release 2014.04.13

Looks like they only offer clips instead of full episodes now. We'll need to add new parsing code as well.

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
@@ -36,6 +39,9 @@ which means you can modify it, redistribute it or use it however you like.
                                      an empty string (--proxy "") for direct
                                      connection
     --no-check-certificate           Suppress HTTPS certificate validation.
+    --prefer-insecure                Use an unencrypted connection to retrieve
+                                     information about the video. (Currently
+                                     supported only for YouTube)
     --cache-dir DIR                  Location in the filesystem where youtube-dl
                                      can store some downloaded information
                                      permanently. By default $XDG_CACHE_HOME
@@ -59,6 +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)
@@ -124,8 +131,12 @@ which means you can modify it, redistribute it or use it however you like.
                                      video id, %(playlist)s for the playlist the
                                      video is in, %(playlist_index)s for the
                                      position in the playlist and %% for a
-                                     literal percent. Use - to output to stdout.
-                                     Can also be used to download to a different
+                                     literal percent. %(height)s and %(width)s
+                                     for the width and height of the video
+                                     format. %(resolution)s for a textual
+                                     description of the resolution of the video
+                                     format. Use - to output to stdout. Can also
+                                     be used to download to a different
                                      directory, for example with -o '/my/downloa
                                      ds/%(uploader)s/%(title)s-%(id)s.%(ext)s' .
     --autonumber-size NUMBER         Specifies the number of digits in
@@ -159,6 +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
@@ -170,7 +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
@@ -187,9 +201,9 @@ which means you can modify it, redistribute it or use it however you like.
                                      preference using slashes: "-f 22/17/18".
                                      "-f mp4" and "-f flv" are also supported.
                                      You can also use the special names "best",
-                                     "bestaudio", "worst", and "worstaudio". By
-                                     default, youtube-dl will pick the best
-                                     quality.
+                                     "bestvideo", "bestaudio", "worst",
+                                     "worstvideo" and "worstaudio". By default,
+                                     youtube-dl will pick the best quality.
     --all-formats                    download all available video formats
     --prefer-free-formats            prefer free video formats unless a specific
                                      one is requested
@@ -236,6 +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)
@@ -357,7 +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=$(find youtube_dl -type f -not -name '*.py')
@@ -70,7 +76,7 @@ RELEASE_FILES="youtube-dl youtube-dl.exe youtube-dl-$version.tar.gz"
 git checkout HEAD -- youtube-dl youtube-dl.exe
 
 /bin/echo -e "\n### Signing and uploading the new binaries to yt-dl.org ..."
-for f in $RELEASE_FILES; do gpg --detach-sig "build/$version/$f"; done
+for f in $RELEASE_FILES; do gpg --passphrase-repeat 5 --detach-sig "build/$version/$f"; done
 scp -r "build/$version" ytdl@yt-dl.org:html/tmp/
 ssh ytdl@yt-dl.org "mv html/tmp/$version html/downloads/"
 ssh ytdl@yt-dl.org "sh html/update_latest.sh $version"
@@ -97,7 +103,7 @@ rm -rf build
 
 make pypi-files
 echo "Uploading to PyPi ..."
-python setup.py sdist upload
+python setup.py sdist bdist_wheel upload
 make clean
 
 /bin/echo -e "\n### DONE!"

docs/.gitignore

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

docs/Makefile

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

docs/conf.py

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

docs/index.rst

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

docs/module_guide.rst

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

setup.cfg

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

test/helper.py

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

test/test_InfoExtractor.py

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

test/test_YoutubeDL.py

@@ -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())
@@ -172,16 +182,34 @@ 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())
         downloaded = ydl.downloaded_info_dicts[0]
         self.assertEqual(downloaded['format_id'], 'vid-high')
 
+    def test_format_selection_video(self):
+        formats = [
+            {'format_id': 'dash-video-low', 'ext': 'mp4', 'preference': 1, 'acodec': 'none', 'url': '_'},
+            {'format_id': 'dash-video-high', 'ext': 'mp4', 'preference': 2, 'acodec': 'none', 'url': '_'},
+            {'format_id': 'vid', 'ext': 'mp4', 'preference': 3, 'url': '_'},
+        ]
+        info_dict = _make_result(formats)
+
+        ydl = YDL({'format': 'bestvideo'})
+        ydl.process_ie_result(info_dict.copy())
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'dash-video-high')
+
+        ydl = YDL({'format': 'worstvideo'})
+        ydl.process_ie_result(info_dict.copy())
+        downloaded = ydl.downloaded_info_dicts[0]
+        self.assertEqual(downloaded['format_id'], 'dash-video-low')
+
     def test_youtube_format_selection(self):
         order = [
             '38', '37', '46', '22', '45', '35', '44', '18', '34', '43', '6', '5', '36', '17', '13',
@@ -199,10 +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'])
@@ -210,7 +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'])

test/test_all_urls.py

@@ -9,7 +9,7 @@ import unittest
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 
-from test.helper import get_testcases
+from test.helper import gettestcases
 
 from youtube_dl.extractor import (
     FacebookIE,
@@ -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'])
@@ -71,6 +72,10 @@ class TestAllURLsMatching(unittest.TestCase):
     def test_youtube_truncated(self):
         self.assertMatch('http://www.youtube.com/watch?', ['youtube:truncated_url'])
 
+    def test_youtube_search_matching(self):
+        self.assertMatch('http://www.youtube.com/results?search_query=making+mustard', ['youtube:search_url'])
+        self.assertMatch('https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', ['youtube:search_url'])
+
     def test_justin_tv_channelid_matching(self):
         self.assertTrue(JustinTVIE.suitable(u"justin.tv/vanillatv"))
         self.assertTrue(JustinTVIE.suitable(u"twitch.tv/vanillatv"))
@@ -101,7 +106,7 @@ class TestAllURLsMatching(unittest.TestCase):
 
     def test_no_duplicates(self):
         ies = gen_extractors()
-        for tc in get_testcases():
+        for tc in gettestcases():
             url = tc['url']
             for ie in ies:
                 if type(ie).__name__ in ('GenericIE', tc['name'] + 'IE'):
@@ -120,6 +125,8 @@ class TestAllURLsMatching(unittest.TestCase):
 
     def test_vimeo_matching(self):
         self.assertMatch('http://vimeo.com/channels/tributes', ['vimeo:channel'])
+        self.assertMatch('http://vimeo.com/channels/31259', ['vimeo:channel'])
+        self.assertMatch('http://vimeo.com/channels/31259/53576664', ['vimeo'])
         self.assertMatch('http://vimeo.com/user7108434', ['vimeo:user'])
         self.assertMatch('http://vimeo.com/user7108434/videos', ['vimeo:user'])
         self.assertMatch('https://vimeo.com/user21297594/review/75524534/3c257a1b5d', ['vimeo:review'])
@@ -135,6 +142,39 @@ class TestAllURLsMatching(unittest.TestCase):
     def test_pbs(self):
         # https://github.com/rg3/youtube-dl/issues/2350
         self.assertMatch('http://video.pbs.org/viralplayer/2365173446/', ['PBS'])
+        self.assertMatch('http://video.pbs.org/widget/partnerplayer/980042464/', ['PBS'])
+
+    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

@@ -8,17 +8,17 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 from test.helper import (
     get_params,
-    get_testcases,
-    try_rm,
+    gettestcases,
+    expect_info_dict,
     md5,
-    report_warning
+    try_rm,
+    report_warning,
 )
 
 
 import hashlib
 import io
 import json
-import re
 import socket
 
 import youtube_dl.YoutubeDL
@@ -51,7 +51,7 @@ def _file_md5(fn):
     with open(fn, 'rb') as f:
         return hashlib.md5(f.read()).hexdigest()
 
-defs = get_testcases()
+defs = gettestcases()
 
 
 class TestDownload(unittest.TestCase):
@@ -73,9 +73,7 @@ def generator(test_case):
         if 'playlist' not in test_case:
             info_dict = test_case.get('info_dict', {})
             if not test_case.get('file') and not (info_dict.get('id') and info_dict.get('ext')):
-                print_skipping('The output file cannot be know, the "file" '
-                    'key is missing or the info_dict is incomplete')
-                return
+                raise Exception('Test definition incorrect. The output file cannot be known. Are both \'id\' and \'ext\' keys present?')
         if 'skip' in test_case:
             print_skipping(test_case['skip'])
             return
@@ -137,36 +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))
-                    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))
-
-                # If checkable fields are missing from the test case, print the info_dict
-                test_info_dict = dict((key, value if not isinstance(value, compat_str) or len(value) < 250 else 'md5:' + md5(value))
-                    for key, value in info_dict.items()
-                    if value and key in ('title', 'description', 'uploader', 'upload_date', 'uploader_id', 'location'))
-                if not all(key in tc.get('info_dict', {}).keys() for key in test_info_dict.keys()):
-                    sys.stderr.write(u'\n"info_dict": ' + json.dumps(test_info_dict, ensure_ascii=False, indent=4) + u'\n')
-
-                # Check for the presence of mandatory fields
-                for key in ('id', 'url', 'title', 'ext'):
-                    self.assertTrue(key in info_dict.keys() and info_dict[key])
-                # Check for mandatory fields that are automatically set by YoutubeDL
-                for key in ['webpage_url', 'extractor', 'extractor_key']:
-                    self.assertTrue(info_dict.get(key), u'Missing field: %s' % key)
+                expect_info_dict(self, tc.get('info_dict', {}), info_dict)
         finally:
             try_rm_tcs_files()
 

test/test_playlists.py

@@ -9,8 +9,10 @@ import sys
 import unittest
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
-from test.helper import FakeYDL
-
+from test.helper import (
+    expect_info_dict,
+    FakeYDL,
+)
 
 from youtube_dl.extractor import (
     AcademicEarthCourseIE,
@@ -36,6 +38,12 @@ from youtube_dl.extractor import (
     RutubeChannelIE,
     GoogleSearchIE,
     GenericIE,
+    TEDIE,
+    ToypicsUserIE,
+    XTubeUserIE,
+    InstagramUserIE,
+    CSpanIE,
+    AolIE,
 )
 
