # that's what we get
             },
         },
+        # second style of embedded ooyala videos
+        {
+            'url': 'http://www.smh.com.au/tv/business/show/financial-review-sunday/behind-the-scenes-financial-review-sunday--4350201.html',
+            'info_dict': {
+                'id': '13djJjYjptA1XpPx8r9kuzPyj3UZH0Uk',
+                'ext': 'mp4',
+                'title': 'Behind-the-scenes: Financial Review Sunday ',
+                'description': 'Step inside Channel Nine studios for an exclusive tour of its upcoming financial business show.',
+            },
+            'params': {
+                # m3u8 download
+                'skip_download': True,
+            },
+        },
+        # google redirect
+        {
+            'url': 'http://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&ved=0CCUQtwIwAA&url=http%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DcmQHVoWB5FY&ei=F-sNU-LLCaXk4QT52ICQBQ&usg=AFQjCNEw4hL29zgOohLXvpJ-Bdh2bils1Q&bvm=bv.61965928,d.bGE',
+            'info_dict': {
+                'id': 'cmQHVoWB5FY',
+                'ext': 'mp4',
+                'upload_date': '20130224',
+                'uploader_id': 'TheVerge',
+                'description': 'Chris Ziegler takes a look at the Alcatel OneTouch Fire and the ZTE Open; two of the first Firefox OS handsets to be officially announced.',
+                'uploader': 'The Verge',
+                'title': 'First Firefox OS phones side-by-side',
+            },
+            'params': {
+                'skip_download': False,
+            }
+        },
+        # embed.ly video
+        {
+            'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
+            'info_dict': {
+                'id': '9ODmcdjQcHQ',
+                'ext': 'mp4',
+                'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
+                'upload_date': '20140225',
+                'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
+                'uploader': 'Tested',
+                'uploader_id': 'testedcom',
+            },
+            # No need to test YoutubeIE here
+            'params': {
+                'skip_download': True,
+            },
+        },
+        # funnyordie embed
+        {
+            'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
+            'md5': '7cf780be104d40fea7bae52eed4a470e',
+            'info_dict': {
+                'id': '18e820ec3f',
+                'ext': 'mp4',
+                'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
+                'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
+            },
+        },
+        # RUTV embed
+        {
+            'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
+            'info_dict': {
+                'id': '776940',
+                'ext': 'mp4',
+                'title': 'Охотское море стало целиком российским',
+                'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
+            },
+            'params': {
+                # m3u8 download
+                'skip_download': True,
+            },
+        },
+        # Embedded TED video
+        {
+            'url': 'http://en.support.wordpress.com/videos/ted-talks/',
+            'md5': 'deeeabcc1085eb2ba205474e7235a3d5',
+            'info_dict': {
+                'id': '981',
+                'ext': 'mp4',
+                'title': 'My web playroom',
+                'uploader': 'Ze Frank',
+                'description': 'md5:ddb2a40ecd6b6a147e400e535874947b',
+            }
+        },
+        # nowvideo embed hidden behind percent encoding
+        {
+            'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
+            'md5': '2baf4ddd70f697d94b1c18cf796d5107',
+            'info_dict': {
+                'id': '06e53103ca9aa',
+                'ext': 'flv',
+                'title': 'Macross Episode 001  Watch Macross Episode 001 onl',
+                'description': 'No description',
+            },
+        },
     ]
 
     def report_download_webpage(self, video_id):
@@ -125,9 +222,14 @@ class GenericIE(InfoExtractor):
                     newurl = newurl.replace(' ', '%20')
                     newheaders = dict((k,v) for k,v in req.headers.items()
                                       if k.lower() not in ("content-length", "content-type"))
+                    try:
+                        # This function was deprecated in python 3.3 and removed in 3.4
+                        origin_req_host = req.get_origin_req_host()
+                    except AttributeError:
+                        origin_req_host = req.origin_req_host
                     return HEADRequest(newurl,
                                        headers=newheaders,
-                                       origin_req_host=req.get_origin_req_host(),
+                                       origin_req_host=origin_req_host,
                                        unverifiable=True)
                 else:
                     raise compat_urllib_error.HTTPError(req.get_full_url(), code, msg, headers, fp)
@@ -159,6 +261,25 @@ class GenericIE(InfoExtractor):
             raise ExtractorError('Invalid URL protocol')
         return response
 
+    def _extract_rss(self, url, video_id, doc):
+        playlist_title = doc.find('./channel/title').text
+        playlist_desc_el = doc.find('./channel/description')
+        playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
+
+        entries = [{
+            '_type': 'url',
+            'url': e.find('link').text,
+            'title': e.find('title').text,
+        } for e in doc.findall('./channel/item')]
+
+        return {
+            '_type': 'playlist',
+            'id': url,
+            'title': playlist_title,
+            'description': playlist_desc,
+            'entries': entries,
+        }
+
     def _real_extract(self, url):
         parsed_url = compat_urlparse.urlparse(url)
         if not parsed_url.scheme:
@@ -175,7 +296,7 @@ class GenericIE(InfoExtractor):
             else:
                 assert ':' in default_search
                 return self.url_result(default_search + url)
-        video_id = os.path.splitext(url.split('/')[-1])[0]
+        video_id = os.path.splitext(url.rstrip('/').split('/')[-1])[0]
 
         self.to_screen('%s: Requesting header' % video_id)
 
@@ -219,6 +340,19 @@ class GenericIE(InfoExtractor):
 
         self.report_extraction(video_id)
 
+        # Is it an RSS feed?
+        try:
+            doc = parse_xml(webpage)
+            if doc.tag == 'rss':
+                return self._extract_rss(url, video_id, doc)
+        except compat_xml_parse_error:
+            pass
+
+        # Sometimes embedded video player is hidden behind percent encoding
+        # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
+        # Unescaping the whole page allows to handle those cases in a generic way
+        webpage = compat_urllib_parse.unquote(webpage)
+
         # it's tempting to parse this further, but you would
         # have to take into account all the variations like
         #   Video Title - Site Name
@@ -252,9 +386,9 @@ class GenericIE(InfoExtractor):
 
         # Look for embedded (iframe) Vimeo player
         mobj = re.search(
-            r'<iframe[^>]+?src="((?:https?:)?//player\.vimeo\.com/video/.+?)"', webpage)
+            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/.+?)\1', webpage)
         if mobj:
-            player_url = unescapeHTML(mobj.group(1))
+            player_url = unescapeHTML(mobj.group('url'))
             surl = smuggle_url(player_url, {'Referer': url})
             return self.url_result(surl, 'Vimeo')
 
@@ -320,9 +454,10 @@ class GenericIE(InfoExtractor):
             return self.url_result(mobj.group('url'))
 
         # Look for Ooyala videos
-        mobj = re.search(r'player.ooyala.com/[^"?]+\?[^"]*?(?:embedCode|ec)=([^"&]+)', webpage)
+        mobj = (re.search(r'player.ooyala.com/[^"?]+\?[^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
+             re.search(r'OO.Player.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage))
         if mobj is not None:
-            return OoyalaIE._build_url_result(mobj.group(1))
+            return OoyalaIE._build_url_result(mobj.group('ec'))
 
         # Look for Aparat videos
         mobj = re.search(r'<iframe src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
@@ -334,11 +469,17 @@ class GenericIE(InfoExtractor):
         if mobj is not None:
             return self.url_result(mobj.group(1), 'Mpora')
 
-        # Look for embedded Novamov player
+        # Look for embedded NovaMov player
         mobj = re.search(
             r'<iframe[^>]+?src=(["\'])(?P<url>http://(?:(?:embed|www)\.)?novamov\.com/embed\.php.+?)\1', webpage)
         if mobj is not None:
-            return self.url_result(mobj.group('url'), 'Novamov')
+            return self.url_result(mobj.group('url'), 'NovaMov')
+
+        # Look for embedded NowVideo player
+        mobj = re.search(
+            r'<iframe[^>]+?src=(["\'])(?P<url>http://(?:(?:embed|www)\.)?nowvideo\.(?:ch|sx|eu)/embed\.php.+?)\1', webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'), 'NowVideo')
 
         # Look for embedded Facebook player
         mobj = re.search(
@@ -346,12 +487,44 @@ class GenericIE(InfoExtractor):
         if mobj is not None:
             return self.url_result(mobj.group('url'), 'Facebook')
 
+        # Look for embedded VK player
+        mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'), 'VK')
+
         # Look for embedded Huffington Post player
         mobj = re.search(
             r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
         if mobj is not None:
             return self.url_result(mobj.group('url'), 'HuffPost')
 
+        # Look for embed.ly
+        mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'))
+        mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
+        if mobj is not None:
+            return self.url_result(compat_urllib_parse.unquote(mobj.group('url')))
+
+        # Look for funnyordie embed
+        matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
+        if matches:
+            urlrs = [self.url_result(unescapeHTML(eurl), 'FunnyOrDie')
+                     for eurl in matches]
+            return self.playlist_result(
+                urlrs, playlist_id=video_id, playlist_title=video_title)
+
+        # Look for embedded RUTV player
+        rutv_url = RUTVIE._extract_url(webpage)
+        if rutv_url:
+            return self.url_result(rutv_url, 'RUTV')
+
+        # Look for embedded TED player
+        mobj = re.search(
+            r'<iframe[^>]+?src=(["\'])(?P<url>http://embed\.ted\.com/.+?)\1', webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'), 'TED')
+
         # Start with something easy: JW Player in SWFObject
         mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
         if mobj is None:
@@ -363,6 +536,7 @@ class GenericIE(InfoExtractor):
         if mobj is None:
             # Broaden the search a little bit: JWPlayer JS loader
             mobj = re.search(r'[^A-Za-z0-9]?file["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage)
+
         if mobj is None:
             # Try to find twitter cards info
             mobj = re.search(r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage)
@@ -376,6 +550,18 @@ class GenericIE(InfoExtractor):
         if mobj is None:
             # HTML5 video
             mobj = re.search(r'<video[^<]*(?:>.*?<source.*?)? src="([^"]+)"', webpage, flags=re.DOTALL)
+        if mobj is None:
+            mobj = re.search(
+                r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
+                r'(?:[a-z-]+="[^"]+"\s+)*?content="[0-9]{,2};url=\'([^\']+)\'"',
+                webpage)
+            if mobj:
+                new_url = mobj.group(1)
+                self.report_following_redirect(new_url)
+                return {
+                    '_type': 'url',
+                    'url': new_url,
+                }
         if mobj is None:
             raise ExtractorError('Unsupported URL: %s' % url)
 

youtube_dl/extractor/googleplus.py

@@ -1,4 +1,5 @@
 # coding: utf-8
+from __future__ import unicode_literals
 
 import datetime
 import re
@@ -10,32 +11,28 @@ from ..utils import (
 
 
 class GooglePlusIE(InfoExtractor):
-    IE_DESC = u'Google Plus'
-    _VALID_URL = r'(?:https://)?plus\.google\.com/(?:[^/]+/)*?posts/(\w+)'
-    IE_NAME = u'plus.google'
+    IE_DESC = 'Google Plus'
+    _VALID_URL = r'https://plus\.google\.com/(?:[^/]+/)*?posts/(?P<id>\w+)'
+    IE_NAME = 'plus.google'
     _TEST = {
-        u"url": u"https://plus.google.com/u/0/108897254135232129896/posts/ZButuJc6CtH",
-        u"file": u"ZButuJc6CtH.flv",
-        u"info_dict": {
-            u"upload_date": u"20120613",
-            u"uploader": u"井上ヨシマサ",
-            u"title": u"嘆きの天使 降臨"
+        'url': 'https://plus.google.com/u/0/108897254135232129896/posts/ZButuJc6CtH',
+        'info_dict': {
+            'id': 'ZButuJc6CtH',
+            'ext': 'flv',
+            'upload_date': '20120613',
+            'uploader': '井上ヨシマサ',
+            'title': '嘆きの天使 降臨',
         }
     }
 
     def _real_extract(self, url):
         # Extract id from URL
         mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError(u'Invalid URL: %s' % url)
 
-        post_url = mobj.group(0)
-        video_id = mobj.group(1)
-
-        video_extension = 'flv'
+        video_id = mobj.group('id')
 
         # Step 1, Retrieve post webpage to extract further information
-        webpage = self._download_webpage(post_url, video_id, u'Downloading entry webpage')
+        webpage = self._download_webpage(url, video_id, 'Downloading entry webpage')
 
         self.report_extraction(video_id)
 
@@ -43,7 +40,7 @@ class GooglePlusIE(InfoExtractor):
         upload_date = self._html_search_regex(
             r'''(?x)<a.+?class="o-U-s\s[^"]+"\s+style="display:\s*none"\s*>
                     ([0-9]{4}-[0-9]{2}-[0-9]{2})</a>''',
-            webpage, u'upload date', fatal=False, flags=re.VERBOSE)
+            webpage, 'upload date', fatal=False, flags=re.VERBOSE)
         if upload_date:
             # Convert timestring to a format suitable for filename
             upload_date = datetime.datetime.strptime(upload_date, "%Y-%m-%d")
@@ -51,28 +48,27 @@ class GooglePlusIE(InfoExtractor):
 
         # Extract uploader
         uploader = self._html_search_regex(r'rel\="author".*?>(.*?)</a>',
-            webpage, u'uploader', fatal=False)
+            webpage, 'uploader', fatal=False)
 
         # Extract title
         # Get the first line for title
         video_title = self._html_search_regex(r'<meta name\=\"Description\" content\=\"(.*?)[\n<"]',
-            webpage, 'title', default=u'NA')
+            webpage, 'title', default='NA')
 
         # Step 2, Simulate clicking the image box to launch video
         DOMAIN = 'https://plus.google.com/'
         video_page = self._search_regex(r'<a href="((?:%s)?photos/.*?)"' % re.escape(DOMAIN),
-            webpage, u'video page URL')
+            webpage, 'video page URL')
         if not video_page.startswith(DOMAIN):
             video_page = DOMAIN + video_page
 
-        webpage = self._download_webpage(video_page, video_id, u'Downloading video page')
+        webpage = self._download_webpage(video_page, video_id, 'Downloading video page')
 
-        # Extract video links on video page
-        """Extract video links of all sizes"""
+        # Extract video links all sizes
         pattern = r'\d+,\d+,(\d+),"(http\://redirector\.googlevideo\.com.*?)"'
         mobj = re.findall(pattern, webpage)
         if len(mobj) == 0:
-            raise ExtractorError(u'Unable to extract video links')
+            raise ExtractorError('Unable to extract video links')
 
         # Sort in resolution
         links = sorted(mobj)
@@ -87,12 +83,11 @@ class GooglePlusIE(InfoExtractor):
         except AttributeError: # Python 3
             video_url = bytes(video_url, 'ascii').decode('unicode-escape')
 
-
-        return [{
-            'id':       video_id,
-            'url':      video_url,
+        return {
+            'id': video_id,
+            'url': video_url,
             'uploader': uploader,
-            'upload_date':  upload_date,
-            'title':    video_title,
-            'ext':      video_extension,
-        }]
+            'upload_date': upload_date,
+            'title': video_title,
+            'ext': 'flv',
+        }

youtube_dl/extractor/googlesearch.py

@@ -46,6 +46,6 @@ class GoogleSearchIE(SearchInfoExtractor):
                     'url': mobj.group(1)
                 })
 
