release 2014.05.12

[FunnyOrDie] fix thumbnails + add test (fixes #2856)

MANIFEST.in

@@ -3,3 +3,4 @@ include test/*.py
 include test/*.json
 include youtube-dl.bash-completion
 include youtube-dl.1
+recursive-include docs Makefile conf.py *.rst

Makefile

@@ -72,8 +72,9 @@ youtube-dl.tar.gz: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-
 		--exclude '__pycache' \
 		--exclude '.git' \
 		--exclude 'testdata' \
+		--exclude 'docs/_build' \
 		-- \
-		bin devscripts test youtube_dl \
+		bin devscripts test youtube_dl docs \
 		CHANGELOG LICENSE README.md README.txt \
 		Makefile MANIFEST.in youtube-dl.1 youtube-dl.bash-completion setup.py \
 		youtube-dl

README.md

@@ -28,6 +28,9 @@ which means you can modify it, redistribute it or use it however you like.
     --user-agent UA                  specify a custom user agent
     --referer REF                    specify a custom referer, use if the video
                                      access is restricted to one domain
+    --add-header FIELD:VALUE         specify a custom HTTP header and its value,
+                                     separated by a colon ':'. You can use this
+                                     option multiple times
     --list-extractors                List all supported extractors and the URLs
                                      they would handle
     --extractor-descriptions         Output descriptions of all supported
@@ -62,6 +65,7 @@ which means you can modify it, redistribute it or use it however you like.
                                      configuration in ~/.config/youtube-dl.conf
                                      (%APPDATA%/youtube-dl/config.txt on
                                      Windows)
+    --encoding ENCODING              Force the specified encoding (experimental)
 
 ## Video Selection:
     --playlist-start NUMBER          playlist video to start at (default is 1)
@@ -166,6 +170,7 @@ which means you can modify it, redistribute it or use it however you like.
 
 ## Verbosity / Simulation Options:
     -q, --quiet                      activates quiet mode
+    --no-warnings                    Ignore warnings
     -s, --simulate                   do not download the video and do not write
                                      anything to disk
     --skip-download                  do not download the video
@@ -177,7 +182,9 @@ which means you can modify it, redistribute it or use it however you like.
     --get-duration                   simulate, quiet but print video length
     --get-filename                   simulate, quiet but print output filename
     --get-format                     simulate, quiet but print output format
-    -j, --dump-json                  simulate, quiet but print JSON information
+    -j, --dump-json                  simulate, quiet but print JSON information.
+                                     See --output for a description of available
+                                     keys.
     --newline                        output progress bar as new lines
     --no-progress                    do not print progress bar
     --console-title                  display progress in console titlebar
@@ -243,6 +250,7 @@ which means you can modify it, redistribute it or use it however you like.
                                      default
     --embed-subs                     embed subtitles in the video (only for mp4
                                      videos)
+    --embed-thumbnail                embed thumbnail in the audio as cover art
     --add-metadata                   write metadata to the video file
     --xattrs                         write metadata to the video file's xattrs
                                      (using dublin core and xdg standards)
@@ -364,7 +372,67 @@ 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 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/).
+If you want to add support for a new site, you can follow this quick list (assuming your service is called `yourextractor`):
+
+1. [Fork this repository](https://github.com/rg3/youtube-dl/fork)
+2. Check out the source code with `git clone git@github.com:YOUR_GITHUB_USERNAME/youtube-dl.git`
+3. Start a new git branch with `cd youtube-dl; git checkout -b yourextractor`
+4. Start with this simple template and save it to `youtube_dl/extractor/yourextractor.py`:
+
+        # coding: utf-8
+        from __future__ import unicode_literals
+
+        import re
+
+        from .common import InfoExtractor
+        
+        
+        class YourExtractorIE(InfoExtractor):
+            _VALID_URL = r'https?://(?:www\.)?yourextractor\.com/watch/(?P<id>[0-9]+)'
+            _TEST = {
+                'url': 'http://yourextractor.com/watch/42',
+                'md5': 'TODO: md5 sum of the first 10KiB of the video file',
+                'info_dict': {
+                    'id': '42',
+                    'ext': 'mp4',
+                    'title': 'Video title goes here',
+                    # TODO more properties, either as:
+                    # * A value
+                    # * MD5 checksum; start the string with md5:
+                    # * A regular expression; start the string with re:
+                    # * Any Python type (for example int or float)
+                }
+            }
+
+            def _real_extract(self, url):
+                mobj = re.match(self._VALID_URL, url)
+                video_id = mobj.group('id')
+
+                # TODO more code goes here, for example ...
+                webpage = self._download_webpage(url, video_id)
+                title = self._html_search_regex(r'<h1>(.*?)</h1>', webpage, 'title')
+
+                return {
+                    'id': video_id,
+                    'title': title,
+                    # TODO more properties (see youtube_dl/extractor/common.py)
+                }
+
+
+5. Add an import in [`youtube_dl/extractor/__init__.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/__init__.py).
+6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done.
+7. 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). Add tests and code for as many as you want.
+8. If you can, check the code with [pyflakes](https://pypi.python.org/pypi/pyflakes) (a good idea) and [pep8](https://pypi.python.org/pypi/pep8) (optional, ignore E501).
+9. When the tests pass, [add](https://www.kernel.org/pub/software/scm/git/docs/git-add.html) the new files and [commit](https://www.kernel.org/pub/software/scm/git/docs/git-commit.html) them and [push](https://www.kernel.org/pub/software/scm/git/docs/git-push.html) the result, like this:
+
+        $ git add youtube_dl/extractor/__init__.py
+        $ git add youtube_dl/extractor/yourextractor.py
+        $ git commit -m '[yourextractor] Add new extractor'
+        $ git push origin yourextractor
+
+10. Finally, [create a pull request](https://help.github.com/articles/creating-a-pull-request). We'll then review and merge it.
+
+In any case, thank you very much for your contributions!
 
 # BUGS
 

devscripts/release.sh

@@ -22,6 +22,12 @@ fi
 
 if [ -z "$1" ]; then echo "ERROR: specify version number like this: $0 1994.09.06"; exit 1; fi
 version="$1"
+major_version=$(echo "$version" | sed -n 's#^\([0-9]*\.[0-9]*\.[0-9]*\).*#\1#p')
+if test "$major_version" '!=' "$(date '+%Y.%m.%d')"; then
+    echo "$version does not start with today's date!"
+    exit 1
+fi
+
 if [ ! -z "`git tag | grep "$version"`" ]; then echo 'ERROR: version already present'; exit 1; fi
 if [ ! -z "`git status --porcelain | grep -v CHANGELOG`" ]; then echo 'ERROR: the working directory is not clean; commit or stash changes'; exit 1; fi
 useless_files=$(find youtube_dl -type f -not -name '*.py')

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
+

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):
@@ -71,15 +74,77 @@ class FakeYDL(YoutubeDL):
             old_report_warning(message)
         self.report_warning = types.MethodType(report_warning, self)
 
-def gettestcases():
+
+def gettestcases(include_onlymatching=False):
     for ie in youtube_dl.extractor.gen_extractors():
         t = getattr(ie, '_TEST', None)
         if t:
-            t['name'] = type(ie).__name__[:-len('IE')]
-            yield t
-        for t in getattr(ie, '_TESTS', []):
+            assert not hasattr(ie, '_TESTS'), \
+                '%s has _TEST and _TESTS' % type(ie).__name__
+            tests = [t]
+        else:
+            tests = getattr(ie, '_TESTS', [])
+        for t in tests:
+            if not include_onlymatching and t.get('only_matching', False):
+                continue
             t['name'] = type(ie).__name__[:-len('IE')]
             yield t
 
 
 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))))
+
+
+def assertRegexpMatches(self, text, regexp, msg=None):
+    if hasattr(self, 'assertRegexpMatches'):
+        return self.assertRegexpMatches(text, regexp, msg)
+    else:
+        m = re.match(regexp, text)
+        if not m:
+            note = 'Regexp didn\'t match: %r not found in %r' % (regexp, text)
+            if msg is None:
+                msg = note
+            else:
+                msg = note + ', ' + msg
+            self.assertTrue(m, msg)

test/test_YoutubeDL.py

@@ -8,7 +8,7 @@ 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 FakeYDL, assertRegexpMatches
 from youtube_dl import YoutubeDL
 from youtube_dl.extractor import YoutubeIE
 
@@ -26,16 +26,27 @@ class YDL(FakeYDL):
         self.msgs.append(msg)
 
 
+def _make_result(formats, **kwargs):
+    res = {
+        'formats': formats,
+        'id': 'testid',
+        'title': 'testttitle',
+        'extractor': 'testex',
+    }
+    res.update(**kwargs)
+    return res
+
+
 class TestFormatSelection(unittest.TestCase):
     def test_prefer_free_formats(self):
         # Same resolution => download webm
         ydl = YDL()
         ydl.params['prefer_free_formats'] = True
         formats = [
-            {'ext': 'webm', 'height': 460},
-            {'ext': 'mp4',  'height': 460},
+            {'ext': 'webm', 'height': 460, 'url': 'x'},
+            {'ext': 'mp4', 'height': 460, 'url': 'y'},
         ]
-        info_dict = {'formats': formats, 'extractor': 'test'}
+        info_dict = _make_result(formats)
         yie = YoutubeIE(ydl)
         yie._sort_formats(info_dict['formats'])
         ydl.process_ie_result(info_dict)
@@ -46,8 +57,8 @@ class TestFormatSelection(unittest.TestCase):
         ydl = YDL()
         ydl.params['prefer_free_formats'] = True
         formats = [
-            {'ext': 'webm', 'height': 720},
-            {'ext': 'mp4', 'height': 1080},
+            {'ext': 'webm', 'height': 720, 'url': 'a'},
+            {'ext': 'mp4', 'height': 1080, 'url': 'b'},
         ]
         info_dict['formats'] = formats
         yie = YoutubeIE(ydl)
@@ -60,9 +71,9 @@ class TestFormatSelection(unittest.TestCase):
         ydl = YDL()
         ydl.params['prefer_free_formats'] = False
         formats = [
-            {'ext': 'webm', 'height': 720},
-            {'ext': 'mp4', 'height': 720},
-            {'ext': 'flv', 'height': 720},
+            {'ext': 'webm', 'height': 720, 'url': '_'},
+            {'ext': 'mp4', 'height': 720, 'url': '_'},
+            {'ext': 'flv', 'height': 720, 'url': '_'},
         ]
         info_dict['formats'] = formats
         yie = YoutubeIE(ydl)
@@ -74,8 +85,8 @@ class TestFormatSelection(unittest.TestCase):
         ydl = YDL()
         ydl.params['prefer_free_formats'] = False
         formats = [
-            {'ext': 'flv', 'height': 720},
-            {'ext': 'webm', 'height': 720},
+            {'ext': 'flv', 'height': 720, 'url': '_'},
+            {'ext': 'webm', 'height': 720, 'url': '_'},
         ]
         info_dict['formats'] = formats
         yie = YoutubeIE(ydl)
@@ -91,8 +102,7 @@ class TestFormatSelection(unittest.TestCase):
             {'format_id': 'great', 'url': 'http://example.com/great', 'preference': 3},
             {'format_id': 'excellent', 'url': 'http://example.com/exc', 'preference': 4},
         ]
-        info_dict = {
-            'formats': formats, 'extractor': 'test', 'id': 'testvid'}
+        info_dict = _make_result(formats)
 
         ydl = YDL()
         ydl.process_ie_result(info_dict)
@@ -120,12 +130,12 @@ class TestFormatSelection(unittest.TestCase):
 
     def test_format_selection(self):
         formats = [
-            {'format_id': '35', 'ext': 'mp4', 'preference': 1},
-            {'format_id': '45', 'ext': 'webm', 'preference': 2},
-            {'format_id': '47', 'ext': 'webm', 'preference': 3},
-            {'format_id': '2', 'ext': 'flv', 'preference': 4},
+            {'format_id': '35', 'ext': 'mp4', 'preference': 1, 'url': '_'},
+            {'format_id': '45', 'ext': 'webm', 'preference': 2, 'url': '_'},
+            {'format_id': '47', 'ext': 'webm', 'preference': 3, 'url': '_'},
+            {'format_id': '2', 'ext': 'flv', 'preference': 4, 'url': '_'},
         ]
-        info_dict = {'formats': formats, 'extractor': 'test'}
+        info_dict = _make_result(formats)
 
         ydl = YDL({'format': '20/47'})
         ydl.process_ie_result(info_dict.copy())
@@ -154,12 +164,12 @@ class TestFormatSelection(unittest.TestCase):
 
     def test_format_selection_audio(self):
         formats = [
-            {'format_id': 'audio-low', 'ext': 'webm', 'preference': 1, 'vcodec': 'none'},
-            {'format_id': 'audio-mid', 'ext': 'webm', 'preference': 2, 'vcodec': 'none'},
-            {'format_id': 'audio-high', 'ext': 'flv', 'preference': 3, 'vcodec': 'none'},
-            {'format_id': 'vid', 'ext': 'mp4', 'preference': 4},
+            {'format_id': 'audio-low', 'ext': 'webm', 'preference': 1, 'vcodec': 'none', 'url': '_'},
+            {'format_id': 'audio-mid', 'ext': 'webm', 'preference': 2, 'vcodec': 'none', 'url': '_'},
+            {'format_id': 'audio-high', 'ext': 'flv', 'preference': 3, 'vcodec': 'none', 'url': '_'},
+            {'format_id': 'vid', 'ext': 'mp4', 'preference': 4, 'url': '_'},
         ]
-        info_dict = {'formats': formats, 'extractor': 'test'}
+        info_dict = _make_result(formats)
 
         ydl = YDL({'format': 'bestaudio'})
         ydl.process_ie_result(info_dict.copy())
@@ -172,10 +182,10 @@ class TestFormatSelection(unittest.TestCase):
         self.assertEqual(downloaded['format_id'], 'audio-low')
 
         formats = [
-            {'format_id': 'vid-low', 'ext': 'mp4', 'preference': 1},
-            {'format_id': 'vid-high', 'ext': 'mp4', 'preference': 2},
+            {'format_id': 'vid-low', 'ext': 'mp4', 'preference': 1, 'url': '_'},
+            {'format_id': 'vid-high', 'ext': 'mp4', 'preference': 2, 'url': '_'},
         ]
-        info_dict = {'formats': formats, 'extractor': 'test'}
+        info_dict = _make_result(formats)
 
         ydl = YDL({'format': 'bestaudio/worstaudio/best'})
         ydl.process_ie_result(info_dict.copy())
@@ -184,11 +194,11 @@ class TestFormatSelection(unittest.TestCase):
 
     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},
+            {'format_id': 'dash-video-low', 'ext': 'mp4', 'preference': 1, 'acodec': 'none', 'url': '_'},
+            {'format_id': 'dash-video-high', 'ext': 'mp4', 'preference': 2, 'acodec': 'none', 'url': '_'},
+            {'format_id': 'vid', 'ext': 'mp4', 'preference': 3, 'url': '_'},
         ]
-        info_dict = {'formats': formats, 'extractor': 'test'}
+        info_dict = _make_result(formats)
 
         ydl = YDL({'format': 'bestvideo'})
         ydl.process_ie_result(info_dict.copy())
@@ -217,10 +227,12 @@ class TestFormatSelection(unittest.TestCase):
         for f1id, f2id in zip(order, order[1:]):
             f1 = YoutubeIE._formats[f1id].copy()
             f1['format_id'] = f1id
+            f1['url'] = 'url:' + f1id
             f2 = YoutubeIE._formats[f2id].copy()
             f2['format_id'] = f2id
+            f2['url'] = 'url:' + f2id
 
-            info_dict = {'formats': [f1, f2], 'extractor': 'youtube'}
+            info_dict = _make_result([f1, f2], extractor='youtube')
             ydl = YDL()
             yie = YoutubeIE(ydl)
             yie._sort_formats(info_dict['formats'])
@@ -228,7 +240,7 @@ class TestFormatSelection(unittest.TestCase):
             downloaded = ydl.downloaded_info_dicts[0]
             self.assertEqual(downloaded['format_id'], f1id)
 
-            info_dict = {'formats': [f2, f1], 'extractor': 'youtube'}
+            info_dict = _make_result([f2, f1], extractor='youtube')
             ydl = YDL()
             yie = YoutubeIE(ydl)
             yie._sort_formats(info_dict['formats'])
@@ -262,6 +274,12 @@ class TestFormatSelection(unittest.TestCase):
         # Replace missing fields with 'NA'
         self.assertEqual(fname('%(uploader_date)s-%(id)s.%(ext)s'), 'NA-1234.mp4')
 
+    def test_format_note(self):
+        ydl = YoutubeDL()
+        self.assertEqual(ydl._format_note({}), '')
+        assertRegexpMatches(self, ydl._format_note({
+            'vbr': 10,
+        }), '^x\s*10k$')
 
 if __name__ == '__main__':
     unittest.main()

test/test_all_urls.py

@@ -49,6 +49,7 @@ class TestAllURLsMatching(unittest.TestCase):
         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'])
+        self.assertMatch('http://www.cleanvideosearch.com/media/action/yt/watch?videoId=8v_4O44sfjM', ['youtube'])
 
     def test_youtube_channel_matching(self):
         assertChannel = lambda url: self.assertMatch(url, ['youtube:channel'])
@@ -76,20 +77,20 @@ class TestAllURLsMatching(unittest.TestCase):
         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"))
-        self.assertTrue(JustinTVIE.suitable(u"www.justin.tv/vanillatv"))
-        self.assertTrue(JustinTVIE.suitable(u"www.twitch.tv/vanillatv"))
-        self.assertTrue(JustinTVIE.suitable(u"http://www.justin.tv/vanillatv"))
-        self.assertTrue(JustinTVIE.suitable(u"http://www.twitch.tv/vanillatv"))
-        self.assertTrue(JustinTVIE.suitable(u"http://www.justin.tv/vanillatv/"))
-        self.assertTrue(JustinTVIE.suitable(u"http://www.twitch.tv/vanillatv/"))
+        self.assertTrue(JustinTVIE.suitable('justin.tv/vanillatv'))
+        self.assertTrue(JustinTVIE.suitable('twitch.tv/vanillatv'))
+        self.assertTrue(JustinTVIE.suitable('www.justin.tv/vanillatv'))
+        self.assertTrue(JustinTVIE.suitable('www.twitch.tv/vanillatv'))
+        self.assertTrue(JustinTVIE.suitable('http://www.justin.tv/vanillatv'))
+        self.assertTrue(JustinTVIE.suitable('http://www.twitch.tv/vanillatv'))
+        self.assertTrue(JustinTVIE.suitable('http://www.justin.tv/vanillatv/'))
+        self.assertTrue(JustinTVIE.suitable('http://www.twitch.tv/vanillatv/'))
 
     def test_justintv_videoid_matching(self):
-        self.assertTrue(JustinTVIE.suitable(u"http://www.twitch.tv/vanillatv/b/328087483"))
+        self.assertTrue(JustinTVIE.suitable('http://www.twitch.tv/vanillatv/b/328087483'))
 
     def test_justin_tv_chapterid_matching(self):
-        self.assertTrue(JustinTVIE.suitable(u"http://www.twitch.tv/tsm_theoddone/c/2349361"))
+        self.assertTrue(JustinTVIE.suitable('http://www.twitch.tv/tsm_theoddone/c/2349361'))
 
     def test_youtube_extract(self):
         assertExtractId = lambda url, id: self.assertEqual(YoutubeIE.extract_id(url), id)
@@ -105,7 +106,7 @@ class TestAllURLsMatching(unittest.TestCase):
 
     def test_no_duplicates(self):
         ies = gen_extractors()
-        for tc in gettestcases():
+        for tc in gettestcases(include_onlymatching=True):
             url = tc['url']
             for ie in ies:
                 if type(ie).__name__ in ('GenericIE', tc['name'] + 'IE'):
@@ -143,5 +144,38 @@ class TestAllURLsMatching(unittest.TestCase):
         self.assertMatch('http://video.pbs.org/viralplayer/2365173446/', ['PBS'])
         self.assertMatch('http://video.pbs.org/widget/partnerplayer/980042464/', ['PBS'])
 
+    def test_ComedyCentralShows(self):
+        self.assertMatch(
+            'http://thedailyshow.cc.com/extended-interviews/xm3fnq/andrew-napolitano-extended-interview',
+            ['ComedyCentralShows'])
+        self.assertMatch(
+            'http://thecolbertreport.cc.com/videos/29w6fx/-realhumanpraise-for-fox-news',
+            ['ComedyCentralShows'])
+        self.assertMatch(
+            'http://thecolbertreport.cc.com/videos/gh6urb/neil-degrasse-tyson-pt--1?xrs=eml_col_031114',
+            ['ComedyCentralShows'])
+        self.assertMatch(
+            'http://thedailyshow.cc.com/guests/michael-lewis/3efna8/exclusive---michael-lewis-extended-interview-pt--3',
+            ['ComedyCentralShows'])
+        self.assertMatch(
+            'http://thedailyshow.cc.com/episodes/sy7yv0/april-8--2014---denis-leary',
+            ['ComedyCentralShows'])
+        self.assertMatch(
+            'http://thecolbertreport.cc.com/episodes/8ase07/april-8--2014---jane-goodall',
+            ['ComedyCentralShows'])
+        self.assertMatch(
+            'http://thedailyshow.cc.com/video-playlists/npde3s/the-daily-show-19088-highlights',
+            ['ComedyCentralShows'])
+        self.assertMatch(
+            'http://thedailyshow.cc.com/special-editions/2l8fdb/special-edition---a-look-back-at-food',
+            ['ComedyCentralShows'])
+
+    def test_yahoo_https(self):
+        # https://github.com/rg3/youtube-dl/issues/2701
+        self.assertMatch(
+            'https://screen.yahoo.com/smartwatches-latest-wearable-gadgets-163745379-cbs.html',
+            ['Yahoo'])
+
+
 if __name__ == '__main__':
     unittest.main()

test/test_download.py

@@ -9,16 +9,16 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 from test.helper import (
     get_params,
     gettestcases,
-    try_rm,
+    expect_info_dict,
     md5,
-    report_warning
+    try_rm,
+    report_warning,
 )
 
 
 import hashlib
 import io
 import json
-import re
 import socket
 
 import youtube_dl.YoutubeDL
@@ -135,40 +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('re:'):
-                        got = info_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 = info_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(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))
-
-                # 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)
-
-                # 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', 'timestamp', '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')
+                expect_info_dict(self, tc.get('info_dict', {}), info_dict)
         finally:
             try_rm_tcs_files()
 

test/test_playlists.py

@@ -9,8 +9,11 @@ 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 (
+    assertRegexpMatches,
+    expect_info_dict,
+    FakeYDL,
+)
 
 from youtube_dl.extractor import (
     AcademicEarthCourseIE,
@@ -23,6 +26,7 @@ from youtube_dl.extractor import (
     UstreamChannelIE,
     SoundcloudSetIE,
     SoundcloudUserIE,
+    SoundcloudPlaylistIE,
     LivestreamIE,
     NHLVideocenterIE,
     BambuserChannelIE,
@@ -37,6 +41,11 @@ from youtube_dl.extractor import (
     GoogleSearchIE,
     GenericIE,
     TEDIE,
+    ToypicsUserIE,
+    XTubeUserIE,
+    InstagramUserIE,
+    CSpanIE,
+    AolIE,
 )
 
 
@@ -117,6 +126,17 @@ class TestPlaylists(unittest.TestCase):
         self.assertEqual(result['id'], '9615865')
         self.assertTrue(len(result['entries']) >= 12)
 
+    def test_soundcloud_playlist(self):
+        dl = FakeYDL()
+        ie = SoundcloudPlaylistIE(dl)
+        result = ie.extract('http://api.soundcloud.com/playlists/4110309')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], '4110309')
+        self.assertEqual(result['title'], 'TILT Brass - Bowery Poetry Club, August \'03 [Non-Site SCR 02]')
+        assertRegexpMatches(
+            self, result['description'], r'TILT Brass - Bowery Poetry Club')
+        self.assertEqual(len(result['entries']), 6)
+
     def test_livestream_event(self):
         dl = FakeYDL()
         ie = LivestreamIE(dl)
@@ -185,8 +205,8 @@ class TestPlaylists(unittest.TestCase):
         self.assertIsPlaylist(result)
         self.assertEqual(result['id'], 'dezhurnyi_angel')
         self.assertEqual(result['title'], 'Дежурный ангел (2010 - 2012)')
-        self.assertTrue(len(result['entries']) >= 36)
-        
+        self.assertTrue(len(result['entries']) >= 23)
+
     def test_ivi_compilation_season(self):
         dl = FakeYDL()
         ie = IviCompilationIE(dl)
@@ -194,7 +214,7 @@ class TestPlaylists(unittest.TestCase):
         self.assertIsPlaylist(result)
         self.assertEqual(result['id'], 'dezhurnyi_angel/season2')
         self.assertEqual(result['title'], 'Дежурный ангел (2010 - 2012) 2 сезон')
-        self.assertTrue(len(result['entries']) >= 20)
+        self.assertTrue(len(result['entries']) >= 7)
         
     def test_imdb_list(self):
         dl = FakeYDL()
@@ -269,5 +289,68 @@ class TestPlaylists(unittest.TestCase):
         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)
+
+    def test_CSpan_playlist(self):
+        dl = FakeYDL()
+        ie = CSpanIE(dl)
+        result = ie.extract(
+            'http://www.c-span.org/video/?318608-1/gm-ignition-switch-recall')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], '342759')
+        self.assertEqual(
+            result['title'], 'General Motors Ignition Switch Recall')
+        whole_duration = sum(e['duration'] for e in result['entries'])
+        self.assertEqual(whole_duration, 14855)
+
+    def test_aol_playlist(self):
+        dl = FakeYDL()
+        ie = AolIE(dl)
+        result = ie.extract(
+            'http://on.aol.com/playlist/brace-yourself---todays-weirdest-news-152147?icid=OnHomepageC4_Omg_Img#_videoid=518184316')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], '152147')
+        self.assertEqual(
+            result['title'], 'Brace Yourself - Today\'s Weirdest News')
+        self.assertTrue(len(result['entries']) >= 10)
+
 if __name__ == '__main__':
     unittest.main()

test/test_subtitles.py

@@ -181,7 +181,7 @@ class TestTedSubtitles(BaseTestSubtitles):
         self.DL.params['writesubtitles'] = True
         self.DL.params['allsubtitles'] = True
         subtitles = self.getSubtitles()
-        self.assertEqual(len(subtitles.keys()), 28)
+        self.assertTrue(len(subtitles.keys()) >= 28)
 
     def test_list_subtitles(self):
         self.DL.expect_warning(u'Automatic Captions not supported by this server')

test/test_utils.py

@@ -10,6 +10,7 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 # Various small unit tests
 import io
+import json
 import xml.etree.ElementTree
 
 #from youtube_dl.utils import htmlentity_transform
@@ -35,6 +36,9 @@ from youtube_dl.utils import (
     url_basename,
     urlencode_postdata,
     xpath_with_ns,
+    parse_iso8601,
+    strip_jsonp,
+    uppercase_escape,
 )
 
 if sys.version_info < (3, 0):
@@ -266,5 +270,19 @@ class TestUtil(unittest.TestCase):
         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)
+
+    def test_strip_jsonp(self):
+        stripped = strip_jsonp('cb ([ {"id":"532cb",\n\n\n"x":\n3}\n]\n);')
+        d = json.loads(stripped)
+        self.assertEqual(d, [{"id": "532cb", "x": 3}])
+
+    def test_uppercase_escpae(self):
+        self.assertEqual(uppercase_escape(u'aä'), u'aä')
+        self.assertEqual(uppercase_escape(u'\\U0001d550'), u'𝕐')
+
 if __name__ == '__main__':
     unittest.main()

youtube_dl/YoutubeDL.py

@@ -8,6 +8,7 @@ import datetime
 import errno
 import io
 import json
+import locale
 import os
 import platform
 import re
@@ -30,6 +31,7 @@ from .utils import (
     ContentTooShortError,
     date_from_str,
     DateRange,
+    DEFAULT_OUTTMPL,
     determine_ext,
     DownloadError,
     encodeFilename,
@@ -94,6 +96,7 @@ class YoutubeDL(object):
     usenetrc:          Use netrc for authentication instead.
     verbose:           Print additional info to stdout.
     quiet:             Do not print messages to stdout.
+    no_warnings:       Do not print out anything for warnings.
     forceurl:          Force printing final URL.
     forcetitle:        Force printing title.
     forceid:           Force printing ID.
@@ -158,6 +161,7 @@ class YoutubeDL(object):
     include_ads:       Download ads as well
     default_search:    Prepend this string if an input url is not valid.
                        'auto' for elaborate guessing
+    encoding:          Use this encoding instead of the system-specified.
 