 
@@ -98,7 +106,7 @@ class TestPlaylists(unittest.TestCase):
         result = ie.extract('http://www.ustream.tv/channel/young-americans-for-liberty')
         self.assertIsPlaylist(result)
         self.assertEqual(result['id'], '5124905')
-        self.assertTrue(len(result['entries']) >= 11)
+        self.assertTrue(len(result['entries']) >= 6)
 
     def test_soundcloud_set(self):
         dl = FakeYDL()
@@ -170,12 +178,12 @@ class TestPlaylists(unittest.TestCase):
     def test_AcademicEarthCourse(self):
         dl = FakeYDL()
         ie = AcademicEarthCourseIE(dl)
-        result = ie.extract('http://academicearth.org/courses/building-dynamic-websites/')
+        result = ie.extract('http://academicearth.org/playlists/laws-of-nature/')
         self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], 'building-dynamic-websites')
-        self.assertEqual(result['title'], 'Building Dynamic Websites')
-        self.assertEqual(result['description'], u"Today's websites are increasingly dynamic. Pages are no longer static HTML files but instead generated by scripts and database calls. User interfaces are more seamless, with technologies like Ajax replacing traditional page reloads. This course teaches students how to build dynamic websites with Ajax and with Linux, Apache, MySQL, and PHP (LAMP), one of today's most popular frameworks. Students learn how to set up domain names with DNS, how to structure pages with XHTML and CSS, how to program in JavaScript and PHP, how to configure Apache and MySQL, how to design and query databases with SQL, how to use Ajax with both XML and JSON, and how to build mashups. The course explores issues of security, scalability, and cross-browser support and also discusses enterprise-level deployments of websites, including third-party hosting, virtualization, colocation in data centers, firewalling, and load-balancing.")
-        self.assertEqual(len(result['entries']), 10)
+        self.assertEqual(result['id'], 'laws-of-nature')
+        self.assertEqual(result['title'], 'Laws of Nature')
+        self.assertEqual(result['description'],u'Introduce yourself to the laws of nature with these free online college lectures from Yale, Harvard, and MIT.')# u"Today's websites are increasingly dynamic. Pages are no longer static HTML files but instead generated by scripts and database calls. User interfaces are more seamless, with technologies like Ajax replacing traditional page reloads. This course teaches students how to build dynamic websites with Ajax and with Linux, Apache, MySQL, and PHP (LAMP), one of today's most popular frameworks. Students learn how to set up domain names with DNS, how to structure pages with XHTML and CSS, how to program in JavaScript and PHP, how to configure Apache and MySQL, how to design and query databases with SQL, how to use Ajax with both XML and JSON, and how to build mashups. The course explores issues of security, scalability, and cross-browser support and also discusses enterprise-level deployments of websites, including third-party hosting, virtualization, colocation in data centers, firewalling, and load-balancing.")
+        self.assertEqual(len(result['entries']), 4)
         
     def test_ivi_compilation(self):
         dl = FakeYDL()
@@ -248,16 +256,88 @@ class TestPlaylists(unittest.TestCase):
         self.assertIsPlaylist(result)
         self.assertEqual(result['id'], 'python language')
         self.assertEqual(result['title'], 'python language')
-        self.assertTrue(len(result['entries']) == 15)
+        self.assertEqual(len(result['entries']), 15)
 
     def test_generic_rss_feed(self):
         dl = FakeYDL()
         ie = GenericIE(dl)
-        result = ie.extract('http://www.escapistmagazine.com/rss/videos/list/1.xml')
+        result = ie.extract('http://phihag.de/2014/youtube-dl/rss.xml')
         self.assertIsPlaylist(result)
-        self.assertEqual(result['id'], 'http://www.escapistmagazine.com/rss/videos/list/1.xml')
+        self.assertEqual(result['id'], 'http://phihag.de/2014/youtube-dl/rss.xml')
         self.assertEqual(result['title'], 'Zero Punctuation')
         self.assertTrue(len(result['entries']) > 10)
 
+    def test_ted_playlist(self):
+        dl = FakeYDL()
+        ie = TEDIE(dl)
+        result = ie.extract('http://www.ted.com/playlists/who_are_the_hackers')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], '10')
+        self.assertEqual(result['title'], 'Who are the hackers?')
+        self.assertTrue(len(result['entries']) >= 6)
+
+    def test_toypics_user(self):
+        dl = FakeYDL()
+        ie = ToypicsUserIE(dl)
+        result = ie.extract('http://videos.toypics.net/Mikey')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], 'Mikey')
+        self.assertTrue(len(result['entries']) >= 17)
+
+    def test_xtube_user(self):
+        dl = FakeYDL()
+        ie = XTubeUserIE(dl)
+        result = ie.extract('http://www.xtube.com/community/profile.php?user=greenshowers')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], 'greenshowers')
+        self.assertTrue(len(result['entries']) >= 155)
+
+    def test_InstagramUser(self):
+        dl = FakeYDL()
+        ie = InstagramUserIE(dl)
+        result = ie.extract('http://instagram.com/porsche')
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['id'], 'porsche')
+        self.assertTrue(len(result['entries']) >= 2)
+        test_video = next(
+            e for e in result['entries']
+            if e['id'] == '614605558512799803_462752227')
+        dl.add_default_extra_info(test_video, ie, '(irrelevant URL)')
+        dl.process_video_result(test_video, download=False)
+        EXPECTED = {
+            'id': '614605558512799803_462752227',
+            'ext': 'mp4',
+            'title': '#Porsche Intelligent Performance.',
+            'thumbnail': 're:^https?://.*\.jpg',
+            'uploader': 'Porsche',
+            'uploader_id': 'porsche',
+            'timestamp': 1387486713,
+            'upload_date': '20131219',
+        }
+        expect_info_dict(self, EXPECTED, test_video)
+
+    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_utils.py

@@ -9,6 +9,8 @@ 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
@@ -21,6 +23,7 @@ from youtube_dl.utils import (
     orderedSet,
     PagedList,
     parse_duration,
+    read_batch_urls,
     sanitize_filename,
     shell_quote,
     smuggle_url,
@@ -31,7 +34,11 @@ from youtube_dl.utils import (
     unified_strdate,
     unsmuggle_url,
     url_basename,
+    urlencode_postdata,
     xpath_with_ns,
+    parse_iso8601,
+    strip_jsonp,
+    uppercase_escape,
 )
 
 if sys.version_info < (3, 0):
@@ -250,5 +257,32 @@ class TestUtil(unittest.TestCase):
     def test_struct_unpack(self):
         self.assertEqual(struct_unpack(u'!B', b'\x00'), (0,))
 
+    def test_read_batch_urls(self):
+        f = io.StringIO(u'''\xef\xbb\xbf foo
+            bar\r
+            baz
+            # More after this line\r
+            ; or after this
+            bam''')
+        self.assertEqual(read_batch_urls(f), [u'foo', u'bar', u'baz', u'bam'])
+
+    def test_urlencode_postdata(self):
+        data = urlencode_postdata({'username': 'foo@bar.com', 'password': '1234'})
+        self.assertTrue(isinstance(data, bytes))
+
+    def test_parse_iso8601(self):
+        self.assertEqual(parse_iso8601('2014-03-23T23:04:26+0100'), 1395612266)
+        self.assertEqual(parse_iso8601('2014-03-23T22:04:26+0000'), 1395612266)
+        self.assertEqual(parse_iso8601('2014-03-23T22:04:26Z'), 1395612266)
+
+    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()

test/test_youtube_lists.py

@@ -16,6 +16,7 @@ from youtube_dl.extractor import (
     YoutubeChannelIE,
     YoutubeShowIE,
     YoutubeTopListIE,
+    YoutubeSearchURLIE,
 )
 
 
@@ -118,6 +119,8 @@ class TestYoutubeLists(unittest.TestCase):
         self.assertEqual(original_video['id'], 'rjFaenf1T-Y')
 
     def test_youtube_toptracks(self):
+        print('Skipping: The playlist page gives error 500')
+        return
         dl = FakeYDL()
         ie = YoutubePlaylistIE(dl)
         result = ie.extract('https://www.youtube.com/playlist?list=MCUS')
@@ -131,5 +134,14 @@ class TestYoutubeLists(unittest.TestCase):
         entries = result['entries']
         self.assertTrue(len(entries) >= 5)
 
+    def test_youtube_search_url(self):
+        dl = FakeYDL()
+        ie = YoutubeSearchURLIE(dl)
+        result = ie.extract('https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video')
+        entries = result['entries']
+        self.assertIsPlaylist(result)
+        self.assertEqual(result['title'], 'youtube-dl test video')
+        self.assertTrue(len(entries) >= 5)
+
 if __name__ == '__main__':
     unittest.main()

youtube_dl/InfoExtractors.py

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

youtube_dl/YoutubeDL.py

@@ -4,9 +4,11 @@
 from __future__ import absolute_import, unicode_literals
 
 import collections
+import datetime
 import errno
 import io
 import json
+import locale
 import os
 import platform
 import re
@@ -93,6 +95,7 @@ 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.
@@ -147,6 +150,8 @@ class YoutubeDL(object):
                        again.
     cookiefile:        File name where cookies should be read from and dumped to.
     nocheckcertificate:Do not verify SSL certificates
+    prefer_insecure:   Use HTTP instead of HTTPS to retrieve information.
+                       At the moment, this is only supported by YouTube.
     proxy:             URL of the proxy server to use
     socket_timeout:    Time to wait for unresponsive hosts, in seconds
     bidi_workaround:   Work around buggy terminals without bidirectional text
@@ -155,6 +160,7 @@ 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:
@@ -280,6 +286,9 @@ 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'):
@@ -289,7 +298,7 @@ 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."""
@@ -299,7 +308,7 @@ 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):
@@ -309,21 +318,21 @@ 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()
@@ -370,12 +379,17 @@ class YoutubeDL(object):
         Print the message to stderr, it will be prefixed with 'WARNING:'
         If stderr is a tty file the 'WARNING:' will be colored
         '''
-        if self._err_file.isatty() and os.name != 'nt':
-            _msg_header = '\033[0;33mWARNING:\033[0m'
+        if self.params.get('logger') is not None:
+            self.params['logger'].warning(message)
         else:
-            _msg_header = 'WARNING:'
-        warning_message = '%s %s' % (_msg_header, message)
-        self.to_stderr(warning_message)
+            if self.params.get('no_warnings'):
+                return
+            if self._err_file.isatty() and os.name != 'nt':
+                _msg_header = '\033[0;33mWARNING:\033[0m'
+            else:
+                _msg_header = 'WARNING:'
+            warning_message = '%s %s' % (_msg_header, message)
+            self.to_stderr(warning_message)
 