-            if (len(entries) >= n) or not re.search(r'class="pn" id="pnnext"', webpage):
+            if (len(entries) >= n) or not re.search(r'id="pnnext"', webpage):
                 res['entries'] = entries[:n]
                 return res

youtube_dl/extractor/helsinki.py

@@ -0,0 +1,62 @@
+# -*- coding: utf-8 -*-
+
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class HelsinkiIE(InfoExtractor):
+    IE_DESC = 'helsinki.fi'
+    _VALID_URL = r'https?://video\.helsinki\.fi/Arkisto/flash\.php\?id=(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://video.helsinki.fi/Arkisto/flash.php?id=20258',
+        'info_dict': {
+            'id': '20258',
+            'ext': 'mp4',
+            'title': 'Tietotekniikkafoorumi-iltapäivä',
+            'description': 'md5:f5c904224d43c133225130fe156a5ee0',
+        },
+        'params': {
+            'skip_download': True,  # RTMP
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        webpage = self._download_webpage(url, video_id)
+        formats = []
+
+        mobj = re.search(r'file=((\w+):[^&]+)', webpage)
+        if mobj:
+            formats.append({
+                'ext': mobj.group(2),
+                'play_path': mobj.group(1),
+                'url': 'rtmp://flashvideo.it.helsinki.fi/vod/',
+                'player_url': 'http://video.helsinki.fi/player.swf',
+                'format_note': 'sd',
+                'quality': 0,
+            })
+
+        mobj = re.search(r'hd\.file=((\w+):[^&]+)', webpage)
+        if mobj:
+            formats.append({
+                'ext': mobj.group(2),
+                'play_path': mobj.group(1),
+                'url': 'rtmp://flashvideo.it.helsinki.fi/vod/',
+                'player_url': 'http://video.helsinki.fi/player.swf',
+                'format_note': 'hd',
+                'quality': 1,
+            })
+
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': self._og_search_title(webpage).replace('Video: ', ''),
+            'description': self._og_search_description(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'formats': formats,
+        }

youtube_dl/extractor/howcast.py

@@ -1,17 +1,20 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
 
 
 class HowcastIE(InfoExtractor):
-    _VALID_URL = r'(?:https?://)?(?:www\.)?howcast\.com/videos/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?howcast\.com/videos/(?P<id>\d+)'
     _TEST = {
-        u'url': u'http://www.howcast.com/videos/390161-How-to-Tie-a-Square-Knot-Properly',
-        u'file': u'390161.mp4',
-        u'md5': u'8b743df908c42f60cf6496586c7f12c3',
-        u'info_dict': {
-            u"description": u"The square knot, also known as the reef knot, is one of the oldest, most basic knots to tie, and can be used in many different ways. Here's the proper way to tie a square knot.", 
-            u"title": u"How to Tie a Square Knot Properly"
+        'url': 'http://www.howcast.com/videos/390161-How-to-Tie-a-Square-Knot-Properly',
+        'md5': '8b743df908c42f60cf6496586c7f12c3',
+        'info_dict': {
+            'id': '390161',
+            'ext': 'mp4',
+            'description': 'The square knot, also known as the reef knot, is one of the oldest, most basic knots to tie, and can be used in many different ways. Here\'s the proper way to tie a square knot.', 
+            'title': 'How to Tie a Square Knot Properly',
         }
     }
 
@@ -24,22 +27,15 @@ class HowcastIE(InfoExtractor):
         self.report_extraction(video_id)
 
         video_url = self._search_regex(r'\'?file\'?: "(http://mobile-media\.howcast\.com/[0-9]+\.mp4)',
-            webpage, u'video URL')
-
-        video_title = self._html_search_regex(r'<meta content=(?:"([^"]+)"|\'([^\']+)\') property=\'og:title\'',
-            webpage, u'title')
+            webpage, 'video URL')
 
         video_description = self._html_search_regex(r'<meta content=(?:"([^"]+)"|\'([^\']+)\') name=\'description\'',
-            webpage, u'description', fatal=False)
+            webpage, 'description', fatal=False)
 
-        thumbnail = self._html_search_regex(r'<meta content=\'(.+?)\' property=\'og:image\'',
-            webpage, u'thumbnail', fatal=False)
-
-        return [{
-            'id':       video_id,
-            'url':      video_url,
-            'ext':      'mp4',
-            'title':    video_title,
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': self._og_search_title(webpage),
             'description': video_description,
-            'thumbnail': thumbnail,
-        }]
+            'thumbnail': self._og_search_thumbnail(webpage),
+        }

youtube_dl/extractor/instagram.py

@@ -1,35 +1,107 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+)
+
 
 class InstagramIE(InfoExtractor):
-    _VALID_URL = r'(?:http://)?instagram\.com/p/(.*?)/'
+    _VALID_URL = r'http://instagram\.com/p/(?P<id>.*?)/'
     _TEST = {
-        u'url': u'http://instagram.com/p/aye83DjauH/?foo=bar#abc',
-        u'file': u'aye83DjauH.mp4',
-        u'md5': u'0d2da106a9d2631273e192b372806516',
-        u'info_dict': {
-            u"uploader_id": u"naomipq", 
-            u"title": u"Video by naomipq",
-            u'description': u'md5:1f17f0ab29bd6fe2bfad705f58de3cb8',
+        'url': 'http://instagram.com/p/aye83DjauH/?foo=bar#abc',
+        'md5': '0d2da106a9d2631273e192b372806516',
+        'info_dict': {
+            'id': 'aye83DjauH',
+            'ext': 'mp4',
+            'uploader_id': 'naomipq',
+            'title': 'Video by naomipq',
+            'description': 'md5:1f17f0ab29bd6fe2bfad705f58de3cb8',
         }
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group(1)
+        video_id = mobj.group('id')
         webpage = self._download_webpage(url, video_id)
         uploader_id = self._search_regex(r'"owner":{"username":"(.+?)"',
-            webpage, u'uploader id', fatal=False)
-        desc = self._search_regex(r'"caption":"(.*?)"', webpage, u'description',
+            webpage, 'uploader id', fatal=False)
+        desc = self._search_regex(r'"caption":"(.*?)"', webpage, 'description',
             fatal=False)
 
-        return [{
-            'id':        video_id,
-            'url':       self._og_search_video_url(webpage, secure=False),
-            'ext':       'mp4',
-            'title':     u'Video by %s' % uploader_id,
+        return {
+            'id': video_id,
+            'url': self._og_search_video_url(webpage, secure=False),
+            'ext': 'mp4',
+            'title': 'Video by %s' % uploader_id,
             'thumbnail': self._og_search_thumbnail(webpage),
-            'uploader_id' : uploader_id,
+            'uploader_id': uploader_id,
             'description': desc,
-        }]
+        }
+
+
+class InstagramUserIE(InfoExtractor):
+    _VALID_URL = r'http://instagram\.com/(?P<username>[^/]{2,})/?(?:$|[?#])'
+    IE_DESC = 'Instagram user profile'
+    IE_NAME = 'instagram:user'
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        uploader_id = mobj.group('username')
+
+        entries = []
+        page_count = 0
+        media_url = 'http://instagram.com/%s/media' % uploader_id
+        while True:
+            page = self._download_json(
+                media_url, uploader_id,
+                note='Downloading page %d ' % (page_count + 1),
+            )
+            page_count += 1
+
+            for it in page['items']:
+                if it.get('type') != 'video':
+                    continue
+                like_count = int_or_none(it.get('likes', {}).get('count'))
+                user = it.get('user', {})
+
+                formats = [{
+                    'format_id': k,
+                    'height': v.get('height'),
+                    'width': v.get('width'),
+                    'url': v['url'],
+                } for k, v in it['videos'].items()]
+                self._sort_formats(formats)
+
+                thumbnails_el = it.get('images', {})
+                thumbnail = thumbnails_el.get('thumbnail', {}).get('url')
+
+                title = it.get('caption', {}).get('text', it['id'])
+
+                entries.append({
+                    'id': it['id'],
+                    'title': title,
+                    'formats': formats,
+                    'thumbnail': thumbnail,
+                    'webpage_url': it.get('link'),
+                    'uploader': user.get('full_name'),
+                    'uploader_id': user.get('username'),
+                    'like_count': like_count,
+                    'timestamp': int_or_none(it.get('created_time')),
+                })
+
+            if not page['items']:
+                break
+            max_id = page['items'][-1]['id']
+            media_url = (
+                'http://instagram.com/%s/media?max_id=%s' % (
+                    uploader_id, max_id))
+
+        return {
+            '_type': 'playlist',
+            'entries': entries,
+            'id': uploader_id,
+            'title': uploader_id,
+        }

youtube_dl/extractor/iprima.py

@@ -6,11 +6,14 @@ from random import random
 from math import floor
 
 from .common import InfoExtractor
-from ..utils import compat_urllib_request
+from ..utils import (
+    compat_urllib_request,
+    ExtractorError,
+)
 
 
 class IPrimaIE(InfoExtractor):
-    _VALID_URL = r'https?://play\.iprima\.cz/(?P<videogroup>.+)/(?P<videoid>.+)'
+    _VALID_URL = r'https?://play\.iprima\.cz/[^?#]+/(?P<id>[^?#]+)'
 
     _TESTS = [{
         'url': 'http://play.iprima.cz/particka/particka-92',
@@ -22,20 +25,37 @@ class IPrimaIE(InfoExtractor):
             'thumbnail': 'http://play.iprima.cz/sites/default/files/image_crops/image_620x349/3/491483_particka-92_image_620x349.jpg',
         },
         'params': {
-            'skip_download': True,
+            'skip_download': True,  # requires rtmpdump
         },
-    },
-    ]
+    }, {
+        'url': 'http://play.iprima.cz/particka/tchibo-particka-jarni-moda',
+        'info_dict': {
+            'id': '9718337',
+            'ext': 'flv',
+            'title': 'Tchibo Partička - Jarní móda',
+            'description': 'md5:589f8f59f414220621ff8882eb3ce7be',
+            'thumbnail': 're:^http:.*\.jpg$',
+        },
+        'params': {
+            'skip_download': True,  # requires rtmpdump
+        },
+        'skip': 'Do not have permission to access this page',
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('videoid')
+        video_id = mobj.group('id')
 
         webpage = self._download_webpage(url, video_id)
 
-        player_url = 'http://embed.livebox.cz/iprimaplay/player-embed-v2.js?__tok%s__=%s' % (
-                         floor(random()*1073741824),
-                         floor(random()*1073741824))
+        if re.search(r'Nemáte oprávnění přistupovat na tuto stránku\.\s*</div>', webpage):
+            raise ExtractorError(
+                '%s said: You do not have permission to access this page' % self.IE_NAME, expected=True)
+
+        player_url = (
+            'http://embed.livebox.cz/iprimaplay/player-embed-v2.js?__tok%s__=%s' %
+            (floor(random()*1073741824), floor(random()*1073741824))
+        )
 
         req = compat_urllib_request.Request(player_url)
         req.add_header('Referer', url)
@@ -44,18 +64,20 @@ class IPrimaIE(InfoExtractor):
         base_url = ''.join(re.findall(r"embed\['stream'\] = '(.+?)'.+'(\?auth=)'.+'(.+?)';", playerpage)[1])
 
         zoneGEO = self._html_search_regex(r'"zoneGEO":(.+?),', webpage, 'zoneGEO')
-
         if zoneGEO != '0':
-            base_url = base_url.replace('token', 'token_'+zoneGEO)
+            base_url = base_url.replace('token', 'token_' + zoneGEO)
 
         formats = []
         for format_id in ['lq', 'hq', 'hd']:
-            filename = self._html_search_regex(r'"%s_id":(.+?),' % format_id, webpage, 'filename')
+            filename = self._html_search_regex(
+                r'"%s_id":(.+?),' % format_id, webpage, 'filename')
 
             if filename == 'null':
                 continue
 
-            real_id = self._search_regex(r'Prima-[0-9]{10}-([0-9]+)_', filename, 'real video id')
+            real_id = self._search_regex(
+                r'Prima-(?:[0-9]{10}|WEB)-([0-9]+)[-_]',
+                filename, 'real video id')
 
             if format_id == 'lq':
                 quality = 0
@@ -63,13 +85,13 @@ class IPrimaIE(InfoExtractor):
                 quality = 1
             elif format_id == 'hd':
                 quality = 2
-                filename = 'hq/'+filename
+                filename = 'hq/' + filename
 
             formats.append({
                 'format_id': format_id,
                 'url': base_url,
                 'quality': quality,
-                'play_path': 'mp4:'+filename.replace('"', '')[:-4],
+                'play_path': 'mp4:' + filename.replace('"', '')[:-4],
                 'rtmp_live': True,
                 'ext': 'flv',
             })

youtube_dl/extractor/ivi.py

@@ -14,15 +14,16 @@ from ..utils import (
 class IviIE(InfoExtractor):
     IE_DESC = 'ivi.ru'
     IE_NAME = 'ivi'
-    _VALID_URL = r'^https?://(?:www\.)?ivi\.ru/watch(?:/(?P<compilationid>[^/]+))?/(?P<videoid>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?ivi\.ru/watch(?:/(?P<compilationid>[^/]+))?/(?P<videoid>\d+)'
 
     _TESTS = [
         # Single movie
         {
             'url': 'http://www.ivi.ru/watch/53141',
-            'file': '53141.mp4',
             'md5': '6ff5be2254e796ed346251d117196cf4',
             'info_dict': {
+                'id': '53141',
+                'ext': 'mp4',
                 'title': 'Иван Васильевич меняет профессию',
                 'description': 'md5:b924063ea1677c8fe343d8a72ac2195f',
                 'duration': 5498,
@@ -33,9 +34,10 @@ class IviIE(InfoExtractor):
         # Serial's serie
         {
             'url': 'http://www.ivi.ru/watch/dezhurnyi_angel/74791',
-            'file': '74791.mp4',
             'md5': '3e6cc9a848c1d2ebcc6476444967baa9',
             'info_dict': {
+                'id': '74791',
+                'ext': 'mp4',
                 'title': 'Дежурный ангел - 1 серия',
                 'duration': 2490,
                 'thumbnail': 'http://thumbs.ivi.ru/f7.vcp.digitalaccess.ru/contents/8/e/bc2f6c2b6e5d291152fdd32c059141.jpg',
@@ -124,7 +126,7 @@ class IviIE(InfoExtractor):
 class IviCompilationIE(InfoExtractor):
     IE_DESC = 'ivi.ru compilations'
     IE_NAME = 'ivi:compilation'
-    _VALID_URL = r'^https?://(?:www\.)?ivi\.ru/watch/(?!\d+)(?P<compilationid>[a-z\d_-]+)(?:/season(?P<seasonid>\d+))?$'
+    _VALID_URL = r'https?://(?:www\.)?ivi\.ru/watch/(?!\d+)(?P<compilationid>[a-z\d_-]+)(?:/season(?P<seasonid>\d+))?$'
 
     def _extract_entries(self, html, compilation_id):
         return [self.url_result('http://www.ivi.ru/watch/%s/%s' % (compilation_id, serie), 'Ivi')

youtube_dl/extractor/jadorecettepub.py

@@ -0,0 +1,48 @@
+# coding: utf-8
+
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from .youtube import YoutubeIE
+
+
+class JadoreCettePubIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?jadorecettepub\.com/[0-9]{4}/[0-9]{2}/(?P<id>.*?)\.html'
+
+    _TEST = {
+        'url': 'http://www.jadorecettepub.com/2010/12/star-wars-massacre-par-les-japonais.html',
+        'md5': '401286a06067c70b44076044b66515de',
+        'info_dict': {
+            'id': 'jLMja3tr7a4',
+            'ext': 'mp4',
+            'title': 'La pire utilisation de Star Wars',
+            'description': "Jadorecettepub.com vous a gratifié de plusieurs pubs géniales utilisant Star Wars et Dark Vador plus particulièrement... Mais l'heure est venue de vous proposer une version totalement massacrée, venue du Japon.  Quand les Japonais détruisent l'image de Star Wars pour vendre du thon en boite, ça promet...",
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        display_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, display_id)
+
+        title = self._html_search_regex(
+            r'<span style="font-size: x-large;"><b>(.*?)</b></span>',
+            webpage, 'title')
+        description = self._html_search_regex(
+            r'(?s)<div id="fb-root">(.*?)<script>', webpage, 'description',
+            fatal=False)
+        real_url = self._search_regex(
+            r'\[/postlink\](.*)endofvid', webpage, 'video URL')
+        video_id = YoutubeIE.extract_id(real_url)
+
+        return {
+            '_type': 'url_transparent',
+            'url': real_url,
+            'id': video_id,
+            'title': title,
+            'description': description,
+        }
+

youtube_dl/extractor/jeuxvideo.py

@@ -1,5 +1,7 @@
 # coding: utf-8
 
+from __future__ import unicode_literals
+
 import json
 import re
 
@@ -10,12 +12,13 @@ class JeuxVideoIE(InfoExtractor):
     _VALID_URL = r'http://.*?\.jeuxvideo\.com/.*/(.*?)-\d+\.htm'
 