     The following parameters are not used by YoutubeDL itself, they are used by
     the FileDownloader:
@@ -283,6 +287,9 @@ class YoutubeDL(object):
         """Print message to stdout if not in quiet mode."""
         return self.to_stdout(message, skip_eol, check_quiet=True)
 
+    def _write_string(self, s, out=None):
+        write_string(s, out=out, encoding=self.params.get('encoding'))
+
     def to_stdout(self, message, skip_eol=False, check_quiet=False):
         """Print message to stdout if not in quiet mode."""
         if self.params.get('logger'):
@@ -292,7 +299,7 @@ class YoutubeDL(object):
             terminator = ['\n', ''][skip_eol]
             output = message + terminator
 
-            write_string(output, self._screen_file)
+            self._write_string(output, self._screen_file)
 
     def to_stderr(self, message):
         """Print message to stderr."""
@@ -302,7 +309,7 @@ class YoutubeDL(object):
         else:
             message = self._bidi_workaround(message)
             output = message + '\n'
-            write_string(output, self._err_file)
+            self._write_string(output, self._err_file)
 
     def to_console_title(self, message):
         if not self.params.get('consoletitle', False):
@@ -312,21 +319,21 @@ class YoutubeDL(object):
             # already of type unicode()
             ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message))
         elif 'TERM' in os.environ:
-            write_string('\033]0;%s\007' % message, self._screen_file)
+            self._write_string('\033]0;%s\007' % message, self._screen_file)
 
     def save_console_title(self):
         if not self.params.get('consoletitle', False):
             return
         if 'TERM' in os.environ:
             # Save the title on stack
-            write_string('\033[22;0t', self._screen_file)
+            self._write_string('\033[22;0t', self._screen_file)
 
     def restore_console_title(self):
         if not self.params.get('consoletitle', False):
             return
         if 'TERM' in os.environ:
             # Restore the title from stack
-            write_string('\033[23;0t', self._screen_file)
+            self._write_string('\033[23;0t', self._screen_file)
 
     def __enter__(self):
         self.save_console_title()
@@ -376,6 +383,8 @@ class YoutubeDL(object):
         if self.params.get('logger') is not None:
             self.params['logger'].warning(message)
         else:
+            if self.params.get('no_warnings'):
+                return
             if self._err_file.isatty() and os.name != 'nt':
                 _msg_header = '\033[0;33mWARNING:\033[0m'
             else:
@@ -432,7 +441,8 @@ class YoutubeDL(object):
                                  if v is not None)
             template_dict = collections.defaultdict(lambda: 'NA', template_dict)
 
-            tmpl = os.path.expanduser(self.params['outtmpl'])
+            outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL)
+            tmpl = os.path.expanduser(outtmpl)
             filename = tmpl % template_dict
             return filename
         except ValueError as err:
@@ -512,13 +522,7 @@ 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:
@@ -537,6 +541,14 @@ class YoutubeDL(object):
         else:
             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={}):
         """
         Take the result of the ie(may be modified) and resolve all unresolved
@@ -695,6 +707,11 @@ class YoutubeDL(object):
     def process_video_result(self, info_dict, download=True):
         assert info_dict.get('_type', 'video') == 'video'
 
+        if 'id' not in info_dict:
+            raise ExtractorError('Missing "id" field in extractor result')
+        if 'title' not in info_dict:
+            raise ExtractorError('Missing "title" field in extractor result')
+
         if 'playlist' not in info_dict:
             # It isn't part of a playlist
             info_dict['playlist'] = None
@@ -726,6 +743,9 @@ class YoutubeDL(object):
 
         # We check that all the formats have the format and format_id fields
         for i, format in enumerate(formats):
+            if 'url' not in format:
+                raise ExtractorError('Missing "url" key in result (index %d)' % i)
+
             if format.get('format_id') is None:
                 format['format_id'] = compat_str(i)
             if format.get('format') is None:
@@ -736,7 +756,7 @@ class YoutubeDL(object):
                 )
             # Automatically determine file extension if missing
             if 'ext' not in format:
-                format['ext'] = determine_ext(format['url'])
+                format['ext'] = determine_ext(format['url']).lower()
 
         format_limit = self.params.get('format_limit', None)
         if format_limit:
@@ -861,7 +881,7 @@ class YoutubeDL(object):
 
         try:
             dn = os.path.dirname(encodeFilename(filename))
-            if dn != '' and not os.path.exists(dn):
+            if dn and not os.path.exists(dn):
                 os.makedirs(dn)
         except (OSError, IOError) as err:
             self.report_error('unable to create directory ' + compat_str(err))
@@ -918,7 +938,7 @@ class YoutubeDL(object):
                         with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8') as subfile:
                                 subfile.write(sub)
                 except (OSError, IOError):
-                    self.report_error('Cannot write subtitles file ' + descfn)
+                    self.report_error('Cannot write subtitles file ' + sub_filename)
                     return
 
         if self.params.get('writeinfojson', False):
@@ -1007,10 +1027,11 @@ class YoutubeDL(object):
 
     def download(self, url_list):
         """Download a given list of URLs."""
+        outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL)
         if (len(url_list) > 1 and
-                '%' not in self.params['outtmpl']
+                '%' not in outtmpl
                 and self.params.get('max_downloads') != 1):
-            raise SameFileError(self.params['outtmpl'])
+            raise SameFileError(outtmpl)
 
         for url in url_list:
             try:
@@ -1121,57 +1142,57 @@ class YoutubeDL(object):
             res = default
         return res
 
-    def list_formats(self, info_dict):
-        def format_note(fdict):
-            res = ''
-            if fdict.get('ext') in ['f4f', 'f4m']:
-                res += '(unsupported) '
-            if fdict.get('format_note') is not None:
-                res += fdict['format_note'] + ' '
-            if fdict.get('tbr') is not None:
-                res += '%4dk ' % fdict['tbr']
-            if fdict.get('container') is not None:
-                if res:
-                    res += ', '
-                res += '%s container' % fdict['container']
-            if (fdict.get('vcodec') is not None and
-                    fdict.get('vcodec') != 'none'):
-                if res:
-                    res += ', '
-                res += fdict['vcodec']
-                if fdict.get('vbr') is not None:
-                    res += '@'
-            elif fdict.get('vbr') is not None and fdict.get('abr') is not None:
-                res += 'video@'
+    def _format_note(self, fdict):
+        res = ''
+        if fdict.get('ext') in ['f4f', 'f4m']:
+            res += '(unsupported) '
+        if fdict.get('format_note') is not None:
+            res += fdict['format_note'] + ' '
+        if fdict.get('tbr') is not None:
+            res += '%4dk ' % fdict['tbr']
+        if fdict.get('container') is not None:
+            if res:
+                res += ', '
+            res += '%s container' % fdict['container']
+        if (fdict.get('vcodec') is not None and
+                fdict.get('vcodec') != 'none'):
+            if res:
+                res += ', '
+            res += fdict['vcodec']
             if fdict.get('vbr') is not None:
-                res += '%4dk' % fdict['vbr']
-            if fdict.get('acodec') is not None:
-                if res:
-                    res += ', '
-                if fdict['acodec'] == 'none':
-                    res += 'video only'
-                else:
-                    res += '%-5s' % fdict['acodec']
-            elif fdict.get('abr') is not None:
-                if res:
-                    res += ', '
-                res += 'audio'
-            if fdict.get('abr') is not None:
-                res += '@%3dk' % fdict['abr']
-            if fdict.get('asr') is not None:
-                res += ' (%5dHz)' % fdict['asr']
-            if fdict.get('filesize') is not None:
-                if res:
-                    res += ', '
-                res += format_bytes(fdict['filesize'])
-            return res
+                res += '@'
+        elif fdict.get('vbr') is not None and fdict.get('abr') is not None:
+            res += 'video@'
+        if fdict.get('vbr') is not None:
+            res += '%4dk' % fdict['vbr']
+        if fdict.get('acodec') is not None:
+            if res:
+                res += ', '
+            if fdict['acodec'] == 'none':
+                res += 'video only'
+            else:
+                res += '%-5s' % fdict['acodec']
+        elif fdict.get('abr') is not None:
+            if res:
+                res += ', '
+            res += 'audio'
+        if fdict.get('abr') is not None:
+            res += '@%3dk' % fdict['abr']
+        if fdict.get('asr') is not None:
+            res += ' (%5dHz)' % fdict['asr']
+        if fdict.get('filesize') is not None:
+            if res:
+                res += ', '
+            res += format_bytes(fdict['filesize'])
+        return res
 
+    def list_formats(self, info_dict):
         def line(format, idlen=20):
             return (('%-' + compat_str(idlen + 1) + 's%-10s%-12s%s') % (
                 format['format_id'],
                 format['ext'],
                 self.format_resolution(format),
-                format_note(format),
+                self._format_note(format),
             ))
 
         formats = info_dict.get('formats', [info_dict])
@@ -1179,8 +1200,8 @@ class YoutubeDL(object):
                     max(len(f['format_id']) for f in formats))
         formats_s = [line(f, idlen) for f in formats]
         if len(formats) > 1:
-            formats_s[0] += (' ' if format_note(formats[0]) else '') + '(worst)'
-            formats_s[-1] += (' ' if format_note(formats[-1]) else '') + '(best)'
+            formats_s[0] += (' ' if self._format_note(formats[0]) else '') + '(worst)'
+            formats_s[-1] += (' ' if self._format_note(formats[-1]) else '') + '(best)'
 
         header_line = line({
             'format_id': 'format code', 'ext': 'extension',
@@ -1195,7 +1216,17 @@ class YoutubeDL(object):
     def print_debug_header(self):
         if not self.params.get('verbose'):
             return
-        write_string('[debug] youtube-dl version ' + __version__ + '\n')
+
+        write_string(
+            '[debug] Encodings: locale %s, fs %s, out %s, pref %s\n' % (
+                locale.getpreferredencoding(),
+                sys.getfilesystemencoding(),
+                sys.stdout.encoding,
+                self.get_encoding()),
+            encoding=None
+        )
+
+        self._write_string('[debug] youtube-dl version ' + __version__ + '\n')
         try:
             sp = subprocess.Popen(
                 ['git', 'rev-parse', '--short', 'HEAD'],
@@ -1204,20 +1235,20 @@ class YoutubeDL(object):
             out, err = sp.communicate()
             out = out.decode().strip()
             if re.match('[0-9a-f]+', out):
-                write_string('[debug] Git HEAD: ' + out + '\n')
+                self._write_string('[debug] Git HEAD: ' + out + '\n')
         except:
             try:
                 sys.exc_clear()
             except:
                 pass
-        write_string('[debug] Python version %s - %s' %
+        self._write_string('[debug] Python version %s - %s' %
                      (platform.python_version(), platform_name()) + '\n')
 
         proxy_map = {}
         for handler in self._opener.handlers:
             if hasattr(handler, 'proxies'):
                 proxy_map.update(handler.proxies)
-        write_string('[debug] Proxy map: ' + compat_str(proxy_map) + '\n')
+        self._write_string('[debug] Proxy map: ' + compat_str(proxy_map) + '\n')
 
     def _setup_opener(self):
         timeout_val = self.params.get('socket_timeout')
@@ -1259,3 +1290,19 @@ class YoutubeDL(object):
         # (See https://github.com/rg3/youtube-dl/issues/1309 for details)
         opener.addheaders = []
         self._opener = opener
+
+    def encode(self, s):
+        if isinstance(s, bytes):
+            return s  # Already encoded
+
+        try:
+            return s.encode(self.get_encoding())
+        except UnicodeEncodeError as err:
+            err.reason = err.reason + '. Check your system encoding configuration or use the --encoding option.'
+            raise
+
+    def get_encoding(self):
+        encoding = self.params.get('encoding')
+        if encoding is None:
+            encoding = preferredencoding()
+        return encoding

youtube_dl/__init__.py

@@ -51,6 +51,9 @@ __authors__  = (
     'David Wagner',
     'Juan C. Olivares',
     'Mattias Harrysson',
+    'phaer',
+    'Sainyam Kapoor',
+    'Nicolas Évrard',
 )
 
 __license__ = 'Public Domain'
@@ -70,6 +73,7 @@ from .utils import (
     compat_getpass,
     compat_print,
     DateRange,
+    DEFAULT_OUTTMPL,
     decodeOption,
     get_term_width,
     DownloadError,
@@ -90,6 +94,8 @@ from .extractor import gen_extractors
 from .version import __version__
 from .YoutubeDL import YoutubeDL
 from .postprocessor import (
+    AtomicParsleyPP,
+    FFmpegAudioFixPP,
     FFmpegMetadataPP,
     FFmpegVideoConvertor,
     FFmpegExtractAudioPP,
@@ -227,6 +233,9 @@ def parseOpts(overrideArguments=None):
     general.add_option('--referer',
             dest='referer', help='specify a custom referer, use if the video access is restricted to one domain',
             metavar='REF', default=None)
+    general.add_option('--add-header',
+            dest='headers', help='specify a custom HTTP header and its value, separated by a colon \':\'. You can use this option multiple times', action="append",
+            metavar='FIELD:VALUE')
     general.add_option('--list-extractors',
             action='store_true', dest='list_extractors',
             help='List all supported extractors and the URLs they would handle', default=False)
@@ -238,7 +247,7 @@ def parseOpts(overrideArguments=None):
         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',
+        '--prefer-insecure', '--prefer-unsecure', 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',
@@ -252,13 +261,17 @@ def parseOpts(overrideArguments=None):
     general.add_option(
         '--bidi-workaround', dest='bidi_workaround', action='store_true',
         help=u'Work around terminals that lack bidirectional text support. Requires bidiv or fribidi executable in PATH')
-    general.add_option('--default-search',
-            dest='default_search', metavar='PREFIX',
-            help='Use this prefix for unqualified URLs. For example "gvsearch2:" downloads two videos from google videos for  youtube-dl "large apple". By default (with value "auto") youtube-dl guesses.')
+    general.add_option(
+        '--default-search',
+        dest='default_search', metavar='PREFIX',
+        help='Use this prefix for unqualified URLs. For example "gvsearch2:" downloads two videos from google videos for  youtube-dl "large apple". By default (with value "auto") youtube-dl guesses.')
     general.add_option(
         '--ignore-config',
         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)')
+    general.add_option(
+        '--encoding', dest='encoding', metavar='ENCODING',
+        help='Force the specified encoding (experimental)')
 
     selection.add_option(
         '--playlist-start',
@@ -361,6 +374,10 @@ def parseOpts(overrideArguments=None):
 
     verbosity.add_option('-q', '--quiet',
             action='store_true', dest='quiet', help='activates quiet mode', default=False)
+    verbosity.add_option(
+        '--no-warnings',
+        dest='no_warnings', action='store_true', default=False,
+        help='Ignore warnings')
     verbosity.add_option('-s', '--simulate',
             action='store_true', dest='simulate', help='do not download the video and do not write anything to disk', default=False)
     verbosity.add_option('--skip-download',
@@ -388,7 +405,7 @@ def parseOpts(overrideArguments=None):
             help='simulate, quiet but print output format', default=False)
     verbosity.add_option('-j', '--dump-json',
             action='store_true', dest='dumpjson',
-            help='simulate, quiet but print JSON information', default=False)
+            help='simulate, quiet but print JSON information. See --output for a description of available keys.', default=False)
     verbosity.add_option('--newline',
             action='store_true', dest='progress_with_newline', help='output progress bar as new lines', default=False)
     verbosity.add_option('--no-progress',
@@ -490,6 +507,8 @@ def parseOpts(overrideArguments=None):
             help='do not overwrite post-processed files; the post-processed files are overwritten by default')
     postproc.add_option('--embed-subs', action='store_true', dest='embedsubtitles', default=False,
             help='embed subtitles in the video (only for mp4 videos)')
+    postproc.add_option('--embed-thumbnail', action='store_true', dest='embedthumbnail', default=False,
+            help='embed thumbnail in the audio as cover art')
     postproc.add_option('--add-metadata', action='store_true', dest='addmetadata', default=False,
             help='write metadata to the video file')
     postproc.add_option('--xattrs', action='store_true', dest='xattrs', default=False,
@@ -532,8 +551,6 @@ def parseOpts(overrideArguments=None):
             write_string(u'[debug] System config: ' + repr(_hide_login_info(systemConf)) + '\n')
             write_string(u'[debug] User config: ' + repr(_hide_login_info(userConf)) + '\n')
             write_string(u'[debug] Command-line args: ' + repr(_hide_login_info(commandLineConf)) + '\n')
-            write_string(u'[debug] Encodings: locale %r, fs %r, out %r, pref: %r\n' %
-                         (locale.getpreferredencoding(), sys.getfilesystemencoding(), sys.stdout.encoding, preferredencoding()))
 
     return parser, opts, args
 
@@ -556,6 +573,16 @@ def _real_main(argv=None):
     if opts.referer is not None:
         std_headers['Referer'] = opts.referer
 
+    # Custom HTTP headers
+    if opts.headers is not None:
+        for h in opts.headers:
+            if h.find(':', 1) < 0:
+                parser.error(u'wrong header formatting, it should be key:value, not "%s"'%h)
+            key, value = h.split(':', 2)
+            if opts.verbose:
+                write_string(u'[debug] Adding header from command line option %s:%s\n'%(key, value))
+            std_headers[key] = value
+
     # Dump user agent
     if opts.dump_user_agent:
         compat_print(std_headers['User-Agent'])
@@ -651,13 +678,13 @@ def _real_main(argv=None):
         if not opts.audioquality.isdigit():
             parser.error(u'invalid audio quality specified')
     if opts.recodevideo is not None:
-        if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg']:
+        if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv']:
             parser.error(u'invalid video recode format specified')
     if opts.date is not None:
         date = DateRange.day(opts.date)
     else:
         date = DateRange(opts.dateafter, opts.datebefore)
-    if opts.default_search not in ('auto', None) and ':' not in opts.default_search:
+    if opts.default_search not in ('auto', 'auto_warning', None) and ':' not in opts.default_search:
         parser.error(u'--default-search invalid; did you forget a colon (:) at the end?')
 
     # Do not download videos when there are audio-only formats
@@ -680,7 +707,7 @@ def _real_main(argv=None):
             or (opts.usetitle and u'%(title)s-%(id)s.%(ext)s')
             or (opts.useid and u'%(id)s.%(ext)s')
             or (opts.autonumber and u'%(autonumber)s-%(id)s.%(ext)s')
-            or u'%(title)s-%(id)s.%(ext)s')
+            or DEFAULT_OUTTMPL)
     if not os.path.splitext(outtmpl)[1] and opts.extractaudio:
         parser.error(u'Cannot download a video and extract audio into the same'
                      u' file! Use "{0}.%(ext)s" instead of "{0}" as the output'
@@ -695,6 +722,7 @@ def _real_main(argv=None):
         'password': opts.password,
         'videopassword': opts.videopassword,
         'quiet': (opts.quiet or any_printing),
+        'no_warnings': opts.no_warnings,
         'forceurl': opts.geturl,
         'forcetitle': opts.gettitle,
         'forceid': opts.getid,
@@ -767,6 +795,7 @@ def _real_main(argv=None):
         'include_ads': opts.include_ads,
         'default_search': opts.default_search,
         'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
+        'encoding': opts.encoding,
     }
 
     with YoutubeDL(ydl_opts) as ydl:
@@ -785,6 +814,10 @@ def _real_main(argv=None):
             ydl.add_post_processor(FFmpegEmbedSubtitlePP(subtitlesformat=opts.subtitlesformat))
         if opts.xattrs:
             ydl.add_post_processor(XAttrMetadataPP())
+        if opts.embedthumbnail:
+            if not opts.addmetadata:
+                ydl.add_post_processor(FFmpegAudioFixPP())
+            ydl.add_post_processor(AtomicParsleyPP())
 
         # Update version
         if opts.update_self:

youtube_dl/downloader/common.py

@@ -4,9 +4,10 @@ import sys
 import time
 
 from ..utils import (
+    compat_str,
     encodeFilename,
-    timeconvert,
     format_bytes,
+    timeconvert,
 )
 
 
@@ -173,7 +174,7 @@ class FileDownloader(object):
                 return
             os.rename(encodeFilename(old_filename), encodeFilename(new_filename))
         except (IOError, OSError) as err:
-            self.report_error(u'unable to rename file: %s' % str(err))
+            self.report_error(u'unable to rename file: %s' % compat_str(err))
 
     def try_utime(self, filename, last_modified_hdr):
         """Try to set the last-modified time of the given file."""

youtube_dl/downloader/f4m.py

@@ -297,6 +297,7 @@ class F4mFD(FileDownloader):
                         break
             frags_filenames.append(frag_filename)
 
+        dest_stream.close()
         self.report_finish(format_bytes(state['downloaded_bytes']), time.time() - start)
 
         self.try_rename(tmpfilename, filename)

youtube_dl/downloader/hls.py

@@ -13,8 +13,10 @@ class HlsFD(FileDownloader):
         self.report_destination(filename)
         tmpfilename = self.temp_name(filename)
 
-        args = ['-y', '-i', url, '-f', 'mp4', '-c', 'copy',
-            '-bsf:a', 'aac_adtstoasc', tmpfilename]
+        args = [
+            '-y', '-i', url, '-f', 'mp4', '-c', 'copy',
+            '-bsf:a', 'aac_adtstoasc',
+            encodeFilename(tmpfilename, for_subprocess=True)]
 
         for program in ['avconv', 'ffmpeg']:
             try:

youtube_dl/downloader/http.py

@@ -14,6 +14,8 @@ from ..utils import (
 
 
 class HttpFD(FileDownloader):
+    _TEST_FILE_SIZE = 10241
+
     def real_download(self, filename, info_dict):
         url = info_dict['url']
         tmpfilename = self.temp_name(filename)
@@ -23,11 +25,15 @@ class HttpFD(FileDownloader):
         headers = {'Youtubedl-no-compression': 'True'}
         if 'user_agent' in info_dict:
             headers['Youtubedl-user-agent'] = info_dict['user_agent']
+        if 'http_referer' in info_dict:
+            headers['Referer'] = info_dict['http_referer']
         basic_request = compat_urllib_request.Request(url, None, headers)
         request = compat_urllib_request.Request(url, None, headers)
 
-        if self.params.get('test', False):
-            request.add_header('Range', 'bytes=0-10240')
+        is_test = self.params.get('test', False)
+
+        if is_test:
+            request.add_header('Range', 'bytes=0-%s' % str(self._TEST_FILE_SIZE - 1))
 
         # Establish possible resume length
         if os.path.isfile(encodeFilename(tmpfilename)):
@@ -98,6 +104,15 @@ class HttpFD(FileDownloader):
             return False
 
         data_len = data.info().get('Content-length', None)
+
+        # Range HTTP header may be ignored/unsupported by a webserver
+        # (e.g. extractor/scivee.py, extractor/bambuser.py).
+        # However, for a test we still would like to download just a piece of a file.
+        # To achieve this we limit data_len to _TEST_FILE_SIZE and manually control
+        # block size when downloading a file.
+        if is_test and (data_len is None or int(data_len) > self._TEST_FILE_SIZE):
+            data_len = self._TEST_FILE_SIZE
+
         if data_len is not None:
             data_len = int(data_len) + resume_len
             min_data_len = self.params.get("min_filesize", None)
@@ -116,7 +131,7 @@ class HttpFD(FileDownloader):
         while True:
             # Download and write
             before = time.time()
-            data_block = data.read(block_size)
+            data_block = data.read(block_size if not is_test else min(block_size, data_len - byte_counter))
             after = time.time()
             if len(data_block) == 0:
                 break
@@ -160,6 +175,9 @@ class HttpFD(FileDownloader):
                 'speed': speed,
             })
 
+            if is_test and byte_counter == data_len:
+                break
+
             # Apply rate limit
             self.slow_down(start, byte_counter - resume_len)
 

youtube_dl/downloader/rtmp.py

@@ -10,6 +10,7 @@ from .common import FileDownloader
 from ..utils import (
     encodeFilename,
     format_bytes,
+    compat_str,
 )
 
 
@@ -127,7 +128,10 @@ class RtmpFD(FileDownloader):
             basic_args += ['--flashVer', flash_version]
         if live:
             basic_args += ['--live']
-        if conn:
+        if isinstance(conn, list):
+            for entry in conn:
+                basic_args += ['--conn', entry]
+        elif isinstance(conn, compat_str):
             basic_args += ['--conn', conn]
         args = basic_args + [[], ['--resume', '--skip', '1']][not live and self.params.get('continuedl', False)]
 

youtube_dl/extractor/__init__.py

@@ -2,6 +2,7 @@ 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
@@ -13,22 +14,26 @@ from .arte import (
     ArteTVConcertIE,
     ArteTVFutureIE,
     ArteTVDDCIE,
+    ArteTVEmbedIE,
 )
 from .auengine import AUEngineIE
 from .bambuser import BambuserIE, BambuserChannelIE
 from .bandcamp import BandcampIE, BandcampAlbumIE
 from .bbccouk import BBCCoUkIE
+from .bilibili import BiliBiliIE
 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 .byutv import BYUtvIE
 from .c56 import C56IE
 from .canal13cl import Canal13clIE
 from .canalplus import CanalplusIE
 from .canalc2 import Canalc2IE
 from .cbs import CBSIE
+from .cbsnews import CBSNewsIE
 from .ceskatelevize import CeskaTelevizeIE
 from .channel9 import Channel9IE
 from .chilloutzone import ChilloutzoneIE
@@ -36,7 +41,9 @@ from .cinemassacre import CinemassacreIE
 from .clipfish import ClipfishIE
 from .cliphunter import CliphunterIE
 from .clipsyndicate import ClipsyndicateIE
+from .clubic import ClubicIE
 from .cmt import CMTIE
+from .cnet import CNETIE
 from .cnn import (
     CNNIE,
     CNNBlogsIE,
@@ -58,12 +65,14 @@ from .dotsub import DotsubIE
 from .dreisat import DreiSatIE
 from .defense import DefenseGouvFrIE
 from .discovery import DiscoveryIE
+from .divxstage import DivxStageIE
 from .dropbox import DropboxIE
 from .ebaumsworld import EbaumsWorldIE
 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
@@ -72,12 +81,14 @@ 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 .franceculture import FranceCultureIE
 from .franceinter import FranceInterIE
 from .francetv import (
     PluzzIE,
@@ -102,6 +113,7 @@ from .hotnewhiphop import HotNewHipHopIE
 from .howcast import HowcastIE
 from .huffpost import HuffPostIE
 from .hypem import HypemIE
+from .iconosquare import IconosquareIE
 from .ign import IGNIE, OneUPIE
 from .imdb import (
     ImdbIE,
@@ -109,7 +121,7 @@ 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 (
@@ -147,10 +159,15 @@ from .mixcloud import MixcloudIE
 from .mpora import MporaIE
 from .mofosex import MofosexIE
 from .mooshare import MooshareIE
+from .morningstar import MorningstarIE
+from .motorsport import MotorsportIE
+from .moviezine import MoviezineIE
+from .movshare import MovShareIE
 from .mtv import (
     MTVIE,
     MTVIggyIE,
 )
+from .musicplayon import MusicPlayOnIE
 from .muzu import MuzuTVIE
 from .myspace import MySpaceIE
 from .myspass import MySpassIE
@@ -164,16 +181,23 @@ from .nbc import (
 from .ndr import NDRIE
 from .ndtv import NDTVIE
 from .newgrounds import NewgroundsIE
+from .newstube import NewstubeIE
 from .nfb import NFBIE
 from .nhl import NHLIE, NHLVideocenterIE
 from .niconico import NiconicoIE
 from .ninegag import NineGagIE
+from .noco import NocoIE
 from .normalboots import NormalbootsIE
 from .novamov import NovaMovIE
 from .nowness import NownessIE
 from .nowvideo import NowVideoIE
+from .nrk import NRKIE
+from .ntv import NTVIE
+from .nytimes import NYTimesIE
+from .oe1 import OE1IE
 from .ooyala import OoyalaIE
 from .orf import ORFIE
+from .parliamentliveuk import ParliamentLiveUKIE
 from .pbs import PBSIE
 from .photobucket import PhotobucketIE
 from .playvid import PlayvidIE
@@ -190,7 +214,10 @@ from .ringtv import RingTVIE
 from .ro220 import Ro220IE
 from .rottentomatoes import RottenTomatoesIE
 from .roxwel import RoxwelIE
+from .rtbf import RTBFIE
 from .rtlnow import RTLnowIE
+from .rts import RTSIE
+from .rtve import RTVEALaCartaIE
 from .rutube import (
     RutubeIE,
     RutubeChannelIE,
@@ -199,9 +226,9 @@ from .rutube import (
 )
 from .rutv import RUTVIE
 from .savefrom import SaveFromIE
+from .scivee import SciVeeIE
 from .servingsys import ServingSysIE
 from .sina import SinaIE
-from .slashdot import SlashdotIE
 from .slideshare import SlideshareIE
 from .smotri import (
     SmotriIE,
@@ -210,7 +237,12 @@ from .smotri import (
     SmotriBroadcastIE,
 )
 from .sohu import SohuIE
-from .soundcloud import SoundcloudIE, SoundcloudSetIE, SoundcloudUserIE
+from .soundcloud import (
+    SoundcloudIE,
+    SoundcloudSetIE,
+    SoundcloudUserIE,
+    SoundcloudPlaylistIE
+)
 from .southparkstudios import (
     SouthParkStudiosIE,
     SouthparkDeIE,
@@ -220,7 +252,6 @@ from .spankwire import SpankwireIE
 from .spiegel import SpiegelIE
 from .spike import SpikeIE
 from .stanfordoc import StanfordOpenClassroomIE
-from .statigram import StatigramIE
 from .steam import SteamIE
 from .streamcloud import StreamcloudIE
 from .streamcz import StreamCZIE
@@ -234,7 +265,9 @@ from .tf1 import TF1IE
 from .theplatform import ThePlatformIE
 from .thisav import ThisAVIE
 from .tinypic import TinyPicIE
+from .tlc import TlcIE, TlcDeIE
 from .toutv import TouTvIE
+from .toypics import ToypicsUserIE, ToypicsIE
 from .traileraddict import TrailerAddictIE
 from .trilulilu import TriluliluIE
 from .trutube import TruTubeIE
@@ -249,18 +282,21 @@ from .udemy import (
     UdemyCourseIE
 )
 from .unistra import UnistraIE
+from .urort import UrortIE
 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 .videott import VideoTtIE
+from .videoweed import VideoWeedIE
 from .vimeo import (
     VimeoIE,
     VimeoChannelIE,
@@ -268,21 +304,28 @@ from .vimeo import (
     VimeoAlbumIE,
     VimeoGroupsIE,
     VimeoReviewIE,
+    VimeoWatchLaterIE,
 )
 from .vine import VineIE
 from .viki import VikiIE
 from .vk import VKIE
 from .vube import VubeIE
+from .vuclip import VuClipIE
+from .washingtonpost import WashingtonPostIE
 from .wat import WatIE
-from .wdr import WDRIE
+from .wdr import (
+    WDRIE,
+    WDRMausIE,
+)
 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,

youtube_dl/extractor/addanime.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -14,14 +16,14 @@ from ..utils import (
 class AddAnimeIE(InfoExtractor):
 
     _VALID_URL = r'^http://(?:\w+\.)?add-anime\.net/watch_video\.php\?(?:.*?)v=(?P<video_id>[\w_]+)(?:.*)'
-    IE_NAME = u'AddAnime'
     _TEST = {
-        u'url': u'http://www.add-anime.net/watch_video.php?v=24MR3YO5SAS9',
-        u'file': u'24MR3YO5SAS9.mp4',
-        u'md5': u'72954ea10bc979ab5e2eb288b21425a0',
-        u'info_dict': {
-            u"description": u"One Piece 606",
-            u"title": u"One Piece 606"
+        'url': 'http://www.add-anime.net/watch_video.php?v=24MR3YO5SAS9',
+        'md5': '72954ea10bc979ab5e2eb288b21425a0',
+        'info_dict': {
+            'id': '24MR3YO5SAS9',
+            'ext': 'mp4',
+            'description': 'One Piece 606',
+            'title': 'One Piece 606',
         }
     }
 