     def report_error(self, message, tb=None):
         '''
@@ -409,6 +423,13 @@ class YoutubeDL(object):
             template_dict['autonumber'] = autonumber_templ % self._num_downloads
             if template_dict.get('playlist_index') is not None:
                 template_dict['playlist_index'] = '%05d' % template_dict['playlist_index']
+            if template_dict.get('resolution') is None:
+                if template_dict.get('width') and template_dict.get('height'):
+                    template_dict['resolution'] = '%dx%d' % (template_dict['width'], template_dict['height'])
+                elif template_dict.get('height'):
+                    template_dict['resolution'] = '%sp' % template_dict['height']
+                elif template_dict.get('width'):
+                    template_dict['resolution'] = '?x%d' % template_dict['width']
 
             sanitize = lambda k, v: sanitize_filename(
                 compat_str(v),
@@ -499,13 +520,7 @@ class YoutubeDL(object):
                         '_type': 'compat_list',
                         'entries': ie_result,
                     }
-                self.add_extra_info(ie_result,
-                    {
-                        'extractor': ie.IE_NAME,
-                        'webpage_url': url,
-                        'webpage_url_basename': url_basename(url),
-                        'extractor_key': ie.ie_key(),
-                    })
+                self.add_default_extra_info(ie_result, ie, url)
                 if process:
                     return self.process_ie_result(ie_result, download, extra_info)
                 else:
@@ -522,7 +537,15 @@ class YoutubeDL(object):
                 else:
                     raise
         else:
-            self.report_error('no suitable InfoExtractor: %s' % url)
+            self.report_error('no suitable InfoExtractor for URL %s' % url)
+
+    def add_default_extra_info(self, ie_result, ie, url):
+        self.add_extra_info(ie_result, {
+            'extractor': ie.IE_NAME,
+            'webpage_url': url,
+            'webpage_url_basename': url_basename(url),
+            'extractor_key': ie.ie_key(),
+        })
 
     def process_ie_result(self, ie_result, download=True, extra_info={}):
         """
@@ -656,6 +679,18 @@ class YoutubeDL(object):
                 if f.get('vcodec') == 'none']
             if audio_formats:
                 return audio_formats[0]
+        elif format_spec == 'bestvideo':
+            video_formats = [
+                f for f in available_formats
+                if f.get('acodec') == 'none']
+            if video_formats:
+                return video_formats[-1]
+        elif format_spec == 'worstvideo':
+            video_formats = [
+                f for f in available_formats
+                if f.get('acodec') == 'none']
+            if video_formats:
+                return video_formats[0]
         else:
             extensions = ['mp4', 'flv', 'webm', '3gp']
             if format_spec in extensions:
@@ -670,11 +705,24 @@ 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
             info_dict['playlist_index'] = None
 
+        if 'display_id' not in info_dict and 'id' in info_dict:
+            info_dict['display_id'] = info_dict['id']
+
+        if info_dict.get('upload_date') is None and info_dict.get('timestamp') is not None:
+            upload_date = datetime.datetime.utcfromtimestamp(
+                info_dict['timestamp'])
+            info_dict['upload_date'] = upload_date.strftime('%Y%m%d')
+
         # This extractors handle format selection themselves
         if info_dict['extractor'] in ['Youku']:
             if download:
@@ -688,8 +736,14 @@ class YoutubeDL(object):
         else:
             formats = info_dict['formats']
 
+        if not formats:
+            raise ExtractorError('No video formats found!')
+
         # We check that all the formats have the format and format_id fields
-        for (i, format) in enumerate(formats):
+        for i, format in enumerate(formats):
+            if '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:
@@ -700,7 +754,7 @@ 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:
@@ -825,7 +879,7 @@ 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))
@@ -882,7 +936,7 @@ 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):
@@ -908,7 +962,7 @@ class YoutubeDL(object):
                     self.to_screen('[%s] %s: Downloading thumbnail ...' %
                                    (info_dict['extractor'], info_dict['id']))
                     try:
-                        uf = compat_urllib_request.urlopen(info_dict['thumbnail'])
+                        uf = self.urlopen(info_dict['thumbnail'])
                         with open(thumb_filename, 'wb') as thumbf:
                             shutil.copyfileobj(uf, thumbf)
                         self.to_screen('[%s] %s: Writing thumbnail to: %s' %
@@ -1154,12 +1208,22 @@ class YoutubeDL(object):
 
     def urlopen(self, req):
         """ Start an HTTP download """
-        return self._opener.open(req)
+        return self._opener.open(req, timeout=self._socket_timeout)
 
     def print_debug_header(self):
         if not self.params.get('verbose'):
             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'],
@@ -1168,24 +1232,24 @@ 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')
-        timeout = 600 if timeout_val is None else float(timeout_val)
+        self._socket_timeout = 600 if timeout_val is None else float(timeout_val)
 
         opts_cookiefile = self.params.get('cookiefile')
         opts_proxy = self.params.get('proxy')
@@ -1224,6 +1288,18 @@ class YoutubeDL(object):
         opener.addheaders = []
         self._opener = opener
 
-        # TODO remove this global modification
-        compat_urllib_request.install_opener(opener)
-        socket.setdefaulttimeout(timeout)
+    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

@@ -47,12 +47,18 @@ __authors__  = (
     'Michael Kaiser',
     'Niklas Laxström',
     'David Triendl',
+    'Anthony Weems',
+    'David Wagner',
+    'Juan C. Olivares',
+    'Mattias Harrysson',
+    'phaer',
+    'Sainyam Kapoor',
 )
 
 __license__ = 'Public Domain'
 
 import codecs
-import getpass
+import io
 import locale
 import optparse
 import os
@@ -63,6 +69,7 @@ import sys
 
 
 from .utils import (
+    compat_getpass,
     compat_print,
     DateRange,
     decodeOption,
@@ -71,6 +78,7 @@ from .utils import (
     get_cachedir,
     MaxDownloadsReached,
     preferredencoding,
+    read_batch_urls,
     SameFileError,
     setproctitle,
     std_headers,
@@ -84,6 +92,8 @@ from .extractor import gen_extractors
 from .version import __version__
 from .YoutubeDL import YoutubeDL
 from .postprocessor import (
+    AtomicParsleyPP,
+    FFmpegAudioFixPP,
     FFmpegMetadataPP,
     FFmpegVideoConvertor,
     FFmpegExtractAudioPP,
@@ -221,6 +231,9 @@ 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)
@@ -231,6 +244,9 @@ def parseOpts(overrideArguments=None):
         '--proxy', dest='proxy', default=None, metavar='URL',
         help='Use the specified HTTP/HTTPS proxy. Pass in an empty string (--proxy "") for direct connection')
     general.add_option('--no-check-certificate', action='store_true', dest='no_check_certificate', default=False, help='Suppress HTTPS certificate validation.')
+    general.add_option(
+        '--prefer-insecure', '--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',
         help='Location in the filesystem where youtube-dl can store some downloaded information permanently. By default $XDG_CACHE_HOME/youtube-dl or ~/.cache/youtube-dl . At the moment, only YouTube player files (for videos with obfuscated signatures) are cached, but that may change.')
@@ -243,14 +259,17 @@ 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',
@@ -310,7 +329,7 @@ def parseOpts(overrideArguments=None):
 
     video_format.add_option('-f', '--format',
             action='store', dest='format', metavar='FORMAT', default=None,
-            help='video format code, specify the order of preference using slashes: "-f 22/17/18". "-f mp4" and "-f flv" are also supported. You can also use the special names "best", "bestaudio", "worst", and "worstaudio". By default, youtube-dl will pick the best quality.')
+            help='video format code, specify the order of preference using slashes: "-f 22/17/18". "-f mp4" and "-f flv" are also supported. You can also use the special names "best", "bestvideo", "bestaudio", "worst", "worstvideo" and "worstaudio". By default, youtube-dl will pick the best quality.')
     video_format.add_option('--all-formats',
             action='store_const', dest='format', help='download all available video formats', const='all')
     video_format.add_option('--prefer-free-formats',
@@ -353,6 +372,10 @@ 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',
@@ -380,7 +403,7 @@ 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',
@@ -425,6 +448,8 @@ def parseOpts(overrideArguments=None):
                   '%(extractor)s for the provider (youtube, metacafe, etc), '
                   '%(id)s for the video id, %(playlist)s for the playlist the video is in, '
                   '%(playlist_index)s for the position in the playlist and %% for a literal percent. '
+                  '%(height)s and %(width)s for the width and height of the video format. '
+                  '%(resolution)s for a textual description of the resolution of the video format. '
                   'Use - to output to stdout. Can also be used to download to a different directory, '
                   'for example with -o \'/my/downloads/%(uploader)s/%(title)s-%(id)s.%(ext)s\' .'))
     filesystem.add_option('--autonumber-size',
@@ -480,6 +505,8 @@ 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,
@@ -522,8 +549,6 @@ 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
 
@@ -546,27 +571,35 @@ 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'])
         sys.exit(0)
 