     _TEST = {
-        u'url': u'http://www.jeuxvideo.com/reportages-videos-jeux/0004/00046170/tearaway-playstation-vita-gc-2013-tearaway-nous-presente-ses-papiers-d-identite-00115182.htm',
-        u'file': u'5182.mp4',
-        u'md5': u'046e491afb32a8aaac1f44dd4ddd54ee',
-        u'info_dict': {
-            u'title': u'GC 2013 : Tearaway nous présente ses papiers d\'identité',
-            u'description': u'Lorsque les développeurs de LittleBigPlanet proposent un nouveau titre, on ne peut que s\'attendre à un résultat original et fort attrayant.\n',
+        'url': 'http://www.jeuxvideo.com/reportages-videos-jeux/0004/00046170/tearaway-playstation-vita-gc-2013-tearaway-nous-presente-ses-papiers-d-identite-00115182.htm',
+        'md5': '046e491afb32a8aaac1f44dd4ddd54ee',
+        'info_dict': {
+            'id': '5182',
+            'ext': 'mp4',
+            'title': 'GC 2013 : Tearaway nous présente ses papiers d\'identité',
+            'description': 'Lorsque les développeurs de LittleBigPlanet proposent un nouveau titre, on ne peut que s\'attendre à un résultat original et fort attrayant.\n',
         },
     }
 
@@ -25,14 +28,14 @@ class JeuxVideoIE(InfoExtractor):
         webpage = self._download_webpage(url, title)
         xml_link = self._html_search_regex(
             r'<param name="flashvars" value="config=(.*?)" />',
-            webpage, u'config URL')
+            webpage, 'config URL')
         
         video_id = self._search_regex(
             r'http://www\.jeuxvideo\.com/config/\w+/\d+/(.*?)/\d+_player\.xml',
-            xml_link, u'video ID')
+            xml_link, 'video ID')
 
         config = self._download_xml(
-            xml_link, title, u'Downloading XML config')
+            xml_link, title, 'Downloading XML config')
         info_json = config.find('format.json').text
         info = json.loads(info_json)['versions'][0]
         

youtube_dl/extractor/jukebox.py

@@ -1,56 +1,61 @@
-# coding: utf-8
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
+    RegexNotFoundError,
     unescapeHTML,
 )
 
+
 class JukeboxIE(InfoExtractor):
     _VALID_URL = r'^http://www\.jukebox?\..+?\/.+[,](?P<video_id>[a-z0-9\-]+)\.html'
-    _IFRAME = r'<iframe .*src="(?P<iframe>[^"]*)".*>'
-    _VIDEO_URL = r'"config":{"file":"(?P<video_url>http:[^"]+[.](?P<video_ext>[^.?]+)[?]mdtk=[0-9]+)"'
-    _TITLE = r'<h1 class="inline">(?P<title>[^<]+)</h1>.*<span id="infos_article_artist">(?P<artist>[^<]+)</span>'
-    _IS_YOUTUBE = r'config":{"file":"(?P<youtube_url>http:[\\][/][\\][/]www[.]youtube[.]com[\\][/]watch[?]v=[^"]+)"'
+    _TEST = {
+        'url': 'http://www.jukebox.es/kosheen/videoclip,pride,r303r.html',
+        'md5': '5dc6477e74b1e37042ac5acedd8413e5',
+        'info_dict': {
+            'id': 'r303r',
+            'ext': 'flv',
+            'title': 'Kosheen-En Vivo Pride',
+            'uploader': 'Kosheen',
+        },
+    }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('video_id')
 
         html = self._download_webpage(url, video_id)
-
-        mobj = re.search(self._IFRAME, html)
-        if mobj is None:
-            raise ExtractorError(u'Cannot extract iframe url')
-        iframe_url = unescapeHTML(mobj.group('iframe'))
+        iframe_url = unescapeHTML(self._search_regex(r'<iframe .*src="([^"]*)"', html, 'iframe url'))
 
         iframe_html = self._download_webpage(iframe_url, video_id, 'Downloading iframe')
-        mobj = re.search(r'class="jkb_waiting"', iframe_html)
-        if mobj is not None:
-            raise ExtractorError(u'Video is not available(in your country?)!')
+        if re.search(r'class="jkb_waiting"', iframe_html) is not None:
+            raise ExtractorError('Video is not available(in your country?)!')
 
         self.report_extraction(video_id)
 
-        mobj = re.search(self._VIDEO_URL, iframe_html)
-        if mobj is None:
-            mobj = re.search(self._IS_YOUTUBE, iframe_html)
-            if mobj is None:
-                raise ExtractorError(u'Cannot extract video url')
-            youtube_url = unescapeHTML(mobj.group('youtube_url')).replace('\/','/')
-            self.to_screen(u'Youtube video detected')
-            return self.url_result(youtube_url,ie='Youtube')
-        video_url = unescapeHTML(mobj.group('video_url')).replace('\/','/')
-        video_ext = unescapeHTML(mobj.group('video_ext'))
+        try:
+            video_url = self._search_regex(r'"config":{"file":"(?P<video_url>http:[^"]+\?mdtk=[0-9]+)"',
+                iframe_html, 'video url')
+            video_url = unescapeHTML(video_url).replace('\/', '/')
+        except RegexNotFoundError:
+            youtube_url = self._search_regex(
+                r'config":{"file":"(http:\\/\\/www\.youtube\.com\\/watch\?v=[^"]+)"',
+                iframe_html, 'youtube url')
+            youtube_url = unescapeHTML(youtube_url).replace('\/', '/')
+            self.to_screen('Youtube video detected')
+            return self.url_result(youtube_url, ie='Youtube')
 
-        mobj = re.search(self._TITLE, html)
-        if mobj is None:
-            raise ExtractorError(u'Cannot extract title')
-        title = unescapeHTML(mobj.group('title'))
-        artist = unescapeHTML(mobj.group('artist'))
+        title = self._html_search_regex(r'<h1 class="inline">([^<]+)</h1>',
+            html, 'title')
+        artist = self._html_search_regex(r'<span id="infos_article_artist">([^<]+)</span>',
+            html, 'artist')
 
-        return [{'id': video_id,
-                 'url': video_url,
-                 'title': artist + '-' + title,
-                 'ext': video_ext
-                 }]
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': artist + '-' + title,
+            'uploader': artist,
+        }

youtube_dl/extractor/kontrtube.py

@@ -0,0 +1,66 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import int_or_none
+
+
+class KontrTubeIE(InfoExtractor):
+    IE_NAME = 'kontrtube'
+    IE_DESC = 'KontrTube.ru - Труба зовёт'
+    _VALID_URL = r'http://(?:www\.)?kontrtube\.ru/videos/(?P<id>\d+)/.+'
+
+    _TEST = {
+        'url': 'http://www.kontrtube.ru/videos/2678/nad-olimpiyskoy-derevney-v-sochi-podnyat-rossiyskiy-flag/',
+        'md5': '975a991a4926c9a85f383a736a2e6b80',
+        'info_dict': {
+            'id': '2678',
+            'ext': 'mp4',
+            'title': 'Над олимпийской деревней в Сочи поднят российский флаг',
+            'description': 'md5:80edc4c613d5887ae8ccf1d59432be41',
+            'thumbnail': 'http://www.kontrtube.ru/contents/videos_screenshots/2000/2678/preview.mp4.jpg',
+            'duration': 270,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id, 'Downloading page')
+
+        video_url = self._html_search_regex(r"video_url: '(.+?)/?',", webpage, 'video URL')
+        thumbnail = self._html_search_regex(r"preview_url: '(.+?)/?',", webpage, 'video thumbnail', fatal=False)
+        title = self._html_search_regex(
+            r'<title>(.+?) - Труба зовёт - Интересный видеохостинг</title>', webpage, 'video title')
+        description = self._html_search_meta('description', webpage, 'video description')
+
+        mobj = re.search(
+            r'<div class="col_2">Длительность: <span>(?P<minutes>\d+)м:(?P<seconds>\d+)с</span></div>', webpage)
+        duration = int(mobj.group('minutes')) * 60 + int(mobj.group('seconds')) if mobj else None
+
+        view_count = self._html_search_regex(
+            r'<div class="col_2">Просмотров: <span>(\d+)</span></div>', webpage, 'view count', fatal=False)
+
+        comment_count = None
+        comment_str = self._html_search_regex(
+            r'Комментарии: <span>([^<]+)</span>', webpage, 'comment count', fatal=False)
+        if comment_str.startswith('комментариев нет'):
+            comment_count = 0
+        else:
+            mobj = re.search(r'\d+ из (?P<total>\d+) комментариев', comment_str)
+            if mobj:
+                comment_count = mobj.group('total')
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'thumbnail': thumbnail,
+            'title': title,
+            'description': description,
+            'duration': duration,
+            'view_count': int_or_none(view_count),
+            'comment_count': int_or_none(comment_count),
+        }

youtube_dl/extractor/lifenews.py

@@ -4,19 +4,24 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import unified_strdate
+from ..utils import (
+    int_or_none,
+    unified_strdate,
+    ExtractorError,
+)
 
 
 class LifeNewsIE(InfoExtractor):
     IE_NAME = 'lifenews'
     IE_DESC = 'LIFE | NEWS'
     _VALID_URL = r'http://lifenews\.ru/(?:mobile/)?news/(?P<id>\d+)'
-    
+
     _TEST = {
         'url': 'http://lifenews.ru/news/126342',
-        'file': '126342.mp4',
         'md5': 'e1b50a5c5fb98a6a544250f2e0db570a',
         'info_dict': {
+            'id': '126342',
+            'ext': 'mp4',
             'title': 'МВД разыскивает мужчин, оставивших в IKEA сумку с автоматом',
             'description': 'Камеры наблюдения гипермаркета зафиксировали троих мужчин, спрятавших оружейный арсенал в камере хранения.',
             'thumbnail': 'http://lifenews.ru/static/posts/2014/1/126342/.video.jpg',
@@ -28,13 +33,11 @@ class LifeNewsIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
 
-        webpage = self._download_webpage('http://lifenews.ru/mobile/news/%s' % video_id, video_id, 'Downloading page')
+        webpage = self._download_webpage('http://lifenews.ru/news/%s' % video_id, video_id, 'Downloading page')
 
-        video_url = self._html_search_regex(
-            r'<video.*?src="([^"]+)".*?></video>', webpage, 'video URL')
-        
-        thumbnail = self._html_search_regex(
-            r'<video.*?poster="([^"]+)".*?"></video>', webpage, 'video thumbnail')
+        videos = re.findall(r'<video.*?poster="(?P<poster>[^"]+)".*?src="(?P<video>[^"]+)".*?></video>', webpage)
+        if not videos:
+            raise ExtractorError('No media links available for %s' % video_id)
 
         title = self._og_search_title(webpage)
         TITLE_SUFFIX = ' - Первый по срочным новостям — LIFE | NEWS'
@@ -44,20 +47,28 @@ class LifeNewsIE(InfoExtractor):
         description = self._og_search_description(webpage)
 
         view_count = self._html_search_regex(
-            r'<div class=\'views\'>(\d+)</div>', webpage, 'view count')
+            r'<div class=\'views\'>(\d+)</div>', webpage, 'view count', fatal=False)
         comment_count = self._html_search_regex(
-            r'<div class=\'comments\'>(\d+)</div>', webpage, 'comment count')
+            r'<div class=\'comments\'>\s*<span class=\'counter\'>(\d+)</span>', webpage, 'comment count', fatal=False)
 
         upload_date = self._html_search_regex(
-            r'<time datetime=\'([^\']+)\'>', webpage, 'upload date')
+            r'<time datetime=\'([^\']+)\'>', webpage, 'upload date',fatal=False)
+        if upload_date is not None:
+            upload_date = unified_strdate(upload_date)
 
-        return {
-            'id': video_id,
-            'url': video_url,
-            'thumbnail': thumbnail,
-            'title': title,
-            'description': description,
-            'view_count': view_count,
-            'comment_count': comment_count,
-            'upload_date': unified_strdate(upload_date),
-        }
+        def make_entry(video_id, media, video_number=None):
+            return {
+                'id': video_id,
+                'url': media[1],
+                'thumbnail': media[0],
+                'title': title if video_number is None else '%s-video%s' % (title, video_number),
+                'description': description,
+                'view_count': int_or_none(view_count),
+                'comment_count': int_or_none(comment_count),
+                'upload_date': upload_date,
+            }
+
+        if len(videos) == 1:
+            return make_entry(video_id, videos[0])
+        else:
+            return [make_entry(video_id, media, video_number+1) for video_number, media in enumerate(videos)]

youtube_dl/extractor/liveleak.py

@@ -4,15 +4,17 @@ import json
 import re
 
 from .common import InfoExtractor
+from ..utils import int_or_none
 
 
 class LiveLeakIE(InfoExtractor):
     _VALID_URL = r'^(?:http://)?(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<video_id>[\w_]+)(?:.*)'
     _TESTS = [{
         'url': 'http://www.liveleak.com/view?i=757_1364311680',
-        'file': '757_1364311680.mp4',
         'md5': '0813c2430bea7a46bf13acf3406992f4',
         'info_dict': {
+            'id': '757_1364311680',
+            'ext': 'mp4',
             'description': 'extremely bad day for this guy..!',
             'uploader': 'ljfriel2',
             'title': 'Most unlucky car accident'
@@ -20,25 +22,62 @@ class LiveLeakIE(InfoExtractor):
     },
     {
         'url': 'http://www.liveleak.com/view?i=f93_1390833151',
-        'file': 'f93_1390833151.mp4',
         'md5': 'd3f1367d14cc3c15bf24fbfbe04b9abf',
         'info_dict': {
+            'id': 'f93_1390833151',
+            'ext': 'mp4',
             'description': 'German Television Channel NDR does an exclusive interview with Edward Snowden.\r\nUploaded on LiveLeak cause German Television thinks the rest of the world isn\'t intereseted in Edward Snowden.',
             'uploader': 'ARD_Stinkt',
             'title': 'German Television does first Edward Snowden Interview (ENGLISH)',
         }
+    },
+    {
+        'url': 'http://www.liveleak.com/view?i=4f7_1392687779',
+        'md5': '42c6d97d54f1db107958760788c5f48f',
+        'info_dict': {
+            'id': '4f7_1392687779',
+            'ext': 'mp4',
+            'description': "The guy with the cigarette seems amazingly nonchalant about the whole thing...  I really hope my friends' reactions would be a bit stronger.\r\n\r\nAction-go to 0:55.",
+            'uploader': 'CapObveus',
+            'title': 'Man is Fatally Struck by Reckless Car While Packing up a Moving Truck',
+            'age_limit': 18,
+        }
     }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-
         video_id = mobj.group('video_id')
         webpage = self._download_webpage(url, video_id)
+
+        video_title = self._og_search_title(webpage).replace('LiveLeak.com -', '').strip()
+        video_description = self._og_search_description(webpage)
+        video_uploader = self._html_search_regex(
+            r'By:.*?(\w+)</a>', webpage, 'uploader', fatal=False)
+        age_limit = int_or_none(self._search_regex(
+            r'you confirm that you are ([0-9]+) years and over.',
+            webpage, 'age limit', default=None))
+
         sources_raw = self._search_regex(
             r'(?s)sources:\s*(\[.*?\]),', webpage, 'video URLs', default=None)
         if sources_raw is None:
-            sources_raw = '[{ %s}]' % (
-                self._search_regex(r'(file: ".*?"),', webpage, 'video URL'))
+            alt_source = self._search_regex(
+                r'(file: ".*?"),', webpage, 'video URL', default=None)
+            if alt_source:
+                sources_raw = '[{ %s}]' % alt_source
+            else:
+                # Maybe an embed?
+                embed_url = self._search_regex(
+                    r'<iframe[^>]+src="(http://www.prochan.com/embed\?[^"]+)"',
+                    webpage, 'embed URL')
+                return {
+                    '_type': 'url_transparent',
+                    'url': embed_url,
+                    'id': video_id,
+                    'title': video_title,
+                    'description': video_description,
+                    'uploader': video_uploader,
+                    'age_limit': age_limit,
+                }
 
         sources_json = re.sub(r'\s([a-z]+):\s', r'"\1": ', sources_raw)
         sources = json.loads(sources_json)
@@ -49,15 +88,11 @@ class LiveLeakIE(InfoExtractor):
         } for s in sources]
         self._sort_formats(formats)
 