@@ -38,10 +40,10 @@ class AddAnimeIE(InfoExtractor):
             redir_webpage = ee.cause.read().decode('utf-8')
             action = self._search_regex(
                 r'<form id="challenge-form" action="([^"]+)"',
-                redir_webpage, u'Redirect form')
+                redir_webpage, 'Redirect form')
             vc = self._search_regex(
                 r'<input type="hidden" name="jschl_vc" value="([^"]+)"/>',
-                redir_webpage, u'redirect vc value')
+                redir_webpage, 'redirect vc value')
             av = re.search(
                 r'a\.value = ([0-9]+)[+]([0-9]+)[*]([0-9]+);',
                 redir_webpage)
@@ -52,19 +54,19 @@ class AddAnimeIE(InfoExtractor):
             parsed_url = compat_urllib_parse_urlparse(url)
             av_val = av_res + len(parsed_url.netloc)
             confirm_url = (
-                parsed_url.scheme + u'://' + parsed_url.netloc +
+                parsed_url.scheme + '://' + parsed_url.netloc +
                 action + '?' +
                 compat_urllib_parse.urlencode({
                     'jschl_vc': vc, 'jschl_answer': compat_str(av_val)}))
             self._download_webpage(
                 confirm_url, video_id,
-                note=u'Confirming after redirect')
+                note='Confirming after redirect')
             webpage = self._download_webpage(url, video_id)
 
         formats = []
         for format_id in ('normal', 'hq'):
             rex = r"var %s_video_file = '(.*?)';" % re.escape(format_id)
-            video_url = self._search_regex(rex, webpage, u'video file URLx',
+            video_url = self._search_regex(rex, webpage, 'video file URLx',
                                            fatal=False)
             if not video_url:
                 continue
@@ -72,14 +74,13 @@ class AddAnimeIE(InfoExtractor):
                 'format_id': format_id,
                 'url': video_url,
             })
-        if not formats:
-            raise ExtractorError(u'Cannot find any video format!')
+        self._sort_formats(formats)
         video_title = self._og_search_title(webpage)
         video_description = self._og_search_description(webpage)
 
         return {
             '_type': 'video',
-            'id':  video_id,
+            'id': video_id,
             'formats': formats,
             'title': video_title,
             'description': video_description

youtube_dl/extractor/aol.py

@@ -0,0 +1,65 @@
+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'''(?x)
+        (?:
+            aol-video:|
+            http://on\.aol\.com/
+            (?:
+                video/.*-|
+                playlist/(?P<playlist_display_id>[^/?#]+?)-(?P<playlist_id>[0-9]+)[?#].*_videoid=
+            )
+        )
+        (?P<id>[0-9]+)
+        (?:$|\?)
+    '''
+
+    _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')
+
+        playlist_id = mobj.group('playlist_id')
+        if playlist_id and not self._downloader.params.get('noplaylist'):
+            self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
+
+            webpage = self._download_webpage(url, playlist_id)
+            title = self._html_search_regex(
+                r'<h1 class="video-title[^"]*">(.+?)</h1>', webpage, 'title')
+            playlist_html = self._search_regex(
+                r"(?s)<ul\s+class='video-related[^']*'>(.*?)</ul>", webpage,
+                'playlist HTML')
+            entries = [{
+                '_type': 'url',
+                'url': 'aol-video:%s' % m.group('id'),
+                'ie_key': 'Aol',
+            } for m in re.finditer(
+                r"<a\s+href='.*videoid=(?P<id>[0-9]+)'\s+class='video-thumb'>",
+                playlist_html)]
+
+            return {
+                '_type': 'playlist',
+                'id': playlist_id,
+                'display_id': mobj.group('playlist_display_id'),
+                'title': title,
+                'entries': entries,
+            }
+
+        return FiveMinIE._build_result(video_id)

youtube_dl/extractor/appletrailers.py

@@ -6,7 +6,6 @@ import json
 from .common import InfoExtractor
 from ..utils import (
     compat_urlparse,
-    determine_ext,
 )
 
 
@@ -16,9 +15,10 @@ class AppleTrailersIE(InfoExtractor):
         "url": "http://trailers.apple.com/trailers/wb/manofsteel/",
         "playlist": [
             {
-                "file": "manofsteel-trailer4.mov",
                 "md5": "d97a8e575432dbcb81b7c3acb741f8a8",
                 "info_dict": {
+                    "id": "manofsteel-trailer4",
+                    "ext": "mov",
                     "duration": 111,
                     "title": "Trailer 4",
                     "upload_date": "20130523",
@@ -26,9 +26,10 @@ class AppleTrailersIE(InfoExtractor):
                 },
             },
             {
-                "file": "manofsteel-trailer3.mov",
                 "md5": "b8017b7131b721fb4e8d6f49e1df908c",
                 "info_dict": {
+                    "id": "manofsteel-trailer3",
+                    "ext": "mov",
                     "duration": 182,
                     "title": "Trailer 3",
                     "upload_date": "20130417",
@@ -36,9 +37,10 @@ class AppleTrailersIE(InfoExtractor):
                 },
             },
             {
-                "file": "manofsteel-trailer.mov",
                 "md5": "d0f1e1150989b9924679b441f3404d48",
                 "info_dict": {
+                    "id": "manofsteel-trailer",
+                    "ext": "mov",
                     "duration": 148,
                     "title": "Trailer",
                     "upload_date": "20121212",
@@ -46,15 +48,16 @@ class AppleTrailersIE(InfoExtractor):
                 },
             },
             {
-                "file": "manofsteel-teaser.mov",
                 "md5": "5fe08795b943eb2e757fa95cb6def1cb",
                 "info_dict": {
+                    "id": "manofsteel-teaser",
+                    "ext": "mov",
                     "duration": 93,
                     "title": "Teaser",
                     "upload_date": "20120721",
                     "uploader_id": "wb",
                 },
-            }
+            },
         ]
     }
 
@@ -65,16 +68,16 @@ class AppleTrailersIE(InfoExtractor):
         movie = mobj.group('movie')
         uploader_id = mobj.group('company')
 
-        playlist_url = compat_urlparse.urljoin(url, u'includes/playlists/itunes.inc')
+        playlist_url = compat_urlparse.urljoin(url, 'includes/playlists/itunes.inc')
         def fix_html(s):
-            s = re.sub(r'(?s)<script[^<]*?>.*?</script>', u'', s)
+            s = re.sub(r'(?s)<script[^<]*?>.*?</script>', '', s)
             s = re.sub(r'<img ([^<]*?)>', r'<img \1/>', s)
             # The ' in the onClick attributes are not escaped, it couldn't be parsed
             # like: http://trailers.apple.com/trailers/wb/gravity/
             def _clean_json(m):
-                return u'iTunes.playURL(%s);' % m.group(1).replace('\'', '&#39;')
+                return 'iTunes.playURL(%s);' % m.group(1).replace('\'', '&#39;')
             s = re.sub(self._JSON_RE, _clean_json, s)
-            s = u'<html>' + s + u'</html>'
+            s = '<html>' + s + u'</html>'
             return s
         doc = self._download_xml(playlist_url, movie, transform_source=fix_html)
 
@@ -82,7 +85,7 @@ class AppleTrailersIE(InfoExtractor):
         for li in doc.findall('./div/ul/li'):
             on_click = li.find('.//a').attrib['onClick']
             trailer_info_json = self._search_regex(self._JSON_RE,
-                on_click, u'trailer info')
+                on_click, 'trailer info')
             trailer_info = json.loads(trailer_info_json)
             title = trailer_info['title']
             video_id = movie + '-' + re.sub(r'[^a-zA-Z0-9]', '', title).lower()
@@ -98,8 +101,7 @@ class AppleTrailersIE(InfoExtractor):
             first_url = trailer_info['url']
             trailer_id = first_url.split('/')[-1].rpartition('_')[0].lower()
             settings_json_url = compat_urlparse.urljoin(url, 'includes/settings/%s.json' % trailer_id)
-            settings_json = self._download_webpage(settings_json_url, trailer_id, u'Downloading settings json')
-            settings = json.loads(settings_json)
+            settings = self._download_json(settings_json_url, trailer_id, 'Downloading settings json')
 
             formats = []
             for format in settings['metadata']['sizes']:
@@ -107,7 +109,6 @@ class AppleTrailersIE(InfoExtractor):
                 format_url = re.sub(r'_(\d*p.mov)', r'_h\1', format['src'])
                 formats.append({
                     'url': format_url,
-                    'ext': determine_ext(format_url),
                     'format': format['type'],
                     'width': format['width'],
                     'height': int(format['height']),

youtube_dl/extractor/arte.py

@@ -2,7 +2,6 @@
 from __future__ import unicode_literals
 
 import re
-import json
 
 from .common import InfoExtractor
 from ..utils import (
@@ -19,114 +18,41 @@ from ..utils import (
 # is different for each one. The videos usually expire in 7 days, so we can't
 # add tests.
 
-class ArteTvIE(InfoExtractor):
-    _VIDEOS_URL = r'(?:http://)?videos\.arte\.tv/(?P<lang>fr|de)/.*-(?P<id>.*?)\.html'
-    _LIVEWEB_URL = r'(?:http://)?liveweb\.arte\.tv/(?P<lang>fr|de)/(?P<subpage>.+?)/(?P<name>.+)'
-    _LIVE_URL = r'index-[0-9]+\.html$'
 
+class ArteTvIE(InfoExtractor):
+    _VALID_URL = r'http://videos\.arte\.tv/(?P<lang>fr|de)/.*-(?P<id>.*?)\.html'
     IE_NAME = 'arte.tv'
 
-    @classmethod
-    def suitable(cls, url):
-        return any(re.match(regex, url) for regex in (cls._VIDEOS_URL, cls._LIVEWEB_URL))
-
-    # TODO implement Live Stream
-    # from ..utils import compat_urllib_parse
-    # def extractLiveStream(self, url):
-    #     video_lang = url.split('/')[-4]
-    #     info = self.grep_webpage(
-    #         url,
-    #         r'src="(.*?/videothek_js.*?\.js)',
-    #         0,
-    #         [
-    #             (1, 'url', 'Invalid URL: %s' % url)
-    #         ]
-    #     )
-    #     http_host = url.split('/')[2]
-    #     next_url = 'http://%s%s' % (http_host, compat_urllib_parse.unquote(info.get('url')))
-    #     info = self.grep_webpage(
-    #         next_url,
-    #         r'(s_artestras_scst_geoFRDE_' + video_lang + '.*?)\'.*?' +
-    #             '(http://.*?\.swf).*?' +
-    #             '(rtmp://.*?)\'',
-    #         re.DOTALL,
-    #         [
-    #             (1, 'path',   'could not extract video path: %s' % url),
-    #             (2, 'player', 'could not extract video player: %s' % url),
-    #             (3, 'url',    'could not extract video url: %s' % url)
-    #         ]
-    #     )
-    #     video_url = '%s/%s' % (info.get('url'), info.get('path'))
-
     def _real_extract(self, url):
-        mobj = re.match(self._VIDEOS_URL, url)
-        if mobj is not None:
-            id = mobj.group('id')
-            lang = mobj.group('lang')
-            return self._extract_video(url, id, lang)
+        mobj = re.match(self._VALID_URL, url)
+        lang = mobj.group('lang')
+        video_id = mobj.group('id')
 
-        mobj = re.match(self._LIVEWEB_URL, url)
-        if mobj is not None:
-            name = mobj.group('name')
-            lang = mobj.group('lang')
-            return self._extract_liveweb(url, name, lang)
-
-        if re.search(self._LIVE_URL, url) is not None:
-            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='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 = self._download_xml(
             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):
-            quality = m.group('quality')
-            if quality == 'hd':
-                return 2
-            else:
-                return 1
-        # We pick the best quality
-        video_urls = sorted(video_urls, key=_key)
-        video_url = list(video_urls)[-1].group('url')
-        
-        title = self._html_search_regex(r'<name>(.*?)</name>', config_xml, 'title')
-        thumbnail = self._html_search_regex(r'<firstThumbnailUrl>(.*?)</firstThumbnailUrl>',
-                                            config_xml, 'thumbnail')
-        return {'id': video_id,
-                'title': title,
-                'thumbnail': thumbnail,
-                'url': video_url,
-                'ext': 'flv',
-                }
+        formats = [{
+            'forma_id': q.attrib['quality'],
+            'url': q.text,
+            'ext': 'flv',
+            'quality': 2 if q.attrib['quality'] == 'hd' else 1,
+        } for q in config.findall('./urls/url')]
+        self._sort_formats(formats)
 
-    def _extract_liveweb(self, url, name, lang):
-        """Extract form http://liveweb.arte.tv/"""
-        webpage = self._download_webpage(url, name)
-        video_id = self._search_regex(r'eventId=(\d+?)("|&)', webpage, 'event id')
-        config_doc = self._download_xml('http://download.liveweb.arte.tv/o21/liveweb/events/event-%s.xml' % video_id,
-                                            video_id, 'Downloading information')
-        event_doc = config_doc.find('event')
-        url_node = event_doc.find('video').find('urlHd')
-        if url_node is None:
-            url_node = event_doc.find('urlSd')
-
-        return {'id': video_id,
-                'title': event_doc.find('name%s' % lang.capitalize()).text,
-                'url': url_node.text.replace('MP4', 'mp4'),
-                'ext': 'flv',
-                'thumbnail': self._og_search_thumbnail(webpage),
-                }
+        title = config.find('.//name').text
+        thumbnail = config.find('.//firstThumbnailUrl').text
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'formats': formats,
+        }
 
 
 class ArteTVPlus7IE(InfoExtractor):
@@ -148,13 +74,12 @@ class ArteTVPlus7IE(InfoExtractor):
         return self._extract_from_webpage(webpage, video_id, lang)
 
     def _extract_from_webpage(self, webpage, video_id, lang):
-        json_url = self._html_search_regex(r'arte_vp_url="(.*?)"', webpage, 'json url')
+        json_url = self._html_search_regex(
+            r'arte_vp_url="(.*?)"', webpage, 'json vp url')
         return self._extract_from_json_url(json_url, video_id, lang)
 
     def _extract_from_json_url(self, json_url, video_id, lang):
-        json_info = self._download_webpage(json_url, video_id, 'Downloading info json')
-        self.report_extraction(video_id)
-        info = json.loads(json_info)
+        info = self._download_json(json_url, video_id)
         player_info = info['videoJsonPlayer']
 
         info_dict = {
@@ -176,6 +101,8 @@ class ArteTVPlus7IE(InfoExtractor):
                 l = 'F'
             elif lang == 'de':
                 l = 'A'
+            else:
+                l = lang
             regexes = [r'VO?%s' % l, r'VO?.-ST%s' % l]
             return any(re.match(r, f['versionCode']) for r in regexes)
         # Some formats may not be in the same language as the url
@@ -194,14 +121,17 @@ class ArteTVPlus7IE(InfoExtractor):
                 return ['HQ', 'MQ', 'EQ', 'SQ'].index(f['quality'])
         else:
             def sort_key(f):
+                versionCode = f.get('versionCode')
+                if versionCode is None:
+                    versionCode = ''
                 return (
                     # Sort first by quality
-                    int(f.get('height',-1)),
-                    int(f.get('bitrate',-1)),
+                    int(f.get('height', -1)),
+                    int(f.get('bitrate', -1)),
                     # The original version with subtitles has lower relevance
-                    re.match(r'VO-ST(F|A)', f.get('versionCode', '')) is None,
+                    re.match(r'VO-ST(F|A)', 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,
+                    re.match(r'VO?(F|A)-STM\1', versionCode) is None,
                     # Prefer http downloads over m3u8
                     0 if f['url'].endswith('m3u8') else 1,
                 )
@@ -302,5 +232,25 @@ class ArteTVConcertIE(ArteTVPlus7IE):
             'ext': 'mp4',
             'title': 'The Notwist im Pariser Konzertclub "Divan du Monde"',
             'upload_date': '20140128',
+            'description': 'md5:486eb08f991552ade77439fe6d82c305',
         },
     }
+
+
+class ArteTVEmbedIE(ArteTVPlus7IE):
+    IE_NAME = 'arte.tv:embed'
+    _VALID_URL = r'''(?x)
+        http://www\.arte\.tv
+        /playerv2/embed\.php\?json_url=
+        (?P<json_url>
+            http://arte\.tv/papi/tvguide/videos/stream/player/
+            (?P<lang>[^/]+)/(?P<id>[^/]+)[^&]*
+        )
+    '''
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        lang = mobj.group('lang')
+        json_url = mobj.group('json_url')
+        return self._extract_from_json_url(json_url, video_id, lang)

youtube_dl/extractor/auengine.py

@@ -11,22 +11,24 @@ from ..utils import (
 
 
 class AUEngineIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?auengine\.com/embed\.php\?.*?file=(?P<id>[^&]+).*?'
+
     _TEST = {
         'url': 'http://auengine.com/embed.php?file=lfvlytY6&w=650&h=370',
-        'file': 'lfvlytY6.mp4',
         'md5': '48972bdbcf1a3a2f5533e62425b41d4f',
         'info_dict': {
+            'id': 'lfvlytY6',
+            'ext': 'mp4',
             'title': '[Commie]The Legend of the Legendary Heroes - 03 - Replication Eye (Alpha Stigma)[F9410F5A]'
         }
     }
-    _VALID_URL = r'(?:http://)?(?:www\.)?auengine\.com/embed\.php\?.*?file=([^&]+).*?'
 
     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)
-        title = self._html_search_regex(r'<title>(?P<title>.+?)</title>',
-                webpage, 'title')
+        title = self._html_search_regex(r'<title>(?P<title>.+?)</title>', webpage, 'title')
         title = title.strip()
         links = re.findall(r'\s(?:file|url):\s*["\']([^\'"]+)["\']', webpage)
         links = map(compat_urllib_parse.unquote, links)
@@ -39,14 +41,15 @@ class AUEngineIE(InfoExtractor):
             elif '/videos/' in link:
                 video_url = link
         if not video_url:
-            raise ExtractorError(u'Could not find video URL')
+            raise ExtractorError('Could not find video URL')
         ext = '.' + determine_ext(video_url)
         if ext == title[-len(ext):]:
             title = title[:-len(ext)]
 
         return {
-            'id':        video_id,
-            'url':       video_url,
-            'title':     title,
+            'id': video_id,
+            'url': video_url,
+            'title': title,
             'thumbnail': thumbnail,
+            'http_referer': 'http://www.auengine.com/flowplayer/flowplayer.commercial-3.2.14.swf',
         }

youtube_dl/extractor/bandcamp.py

@@ -12,7 +12,7 @@ from ..utils import (
 
 
 class BandcampIE(InfoExtractor):
-    _VALID_URL = r'http://.*?\.bandcamp\.com/track/(?P<title>.*)'
+    _VALID_URL = r'https?://.*?\.bandcamp\.com/track/(?P<title>.*)'
     _TESTS = [{
         'url': 'http://youtube-dl.bandcamp.com/track/youtube-dl-test-song',
         'file': '1812978515.mp3',
@@ -100,7 +100,7 @@ class BandcampIE(InfoExtractor):
 
 class BandcampAlbumIE(InfoExtractor):
     IE_NAME = 'Bandcamp:album'
-    _VALID_URL = r'http://.*?\.bandcamp\.com/album/(?P<title>.*)'
+    _VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com(?:/album/(?P<title>[^?#]+))?'
 
     _TEST = {
         'url': 'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1',
@@ -128,8 +128,10 @@ class BandcampAlbumIE(InfoExtractor):
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
+        playlist_id = mobj.group('subdomain')
         title = mobj.group('title')
-        webpage = self._download_webpage(url, title)
+        display_id = title or playlist_id
+        webpage = self._download_webpage(url, display_id)
         tracks_paths = re.findall(r'<a href="(.*?)" itemprop="url">', webpage)
         if not tracks_paths:
             raise ExtractorError('The page doesn\'t contain any tracks')
@@ -139,6 +141,8 @@ class BandcampAlbumIE(InfoExtractor):
         title = self._search_regex(r'album_title : "(.*?)"', webpage, 'title')
         return {
             '_type': 'playlist',
+            'id': playlist_id,
+            'display_id': display_id,
             'title': title,
             'entries': entries,
         }

youtube_dl/extractor/bilibili.py

@@ -0,0 +1,106 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_parse_qs,
+    ExtractorError,
+    int_or_none,
+    unified_strdate,
+)
+
+
+class BiliBiliIE(InfoExtractor):
+    _VALID_URL = r'http://www\.bilibili\.tv/video/av(?P<id>[0-9]+)/'
+
+    _TEST = {
+        'url': 'http://www.bilibili.tv/video/av1074402/',
+        'md5': '2c301e4dab317596e837c3e7633e7d86',
+        'info_dict': {
+            'id': '1074402',
+            'ext': 'flv',
+            'title': '【金坷垃】金泡沫',
+            'duration': 308,
+            'upload_date': '20140420',
+            'thumbnail': 're:^https?://.+\.jpg',
+        },
+    }
+
+    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_code = self._search_regex(
+            r'(?s)<div itemprop="video".*?>(.*?)</div>', webpage, 'video code')
+
+        title = self._html_search_meta(
+            'media:title', video_code, 'title', fatal=True)
+        duration_str = self._html_search_meta(
+            'duration', video_code, 'duration')
+        if duration_str is None:
+            duration = None
+        else:
+            duration_mobj = re.match(
+                r'^T(?:(?P<hours>[0-9]+)H)?(?P<minutes>[0-9]+)M(?P<seconds>[0-9]+)S$',
+                duration_str)
+            duration = (
+                int_or_none(duration_mobj.group('hours'), default=0) * 3600 +
+                int(duration_mobj.group('minutes')) * 60 +
+                int(duration_mobj.group('seconds')))
+        upload_date = unified_strdate(self._html_search_meta(
+            'uploadDate', video_code, fatal=False))
+        thumbnail = self._html_search_meta(
+            'thumbnailUrl', video_code, 'thumbnail', fatal=False)
+
+        player_params = compat_parse_qs(self._html_search_regex(
+            r'<iframe .*?class="player" src="https://secure.bilibili.tv/secure,([^"]+)"',
+            webpage, 'player params'))
+
+        if 'cid' in player_params:
+            cid = player_params['cid'][0]
+
+            lq_doc = self._download_xml(
+                'http://interface.bilibili.cn/v_cdn_play?cid=%s' % cid,
+                video_id,
+                note='Downloading LQ video info'
+            )
+            lq_durl = lq_doc.find('.//durl')
+            formats = [{
+                'format_id': 'lq',
+                'quality': 1,
+                'url': lq_durl.find('./url').text,
+                'filesize': int_or_none(
+                    lq_durl.find('./size'), get_attr='text'),
+            }]
+
+            hq_doc = self._download_xml(
+                'http://interface.bilibili.cn/playurl?cid=%s' % cid,
+                video_id,
+                note='Downloading HQ video info',
+                fatal=False,
+            )
+            if hq_doc is not False:
+                hq_durl = hq_doc.find('.//durl')
+                formats.append({
+                    'format_id': 'hq',
+                    'quality': 2,
+                    'ext': 'flv',
+                    'url': hq_durl.find('./url').text,
+                    'filesize': int_or_none(
+                        hq_durl.find('./size'), get_attr='text'),
+                })
+        else:
+            raise ExtractorError('Unsupported player parameters: %r' % (player_params,))
+
+        self._sort_formats(formats)
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'duration': duration,
+            'upload_date': upload_date,
+            'thumbnail': thumbnail,
+        }

youtube_dl/extractor/bloomberg.py

@@ -1,22 +1,21 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
-from .ooyala import OoyalaIE
 
 
 class BloombergIE(InfoExtractor):
     _VALID_URL = r'https?://www\.bloomberg\.com/video/(?P<name>.+?)\.html'
 
     _TEST = {
-        u'url': u'http://www.bloomberg.com/video/shah-s-presentation-on-foreign-exchange-strategies-qurhIVlJSB6hzkVi229d8g.html',
-        u'file': u'12bzhqZTqQHmmlA8I-i0NpzJgcG5NNYX.mp4',
-        u'info_dict': {
-            u'title': u'Shah\'s Presentation on Foreign-Exchange Strategies',
-            u'description': u'md5:abc86e5236f9f0e4866c59ad36736686',
-        },
-        u'params': {
-            # Requires ffmpeg (m3u8 manifest)
-            u'skip_download': True,
+        'url': 'http://www.bloomberg.com/video/shah-s-presentation-on-foreign-exchange-strategies-qurhIVlJSB6hzkVi229d8g.html',
+        'md5': '7bf08858ff7c203c870e8a6190e221e5',
+        'info_dict': {
+            'id': 'qurhIVlJSB6hzkVi229d8g',
+            'ext': 'flv',
+            'title': 'Shah\'s Presentation on Foreign-Exchange Strategies',
+            'description': 'md5:0681e0d30dcdfc6abf34594961d8ea88',
         },
     }
 
@@ -24,7 +23,16 @@ class BloombergIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         name = mobj.group('name')
         webpage = self._download_webpage(url, name)
-        embed_code = self._search_regex(
-            r'<source src="https?://[^/]+/[^/]+/[^/]+/([^/]+)', webpage,
-            'embed code')
-        return OoyalaIE._build_url_result(embed_code)
+        f4m_url = self._search_regex(
+            r'<source src="(https?://[^"]+\.f4m.*?)"', webpage,
+            'f4m url')
+        title = re.sub(': Video$', '', self._og_search_title(webpage))
+
+        return {
+            'id': name.split('-')[-1],
+            'title': title,
+            'url': f4m_url,
+            'ext': 'flv',
+            'description': self._og_search_description(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
+        }

youtube_dl/extractor/br.py

@@ -4,39 +4,72 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import ExtractorError
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+)
 
 
 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"
+    IE_DESC = 'Bayerischer Rundfunk Mediathek'
+    _VALID_URL = r'https?://(?:www\.)?br\.de/(?:[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/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
+            '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',
             }
-        }
+        },
+        {
+            'url': 'http://www.br.de/nachrichten/schaeuble-haushaltsentwurf-bundestag-100.html',
+            'md5': '3db0df1a9a9cd9fa0c70e6ea8aa8e820',
+            'info_dict': {
+                'id': 'c6aae3de-2cf9-43f2-957f-f17fef9afaab',
+                'ext': 'aac',
+                'title': '"Keine neuen Schulden im nächsten Jahr"',
+                'description': 'Haushaltsentwurf: "Keine neuen Schulden im nächsten Jahr"',
+            }
+        },
+        {
+            'url': 'http://www.br.de/radio/bayern1/service/team/videos/team-video-erdelt100.html',
+            'md5': 'dbab0aef2e047060ea7a21fc1ce1078a',
+            'info_dict': {
+                'id': '6ba73750-d405-45d3-861d-1ce8c524e059',
+                'ext': 'mp4',
+                'title': 'Umweltbewusster Häuslebauer',
+                'description': 'Uwe Erdelt: Umweltbewusster Häuslebauer',
+            }
+        },
+        {
+            'url': 'http://www.br.de/fernsehen/br-alpha/sendungen/kant-fuer-anfaenger/kritik-der-reinen-vernunft/kant-kritik-01-metaphysik100.html',
+            'md5': '23bca295f1650d698f94fc570977dae3',
+            'info_dict': {
+                'id': 'd982c9ce-8648-4753-b358-98abb8aec43d',
+                'ext': 'mp4',
+                'title': 'Folge 1 - Metaphysik',
+                'description': 'Kant für Anfänger: Folge 1 - Metaphysik',
+                'uploader': 'Eva Maria Steimle',
+                'upload_date': '20140117',
+            }
+        },
     ]
 
     def _real_extract(self, url):
@@ -44,56 +77,63 @@ class BRIE(InfoExtractor):
         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")
+            r"return BRavFramework\.register\(BRavFramework\('avPlayer_(?:[a-f0-9-]{36})'\)\.setup\({dataURL:'(/(?:[a-z0-9\-]+/)+[a-z0-9/~_.-]+)'}\)\);", 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)
+        medias = []
 
-        if len(videos) > 1:
+        for xml_media in xml.findall('video') + xml.findall('audio'):
+            media = {
+                'id': xml_media.get('externalId'),
+                'title': xml_media.find('title').text,
+                'formats': self._extract_formats(xml_media.find('assets')),
+                'thumbnails': self._extract_thumbnails(xml_media.find('teaserImage/variants')),
+                'description': ' '.join(xml_media.find('shareTitle').text.splitlines()),
+                'webpage_url': xml_media.find('permalink').text
+            }
+            if xml_media.find('author').text:
+                media['uploader'] = xml_media.find('author').text
+            if xml_media.find('broadcastDate').text:
+                media['upload_date'] = ''.join(reversed(xml_media.find('broadcastDate').text.split('.')))
+            medias.append(media)
+
+        if len(medias) > 1:
             self._downloader.report_warning(
-                'found multiple videos; please '
+                'found multiple medias; 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]
+        if not medias:
+            raise ExtractorError('No media entries found')
+        return medias[0]
 
     def _extract_formats(self, assets):
+
+        def text_or_none(asset, tag):
+            elem = asset.find(tag)
+            return None if elem is None else elem.text
+
         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]
+            'url': text_or_none(asset, 'downloadUrl'),
+            'ext': text_or_none(asset, 'mediaType'),
+            'format_id': asset.get('type'),
+            'width': int_or_none(text_or_none(asset, 'frameWidth')),
+            'height': int_or_none(text_or_none(asset, 'frameHeight')),
+            'tbr': int_or_none(text_or_none(asset, 'bitrateVideo')),
+            'abr': int_or_none(text_or_none(asset, 'bitrateAudio')),
+            'vcodec': text_or_none(asset, 'codecVideo'),
+            'acodec': text_or_none(asset, 'codecAudio'),
+            'container': text_or_none(asset, 'mediaType'),
+            'filesize': int_or_none(text_or_none(asset, 'size')),
+        } 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)
+            'url': self._BASE_URL + variant.find('url').text,
+            'width': int_or_none(variant.find('width').text),
+            'height': int_or_none(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

@@ -27,9 +27,10 @@ class BreakIE(InfoExtractor):
             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')
+        youtube_id = info.get('youtubeId')
+        if youtube_id:
+            return self.url_result(youtube_id, 'Youtube')
+
         final_url = video_url + '?' + info['AuthToken']
         return {
             'id': video_id,

youtube_dl/extractor/brightcove.py

@@ -87,7 +87,7 @@ class BrightcoveIE(InfoExtractor):
         object_str = object_str.replace('<--', '<!--')
         object_str = fix_xml_ampersands(object_str)
 