     # Batch file verification
-    batchurls = []
+    batch_urls = []
     if opts.batchfile is not None:
         try:
             if opts.batchfile == '-':
                 batchfd = sys.stdin
             else:
-                batchfd = open(opts.batchfile, 'r')
-            batchurls = batchfd.readlines()
-            batchurls = [x.strip() for x in batchurls]
-            batchurls = [x for x in batchurls if len(x) > 0 and not re.search(r'^[#/;]', x)]
+                batchfd = io.open(opts.batchfile, 'r', encoding='utf-8', errors='ignore')
+            batch_urls = read_batch_urls(batchfd)
             if opts.verbose:
-                write_string(u'[debug] Batch file urls: ' + repr(batchurls) + u'\n')
+                write_string(u'[debug] Batch file urls: ' + repr(batch_urls) + u'\n')
         except IOError:
             sys.exit(u'ERROR: batch file could not be read')
-    all_urls = batchurls + args
+    all_urls = batch_urls + args
     all_urls = [url.strip() for url in all_urls]
     _enc = preferredencoding()
     all_urls = [url.decode(_enc, 'ignore') if isinstance(url, bytes) else url for url in all_urls]
@@ -605,7 +638,7 @@ def _real_main(argv=None):
     if opts.usetitle and opts.useid:
         parser.error(u'using title conflicts with using video ID')
     if opts.username is not None and opts.password is None:
-        opts.password = getpass.getpass(u'Type account password and press return:')
+        opts.password = compat_getpass(u'Type account password and press [Return]: ')
     if opts.ratelimit is not None:
         numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
         if numeric_limit is None:
@@ -649,7 +682,7 @@ def _real_main(argv=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
@@ -687,6 +720,7 @@ 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,
@@ -750,6 +784,7 @@ def _real_main(argv=None):
         'download_archive': download_archive_fn,
         'cookiefile': opts.cookiefile,
         'nocheckcertificate': opts.no_check_certificate,
+        'prefer_insecure': opts.prefer_insecure,
         'proxy': opts.proxy,
         'socket_timeout': opts.socket_timeout,
         'bidi_workaround': opts.bidi_workaround,
@@ -758,6 +793,7 @@ 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:
@@ -776,6 +812,10 @@ 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

@@ -23,6 +23,8 @@ 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)
 
@@ -49,7 +51,7 @@ class HttpFD(FileDownloader):
         while count <= retries:
             # Establish connection
             try:
-                data = compat_urllib_request.urlopen(request)
+                data = self.ydl.urlopen(request)
                 break
             except (compat_urllib_error.HTTPError, ) as err:
                 if (err.code < 500 or err.code >= 600) and err.code != 416:
@@ -59,7 +61,7 @@ class HttpFD(FileDownloader):
                     # Unable to resume (requested range not satisfiable)
                     try:
                         # Open the connection again without the range header
-                        data = compat_urllib_request.urlopen(basic_request)
+                        data = self.ydl.urlopen(basic_request)
                         content_length = data.info()['Content-Length']
                     except (compat_urllib_error.HTTPError, ) as err:
                         if err.code < 500 or err.code >= 600:
@@ -85,6 +87,7 @@ class HttpFD(FileDownloader):
                         else:
                             # The length does not match, we start the download over
                             self.report_unable_to_resume()
+                            resume_len = 0
                             open_mode = 'wb'
                             break
             # Retry

youtube_dl/downloader/rtmp.py

@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+
 import os
 import re
 import subprocess
@@ -22,7 +24,7 @@ class RtmpFD(FileDownloader):
             proc_stderr_closed = False
             while not proc_stderr_closed:
                 # read line from stderr
-                line = u''
+                line = ''
                 while True:
                     char = proc.stderr.read(1)
                     if not char:
@@ -46,7 +48,7 @@ class RtmpFD(FileDownloader):
                     data_len = None
                     if percent > 0:
                         data_len = int(downloaded_data_len * 100 / percent)
-                    data_len_str = u'~' + format_bytes(data_len)
+                    data_len_str = '~' + format_bytes(data_len)
                     self.report_progress(percent, data_len_str, speed, eta)
                     cursor_in_new_line = False
                     self._hook_progress({
@@ -76,12 +78,12 @@ class RtmpFD(FileDownloader):
                         })
                     elif self.params.get('verbose', False):
                         if not cursor_in_new_line:
-                            self.to_screen(u'')
+                            self.to_screen('')
                         cursor_in_new_line = True
-                        self.to_screen(u'[rtmpdump] '+line)
+                        self.to_screen('[rtmpdump] '+line)
             proc.wait()
             if not cursor_in_new_line:
-                self.to_screen(u'')
+                self.to_screen('')
             return proc.returncode
 
         url = info_dict['url']
@@ -102,7 +104,7 @@ class RtmpFD(FileDownloader):
         try:
             subprocess.call(['rtmpdump', '-h'], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
         except (OSError, IOError):
-            self.report_error(u'RTMP download detected but "rtmpdump" could not be run')
+            self.report_error('RTMP download detected but "rtmpdump" could not be run')
             return False
 
         # Download using rtmpdump. rtmpdump returns exit code 2 when
@@ -127,7 +129,7 @@ class RtmpFD(FileDownloader):
             basic_args += ['--live']
         if conn:
             basic_args += ['--conn', conn]
-        args = basic_args + [[], ['--resume', '--skip', '1']][self.params.get('continuedl', False)]
+        args = basic_args + [[], ['--resume', '--skip', '1']][not live and self.params.get('continuedl', False)]
 
         if sys.platform == 'win32' and sys.version_info < (3, 0):
             # Windows subprocess module does not actually support Unicode
@@ -150,26 +152,35 @@ class RtmpFD(FileDownloader):
                 shell_quote = lambda args: ' '.join(map(pipes.quote, str_args))
             except ImportError:
                 shell_quote = repr
-            self.to_screen(u'[debug] rtmpdump command line: ' + shell_quote(str_args))
+            self.to_screen('[debug] rtmpdump command line: ' + shell_quote(str_args))
+
+        RD_SUCCESS = 0
+        RD_FAILED = 1
+        RD_INCOMPLETE = 2
+        RD_NO_CONNECT = 3
 
         retval = run_rtmpdump(args)
 
-        while (retval == 2 or retval == 1) and not test:
+        if retval == RD_NO_CONNECT:
+            self.report_error('[rtmpdump] Could not connect to RTMP server.')
+            return False
+
+        while (retval == RD_INCOMPLETE or retval == RD_FAILED) and not test and not live:
             prevsize = os.path.getsize(encodeFilename(tmpfilename))
-            self.to_screen(u'[rtmpdump] %s bytes' % prevsize)
+            self.to_screen('[rtmpdump] %s bytes' % prevsize)
             time.sleep(5.0) # This seems to be needed
-            retval = run_rtmpdump(basic_args + ['-e'] + [[], ['-k', '1']][retval == 1])
+            retval = run_rtmpdump(basic_args + ['-e'] + [[], ['-k', '1']][retval == RD_FAILED])
             cursize = os.path.getsize(encodeFilename(tmpfilename))
-            if prevsize == cursize and retval == 1:
+            if prevsize == cursize and retval == RD_FAILED:
                 break
              # Some rtmp streams seem abort after ~ 99.8%. Don't complain for those
-            if prevsize == cursize and retval == 2 and cursize > 1024:
-                self.to_screen(u'[rtmpdump] Could not download the whole video. This can happen for some advertisements.')
-                retval = 0
+            if prevsize == cursize and retval == RD_INCOMPLETE and cursize > 1024:
+                self.to_screen('[rtmpdump] Could not download the whole video. This can happen for some advertisements.')
+                retval = RD_SUCCESS
                 break
-        if retval == 0 or (test and retval == 2):
+        if retval == RD_SUCCESS or (test and retval == RD_INCOMPLETE):
             fsize = os.path.getsize(encodeFilename(tmpfilename))
-            self.to_screen(u'[rtmpdump] %s bytes' % fsize)
+            self.to_screen('[rtmpdump] %s bytes' % fsize)
             self.try_rename(tmpfilename, filename)
             self._hook_progress({
                 'downloaded_bytes': fsize,
@@ -179,6 +190,6 @@ class RtmpFD(FileDownloader):
             })
             return True
         else:
-            self.to_stderr(u"\n")
-            self.report_error(u'rtmpdump exited with code %d' % retval)
+            self.to_stderr('\n')
+            self.report_error('rtmpdump exited with code %d' % retval)
             return False