-        video_title = self._og_search_title(webpage).replace('LiveLeak.com -', '').strip()
-        video_description = self._og_search_description(webpage)
-        video_uploader = self._html_search_regex(
-            r'By:.*?(\w+)</a>', webpage, 'uploader', fatal=False)
-
         return {
             'id': video_id,
             'title': video_title,
             'description': video_description,
             'uploader': video_uploader,
             'formats': formats,
+            'age_limit': age_limit,
         }

youtube_dl/extractor/lynda.py

@@ -8,7 +8,9 @@ from .common import InfoExtractor
 from ..utils import (
     compat_urllib_parse,
     compat_urllib_request,
-    ExtractorError
+    ExtractorError,
+    int_or_none,
+    compat_str,
 )
 
 
@@ -19,16 +21,17 @@ class LyndaIE(SubtitlesInfoExtractor):
     _LOGIN_URL = 'https://www.lynda.com/login/login.aspx'
     _NETRC_MACHINE = 'lynda'
 
-    _SUCCESSFUL_LOGIN_REGEX = r'<a href="https://www.lynda.com/home/userAccount/ChangeContactInfo.aspx" data-qa="eyebrow_account_menu">My account'
+    _SUCCESSFUL_LOGIN_REGEX = r'isLoggedIn: true'
     _TIMECODE_REGEX = r'\[(?P<timecode>\d+:\d+:\d+[\.,]\d+)\]'
 
     ACCOUNT_CREDENTIALS_HINT = 'Use --username and --password options to provide lynda.com account credentials.'
 
     _TEST = {
         'url': 'http://www.lynda.com/Bootstrap-tutorials/Using-exercise-files/110885/114408-4.html',
-        'file': '114408.mp4',
         'md5': 'ecfc6862da89489161fb9cd5f5a6fac1',
         'info_dict': {
+            'id': '114408',
+            'ext': 'mp4',
             'title': 'Using the exercise files',
             'duration': 68
         }
@@ -41,27 +44,44 @@ class LyndaIE(SubtitlesInfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group(1)
 
-        page = self._download_webpage('http://www.lynda.com/ajax/player?videoId=%s&type=video' % video_id,
-                                      video_id, 'Downloading video JSON')
+        page = self._download_webpage('http://www.lynda.com/ajax/player?videoId=%s&type=video' % video_id, video_id,
+            'Downloading video JSON')
         video_json = json.loads(page)
 
         if 'Status' in video_json:
             raise ExtractorError('lynda returned error: %s' % video_json['Message'], expected=True)
 
         if video_json['HasAccess'] is False:
-            raise ExtractorError('Video %s is only available for members. ' % video_id + self.ACCOUNT_CREDENTIALS_HINT, expected=True)
+            raise ExtractorError(
+                'Video %s is only available for members. ' % video_id + self.ACCOUNT_CREDENTIALS_HINT, expected=True)
 
-        video_id = video_json['ID']
+        video_id = compat_str(video_json['ID'])
         duration = video_json['DurationInSeconds']
         title = video_json['Title']
 
-        formats = [{'url': fmt['Url'],
+        formats = []
+
+        fmts = video_json.get('Formats')
+        if fmts:
+            formats.extend([
+                {
+                    'url': fmt['Url'],
                     'ext': fmt['Extension'],
                     'width': fmt['Width'],
                     'height': fmt['Height'],
                     'filesize': fmt['FileSize'],
                     'format_id': str(fmt['Resolution'])
-                    } for fmt in video_json['Formats']]
+                } for fmt in fmts])
+
+        prioritized_streams = video_json.get('PrioritizedStreams')
+        if prioritized_streams:
+            formats.extend([
+                {
+                    'url': video_url,
+                    'width': int_or_none(format_id),
+                    'format_id': format_id,
+                } for format_id, video_url in prioritized_streams['0'].items()
+            ])
 
         self._sort_formats(formats)
 
@@ -91,7 +111,7 @@ class LyndaIE(SubtitlesInfoExtractor):
             'stayPut': 'false'
         }        
         request = compat_urllib_request.Request(self._LOGIN_URL, compat_urllib_parse.urlencode(login_form))
-        login_page = self._download_webpage(request, None, note='Logging in as %s' % username)
+        login_page = self._download_webpage(request, None, 'Logging in as %s' % username)
 
         # Not (yet) logged in
         m = re.search(r'loginResultJson = \'(?P<json>[^\']+)\';', login_page)
@@ -116,7 +136,7 @@ class LyndaIE(SubtitlesInfoExtractor):
                     'stayPut': 'false',
                 }
                 request = compat_urllib_request.Request(self._LOGIN_URL, compat_urllib_parse.urlencode(confirm_form))
-                login_page = self._download_webpage(request, None, note='Confirming log in and log out from another device')
+                login_page = self._download_webpage(request, None, 'Confirming log in and log out from another device')
 
         if re.search(self._SUCCESSFUL_LOGIN_REGEX, login_page) is None:
             raise ExtractorError('Unable to log in')
@@ -150,7 +170,7 @@ class LyndaIE(SubtitlesInfoExtractor):
 
     def _get_available_subtitles(self, video_id, webpage):
         url = 'http://www.lynda.com/ajax/player?videoId=%s&type=transcript' % video_id
-        sub = self._download_webpage(url, None, note=False)
+        sub = self._download_webpage(url, None, False)
         sub_json = json.loads(sub)
         return {'en': url} if len(sub_json) > 0 else {}
 
@@ -179,6 +199,9 @@ class LyndaCourseIE(InfoExtractor):
         videos = []
         (username, _) = self._get_login_info()
 
+        # Might want to extract videos right here from video['Formats'] as it seems 'Formats' is not provided
+        # by single video API anymore
+
         for chapter in course_json['Chapters']:
             for video in chapter['Videos']:
                 if username is None and video['HasAccess'] is False:

youtube_dl/extractor/mailru.py

@@ -0,0 +1,66 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import re
+import datetime
+
+from .common import InfoExtractor
+
+
+class MailRuIE(InfoExtractor):
+    IE_NAME = 'mailru'
+    IE_DESC = 'Видео@Mail.Ru'
+    _VALID_URL = r'http://(?:www\.)?my\.mail\.ru/video/.*#video=/?(?P<id>[^/]+/[^/]+/[^/]+/\d+)'
+
+    _TEST = {
+        'url': 'http://my.mail.ru/video/top#video=/mail/sonypicturesrus/75/76',
+        'md5': 'dea205f03120046894db4ebb6159879a',
+        'info_dict': {
+            'id': '46301138',
+            'ext': 'mp4',
+            'title': 'Новый Человек-Паук. Высокое напряжение. Восстание Электро',
+            'upload_date': '20140224',
+            'uploader': 'sonypicturesrus',
+            'uploader_id': 'sonypicturesrus@mail.ru',
+            'duration': 184,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        video_data = self._download_json(
+            'http://videoapi.my.mail.ru/videos/%s.json?new=1' % video_id, video_id, 'Downloading video JSON')
+
+        author = video_data['author']
+        uploader = author['name']
+        uploader_id = author['id']
+
+        movie = video_data['movie']
+        content_id = str(movie['contentId'])
+        title = movie['title']
+        thumbnail = movie['poster']
+        duration = movie['duration']
+
+        upload_date = datetime.datetime.fromtimestamp(video_data['timestamp']).strftime('%Y%m%d')
+        view_count = video_data['views_count']
+
+        formats = [
+            {
+                'url': video['url'],
+                'format_id': video['name'],
+            } for video in video_data['videos']
+        ]
+
+        return {
+            'id': content_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'upload_date': upload_date,
+            'uploader': uploader,
+            'uploader_id': uploader_id,
+            'duration': duration,
+            'view_count': view_count,
+            'formats': formats,
+        }

youtube_dl/extractor/metacafe.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -9,104 +11,103 @@ from ..utils import (
     ExtractorError,
 )
 
-class MetacafeIE(InfoExtractor):
-    """Information Extractor for metacafe.com."""
 
-    _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*'
+class MetacafeIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*'
     _DISCLAIMER = 'http://www.metacafe.com/family_filter/'
     _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
-    IE_NAME = u'metacafe'
+    IE_NAME = 'metacafe'
     _TESTS = [
-    # Youtube video
-    {
-        u"add_ie": ["Youtube"],
-        u"url":  u"http://metacafe.com/watch/yt-_aUehQsCQtM/the_electric_company_short_i_pbs_kids_go/",
-        u"file":  u"_aUehQsCQtM.mp4",
-        u"info_dict": {
-            u"upload_date": u"20090102",
-            u"title": u"The Electric Company | \"Short I\" | PBS KIDS GO!",
-            u"description": u"md5:2439a8ef6d5a70e380c22f5ad323e5a8",
-            u"uploader": u"PBS",
-            u"uploader_id": u"PBS"
-        }
-    },
-    # Normal metacafe video
-    {
-        u'url': u'http://www.metacafe.com/watch/11121940/news_stuff_you_wont_do_with_your_playstation_4/',
-        u'md5': u'6e0bca200eaad2552e6915ed6fd4d9ad',
-        u'info_dict': {
-            u'id': u'11121940',
-            u'ext': u'mp4',
-            u'title': u'News: Stuff You Won\'t Do with Your PlayStation 4',
-            u'uploader': u'ign',
-            u'description': u'Sony released a massive FAQ on the PlayStation Blog detailing the PS4\'s capabilities and limitations.',
+        # Youtube video
+        {
+            'add_ie': ['Youtube'],
+            'url':  'http://metacafe.com/watch/yt-_aUehQsCQtM/the_electric_company_short_i_pbs_kids_go/',
+            'info_dict': {
+                'id': '_aUehQsCQtM',
+                'ext': 'mp4',
+                'upload_date': '20090102',
+                'title': 'The Electric Company | "Short I" | PBS KIDS GO!',
+                'description': 'md5:2439a8ef6d5a70e380c22f5ad323e5a8',
+                'uploader': 'PBS',
+                'uploader_id': 'PBS'
+            }
         },
-    },
-    # AnyClip video
-    {
-        u"url": u"http://www.metacafe.com/watch/an-dVVXnuY7Jh77J/the_andromeda_strain_1971_stop_the_bomb_part_3/",
-        u"file": u"an-dVVXnuY7Jh77J.mp4",
-        u"info_dict": {
-            u"title": u"The Andromeda Strain (1971): Stop the Bomb Part 3",
-            u"uploader": u"anyclip",
-            u"description": u"md5:38c711dd98f5bb87acf973d573442e67",
+        # Normal metacafe video
+        {
+            'url': 'http://www.metacafe.com/watch/11121940/news_stuff_you_wont_do_with_your_playstation_4/',
+            'md5': '6e0bca200eaad2552e6915ed6fd4d9ad',
+            'info_dict': {
+                'id': '11121940',
+                'ext': 'mp4',
+                'title': 'News: Stuff You Won\'t Do with Your PlayStation 4',
+                'uploader': 'ign',
+                'description': 'Sony released a massive FAQ on the PlayStation Blog detailing the PS4\'s capabilities and limitations.',
+            },
         },
-    },
-    # age-restricted video
-    {
-        u'url': u'http://www.metacafe.com/watch/5186653/bbc_internal_christmas_tape_79_uncensored_outtakes_etc/',
-        u'md5': u'98dde7c1a35d02178e8ab7560fe8bd09',
-        u'info_dict': {
-            u'id': u'5186653',
-            u'ext': u'mp4',
-            u'title': u'BBC INTERNAL Christmas Tape \'79 - UNCENSORED Outtakes, Etc.',
-            u'uploader': u'Dwayne Pipe',
-            u'description': u'md5:950bf4c581e2c059911fa3ffbe377e4b',
-            u'age_limit': 18,
+        # AnyClip video
+        {
+            'url': 'http://www.metacafe.com/watch/an-dVVXnuY7Jh77J/the_andromeda_strain_1971_stop_the_bomb_part_3/',
+            'info_dict': {
+                'id': 'an-dVVXnuY7Jh77J',
+                'ext': 'mp4',
+                'title': 'The Andromeda Strain (1971): Stop the Bomb Part 3',
+                'uploader': 'anyclip',
+                'description': 'md5:38c711dd98f5bb87acf973d573442e67',
+            },
         },
-    },
-    # cbs video
-    {
-        u'url': u'http://www.metacafe.com/watch/cb-0rOxMBabDXN6/samsung_galaxy_note_2_samsungs_next_generation_phablet/',
-        u'info_dict': {
-            u'id': u'0rOxMBabDXN6',
-            u'ext': u'flv',
-            u'title': u'Samsung Galaxy Note 2: Samsung\'s next-generation phablet',
-            u'description': u'md5:54d49fac53d26d5a0aaeccd061ada09d',
-            u'duration': 129,
+        # age-restricted video
+        {
+            'url': 'http://www.metacafe.com/watch/5186653/bbc_internal_christmas_tape_79_uncensored_outtakes_etc/',
+            'md5': '98dde7c1a35d02178e8ab7560fe8bd09',
+            'info_dict': {
+                'id': '5186653',
+                'ext': 'mp4',
+                'title': 'BBC INTERNAL Christmas Tape \'79 - UNCENSORED Outtakes, Etc.',
+                'uploader': 'Dwayne Pipe',
+                'description': 'md5:950bf4c581e2c059911fa3ffbe377e4b',
+                'age_limit': 18,
+            },
         },
-        u'params': {
-            # rtmp download
-            u'skip_download': True,
+        # cbs video
+        {
+            'url': 'http://www.metacafe.com/watch/cb-8VD4r_Zws8VP/open_this_is_face_the_nation_february_9/',
+            'info_dict': {
+                'id': '8VD4r_Zws8VP',
+                'ext': 'flv',
+                'title': 'Open: This is Face the Nation, February 9',
+                'description': 'md5:8a9ceec26d1f7ed6eab610834cc1a476',
+                'duration': 96,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
         },
-    },
     ]
 