-        object_doc = xml.etree.ElementTree.fromstring(object_str)
+        object_doc = xml.etree.ElementTree.fromstring(object_str.encode('utf-8'))
 
         fv_el = find_xpath_attr(object_doc, './param', 'name', 'flashVars')
         if fv_el is not None:
@@ -140,7 +140,11 @@ class BrightcoveIE(InfoExtractor):
 
         url_m = re.search(r'<meta\s+property="og:video"\s+content="(http://c.brightcove.com/[^"]+)"', webpage)
         if url_m:
-            return [unescapeHTML(url_m.group(1))]
+            url = unescapeHTML(url_m.group(1))
+            # Some sites don't add it, we can't download with this url, for example:
+            # http://www.ktvu.com/videos/news/raw-video-caltrain-releases-video-of-man-almost/vCTZdY/
+            if 'playerKey' in url:
+                return [url]
 
         matches = re.findall(
             r'''(?sx)<object

youtube_dl/extractor/byutv.py

@@ -0,0 +1,48 @@
+from __future__ import unicode_literals
+
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+
+class BYUtvIE(InfoExtractor):
+    _VALID_URL = r'^https?://(?:www\.)?byutv.org/watch/[0-9a-f-]+/(?P<video_id>[^/?#]+)'
+    _TEST = {
+        'url': 'http://www.byutv.org/watch/44e80f7b-e3ba-43ba-8c51-b1fd96c94a79/granite-flats-talking',
+        'info_dict': {
+            'id': 'granite-flats-talking',
+            'ext': 'mp4',
+            'description': 'md5:4e9a7ce60f209a33eca0ac65b4918e1c',
+            'title': 'Talking',
+            'thumbnail': 're:^https?://.*promo.*'
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }
+
+    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)
+        episode_code = self._search_regex(
+            r'(?s)episode:(.*?\}),\s*\n', webpage, 'episode information')
+        episode_json = re.sub(
+            r'(\n\s+)([a-zA-Z]+):\s+\'(.*?)\'', r'\1"\2": "\3"', episode_code)
+        ep = json.loads(episode_json)
+
+        if ep['providerType'] == 'Ooyala':
+            return {
+                '_type': 'url_transparent',
+                'ie_key': 'Ooyala',
+                'url': 'ooyala:%s' % ep['providerId'],
+                'id': video_id,
+                'title': ep['title'],
+                'description': ep.get('description'),
+                'thumbnail': ep.get('imageThumbnail'),
+            }
+        else:
+            raise ExtractorError('Unsupported provider %s' % ep['provider'])

youtube_dl/extractor/c56.py

@@ -2,39 +2,46 @@
 from __future__ import unicode_literals
 
 import re
-import json
 
 from .common import InfoExtractor
 
 
 class C56IE(InfoExtractor):
-    _VALID_URL = r'https?://((www|player)\.)?56\.com/(.+?/)?(v_|(play_album.+-))(?P<textid>.+?)\.(html|swf)'
+    _VALID_URL = r'https?://(?:(?:www|player)\.)?56\.com/(?:.+?/)?(?:v_|(?:play_album.+-))(?P<textid>.+?)\.(?:html|swf)'
     IE_NAME = '56.com'
     _TEST = {
         'url': 'http://www.56.com/u39/v_OTM0NDA3MTY.html',
-        'file': '93440716.flv',
         'md5': 'e59995ac63d0457783ea05f93f12a866',
         'info_dict': {
+            'id': '93440716',
+            'ext': 'flv',
             'title': '网事知多少 第32期：车怒',
+            'duration': 283.813,
         },
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE)
         text_id = mobj.group('textid')
-        info_page = self._download_webpage('http://vxml.56.com/json/%s/' % text_id,
-                                           text_id, 'Downloading video info')
-        info = json.loads(info_page)['info']
-        formats = [{
-            'format_id': f['type'],
-            'filesize': int(f['filesize']),
-            'url': f['url']
-        } for f in info['rfiles']]
+
+        page = self._download_json(
+            'http://vxml.56.com/json/%s/' % text_id, text_id, 'Downloading video info')
+
+        info = page['info']
+
+        formats = [
+            {
+                'format_id': f['type'],
+                'filesize': int(f['filesize']),
+                'url': f['url']
+            } for f in info['rfiles']
+        ]
         self._sort_formats(formats)
 
         return {
             'id': info['vid'],
             'title': info['Subject'],
+            'duration': int(info['duration']) / 1000.0,
             'formats': formats,
             'thumbnail': info.get('bimg') or info.get('img'),
         }

youtube_dl/extractor/canalplus.py

@@ -1,53 +1,72 @@
 # encoding: utf-8
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
-from ..utils import unified_strdate
+from ..utils import (
+    unified_strdate,
+    url_basename,
+)
 
 
 class CanalplusIE(InfoExtractor):
-    _VALID_URL = r'https?://(www\.canalplus\.fr/.*?/(?P<path>.*)|player\.canalplus\.fr/#/(?P<id>\d+))'
+    _VALID_URL = r'https?://(?:www\.canalplus\.fr/.*?/(?P<path>.*)|player\.canalplus\.fr/#/(?P<id>[0-9]+))'
     _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/cplus/%s'
-    IE_NAME = u'canalplus.fr'
+    IE_NAME = 'canalplus.fr'
 
     _TEST = {
-        u'url': u'http://www.canalplus.fr/c-infos-documentaires/pid1830-c-zapping.html?vid=922470',
-        u'file': u'922470.flv',
-        u'info_dict': {
-            u'title': u'Zapping - 26/08/13',
-            u'description': u'Le meilleur de toutes les chaînes, tous les jours.\nEmission du 26 août 2013',
-            u'upload_date': u'20130826',
-        },
-        u'params': {
-            u'skip_download': True,
+        'url': 'http://www.canalplus.fr/c-infos-documentaires/pid1830-c-zapping.html?vid=922470',
+        'md5': '3db39fb48b9685438ecf33a1078023e4',
+        'info_dict': {
+            'id': '922470',
+            'ext': 'flv',
+            'title': 'Zapping - 26/08/13',
+            'description': 'Le meilleur de toutes les chaînes, tous les jours.\nEmission du 26 août 2013',
+            'upload_date': '20130826',
         },
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.groupdict().get('id')
+
+        # Beware, some subclasses do not define an id group
+        display_id = url_basename(mobj.group('path'))
+
         if video_id is None:
-            webpage = self._download_webpage(url, mobj.group('path'))
-            video_id = self._search_regex(r'videoId = "(\d+)";', webpage, u'video id')
+            webpage = self._download_webpage(url, display_id)
+            video_id = self._search_regex(r'<canal:player videoId="(\d+)"', webpage, 'video id')
+
         info_url = self._VIDEO_INFO_TEMPLATE % video_id
-        doc = self._download_xml(info_url,video_id, 
-                                           u'Downloading video info')
+        doc = self._download_xml(info_url, video_id, 'Downloading video XML')
 
-        self.report_extraction(video_id)
         video_info = [video for video in doc if video.find('ID').text == video_id][0]
-        infos = video_info.find('INFOS')
         media = video_info.find('MEDIA')
-        formats = [media.find('VIDEOS/%s' % format)
-            for format in ['BAS_DEBIT', 'HAUT_DEBIT', 'HD']]
-        video_url = [format.text for format in formats if format is not None][-1]
+        infos = video_info.find('INFOS')
 
-        return {'id': video_id,
-                'title': u'%s - %s' % (infos.find('TITRAGE/TITRE').text,
-                                       infos.find('TITRAGE/SOUS_TITRE').text),
-                'url': video_url,
-                'ext': 'flv',
-                'upload_date': unified_strdate(infos.find('PUBLICATION/DATE').text),
-                'thumbnail': media.find('IMAGES/GRAND').text,
-                'description': infos.find('DESCRIPTION').text,
-                'view_count': int(infos.find('NB_VUES').text),
-                }
+        preferences = ['MOBILE', 'BAS_DEBIT', 'HAUT_DEBIT', 'HD', 'HLS', 'HDS']
+
+        formats = [
+            {
+                'url': fmt.text + '?hdcore=2.11.3' if fmt.tag == 'HDS' else fmt.text,
+                'format_id': fmt.tag,
+                'ext': 'mp4' if fmt.tag == 'HLS' else 'flv',
+                'preference': preferences.index(fmt.tag) if fmt.tag in preferences else -1,
+            } for fmt in media.find('VIDEOS') if fmt.text
+        ]
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': '%s - %s' % (infos.find('TITRAGE/TITRE').text,
+                                  infos.find('TITRAGE/SOUS_TITRE').text),
+            'upload_date': unified_strdate(infos.find('PUBLICATION/DATE').text),
+            'thumbnail': media.find('IMAGES/GRAND').text,
+            'description': infos.find('DESCRIPTION').text,
+            'view_count': int(infos.find('NB_VUES').text),
+            'like_count': int(infos.find('NB_LIKES').text),
+            'comment_count': int(infos.find('NB_COMMENTS').text),
+            'formats': formats,
+        }

youtube_dl/extractor/cbsnews.py

@@ -0,0 +1,87 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import re
+import json
+
+from .common import InfoExtractor
+
+
+class CBSNewsIE(InfoExtractor):
+    IE_DESC = 'CBS News'
+    _VALID_URL = r'http://(?:www\.)?cbsnews\.com/(?:[^/]+/)+(?P<id>[\da-z_-]+)'
+
+    _TESTS = [
+        {
+            'url': 'http://www.cbsnews.com/news/tesla-and-spacex-elon-musks-industrial-empire/',
+            'info_dict': {
+                'id': 'tesla-and-spacex-elon-musks-industrial-empire',
+                'ext': 'flv',
+                'title': 'Tesla and SpaceX: Elon Musk\'s industrial empire',
+                'thumbnail': 'http://beta.img.cbsnews.com/i/2014/03/30/60147937-2f53-4565-ad64-1bdd6eb64679/60-0330-pelley-640x360.jpg',
+                'duration': 791,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+        },
+        {
+            'url': 'http://www.cbsnews.com/videos/fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack/',
+            'info_dict': {
+                'id': 'fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack',
+                'ext': 'flv',
+                'title': 'Fort Hood shooting: Army downplays mental illness as cause of attack',
+                'thumbnail': 'http://cbsnews2.cbsistatic.com/hub/i/r/2014/04/04/0c9fbc66-576b-41ca-8069-02d122060dd2/thumbnail/140x90/6dad7a502f88875ceac38202984b6d58/en-0404-werner-replace-640x360.jpg',
+                'duration': 205,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+        },
+    ]
+
+    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_info = json.loads(self._html_search_regex(
+            r'(?:<ul class="media-list items" id="media-related-items"><li data-video-info|<div id="cbsNewsVideoPlayer" data-video-player-options)=\'({.+?})\'',
+            webpage, 'video JSON info'))
+
+        item = video_info['item'] if 'item' in video_info else video_info
+        title = item.get('articleTitle') or item.get('hed')
+        duration = item.get('duration')
+        thumbnail = item.get('mediaImage') or item.get('thumbnail')
+
+        formats = []
+        for format_id in ['RtmpMobileLow', 'RtmpMobileHigh', 'Hls', 'RtmpDesktop']:
+            uri = item.get('media' + format_id + 'URI')
+            if not uri:
+                continue
+            fmt = {
+                'url': uri,
+                'format_id': format_id,
+            }
+            if uri.startswith('rtmp'):
+                fmt.update({
+                    'app': 'ondemand?auth=cbs',
+                    'play_path': 'mp4:' + uri.split('<break>')[-1],
+                    'player_url': 'http://www.cbsnews.com/[[IMPORT]]/vidtech.cbsinteractive.com/player/3_3_0/CBSI_PLAYER_HD.swf',
+                    'page_url': 'http://www.cbsnews.com',
+                    'ext': 'flv',
+                })
+            elif uri.endswith('.m3u8'):
+                fmt['ext'] = 'mp4'
+            formats.append(fmt)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'formats': formats,
+        }

youtube_dl/extractor/cinemassacre.py

@@ -9,12 +9,12 @@ from ..utils import (
 
 
 class CinemassacreIE(InfoExtractor):
-    _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})/.+?'
+    _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})/(?P<display_id>[^?#/]+)'
     _TESTS = [
         {
             'url': 'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/',
             'file': '19911.mp4',
-            'md5': 'fde81fbafaee331785f58cd6c0d46190',
+            'md5': '782f8504ca95a0eba8fc9177c373eec7',
             'info_dict': {
                 'upload_date': '20121110',
                 'title': '“Angry Video Game Nerd: The Movie” – Trailer',
@@ -24,7 +24,7 @@ class CinemassacreIE(InfoExtractor):
         {
             'url': 'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940',
             'file': '521be8ef82b16.mp4',
-            'md5': 'd72f10cd39eac4215048f62ab477a511',
+            'md5': 'dec39ee5118f8d9cc067f45f9cbe3a35',
             'info_dict': {
                 'upload_date': '20131002',
                 'title': 'The Mummy’s Hand (1940)',
@@ -34,8 +34,9 @@ class CinemassacreIE(InfoExtractor):
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
+        display_id = mobj.group('display_id')
 
-        webpage = self._download_webpage(url, None)  # Don't know video id yet
+        webpage = self._download_webpage(url, display_id)
         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:
@@ -43,33 +44,36 @@ class CinemassacreIE(InfoExtractor):
         playerdata_url = mobj.group('embed_url')
         video_id = mobj.group('video_id')
 
-        video_title = self._html_search_regex(r'<title>(?P<title>.+?)\|',
-            webpage, 'title')
-        video_description = self._html_search_regex(r'<div class="entry-content">(?P<description>.+?)</div>',
+        video_title = self._html_search_regex(
+            r'<title>(?P<title>.+?)\|', webpage, 'title')
+        video_description = self._html_search_regex(
+            r'<div class="entry-content">(?P<description>.+?)</div>',
             webpage, 'description', flags=re.DOTALL, fatal=False)
-        if len(video_description) == 0:
-            video_description = None
 
         playerdata = self._download_webpage(playerdata_url, video_id)
 
-        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')
+        sd_url = self._html_search_regex(r'file: \'([^\']+)\', label: \'SD\'', playerdata, 'sd_file')
+        hd_url = self._html_search_regex(
+            r'file: \'([^\']+)\', label: \'HD\'', playerdata, 'hd_file',
+            default=None)
         video_thumbnail = self._html_search_regex(r'image: \'(?P<thumbnail>[^\']+)\'', playerdata, 'thumbnail', fatal=False)
 
-        formats = [
-            {
-                'url': sd_url,
-                'ext': 'mp4',
-                'format': 'sd',
-                'format_id': 'sd',
-            },
-            {
+        formats = [{
+            'url': sd_url,
+            'ext': 'mp4',
+            'format': 'sd',
+            'format_id': 'sd',
+            'quality': 1,
+        }]
+        if hd_url:
+            formats.append({
                 'url': hd_url,
                 'ext': 'mp4',
                 'format': 'hd',
                 'format_id': 'hd',
-            },
-        ]
+                'quality': 2,
+            })
+        self._sort_formats(formats)
 
         return {
             'id': video_id,

youtube_dl/extractor/clipfish.py

@@ -1,22 +1,28 @@
+from __future__ import unicode_literals
+
 import re
 import time
 import xml.etree.ElementTree
 
 from .common import InfoExtractor
-from ..utils import ExtractorError
+from ..utils import (
+    ExtractorError,
+    parse_duration,
+)
 
 
 class ClipfishIE(InfoExtractor):
-    IE_NAME = u'clipfish'
+    IE_NAME = 'clipfish'
 
     _VALID_URL = r'^https?://(?:www\.)?clipfish\.de/.*?/video/(?P<id>[0-9]+)/'
     _TEST = {
-        u'url': u'http://www.clipfish.de/special/game-trailer/video/3966754/fifa-14-e3-2013-trailer/',
-        u'file': u'3966754.mp4',
-        u'md5': u'2521cd644e862936cf2e698206e47385',
-        u'info_dict': {
-            u'title': u'FIFA 14 - E3 2013 Trailer',
-            u'duration': 82,
+        'url': 'http://www.clipfish.de/special/game-trailer/video/3966754/fifa-14-e3-2013-trailer/',
+        'md5': '2521cd644e862936cf2e698206e47385',
+        'info_dict': {
+            'id': '3966754',
+            'ext': 'mp4',
+            'title': 'FIFA 14 - E3 2013 Trailer',
+            'duration': 82,
         },
         u'skip': 'Blocked in the US'
     }
@@ -33,21 +39,10 @@ class ClipfishIE(InfoExtractor):
         video_url = doc.find('filename').text
         if video_url is None:
             xml_bytes = xml.etree.ElementTree.tostring(doc)
-            raise ExtractorError(u'Cannot find video URL in document %r' %
+            raise ExtractorError('Cannot find video URL in document %r' %
                                  xml_bytes)
         thumbnail = doc.find('imageurl').text
-        duration_str = doc.find('duration').text
-        m = re.match(
-            r'^(?P<hours>[0-9]+):(?P<minutes>[0-9]{2}):(?P<seconds>[0-9]{2}):(?P<ms>[0-9]*)$',
-            duration_str)
-        if m:
-            duration = (
-                (int(m.group('hours')) * 60 * 60) +
-                (int(m.group('minutes')) * 60) +
-                (int(m.group('seconds')))
-            )
-        else:
-            duration = None
+        duration = parse_duration(doc.find('duration').text)
 
         return {
             'id': video_id,

youtube_dl/extractor/clipsyndicate.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -11,13 +13,14 @@ class ClipsyndicateIE(InfoExtractor):
     _VALID_URL = r'http://www\.clipsyndicate\.com/video/play(list/\d+)?/(?P<id>\d+)'
 
     _TEST = {
-        u'url': u'http://www.clipsyndicate.com/video/play/4629301/brick_briscoe',
-        u'md5': u'4d7d549451bad625e0ff3d7bd56d776c',
-        u'info_dict': {
-            u'id': u'4629301',
-            u'ext': u'mp4',
-            u'title': u'Brick Briscoe',
-            u'duration': 612,
+        'url': 'http://www.clipsyndicate.com/video/play/4629301/brick_briscoe',
+        'md5': '4d7d549451bad625e0ff3d7bd56d776c',
+        'info_dict': {
+            'id': '4629301',
+            'ext': 'mp4',
+            'title': 'Brick Briscoe',
+            'duration': 612,
+            'thumbnail': 're:^https?://.+\.jpg',
         },
     }
 
@@ -26,13 +29,13 @@ class ClipsyndicateIE(InfoExtractor):
         video_id = mobj.group('id')
         js_player = self._download_webpage(
             'http://eplayer.clipsyndicate.com/embed/player.js?va_id=%s' % video_id,
-            video_id, u'Downlaoding player')
+            video_id, 'Downlaoding player')
         # it includes a required token
-        flvars = self._search_regex(r'flvars: "(.*?)"', js_player, u'flvars')
+        flvars = self._search_regex(r'flvars: "(.*?)"', js_player, 'flvars')
 
         pdoc = self._download_xml(
             'http://eplayer.clipsyndicate.com/osmf/playlist?%s' % flvars,
-            video_id, u'Downloading video info',
+            video_id, 'Downloading video info',
             transform_source=fix_xml_ampersands)
 
         track_doc = pdoc.find('trackList/track')

youtube_dl/extractor/clubic.py

@@ -0,0 +1,58 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    qualities,
+)
+
+
+class ClubicIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?clubic\.com/video/[^/]+/video.*-(?P<id>[0-9]+)\.html'
+
+    _TEST = {
+        'url': 'http://www.clubic.com/video/clubic-week/video-clubic-week-2-0-le-fbi-se-lance-dans-la-photo-d-identite-448474.html',
+        'md5': '1592b694ba586036efac1776b0b43cd3',
+        'info_dict': {
+            'id': '448474',
+            'ext': 'mp4',
+            'title': 'Clubic Week 2.0 : le FBI se lance dans la photo d\u0092identité',
+            'description': 're:Gueule de bois chez Nokia. Le constructeur a indiqué cette.*',
+            'thumbnail': 're:^http://img\.clubic\.com/.*\.jpg$',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        player_url = 'http://player.m6web.fr/v1/player/clubic/%s.html' % video_id
+        player_page = self._download_webpage(player_url, video_id)
+
+        config_json = self._search_regex(
+            r'(?m)M6\.Player\.config\s*=\s*(\{.+?\});$', player_page,
+            'configuration')
+        config = json.loads(config_json)
+
+        video_info = config['videoInfo']
+        sources = config['sources']
+        quality_order = qualities(['sd', 'hq'])
+
+        formats = [{
+            'format_id': src['streamQuality'],
+            'url': src['src'],
+            'quality': quality_order(src['streamQuality']),
+        } for src in sources]
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': video_info['title'],
+            'formats': formats,
+            'description': clean_html(video_info.get('description')),
+            'thumbnail': config.get('poster'),
+        }

youtube_dl/extractor/cnet.py

@@ -0,0 +1,75 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+)
+
+
+class CNETIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?cnet\.com/videos/(?P<id>[^/]+)/'
+    _TEST = {
+        'url': 'http://www.cnet.com/videos/hands-on-with-microsofts-windows-8-1-update/',
+        'md5': '041233212a0d06b179c87cbcca1577b8',
+        'info_dict': {
+            'id': '56f4ea68-bd21-4852-b08c-4de5b8354c60',
+            'ext': 'mp4',
+            'title': 'Hands-on with Microsoft Windows 8.1 Update',
+            'description': 'The new update to the Windows 8 OS brings improved performance for mouse and keyboard users.',
+            'thumbnail': 're:^http://.*/flmswindows8.jpg$',
+            'uploader_id': 'sarah.mitroff@cbsinteractive.com',
+            'uploader': 'Sarah Mitroff',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        display_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, display_id)
+        data_json = self._html_search_regex(
+            r"<div class=\"cnetVideoPlayer\"\s+.*?data-cnet-video-options='([^']+)'",
+            webpage, 'data json')
+        data = json.loads(data_json)
+        vdata = data['video']
+        if not vdata:
+            vdata = data['videos'][0]
+        if not vdata:
+            raise ExtractorError('Cannot find video data')
+
+        video_id = vdata['id']
+        title = vdata['headline']
+        description = vdata.get('dek')
+        thumbnail = vdata.get('image', {}).get('path')
+        author = vdata.get('author')
+        if author:
+            uploader = '%s %s' % (author['firstName'], author['lastName'])
+            uploader_id = author.get('email')
+        else:
+            uploader = None
+            uploader_id = None
+
+        formats = [{
+            'format_id': '%s-%s-%s' % (
+                f['type'], f['format'],
+                int_or_none(f.get('bitrate'), 1000, default='')),
+            'url': f['uri'],
+            'tbr': int_or_none(f.get('bitrate'), 1000),
+        } for f in vdata['files']['data']]
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'formats': formats,
+            'description': description,
+            'uploader': uploader,
+            'uploader_id': uploader_id,
+            'thumbnail': thumbnail,
+        }

youtube_dl/extractor/comedycentral.py

@@ -7,8 +7,8 @@ from .mtv import MTVServicesInfoExtractor
 from ..utils import (
     compat_str,
     compat_urllib_parse,
-
     ExtractorError,
+    float_or_none,
     unified_strdate,
 )
 
@@ -21,7 +21,7 @@ class ComedyCentralIE(MTVServicesInfoExtractor):
 
     _TEST = {
         'url': 'http://www.comedycentral.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother',
-        'md5': '4167875aae411f903b751a21f357f1ee',
+        'md5': 'c4f48e9eda1b16dd10add0744344b6d8',
         'info_dict': {
             'id': 'cef0cbb3-e776-4bc9-b62e-8016deccb354',
             'ext': 'mp4',
@@ -32,31 +32,34 @@ class ComedyCentralIE(MTVServicesInfoExtractor):
 
 
 class ComedyCentralShowsIE(InfoExtractor):
-    IE_DESC = 'The Daily Show / Colbert Report'
+    IE_DESC = 'The Daily Show / The Colbert Report'
     # urls can be abbreviations like :thedailyshow or :colbert
     # urls for episodes like:
     # or urls for clips like: http://www.thedailyshow.com/watch/mon-december-10-2012/any-given-gun-day
     #                     or: http://www.colbertnation.com/the-colbert-report-videos/421667/november-29-2012/moon-shattering-news
     #                     or: http://www.colbertnation.com/the-colbert-report-collections/422008/festival-of-lights/79524
-    _VALID_URL = r"""^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport)
-                      |(https?://)?(www\.)?
-                          (?P<showname>thedailyshow|colbertnation)\.com/
-                         (full-episodes/(?P<episode>.*)|
+    _VALID_URL = r'''(?x)^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport)
+                      |https?://(:www\.)?
+                          (?P<showname>thedailyshow|thecolbertreport)\.(?:cc\.)?com/
+                         ((?:full-)?episodes/(?:[0-9a-z]{6}/)?(?P<episode>.*)|
                           (?P<clip>
-                              (the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?))
-                              |(watch/(?P<date>[^/]*)/(?P<tdstitle>.*)))|
+                              (?:(?:guests/[^/]+|videos|video-playlists|special-editions)/[^/]+/(?P<videotitle>[^/?#]+))
+                              |(the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?))
+                              |(watch/(?P<date>[^/]*)/(?P<tdstitle>.*))
+                          )|
                           (?P<interview>
-                              extended-interviews/(?P<interID>[0-9]+)/playlist_tds_extended_(?P<interview_title>.*?)/.*?)))
-                     $"""
+                              extended-interviews/(?P<interID>[0-9a-z]+)/(?:playlist_tds_extended_)?(?P<interview_title>.*?)(/.*?)?)))
+                     (?:[?#].*|$)'''
     _TEST = {
-        'url': 'http://www.thedailyshow.com/watch/thu-december-13-2012/kristen-stewart',
-        'file': '422212.mp4',
+        'url': 'http://thedailyshow.cc.com/watch/thu-december-13-2012/kristen-stewart',
         'md5': '4e2f5cb088a83cd8cdb7756132f9739d',
         'info_dict': {
-            "upload_date": "20121214",
-            "description": "Kristen Stewart",
-            "uploader": "thedailyshow",
-            "title": "thedailyshow-kristen-stewart part 1"
+            'id': 'ab9ab3e7-5a98-4dbe-8b21-551dc0523d55',
+            'ext': 'mp4',
+            'upload_date': '20121213',
+            'description': 'Kristen Stewart learns to let loose in "On the Road."',
+            'uploader': 'thedailyshow',
+            'title': 'thedailyshow kristen-stewart part 1',
         }
     }
 
@@ -79,11 +82,6 @@ class ComedyCentralShowsIE(InfoExtractor):
         '400': (384, 216),
     }
 
-    @classmethod
-    def suitable(cls, url):
-        """Receives a URL and returns True if suitable for this IE."""
-        return re.match(cls._VALID_URL, url, re.VERBOSE) is not None
-
     @staticmethod
     def _transform_rtmp_url(rtmp_video_url):
         m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp\.comedystor/.*)$', rtmp_video_url)
@@ -99,14 +97,16 @@ class ComedyCentralShowsIE(InfoExtractor):
 
         if mobj.group('shortname'):
             if mobj.group('shortname') in ('tds', 'thedailyshow'):
-                url = 'http://www.thedailyshow.com/full-episodes/'
+                url = 'http://thedailyshow.cc.com/full-episodes/'
             else:
-                url = 'http://www.colbertnation.com/full-episodes/'
+                url = 'http://thecolbertreport.cc.com/full-episodes/'
             mobj = re.match(self._VALID_URL, url, re.VERBOSE)
             assert mobj is not None
 
         if mobj.group('clip'):
-            if mobj.group('showname') == 'thedailyshow':
+            if mobj.group('videotitle'):
+                epTitle = mobj.group('videotitle')
+            elif mobj.group('showname') == 'thedailyshow':
                 epTitle = mobj.group('tdstitle')
             else:
                 epTitle = mobj.group('cntitle')
@@ -120,9 +120,9 @@ class ComedyCentralShowsIE(InfoExtractor):
                 epTitle = mobj.group('showname')
             else:
                 epTitle = mobj.group('episode')
+        show_name = mobj.group('showname')
 
-        self.report_extraction(epTitle)
-        webpage,htmlHandle = self._download_webpage_handle(url, epTitle)
+        webpage, htmlHandle = self._download_webpage_handle(url, epTitle)
         if dlNewest:
             url = htmlHandle.geturl()
             mobj = re.match(self._VALID_URL, url, re.VERBOSE)
@@ -130,71 +130,86 @@ class ComedyCentralShowsIE(InfoExtractor):
                 raise ExtractorError('Invalid redirected URL: ' + url)
             if mobj.group('episode') == '':
                 raise ExtractorError('Redirected URL is still not specific: ' + url)
-            epTitle = mobj.group('episode')
+            epTitle = mobj.group('episode').rpartition('/')[-1]
 
         mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*(?:episode|video).*?:.*?))"', webpage)
-
         if len(mMovieParams) == 0:
             # The Colbert Report embeds the information in a without
             # a URL prefix; so extract the alternate reference
             # and then add the URL prefix manually.
 