youtube_dl/extractor/__init__.py

@@ -1,6 +1,8 @@
 from .academicearth import AcademicEarthCourseIE
 from .addanime import AddAnimeIE
+from .aftonbladet import AftonbladetIE
 from .anitube import AnitubeIE
+from .aol import AolIE
 from .aparat import AparatIE
 from .appletrailers import AppleTrailersIE
 from .archiveorg import ArchiveOrgIE
@@ -9,8 +11,10 @@ from .arte import (
     ArteTvIE,
     ArteTVPlus7IE,
     ArteTVCreativeIE,
+    ArteTVConcertIE,
     ArteTVFutureIE,
     ArteTVDDCIE,
+    ArteTVEmbedIE,
 )
 from .auengine import AUEngineIE
 from .bambuser import BambuserIE, BambuserChannelIE
@@ -22,10 +26,14 @@ 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
 from .cinemassacre import CinemassacreIE
@@ -33,6 +41,7 @@ from .clipfish import ClipfishIE
 from .cliphunter import CliphunterIE
 from .clipsyndicate import ClipsyndicateIE
 from .cmt import CMTIE
+from .cnet import CNETIE
 from .cnn import (
     CNNIE,
     CNNBlogsIE,
@@ -50,17 +59,18 @@ from .dailymotion import (
     DailymotionUserIE,
 )
 from .daum import DaumIE
-from .depositfiles import DepositFilesIE
 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
@@ -69,12 +79,14 @@ 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,
@@ -89,6 +101,7 @@ from .funnyordie import FunnyOrDieIE
 from .gamekings import GamekingsIE
 from .gamespot import GameSpotIE
 from .gametrailers import GametrailersIE
+from .gdcvault import GDCVaultIE
 from .generic import GenericIE
 from .googleplus import GooglePlusIE
 from .googlesearch import GoogleSearchIE
@@ -105,7 +118,7 @@ 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 (
@@ -133,26 +146,34 @@ from .lynda import (
 )
 from .m6 import M6IE
 from .macgamestore import MacGameStoreIE
+from .mailru import MailRuIE
 from .malemotion import MalemotionIE
 from .mdr import MDRIE
 from .metacafe import MetacafeIE
 from .metacritic import MetacriticIE
-from .mit import TechTVMITIE, MITIE
+from .mit import TechTVMITIE, MITIE, OCWMITIE
 from .mixcloud import MixcloudIE
 from .mpora import MporaIE
 from .mofosex import MofosexIE
 from .mooshare import MooshareIE
+from .morningstar import MorningstarIE
+from .motorsport import MotorsportIE
+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
 from .myvideo import MyVideoIE
 from .naver import NaverIE
 from .nba import NBAIE
-from .nbc import NBCNewsIE
+from .nbc import (
+    NBCIE,
+    NBCNewsIE,
+)
 from .ndr import NDRIE
 from .ndtv import NDTVIE
 from .newgrounds import NewgroundsIE
@@ -161,17 +182,22 @@ from .nhl import NHLIE, NHLVideocenterIE
 from .niconico import NiconicoIE
 from .ninegag import NineGagIE
 from .normalboots import NormalbootsIE
-from .novamov import NovamovIE
+from .novamov import NovaMovIE
 from .nowness import NownessIE
 from .nowvideo import NowVideoIE
+from .ntv import NTVIE
+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
 from .podomatic import PodomaticIE
 from .pornhd import PornHdIE
 from .pornhub import PornHubIE
 from .pornotube import PornotubeIE
+from .prosiebensat1 import ProSiebenSat1IE
 from .pyvideo import PyvideoIE
 from .radiofrance import RadioFranceIE
 from .rbmaradio import RBMARadioIE
@@ -181,16 +207,18 @@ from .ro220 import Ro220IE
 from .rottentomatoes import RottenTomatoesIE
 from .roxwel import RoxwelIE
 from .rtlnow import RTLnowIE
+from .rts import RTSIE
+from .rtve import RTVEALaCartaIE
 from .rutube import (
     RutubeIE,
     RutubeChannelIE,
     RutubeMovieIE,
     RutubePersonIE,
 )
+from .rutv import RUTVIE
 from .savefrom import SaveFromIE
 from .servingsys import ServingSysIE
 from .sina import SinaIE
-from .slashdot import SlashdotIE
 from .slideshare import SlideshareIE
 from .smotri import (
     SmotriIE,
@@ -224,6 +252,7 @@ from .theplatform import ThePlatformIE
 from .thisav import ThisAVIE
 from .tinypic import TinyPicIE
 from .toutv import TouTvIE
+from .toypics import ToypicsUserIE, ToypicsIE
 from .traileraddict import TrailerAddictIE
 from .trilulilu import TriluliluIE
 from .trutube import TruTubeIE
@@ -231,20 +260,27 @@ from .tube8 import Tube8IE
 from .tudou import TudouIE
 from .tumblr import TumblrIE
 from .tutv import TutvIE
+from .tvigle import TvigleIE
 from .tvp import TvpIE
+from .udemy import (
+    UdemyIE,
+    UdemyCourseIE
+)
 from .unistra import UnistraIE
+from .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 .videoweed import VideoWeedIE
 from .vimeo import (
     VimeoIE,
     VimeoChannelIE,
@@ -257,15 +293,21 @@ from .vine import VineIE
 from .viki import VikiIE
 from .vk import VKIE
 from .vube import VubeIE
+from .washingtonpost import WashingtonPostIE
 from .wat import WatIE
+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,
@@ -276,19 +318,20 @@ from .youku import YoukuIE
 from .youporn import YouPornIE
 from .youtube import (
     YoutubeIE,
-    YoutubePlaylistIE,
-    YoutubeSearchIE,
-    YoutubeSearchDateIE,
-    YoutubeUserIE,
     YoutubeChannelIE,
-    YoutubeShowIE,
-    YoutubeSubscriptionsIE,
-    YoutubeRecommendedIE,
-    YoutubeTruncatedURLIE,
-    YoutubeWatchLaterIE,
     YoutubeFavouritesIE,
     YoutubeHistoryIE,
+    YoutubePlaylistIE,
+    YoutubeRecommendedIE,
+    YoutubeSearchDateIE,
+    YoutubeSearchIE,
+    YoutubeSearchURLIE,
+    YoutubeShowIE,
+    YoutubeSubscriptionsIE,
     YoutubeTopListIE,
+    YoutubeTruncatedURLIE,
+    YoutubeUserIE,
+    YoutubeWatchLaterIE,
 )
 from .zdf import ZDFIE
 

youtube_dl/extractor/academicearth.py

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

youtube_dl/extractor/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/aftonbladet.py

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

youtube_dl/extractor/aol.py

@@ -0,0 +1,65 @@
+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 (
@@ -19,115 +18,46 @@ 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(u'Arte live streams are not yet supported, sorry')
-            # self.extractLiveStream(url)
-            # return
-
-    def _extract_video(self, url, video_id, lang):
-        """Extract from videos.arte.tv"""
         ref_xml_url = url.replace('/videos/', '/do_delegate/videos/')
         ref_xml_url = ref_xml_url.replace('.html', ',view,asPlayerXml.xml')
-        ref_xml_doc = self._download_xml(ref_xml_url, video_id, note=u'Downloading metadata')
+        ref_xml_doc = self._download_xml(
+            ref_xml_url, video_id, note='Downloading metadata')
         config_node = find_xpath_attr(ref_xml_doc, './/video', 'lang', lang)
         config_xml_url = config_node.attrib['ref']
-        config_xml = self._download_webpage(config_xml_url, video_id, note=u'Downloading configuration')
+        config = 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):
     IE_NAME = 'arte.tv:+7'
-    _VALID_URL = r'https?://www\.arte.tv/guide/(?P<lang>fr|de)/(?:(?:sendungen|emissions)/)?(?P<id>.*?)/(?P<name>.*?)(\?.*)?'
+    _VALID_URL = r'https?://(?:www\.)?arte\.tv/guide/(?P<lang>fr|de)/(?:(?:sendungen|emissions)/)?(?P<id>.*?)/(?P<name>.*?)(\?.*)?'
 
     @classmethod
     def _extract_url_info(cls, url):
@@ -148,9 +78,7 @@ class ArteTVPlus7IE(InfoExtractor):
         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 = {
@@ -172,6 +100,8 @@ 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
@@ -198,6 +128,8 @@ class ArteTVPlus7IE(InfoExtractor):
                     re.match(r'VO-ST(F|A)', f.get('versionCode', '')) is None,
                     # The version with sourds/mal subtitles has also lower relevance
                     re.match(r'VO?(F|A)-STM\1', f.get('versionCode', '')) is None,
+                    # Prefer http downloads over m3u8
+                    0 if f['url'].endswith('m3u8') else 1,
                 )
         formats = sorted(formats, key=sort_key)
         def _format(format_info):
@@ -238,8 +170,9 @@ class ArteTVCreativeIE(ArteTVPlus7IE):
 
     _TEST = {
         'url': 'http://creative.arte.tv/de/magazin/agentur-amateur-corporate-design',
-        'file': '050489-002.mp4',
         'info_dict': {
+            'id': '050489-002',
+            'ext': 'mp4',
             'title': 'Agentur Amateur / Agence Amateur #2 : Corporate Design',
         },
     }
@@ -251,8 +184,9 @@ class ArteTVFutureIE(ArteTVPlus7IE):
 
     _TEST = {
         'url': 'http://future.arte.tv/fr/sujet/info-sciences#article-anchor-7081',
-        'file': '050940-003.mp4',
         'info_dict': {
+            'id': '050940-003',
+            'ext': 'mp4',
             'title': 'Les champignons au secours de la planète',
         },
     }
@@ -266,7 +200,7 @@ class ArteTVFutureIE(ArteTVPlus7IE):
 
 class ArteTVDDCIE(ArteTVPlus7IE):
     IE_NAME = 'arte.tv:ddc'
-    _VALID_URL = r'http?://ddc\.arte\.tv/(?P<lang>emission|folge)/(?P<id>.+)'
+    _VALID_URL = r'https?://ddc\.arte\.tv/(?P<lang>emission|folge)/(?P<id>.+)'
 
     def _real_extract(self, url):
         video_id, lang = self._extract_url_info(url)
@@ -280,3 +214,39 @@ class ArteTVDDCIE(ArteTVPlus7IE):
         javascriptPlayerGenerator = self._download_webpage(script_url, video_id, 'Download javascript player generator')
         json_url = self._search_regex(r"json_url=(.*)&rendering_place.*", javascriptPlayerGenerator, 'json url')
         return self._extract_from_json_url(json_url, video_id, lang)
+
+
+class ArteTVConcertIE(ArteTVPlus7IE):
+    IE_NAME = 'arte.tv:concert'
+    _VALID_URL = r'https?://concert\.arte\.tv/(?P<lang>de|fr)/(?P<id>.+)'
+
+    _TEST = {
+        'url': 'http://concert.arte.tv/de/notwist-im-pariser-konzertclub-divan-du-monde',
+        'md5': '9ea035b7bd69696b67aa2ccaaa218161',
+        'info_dict': {
+            'id': '186',
+            'ext': 'mp4',
+            'title': 'The Notwist im Pariser Konzertclub "Divan du Monde"',
+            'upload_date': '20140128',
+            'description': 'md5:486eb08f991552ade77439fe6d82c305',
+        },
+    }
+
+
+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/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

@@ -4,77 +4,136 @@ 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/)?(?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'
 