-
     def report_disclaimer(self):
-        """Report disclaimer retrieval."""
-        self.to_screen(u'Retrieving disclaimer')
+        self.to_screen('Retrieving disclaimer')
 
     def _real_initialize(self):
         # Retrieve disclaimer
         self.report_disclaimer()
-        self._download_webpage(self._DISCLAIMER, None, False, u'Unable to retrieve disclaimer')
+        self._download_webpage(self._DISCLAIMER, None, False, 'Unable to retrieve disclaimer')
 
         # Confirm age
         disclaimer_form = {
             'filters': '0',
             'submit': "Continue - I'm over 18",
-            }
+        }
         request = compat_urllib_request.Request(self._FILTER_POST, compat_urllib_parse.urlencode(disclaimer_form))
         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
         self.report_age_confirmation()
-        self._download_webpage(request, None, False, u'Unable to confirm age')
+        self._download_webpage(request, None, False, 'Unable to confirm age')
 
     def _real_extract(self, url):
         # Extract id and simplified title from URL
         mobj = re.match(self._VALID_URL, url)
         if mobj is None:
-            raise ExtractorError(u'Invalid URL: %s' % url)
+            raise ExtractorError('Invalid URL: %s' % url)
 
         video_id = mobj.group(1)
 
@@ -153,22 +154,24 @@ class MetacafeIE(InfoExtractor):
             else:
                 mobj = re.search(r' name="flashvars" value="(.*?)"', webpage)
                 if mobj is None:
-                    raise ExtractorError(u'Unable to extract media URL')
+                    raise ExtractorError('Unable to extract media URL')
                 vardict = compat_parse_qs(mobj.group(1))
                 if 'mediaData' not in vardict:
-                    raise ExtractorError(u'Unable to extract media URL')
-                mobj = re.search(r'"mediaURL":"(?P<mediaURL>http.*?)",(.*?)"key":"(?P<key>.*?)"', vardict['mediaData'][0])
+                    raise ExtractorError('Unable to extract media URL')
+                mobj = re.search(
+                    r'"mediaURL":"(?P<mediaURL>http.*?)",(.*?)"key":"(?P<key>.*?)"', vardict['mediaData'][0])
                 if mobj is None:
-                    raise ExtractorError(u'Unable to extract media URL')
+                    raise ExtractorError('Unable to extract media URL')
                 mediaURL = mobj.group('mediaURL').replace('\\/', '/')
                 video_url = '%s?__gda__=%s' % (mediaURL, mobj.group('key'))
                 video_ext = determine_ext(video_url)
 
-        video_title = self._html_search_regex(r'(?im)<title>(.*) - Video</title>', webpage, u'title')
+        video_title = self._html_search_regex(r'(?im)<title>(.*) - Video</title>', webpage, 'title')
         description = self._og_search_description(webpage)
+        thumbnail = self._og_search_thumbnail(webpage)
         video_uploader = self._html_search_regex(
                 r'submitter=(.*?);|googletag\.pubads\(\)\.setTargeting\("(?:channel|submiter)","([^"]+)"\);',
-                webpage, u'uploader nickname', fatal=False)
+                webpage, 'uploader nickname', fatal=False)
 
         if re.search(r'"contentRating":"restricted"', webpage) is not None:
             age_limit = 18
@@ -176,13 +179,12 @@ class MetacafeIE(InfoExtractor):
             age_limit = 0
 
         return {
-            '_type':    'video',
-            'id':       video_id,
-            'url':      video_url,
+            'id': video_id,
+            'url': video_url,
             'description': description,
             'uploader': video_uploader,
-            'upload_date':  None,
-            'title':    video_title,
-            'ext':      video_ext,
+            'title': video_title,
+            'thumbnail':thumbnail,
+            'ext': video_ext,
             'age_limit': age_limit,
         }

youtube_dl/extractor/mit.py

@@ -1,24 +1,30 @@
+from __future__ import unicode_literals
+
 import re
 import json
 
 from .common import InfoExtractor
+from .youtube import YoutubeIE
 from ..utils import (
+    compat_urlparse,
     clean_html,
+    ExtractorError,
     get_element_by_id,
 )
 
 
 class TechTVMITIE(InfoExtractor):
-    IE_NAME = u'techtv.mit.edu'
+    IE_NAME = 'techtv.mit.edu'
     _VALID_URL = r'https?://techtv\.mit\.edu/(videos|embeds)/(?P<id>\d+)'
 
     _TEST = {
-        u'url': u'http://techtv.mit.edu/videos/25418-mit-dna-learning-center-set',
-        u'file': u'25418.mp4',
-        u'md5': u'1f8cb3e170d41fd74add04d3c9330e5f',
-        u'info_dict': {
-            u'title': u'MIT DNA Learning Center Set',
-            u'description': u'md5:82313335e8a8a3f243351ba55bc1b474',
+        'url': 'http://techtv.mit.edu/videos/25418-mit-dna-learning-center-set',
+        'md5': '1f8cb3e170d41fd74add04d3c9330e5f',
+        'info_dict': {
+            'id': '25418',
+            'ext': 'mp4',
+            'title': 'MIT DNA Learning Center Set',
+            'description': 'md5:82313335e8a8a3f243351ba55bc1b474',
         },
     }
 
@@ -27,12 +33,12 @@ class TechTVMITIE(InfoExtractor):
         video_id = mobj.group('id')
         raw_page = self._download_webpage(
             'http://techtv.mit.edu/videos/%s' % video_id, video_id)
-        clean_page = re.compile(u'<!--.*?-->', re.S).sub(u'', raw_page)
+        clean_page = re.compile(r'<!--.*?-->', re.S).sub('', raw_page)
 
-        base_url = self._search_regex(r'ipadUrl: \'(.+?cloudfront.net/)',
-            raw_page, u'base url')
-        formats_json = self._search_regex(r'bitrates: (\[.+?\])', raw_page,
-            u'video formats')
+        base_url = self._search_regex(
+            r'ipadUrl: \'(.+?cloudfront.net/)', raw_page, 'base url')
+        formats_json = self._search_regex(
+            r'bitrates: (\[.+?\])', raw_page, 'video formats')
         formats_mit = json.loads(formats_json)
         formats = [
             {
@@ -48,28 +54,31 @@ class TechTVMITIE(InfoExtractor):
 
         title = get_element_by_id('edit-title', clean_page)
         description = clean_html(get_element_by_id('edit-description', clean_page))
-        thumbnail = self._search_regex(r'playlist:.*?url: \'(.+?)\'',
-            raw_page, u'thumbnail', flags=re.DOTALL)
+        thumbnail = self._search_regex(
+            r'playlist:.*?url: \'(.+?)\'',
+            raw_page, 'thumbnail', flags=re.DOTALL)
 
-        return {'id': video_id,
-                'title': title,
-                'formats': formats,
-                'description': description,
-                'thumbnail': thumbnail,
-                }
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'description': description,
+            'thumbnail': thumbnail,
+        }
 
 
 class MITIE(TechTVMITIE):
-    IE_NAME = u'video.mit.edu'
+    IE_NAME = 'video.mit.edu'
     _VALID_URL = r'https?://video\.mit\.edu/watch/(?P<title>[^/]+)'
 
     _TEST = {
-        u'url': u'http://video.mit.edu/watch/the-government-is-profiling-you-13222/',
-        u'file': u'21783.mp4',
-        u'md5': u'7db01d5ccc1895fc5010e9c9e13648da',
-        u'info_dict': {
-            u'title': u'The Government is Profiling You',
-            u'description': u'md5:ad5795fe1e1623b73620dbfd47df9afd',
+        'url': 'http://video.mit.edu/watch/the-government-is-profiling-you-13222/',
+        'md5': '7db01d5ccc1895fc5010e9c9e13648da',
+        'info_dict': {
+            'id': '21783',
+            'ext': 'mp4',
+            'title': 'The Government is Profiling You',
+            'description': 'md5:ad5795fe1e1623b73620dbfd47df9afd',
         },
     }
 
@@ -77,7 +86,73 @@ class MITIE(TechTVMITIE):
         mobj = re.match(self._VALID_URL, url)
         page_title = mobj.group('title')
         webpage = self._download_webpage(url, page_title)
-        self.to_screen('%s: Extracting %s url' % (page_title, TechTVMITIE.IE_NAME))
-        embed_url = self._search_regex(r'<iframe .*?src="(.+?)"', webpage,
-            u'embed url')
+        embed_url = self._search_regex(
+            r'<iframe .*?src="(.+?)"', webpage, 'embed url')
         return self.url_result(embed_url, ie='TechTVMIT')
+
+
+class OCWMITIE(InfoExtractor):
+    IE_NAME = 'ocw.mit.edu'
+    _VALID_URL = r'^http://ocw\.mit\.edu/courses/(?P<topic>[a-z0-9\-]+)'
+    _BASE_URL = 'http://ocw.mit.edu/'
+
+    _TESTS = [
+        {
+            'url': 'http://ocw.mit.edu/courses/electrical-engineering-and-computer-science/6-041-probabilistic-systems-analysis-and-applied-probability-fall-2010/video-lectures/lecture-7-multiple-variables-expectations-independence/',
+            'info_dict': {
+                'id': 'EObHWIEKGjA',
+                'ext': 'mp4',
+                'title': 'Lecture 7: Multiple Discrete Random Variables: Expectations, Conditioning, Independence',
+                'description': 'In this lecture, the professor discussed multiple random variables, expectations, and binomial distribution.',
+                #'subtitles': 'http://ocw.mit.edu/courses/electrical-engineering-and-computer-science/6-041-probabilistic-systems-analysis-and-applied-probability-fall-2010/video-lectures/lecture-7-multiple-variables-expectations-independence/MIT6_041F11_lec07_300k.mp4.srt'
+            }
+        },
+        {
+            'url': 'http://ocw.mit.edu/courses/mathematics/18-01sc-single-variable-calculus-fall-2010/1.-differentiation/part-a-definition-and-basic-rules/session-1-introduction-to-derivatives/',
+            'info_dict': {
+                'id': '7K1sB05pE0A',
+                'ext': 'mp4',
+                'title': 'Session 1: Introduction to Derivatives',
+                'description': 'This section contains lecture video excerpts, lecture notes, an interactive mathlet with supporting documents, and problem solving videos.',
+                #'subtitles': 'http://ocw.mit.edu//courses/mathematics/18-01sc-single-variable-calculus-fall-2010/ocw-18.01-f07-lec01_300k.SRT'
+            }
+        }
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        topic = mobj.group('topic')
+
+        webpage = self._download_webpage(url, topic)
+        title = self._html_search_meta('WT.cg_s', webpage)
+        description = self._html_search_meta('Description', webpage)
+
+        # search for call to ocw_embed_chapter_media(container_id, media_url, provider, page_url, image_url, start, stop, captions_file)
+        embed_chapter_media = re.search(r'ocw_embed_chapter_media\((.+?)\)', webpage)
+        if embed_chapter_media:
+            metadata = re.sub(r'[\'"]', '', embed_chapter_media.group(1))
+            metadata = re.split(r', ?', metadata)
+            yt = metadata[1]
+            subs = compat_urlparse.urljoin(self._BASE_URL, metadata[7])
+        else:
+            # search for call to ocw_embed_chapter_media(container_id, media_url, provider, page_url, image_url, captions_file)
+            embed_media = re.search(r'ocw_embed_media\((.+?)\)', webpage)
+            if embed_media:
+                metadata = re.sub(r'[\'"]', '', embed_media.group(1))
+                metadata = re.split(r', ?', metadata)
+                yt = metadata[1]
+                subs = compat_urlparse.urljoin(self._BASE_URL, metadata[5])
+            else:
+                raise ExtractorError('Unable to find embedded YouTube video.')
+        video_id = YoutubeIE.extract_id(yt)
+
+        return {
+            '_type': 'url_transparent',
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'url': yt,
+            'url_transparent'
+            'subtitles': subs,
+            'ie_key': 'Youtube',
+        }

youtube_dl/extractor/mixcloud.py

@@ -5,18 +5,20 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     unified_strdate,
+    compat_urllib_parse,
     ExtractorError,
 )
 
 
 class MixcloudIE(InfoExtractor):
-    _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([\w\d-]+)/([\w\d-]+)'
+    _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([^/]+)/([^/]+)'
     IE_NAME = 'mixcloud'
 
     _TEST = {
         'url': 'http://www.mixcloud.com/dholbach/cryptkeeper/',
-        'file': 'dholbach-cryptkeeper.mp3',
         'info_dict': {
+            'id': 'dholbach-cryptkeeper',
+            'ext': 'mp3',
             'title': 'Cryptkeeper',
             'description': 'After quite a long silence from myself, finally another Drum\'n\'Bass mix with my favourite current dance floor bangers.',
             'uploader': 'Daniel Holbach',
@@ -45,7 +47,7 @@ class MixcloudIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         uploader = mobj.group(1)
         cloudcast_name = mobj.group(2)
-        track_id = '-'.join((uploader, cloudcast_name))
+        track_id = compat_urllib_parse.unquote('-'.join((uploader, cloudcast_name)))
 
         webpage = self._download_webpage(url, track_id)
 

youtube_dl/extractor/mooshare.py

@@ -61,7 +61,7 @@ class MooshareIE(InfoExtractor):
         }
 
         request = compat_urllib_request.Request(
-            'http://mooshare.biz/8dqtk4bjbp8g', compat_urllib_parse.urlencode(download_form))
+            'http://mooshare.biz/%s' % video_id, compat_urllib_parse.urlencode(download_form))
         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
 
         self.to_screen('%s: Waiting for timeout' % video_id)
@@ -111,4 +111,4 @@ class MooshareIE(InfoExtractor):
             'thumbnail': thumbnail,
             'duration': duration,
             'formats': formats,
-        }
+        }

youtube_dl/extractor/mtv.py

@@ -5,9 +5,12 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     compat_urllib_parse,
+    compat_urllib_request,
     ExtractorError,
     find_xpath_attr,
     fix_xml_ampersands,
+    HEADRequest,
+    unescapeHTML,
     url_basename,
     RegexNotFoundError,
 )
@@ -18,6 +21,7 @@ def _media_xml_tag(tag):
 
 
 class MTVServicesInfoExtractor(InfoExtractor):
+    _MOBILE_TEMPLATE = None
     @staticmethod
     def _id_from_uri(uri):
         return uri.split(':')[-1]
@@ -39,9 +43,29 @@ class MTVServicesInfoExtractor(InfoExtractor):
         else:
             return thumb_node.attrib['url']
 