-            altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video).*?:.*?)"', webpage)
+            altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video|playlist).*?:.*?)"', webpage)
             if len(altMovieParams) == 0:
                 raise ExtractorError('unable to find Flash URL in webpage ' + url)
             else:
                 mMovieParams = [("http://media.mtvnservices.com/" + altMovieParams[0], altMovieParams[0])]
 
         uri = mMovieParams[0][1]
-        indexUrl = 'http://shadow.comedycentral.com/feeds/video_player/mrss/?' + compat_urllib_parse.urlencode({'uri': uri})
-        idoc = self._download_xml(indexUrl, epTitle,
-                                          'Downloading show index',
-                                          'unable to download episode index')
+        # Correct cc.com in uri
+        uri = re.sub(r'(episode:[^.]+)(\.cc)?\.com', r'\1.cc.com', uri)
 
-        results = []
+        index_url = 'http://%s.cc.com/feeds/mrss?%s' % (show_name, compat_urllib_parse.urlencode({'uri': uri}))
+        idoc = self._download_xml(
+            index_url, epTitle,
+            'Downloading show index', 'Unable to download episode index')
 
-        itemEls = idoc.findall('.//item')
-        for partNum,itemEl in enumerate(itemEls):
-            mediaId = itemEl.findall('./guid')[0].text
-            shortMediaId = mediaId.split(':')[-1]
-            showId = mediaId.split(':')[-2].replace('.com', '')
-            officialTitle = itemEl.findall('./title')[0].text
-            officialDate = unified_strdate(itemEl.findall('./pubDate')[0].text)
+        title = idoc.find('./channel/title').text
+        description = idoc.find('./channel/description').text
 
-            configUrl = ('http://www.comedycentral.com/global/feeds/entertainment/media/mediaGenEntertainment.jhtml?' +
-                        compat_urllib_parse.urlencode({'uri': mediaId}))
-            cdoc = self._download_xml(configUrl, epTitle,
-                                               'Downloading configuration for %s' % shortMediaId)
+        entries = []
+        item_els = idoc.findall('.//item')
+        for part_num, itemEl in enumerate(item_els):
+            upload_date = unified_strdate(itemEl.findall('./pubDate')[0].text)
+            thumbnail = itemEl.find('.//{http://search.yahoo.com/mrss/}thumbnail').attrib.get('url')
+
+            content = itemEl.find('.//{http://search.yahoo.com/mrss/}content')
+            duration = float_or_none(content.attrib.get('duration'))
+            mediagen_url = content.attrib['url']
+            guid = itemEl.find('./guid').text.rpartition(':')[-1]
+
+            cdoc = self._download_xml(
+                mediagen_url, epTitle,
+                'Downloading configuration for segment %d / %d' % (part_num + 1, len(item_els)))
 
             turls = []
             for rendition in cdoc.findall('.//rendition'):
                 finfo = (rendition.attrib['bitrate'], rendition.findall('./src')[0].text)
                 turls.append(finfo)
 
-            if len(turls) == 0:
-                self._downloader.report_error('unable to download ' + mediaId + ': No videos found')
-                continue
-
             formats = []
             for format, rtmp_video_url in turls:
                 w, h = self._video_dimensions.get(format, (None, None))
                 formats.append({
+                    'format_id': 'vhttp-%s' % format,
                     'url': self._transform_rtmp_url(rtmp_video_url),
                     'ext': self._video_extensions.get(format, 'mp4'),
-                    'format_id': format,
                     'height': h,
                     'width': w,
                 })
+                formats.append({
+                    'format_id': 'rtmp-%s' % format,
+                    'url': rtmp_video_url,
+                    'ext': self._video_extensions.get(format, 'mp4'),
+                    'height': h,
+                    'width': w,
+                })
+                self._sort_formats(formats)
 
-            effTitle = showId + '-' + epTitle + ' part ' + compat_str(partNum+1)
-            results.append({
-                'id': shortMediaId,
+            virtual_id = show_name + ' ' + epTitle + ' part ' + compat_str(part_num + 1)
+            entries.append({
+                'id': guid,
+                'title': virtual_id,
                 'formats': formats,
-                'uploader': showId,
-                'upload_date': officialDate,
-                'title': effTitle,
-                'thumbnail': None,
-                'description': compat_str(officialTitle),
+                'uploader': show_name,
+                'upload_date': upload_date,
+                'duration': duration,
+                'thumbnail': thumbnail,
+                'description': description,
             })
 
-        return results
+        return {
+            '_type': 'playlist',
+            'entries': entries,
+            'title': show_name + ' ' + title,
+            'description': description,
+        }

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
@@ -251,7 +251,21 @@ class InfoExtractor(object):
             with open(filename, 'wb') as outf:
                 outf.write(webpage_bytes)
 
-        content = webpage_bytes.decode(encoding, 'replace')
+        try:
+            content = webpage_bytes.decode(encoding, 'replace')
+        except LookupError:
+            content = webpage_bytes.decode('utf-8', 'replace')
+
+        if (u'<title>Access to this site is blocked</title>' in content and
+                u'Websense' in content[:512]):
+            msg = u'Access to this webpage has been blocked by Websense filtering software in your network.'
+            blocked_iframe = self._html_search_regex(
+                r'<iframe src="([^"]+)"', content,
+                u'Websense information URL', default=None)
+            if blocked_iframe:
+                msg += u' Visit %s for more details' % blocked_iframe
+            raise ExtractorError(msg, expected=True)
+
         return (content, urlh)
 
     def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True):
@@ -265,9 +279,12 @@ class InfoExtractor(object):
 
     def _download_xml(self, url_or_request, video_id,
                       note=u'Downloading XML', errnote=u'Unable to download XML',
-                      transform_source=None):
+                      transform_source=None, fatal=True):
         """Return the xml as an xml.etree.ElementTree.Element"""
-        xml_string = self._download_webpage(url_or_request, video_id, note, errnote)
+        xml_string = self._download_webpage(
+            url_or_request, video_id, note, errnote, fatal=fatal)
+        if xml_string is False:
+            return xml_string
         if transform_source:
             xml_string = transform_source(xml_string)
         return xml.etree.ElementTree.fromstring(xml_string.encode('utf-8'))
@@ -531,6 +548,13 @@ class InfoExtractor(object):
             )
         formats.sort(key=_formats_key)
 
+    def http_scheme(self):
+        """ Either "https:" or "https:", depending on the user's preferences """
+        return (
+            'http:'
+            if self._downloader.params.get('prefer_insecure', False)
+            else 'https:')
+
 
 class SearchInfoExtractor(InfoExtractor):
     """
@@ -574,3 +598,4 @@ class SearchInfoExtractor(InfoExtractor):
     @property
     def SEARCH_KEY(self):
         return self._SEARCH_KEY
+

youtube_dl/extractor/condenast.py

@@ -28,16 +28,18 @@ class CondeNastIE(InfoExtractor):
         'glamour': 'Glamour',
         'wmagazine': 'W Magazine',
         'vanityfair': 'Vanity Fair',
+        'cnevids': 'Condé Nast',
     }
 
-    _VALID_URL = r'http://(video|www)\.(?P<site>%s)\.com/(?P<type>watch|series|video)/(?P<id>.+)' % '|'.join(_SITES.keys())
+    _VALID_URL = r'http://(video|www|player)\.(?P<site>%s)\.com/(?P<type>watch|series|video|embed)/(?P<id>[^/?#]+)' % '|'.join(_SITES.keys())
     IE_DESC = 'Condé Nast media group: %s' % ', '.join(sorted(_SITES.values()))
 
     _TEST = {
         'url': 'http://video.wired.com/watch/3d-printed-speakers-lit-with-led',
-        'file': '5171b343c2b4c00dd0c1ccb3.mp4',
         'md5': '1921f713ed48aabd715691f774c451f7',
         'info_dict': {
+            'id': '5171b343c2b4c00dd0c1ccb3',
+            'ext': 'mp4',
             'title': '3D Printed Speakers Lit With LED',
             'description': 'Check out these beautiful 3D printed LED speakers.  You can\'t actually buy them, but LumiGeek is working on a board that will let you make you\'re own.',
         }
@@ -55,12 +57,16 @@ class CondeNastIE(InfoExtractor):
         entries = [self.url_result(build_url(path), 'CondeNast') for path in paths]
         return self.playlist_result(entries, playlist_title=title)
 
-    def _extract_video(self, webpage):
-        description = self._html_search_regex([r'<div class="cne-video-description">(.+?)</div>',
-                                               r'<div class="video-post-content">(.+?)</div>',
-                                               ],
-                                              webpage, 'description',
-                                              fatal=False, flags=re.DOTALL)
+    def _extract_video(self, webpage, url_type):
+        if url_type != 'embed':
+            description = self._html_search_regex(
+                [
+                    r'<div class="cne-video-description">(.+?)</div>',
+                    r'<div class="video-post-content">(.+?)</div>',
+                ],
+                webpage, 'description', fatal=False, flags=re.DOTALL)
+        else:
+            description = None
         params = self._search_regex(r'var params = {(.+?)}[;,]', webpage,
                                     'player params', flags=re.DOTALL)
         video_id = self._search_regex(r'videoId: [\'"](.+?)[\'"]', params, 'video id')
@@ -99,12 +105,12 @@ class CondeNastIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         site = mobj.group('site')
         url_type = mobj.group('type')
-        id = mobj.group('id')
+        item_id = mobj.group('id')
 
-        self.to_screen(u'Extracting from %s with the Condé Nast extractor' % self._SITES[site])
-        webpage = self._download_webpage(url, id)
+        self.to_screen('Extracting from %s with the Condé Nast extractor' % self._SITES[site])
+        webpage = self._download_webpage(url, item_id)
 
         if url_type == 'series':
             return self._extract_series(url, webpage)
         else:
-            return self._extract_video(webpage)
+            return self._extract_video(webpage, url_type)

youtube_dl/extractor/cspan.py

@@ -4,15 +4,16 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
+    int_or_none,
     unescapeHTML,
     find_xpath_attr,
 )
 
 
 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 +23,24 @@ 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(
             [
@@ -43,18 +55,29 @@ class CSpanIE(InfoExtractor):
         info_url = 'http://c-spanvideo.org/videoLibrary/assets/player/ajax-player.php?os=android&html5=program&id=' + video_id
         data = self._download_json(info_url, video_id)
 
-        url = unescapeHTML(data['video']['files'][0]['path']['#text'])
-
-        doc = self._download_xml('http://www.c-span.org/common/services/flashXml.php?programid=' + video_id,
+        doc = self._download_xml(
+            'http://www.c-span.org/common/services/flashXml.php?programid=' + video_id,
             video_id)
 
-        def find_string(s):
-            return find_xpath_attr(doc, './/string', 'name', s).text
+        title = find_xpath_attr(doc, './/string', 'name', 'title').text
+        thumbnail = find_xpath_attr(doc, './/string', 'name', 'poster').text
+
+        files = data['video']['files']
+
+        entries = [{
+            'id': '%s_%d' % (video_id, partnum + 1),
+            'title': (
+                title if len(files) == 1 else
+                '%s part %d' % (title, partnum + 1)),
+            'url': unescapeHTML(f['path']['#text']),
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': int_or_none(f.get('length', {}).get('#text')),
+        } for partnum, f in enumerate(files)]
 
         return {
+            '_type': 'playlist',
+            'entries': entries,
+            'title': title,
             'id': video_id,
-            'title': find_string('title'),
-            'url': url,
-            'description': description,
-            'thumbnail': find_string('poster'),
         }

youtube_dl/extractor/dailymotion.py

@@ -8,13 +8,11 @@ from .subtitles import SubtitlesInfoExtractor
 from ..utils import (
     compat_urllib_request,
     compat_str,
-    get_element_by_attribute,
-    get_element_by_id,
     orderedSet,
     str_to_int,
     int_or_none,
-
     ExtractorError,
+    unescapeHTML,
 )
 
 class DailymotionBaseInfoExtractor(InfoExtractor):
@@ -180,7 +178,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
 class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
     IE_NAME = u'dailymotion:playlist'
     _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P<id>.+?)/'
-    _MORE_PAGES_INDICATOR = r'<div class="next">.*?<a.*?href="/playlist/.+?".*?>.*?</a>.*?</div>'
+    _MORE_PAGES_INDICATOR = r'(?s)<div class="pages[^"]*">.*?<a\s+class="[^"]*?icon-arrow_right[^"]*?"'
     _PAGE_TEMPLATE = 'https://www.dailymotion.com/playlist/%s/%s'
 
     def _extract_entries(self, id):
@@ -190,10 +188,9 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
             webpage = self._download_webpage(request,
                                              id, u'Downloading page %s' % pagenum)
 
-            playlist_el = get_element_by_attribute(u'class', u'row video_list', webpage)
-            video_ids.extend(re.findall(r'data-id="(.+?)"', playlist_el))
+            video_ids.extend(re.findall(r'data-xid="(.+?)"', webpage))
 
-            if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
+            if re.search(self._MORE_PAGES_INDICATOR, webpage) is None:
                 break
         return [self.url_result('http://www.dailymotion.com/video/%s' % video_id, 'Dailymotion')
                    for video_id in orderedSet(video_ids)]
@@ -203,26 +200,26 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
         playlist_id = mobj.group('id')
         webpage = self._download_webpage(url, playlist_id)
 
-        return {'_type': 'playlist',
-                'id': playlist_id,
-                'title': get_element_by_id(u'playlist_name', webpage),
-                'entries': self._extract_entries(playlist_id),
-                }
+        return {
+            '_type': 'playlist',
+            'id': playlist_id,
+            'title': self._og_search_title(webpage),
+            'entries': self._extract_entries(playlist_id),
+        }
 
 
 class DailymotionUserIE(DailymotionPlaylistIE):
     IE_NAME = u'dailymotion:user'
-    _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/user/(?P<user>[^/]+)'
-    _MORE_PAGES_INDICATOR = r'<div class="next">.*?<a.*?href="/user/.+?".*?>.*?</a>.*?</div>'
+    _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/user/(?P<user>[^/]+)'
     _PAGE_TEMPLATE = 'http://www.dailymotion.com/user/%s/%s'
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         user = mobj.group('user')
         webpage = self._download_webpage(url, user)
-        full_user = self._html_search_regex(
-            r'<a class="label" href="/%s".*?>(.*?)</' % re.escape(user),
-            webpage, u'user', flags=re.DOTALL)
+        full_user = unescapeHTML(self._html_search_regex(
+            r'<a class="nav-image" title="([^"]+)" href="/%s">' % re.escape(user),
+            webpage, u'user', flags=re.DOTALL))
 
         return {
             '_type': 'playlist',

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/discovery.py

@@ -10,9 +10,10 @@ class DiscoveryIE(InfoExtractor):
     _VALID_URL = r'http://dsc\.discovery\.com\/[a-zA-Z0-9\-]*/[a-zA-Z0-9\-]*/videos/(?P<id>[a-zA-Z0-9\-]*)(.htm)?'
     _TEST = {
         'url': 'http://dsc.discovery.com/tv-shows/mythbusters/videos/mission-impossible-outtakes.htm',
-        'file': '614784.mp4',
         'md5': 'e12614f9ee303a6ccef415cb0793eba2',
         'info_dict': {
+            'id': '614784',
+            'ext': 'mp4',
             'title': 'MythBusters: Mission Impossible Outtakes',
             'description': ('Watch Jamie Hyneman and Adam Savage practice being'
                 ' each other -- to the point of confusing Jamie\'s dog -- and '
@@ -34,7 +35,7 @@ class DiscoveryIE(InfoExtractor):
         formats = []
         for f in info['mp4']:
             formats.append(
-                {'url': f['src'], r'ext': r'mp4', 'tbr': int(f['bitrate'][:-1])})
+                {'url': f['src'], 'ext': 'mp4', 'tbr': int(f['bitrate'][:-1])})
 
         return {
             'id': info['contentId'],

youtube_dl/extractor/divxstage.py

@@ -0,0 +1,27 @@
+from __future__ import unicode_literals
+
+from .novamov import NovaMovIE
+
+
+class DivxStageIE(NovaMovIE):
+    IE_NAME = 'divxstage'
+    IE_DESC = 'DivxStage'
+
+    _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'divxstage\.(?:eu|net|ch|co|at|ag)'}
+
+    _HOST = 'www.divxstage.eu'
+
+    _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
+    _TITLE_REGEX = r'<div class="video_det">\s*<strong>([^<]+)</strong>'
+    _DESCRIPTION_REGEX = r'<div class="video_det">\s*<strong>[^<]+</strong>\s*<p>([^<]+)</p>'
+
+    _TEST = {
+        'url': 'http://www.divxstage.eu/video/57f238e2e5e01',
+        'md5': '63969f6eb26533a1968c4d325be63e72',
+        'info_dict': {
+            'id': '57f238e2e5e01',
+            'ext': 'flv',
+            'title': 'youtubedl test video',
+            'description': 'This is a test video for youtubedl.',
+        }
+    }

youtube_dl/extractor/ehow.py

@@ -1,23 +1,25 @@
+from __future__ import unicode_literals
+
 import re
 
 from ..utils import (
     compat_urllib_parse,
-    determine_ext
 )
 from .common import InfoExtractor
 
 
 class EHowIE(InfoExtractor):
-    IE_NAME = u'eHow'
-    _VALID_URL = r'(?:https?://)?(?:www\.)?ehow\.com/[^/_?]*_(?P<id>[0-9]+)'
+    IE_NAME = 'eHow'
+    _VALID_URL = r'https?://(?:www\.)?ehow\.com/[^/_?]*_(?P<id>[0-9]+)'
     _TEST = {
-        u'url': u'http://www.ehow.com/video_12245069_hardwood-flooring-basics.html',
-        u'file': u'12245069.flv',
-        u'md5': u'9809b4e3f115ae2088440bcb4efbf371',
-        u'info_dict': {
-            u"title": u"Hardwood Flooring Basics",
-            u"description": u"Hardwood flooring may be time consuming, but its ultimately a pretty straightforward concept. Learn about hardwood flooring basics with help from a hardware flooring business owner in this free video...",
-   			u"uploader": u"Erick Nathan"
+        'url': 'http://www.ehow.com/video_12245069_hardwood-flooring-basics.html',
+        'md5': '9809b4e3f115ae2088440bcb4efbf371',
+        'info_dict': {
+            'id': '12245069',
+            'ext': 'flv',
+            'title': 'Hardwood Flooring Basics',
+            'description': 'Hardwood flooring may be time consuming, but its ultimately a pretty straightforward concept. Learn about hardwood flooring basics with help from a hardware flooring business owner in this free video...',
+            'uploader': 'Erick Nathan',
         }
     }
 
@@ -26,21 +28,16 @@ class EHowIE(InfoExtractor):
         video_id = mobj.group('id')
         webpage = self._download_webpage(url, video_id)
         video_url = self._search_regex(r'(?:file|source)=(http[^\'"&]*)',
-            webpage, u'video URL')
-        final_url = compat_urllib_parse.unquote(video_url)        
-        uploader = self._search_regex(r'<meta name="uploader" content="(.+?)" />',
-            webpage, u'uploader')
+            webpage, 'video URL')
+        final_url = compat_urllib_parse.unquote(video_url)
+        uploader = self._html_search_meta('uploader', webpage)
         title = self._og_search_title(webpage).replace(' | eHow', '')
-        ext = determine_ext(final_url)
 
         return {
-            '_type':       'video',
-            'id':          video_id,
-            'url':         final_url,
-            'ext':         ext,
-            'title':       title,
-            'thumbnail':   self._og_search_thumbnail(webpage),
+            'id': video_id,
+            'url': final_url,
+            'title': title,
+            'thumbnail': self._og_search_thumbnail(webpage),
             'description': self._og_search_description(webpage),
-            'uploader':    uploader,
+            'uploader': uploader,
         }
-

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/extremetube.py

@@ -1,4 +1,5 @@
-import os
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -8,18 +9,23 @@ from ..utils import (
     compat_urllib_parse,
 )
 
+
 class ExtremeTubeIE(InfoExtractor):
-    _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>extremetube\.com/video/.+?(?P<videoid>[0-9]+))(?:[/?&]|$)'
-    _TEST = {
-        u'url': u'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431',
-        u'file': u'652431.mp4',
-        u'md5': u'1fb9228f5e3332ec8c057d6ac36f33e0',
-        u'info_dict': {
-            u"title": u"Music Video 14 british euro brit european cumshots swallow",
-            u"uploader": u"unknown",
-            u"age_limit": 18,
+    _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>extremetube\.com/.*?video/.+?(?P<videoid>[0-9]+))(?:[/?&]|$)'
+    _TESTS = [{
+        'url': 'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431',
+        'md5': '1fb9228f5e3332ec8c057d6ac36f33e0',
+        'info_dict': {
+            'id': '652431',
+            'ext': 'mp4',
+            'title': 'Music Video 14 british euro brit european cumshots swallow',
+            'uploader': 'unknown',
+            'age_limit': 18,
         }
-    }
+    }, {
+        'url': 'http://www.extremetube.com/gay/video/abcde-1234',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -30,11 +36,14 @@ class ExtremeTubeIE(InfoExtractor):
         req.add_header('Cookie', 'age_verified=1')
         webpage = self._download_webpage(req, video_id)
 
-        video_title = self._html_search_regex(r'<h1 [^>]*?title="([^"]+)"[^>]*>\1<', webpage, u'title')
-        uploader = self._html_search_regex(r'>Posted by:(?=<)(?:\s|<[^>]*>)*(.+?)\|', webpage, u'uploader', fatal=False)
-        video_url = compat_urllib_parse.unquote(self._html_search_regex(r'video_url=(.+?)&amp;', webpage, u'video_url'))
+        video_title = self._html_search_regex(
+            r'<h1 [^>]*?title="([^"]+)"[^>]*>\1<', webpage, 'title')
+        uploader = self._html_search_regex(
+            r'>Posted by:(?=<)(?:\s|<[^>]*>)*(.+?)\|', webpage, 'uploader',
+            fatal=False)
+        video_url = compat_urllib_parse.unquote(self._html_search_regex(
+            r'video_url=(.+?)&amp;', webpage, 'video_url'))
         path = compat_urllib_parse_urlparse(video_url).path
-        extension = os.path.splitext(path)[1][1:]
         format = path.split('/')[5].split('_')[:2]
         format = "-".join(format)
 
@@ -43,7 +52,6 @@ class ExtremeTubeIE(InfoExtractor):
             'title': video_title,
             'uploader': uploader,
             'url': video_url,
-            'ext': extension,
             'format': format,
             'format_id': format,
             'age_limit': 18,

youtube_dl/extractor/facebook.py

@@ -76,9 +76,8 @@ class FacebookIE(InfoExtractor):
 
             check_form = {
                 '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'),
+                'h': self._search_regex(r'name="h" value="(\w*?)"', login_results, 'h'),
                 'name_action_selected': 'dont_save',
-                'submit[Continue]': self._search_regex(r'<button[^>]+value="(.*?)"[^>]+name="submit\[Continue\]"', login_results, 'continue'),
             }
             check_req = compat_urllib_request.Request(self._CHECKPOINT_URL, urlencode_postdata(check_form))
             check_req.add_header('Content-Type', 'application/x-www-form-urlencoded')

youtube_dl/extractor/firstpost.py

@@ -6,7 +6,6 @@ from .common import InfoExtractor
 
 
 class FirstpostIE(InfoExtractor):
-    IE_NAME = 'Firstpost.com'
     _VALID_URL = r'http://(?:www\.)?firstpost\.com/[^/]+/.*-(?P<id>[0-9]+)\.html'
 
     _TEST = {
@@ -16,7 +15,6 @@ class FirstpostIE(InfoExtractor):
             'id': '1025403',
             'ext': 'mp4',
             'title': 'India to launch indigenous aircraft carrier INS Vikrant today',
-            'description': 'Its flight deck is over twice the size of a football field, its power unit can light up the entire Kochi city and the cabling is enough to cover the distance between here to Delhi.',
         }
     }
 
@@ -24,15 +22,26 @@ class FirstpostIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
 
-        webpage = self._download_webpage(url, video_id)
-        video_url = self._html_search_regex(
-            r'<div.*?name="div_video".*?flashvars="([^"]+)">',
-            webpage, 'video URL')
+        data = self._download_xml(
+            'http://www.firstpost.com/getvideoxml-%s.xml' % video_id, video_id,
+            'Downloading video XML')
+
+        item = data.find('./playlist/item')
+        thumbnail = item.find('./image').text
+        title = item.find('./title').text
+
+        formats = [
+            {
+                'url': details.find('./file').text,
+                'format_id': details.find('./label').text.strip(),
+                'width': int(details.find('./width').text.strip()),
+                'height': int(details.find('./height').text.strip()),
+            } for details in item.findall('./source/file_details') if details.find('./file').text
+        ]
 
         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),
+            'title': title,
+            'thumbnail': thumbnail,
+            'formats': formats,
         }

youtube_dl/extractor/fivemin.py

@@ -0,0 +1,88 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_str,
+    compat_urllib_parse,
+    ExtractorError,
+)
+
+
+class FiveMinIE(InfoExtractor):
+    IE_NAME = '5min'
+    _VALID_URL = r'''(?x)
+        (?:https?://[^/]*?5min\.com/Scripts/PlayerSeed\.js\?(.*?&)?playList=|
+            5min:)
+        (?P<id>\d+)
+        '''
+
+    _TESTS = [
+        {
+            # 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',
+            },
+        },
+        {
+            # From http://on.aol.com/video/how-to-make-a-next-level-fruit-salad-518086247
+            'url': '5min:518086247',
+            'md5': 'e539a9dd682c288ef5a498898009f69e',
+            'info_dict': {
+                'id': '518086247',
+                'ext': 'mp4',
+                'title': 'How to Make a Next-Level Fruit Salad',
+            },
+        },
+    ]
+
+    @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')
+        embed_url = 'https://embed.5min.com/playerseed/?playList=%s' % video_id
+        embed_page = self._download_webpage(embed_url, video_id,
+            'Downloading embed page')
+        sid = self._search_regex(r'sid=(\d+)', embed_page, 'sid')
+        query = compat_urllib_parse.urlencode({
+            'func': 'GetResults',
+            'playlist': video_id,
+            'sid': sid,
+            'isPlayerSeed': 'true',
+            'url': embed_url,
+        })
+        response = self._download_json(
+            'https://syn.5min.com/handlers/SenseHandler.ashx?' + query,
+            video_id)
+        if not response['success']:
+            err_msg = response['errorMessage']
+            if err_msg == 'ErrorVideoUserNotGeo':
+                msg = 'Video not available from your location'
+            else:
+                msg = 'Aol said: %s' % err_msg
+            raise ExtractorError(msg, expected=True, video_id=video_id)
+        info = response['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/franceculture.py

@@ -0,0 +1,77 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_parse_qs,
+    compat_urlparse,
+)
+
+
+class FranceCultureIE(InfoExtractor):
+    _VALID_URL = r'(?P<baseurl>http://(?:www\.)?franceculture\.fr/)player/reecouter\?play=(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://www.franceculture.fr/player/reecouter?play=4795174',
+        'info_dict': {
+            'id': '4795174',
+            'ext': 'mp3',
+            'title': 'Rendez-vous au pays des geeks',
+            'vcodec': 'none',
+            'uploader': 'Colette Fellous',
+            'upload_date': '20140301',
+            'duration': 3601,
+            'thumbnail': r're:^http://www\.franceculture\.fr/.*/images/player/Carnet-nomade\.jpg$',
+            'description': 'Avec :Jean-Baptiste Péretié pour son documentaire sur Arte "La revanche des « geeks », une enquête menée aux Etats-Unis dans la S ...',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        baseurl = mobj.group('baseurl')
+
+        webpage = self._download_webpage(url, video_id)
+        params_code = self._search_regex(
+            r"<param name='movie' value='/sites/all/modules/rf/rf_player/swf/loader.swf\?([^']+)' />",
+            webpage, 'parameter code')
+        params = compat_parse_qs(params_code)
+        video_url = compat_urlparse.urljoin(baseurl, params['urlAOD'][0])
+
+        title = self._html_search_regex(
+            r'<h1 class="title[^"]+">(.+?)</h1>', webpage, 'title')
+        uploader = self._html_search_regex(
+            r'(?s)<div id="emission".*?<span class="author">(.*?)</span>',
+            webpage, 'uploader', fatal=False)
+        thumbnail_part = self._html_search_regex(
+            r'(?s)<div id="emission".*?<img src="([^"]+)"', webpage,
+            'thumbnail', fatal=False)
+        if thumbnail_part is None:
+            thumbnail = None
+        else:
+            thumbnail = compat_urlparse.urljoin(baseurl, thumbnail_part)
+        description = self._html_search_regex(
+            r'(?s)<p class="desc">(.*?)</p>', webpage, 'description')
+
+        info = json.loads(params['infoData'][0])[0]
+        duration = info.get('media_length')
+        upload_date_candidate = info.get('media_section5')
+        upload_date = (
+            upload_date_candidate
+            if (upload_date_candidate is not None and
+                re.match(r'[0-9]{8}$', upload_date_candidate))
+            else None)
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'vcodec': 'none' if video_url.lower().endswith('.mp3') else None,
+            'duration': duration,
+            'uploader': uploader,
+            'upload_date': upload_date,
+            'title': title,
+            'thumbnail': thumbnail,
+            'description': description,
+        }

youtube_dl/extractor/funnyordie.py

@@ -4,22 +4,32 @@ import json
 import re
 
 from .common import InfoExtractor
+from ..utils import ExtractorError
 
 
 class FunnyOrDieIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?funnyordie\.com/(?P<type>embed|videos)/(?P<id>[0-9a-f]+)(?:$|[?#/])'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.funnyordie.com/videos/0732f586d7/heart-shaped-box-literal-video-version',
-        'file': '0732f586d7.mp4',
-        'md5': 'f647e9e90064b53b6e046e75d0241fbd',
+        'md5': 'bcd81e0c4f26189ee09be362ad6e6ba9',
         'info_dict': {
-            'description': ('Lyrics changed to match the video. Spoken cameo '
-                'by Obscurus Lupa (from ThatGuyWithTheGlasses.com). Based on a '
-                'concept by Dustin McLean (DustFilms.com). Performed, edited, '
-                'and written by David A. Scott.'),
+            'id': '0732f586d7',
+            'ext': 'mp4',
             'title': 'Heart-Shaped Box: Literal Video Version',
+            'description': 'md5:ea09a01bc9a1c46d9ab696c01747c338',
+            'thumbnail': 're:^http:.*\.jpg$',
         },
-    }
+    }, {
+        'url': 'http://www.funnyordie.com/embed/e402820827',
+        'md5': 'ff4d83318f89776ed0250634cfaa8d36',
+        'info_dict': {
+            'id': 'e402820827',
+            'ext': 'mp4',
+            'title': 'Please Use This Song (Jon Lajoie)',
+            'description': 'md5:2ed27d364f5a805a6dba199faaf6681d',
+            'thumbnail': 're:^http:.*\.jpg$',
+        },
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -27,27 +37,34 @@ class FunnyOrDieIE(InfoExtractor):
         video_id = mobj.group('id')
         webpage = self._download_webpage(url, video_id)
 
-        video_url = self._search_regex(
-            [r'type="video/mp4" src="(.*?)"', r'src="([^>]*?)" type=\'video/mp4\''],
-            webpage, 'video URL', flags=re.DOTALL)
+        links = re.findall(r'<source src="([^"]+/v)\d+\.([^"]+)" type=\'video', webpage)
+        if not links:
+            raise ExtractorError('No media links available for %s' % video_id)
 