-    _TEST = {
-        "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"
-        }
-    }
+    _TESTS = [
+        {
+            'url': 'http://www.br.de/mediathek/video/anselm-gruen-114.html',
+            'md5': 'c4f83cf0f023ba5875aba0bf46860df2',
+            'info_dict': {
+                'id': '2c8d81c5-6fb7-4a74-88d4-e768e5856532',
+                'ext': 'mp4',
+                'title': 'Feiern und Verzichten',
+                'description': 'Anselm Grün: Feiern und Verzichten',
+                'uploader': 'BR/Birgit Baier',
+                'upload_date': '20140301',
+            }
+        },
+        {
+            'url': 'http://www.br.de/mediathek/video/sendungen/unter-unserem-himmel/unter-unserem-himmel-alpen-ueber-den-pass-100.html',
+            'md5': 'ab451b09d861dbed7d7cc9ab0be19ebe',
+            'info_dict': {
+                'id': '2c060e69-3a27-4e13-b0f0-668fac17d812',
+                'ext': 'mp4',
+                'title': 'Über den Pass',
+                'description': 'Die Eroberung der Alpen: Über den Pass',
+            }
+        },
+        {
+            '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):
         mobj = re.match(self._VALID_URL, url)
         display_id = mobj.group('id')
         page = self._download_webpage(url, display_id)
         xml_url = self._search_regex(
-            r"return BRavFramework\.register\(BRavFramework\('avPlayer_(?:[a-f0-9-]{36})'\)\.setup\({dataURL:'(/mediathek/video/[a-z0-9/~_.-]+)'}\)\);", page, "XMLURL")
+            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 = [{
-            "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()),
-            "uploader": xml_video.find("author").text,
-            "upload_date": "".join(reversed(xml_video.find("broadcastDate").text.split("."))),
-            "webpage_url": xml_video.find("permalink").text,
-        } for xml_video in xml.findall("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

@@ -23,13 +23,14 @@ class BreakIE(InfoExtractor):
         video_id = mobj.group(1).split("-")[-1]
         embed_url = 'http://www.break.com/embed/%s' % video_id
         webpage = self._download_webpage(embed_url, video_id)
-        info_json = self._search_regex(r'var embedVars = ({.*?});', webpage,
-                                       'info json', flags=re.DOTALL)
+        info_json = self._search_regex(r'var embedVars = ({.*})\s*?</script>',
+            webpage, 'info json', flags=re.DOTALL)
         info = json.loads(info_json)
         video_url = info['videoUri']
-        m_youtube = re.search(r'(https?://www\.youtube\.com/watch\?v=.*)', video_url)
-        if m_youtube is not None:
-            return self.url_result(m_youtube.group(1), 'Youtube')
+        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/canal13cl.py

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

youtube_dl/extractor/canalplus.py

@@ -28,7 +28,7 @@ class CanalplusIE(InfoExtractor):
         video_id = mobj.groupdict().get('id')
         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')
+            video_id = self._search_regex(r'<canal:player videoId="(\d+)"', webpage, u'video id')
         info_url = self._VIDEO_INFO_TEMPLATE % video_id
         doc = self._download_xml(info_url,video_id, 
                                            u'Downloading video info')

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/ceskatelevize.py

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

youtube_dl/extractor/cinemassacre.py

@@ -1,4 +1,5 @@
 # encoding: utf-8
+from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
@@ -8,77 +9,71 @@ from ..utils import (
 
 
 class CinemassacreIE(InfoExtractor):
-    _VALID_URL = r'(?:http://)?(?:www\.)?(?P<url>cinemassacre\.com/(?P<date_Y>[0-9]{4})/(?P<date_m>[0-9]{2})/(?P<date_d>[0-9]{2})/.+?)(?:[/?].*)?'
-    _TESTS = [{
-        u'url': u'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/',
-        u'file': u'19911.flv',
-        u'info_dict': {
-            u'upload_date': u'20121110',
-            u'title': u'“Angry Video Game Nerd: The Movie” – Trailer',
-            u'description': u'md5:fb87405fcb42a331742a0dce2708560b',
+    _VALID_URL = r'http://(?:www\.)?cinemassacre\.com/(?P<date_Y>[0-9]{4})/(?P<date_m>[0-9]{2})/(?P<date_d>[0-9]{2})/(?P<display_id>[^?#/]+)'
+    _TESTS = [
+        {
+            'url': 'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/',
+            'file': '19911.mp4',
+            'md5': '782f8504ca95a0eba8fc9177c373eec7',
+            'info_dict': {
+                'upload_date': '20121110',
+                'title': '“Angry Video Game Nerd: The Movie” – Trailer',
+                'description': 'md5:fb87405fcb42a331742a0dce2708560b',
+            },
         },
-        u'params': {
-            # rtmp download
-            u'skip_download': True,
-        },
-    },
-    {
-        u'url': u'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940',
-        u'file': u'521be8ef82b16.flv',
-        u'info_dict': {
-            u'upload_date': u'20131002',
-            u'title': u'The Mummy’s Hand (1940)',
-        },
-        u'params': {
-            # rtmp download
-            u'skip_download': True,
-        },
-    }]
+        {
+            'url': 'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940',
+            'file': '521be8ef82b16.mp4',
+            'md5': 'dec39ee5118f8d9cc067f45f9cbe3a35',
+            'info_dict': {
+                'upload_date': '20131002',
+                'title': 'The Mummy’s Hand (1940)',
+            },
+        }
+    ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
+        display_id = mobj.group('display_id')
 
-        webpage_url = u'http://' + mobj.group('url')
-        webpage = self._download_webpage(webpage_url, None) # Don't know video id yet
+        webpage = self._download_webpage(url, 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:
-            raise ExtractorError(u'Can\'t extract embed url and video id')
-        playerdata_url = mobj.group(u'embed_url')
-        video_id = mobj.group(u'video_id')
+            raise ExtractorError('Can\'t extract embed url and video id')
+        playerdata_url = mobj.group('embed_url')
+        video_id = mobj.group('video_id')
 
-        video_title = self._html_search_regex(r'<title>(?P<title>.+?)\|',
-            webpage, u'title')
-        video_description = self._html_search_regex(r'<div class="entry-content">(?P<description>.+?)</div>',
-            webpage, u'description', flags=re.DOTALL, fatal=False)
-        if len(video_description) == 0:
-            video_description = None
+        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)
 
         playerdata = self._download_webpage(playerdata_url, video_id)
-        url = self._html_search_regex(r'\'streamer\': \'(?P<url>[^\']+)\'', playerdata, u'url')
 
-        sd_file = self._html_search_regex(r'\'file\': \'(?P<sd_file>[^\']+)\'', playerdata, u'sd_file')
-        hd_file = self._html_search_regex(r'\'?file\'?: "(?P<hd_file>[^"]+)"', playerdata, u'hd_file')
-        video_thumbnail = self._html_search_regex(r'\'image\': \'(?P<thumbnail>[^\']+)\'', playerdata, u'thumbnail', fatal=False)
+        sd_url = self._html_search_regex(r'file: \'([^\']+)\', 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': url,
-                'play_path': 'mp4:' + sd_file,
-                'rtmp_live': True, # workaround
-                'ext': 'flv',
-                'format': 'sd',
-                'format_id': 'sd',
-            },
-            {
-                'url': url,
-                'play_path': 'mp4:' + hd_file,
-                'rtmp_live': True, # workaround
-                'ext': 'flv',
+        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/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\" 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/collegehumor.py

@@ -17,8 +17,9 @@ class CollegeHumorIE(InfoExtractor):
             'id': '6902724',
             'ext': 'mp4',
             'title': 'Comic-Con Cosplay Catastrophe',
-            'description': 'Fans get creative this year',
+            'description': "Fans get creative this year at San Diego.  Too creative.  And yes, that's really Joss Whedon.",
             'age_limit': 13,
+            'duration': 187,
         },
     },
     {
@@ -28,22 +29,22 @@ class CollegeHumorIE(InfoExtractor):
             'id': '3505939',
             'ext': 'mp4',
             'title': 'Font Conference',
-            'description': 'This video wasn\'t long enough,',
+            'description': "This video wasn't long enough, so we made it double-spaced.",
             'age_limit': 10,
             'duration': 179,
         },
     },
     # embedded youtube video
     {
-        'url': 'http://www.collegehumor.com/embed/6950457',
+        'url': 'http://www.collegehumor.com/embed/6950306',
         'info_dict': {
-            'id': 'W5gMp3ZjYg4',
+            'id': 'Z-bao9fg6Yc',
             'ext': 'mp4',
-            'title': 'Funny Dogs Protecting Babies Compilation 2014 [NEW HD]',
-            'uploader': 'Funnyplox TV',
-            'uploader_id': 'funnyploxtv',
-            'description': 'md5:7ded37421526d54afdf005e25bc2b7a3',
-            'upload_date': '20140128',
+            'title': 'Young Americans Think President John F. Kennedy Died THIS MORNING IN A CAR ACCIDENT!!!',
+            'uploader': 'Mark Dice',
+            'uploader_id': 'MarkDice',
+            'description': 'md5:62c3dab9351fac7bb44b53b69511d87f',
+            'upload_date': '20140127',
         },
         'params': {
             'skip_download': True,
@@ -87,6 +88,7 @@ class CollegeHumorIE(InfoExtractor):
         self._sort_formats(formats)
 
         duration = int_or_none(vdata.get('duration'), 1000)
+        like_count = int_or_none(vdata.get('likes'))
 
         return {
             'id': video_id,
@@ -96,4 +98,5 @@ class CollegeHumorIE(InfoExtractor):
             'formats': formats,
             'age_limit': age_limit,
             'duration': duration,
+            'like_count': like_count,
         }

youtube_dl/extractor/comedycentral.py

@@ -7,21 +7,21 @@ from .mtv import MTVServicesInfoExtractor
 from ..utils import (
     compat_str,
     compat_urllib_parse,
-
     ExtractorError,
+    float_or_none,
     unified_strdate,
 )
 
 
 class ComedyCentralIE(MTVServicesInfoExtractor):
-    _VALID_URL = r'''(?x)https?://(?:www\.)?comedycentral\.com/
+    _VALID_URL = r'''(?x)https?://(?:www\.)?(comedycentral|cc)\.com/
         (video-clips|episodes|cc-studios|video-collections)
         /(?P<title>.*)'''
     _FEED_URL = 'http://comedycentral.com/feeds/mrss/'
 
     _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
@@ -88,12 +88,18 @@ class InfoExtractor(object):
 
     The following fields are optional:
 
+    display_id      An alternative identifier for the video, not necessarily
+                    unique, but available before title. Typically, id is
+                    something like "4234987", title "Dancing naked mole rats",
+                    and display_id "dancing-naked-mole-rats"
     thumbnails:     A list of dictionaries (with the entries "resolution" and
                     "url") for the varying thumbnails
     thumbnail:      Full URL to a video thumbnail image.
     description:    One-line video description.
     uploader:       Full name of the video uploader.
+    timestamp:      UNIX timestamp of the moment the video became available.
     upload_date:    Video upload date (YYYYMMDD).
+                    If not explicitly set, calculated from timestamp.
     uploader_id:    Nickname or id of the video uploader.
     location:       Physical location of the video.
     subtitles:      The subtitle file contents as a dictionary in the format
@@ -114,9 +120,6 @@ class InfoExtractor(object):
     _real_extract() methods and define a _VALID_URL regexp.
     Probably, they should also be added to the list of extractors.
 