-    def _extract_video_formats(self, mdoc):
-        if re.match(r'.*/error_country_block\.swf$', mdoc.find('.//src').text) is not None:
-            raise ExtractorError('This video is not available from your country.', expected=True)
+    def _extract_mobile_video_formats(self, mtvn_id):
+        webpage_url = self._MOBILE_TEMPLATE % mtvn_id
+        req = compat_urllib_request.Request(webpage_url)
+        # Otherwise we get a webpage that would execute some javascript
+        req.add_header('Youtubedl-user-agent', 'curl/7')
+        webpage = self._download_webpage(req, mtvn_id,
+            'Downloading mobile page')
+        metrics_url = unescapeHTML(self._search_regex(r'<a href="(http://metrics.+?)"', webpage, 'url'))
+        req = HEADRequest(metrics_url)
+        response = self._request_webpage(req, mtvn_id, 'Resolving url')
+        url = response.geturl()
+        # Transform the url to get the best quality:
+        url = re.sub(r'.+pxE=mp4', 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=0+_pxK=18639+_pxE=mp4', url, 1)
+        return [{'url': url,'ext': 'mp4'}]
+
+    def _extract_video_formats(self, mdoc, mtvn_id):
+        if re.match(r'.*/(error_country_block\.swf|geoblock\.mp4)$', mdoc.find('.//src').text) is not None:
+            if mtvn_id is not None and self._MOBILE_TEMPLATE is not None:
+                self.to_screen('The normal version is not available from your '
+                    'country, trying with the mobile version')
+                return self._extract_mobile_video_formats(mtvn_id)
+            raise ExtractorError('This video is not available from your country.',
+                expected=True)
 
         formats = []
         for rendition in mdoc.findall('.//rendition'):
@@ -82,21 +106,28 @@ class MTVServicesInfoExtractor(InfoExtractor):
             title_el = find_xpath_attr(
                 itemdoc, './/{http://search.yahoo.com/mrss/}category',
                 'scheme', 'urn:mtvn:video_title')
+        if title_el is None:
+            title_el = itemdoc.find('.//{http://search.yahoo.com/mrss/}title')
         if title_el is None:
             title_el = itemdoc.find('.//title')
             if title_el.text is None:
                 title_el = None
-        if title_el is None:
-            title_el = itemdoc.find('.//{http://search.yahoo.com/mrss/}title')
 
         title = title_el.text
         if title is None:
             raise ExtractorError('Could not find video title')
         title = title.strip()
 
+        # This a short id that's used in the webpage urls
+        mtvn_id = None
+        mtvn_id_node = find_xpath_attr(itemdoc, './/{http://search.yahoo.com/mrss/}category',
+                'scheme', 'urn:mtvn:id')
+        if mtvn_id_node is not None:
+            mtvn_id = mtvn_id_node.text
+
         return {
             'title': title,
-            'formats': self._extract_video_formats(mediagen_doc),
+            'formats': self._extract_video_formats(mediagen_doc, mtvn_id),
             'id': video_id,
             'thumbnail': self._get_thumbnail_url(uri, itemdoc),
             'description': description,

youtube_dl/extractor/myvideo.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import binascii
 import base64
 import hashlib
@@ -14,18 +16,16 @@ from ..utils import (
 )
 
 
-
 class MyVideoIE(InfoExtractor):
-    """Information Extractor for myvideo.de."""
-
-    _VALID_URL = r'(?:http://)?(?:www\.)?myvideo\.de/(?:[^/]+/)?watch/([0-9]+)/([^?/]+).*'
-    IE_NAME = u'myvideo'
+    _VALID_URL = r'http://(?:www\.)?myvideo\.de/(?:[^/]+/)?watch/(?P<id>[0-9]+)/[^?/]+.*'
+    IE_NAME = 'myvideo'
     _TEST = {
-        u'url': u'http://www.myvideo.de/watch/8229274/bowling_fail_or_win',
-        u'file': u'8229274.flv',
-        u'md5': u'2d2753e8130479ba2cb7e0a37002053e',
-        u'info_dict': {
-            u"title": u"bowling-fail-or-win"
+        'url': 'http://www.myvideo.de/watch/8229274/bowling_fail_or_win',
+        'md5': '2d2753e8130479ba2cb7e0a37002053e',
+        'info_dict': {
+            'id': '8229274',
+            'ext': 'flv',
+            'title': 'bowling-fail-or-win',
         }
     }
 
@@ -53,10 +53,7 @@ class MyVideoIE(InfoExtractor):
 
     def _real_extract(self,url):
         mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError(u'invalid URL: %s' % url)
-
-        video_id = mobj.group(1)
+        video_id = mobj.group('id')
 
         GK = (
           b'WXpnME1EZGhNRGhpTTJNM01XVmhOREU0WldNNVpHTTJOakpt'
@@ -74,37 +71,33 @@ class MyVideoIE(InfoExtractor):
             video_url = mobj.group(1) + '.flv'
 
             video_title = self._html_search_regex('<title>([^<]+)</title>',
-                webpage, u'title')
+                webpage, 'title')
 
-            video_ext = self._search_regex('[.](.+?)$', video_url, u'extension')
-
-            return [{
-                'id':       video_id,
-                'url':      video_url,
-                'uploader': None,
-                'upload_date':  None,
-                'title':    video_title,
-                'ext':      video_ext,
-            }]
+            return {
+                'id': video_id,
+                'url': video_url,
+                'title': video_title,
+            }
 
         mobj = re.search(r'data-video-service="/service/data/video/%s/config' % video_id, webpage)
         if mobj is not None:
             request = compat_urllib_request.Request('http://www.myvideo.de/service/data/video/%s/config' % video_id, '')
             response = self._download_webpage(request, video_id,
-                                              u'Downloading video info')
+                                              'Downloading video info')
             info = json.loads(base64.b64decode(response).decode('utf-8'))
-            return {'id': video_id,
-                    'title': info['title'],
-                    'url': info['streaming_url'].replace('rtmpe', 'rtmpt'),
-                    'play_path': info['filename'],
-                    'ext': 'flv',
-                    'thumbnail': info['thumbnail'][0]['url'],
-                    }
+            return {
+                'id': video_id,
+                'title': info['title'],
+                'url': info['streaming_url'].replace('rtmpe', 'rtmpt'),
+                'play_path': info['filename'],
+                'ext': 'flv',
+                'thumbnail': info['thumbnail'][0]['url'],
+            }
 
         # try encxml
         mobj = re.search('var flashvars={(.+?)}', webpage)
         if mobj is None:
-            raise ExtractorError(u'Unable to extract video')
+            raise ExtractorError('Unable to extract video')
 
         params = {}
         encxml = ''
@@ -118,7 +111,7 @@ class MyVideoIE(InfoExtractor):
             params['domain'] = 'www.myvideo.de'
         xmldata_url = '%s?%s' % (encxml, compat_urllib_parse.urlencode(params))
         if 'flash_playertype=MTV' in xmldata_url:
-            self._downloader.report_warning(u'avoiding MTV player')
+            self._downloader.report_warning('avoiding MTV player')
             xmldata_url = (
                 'http://www.myvideo.de/dynamic/get_player_video_xml.php'
                 '?flash_playertype=D&ID=%s&_countlimit=4&autorun=yes'
@@ -144,7 +137,7 @@ class MyVideoIE(InfoExtractor):
             video_url = compat_urllib_parse.unquote(mobj.group(1))
             if 'myvideo2flash' in video_url:
                 self.report_warning(
-                    u'Rewriting URL to use unencrypted rtmp:// ...',
+                    'Rewriting URL to use unencrypted rtmp:// ...',
                     video_id)
                 video_url = video_url.replace('rtmpe://', 'rtmp://')
 
@@ -152,39 +145,31 @@ class MyVideoIE(InfoExtractor):
             # extract non rtmp videos
             mobj = re.search('path=\'(http.*?)\' source=\'(.*?)\'', dec_data)
             if mobj is None:
-                raise ExtractorError(u'unable to extract url')
+                raise ExtractorError('unable to extract url')
             video_url = compat_urllib_parse.unquote(mobj.group(1)) + compat_urllib_parse.unquote(mobj.group(2))
 
-        video_file = self._search_regex('source=\'(.*?)\'', dec_data, u'video file')
+        video_file = self._search_regex('source=\'(.*?)\'', dec_data, 'video file')
         video_file = compat_urllib_parse.unquote(video_file)
 
         if not video_file.endswith('f4m'):
             ppath, prefix = video_file.split('.')
             video_playpath = '%s:%s' % (prefix, ppath)
-            video_hls_playlist = ''
         else:
             video_playpath = ''
-            video_hls_playlist = (
-                video_file
-            ).replace('.f4m', '.m3u8')
 
-        video_swfobj = self._search_regex('swfobject.embedSWF\(\'(.+?)\'', webpage, u'swfobj')
+        video_swfobj = self._search_regex('swfobject.embedSWF\(\'(.+?)\'', webpage, 'swfobj')
         video_swfobj = compat_urllib_parse.unquote(video_swfobj)
 
         video_title = self._html_search_regex("<h1(?: class='globalHd')?>(.*?)</h1>",
-            webpage, u'title')
+            webpage, 'title')
 
-        return [{
-            'id':                 video_id,
-            'url':                video_url,
-            'tc_url':             video_url,
-            'uploader':           None,
-            'upload_date':        None,
-            'title':              video_title,
-            'ext':                u'flv',
-            'play_path':          video_playpath,
-            'video_file':         video_file,
-            'video_hls_playlist': video_hls_playlist,
-            'player_url':         video_swfobj,
-        }]
+        return {
+            'id': video_id,
+            'url': video_url,
+            'tc_url': video_url,
+            'title': video_title,
+            'ext': 'flv',
+            'play_path': video_playpath,
+            'player_url': video_swfobj,
+        }
 

youtube_dl/extractor/nbc.py

@@ -1,19 +1,46 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
 from ..utils import find_xpath_attr, compat_str
 
 
+class NBCIE(InfoExtractor):
+    _VALID_URL = r'http://www\.nbc\.com/[^/]+/video/[^/]+/(?P<id>n?\d+)'
+
+    _TEST = {
+        'url': 'http://www.nbc.com/chicago-fire/video/i-am-a-firefighter/2734188',
+        'md5': '54d0fbc33e0b853a65d7b4de5c06d64e',
+        'info_dict': {
+            'id': 'u1RInQZRN7QJ',
+            'ext': 'flv',
+            'title': 'I Am a Firefighter',
+            'description': 'An emergency puts Dawson\'sf irefighter skills to the ultimate test in this four-part digital series.',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        webpage = self._download_webpage(url, video_id)
+        theplatform_url = self._search_regex('class="video-player video-player-full" data-mpx-url="(.*?)"', webpage, 'theplatform url')
+        if theplatform_url.startswith('//'):
+            theplatform_url = 'http:' + theplatform_url
+        return self.url_result(theplatform_url)
+
+
 class NBCNewsIE(InfoExtractor):
     _VALID_URL = r'https?://www\.nbcnews\.com/video/.+?/(?P<id>\d+)'
 
     _TEST = {
-        u'url': u'http://www.nbcnews.com/video/nbc-news/52753292',
-        u'file': u'52753292.flv',
-        u'md5': u'47abaac93c6eaf9ad37ee6c4463a5179',
-        u'info_dict': {
-            u'title': u'Crew emerges after four-month Mars food study',
-            u'description': u'md5:24e632ffac72b35f8b67a12d1b6ddfc1',
+        'url': 'http://www.nbcnews.com/video/nbc-news/52753292',
+        'md5': '47abaac93c6eaf9ad37ee6c4463a5179',
+        'info_dict': {
+            'id': '52753292',
+            'ext': 'flv',
+            'title': 'Crew emerges after four-month Mars food study',
+            'description': 'md5:24e632ffac72b35f8b67a12d1b6ddfc1',
         },
     }
 
@@ -23,10 +50,11 @@ class NBCNewsIE(InfoExtractor):
         all_info = self._download_xml('http://www.nbcnews.com/id/%s/displaymode/1219' % video_id, video_id)
         info = all_info.find('video')
 
-        return {'id': video_id,
-                'title': info.find('headline').text,
-                'ext': 'flv',
-                'url': find_xpath_attr(info, 'media', 'type', 'flashVideo').text,
-                'description': compat_str(info.find('caption').text),
-                'thumbnail': find_xpath_attr(info, 'media', 'type', 'thumbnail').text,
-                }
+        return {
+            'id': video_id,
+            'title': info.find('headline').text,
+            'ext': 'flv',
+            'url': find_xpath_attr(info, 'media', 'type', 'flashVideo').text,
+            'description': compat_str(info.find('caption').text),
+            'thumbnail': find_xpath_attr(info, 'media', 'type', 'thumbnail').text,
+        }

youtube_dl/extractor/ndr.py

@@ -0,0 +1,89 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+
+class NDRIE(InfoExtractor):
+    IE_NAME = 'ndr'
+    IE_DESC = 'NDR.de - Mediathek'
+    _VALID_URL = r'https?://www\.ndr\.de/.+?(?P<id>\d+)\.html'
+
+    _TESTS = [
+        {
+            'url': 'http://www.ndr.de/fernsehen/sendungen/markt/markt7959.html',
+            'md5': 'e7a6079ca39d3568f4996cb858dd6708',
+            'note': 'Video file',
+            'info_dict': {
+                'id': '7959',
+                'ext': 'mp4',
+                'title': 'Markt - die ganze Sendung',
+                'description': 'md5:af9179cf07f67c5c12dc6d9997e05725',
+                'duration': 2655,
+            },
+        },
+        {
+            'url': 'http://www.ndr.de/info/audio51535.html',
+            'md5': 'bb3cd38e24fbcc866d13b50ca59307b8',
+            'note': 'Audio file',
+            'info_dict': {
+                'id': '51535',
+                'ext': 'mp3',
+                'title': 'La Valette entgeht der Hinrichtung',
+                'description': 'md5:22f9541913a40fe50091d5cdd7c9f536',
+                'duration': 884,
+            }
+        }
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        page = self._download_webpage(url, video_id, 'Downloading page')
+
+        title = self._og_search_title(page)
+        description = self._og_search_description(page)
+
+        mobj = re.search(
+            r'<div class="duration"><span class="min">(?P<minutes>\d+)</span>:<span class="sec">(?P<seconds>\d+)</span></div>',
+            page)
+        duration = int(mobj.group('minutes')) * 60 + int(mobj.group('seconds')) if mobj else None
+
+        formats = []
+
+        mp3_url = re.search(r'''{src:'(?P<audio>[^']+)', type:"audio/mp3"},''', page)
+        if mp3_url:
+            formats.append({
+                'url': mp3_url.group('audio'),
+                'format_id': 'mp3',
+            })
+
+        thumbnail = None
+
+        video_url = re.search(r'''3: {src:'(?P<video>.+?)\.hi\.mp4', type:"video/mp4"},''', page)
+        if video_url:
+            thumbnail = self._html_search_regex(r'(?m)title: "NDR PLAYER",\s*poster: "([^"]+)",',
+                page, 'thumbnail', fatal=False)
+            if thumbnail:
+                thumbnail = 'http://www.ndr.de' + thumbnail
+            for format_id in ['lo', 'hi', 'hq']:
+                formats.append({
+                    'url': '%s.%s.mp4' % (video_url.group('video'), format_id),
+                    'format_id': format_id,
+                })
+
+        if not formats:
+            raise ExtractorError('No media links available for %s' % video_id)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'formats': formats,
+        }