-        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
+        links.sort(key=lambda link: 1 if link[1] == 'mp4' else 0)
+
+        bitrates = self._html_search_regex(r'<source src="[^"]+/v,((?:\d+,)+)\.mp4\.csmil', webpage, 'video bitrates')
+        bitrates = [int(b) for b in bitrates.rstrip(',').split(',')]
+        bitrates.sort()
+
+        formats = []
+
+        for bitrate in bitrates:
+            for link in links:
+                formats.append({
+                    'url': '%s%d.%s' % (link[0], bitrate, link[1]),
+                    'format_id': '%s-%d' % (link[1], bitrate),
+                    'vbr': bitrate,
+                })
+
+        post_json = self._search_regex(
+            r'fb_post\s*=\s*(\{.*?\});', webpage, 'post details')
+        post = json.loads(post_json)
 
         return {
             'id': video_id,
-            'url': video_url,
-            'ext': 'mp4',
-            'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
+            'title': post['name'],
+            'description': post.get('description'),
+            'thumbnail': post.get('picture'),
+            'formats': formats,
         }

youtube_dl/extractor/generic.py

@@ -25,6 +25,7 @@ from ..utils import (
 from .brightcove import BrightcoveIE
 from .ooyala import OoyalaIE
 from .rutv import RUTVIE
+from .smotri import SmotriIE
 
 
 class GenericIE(InfoExtractor):
@@ -34,9 +35,10 @@ class GenericIE(InfoExtractor):
     _TESTS = [
         {
             'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
-            'file': '13601338388002.mp4',
-            'md5': '6e15c93721d7ec9e9ca3fdbf07982cfd',
+            'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
             'info_dict': {
+                'id': '13601338388002',
+                'ext': 'mp4',
                 'uploader': 'www.hodiho.fr',
                 'title': 'R\u00e9gis plante sa Jeep',
             }
@@ -45,8 +47,9 @@ class GenericIE(InfoExtractor):
         {
             'add_ie': ['Bandcamp'],
             'url': 'http://bronyrock.com/track/the-pony-mash',
-            'file': '3235767654.mp3',
             'info_dict': {
+                'id': '3235767654',
+                'ext': 'mp3',
                 'title': 'The Pony Mash',
                 'uploader': 'M_Pallante',
             },
@@ -72,15 +75,27 @@ class GenericIE(InfoExtractor):
         {
             # https://github.com/rg3/youtube-dl/issues/2253
             'url': 'http://bcove.me/i6nfkrc3',
-            'file': '3101154703001.mp4',
             'md5': '0ba9446db037002366bab3b3eb30c88c',
             'info_dict': {
+                'id': '3101154703001',
+                'ext': 'mp4',
                 'title': 'Still no power',
                 'uploader': 'thestar.com',
                 'description': 'Mississauga resident David Farmer is still out of power as a result of the ice storm a month ago. To keep the house warm, Farmer cuts wood from his property for a wood burning stove downstairs.',
             },
             'add_ie': ['Brightcove'],
         },
+        {
+            'url': 'http://www.championat.com/video/football/v/87/87499.html',
+            'md5': 'fb973ecf6e4a78a67453647444222983',
+            'info_dict': {
+                'id': '3414141473001',
+                'ext': 'mp4',
+                'title': 'Видео. Удаление Дзагоева (ЦСКА)',
+                'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
+                'uploader': 'Championat',
+            },
+        },
         # Direct link to a video
         {
             'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
@@ -171,6 +186,80 @@ class GenericIE(InfoExtractor):
                 'uploader': 'Ze Frank',
                 'description': 'md5:ddb2a40ecd6b6a147e400e535874947b',
             }
+        },
+        # Embeded Ustream video
+        {
+            'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
+            'md5': '27b99cdb639c9b12a79bca876a073417',
+            'info_dict': {
+                'id': '45734260',
+                'ext': 'flv',
+                'uploader': 'AU SPA:  The NSA and Privacy',
+                'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
+            }
+        },
+        # 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',
+            },
+        },
+        # arte embed
+        {
+            'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
+            'md5': '7653032cbb25bf6c80d80f217055fa43',
+            'info_dict': {
+                'id': '048195-004_PLUS7-F',
+                'ext': 'flv',
+                'title': 'X:enius',
+                'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
+                'upload_date': '20140320',
+            },
+            'params': {
+                'skip_download': 'Requires rtmpdump'
+            }
+        },
+        # smotri embed
+        {
+            'url': 'http://rbctv.rbc.ru/archive/news/562949990879132.shtml',
+            'md5': 'ec40048448e9284c9a1de77bb188108b',
+            'info_dict': {
+                'id': 'v27008541fad',
+                'ext': 'mp4',
+                'title': 'Крым и Севастополь вошли в состав России',
+                'description': 'md5:fae01b61f68984c7bd2fa741e11c3175',
+                'duration': 900,
+                'upload_date': '20140318',
+                'uploader': 'rbctv_2012_4',
+                'uploader_id': 'rbctv_2012_4',
+            },
+        },
+        # Condé Nast embed
+        {
+            'url': 'http://www.wired.com/2014/04/honda-asimo/',
+            'md5': 'ba0dfe966fa007657bd1443ee672db0f',
+            'info_dict': {
+                'id': '53501be369702d3275860000',
+                'ext': 'mp4',
+                'title': 'Honda’s  New Asimo Robot Is More Human Than Ever',
+            }
+        },
+        # Dailymotion embed
+        {
+            'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
+            'md5': '441aeeb82eb72c422c7f14ec533999cd',
+            'info_dict': {
+                'id': 'k2mm4bCdJ6CQ2i7c8o2',
+                'ext': 'mp4',
+                'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
+                'uploader': 'Spi0n',
+            },
+            'add_ie': ['Dailymotion'],
         }
     ]
 
@@ -256,17 +345,26 @@ class GenericIE(InfoExtractor):
         }
 
     def _real_extract(self, url):
+        if url.startswith('//'):
+            return {
+                '_type': 'url',
+                'url': self.http_scheme() + url,
+            }
+
         parsed_url = compat_urlparse.urlparse(url)
         if not parsed_url.scheme:
             default_search = self._downloader.params.get('default_search')
             if default_search is None:
-                default_search = 'auto'
+                default_search = 'auto_warning'
 
-            if default_search == 'auto':
+            if default_search in ('auto', 'auto_warning'):
                 if '/' in url:
                     self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
                     return self.url_result('http://' + url)
                 else:
+                    if default_search == 'auto_warning':
+                        self._downloader.report_warning(
+                            'Falling back to youtube search for  %s . Set --default-search to "auto" to suppress this warning.' % url)
                     return self.url_result('ytsearch:' + url)
             else:
                 assert ':' in default_search
@@ -323,6 +421,11 @@ class GenericIE(InfoExtractor):
         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
@@ -384,7 +487,7 @@ class GenericIE(InfoExtractor):
         matches = re.findall(
             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
         if matches:
-            urlrs = [self.url_result(unescapeHTML(tuppl[1]), 'Dailymotion')
+            urlrs = [self.url_result(unescapeHTML(tuppl[1]))
                      for tuppl in matches]
             return self.playlist_result(
                 urlrs, playlist_id=video_id, playlist_title=video_title)
@@ -410,6 +513,22 @@ class GenericIE(InfoExtractor):
         if mobj:
             return self.url_result(mobj.group(1), 'BlipTV')
 
+        # Look for embedded condenast player
+        matches = re.findall(
+            r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
+            webpage)
+        if matches:
+            return {
+                '_type': 'playlist',
+                'entries': [{
+                    '_type': 'url',
+                    'ie_key': 'CondeNast',
+                    'url': ma,
+                } for ma in matches],
+                'title': video_title,
+                'id': video_id,
+            }
+
         # Look for Bandcamp pages with custom domain
         mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
         if mobj is not None:
@@ -424,12 +543,13 @@ 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)
+        mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
         if mobj is not None:
             return self.url_result(mobj.group(1), 'Aparat')
 
@@ -438,17 +558,18 @@ 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-based player
         mobj = re.search(
-            r'<iframe[^>]+?src=(["\'])(?P<url>http://(?:(?:embed|www)\.)?novamov\.com/embed\.php.+?)\1', webpage)
+            r'''(?x)<iframe[^>]+?src=(["\'])
+                    (?P<url>http://(?:(?:embed|www)\.)?
+                        (?:novamov\.com|
+                           nowvideo\.(?:ch|sx|eu|at|ag|co)|
+                           videoweed\.(?:es|com)|
+                           movshare\.(?:net|sx|ag)|
+                           divxstage\.(?:eu|net|ch|co|at|ag))
+                        /embed\.php.+?)\1''', webpage)
         if mobj is not None:
-            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')
+            return self.url_result(mobj.group('url'))
 
         # Look for embedded Facebook player
         mobj = re.search(
@@ -488,71 +609,110 @@ class GenericIE(InfoExtractor):
         if rutv_url:
             return self.url_result(rutv_url, 'RUTV')
 
-        # Start with something easy: JW Player in SWFObject
-        mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
-        if mobj is None:
-            # Look for gorilla-vid style embedding
-            mobj = re.search(r'(?s)(?:jw_plugins|JWPlayerOptions).*?file\s*:\s*["\'](.*?)["\']', webpage)
-        if mobj is None:
-            # Broaden the search a little bit
-            mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)
-        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)
-
         # 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')
 
-        if mobj is None:
+        # Look for embedded Ustream videos
+        mobj = re.search(
+            r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'), 'Ustream')
+
+        # Look for embedded arte.tv player
+        mobj = re.search(
+            r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
+            webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'), 'ArteTVEmbed')
+
+        # Look for embedded smotri.com player
+        smotri_url = SmotriIE._extract_url(webpage)
+        if smotri_url:
+            return self.url_result(smotri_url, 'Smotri')
+
+        # Look for embeded soundcloud player
+        mobj = re.search(
+            r'<iframe src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
+            webpage)
+        if mobj is not None:
+            url = unescapeHTML(mobj.group('url'))
+            return self.url_result(url)
+
+        # Start with something easy: JW Player in SWFObject
+        found = re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
+        if not found:
+            # Look for gorilla-vid style embedding
+            found = re.findall(r'''(?sx)
+                (?:
+                    jw_plugins|
+                    JWPlayerOptions|
+                    jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
+                )
+                .*?file\s*:\s*["\'](.*?)["\']''', webpage)
+        if not found:
+            # Broaden the search a little bit
+            found = re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)
+        if not found:
+            # Broaden the findall a little bit: JWPlayer JS loader
+            found = re.findall(r'[^A-Za-z0-9]?file["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage)
+        if not found:
             # Try to find twitter cards info
-            mobj = re.search(r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage)
-        if mobj is None:
+            found = re.findall(r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage)
+        if not found:
             # We look for Open Graph info:
             # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
-            m_video_type = re.search(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
+            m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
             # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
             if m_video_type is not None:
-                mobj = re.search(r'<meta.*?property="og:video".*?content="(.*?)"', webpage)
-        if mobj is None:
+                found = re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage)
+        if not found:
             # HTML5 video
-            mobj = re.search(r'<video[^<]*(?:>.*?<source.*?)? src="([^"]+)"', webpage, flags=re.DOTALL)
-        if mobj is None:
-            mobj = re.search(
+            found = re.findall(r'(?s)<video[^<]*(?:>.*?<source.*?)? src="([^"]+)"', webpage)
+        if not found:
+            found = re.findall(
                 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)
+            if found:
+                new_url = found.group(1)
                 self.report_following_redirect(new_url)
                 return {
                     '_type': 'url',
                     'url': new_url,
                 }
-        if mobj is None:
+        if not found:
             raise ExtractorError('Unsupported URL: %s' % url)
 
-        # It's possible that one of the regexes
-        # matched, but returned an empty group:
-        if mobj.group(1) is None:
-            raise ExtractorError('Did not find a valid video URL at %s' % url)
+        entries = []
+        for video_url in found:
+            video_url = compat_urlparse.urljoin(url, video_url)
+            video_id = compat_urllib_parse.unquote(os.path.basename(video_url))
 
-        video_url = mobj.group(1)
-        video_url = compat_urlparse.urljoin(url, video_url)
-        video_id = compat_urllib_parse.unquote(os.path.basename(video_url))
+            # Sometimes, jwplayer extraction will result in a YouTube URL
+            if YoutubeIE.suitable(video_url):
+                entries.append(self.url_result(video_url, 'Youtube'))
+                continue
 
-        # Sometimes, jwplayer extraction will result in a YouTube URL
-        if YoutubeIE.suitable(video_url):
-            return self.url_result(video_url, 'Youtube')
+            # here's a fun little line of code for you:
+            video_id = os.path.splitext(video_id)[0]
 
-        # here's a fun little line of code for you:
-        video_id = os.path.splitext(video_id)[0]
+            entries.append({
+                'id': video_id,
+                'url': video_url,
+                'uploader': video_uploader,
+                'title': video_title,
+            })
+
+        if len(entries) == 1:
+            return entries[0]
+        else:
+            for num, e in enumerate(entries, start=1):
+                e['title'] = '%s (%d)' % (e['title'], num)
+            return {
+                '_type': 'playlist',
+                'entries': entries,
+            }
 
-        return {
-            'id': video_id,
-            'url': video_url,
-            'uploader': video_uploader,
-            'title': video_title,
-        }

youtube_dl/extractor/huffpost.py

@@ -21,9 +21,10 @@ class HuffPostIE(InfoExtractor):
 
     _TEST = {
         'url': 'http://live.huffingtonpost.com/r/segment/legalese-it/52dd3e4b02a7602131000677',
-        'file': '52dd3e4b02a7602131000677.mp4',
         'md5': '55f5e8981c1c80a64706a44b74833de8',
         'info_dict': {
+            'id': '52dd3e4b02a7602131000677',
+            'ext': 'mp4',
             'title': 'Legalese It! with @MikeSacksHP',
             'description': 'This week on Legalese It, Mike talks to David Bosco about his new book on the ICC, "Rough Justice," he also discusses the Virginia AG\'s historic stance on gay marriage, the execution of Edgar Tamayo, the ICC\'s delay of Kenya\'s President and more.  ',
             'duration': 1549,

youtube_dl/extractor/iconosquare.py

@@ -5,8 +5,8 @@ import re
 from .common import InfoExtractor
 
 
-class StatigramIE(InfoExtractor):
-    _VALID_URL = r'https?://(www\.)?statigr\.am/p/(?P<id>[^/]+)'
+class IconosquareIE(InfoExtractor):
+    _VALID_URL = r'https?://(www\.)?(?:iconosquare\.com|statigr\.am)/p/(?P<id>[^/]+)'
     _TEST = {
         'url': 'http://statigr.am/p/522207370455279102_24101272',
         'md5': '6eb93b882a3ded7c378ee1d6884b1814',
@@ -15,6 +15,7 @@ class StatigramIE(InfoExtractor):
             'ext': 'mp4',
             'uploader_id': 'aguynamedpatrick',
             'title': 'Instagram photo by @aguynamedpatrick (Patrick Janelle)',
+            'description': 'md5:644406a9ec27457ed7aa7a9ebcd4ce3d',
         },
     }
 
@@ -25,7 +26,7 @@ class StatigramIE(InfoExtractor):
         html_title = self._html_search_regex(
             r'<title>(.+?)</title>',
             webpage, 'title')
-        title = re.sub(r'(?: *\(Videos?\))? \| Statigram$', '', html_title)
+        title = re.sub(r'(?: *\(Videos?\))? \| (?:Iconosquare|Statigram)$', '', html_title)
         uploader_id = self._html_search_regex(
             r'@([^ ]+)', title, 'uploader name', fatal=False)
 
@@ -33,6 +34,7 @@ class StatigramIE(InfoExtractor):
             'id': video_id,
             'url': self._og_search_video_url(webpage),
             'title': title,
+            'description': self._og_search_description(webpage),
             'thumbnail': self._og_search_thumbnail(webpage),
             'uploader_id': uploader_id
         }

youtube_dl/extractor/ign.py

@@ -1,10 +1,8 @@
+from __future__ import unicode_literals
+
 import re
-import json
 
 from .common import InfoExtractor
-from ..utils import (
-    determine_ext,
-)
 
 
 class IGNIE(InfoExtractor):
@@ -14,52 +12,57 @@ class IGNIE(InfoExtractor):
     """
 
     _VALID_URL = r'https?://.+?\.ign\.com/(?P<type>videos|show_videos|articles|(?:[^/]*/feature))(/.+)?/(?P<name_or_id>.+)'
-    IE_NAME = u'ign.com'
+    IE_NAME = 'ign.com'
 
     _CONFIG_URL_TEMPLATE = 'http://www.ign.com/videos/configs/id/%s.config'
-    _DESCRIPTION_RE = [r'<span class="page-object-description">(.+?)</span>',
-                       r'id="my_show_video">.*?<p>(.*?)</p>',
-                       ]
+    _DESCRIPTION_RE = [
+        r'<span class="page-object-description">(.+?)</span>',
+        r'id="my_show_video">.*?<p>(.*?)</p>',
+    ]
 
     _TESTS = [
         {
-            u'url': u'http://www.ign.com/videos/2013/06/05/the-last-of-us-review',
-            u'file': u'8f862beef863986b2785559b9e1aa599.mp4',
-            u'md5': u'eac8bdc1890980122c3b66f14bdd02e9',
-            u'info_dict': {
-                u'title': u'The Last of Us Review',
-                u'description': u'md5:c8946d4260a4d43a00d5ae8ed998870c',
+            'url': 'http://www.ign.com/videos/2013/06/05/the-last-of-us-review',
+            'md5': 'eac8bdc1890980122c3b66f14bdd02e9',
+            'info_dict': {
+                'id': '8f862beef863986b2785559b9e1aa599',
+                'ext': 'mp4',
+                'title': 'The Last of Us Review',
+                'description': 'md5:c8946d4260a4d43a00d5ae8ed998870c',
             }
         },
         {
-            u'url': u'http://me.ign.com/en/feature/15775/100-little-things-in-gta-5-that-will-blow-your-mind',
-            u'playlist': [
+            'url': 'http://me.ign.com/en/feature/15775/100-little-things-in-gta-5-that-will-blow-your-mind',
+            'playlist': [
                 {
-                    u'file': u'5ebbd138523268b93c9141af17bec937.mp4',
-                    u'info_dict': {
-                        u'title': u'GTA 5 Video Review',
-                        u'description': u'Rockstar drops the mic on this generation of games. Watch our review of the masterly Grand Theft Auto V.',
+                    'info_dict': {
+                        'id': '5ebbd138523268b93c9141af17bec937',
+                        'ext': 'mp4',
+                        'title': 'GTA 5 Video Review',
+                        'description': 'Rockstar drops the mic on this generation of games. Watch our review of the masterly Grand Theft Auto V.',
                     },
                 },
                 {
-                    u'file': u'638672ee848ae4ff108df2a296418ee2.mp4',
-                    u'info_dict': {
-                        u'title': u'26 Twisted Moments from GTA 5 in Slow Motion',
-                        u'description': u'The twisted beauty of GTA 5 in stunning slow motion.',
+                    'info_dict': {
+                        'id': '638672ee848ae4ff108df2a296418ee2',
+                        'ext': 'mp4',
+                        'title': '26 Twisted Moments from GTA 5 in Slow Motion',
+                        'description': 'The twisted beauty of GTA 5 in stunning slow motion.',
                     },
                 },
             ],
-            u'params': {
-                u'skip_download': True,
+            'params': {
+                'skip_download': True,
             },
         },
     ]
 
     def _find_video_id(self, webpage):
-        res_id = [r'data-video-id="(.+?)"',
-                  r'<object id="vid_(.+?)"',
-                  r'<meta name="og:image" content=".*/(.+?)-(.+?)/.+.jpg"',
-                  ]
+        res_id = [
+            r'data-video-id="(.+?)"',
+            r'<object id="vid_(.+?)"',
+            r'<meta name="og:image" content=".*/(.+?)-(.+?)/.+.jpg"',
+        ]
         return self._search_regex(res_id, webpage, 'video id')
 
     def _real_extract(self, url):
@@ -68,7 +71,7 @@ class IGNIE(InfoExtractor):
         page_type = mobj.group('type')
         webpage = self._download_webpage(url, name_or_id)
         if page_type == 'articles':
-            video_url = self._search_regex(r'var videoUrl = "(.+?)"', webpage, u'video url')
+            video_url = self._search_regex(r'var videoUrl = "(.+?)"', webpage, 'video url')
             return self.url_result(video_url, ie='IGN')
         elif page_type != 'video':
             multiple_urls = re.findall(
@@ -80,50 +83,42 @@ class IGNIE(InfoExtractor):
         video_id = self._find_video_id(webpage)
         result = self._get_video_info(video_id)
         description = self._html_search_regex(self._DESCRIPTION_RE,
-                                              webpage, 'video description',
-                                              flags=re.DOTALL)
+            webpage, 'video description', flags=re.DOTALL)
         result['description'] = description
         return result
 
     def _get_video_info(self, video_id):
         config_url = self._CONFIG_URL_TEMPLATE % video_id
-        config = json.loads(self._download_webpage(config_url, video_id,
-                            u'Downloading video info'))
+        config = self._download_json(config_url, video_id)
         media = config['playlist']['media']
-        video_url = media['url']
 
-        return {'id': media['metadata']['videoId'],
-                'url': video_url,
-                'ext': determine_ext(video_url),
-                'title': media['metadata']['title'],
-                'thumbnail': media['poster'][0]['url'].replace('{size}', 'grande'),
-                }
+        return {
+            'id': media['metadata']['videoId'],
+            'url': media['url'],
+            'title': media['metadata']['title'],
+            'thumbnail': media['poster'][0]['url'].replace('{size}', 'grande'),
+        }
 
 
 class OneUPIE(IGNIE):
-    """Extractor for 1up.com, it uses the ign videos system."""
-
     _VALID_URL = r'https?://gamevideos\.1up\.com/(?P<type>video)/id/(?P<name_or_id>.+)'
     IE_NAME = '1up.com'
 
     _DESCRIPTION_RE = r'<div id="vid_summary">(.+?)</div>'
 
-    _TEST = {
-        u'url': u'http://gamevideos.1up.com/video/id/34976',
-        u'file': u'34976.mp4',
-        u'md5': u'68a54ce4ebc772e4b71e3123d413163d',
-        u'info_dict': {
-            u'title': u'Sniper Elite V2 - Trailer',
-            u'description': u'md5:5d289b722f5a6d940ca3136e9dae89cf',
+    _TESTS = [{
+        'url': 'http://gamevideos.1up.com/video/id/34976',
+        'md5': '68a54ce4ebc772e4b71e3123d413163d',
+        'info_dict': {
+            'id': '34976',
+            'ext': 'mp4',
+            'title': 'Sniper Elite V2 - Trailer',
+            'description': 'md5:5d289b722f5a6d940ca3136e9dae89cf',
         }
-    }
-
-    # Override IGN tests
-    _TESTS = []
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        id = mobj.group('name_or_id')
         result = super(OneUPIE, self)._real_extract(url)
-        result['id'] = id
+        result['id'] = mobj.group('name_or_id')
         return result

youtube_dl/extractor/infoq.py

@@ -11,16 +11,15 @@ from ..utils import (
 
 class InfoQIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?infoq\.com/[^/]+/(?P<id>[^/]+)$'
+
     _TEST = {
-        "name": "InfoQ",
-        "url": "http://www.infoq.com/presentations/A-Few-of-My-Favorite-Python-Things",
-        "file": "12-jan-pythonthings.mp4",
-        "info_dict": {
-            "description": "Mike Pirnat presents some tips and tricks, standard libraries and third party packages that make programming in Python a richer experience.",
-            "title": "A Few of My Favorite [Python] Things",
-        },
-        "params": {
-            "skip_download": True,
+        'url': 'http://www.infoq.com/presentations/A-Few-of-My-Favorite-Python-Things',
+        'md5': 'b5ca0e0a8c1fed93b0e65e48e462f9a2',
+        'info_dict': {
+            'id': '12-jan-pythonthings',
+            'ext': 'mp4',
+            'description': 'Mike Pirnat presents some tips and tricks, standard libraries and third party packages that make programming in Python a richer experience.',
+            'title': 'A Few of My Favorite [Python] Things',
         },
     }
 
@@ -30,26 +29,39 @@ class InfoQIE(InfoExtractor):
 
         webpage = self._download_webpage(url, video_id)
 
+        video_title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title')
+        video_description = self._html_search_meta('description', webpage, 'description')
+
+        # The server URL is hardcoded
+        video_url = 'rtmpe://video.infoq.com/cfx/st/'
+
         # Extract video URL
-        encoded_id = self._search_regex(r"jsclassref ?= ?'([^']*)'", webpage, 'encoded id')
+        encoded_id = self._search_regex(
+            r"jsclassref\s*=\s*'([^']*)'", webpage, 'encoded id')
         real_id = compat_urllib_parse.unquote(base64.b64decode(encoded_id.encode('ascii')).decode('utf-8'))
-        video_url = 'rtmpe://video.infoq.com/cfx/st/' + real_id
+        playpath = 'mp4:' + real_id
 
-        # Extract title
-        video_title = self._search_regex(r'contentTitle = "(.*?)";',
-            webpage, 'title')
-
-        # Extract description
-        video_description = self._html_search_regex(r'<meta name="description" content="(.*)"(?:\s*/)?>',
-            webpage, 'description', fatal=False)
-
-        video_filename = video_url.split('/')[-1]
+        video_filename = playpath.split('/')[-1]
         video_id, extension = video_filename.split('.')
 
+        http_base = self._search_regex(
+            r'EXPRESSINSTALL_SWF\s*=\s*"(https?://[^/"]+/)', webpage,
+            'HTTP base URL')
+
+        formats = [{
+            'format_id': 'rtmp',
+            'url': video_url,
+            'ext': extension,
+            'play_path': playpath,
+        }, {
+            'format_id': 'http',
+            'url': http_base + real_id,
+        }]
+        self._sort_formats(formats)
+
         return {
             'id': video_id,
-            'url': video_url,
             'title': video_title,
-            'ext': extension,  # Extension is always(?) mp4, but seems to be flv
             'description': video_description,
+            'formats': formats,
         }

youtube_dl/extractor/instagram.py

@@ -3,6 +3,9 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+)
 
 
 class InstagramIE(InfoExtractor):
@@ -37,3 +40,68 @@ class InstagramIE(InfoExtractor):
             '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/jukebox.py

@@ -14,7 +14,7 @@ class JukeboxIE(InfoExtractor):
     _VALID_URL = r'^http://www\.jukebox?\..+?\/.+[,](?P<video_id>[a-z0-9\-]+)\.html'
     _TEST = {
         'url': 'http://www.jukebox.es/kosheen/videoclip,pride,r303r.html',
-        'md5': '5dc6477e74b1e37042ac5acedd8413e5',
+        'md5': '1574e9b4d6438446d5b7dbcdf2786276',
         'info_dict': {
             'id': 'r303r',
             'ext': 'flv',

youtube_dl/extractor/justintv.py

@@ -1,9 +1,12 @@
+from __future__ import unicode_literals
+
 import json
 import os
 import re
 
 from .common import InfoExtractor
 from ..utils import (
+    compat_str,
     ExtractorError,
     formatSeconds,
 )
@@ -24,34 +27,31 @@ class JustinTVIE(InfoExtractor):
         /?(?:\#.*)?$
         """
     _JUSTIN_PAGE_LIMIT = 100
-    IE_NAME = u'justin.tv'
+    IE_NAME = 'justin.tv'
+    IE_DESC = 'justin.tv and twitch.tv'
     _TEST = {
-        u'url': u'http://www.twitch.tv/thegamedevhub/b/296128360',
-        u'file': u'296128360.flv',
-        u'md5': u'ecaa8a790c22a40770901460af191c9a',
-        u'info_dict': {
-            u"upload_date": u"20110927", 
-            u"uploader_id": 25114803, 
-            u"uploader": u"thegamedevhub", 
-            u"title": u"Beginner Series - Scripting With Python Pt.1"
+        'url': 'http://www.twitch.tv/thegamedevhub/b/296128360',
+        'md5': 'ecaa8a790c22a40770901460af191c9a',
+        'info_dict': {
+            'id': '296128360',
+            'ext': 'flv',
+            'upload_date': '20110927',
+            'uploader_id': 25114803,
+            'uploader': 'thegamedevhub',
+            'title': 'Beginner Series - Scripting With Python Pt.1'
         }
     }
 
-    def report_download_page(self, channel, offset):
-        """Report attempt to download a single page of videos."""
-        self.to_screen(u'%s: Downloading video information from %d to %d' %
-                (channel, offset, offset + self._JUSTIN_PAGE_LIMIT))
-
     # Return count of items, list of *valid* items
     def _parse_page(self, url, video_id):
         info_json = self._download_webpage(url, video_id,
-                                           u'Downloading video info JSON',
-                                           u'unable to download video info JSON')
+                                           'Downloading video info JSON',
+                                           'unable to download video info JSON')
 
         response = json.loads(info_json)
         if type(response) != list:
             error_text = response.get('error', 'unknown error')
-            raise ExtractorError(u'Justin.tv API: %s' % error_text)
+            raise ExtractorError('Justin.tv API: %s' % error_text)
         info = []
         for clip in response:
             video_url = clip['video_file_url']
@@ -62,7 +62,7 @@ class JustinTVIE(InfoExtractor):
                 video_id = clip['id']
                 video_title = clip.get('title', video_id)
                 info.append({
-                    'id': video_id,
+                    'id': compat_str(video_id),
                     'url': video_url,
                     'title': video_title,
                     'uploader': clip.get('channel_name', video_uploader_id),
@@ -74,8 +74,6 @@ class JustinTVIE(InfoExtractor):
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError(u'invalid URL: %s' % url)
 
         api_base = 'http://api.justin.tv'
         paged = False
@@ -89,40 +87,41 @@ class JustinTVIE(InfoExtractor):
             webpage = self._download_webpage(url, chapter_id)
             m = re.search(r'PP\.archive_id = "([0-9]+)";', webpage)
             if not m:
-                raise ExtractorError(u'Cannot find archive of a chapter')
+                raise ExtractorError('Cannot find archive of a chapter')
             archive_id = m.group(1)
 
             api = api_base + '/broadcast/by_chapter/%s.xml' % chapter_id
-            doc = self._download_xml(api, chapter_id,
-                                             note=u'Downloading chapter information',
-                                             errnote=u'Chapter information download failed')
+            doc = self._download_xml(
+                api, chapter_id,
+                note='Downloading chapter information',
+                errnote='Chapter information download failed')
             for a in doc.findall('.//archive'):
                 if archive_id == a.find('./id').text:
                     break
             else:
-                raise ExtractorError(u'Could not find chapter in chapter information')
+                raise ExtractorError('Could not find chapter in chapter information')
 
             video_url = a.find('./video_file_url').text
-            video_ext = video_url.rpartition('.')[2] or u'flv'
+            video_ext = video_url.rpartition('.')[2] or 'flv'
 
-            chapter_api_url = u'https://api.twitch.tv/kraken/videos/c' + chapter_id
-            chapter_info_json = self._download_webpage(chapter_api_url, u'c' + chapter_id,
-                                   note='Downloading chapter metadata',
-                                   errnote='Download of chapter metadata failed')
-            chapter_info = json.loads(chapter_info_json)
+            chapter_api_url = 'https://api.twitch.tv/kraken/videos/c' + chapter_id
+            chapter_info = self._download_json(
+                chapter_api_url, 'c' + chapter_id,
+                note='Downloading chapter metadata',
+                errnote='Download of chapter metadata failed')
 
             bracket_start = int(doc.find('.//bracket_start').text)
             bracket_end = int(doc.find('.//bracket_end').text)
 
             # TODO determine start (and probably fix up file)
             #  youtube-dl -v http://www.twitch.tv/firmbelief/c/1757457
-            #video_url += u'?start=' + TODO:start_timestamp
+            #video_url += '?start=' + TODO:start_timestamp
             # bracket_start is 13290, but we want 51670615
-            self._downloader.report_warning(u'Chapter detected, but we can just download the whole file. '
-                                            u'Chapter starts at %s and ends at %s' % (formatSeconds(bracket_start), formatSeconds(bracket_end)))
+            self._downloader.report_warning('Chapter detected, but we can just download the whole file. '
+                                            'Chapter starts at %s and ends at %s' % (formatSeconds(bracket_start), formatSeconds(bracket_end)))
 
             info = {
-                'id': u'c' + chapter_id,
+                'id': 'c' + chapter_id,
                 'url': video_url,
                 'ext': video_ext,
                 'title': chapter_info['title'],
@@ -131,14 +130,12 @@ class JustinTVIE(InfoExtractor):
                 'uploader': chapter_info['channel']['display_name'],
                 'uploader_id': chapter_info['channel']['name'],
             }
-            return [info]
+            return info
         else:
             video_id = mobj.group('videoid')
             api = api_base + '/broadcast/by_archive/%s.json' % video_id
 
-        self.report_extraction(video_id)
-
-        info = []
+        entries = []
         offset = 0
         limit = self._JUSTIN_PAGE_LIMIT
         while True:
@@ -146,8 +143,12 @@ class JustinTVIE(InfoExtractor):
                 self.report_download_page(video_id, offset)
             page_url = api + ('?offset=%d&limit=%d' % (offset, limit))
             page_count, page_info = self._parse_page(page_url, video_id)
-            info.extend(page_info)
+            entries.extend(page_info)
             if not paged or page_count != limit:
                 break
             offset += limit
-        return info
+        return {
+            '_type': 'playlist',
+            'id': video_id,
+            'entries': entries,
+        }

youtube_dl/extractor/keezmovies.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import os
 import re
 