-    _real_extract() must return a *list* of information dictionaries as
-    described above.
-
     Finally, the _WORKING attribute should be set to False for broken IEs
     in order to warn the users and skip the tests.
     """
@@ -248,7 +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):
@@ -432,14 +449,14 @@ class InfoExtractor(object):
         if secure: regexes = self._og_regexes('video:secure_url') + regexes
         return self._html_search_regex(regexes, html, name, **kargs)
 
-    def _html_search_meta(self, name, html, display_name=None):
+    def _html_search_meta(self, name, html, display_name=None, fatal=False):
         if display_name is None:
             display_name = name
         return self._html_search_regex(
             r'''(?ix)<meta
                     (?=[^>]+(?:itemprop|name|property)=["\']%s["\'])
                     [^>]+content=["\']([^"\']+)["\']''' % re.escape(name),
-            html, display_name, fatal=False)
+            html, display_name, fatal=fatal)
 
     def _dc_search_uploader(self, html):
         return self._html_search_meta('dc.creator', html, 'uploader')

youtube_dl/extractor/crunchyroll.py

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

youtube_dl/extractor/cspan.py

@@ -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

@@ -8,10 +8,10 @@ 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,
 )
@@ -124,7 +124,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
             if video_url is not None:
                 m_size = re.search(r'H264-(\d+)x(\d+)', video_url)
                 if m_size is not None:
-                    width, height = m_size.group(1), m_size.group(2)
+                    width, height = map(int_or_none, (m_size.group(1), m_size.group(2)))
                 else:
                     width, height = None, None
                 formats.append({
@@ -179,7 +179,7 @@ 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):
@@ -189,10 +189,9 @@ 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-id="(.+?)"', 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)]
@@ -202,17 +201,17 @@ 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):

youtube_dl/extractor/daum.py

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

youtube_dl/extractor/depositfiles.py

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

youtube_dl/extractor/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/facebook.py

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

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

youtube_dl/extractor/fourtube.py

@@ -8,8 +8,8 @@ from ..utils import (
     unified_strdate,
     str_to_int,
     parse_duration,
+    clean_html,
 )
-from youtube_dl.utils import clean_html
 
 
 class FourTubeIE(InfoExtractor):

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

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

youtube_dl/extractor/gamekings.py

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

youtube_dl/extractor/gdcvault.py

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

youtube_dl/extractor/generic.py

@@ -4,7 +4,6 @@ from __future__ import unicode_literals
 
 import os
 import re
-import xml.etree.ElementTree
 
 from .common import InfoExtractor
 from .youtube import YoutubeIE
@@ -17,6 +16,7 @@ from ..utils import (
 
     ExtractorError,
     HEADRequest,
+    parse_xml,
     smuggle_url,
     unescapeHTML,
     unified_strdate,
@@ -24,6 +24,8 @@ from ..utils import (
 )
 from .brightcove import BrightcoveIE
 from .ooyala import OoyalaIE
+from .rutv import RUTVIE
+from .smotri import SmotriIE
 
 
 class GenericIE(InfoExtractor):
@@ -80,13 +82,24 @@ class GenericIE(InfoExtractor):
             },
             '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',
-            'file': 'trailer.mp4',
             'md5': '67d406c2bcb6af27fa886f31aa934bbe',
             'info_dict': {
                 'id': 'trailer',
+                'ext': 'mp4',
                 'title': 'trailer',
                 'upload_date': '20100513',
             }
@@ -94,7 +107,6 @@ class GenericIE(InfoExtractor):
         # ooyala video
         {
             'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
-            'file': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ.mp4',
             'md5': '5644c6ca5d5782c1d0d350dad9bd840c',
             'info_dict': {
                 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
@@ -102,6 +114,128 @@ class GenericIE(InfoExtractor):
                 'title': '2cc213299525360.mov',  # that's what we get
             },
         },
+        # google redirect
+        {
+            'url': 'http://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&ved=0CCUQtwIwAA&url=http%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DcmQHVoWB5FY&ei=F-sNU-LLCaXk4QT52ICQBQ&usg=AFQjCNEw4hL29zgOohLXvpJ-Bdh2bils1Q&bvm=bv.61965928,d.bGE',
+            'info_dict': {
+                'id': 'cmQHVoWB5FY',
+                'ext': 'mp4',
+                'upload_date': '20130224',
+                'uploader_id': 'TheVerge',
+                'description': 'Chris Ziegler takes a look at the Alcatel OneTouch Fire and the ZTE Open; two of the first Firefox OS handsets to be officially announced.',
+                'uploader': 'The Verge',
+                'title': 'First Firefox OS phones side-by-side',
+            },
+            'params': {
+                'skip_download': False,
+            }
+        },
+        # embed.ly video
+        {
+            'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
+            'info_dict': {
+                'id': '9ODmcdjQcHQ',
+                'ext': 'mp4',
+                'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
+                'upload_date': '20140225',
+                'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
+                'uploader': 'Tested',
+                'uploader_id': 'testedcom',
+            },
+            # No need to test YoutubeIE here
+            'params': {
+                'skip_download': True,
+            },
+        },
+        # funnyordie embed
+        {
+            'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
+            'md5': '7cf780be104d40fea7bae52eed4a470e',
+            'info_dict': {
+                'id': '18e820ec3f',
+                'ext': 'mp4',
+                'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
+                'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
+            },
+        },
+        # RUTV embed
+        {
+            'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
+            'info_dict': {
+                'id': '776940',
+                'ext': 'mp4',
+                'title': 'Охотское море стало целиком российским',
+                'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
+            },
+            'params': {
+                # m3u8 download
+                'skip_download': True,
+            },
+        },
+        # Embedded TED video
+        {
+            'url': 'http://en.support.wordpress.com/videos/ted-talks/',
+            'md5': 'deeeabcc1085eb2ba205474e7235a3d5',
+            'info_dict': {
+                'id': '981',
+                'ext': 'mp4',
+                'title': 'My web playroom',
+                'uploader': 'Ze Frank',
+                'description': 'md5:ddb2a40ecd6b6a147e400e535874947b',
+            }
+        },
+        # 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',
+            },
+        },
     ]
 
     def report_download_webpage(self, video_id):
@@ -127,9 +261,14 @@ class GenericIE(InfoExtractor):
                     newurl = newurl.replace(' ', '%20')
                     newheaders = dict((k,v) for k,v in req.headers.items()
                                       if k.lower() not in ("content-length", "content-type"))
+                    try:
+                        # This function was deprecated in python 3.3 and removed in 3.4
+                        origin_req_host = req.get_origin_req_host()
+                    except AttributeError:
+                        origin_req_host = req.origin_req_host
                     return HEADRequest(newurl,
                                        headers=newheaders,
-                                       origin_req_host=req.get_origin_req_host(),
+                                       origin_req_host=origin_req_host,
                                        unverifiable=True)
                 else:
                     raise compat_urllib_error.HTTPError(req.get_full_url(), code, msg, headers, fp)
@@ -185,18 +324,21 @@ class GenericIE(InfoExtractor):
         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
                 return self.url_result(default_search + url)
-        video_id = os.path.splitext(url.split('/')[-1])[0]
+        video_id = os.path.splitext(url.rstrip('/').split('/')[-1])[0]
 
         self.to_screen('%s: Requesting header' % video_id)
 
@@ -242,12 +384,17 @@ class GenericIE(InfoExtractor):
 
         # Is it an RSS feed?
         try:
-            doc = xml.etree.ElementTree.fromstring(webpage.encode('utf-8'))
+            doc = parse_xml(webpage)
             if doc.tag == 'rss':
                 return self._extract_rss(url, video_id, doc)
         except compat_xml_parse_error:
             pass
 
+        # Sometimes embedded video player is hidden behind percent encoding
+        # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
+        # Unescaping the whole page allows to handle those cases in a generic way
+        webpage = compat_urllib_parse.unquote(webpage)
+
         # it's tempting to parse this further, but you would
         # have to take into account all the variations like
         #   Video Title - Site Name
@@ -281,9 +428,9 @@ class GenericIE(InfoExtractor):
 
         # Look for embedded (iframe) Vimeo player
         mobj = re.search(
-            r'<iframe[^>]+?src="((?:https?:)?//player\.vimeo\.com/video/.+?)"', webpage)
+            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/.+?)\1', webpage)
         if mobj:
-            player_url = unescapeHTML(mobj.group(1))
+            player_url = unescapeHTML(mobj.group('url'))
             surl = smuggle_url(player_url, {'Referer': url})
             return self.url_result(surl, 'Vimeo')
 
@@ -349,9 +496,10 @@ class GenericIE(InfoExtractor):
             return self.url_result(mobj.group('url'))
 