youtube_dl/extractor/nfb.py

@@ -0,0 +1,94 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_request,
+    compat_urllib_parse,
+)
+
+
+class NFBIE(InfoExtractor):
+    IE_NAME = 'nfb'
+    IE_DESC = 'National Film Board of Canada'
+    _VALID_URL = r'https?://(?:www\.)?(nfb|onf)\.ca/film/(?P<id>[\da-z_-]+)'
+
+    _TEST = {
+        'url': 'https://www.nfb.ca/film/qallunaat_why_white_people_are_funny',
+        'info_dict': {
+            'id': 'qallunaat_why_white_people_are_funny',
+            'ext': 'mp4',
+            'title': 'Qallunaat! Why White People Are Funny ',
+            'description': 'md5:836d8aff55e087d04d9f6df554d4e038',
+            'duration': 3128,
+            'uploader': 'Mark Sandiford',
+            'uploader_id': 'mark-sandiford',
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        page = self._download_webpage('https://www.nfb.ca/film/%s' % video_id, video_id, 'Downloading film page')
+
+        uploader_id = self._html_search_regex(r'<a class="director-link" href="/explore-all-directors/([^/]+)/"',
+            page, 'director id', fatal=False)
+        uploader = self._html_search_regex(r'<em class="director-name" itemprop="name">([^<]+)</em>',
+            page, 'director name', fatal=False)
+
+        request = compat_urllib_request.Request('https://www.nfb.ca/film/%s/player_config' % video_id,
+            compat_urllib_parse.urlencode({'getConfig': 'true'}).encode('ascii'))
+        request.add_header('Content-Type', 'application/x-www-form-urlencoded')
+        request.add_header('X-NFB-Referer', 'http://www.nfb.ca/medias/flash/NFBVideoPlayer.swf')
+
+        config = self._download_xml(request, video_id, 'Downloading player config XML')
+
+        title = None
+        description = None
+        thumbnail = None
+        duration = None
+        formats = []
+
+        def extract_thumbnail(media):
+            thumbnails = {}
+            for asset in media.findall('assets/asset'):
+                thumbnails[asset.get('quality')] = asset.find('default/url').text
+            if not thumbnails:
+                return None
+            if 'high' in thumbnails:
+                return thumbnails['high']
+            return list(thumbnails.values())[0]
+
+        for media in config.findall('./player/stream/media'):
+            if media.get('type') == 'posterImage':
+                thumbnail = extract_thumbnail(media)
+            elif media.get('type') == 'video':
+                duration = int(media.get('duration'))
+                title = media.find('title').text
+                description = media.find('description').text
+                # It seems assets always go from lower to better quality, so no need to sort
+                formats = [{
+                    'url': x.find('default/streamerURI').text,
+                    'app': x.find('default/streamerURI').text.split('/', 3)[3],
+                    'play_path': x.find('default/url').text,
+                    'rtmp_live': False,
+                    'ext': 'mp4',
+                    'format_id': x.get('quality'),
+                } for x in media.findall('assets/asset')]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'uploader': uploader,
+            'uploader_id': uploader_id,
+            'formats': formats,
+        }

youtube_dl/extractor/ninegag.py

@@ -1,6 +1,5 @@
 from __future__ import unicode_literals
 
-import json
 import re
 
 from .common import InfoExtractor
@@ -12,10 +11,13 @@ class NineGagIE(InfoExtractor):
 
     _TEST = {
         "url": "http://9gag.tv/v/1912",
-        "file": "1912.mp4",
         "info_dict": {
+            "id": "1912",
+            "ext": "mp4",
             "description": "This 3-minute video will make you smile and then make you feel untalented and insignificant. Anyway, you should share this awesomeness. (Thanks, Dino!)",
-            "title": "\"People Are Awesome 2013\" Is Absolutely Awesome"
+            "title": "\"People Are Awesome 2013\" Is Absolutely Awesome",
+            "view_count": int,
+            "thumbnail": "re:^https?://",
         },
         'add_ie': ['Youtube']
     }
@@ -25,21 +27,27 @@ class NineGagIE(InfoExtractor):
         video_id = mobj.group('id')
 
         webpage = self._download_webpage(url, video_id)
-        data_json = self._html_search_regex(r'''(?x)
-            <div\s*id="tv-video"\s*data-video-source="youtube"\s*
-                data-video-meta="([^"]+)"''', webpage, 'video metadata')
 
-        data = json.loads(data_json)
+        youtube_id = self._html_search_regex(
+            r'(?s)id="jsid-video-post-container".*?data-external-id="([^"]+)"',
+            webpage, 'video ID')
+        description = self._html_search_regex(
+            r'(?s)<div class="video-caption">.*?<p>(.*?)</p>', webpage,
+            'description', fatal=False)
+        view_count_str = self._html_search_regex(
+            r'<p><b>([0-9][0-9,]*)</b> views</p>', webpage, 'view count',
+            fatal=False)
+        view_count = (
+            None if view_count_str is None
+            else int(view_count_str.replace(',', '')))
 
         return {
             '_type': 'url_transparent',
-            'url': data['youtubeVideoId'],
+            'url': youtube_id,
             'ie_key': 'Youtube',
             'id': video_id,
-            'title': data['title'],
-            'description': data['description'],
-            'view_count': int(data['view_count']),
-            'like_count': int(data['statistic']['like']),
-            'dislike_count': int(data['statistic']['dislike']),
-            'thumbnail': data['thumbnail_url'],
+            'title': self._og_search_title(webpage),
+            'description': description,
+            'view_count': view_count,
+            'thumbnail': self._og_search_thumbnail(webpage),
         }

youtube_dl/extractor/normalboots.py

@@ -1,61 +1,51 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
 
 from ..utils import (
-    ExtractorError,
     unified_strdate,
 )
 
+
 class NormalbootsIE(InfoExtractor):
-    _VALID_URL = r'(?:http://)?(?:www\.)?normalboots\.com/video/(?P<videoid>[0-9a-z-]*)/?$'
+    _VALID_URL = r'http://(?:www\.)?normalboots\.com/video/(?P<videoid>[0-9a-z-]*)/?$'
     _TEST = {
-        u'url': u'http://normalboots.com/video/home-alone-games-jontron/',
-        u'file': u'home-alone-games-jontron.mp4',
-        u'md5': u'8bf6de238915dd501105b44ef5f1e0f6',
-        u'info_dict': {
-            u'title': u'Home Alone Games - JonTron - NormalBoots',
-            u'description': u'Jon is late for Christmas. Typical. Thanks to: Paul Ritchey for Co-Writing/Filming: http://www.youtube.com/user/ContinueShow Michael Azzi for Christmas Intro Animation: http://michafrar.tumblr.com/ Jerrod Waters for Christmas Intro Music: http://www.youtube.com/user/xXJerryTerryXx Casey Ormond for \u2018Tense Battle Theme\u2019:\xa0http://www.youtube.com/Kiamet/',
-            u'uploader': u'JonTron',
-            u'upload_date': u'20140125',
+        'url': 'http://normalboots.com/video/home-alone-games-jontron/',
+        'md5': '8bf6de238915dd501105b44ef5f1e0f6',
+        'info_dict': {
+            'id': 'home-alone-games-jontron',
+            'ext': 'mp4',
+            'title': 'Home Alone Games - JonTron - NormalBoots',
+            'description': 'Jon is late for Christmas. Typical. Thanks to: Paul Ritchey for Co-Writing/Filming: http://www.youtube.com/user/ContinueShow Michael Azzi for Christmas Intro Animation: http://michafrar.tumblr.com/ Jerrod Waters for Christmas Intro Music: http://www.youtube.com/user/xXJerryTerryXx Casey Ormond for ‘Tense Battle Theme’:\xa0http://www.youtube.com/Kiamet/',
+            'uploader': 'JonTron',
+            'upload_date': '20140125',
         }
     }
-    
+
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError(u'Invalid URL: %s' % url)
         video_id = mobj.group('videoid')
-        
-        info = {
-            'id': video_id,
-            'uploader': None,
-            'upload_date': None,
-        }
-        
-        if url[:4] != 'http':
-            url = 'http://' + url
-        
+
         webpage = self._download_webpage(url, video_id)
-        video_title = self._og_search_title(webpage)
-        video_description = self._og_search_description(webpage)
-        video_thumbnail = self._og_search_thumbnail(webpage)
         video_uploader = self._html_search_regex(r'Posted\sby\s<a\shref="[A-Za-z0-9/]*">(?P<uploader>[A-Za-z]*)\s</a>',
             webpage, 'uploader')
-        raw_upload_date = self._html_search_regex('<span style="text-transform:uppercase; font-size:inherit;">[A-Za-z]+, (?P<date>.*)</span>', 
+        raw_upload_date = self._html_search_regex('<span style="text-transform:uppercase; font-size:inherit;">[A-Za-z]+, (?P<date>.*)</span>',
             webpage, 'date')
         video_upload_date = unified_strdate(raw_upload_date)
-        video_upload_date = unified_strdate(raw_upload_date)
-            
+
         player_url = self._html_search_regex(r'<iframe\swidth="[0-9]+"\sheight="[0-9]+"\ssrc="(?P<url>[\S]+)"', webpage, 'url')
         player_page = self._download_webpage(player_url, video_id)
-        video_url = u'http://player.screenwavemedia.com/' + self._html_search_regex(r"'file':\s'(?P<file>[0-9A-Za-z-_\.]+)'", player_page, 'file')
-        
-        info['url'] = video_url
-        info['title'] = video_title
-        info['description'] = video_description
-        info['thumbnail'] = video_thumbnail
-        info['uploader'] = video_uploader
-        info['upload_date'] = video_upload_date
-        
-        return info
+        video_url = self._html_search_regex(r"file:\s'(?P<file>[^']+\.mp4)'", player_page, 'file')
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': self._og_search_title(webpage),
+            'description': self._og_search_description(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'uploader': video_uploader,
+            'upload_date': video_upload_date,
+        }

youtube_dl/extractor/novamov.py

@@ -9,14 +9,25 @@ from ..utils import (
 )
 
 
-class NovamovIE(InfoExtractor):
-    _VALID_URL = r'http://(?:(?:www\.)?novamov\.com/video/|(?:(?:embed|www)\.)novamov\.com/embed\.php\?v=)(?P<videoid>[a-z\d]{13})'
+class NovaMovIE(InfoExtractor):
+    IE_NAME = 'novamov'
+    IE_DESC = 'NovaMov'
+
+    _VALID_URL = r'http://(?:(?:www\.)?%(host)s/video/|(?:(?:embed|www)\.)%(host)s/embed\.php\?(?:.*?&)?v=)(?P<videoid>[a-z\d]{13})' % {'host': 'novamov\.com'}
+
+    _HOST = 'www.novamov.com'
+
+    _FILE_DELETED_REGEX = r'This file no longer exists on our servers!</h2>'
+    _FILEKEY_REGEX = r'flashvars\.filekey="(?P<filekey>[^"]+)";'
+    _TITLE_REGEX = r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>([^<]+)</h3>'
+    _DESCRIPTION_REGEX = r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>[^<]+</h3><p>([^<]+)</p>'
 
     _TEST = {
         'url': 'http://www.novamov.com/video/4rurhn9x446jj',
-        'file': '4rurhn9x446jj.flv',
         'md5': '7205f346a52bbeba427603ba10d4b935',
         'info_dict': {
+            'id': '4rurhn9x446jj',
+            'ext': 'flv',
             'title': 'search engine optimization',
             'description': 'search engine optimization is used to rank the web page in the google search engine'
         },
@@ -27,31 +38,26 @@ class NovamovIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('videoid')
 
-        page = self._download_webpage('http://www.novamov.com/video/%s' % video_id,
-                                      video_id, 'Downloading video page')
+        page = self._download_webpage(
+            'http://%s/video/%s' % (self._HOST, video_id), video_id, 'Downloading video page')
 
-        if re.search(r'This file no longer exists on our servers!</h2>', page) is not None:
+        if re.search(self._FILE_DELETED_REGEX, page) is not None:
             raise ExtractorError(u'Video %s does not exist' % video_id, expected=True)
 
-        filekey = self._search_regex(
-            r'flashvars\.filekey="(?P<filekey>[^"]+)";', page, 'filekey')
+        filekey = self._search_regex(self._FILEKEY_REGEX, page, 'filekey')
 
-        title = self._html_search_regex(
-            r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>([^<]+)</h3>',
-            page, 'title', fatal=False)
+        title = self._html_search_regex(self._TITLE_REGEX, page, 'title', fatal=False)
 
-        description = self._html_search_regex(
-            r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>[^<]+</h3><p>([^<]+)</p>',
-            page, 'description', fatal=False)
+        description = self._html_search_regex(self._DESCRIPTION_REGEX, page, 'description', default='', fatal=False)
 
         api_response = self._download_webpage(
-            'http://www.novamov.com/api/player.api.php?key=%s&file=%s' % (filekey, video_id),
-            video_id, 'Downloading video api response')
+            'http://%s/api/player.api.php?key=%s&file=%s' % (self._HOST, filekey, video_id), video_id,
+            'Downloading video api response')
 
         response = compat_urlparse.parse_qs(api_response)
 
         if 'error_msg' in response:
-            raise ExtractorError('novamov returned error: %s' % response['error_msg'][0], expected=True)
+            raise ExtractorError('%s returned error: %s' % (self.IE_NAME, response['error_msg'][0]), expected=True)
 
         video_url = response['url'][0]
 
@@ -60,4 +66,4 @@ class NovamovIE(InfoExtractor):
             'url': video_url,
             'title': title,
             'description': description
-        }
+        }

youtube_dl/extractor/nowvideo.py

@@ -1,46 +1,28 @@
-import re
+from __future__ import unicode_literals
 
-from .common import InfoExtractor
-from ..utils import compat_urlparse
+from .novamov import NovaMovIE
 
 
-class NowVideoIE(InfoExtractor):
-    _VALID_URL = r'(?:https?://)?(?:www\.)?nowvideo\.(?:ch|sx)/video/(?P<id>\w+)'
+class NowVideoIE(NovaMovIE):
+    IE_NAME = 'nowvideo'
+    IE_DESC = 'NowVideo'
+
+    _VALID_URL = r'http://(?:(?:www\.)?%(host)s/video/|(?:(?:embed|www)\.)%(host)s/embed\.php\?(?:.*?&)?v=)(?P<videoid>[a-z\d]{13})' % {'host': 'nowvideo\.(?:ch|sx|eu)'}
+
+    _HOST = 'www.nowvideo.ch'
+
+    _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
+    _FILEKEY_REGEX = r'var fkzd="([^"]+)";'
+    _TITLE_REGEX = r'<h4>([^<]+)</h4>'
+    _DESCRIPTION_REGEX = r'</h4>\s*<p>([^<]+)</p>'
+
     _TEST = {
-        u'url': u'http://www.nowvideo.ch/video/0mw0yow7b6dxa',
-        u'file': u'0mw0yow7b6dxa.flv',
-        u'md5': u'f8fbbc8add72bd95b7850c6a02fc8817',
-        u'info_dict': {
-            u"title": u"youtubedl test video _BaW_jenozKc.mp4"
+        'url': 'http://www.nowvideo.ch/video/0mw0yow7b6dxa',
+        'md5': 'f8fbbc8add72bd95b7850c6a02fc8817',
+        'info_dict': {
+            'id': '0mw0yow7b6dxa',
+            'ext': 'flv',
+            'title': 'youtubedl test video _BaW_jenozKc.mp4',
+            'description': 'Description',
         }
-    }
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-
-        video_id = mobj.group('id')
-        webpage_url = 'http://www.nowvideo.ch/video/' + video_id
-        embed_url = 'http://embed.nowvideo.ch/embed.php?v=' + video_id
-        webpage = self._download_webpage(webpage_url, video_id)
-        embed_page = self._download_webpage(embed_url, video_id,
-            u'Downloading embed page')
-
-        self.report_extraction(video_id)
-
-        video_title = self._html_search_regex(r'<h4>(.*)</h4>',
-            webpage, u'video title')
-
-        video_key = self._search_regex(r'var fkzd="(.*)";',
-            embed_page, u'video key')
-
-        api_call = "http://www.nowvideo.ch/api/player.api.php?file={0}&numOfErrors=0&cid=1&key={1}".format(video_id, video_key)
-        api_response = self._download_webpage(api_call, video_id,
-            u'Downloading API page')
-        video_url = compat_urlparse.parse_qs(api_response)[u'url'][0]
-
-        return [{
-            'id':        video_id,
-            'url':       video_url,
-            'ext':       'flv',
-            'title':     video_title,
-        }]
+    }

youtube_dl/extractor/ooyala.py

@@ -1,20 +1,23 @@
+from __future__ import unicode_literals
 import re
 import json
 
 from .common import InfoExtractor
 from ..utils import unescapeHTML
 
+
 class OoyalaIE(InfoExtractor):
     _VALID_URL = r'https?://.+?\.ooyala\.com/.*?(?:embedCode|ec)=(?P<id>.+?)(&|$)'
 