@@ -11,22 +13,22 @@ from ..aes import (
     aes_decrypt_text
 )
 
+
 class KeezMoviesIE(InfoExtractor):
-    _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>keezmovies\.com/video/.+?(?P<videoid>[0-9]+))(?:[/?&]|$)'
+    _VALID_URL = r'^https?://(?:www\.)?keezmovies\.com/video/.+?(?P<videoid>[0-9]+)(?:[/?&]|$)'
     _TEST = {
-        u'url': u'http://www.keezmovies.com/video/petite-asian-lady-mai-playing-in-bathtub-1214711',
-        u'file': u'1214711.mp4',
-        u'md5': u'6e297b7e789329923fcf83abb67c9289',
-        u'info_dict': {
-            u"title": u"Petite Asian Lady Mai Playing In Bathtub",
-            u"age_limit": 18,
+        'url': 'http://www.keezmovies.com/video/petite-asian-lady-mai-playing-in-bathtub-1214711',
+        'file': '1214711.mp4',
+        'md5': '6e297b7e789329923fcf83abb67c9289',
+        'info_dict': {
+            'title': 'Petite Asian Lady Mai Playing In Bathtub',
+            'age_limit': 18,
         }
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('videoid')
-        url = 'http://www.' + mobj.group('url')
 
         req = compat_urllib_request.Request(url)
         req.add_header('Cookie', 'age_verified=1')
@@ -38,10 +40,10 @@ class KeezMoviesIE(InfoExtractor):
             embedded_url = mobj.group(1)
             return self.url_result(embedded_url)
 
-        video_title = self._html_search_regex(r'<h1 [^>]*>([^<]+)', webpage, u'title')
-        video_url = compat_urllib_parse.unquote(self._html_search_regex(r'video_url=(.+?)&amp;', webpage, u'video_url'))
-        if webpage.find('encrypted=true')!=-1:
-            password = self._html_search_regex(r'video_title=(.+?)&amp;', webpage, u'password')
+        video_title = self._html_search_regex(r'<h1 [^>]*>([^<]+)', webpage, 'title')
+        video_url = compat_urllib_parse.unquote(self._html_search_regex(r'video_url=(.+?)&amp;', webpage, 'video_url'))
+        if 'encrypted=true' in webpage:
+            password = self._html_search_regex(r'video_title=(.+?)&amp;', webpage, 'password')
             video_url = aes_decrypt_text(video_url, password, 32).decode('utf-8')
         path = compat_urllib_parse_urlparse(video_url).path
         extension = os.path.splitext(path)[1][1:]

youtube_dl/extractor/kickstarter.py

@@ -1,37 +1,39 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
 
 
 class KickStarterIE(InfoExtractor):
-    _VALID_URL = r'https?://www\.kickstarter\.com/projects/(?P<id>\d*)/.*'
+    _VALID_URL = r'https?://www\.kickstarter\.com/projects/(?P<id>[^/]*)/.*'
     _TEST = {
-        u"url": u"https://www.kickstarter.com/projects/1404461844/intersection-the-story-of-josh-grant?ref=home_location",
-        u"file": u"1404461844.mp4",
-        u"md5": u"c81addca81327ffa66c642b5d8b08cab",
-        u"info_dict": {
-            u"title": u"Intersection: The Story of Josh Grant by Kyle Cowling",
+        'url': 'https://www.kickstarter.com/projects/1404461844/intersection-the-story-of-josh-grant?ref=home_location',
+        'md5': 'c81addca81327ffa66c642b5d8b08cab',
+        'info_dict': {
+            'id': '1404461844',
+            'ext': 'mp4',
+            'title': 'Intersection: The Story of Josh Grant by Kyle Cowling',
+            'description': 'A unique motocross documentary that examines the '
+                'life and mind of one of sports most elite athletes: Josh Grant.',
         },
     }
 
     def _real_extract(self, url):
         m = re.match(self._VALID_URL, url)
         video_id = m.group('id')
-        webpage_src = self._download_webpage(url, video_id)
+        webpage = self._download_webpage(url, video_id)
 
-        video_url = self._search_regex(r'data-video="(.*?)">',
-            webpage_src, u'video URL')
-        if 'mp4' in video_url:
-            ext = 'mp4'
-        else:
-            ext = 'flv'
-        video_title = self._html_search_regex(r"<title>(.*?)</title>",
-            webpage_src, u'title').rpartition(u'\u2014 Kickstarter')[0].strip()
+        video_url = self._search_regex(r'data-video-url="(.*?)"',
+            webpage, 'video URL')
+        video_title = self._html_search_regex(r'<title>(.*?)</title>',
+            webpage, 'title').rpartition('— Kickstarter')[0].strip()
 
-        results = [{
-                    'id': video_id,
-                    'url': video_url,
-                    'title': video_title,
-                    'ext': ext,
-                    }]
-        return results
+        return {
+            'id': video_id,
+            'url': video_url,
+            'title': video_title,
+            'description': self._og_search_description(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
+        }

youtube_dl/extractor/mdr.py

@@ -1,15 +1,18 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-)
 
 
 class MDRIE(InfoExtractor):
-    _VALID_URL = r'^(?P<domain>(?:https?://)?(?:www\.)?mdr\.de)/mediathek/(?:.*)/(?P<type>video|audio)(?P<video_id>[^/_]+)_.*'
+    _VALID_URL = r'^(?P<domain>https?://(?:www\.)?mdr\.de)/(?:.*)/(?P<type>video|audio)(?P<video_id>[^/_]+)(?:_|\.html)'
     
     # No tests, MDR regularily deletes its videos
+    _TEST = {
+        'url': 'http://www.mdr.de/fakt/video189002.html',
+        'only_matching': True,
+    }
 
     def _real_extract(self, url):
         m = re.match(self._VALID_URL, url)
@@ -19,9 +22,9 @@ class MDRIE(InfoExtractor):
         # determine title and media streams from webpage
         html = self._download_webpage(url, video_id)
 
-        title = self._html_search_regex(r'<h2>(.*?)</h2>', html, u'title')
+        title = self._html_search_regex(r'<h[12]>(.*?)</h[12]>', html, 'title')
         xmlurl = self._search_regex(
-            r'(/mediathek/(?:.+)/(?:video|audio)[0-9]+-avCustom.xml)', html, u'XML URL')
+            r'dataURL:\'(/(?:.+)/(?:video|audio)[0-9]+-avCustom.xml)', html, 'XML URL')
 
         doc = self._download_xml(domain + xmlurl, video_id)
         formats = []
@@ -41,7 +44,7 @@ class MDRIE(InfoExtractor):
             if vbr_el is None:
                 format.update({
                     'vcodec': 'none',
-                    'format_id': u'%s-%d' % (media_type, abr),
+                    'format_id': '%s-%d' % (media_type, abr),
                 })
             else:
                 vbr = int(vbr_el.text) // 1000
@@ -49,12 +52,9 @@ class MDRIE(InfoExtractor):
                     'vbr': vbr,
                     'width': int(a.find('frameWidth').text),
                     'height': int(a.find('frameHeight').text),
-                    'format_id': u'%s-%d' % (media_type, vbr),
+                    'format_id': '%s-%d' % (media_type, vbr),
                 })
             formats.append(format)
-        if not formats:
-            raise ExtractorError(u'Could not find any valid formats')
-
         self._sort_formats(formats)
 
         return {

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)
 
@@ -153,23 +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
@@ -177,14 +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,
+            'title': video_title,
             'thumbnail':thumbnail,
-            'ext':      video_ext,
+            'ext': video_ext,
             'age_limit': age_limit,
         }

youtube_dl/extractor/metacritic.py

@@ -13,8 +13,9 @@ class MetacriticIE(InfoExtractor):
 
     _TEST = {
         'url': 'http://www.metacritic.com/game/playstation-4/infamous-second-son/trailers/3698222',
-        'file': '3698222.mp4',
         'info_dict': {
+            'id': '3698222',
+            'ext': 'mp4',
             'title': 'inFamous: Second Son - inSide Sucker Punch: Smoke & Mirrors',
             'description': 'Take a peak behind-the-scenes to see how Sucker Punch brings smoke into the universe of inFAMOUS Second Son on the PS4.',
             'duration': 221,

youtube_dl/extractor/mooshare.py

@@ -14,7 +14,7 @@ from ..utils import (
 class MooshareIE(InfoExtractor):
     IE_NAME = 'mooshare'
     IE_DESC = 'Mooshare.biz'
-    _VALID_URL = r'http://mooshare\.biz/(?P<id>[\da-z]{12})'
+    _VALID_URL = r'http://(?:www\.)?mooshare\.biz/(?P<id>[\da-z]{12})'
 
     _TESTS = [
         {

youtube_dl/extractor/morningstar.py

@@ -0,0 +1,47 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class MorningstarIE(InfoExtractor):
+    IE_DESC = 'morningstar.com'
+    _VALID_URL = r'https?://(?:www\.)?morningstar\.com/[cC]over/video[cC]enter\.aspx\?id=(?P<id>[0-9]+)'
+    _TEST = {
+        'url': 'http://www.morningstar.com/cover/videocenter.aspx?id=615869',
+        'md5': '6c0acface7a787aadc8391e4bbf7b0f5',
+        'info_dict': {
+            'id': '615869',
+            'ext': 'mp4',
+            'title': 'Get Ahead of the Curve on 2013 Taxes',
+            'description': "Vanguard's Joel Dickson on managing higher tax rates for high-income earners and fund capital-gain distributions in 2013.",
+            'thumbnail': r're:^https?://.*m(?:orning)?star\.com/.+thumb\.jpg$'
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+        title = self._html_search_regex(
+            r'<h1 id="titleLink">(.*?)</h1>', webpage, 'title')
+        video_url = self._html_search_regex(
+            r'<input type="hidden" id="hidVideoUrl" value="([^"]+)"',
+            webpage, 'video URL')
+        thumbnail = self._html_search_regex(
+            r'<input type="hidden" id="hidSnapshot" value="([^"]+)"',
+            webpage, 'thumbnail', fatal=False)
+        description = self._html_search_regex(
+            r'<div id="mstarDeck".*?>(.*?)</div>',
+            webpage, 'description', fatal=False)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'url': video_url,
+            'thumbnail': thumbnail,
+            'description': description,
+        }

youtube_dl/extractor/motorsport.py

@@ -0,0 +1,63 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import hashlib
+import json
+import re
+import time
+
+from .common import InfoExtractor
+from ..utils import (
+    compat_parse_qs,
+    compat_str,
+    int_or_none,
+)
+
+
+class MotorsportIE(InfoExtractor):
+    IE_DESC = 'motorsport.com'
+    _VALID_URL = r'http://www\.motorsport\.com/[^/?#]+/video/(?:[^/?#]+/)(?P<id>[^/]+)/(?:$|[?#])'
+    _TEST = {
+        'url': 'http://www.motorsport.com/f1/video/main-gallery/red-bull-racing-2014-rules-explained/',
+        'md5': '5592cb7c5005d9b2c163df5ac3dc04e4',
+        'info_dict': {
+            'id': '7063',
+            'ext': 'mp4',
+            'title': 'Red Bull Racing: 2014 Rules Explained',
+            'duration': 207,
+            'description': 'A new clip from Red Bull sees Daniel Ricciardo and Sebastian Vettel explain the 2014 Formula One regulations – which are arguably the most complex the sport has ever seen.',
+            'uploader': 'rainiere',
+            'thumbnail': r're:^http://.*motorsport\.com/.+\.jpg$'
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        display_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, display_id)
+        flashvars_code = self._html_search_regex(
+            r'<embed id="player".*?flashvars="([^"]+)"', webpage, 'flashvars')
+        flashvars = compat_parse_qs(flashvars_code)
+        params = json.loads(flashvars['parameters'][0])
+
+        e = compat_str(int(time.time()) + 24 * 60 * 60)
+        base_video_url = params['location'] + '?e=' + e
+        s = 'h3hg713fh32'
+        h = hashlib.md5((s + base_video_url).encode('utf-8')).hexdigest()
+        video_url = base_video_url + '&h=' + h
+
+        uploader = self._html_search_regex(
+            r'(?s)<span class="label">Video by: </span>(.*?)</a>', webpage,
+            'uploader', fatal=False)
+
+        return {
+            'id': params['video_id'],
+            'display_id': display_id,
+            'title': params['title'],
+            'url': video_url,
+            'description': params.get('description'),
+            'thumbnail': params.get('main_thumb'),
+            'duration': int_or_none(params.get('duration')),
+            'uploader': uploader,
+        }

youtube_dl/extractor/moviezine.py

@@ -0,0 +1,45 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class MoviezineIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.moviezine\.se/video/(?P<id>[^?#]+)'
+
+    _TEST = {
+        'url': 'http://www.moviezine.se/video/205866',
+        'info_dict': {
+            'id': '205866',
+            'ext': 'mp4',
+            'title': 'Oculus - Trailer 1',
+            'description': 'md5:40cc6790fc81d931850ca9249b40e8a4',
+            'thumbnail': 're:http://.*\.jpg',
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+        jsplayer = self._download_webpage('http://www.moviezine.se/api/player.js?video=%s' % video_id, video_id, 'Downloading js api player')
+
+        formats =[{
+            'format_id': 'sd',
+            'url': self._html_search_regex(r'file: "(.+?)",', jsplayer, 'file'),
+            'quality': 0,
+            'ext': 'mp4',
+        }]
+
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': self._search_regex(r'title: "(.+?)",', jsplayer, 'title'),
+            'thumbnail': self._search_regex(r'image: "(.+?)",', jsplayer, 'image'),
+            'formats': formats,
+            'description': self._og_search_description(webpage),
+        }

youtube_dl/extractor/movshare.py

@@ -0,0 +1,27 @@
+from __future__ import unicode_literals
+
+from .novamov import NovaMovIE
+
+
+class MovShareIE(NovaMovIE):
+    IE_NAME = 'movshare'
+    IE_DESC = 'MovShare'
+
+    _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'movshare\.(?:net|sx|ag)'}
+
+    _HOST = 'www.movshare.net'
+
+    _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
+    _TITLE_REGEX = r'<strong>Title:</strong> ([^<]+)</p>'
+    _DESCRIPTION_REGEX = r'<strong>Description:</strong> ([^<]+)</p>'
+
+    _TEST = {
+        'url': 'http://www.movshare.net/video/559e28be54d96',
+        'md5': 'abd31a2132947262c50429e1d16c1bfd',
+        'info_dict': {
+            'id': '559e28be54d96',
+            'ext': 'flv',
+            'title': 'dissapeared image',
+            'description': 'optical illusion  dissapeared image  magic illusion',
+        }
+    }

youtube_dl/extractor/mpora.py

@@ -4,9 +4,7 @@ import json
 import re
 
 from .common import InfoExtractor
-from ..utils import (
-    int_or_none,
-)
+from ..utils import int_or_none
 
 
 class MporaIE(InfoExtractor):
@@ -20,7 +18,7 @@ class MporaIE(InfoExtractor):
         'info_dict': {
             'title': 'Katy Curd -  Winter in the Forest',
             'duration': 416,
-            'uploader': 'petenewman',
+            'uploader': 'Peter Newman Media',
         },
     }
 

youtube_dl/extractor/musicplayon.py

@@ -0,0 +1,75 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import int_or_none
+
+
+class MusicPlayOnIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:.+?\.)?musicplayon\.com/play(?:-touch)?\?(?:v|pl=100&play)=(?P<id>\d+)'
+
+    _TEST = {
+        'url': 'http://en.musicplayon.com/play?v=433377',
+        'info_dict': {
+            'id': '433377',
+            'ext': 'mp4',
+            'title': 'Rick Ross - Interview On Chelsea Lately (2014)',
+            'description': 'Rick Ross Interview On Chelsea Lately',
+            'duration': 342,
+            'uploader': 'ultrafish',
+        },
+        'params': {
+            # m3u8 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(url, video_id)
+
+        title = self._og_search_title(page)
+        description = self._og_search_description(page)
+        thumbnail = self._og_search_thumbnail(page)
+        duration = self._html_search_meta('video:duration', page, 'duration', fatal=False)
+        view_count = self._og_search_property('count', page, fatal=False)
+        uploader = self._html_search_regex(
+            r'<div>by&nbsp;<a href="[^"]+" class="purple">([^<]+)</a></div>', page, 'uploader', fatal=False)
+
+        formats = [
+            {
+                'url': 'http://media0-eu-nl.musicplayon.com/stream-mobile?id=%s&type=.mp4' % video_id,
+                'ext': 'mp4',
+            }
+        ]
+
+        manifest = self._download_webpage(
+            'http://en.musicplayon.com/manifest.m3u8?v=%s' % video_id, video_id, 'Downloading manifest')
+
+        for entry in manifest.split('#')[1:]:
+            if entry.startswith('EXT-X-STREAM-INF:'):
+                meta, url, _ = entry.split('\n')
+                params = dict(param.split('=') for param in meta.split(',')[1:])
+                formats.append({
+                    'url': url,
+                    'ext': 'mp4',
+                    'tbr': int(params['BANDWIDTH']),
+                    'width': int(params['RESOLUTION'].split('x')[1]),
+                    'height': int(params['RESOLUTION'].split('x')[-1]),
+                    'format_note': params['NAME'].replace('"', '').strip(),
+                })
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'uploader': uploader,
+            'duration': int_or_none(duration),
+            'view_count': int_or_none(view_count),
+            'formats': formats,
+        }

youtube_dl/extractor/nba.py

@@ -6,12 +6,13 @@ from .common import InfoExtractor
 
 
 class NBAIE(InfoExtractor):
-    _VALID_URL = r'^(?:https?://)?(?:watch\.|www\.)?nba\.com/(?:nba/)?video(/[^?]*?)(?:/index\.html)?(?:\?.*)?$'
+    _VALID_URL = r'https?://(?:watch\.|www\.)?nba\.com/(?:nba/)?video(?P<id>/[^?]*?)(?:/index\.html)?(?:\?.*)?$'
     _TEST = {
         'url': 'http://www.nba.com/video/games/nets/2012/12/04/0021200253-okc-bkn-recap.nba/index.html',
-        'file': u'0021200253-okc-bkn-recap.nba.mp4',
         'md5': u'c0edcfc37607344e2ff8f13c378c88a4',
         'info_dict': {
+            'id': '0021200253-okc-bkn-recap.nba',
+            'ext': 'mp4',
             'description': 'Kevin Durant scores 32 points and dishes out six assists as the Thunder beat the Nets in Brooklyn.',
             'title': 'Thunder vs. Nets',
         },
@@ -19,7 +20,7 @@ class NBAIE(InfoExtractor):
 
     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)
 
@@ -33,7 +34,6 @@ class NBAIE(InfoExtractor):
         return {
             'id': shortened_video_id,
             'url': video_url,
-            'ext': 'mp4',
             'title': title,
             'description': description,
         }

youtube_dl/extractor/newstube.py

@@ -0,0 +1,87 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+
+class NewstubeIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?newstube\.ru/media/(?P<id>.+)'
+    _TEST = {
+        'url': 'http://newstube.ru/media/na-korable-progress-prodolzhaetsya-testirovanie-sistemy-kurs',
+        'info_dict': {
+            'id': 'd156a237-a6e9-4111-a682-039995f721f1',
+            'ext': 'flv',
+            'title': 'На корабле «Прогресс» продолжается тестирование системы «Курс»',
+            'description': 'md5:d0cbe7b4a6f600552617e48548d5dc77',
+            'duration': 20.04,
+        },
+        '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(url, video_id, 'Downloading page')
+
+        video_guid = self._html_search_regex(
+            r'<meta property="og:video" content="https?://(?:www\.)?newstube\.ru/freshplayer\.swf\?guid=(?P<guid>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})',
+            page, 'video GUID')
+
+        player = self._download_xml(
+            'http://p.newstube.ru/v2/player.asmx/GetAutoPlayInfo6?state=&url=%s&sessionId=&id=%s&placement=profile&location=n2' % (url, video_guid),
+            video_guid, 'Downloading player XML')
+
+        def ns(s):
+            return s.replace('/', '/%(ns)s') % {'ns': '{http://app1.newstube.ru/N2SiteWS/player.asmx}'}
+
+        session_id = player.find(ns('./SessionId')).text
+        media_info = player.find(ns('./Medias/MediaInfo'))
+        title = media_info.find(ns('./Name')).text
+        description = self._og_search_description(page)
+        thumbnail = media_info.find(ns('./KeyFrame')).text
+        duration = int(media_info.find(ns('./Duration')).text) / 1000.0
+
+        formats = []
+
+        for stream_info in media_info.findall(ns('./Streams/StreamInfo')):
+            media_location = stream_info.find(ns('./MediaLocation'))
+            if media_location is None:
+                continue
+
+            server = media_location.find(ns('./Server')).text
+            app = media_location.find(ns('./App')).text
+            media_id = stream_info.find(ns('./Id')).text
+            quality_id = stream_info.find(ns('./QualityId')).text
+            name = stream_info.find(ns('./Name')).text
+            width = int(stream_info.find(ns('./Width')).text)
+            height = int(stream_info.find(ns('./Height')).text)
+
+            formats.append({
+                'url': 'rtmp://%s/%s' % (server, app),
+                'app': app,
+                'play_path': '01/%s' % video_guid.upper(),
+                'rtmp_conn': ['S:%s' % session_id, 'S:%s' % media_id, 'S:n2'],
+                'page_url': url,
+                'ext': 'flv',
+                'format_id': quality_id,
+                'format_note': name,
+                'width': width,
+                'height': height,
+            })
+
+        self._sort_formats(formats)
+
+        return {
+            'id': video_guid,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'formats': formats,
+        }

youtube_dl/extractor/nfb.py

@@ -73,14 +73,16 @@ class NFBIE(InfoExtractor):
                 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')]
+                for asset in media.findall('assets/asset'):
+                    for x in asset:
+                        formats.append({
+                            'url': x.find('streamerURI').text,
+                            'app': x.find('streamerURI').text.split('/', 3)[3],
+                            'play_path': x.find('url').text,
+                            'rtmp_live': False,
+                            'ext': 'mp4',
+                            'format_id': '%s-%s' % (x.tag, asset.get('quality')),
+                        })
 
         return {
             'id': video_id,

youtube_dl/extractor/niconico.py

@@ -1,12 +1,10 @@
 # encoding: utf-8
+from __future__ import unicode_literals
 
 import re
-import socket
 
 from .common import InfoExtractor
 from ..utils import (
-    compat_http_client,
-    compat_urllib_error,
     compat_urllib_parse,
     compat_urllib_request,
     compat_urlparse,
@@ -18,57 +16,54 @@ from ..utils import (
 
 
 class NiconicoIE(InfoExtractor):
-    IE_NAME = u'niconico'
-    IE_DESC = u'ニコニコ動画'
+    IE_NAME = 'niconico'
+    IE_DESC = 'ニコニコ動画'
 
     _TEST = {
-        u'url': u'http://www.nicovideo.jp/watch/sm22312215',
-        u'file': u'sm22312215.mp4',
-        u'md5': u'd1a75c0823e2f629128c43e1212760f9',
-        u'info_dict': {
-            u'title': u'Big Buck Bunny',
-            u'uploader': u'takuya0301',
-            u'uploader_id': u'2698420',
-            u'upload_date': u'20131123',
-            u'description': u'(c) copyright 2008, Blender Foundation / www.bigbuckbunny.org',
+        'url': 'http://www.nicovideo.jp/watch/sm22312215',
+        'md5': 'd1a75c0823e2f629128c43e1212760f9',
+        'info_dict': {
+            'id': 'sm22312215',
+            'ext': 'mp4',
+            'title': 'Big Buck Bunny',
+            'uploader': 'takuya0301',
+            'uploader_id': '2698420',
+            'upload_date': '20131123',
+            'description': '(c) copyright 2008, Blender Foundation / www.bigbuckbunny.org',
         },
-        u'params': {
-            u'username': u'ydl.niconico@gmail.com',
-            u'password': u'youtube-dl',
+        'params': {
+            'username': 'ydl.niconico@gmail.com',
+            'password': 'youtube-dl',
         },
     }
 
     _VALID_URL = r'^https?://(?:www\.|secure\.)?nicovideo\.jp/watch/([a-z][a-z][0-9]+)(?:.*)$'
     _NETRC_MACHINE = 'niconico'
-    # If True it will raise an error if no login info is provided
-    _LOGIN_REQUIRED = True
 
     def _real_initialize(self):
         self._login()
 
     def _login(self):
         (username, password) = self._get_login_info()
-        # No authentication to be performed
         if username is None:
-            if self._LOGIN_REQUIRED:
-                raise ExtractorError(u'No login info available, needed for using %s.' % self.IE_NAME, expected=True)
-            return False
+            # Login is required
+            raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
 
         # Log in
         login_form_strs = {
-            u'mail': username,
-            u'password': password,
+            'mail': username,
+            'password': password,
         }
         # Convert to UTF-8 *before* urlencode because Python 2.x's urlencode
         # chokes on unicode
-        login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k,v in login_form_strs.items())
+        login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k, v in login_form_strs.items())
         login_data = compat_urllib_parse.urlencode(login_form).encode('utf-8')
         request = compat_urllib_request.Request(
-            u'https://secure.nicovideo.jp/secure/login', login_data)
+            'https://secure.nicovideo.jp/secure/login', login_data)
         login_results = self._download_webpage(
-            request, u'', note=u'Logging in', errnote=u'Unable to log in')
+            request, None, note='Logging in', errnote='Unable to log in')
         if re.search(r'(?i)<h1 class="mb8p4">Log in error</h1>', login_results) is not None:
-            self._downloader.report_warning(u'unable to log in: bad username or password')
+            self._downloader.report_warning('unable to log in: bad username or password')
             return False
         return True
 
@@ -82,12 +77,12 @@ class NiconicoIE(InfoExtractor):
 
         video_info = self._download_xml(
             'http://ext.nicovideo.jp/api/getthumbinfo/' + video_id, video_id,
-            note=u'Downloading video info page')
+            note='Downloading video info page')
 
         # Get flv info
         flv_info_webpage = self._download_webpage(
-            u'http://flapi.nicovideo.jp/api/getflv?v=' + video_id,
-            video_id, u'Downloading flv info')
+            'http://flapi.nicovideo.jp/api/getflv?v=' + video_id,
+            video_id, 'Downloading flv info')
         video_real_url = compat_urlparse.parse_qs(flv_info_webpage)['url'][0]
 
         # Start extracting information
@@ -106,22 +101,22 @@ class NiconicoIE(InfoExtractor):
         url = 'http://seiga.nicovideo.jp/api/user/info?id=' + video_uploader_id
         try:
             user_info = self._download_xml(
-                url, video_id, note=u'Downloading user information')
+                url, video_id, note='Downloading user information')
             video_uploader = user_info.find('.//nickname').text
-        except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
-            self._downloader.report_warning(u'Unable to download user info webpage: %s' % compat_str(err))
+        except ExtractorError as err:
+            self._downloader.report_warning('Unable to download user info webpage: %s' % compat_str(err))
 
         return {
-            'id':          video_id,
-            'url':         video_real_url,
-            'title':       video_title,
-            'ext':         video_extension,
-            'format':      video_format,
-            'thumbnail':   video_thumbnail,
+            'id': video_id,
+            'url': video_real_url,
+            'title': video_title,
+            'ext': video_extension,
+            'format': video_format,
+            'thumbnail': video_thumbnail,
             'description': video_description,
-            'uploader':    video_uploader,
+            'uploader': video_uploader,
             'upload_date': video_upload_date,
             'uploader_id': video_uploader_id,
-            'view_count':  video_view_count,
+            'view_count': video_view_count,
             'webpage_url': video_webpage_url,
         }

youtube_dl/extractor/ninegag.py

@@ -1,15 +1,22 @@
 from __future__ import unicode_literals
 
 import re
+import json
 
 from .common import InfoExtractor
+from ..utils import str_to_int
 
 
 class NineGagIE(InfoExtractor):
     IE_NAME = '9gag'
-    _VALID_URL = r'^https?://(?:www\.)?9gag\.tv/v/(?P<id>[0-9]+)'
+    _VALID_URL = r'''(?x)^https?://(?:www\.)?9gag\.tv/
+        (?:
+            v/(?P<numid>[0-9]+)|
+            p/(?P<id>[a-zA-Z0-9]+)/(?P<display_id>[^?#/]+)
+        )
+    '''
 
-    _TEST = {
+    _TESTS = [{
         "url": "http://9gag.tv/v/1912",
         "info_dict": {
             "id": "1912",
@@ -20,34 +27,42 @@ class NineGagIE(InfoExtractor):
             "thumbnail": "re:^https?://",
         },
         'add_ie': ['Youtube']
-    }
+    },
+    {
+        'url': 'http://9gag.tv/p/KklwM/alternate-banned-opening-scene-of-gravity?ref=fsidebar',
+        'info_dict': {
+            'id': 'KklwM',
+            'ext': 'mp4',
+            'display_id': 'alternate-banned-opening-scene-of-gravity',
+            "description": "While Gravity was a pretty awesome movie already, YouTuber Krishna Shenoi came up with a way to improve upon it, introducing a much better solution to Sandra Bullock's seemingly endless tumble in space. The ending is priceless.",
+            'title': "Banned Opening Scene Of \"Gravity\" That Changes The Whole Movie",
+        },
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = mobj.group('numid') or mobj.group('id')
+        display_id = mobj.group('display_id') or video_id
 
-        webpage = self._download_webpage(url, video_id)
+        webpage = self._download_webpage(url, display_id)
 
-        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(',', '')))
+        post_view = json.loads(self._html_search_regex(
+            r'var postView = new app\.PostView\({\s*post:\s*({.+?}),', webpage, 'post view'))
+
+        youtube_id = post_view['videoExternalId']
+        title = post_view['title']
+        description = post_view['description']
+        view_count = str_to_int(post_view['externalView'])
+        thumbnail = post_view.get('thumbnail_700w') or post_view.get('ogImageUrl') or post_view.get('thumbnail_300w')
 
         return {
             '_type': 'url_transparent',
             'url': youtube_id,
             'ie_key': 'Youtube',
             'id': video_id,
-            'title': self._og_search_title(webpage),
+            'display_id': display_id,
+            'title': title,
             'description': description,
             'view_count': view_count,
-            'thumbnail': self._og_search_thumbnail(webpage),
+            'thumbnail': thumbnail,
         }

youtube_dl/extractor/noco.py

@@ -0,0 +1,105 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    unified_strdate,
+    compat_str,
+)
+
+
+class NocoIE(InfoExtractor):
+    _VALID_URL = r'http://(?:(?:www\.)?noco\.tv/emission/|player\.noco\.tv/\?idvideo=)(?P<id>\d+)'
+
+    _TEST = {
+        'url': 'http://noco.tv/emission/11538/nolife/ami-ami-idol-hello-france/',
+        'md5': '0a993f0058ddbcd902630b2047ef710e',
+        'info_dict': {
+            'id': '11538',
+            'ext': 'mp4',
+            'title': 'Ami Ami Idol - Hello! France',
+            'description': 'md5:4eaab46ab68fa4197a317a88a53d3b86',
+            'upload_date': '20140412',
+            'uploader': 'Nolife',
+            'uploader_id': 'NOL',
+            'duration': 2851.2,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        medias = self._download_json(
+            'http://api.noco.tv/1.0/video/medias/%s' % video_id, video_id, 'Downloading video JSON')
+
+        formats = []
+
+        for fmt in medias['fr']['video_list']['default']['quality_list']:
+            format_id = fmt['quality_key']
+
+            file = self._download_json(
+                'http://api.noco.tv/1.0/video/file/%s/fr/%s' % (format_id.lower(), video_id),
+                video_id, 'Downloading %s video JSON' % format_id)
+
+            file_url = file['file']
+            if not file_url:
+                continue
+
+            if file_url == 'forbidden':
+                raise ExtractorError(
+                    '%s returned error: %s - %s' % (
+                        self.IE_NAME, file['popmessage']['title'], file['popmessage']['message']),
+                    expected=True)
+
+            formats.append({
+                'url': file_url,
+                'format_id': format_id,
+                'width': fmt['res_width'],
+                'height': fmt['res_lines'],
+                'abr': fmt['audiobitrate'],
+                'vbr': fmt['videobitrate'],
+                'filesize': fmt['filesize'],
+                'format_note': fmt['quality_name'],
+                'preference': fmt['priority'],
+            })
+
+        self._sort_formats(formats)
+
+        show = self._download_json(
+            'http://api.noco.tv/1.0/shows/show/%s' % video_id, video_id, 'Downloading show JSON')[0]
+
+        upload_date = unified_strdate(show['indexed'])
+        uploader = show['partner_name']
+        uploader_id = show['partner_key']
+        duration = show['duration_ms'] / 1000.0
+        thumbnail = show['screenshot']
+
+        episode = show.get('show_TT') or show.get('show_OT')
+        family = show.get('family_TT') or show.get('family_OT')
+        episode_number = show.get('episode_number')
+
+        title = ''
+        if family:
+            title += family
+        if episode_number:
+            title += ' #' + compat_str(episode_number)
+        if episode:
+            title += ' - ' + episode
+
+        description = show.get('show_resume') or show.get('family_resume')
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'upload_date': upload_date,
+            'uploader': uploader,
+            'uploader_id': uploader_id,
+            'duration': duration,
+            'formats': formats,
+        }

youtube_dl/extractor/novamov.py

@@ -13,7 +13,8 @@ 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'}
+    _VALID_URL_TEMPLATE = r'http://(?:(?:www\.)?%(host)s/(?:file|video)/|(?:(?:embed|www)\.)%(host)s/embed\.php\?(?:.*?&)?v=)(?P<id>[a-z\d]{13})'
+    _VALID_URL = _VALID_URL_TEMPLATE % {'host': 'novamov\.com'}
 
     _HOST = 'www.novamov.com'
 
@@ -36,18 +37,17 @@ class NovaMovIE(InfoExtractor):
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('videoid')
+        video_id = mobj.group('id')
 
         page = self._download_webpage(
             'http://%s/video/%s' % (self._HOST, video_id), video_id, 'Downloading video page')
 
         if re.search(self._FILE_DELETED_REGEX, page) is not None:
-            raise ExtractorError(u'Video %s does not exist' % video_id, expected=True)
+            raise ExtractorError('Video %s does not exist' % video_id, expected=True)
 
         filekey = self._search_regex(self._FILEKEY_REGEX, page, 'filekey')
 
         title = self._html_search_regex(self._TITLE_REGEX, page, 'title', fatal=False)
-
         description = self._html_search_regex(self._DESCRIPTION_REGEX, page, 'description', default='', fatal=False)
 
         api_response = self._download_webpage(

youtube_dl/extractor/nowvideo.py

@@ -7,7 +7,7 @@ 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)'}
+    _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'nowvideo\.(?:ch|sx|eu|at|ag|co)'}
 
     _HOST = 'www.nowvideo.ch'
 

youtube_dl/extractor/nrk.py

@@ -0,0 +1,67 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+
+class NRKIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?nrk\.no/(?:video|lyd)/[^/]+/(?P<id>[\dA-F]{16})'
+
+    _TESTS = [
+        {
+            'url': 'http://www.nrk.no/video/dompap_og_andre_fugler_i_piip_show/D0FA54B5C8B6CE59/emne/piipshow/',
+            'md5': 'a6eac35052f3b242bb6bb7f43aed5886',
+            'info_dict': {
+                'id': '150533',
+                'ext': 'flv',
+                'title': 'Dompap og andre fugler i Piip-Show',
+                'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f'
+            }
+        },
+        {
+            'url': 'http://www.nrk.no/lyd/lyd_av_oppleser_for_blinde/AEFDDD5473BA0198/',
+            'md5': '3471f2a51718195164e88f46bf427668',
+            'info_dict': {
+                'id': '154915',
+                'ext': 'flv',
+                'title': 'Slik høres internett ut når du er blind',
+                'description': 'md5:a621f5cc1bd75c8d5104cb048c6b8568',
+            }
+        },
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        page = self._download_webpage(url, video_id)
+
+        video_id = self._html_search_regex(r'<div class="nrk-video" data-nrk-id="(\d+)">', page, 'video id')
+
+        data = self._download_json(
+            'http://v7.psapi.nrk.no/mediaelement/%s' % video_id, video_id, 'Downloading media JSON')
+
+        if data['usageRights']['isGeoBlocked']:
+            raise ExtractorError('NRK har ikke rettig-heter til å vise dette programmet utenfor Norge', expected=True)
+
+        video_url = data['mediaUrl'] + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124'
+
+        images = data.get('images')
+        if images:
+            thumbnails = images['webImages']
+            thumbnails.sort(key=lambda image: image['pixelWidth'])
+            thumbnail = thumbnails[-1]['imageUrl']
+        else:
+            thumbnail = None
+
+        return {
+            'id': video_id,
+            'url': video_url,
+            'ext': 'flv',
+            'title': data['title'],
+            'description': data['description'],
+            'thumbnail': thumbnail,
+        }

youtube_dl/extractor/ntv.py

@@ -0,0 +1,149 @@
+# encoding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    unescapeHTML
+)
+
+
+class NTVIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?ntv\.ru/(?P<id>.+)'
+
+    _TESTS = [
+        {
+            'url': 'http://www.ntv.ru/novosti/863142/',
+            'info_dict': {
+                'id': '746000',
+                'ext': 'flv',
+                'title': 'Командующий Черноморским флотом провел переговоры в штабе ВМС Украины',
+                'description': 'Командующий Черноморским флотом провел переговоры в штабе ВМС Украины',
+                'duration': 136,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+        },
+        {
+            'url': 'http://www.ntv.ru/video/novosti/750370/',
+            'info_dict': {
+                'id': '750370',
+                'ext': 'flv',
+                'title': 'Родные пассажиров пропавшего Boeing не верят в трагический исход',
+                'description': 'Родные пассажиров пропавшего Boeing не верят в трагический исход',
+                'duration': 172,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+        },
+        {
+            'url': 'http://www.ntv.ru/peredacha/segodnya/m23700/o232416',
+            'info_dict': {
+                'id': '747480',
+                'ext': 'flv',
+                'title': '«Сегодня». 21 марта 2014 года. 16:00 ',
+                'description': '«Сегодня». 21 марта 2014 года. 16:00 ',
+                'duration': 1496,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+        },
+        {
+            'url': 'http://www.ntv.ru/kino/Koma_film',
+            'info_dict': {
+                'id': '758100',
+                'ext': 'flv',
+                'title': 'Остросюжетный фильм «Кома»',
+                'description': 'Остросюжетный фильм «Кома»',
+                'duration': 5592,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+        },
+        {
+            'url': 'http://www.ntv.ru/serial/Delo_vrachey/m31760/o233916/',
+            'info_dict': {
+                'id': '751482',
+                'ext': 'flv',
+                'title': '«Дело врачей»: «Деревце жизни»',
+                'description': '«Дело врачей»: «Деревце жизни»',
+                'duration': 2590,
+            },
+            'params': {
+                # rtmp download
+                'skip_download': True,
+            },
+        },
+    ]
+
+    _VIDEO_ID_REGEXES = [
+        r'<meta property="og:url" content="http://www\.ntv\.ru/video/(\d+)',
+        r'<video embed=[^>]+><id>(\d+)</id>',
+        r'<video restriction[^>]+><key>(\d+)</key>',
+    ]
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        page = self._download_webpage(url, video_id)
+
+        video_id = self._html_search_regex(self._VIDEO_ID_REGEXES, page, 'video id')
+
+        player = self._download_xml('http://www.ntv.ru/vi%s/' % video_id, video_id, 'Downloading video XML')
+        title = unescapeHTML(player.find('./data/title').text)
+        description = unescapeHTML(player.find('./data/description').text)
+
+        video = player.find('./data/video')
+        video_id = video.find('./id').text
+        thumbnail = video.find('./splash').text
+        duration = int(video.find('./totaltime').text)
+        view_count = int(video.find('./views').text)
+        puid22 = video.find('./puid22').text
+
+        apps = {
+            '4': 'video1',
+            '7': 'video2',
+        }
+
+        app = apps.get(puid22, apps['4'])
+
+        formats = []
+        for format_id in ['', 'hi', 'webm']:
+            file = video.find('./%sfile' % format_id)
+            if file is None:
+                continue
+            size = video.find('./%ssize' % format_id)
+            formats.append({
+                'url': 'rtmp://media.ntv.ru/%s' % app,
+                'app': app,
+                'play_path': file.text,
+                'rtmp_conn': 'B:1',
+                'player_url': 'http://www.ntv.ru/swf/vps1.swf?update=20131128',
+                'page_url': 'http://www.ntv.ru',
+                'flash_ver': 'LNX 11,2,202,341',
+                'rtmp_live': True,
+                'ext': 'flv',
+                'filesize': int(size.text),
+            })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'view_count': view_count,
+            'formats': formats,
+        }

youtube_dl/extractor/nytimes.py

@@ -0,0 +1,77 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import parse_iso8601
+
+
+class NYTimesIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?nytimes\.com/video/(?:[^/]+/)+(?P<id>\d+)'
+
+    _TEST = {
+        'url': 'http://www.nytimes.com/video/opinion/100000002847155/verbatim-what-is-a-photocopier.html?playlistId=100000001150263',
+        'md5': '18a525a510f942ada2720db5f31644c0',
+        'info_dict': {
+            'id': '100000002847155',
+            'ext': 'mov',
+            'title': 'Verbatim: What Is a Photocopier?',
+            'description': 'md5:93603dada88ddbda9395632fdc5da260',
+            'timestamp': 1398631707,
+            'upload_date': '20140427',
+            'uploader': 'Brett Weiner',
+            'duration': 419,
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        video_data = self._download_json(
+            'http://www.nytimes.com/svc/video/api/v2/video/%s' % video_id, video_id, 'Downloading video JSON')
+
+        title = video_data['headline']
+        description = video_data['summary']
+        duration = video_data['duration'] / 1000.0
+
+        uploader = video_data['byline']
+        timestamp = parse_iso8601(video_data['publication_date'][:-8])
+
+        def get_file_size(file_size):
+            if isinstance(file_size, int):
+                return file_size
+            elif isinstance(file_size, dict):
+                return int(file_size.get('value', 0))
+            else:
+                return 0
+
+        formats = [
+            {
+                'url': video['url'],
+                'format_id': video['type'],
+                'vcodec': video['video_codec'],
+                'width': video['width'],
+                'height': video['height'],
+                'filesize': get_file_size(video['fileSize']),
+            } for video in video_data['renditions']
+        ]
+        self._sort_formats(formats)
+
+        thumbnails = [
+            {
+                'url': 'http://www.nytimes.com/%s' % image['url'],
+                'resolution': '%dx%d' % (image['width'], image['height']),
+            } for image in video_data['images']
+        ]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'timestamp': timestamp,
+            'uploader': uploader,
+            'duration': duration,
+            'formats': formats,
+            'thumbnails': thumbnails,
+        }

youtube_dl/extractor/oe1.py

@@ -0,0 +1,40 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import calendar
+import datetime
+import re
+
+from .common import InfoExtractor
+
+# audios on oe1.orf.at are only available for 7 days, so we can't
+# add tests.
+
+
+class OE1IE(InfoExtractor):
+    IE_DESC = 'oe1.orf.at'
+    _VALID_URL = r'http://oe1\.orf\.at/programm/(?P<id>[0-9]+)'
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        show_id = mobj.group('id')
+
+        data = self._download_json(
+            'http://oe1.orf.at/programm/%s/konsole' % show_id,
+            show_id
+        )
+
+        timestamp = datetime.datetime.strptime('%s %s' % (
+            data['item']['day_label'],
+            data['item']['time']
+        ), '%d.%m.%Y %H:%M')
+        unix_timestamp = calendar.timegm(timestamp.utctimetuple())
+
+        return {
+            'id': show_id,
+            'title': data['item']['title'],
+            'url': data['item']['url_stream'],
+            'ext': 'mp3',
+            'description': data['item'].get('info'),
+            'timestamp': unix_timestamp
+        }

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>.+?)(&|$)'
+    _VALID_URL = r'(?:ooyala:|https?://.+?\.ooyala\.com/.*?(?:embedCode|ec)=)(?P<id>.+?)(&|$)'
 
     _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/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/podomatic.py

@@ -6,22 +6,36 @@ import re
 from .common import InfoExtractor
 from ..utils import int_or_none
 
-
 class PodomaticIE(InfoExtractor):
     IE_NAME = 'podomatic'
     _VALID_URL = r'^(?P<proto>https?)://(?P<channel>[^.]+)\.podomatic\.com/entry/(?P<id>[^?]+)'
 
-    _TEST = {
-        "url": "http://scienceteachingtips.podomatic.com/entry/2009-01-02T16_03_35-08_00",
-        "file": "2009-01-02T16_03_35-08_00.mp3",
-        "md5": "84bb855fcf3429e6bf72460e1eed782d",
-        "info_dict": {
-            "uploader": "Science Teaching Tips",
-            "uploader_id": "scienceteachingtips",
-            "title": "64.  When the Moon Hits Your Eye",
-            "duration": 446,
-        }
-    }
+    _TESTS = [
+        {
+            'url': 'http://scienceteachingtips.podomatic.com/entry/2009-01-02T16_03_35-08_00',
+            'md5': '84bb855fcf3429e6bf72460e1eed782d',
+            'info_dict': {
+                'id': '2009-01-02T16_03_35-08_00',
+                'ext': 'mp3',
+                'uploader': 'Science Teaching Tips',
+                'uploader_id': 'scienceteachingtips',
+                'title': '64.  When the Moon Hits Your Eye',
+                'duration': 446,
+            }
+        },
+        {
+            'url': 'http://ostbahnhof.podomatic.com/entry/2013-11-15T16_31_21-08_00',
+            'md5': 'd2cf443931b6148e27638650e2638297',
+            'info_dict': {
+                'id': '2013-11-15T16_31_21-08_00',
+                'ext': 'mp3',
+                'uploader': 'Ostbahnhof / Techno Mix',
+                'uploader_id': 'ostbahnhof',
+                'title': 'Einunddreizig',
+                'duration': 3799,
+            }
+        },
+    ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -32,10 +46,12 @@ class PodomaticIE(InfoExtractor):
                      '?permalink=true&rtmp=0') %
                     (mobj.group('proto'), channel, video_id))
         data_json = self._download_webpage(
-            json_url, video_id, note=u'Downloading video info')
+            json_url, video_id, 'Downloading video info')
         data = json.loads(data_json)
 
         video_url = data['downloadLink']
+        if not video_url:
+            video_url = '%s/%s' % (data['streamer'].replace('rtmp', 'http'), data['mediaLocation'])
         uploader = data['podcast']
         title = data['title']
         thumbnail = data['imageLocation']

youtube_dl/extractor/pornhd.py

@@ -1,44 +1,81 @@
 from __future__ import unicode_literals
 
 import re
+import json
 
 from .common import InfoExtractor
-from ..utils import compat_urllib_parse
+from ..utils import int_or_none
 
 
 class PornHdIE(InfoExtractor):
-    _VALID_URL = r'(?:http://)?(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P<video_id>[0-9]+)/(?P<video_title>.+)'
+    _VALID_URL = r'http://(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P<id>\d+)'
     _TEST = {
         'url': 'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
-        'file': '1962.flv',
-        'md5': '35272469887dca97abd30abecc6cdf75',
+        'md5': '956b8ca569f7f4d8ec563e2c41598441',
         'info_dict': {
-            "title": "sierra-day-gets-his-cum-all-over-herself-hd-porn-video",
-            "age_limit": 18,
+            'id': '1962',
+            'ext': 'mp4',
+            'title': 'Sierra loves doing laundry',
+            'description': 'md5:8ff0523848ac2b8f9b065ba781ccf294',
+            'age_limit': 18,
         }
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-
-        video_id = mobj.group('video_id')
-        video_title = mobj.group('video_title')
+        video_id = mobj.group('id')
 
         webpage = self._download_webpage(url, video_id)
 
-        next_url = self._html_search_regex(
-            r'&hd=(http.+?)&', webpage, 'video URL')
-        next_url = compat_urllib_parse.unquote(next_url)
+        title = self._og_search_title(webpage)
+        TITLE_SUFFIX = ' porn HD Video | PornHD.com '
+        if title.endswith(TITLE_SUFFIX):
+            title = title[:-len(TITLE_SUFFIX)]
 
-        video_url = self._download_webpage(
-            next_url, video_id, note='Retrieving video URL',
-            errnote='Could not retrieve video URL')
-        age_limit = 18
+        description = self._html_search_regex(
+            r'<div class="description">([^<]+)</div>', webpage, 'description', fatal=False)
+        view_count = int_or_none(self._html_search_regex(
+            r'(\d+) views 	</span>', webpage, 'view count', fatal=False))
+
+        formats = [
+            {
+                'url': format_url,
+                'ext': format.lower(),
+                'format_id': '%s-%s' % (format.lower(), quality.lower()),
+                'quality': 1 if quality.lower() == 'high' else 0,
+            } for format, quality, format_url in re.findall(
+                r'var __video([\da-zA-Z]+?)(Low|High)StreamUrl = \'(http://.+?)\?noProxy=1\'', webpage)
+        ]
+
+        mobj = re.search(r'flashVars = (?P<flashvars>{.+?});', webpage)
+        if mobj:
+            flashvars = json.loads(mobj.group('flashvars'))
+            formats.extend([
+                {
+                    'url': flashvars['hashlink'].replace('?noProxy=1', ''),
+                    'ext': 'flv',
+                    'format_id': 'flv-low',
+                    'quality': 0,
+                },
+                {
+                    'url': flashvars['hd'].replace('?noProxy=1', ''),
+                    'ext': 'flv',
+                    'format_id': 'flv-high',
+                    'quality': 1,
+                }
+            ])
+            thumbnail = flashvars['urlWallpaper']
+        else:
+            thumbnail = self._og_search_thumbnail(webpage)
+
+        self._sort_formats(formats)
 
         return {
             'id': video_id,
-            'url': video_url,
-            'ext': 'flv',
-            'title': video_title,
-            'age_limit': age_limit,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'view_count': view_count,
+            'formats': formats,
+            'age_limit': 18,
         }

youtube_dl/extractor/pornhub.py

@@ -8,6 +8,7 @@ from ..utils import (
     compat_urllib_parse_urlparse,
     compat_urllib_request,
     compat_urllib_parse,
+    str_to_int,
 )
 from ..aes import (
     aes_decrypt_text
@@ -27,6 +28,12 @@ class PornHubIE(InfoExtractor):
         }
     }
 
+    def _extract_count(self, pattern, webpage, name):
+        count = self._html_search_regex(pattern, webpage, '%s count' % name, fatal=False)
+        if count:
+            count = str_to_int(count)
+        return count
+
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('videoid')
@@ -37,11 +44,19 @@ class PornHubIE(InfoExtractor):
         webpage = self._download_webpage(req, video_id)
 
         video_title = self._html_search_regex(r'<h1 [^>]+>([^<]+)', webpage, 'title')
-        video_uploader = self._html_search_regex(r'<b>From: </b>(?:\s|<[^>]*>)*(.+?)<', webpage, 'uploader', fatal=False)
+        video_uploader = self._html_search_regex(
+            r'(?s)<div class="video-info-row">\s*From:&nbsp;.+?<(?:a href="/users/|<span class="username)[^>]+>(.+?)<',
+            webpage, 'uploader', fatal=False)
         thumbnail = self._html_search_regex(r'"image_url":"([^"]+)', webpage, 'thumbnail', fatal=False)
         if thumbnail:
             thumbnail = compat_urllib_parse.unquote(thumbnail)
 
+        view_count = self._extract_count(r'<span class="count">([\d,\.]+)</span> views', webpage, 'view')
+        like_count = self._extract_count(r'<span class="votesUp">([\d,\.]+)</span>', webpage, 'like')
+        dislike_count = self._extract_count(r'<span class="votesDown">([\d,\.]+)</span>', webpage, 'dislike')
+        comment_count = self._extract_count(
+            r'All comments \(<var class="videoCommentCount">([\d,\.]+)</var>', webpage, 'comment')
+
         video_urls = list(map(compat_urllib_parse.unquote , re.findall(r'"quality_[0-9]{3}p":"([^"]+)', webpage)))
         if webpage.find('"encrypted":true') != -1:
             password = compat_urllib_parse.unquote_plus(self._html_search_regex(r'"video_title":"([^"]+)', webpage, 'password'))
@@ -77,6 +92,10 @@ class PornHubIE(InfoExtractor):
             'uploader': video_uploader,
             'title': video_title,
             'thumbnail': thumbnail,
+            'view_count': view_count,
+            'like_count': like_count,
+            'dislike_count': dislike_count,
+            'comment_count': comment_count,
             'formats': formats,
             'age_limit': 18,
         }

youtube_dl/extractor/prosiebensat1.py

@@ -8,8 +8,6 @@ from .common import InfoExtractor
 from ..utils import (
     compat_urllib_parse,
     unified_strdate,
-    clean_html,
-    RegexNotFoundError,
 )
 
 
@@ -160,6 +158,7 @@ class ProSiebenSat1IE(InfoExtractor):
     _CLIPID_REGEXES = [
         r'"clip_id"\s*:\s+"(\d+)"',
         r'clipid: "(\d+)"',
+        r'clipId=(\d+)',
     ]
     _TITLE_REGEXES = [
         r'<h2 class="subtitle" itemprop="name">\s*(.+?)</h2>',
@@ -187,16 +186,7 @@ class ProSiebenSat1IE(InfoExtractor):
 
         page = self._download_webpage(url, video_id, 'Downloading page')
 
-        def extract(patterns, name, page, fatal=False):
-            for pattern in patterns:
-                mobj = re.search(pattern, page)
-                if mobj:
-                    return clean_html(mobj.group(1))
-            if fatal:
-                raise RegexNotFoundError(u'Unable to extract %s' % name)
-            return None
-
-        clip_id = extract(self._CLIPID_REGEXES, 'clip id', page, fatal=True)
+        clip_id = self._html_search_regex(self._CLIPID_REGEXES, page, 'clip id')
 
         access_token = 'testclient'
         client_name = 'kolibri-1.2.5'
@@ -245,13 +235,12 @@ class ProSiebenSat1IE(InfoExtractor):
 
         urls = self._download_json(url_api_url, clip_id, 'Downloading urls JSON')
 
-        title = extract(self._TITLE_REGEXES, 'title', page, fatal=True)
-        description = extract(self._DESCRIPTION_REGEXES, 'description', page)
+        title = self._html_search_regex(self._TITLE_REGEXES, page, 'title')
+        description = self._html_search_regex(self._DESCRIPTION_REGEXES, page, 'description', fatal=False)
         thumbnail = self._og_search_thumbnail(page)
 
-        upload_date = extract(self._UPLOAD_DATE_REGEXES, 'upload date', page)
-        if upload_date:
-            upload_date = unified_strdate(upload_date)
+        upload_date = unified_strdate(self._html_search_regex(
+            self._UPLOAD_DATE_REGEXES, page, 'upload date', fatal=False))
 
         formats = []
 

youtube_dl/extractor/pyvideo.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import re
 import os
 
@@ -5,45 +7,51 @@ from .common import InfoExtractor
 
 
 class PyvideoIE(InfoExtractor):
-    _VALID_URL = r'(?:http://)?(?:www\.)?pyvideo\.org/video/(?P<id>\d+)/(.*)'
-    _TESTS = [{
-        u'url': u'http://pyvideo.org/video/1737/become-a-logging-expert-in-30-minutes',
-        u'file': u'24_4WWkSmNo.mp4',
-        u'md5': u'de317418c8bc76b1fd8633e4f32acbc6',
-        u'info_dict': {
-            u"title": u"Become a logging expert in 30 minutes",
-            u"description": u"md5:9665350d466c67fb5b1598de379021f7",
-            u"upload_date": u"20130320",
-            u"uploader": u"NextDayVideo",
-            u"uploader_id": u"NextDayVideo",
+    _VALID_URL = r'http://(?:www\.)?pyvideo\.org/video/(?P<id>\d+)/(.*)'
+
+    _TESTS = [
+        {
+            'url': 'http://pyvideo.org/video/1737/become-a-logging-expert-in-30-minutes',
+            'md5': 'de317418c8bc76b1fd8633e4f32acbc6',
+            'info_dict': {
+                'id': '24_4WWkSmNo',
+                'ext': 'mp4',
+                'title': 'Become a logging expert in 30 minutes',
+                'description': 'md5:9665350d466c67fb5b1598de379021f7',
+                'upload_date': '20130320',
+                'uploader': 'NextDayVideo',
+                'uploader_id': 'NextDayVideo',
+            },
+            'add_ie': ['Youtube'],
         },
-        u'add_ie': ['Youtube'],
-    },
-    {
-        u'url': u'http://pyvideo.org/video/2542/gloriajw-spotifywitherikbernhardsson182m4v',
-        u'md5': u'5fe1c7e0a8aa5570330784c847ff6d12',
-        u'info_dict': {
-            u'id': u'2542',
-            u'ext': u'm4v',
-            u'title': u'Gloriajw-SpotifyWithErikBernhardsson182',
+        {
+            'url': 'http://pyvideo.org/video/2542/gloriajw-spotifywitherikbernhardsson182m4v',
+            'md5': '5fe1c7e0a8aa5570330784c847ff6d12',
+            'info_dict': {
+                'id': '2542',
+                'ext': 'm4v',
+                'title': 'Gloriajw-SpotifyWithErikBernhardsson182',
+            },
         },
-    },
     ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
-        webpage = self._download_webpage(url, video_id)
-        m_youtube = re.search(r'(https?://www\.youtube\.com/watch\?v=.*)', webpage)
 
+        webpage = self._download_webpage(url, video_id)
+
+        m_youtube = re.search(r'(https?://www\.youtube\.com/watch\?v=.*)', webpage)
         if m_youtube is not None:
             return self.url_result(m_youtube.group(1), 'Youtube')
 
-        title = self._html_search_regex(r'<div class="section">.*?<h3>([^>]+?)</h3>',
-            webpage, u'title', flags=re.DOTALL)
-        video_url = self._search_regex([r'<source src="(.*?)"',
-            r'<dt>Download</dt>.*?<a href="(.+?)"'],
-            webpage, u'video url', flags=re.DOTALL)
+        title = self._html_search_regex(
+            r'<div class="section">.*?<h3(?:\s+class="[^"]*")?>([^>]+?)</h3>',
+            webpage, 'title', flags=re.DOTALL)
+        video_url = self._search_regex(
+            [r'<source src="(.*?)"', r'<dt>Download</dt>.*?<a href="(.+?)"'],
+            webpage, 'video url', flags=re.DOTALL)
+
         return {
             'id': video_id,
             'title': os.path.splitext(title)[0],

youtube_dl/extractor/radiofrance.py

@@ -1,4 +1,6 @@
 # coding: utf-8
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
@@ -6,16 +8,17 @@ from .common import InfoExtractor
 
 class RadioFranceIE(InfoExtractor):
     _VALID_URL = r'^https?://maison\.radiofrance\.fr/radiovisions/(?P<id>[^?#]+)'
-    IE_NAME = u'radiofrance'
+    IE_NAME = 'radiofrance'
 
     _TEST = {
-        u'url': u'http://maison.radiofrance.fr/radiovisions/one-one',
-        u'file': u'one-one.ogg',
-        u'md5': u'bdbb28ace95ed0e04faab32ba3160daf',
-        u'info_dict': {
-            u"title": u"One to one",
-            u"description": u"Plutôt que d'imaginer la radio de demain comme technologie ou comme création de contenu, je veux montrer que quelles que soient ses évolutions, j'ai l'intime conviction que la radio continuera d'être un grand média de proximité pour les auditeurs.",
-            u"uploader": u"Thomas Hercouët",
+        'url': 'http://maison.radiofrance.fr/radiovisions/one-one',
+        'md5': 'bdbb28ace95ed0e04faab32ba3160daf',
+        'info_dict': {
+            'id': 'one-one',
+            'ext': 'ogg',
+            "title": "One to one",
+            "description": "Plutôt que d'imaginer la radio de demain comme technologie ou comme création de contenu, je veux montrer que quelles que soient ses évolutions, j'ai l'intime conviction que la radio continuera d'être un grand média de proximité pour les auditeurs.",
+            "uploader": "Thomas Hercouët",
         },
     }
 
@@ -24,27 +27,28 @@ class RadioFranceIE(InfoExtractor):
         video_id = m.group('id')
 
         webpage = self._download_webpage(url, video_id)
-        title = self._html_search_regex(r'<h1>(.*?)</h1>', webpage, u'title')
+        title = self._html_search_regex(r'<h1>(.*?)</h1>', webpage, 'title')
         description = self._html_search_regex(
             r'<div class="bloc_page_wrapper"><div class="text">(.*?)</div>',
-            webpage, u'description', fatal=False)
+            webpage, 'description', fatal=False)
         uploader = self._html_search_regex(
             r'<div class="credit">&nbsp;&nbsp;&copy;&nbsp;(.*?)</div>',
-            webpage, u'uploader', fatal=False)
+            webpage, 'uploader', fatal=False)
 
         formats_str = self._html_search_regex(
             r'class="jp-jplayer[^"]*" data-source="([^"]+)">',
-            webpage, u'audio URLs')
+            webpage, 'audio URLs')
         formats = [
             {
                 'format_id': fm[0],
                 'url': fm[1],
                 'vcodec': 'none',
+                'preference': i,
             }
-            for fm in
-            re.findall(r"([a-z0-9]+)\s*:\s*'([^']+)'", formats_str)
+            for i, fm in
+            enumerate(re.findall(r"([a-z0-9]+)\s*:\s*'([^']+)'", formats_str))
         ]
-        # No sorting, we don't know any more about these formats
+        self._sort_formats(formats)
 
         return {
             'id': video_id,