     _TEST = {
         # From http://it.slashdot.org/story/13/04/25/178216/recovering-data-from-broken-hard-drives-and-ssds-video
-        u'url': u'http://player.ooyala.com/player.js?embedCode=pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8',
-        u'file': u'pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8.mp4',
-        u'md5': u'3f5cceb3a7bf461d6c29dc466cf8033c',
-        u'info_dict': {
-            u'title': u'Explaining Data Recovery from Hard Drives and SSDs',
-            u'description': u'How badly damaged does a drive have to be to defeat Russell and his crew? Apparently, smashed to bits.',
+        'url': 'http://player.ooyala.com/player.js?embedCode=pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8',
+        'md5': '3f5cceb3a7bf461d6c29dc466cf8033c',
+        'info_dict': {
+            'id': 'pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8',
+            'ext': 'mp4',
+            'title': 'Explaining Data Recovery from Hard Drives and SSDs',
+            'description': 'How badly damaged does a drive have to be to defeat Russell and his crew? Apparently, smashed to bits.',
         },
     }
 
@@ -28,13 +31,14 @@ class OoyalaIE(InfoExtractor):
             ie=cls.ie_key())
 
     def _extract_result(self, info, more_info):
-        return {'id': info['embedCode'],
-                'ext': 'mp4',
-                'title': unescapeHTML(info['title']),
-                'url': info.get('ipad_url') or info['url'],
-                'description': unescapeHTML(more_info['description']),
-                'thumbnail': more_info['promo'],
-                }
+        return {
+            'id': info['embedCode'],
+            'ext': 'mp4',
+            'title': unescapeHTML(info['title']),
+            'url': info.get('ipad_url') or info['url'],
+            'description': unescapeHTML(more_info['description']),
+            'thumbnail': more_info['promo'],
+        }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -42,22 +46,23 @@ class OoyalaIE(InfoExtractor):
         player_url = 'http://player.ooyala.com/player.js?embedCode=%s' % embedCode
         player = self._download_webpage(player_url, embedCode)
         mobile_url = self._search_regex(r'mobile_player_url="(.+?)&device="',
-                                        player, u'mobile player url')
+                                        player, 'mobile player url')
         mobile_player = self._download_webpage(mobile_url, embedCode)
         videos_info = self._search_regex(
             r'var streams=window.oo_testEnv\?\[\]:eval\("\((\[{.*?}\])\)"\);',
-            mobile_player, u'info').replace('\\"','"')
-        videos_more_info = self._search_regex(r'eval\("\(({.*?\\"promo\\".*?})\)"', mobile_player, u'more info').replace('\\"','"')
+            mobile_player, 'info').replace('\\"','"')
+        videos_more_info = self._search_regex(r'eval\("\(({.*?\\"promo\\".*?})\)"', mobile_player, 'more info').replace('\\"','"')
         videos_info = json.loads(videos_info)
         videos_more_info =json.loads(videos_more_info)
 
         if videos_more_info.get('lineup'):
             videos = [self._extract_result(info, more_info) for (info, more_info) in zip(videos_info, videos_more_info['lineup'])]
-            return {'_type': 'playlist',
-                    'id': embedCode,
-                    'title': unescapeHTML(videos_more_info['title']),
-                    'entries': videos,
-                    }
+            return {
+                '_type': 'playlist',
+                'id': embedCode,
+                'title': unescapeHTML(videos_more_info['title']),
+                'entries': videos,
+            }
         else:
             return self._extract_result(videos_info[0], videos_more_info)
         

youtube_dl/extractor/orf.py

@@ -8,6 +8,7 @@ from .common import InfoExtractor
 from ..utils import (
     HEADRequest,
     unified_strdate,
+    ExtractorError,
 )
 
 
@@ -35,7 +36,15 @@ class ORFIE(InfoExtractor):
         data_json = self._search_regex(
             r'initializeAdworx\((.+?)\);\n', webpage, 'video info')
         all_data = json.loads(data_json)
-        sdata = all_data[0]['values']['segments']
+
+        def get_segments(all_data):
+            for data in all_data:
+                if data['name'] == 'Tracker::EPISODE_DETAIL_PAGE_OVER_PROGRAM':
+                    return data['values']['segments']
+
+        sdata = get_segments(all_data)
+        if not sdata:
+            raise ExtractorError('Unable to extract segments')
 
         def quality_to_int(s):
             m = re.search('([0-9]+)', s)

youtube_dl/extractor/parliamentliveuk.py

@@ -0,0 +1,53 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class ParliamentLiveUKIE(InfoExtractor):
+    IE_NAME = 'parliamentlive.tv'
+    IE_DESC = 'UK parliament videos'
+    _VALID_URL = r'https?://www\.parliamentlive\.tv/Main/Player\.aspx\?(?:[^&]+&)*?meetingId=(?P<id>[0-9]+)'
+
+    _TEST = {
+        'url': 'http://www.parliamentlive.tv/Main/Player.aspx?meetingId=15121&player=windowsmedia',
+        'info_dict': {
+            'id': '15121',
+            'ext': 'asf',
+            'title': 'hoc home affairs committee, 18 mar 2014.pm',
+            'description': 'md5:033b3acdf83304cd43946b2d5e5798d1',
+        },
+        'params': {
+            'skip_download': True,  # Requires mplayer (mms)
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        webpage = self._download_webpage(url, video_id)
+
+        asx_url = self._html_search_regex(
+            r'embed.*?src="([^"]+)" name="MediaPlayer"', webpage,
+            'metadata URL')
+        asx = self._download_xml(asx_url, video_id, 'Downloading ASX metadata')
+        video_url = asx.find('.//REF').attrib['HREF']
+
+        title = self._search_regex(
+            r'''(?x)player\.setClipDetails\(
+                (?:(?:[0-9]+|"[^"]+"),\s*){2}
+                "([^"]+",\s*"[^"]+)"
+                ''',
+            webpage, 'title').replace('", "', ', ')
+        description = self._html_search_regex(
+            r'(?s)<span id="MainContentPlaceHolder_CaptionsBlock_WitnessInfo">(.*?)</span>',
+            webpage, 'description')
+
+        return {
+            'id': video_id,
+            'ext': 'asf',
+            'url': video_url,
+            'title': title,
+            'description': description,
+        }

youtube_dl/extractor/pbs.py

@@ -3,17 +3,20 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..utils import (
+    US_RATINGS,
+)
 
 
 class PBSIE(InfoExtractor):
     _VALID_URL = r'''(?x)https?://
         (?:
             # Direct video URL
-            video\.pbs\.org/video/(?P<id>[0-9]+)/? |
+            video\.pbs\.org/(?:viralplayer|video)/(?P<id>[0-9]+)/? |
             # Article with embedded player
            (?:www\.)?pbs\.org/(?:[^/]+/){2,5}(?P<presumptive_id>[^/]+)/?(?:$|[?\#]) |
            # Player
-           video\.pbs\.org/partnerplayer/(?P<player_id>[^/]+)/
+           video\.pbs\.org/(?:widget/)?partnerplayer/(?P<player_id>[^/]+)/
         )
     '''
 
@@ -57,6 +60,11 @@ class PBSIE(InfoExtractor):
         info_url = 'http://video.pbs.org/videoInfo/%s?format=json' % video_id
         info = self._download_json(info_url, display_id)
 
+        rating_str = info.get('rating')
+        if rating_str is not None:
+            rating_str = rating_str.rpartition('-')[2]
+        age_limit = US_RATINGS.get(rating_str)
+
         return {
             'id': video_id,
             'title': info['title'],
@@ -65,4 +73,5 @@ class PBSIE(InfoExtractor):
             'description': info['program'].get('description'),
             'thumbnail': info.get('image_url'),
             'duration': info.get('duration'),
+            'age_limit': age_limit,
         }

youtube_dl/extractor/photobucket.py

@@ -1,76 +1,43 @@
+from __future__ import unicode_literals
+
 import datetime
 import json
 import re
 
 from .common import InfoExtractor
 
-from ..utils import (
-    ExtractorError,
-)
 
 class PhotobucketIE(InfoExtractor):
-    """Information extractor for photobucket.com."""
-
-    # TODO: the original _VALID_URL was:
-    # r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*[\?\&]current=(.*\.flv)'
-    # Check if it's necessary to keep the old extracion process
-    _VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*(([\?\&]current=)|_)(?P<id>.*)\.(?P<ext>(flv)|(mp4))'
-    IE_NAME = u'photobucket'
+    _VALID_URL = r'http://(?:[a-z0-9]+\.)?photobucket\.com/.*(([\?\&]current=)|_)(?P<id>.*)\.(?P<ext>(flv)|(mp4))'
     _TEST = {
-        u'url': u'http://media.photobucket.com/user/rachaneronas/media/TiredofLinkBuildingTryBacklinkMyDomaincom_zpsc0c3b9fa.mp4.html?filters[term]=search&filters[primary]=videos&filters[secondary]=images&sort=1&o=0',
-        u'file': u'zpsc0c3b9fa.mp4',
-        u'md5': u'7dabfb92b0a31f6c16cebc0f8e60ff99',
-        u'info_dict': {
-            u"upload_date": u"20130504", 
-            u"uploader": u"rachaneronas", 
-            u"title": u"Tired of Link Building? Try BacklinkMyDomain.com!"
+        'url': 'http://media.photobucket.com/user/rachaneronas/media/TiredofLinkBuildingTryBacklinkMyDomaincom_zpsc0c3b9fa.mp4.html?filters[term]=search&filters[primary]=videos&filters[secondary]=images&sort=1&o=0',
+        'file': 'zpsc0c3b9fa.mp4',
+        'md5': '7dabfb92b0a31f6c16cebc0f8e60ff99',
+        'info_dict': {
+            'upload_date': '20130504',
+            'uploader': 'rachaneronas',
+            'title': 'Tired of Link Building? Try BacklinkMyDomain.com!',
         }
     }
 
     def _real_extract(self, url):
-        # Extract id from URL
         mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError(u'Invalid URL: %s' % url)
-
         video_id = mobj.group('id')
-
         video_extension = mobj.group('ext')
 
-        # Retrieve video webpage to extract further information
         webpage = self._download_webpage(url, video_id)
 
         # Extract URL, uploader, and title from webpage
         self.report_extraction(video_id)
-        # We try first by looking the javascript code:
-        mobj = re.search(r'Pb\.Data\.Shared\.put\(Pb\.Data\.Shared\.MEDIA, (?P<json>.*?)\);', webpage)
-        if mobj is not None:
-            info = json.loads(mobj.group('json'))
-            return [{
-                'id':       video_id,
-                'url':      info[u'downloadUrl'],
-                'uploader': info[u'username'],
-                'upload_date':  datetime.date.fromtimestamp(info[u'creationDate']).strftime('%Y%m%d'),
-                'title':    info[u'title'],
-                'ext':      video_extension,
-                'thumbnail': info[u'thumbUrl'],
-            }]
-
-        # We try looking in other parts of the webpage
-        video_url = self._search_regex(r'<link rel="video_src" href=".*\?file=([^"]+)" />',
-            webpage, u'video URL')
-
-        mobj = re.search(r'<title>(.*) video by (.*) - Photobucket</title>', webpage)
-        if mobj is None:
-            raise ExtractorError(u'Unable to extract title')
-        video_title = mobj.group(1).decode('utf-8')
-        video_uploader = mobj.group(2).decode('utf-8')
-
-        return [{
-            'id':       video_id.decode('utf-8'),
-            'url':      video_url.decode('utf-8'),
-            'uploader': video_uploader,
-            'upload_date':  None,
-            'title':    video_title,
-            'ext':      video_extension.decode('utf-8'),
-        }]
+        info_json = self._search_regex(r'Pb\.Data\.Shared\.put\(Pb\.Data\.Shared\.MEDIA, (.*?)\);',
+            webpage, 'info json')
+        info = json.loads(info_json)
+        return {
+            'id': video_id,
+            'url': info['downloadUrl'],
+            'uploader': info['username'],
+            'upload_date': datetime.date.fromtimestamp(info['creationDate']).strftime('%Y%m%d'),
+            'title': info['title'],
+            'ext': video_extension,
+            'thumbnail': info['thumbUrl'],
+        }

youtube_dl/extractor/playvid.py

@@ -0,0 +1,80 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_urllib_parse,
+)
+
+
+class PlayvidIE(InfoExtractor):
+    _VALID_URL = r'^https?://www\.playvid\.com/watch(\?v=|/)(?P<id>.+?)(?:#|$)'
+    _TEST = {
+        'url': 'http://www.playvid.com/watch/agbDDi7WZTV',
+        'md5': '44930f8afa616efdf9482daf4fe53e1e',
+        'info_dict': {
+            'id': 'agbDDi7WZTV',
+            'ext': 'mp4',
+            'title': 'Michelle Lewin in Miami Beach',
+            'duration': 240,
+            'age_limit': 18,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+
+        video_title = None
+        duration = None
+        video_thumbnail = None
+        formats = []
+
+        # most of the information is stored in the flashvars
+        flashvars = self._html_search_regex(
+            r'flashvars="(.+?)"', webpage, 'flashvars')
+
+        infos = compat_urllib_parse.unquote(flashvars).split(r'&')
+        for info in infos:
+            videovars_match = re.match(r'^video_vars\[(.+?)\]=(.+?)$', info)
+            if videovars_match:
+                key = videovars_match.group(1)
+                val = videovars_match.group(2)
+
+                if key == 'title':
+                    video_title = compat_urllib_parse.unquote_plus(val)
+                if key == 'duration':
+                    try:
+                        duration = int(val)
+                    except ValueError:
+                        pass
+                if key == 'big_thumb':
+                    video_thumbnail = val
+
+                videourl_match = re.match(
+                    r'^video_urls\]\[(?P<resolution>[0-9]+)p', key)
+                if videourl_match:
+                    height = int(videourl_match.group('resolution'))
+                    formats.append({
+                        'height': height,
+                        'url': val,
+                    })
+        self._sort_formats(formats)
+
+        # Extract title - should be in the flashvars; if not, look elsewhere
+        if video_title is None:
+            video_title = self._html_search_regex(
+                r'<title>(.*?)</title', webpage, 'title')
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            'title': video_title,
+            'thumbnail': video_thumbnail,
+            'duration': duration,
+            'description': None,
+            'age_limit': 18
+        }