         # Look for Ooyala videos
-        mobj = re.search(r'player.ooyala.com/[^"?]+\?[^"]*?(?:embedCode|ec)=([^"&]+)', webpage)
+        mobj = (re.search(r'player.ooyala.com/[^"?]+\?[^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
+             re.search(r'OO.Player.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage))
         if mobj is not None:
-            return OoyalaIE._build_url_result(mobj.group(1))
+            return OoyalaIE._build_url_result(mobj.group('ec'))
 
         # Look for Aparat videos
         mobj = re.search(r'<iframe src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
@@ -363,11 +511,18 @@ 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')
+            return self.url_result(mobj.group('url'))
 
         # Look for embedded Facebook player
         mobj = re.search(
@@ -375,12 +530,62 @@ class GenericIE(InfoExtractor):
         if mobj is not None:
             return self.url_result(mobj.group('url'), 'Facebook')
 
+        # Look for embedded VK player
+        mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'), 'VK')
+
         # Look for embedded Huffington Post player
         mobj = re.search(
             r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
         if mobj is not None:
             return self.url_result(mobj.group('url'), 'HuffPost')
 
+        # Look for embed.ly
+        mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'))
+        mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
+        if mobj is not None:
+            return self.url_result(compat_urllib_parse.unquote(mobj.group('url')))
+
+        # Look for funnyordie embed
+        matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
+        if matches:
+            urlrs = [self.url_result(unescapeHTML(eurl), 'FunnyOrDie')
+                     for eurl in matches]
+            return self.playlist_result(
+                urlrs, playlist_id=video_id, playlist_title=video_title)
+
+        # Look for embedded RUTV player
+        rutv_url = RUTVIE._extract_url(webpage)
+        if rutv_url:
+            return self.url_result(rutv_url, 'RUTV')
+
+        # Look for embedded TED player
+        mobj = re.search(
+            r'<iframe[^>]+?src=(["\'])(?P<url>http://embed\.ted\.com/.+?)\1', webpage)
+        if mobj is not None:
+            return self.url_result(mobj.group('url'), 'TED')
+
+        # 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')
+
         # Start with something easy: JW Player in SWFObject
         mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
         if mobj is None:
@@ -392,6 +597,7 @@ class GenericIE(InfoExtractor):
         if mobj is None:
             # Broaden the search a little bit: JWPlayer JS loader
             mobj = re.search(r'[^A-Za-z0-9]?file["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage)
+
         if mobj is None:
             # Try to find twitter cards info
             mobj = re.search(r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage)
@@ -405,6 +611,18 @@ class GenericIE(InfoExtractor):
         if mobj is None:
             # HTML5 video
             mobj = re.search(r'<video[^<]*(?:>.*?<source.*?)? src="([^"]+)"', webpage, flags=re.DOTALL)
+        if mobj is None:
+            mobj = re.search(
+                r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
+                r'(?:[a-z-]+="[^"]+"\s+)*?content="[0-9]{,2};url=\'([^\']+)\'"',
+                webpage)
+            if mobj:
+                new_url = mobj.group(1)
+                self.report_following_redirect(new_url)
+                return {
+                    '_type': 'url',
+                    'url': new_url,
+                }
         if mobj is None:
             raise ExtractorError('Unsupported URL: %s' % url)
 

youtube_dl/extractor/googlesearch.py

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

youtube_dl/extractor/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/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(
@@ -80,41 +83,37 @@ 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',
+        'url': 'http://gamevideos.1up.com/video/id/34976',
+        'md5': '68a54ce4ebc772e4b71e3123d413163d',
+        'info_dict': {
+            'id': '34976',
+            'ext': 'mp4',
+            'title': 'Sniper Elite V2 - Trailer',
+            'description': 'md5:5d289b722f5a6d940ca3136e9dae89cf',
         }
     }
 
@@ -123,7 +122,6 @@ class OneUPIE(IGNIE):
 
     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/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/iprima.py

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

youtube_dl/extractor/jukebox.py

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

youtube_dl/extractor/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/kontrtube.py

@@ -4,6 +4,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..utils import int_or_none
 
 
 class KontrTubeIE(InfoExtractor):
@@ -32,27 +33,26 @@ class KontrTubeIE(InfoExtractor):
 
         video_url = self._html_search_regex(r"video_url: '(.+?)/?',", webpage, 'video URL')
         thumbnail = self._html_search_regex(r"preview_url: '(.+?)/?',", webpage, 'video thumbnail', fatal=False)
-        title = self._html_search_regex(r'<title>(.+?) - Труба зовёт - Интересный видеохостинг</title>', webpage,
-            'video title')
+        title = self._html_search_regex(
+            r'<title>(.+?) - Труба зовёт - Интересный видеохостинг</title>', webpage, 'video title')
         description = self._html_search_meta('description', webpage, 'video description')
 
-        mobj = re.search(r'<div class="col_2">Длительность: <span>(?P<minutes>\d+)м:(?P<seconds>\d+)с</span></div>',
-            webpage)
+        mobj = re.search(
+            r'<div class="col_2">Длительность: <span>(?P<minutes>\d+)м:(?P<seconds>\d+)с</span></div>', webpage)
         duration = int(mobj.group('minutes')) * 60 + int(mobj.group('seconds')) if mobj else None
 
-        view_count = self._html_search_regex(r'<div class="col_2">Просмотров: <span>(\d+)</span></div>', webpage,
-            'view count', fatal=False)
-        view_count = int(view_count) if view_count is not None else None
+        view_count = self._html_search_regex(
+            r'<div class="col_2">Просмотров: <span>(\d+)</span></div>', webpage, 'view count', fatal=False)
 
         comment_count = None
-        comment_str = self._html_search_regex(r'Комментарии: <span>([^<]+)</span>', webpage, 'comment count',
-            fatal=False)
+        comment_str = self._html_search_regex(
+            r'Комментарии: <span>([^<]+)</span>', webpage, 'comment count', fatal=False)
         if comment_str.startswith('комментариев нет'):
             comment_count = 0
         else:
             mobj = re.search(r'\d+ из (?P<total>\d+) комментариев', comment_str)
             if mobj:
-                comment_count = int(mobj.group('total'))
+                comment_count = mobj.group('total')
 
         return {
             'id': video_id,
@@ -61,6 +61,6 @@ class KontrTubeIE(InfoExtractor):
             'title': title,
             'description': description,
             'duration': duration,
-            'view_count': view_count,
-            'comment_count': comment_count,
+            'view_count': int_or_none(view_count),
+            'comment_count': int_or_none(comment_count),
         }

youtube_dl/extractor/lifenews.py

@@ -6,7 +6,8 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     int_or_none,
-    unified_strdate
+    unified_strdate,
+    ExtractorError,
 )
 
 
@@ -32,13 +33,11 @@ class LifeNewsIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
 
-        webpage = self._download_webpage('http://lifenews.ru/mobile/news/%s' % video_id, video_id, 'Downloading page')
+        webpage = self._download_webpage('http://lifenews.ru/news/%s' % video_id, video_id, 'Downloading page')
 
-        video_url = self._html_search_regex(
-            r'<video.*?src="([^"]+)".*?></video>', webpage, 'video URL')
-
-        thumbnail = self._html_search_regex(
-            r'<video.*?poster="([^"]+)".*?"></video>', webpage, 'video thumbnail')
+        videos = re.findall(r'<video.*?poster="(?P<poster>[^"]+)".*?src="(?P<video>[^"]+)".*?></video>', webpage)
+        if not videos:
+            raise ExtractorError('No media links available for %s' % video_id)
 
         title = self._og_search_title(webpage)
         TITLE_SUFFIX = ' - Первый по срочным новостям — LIFE | NEWS'
@@ -50,20 +49,26 @@ class LifeNewsIE(InfoExtractor):
         view_count = self._html_search_regex(
             r'<div class=\'views\'>(\d+)</div>', webpage, 'view count', fatal=False)
         comment_count = self._html_search_regex(
-            r'<div class=\'comments\'>(\d+)</div>', webpage, 'comment count', fatal=False)
+            r'<div class=\'comments\'>\s*<span class=\'counter\'>(\d+)</span>', webpage, 'comment count', fatal=False)
 
         upload_date = self._html_search_regex(
             r'<time datetime=\'([^\']+)\'>', webpage, 'upload date',fatal=False)
         if upload_date is not None:
             upload_date = unified_strdate(upload_date)
 
-        return {
-            'id': video_id,
-            'url': video_url,
-            'thumbnail': thumbnail,
-            'title': title,
-            'description': description,
-            'view_count': int_or_none(view_count),
-            'comment_count': int_or_none(comment_count),
-            'upload_date': upload_date,
-        }
+        def make_entry(video_id, media, video_number=None):
+            return {
+                'id': video_id,
+                'url': media[1],
+                'thumbnail': media[0],
+                'title': title if video_number is None else '%s-video%s' % (title, video_number),
+                'description': description,
+                'view_count': int_or_none(view_count),
+                'comment_count': int_or_none(comment_count),
+                'upload_date': upload_date,
+            }
+
+        if len(videos) == 1:
+            return make_entry(video_id, videos[0])
+        else:
+            return [make_entry(video_id, media, video_number+1) for video_number, media in enumerate(videos)]

youtube_dl/extractor/lynda.py

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

youtube_dl/extractor/mailru.py

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

youtube_dl/extractor/metacafe.py

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

youtube_dl/extractor/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/mit.py

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

youtube_dl/extractor/mixcloud.py

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

youtube_dl/extractor/mooshare.py

@@ -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/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/mtv.py

@@ -5,9 +5,12 @@ import re
 from .common import InfoExtractor
 from ..utils import (
     compat_urllib_parse,
+    compat_urllib_request,
     ExtractorError,
     find_xpath_attr,
     fix_xml_ampersands,
+    HEADRequest,
+    unescapeHTML,
     url_basename,
     RegexNotFoundError,
 )
@@ -18,6 +21,7 @@ def _media_xml_tag(tag):
 
 
 class MTVServicesInfoExtractor(InfoExtractor):
+    _MOBILE_TEMPLATE = None
     @staticmethod
     def _id_from_uri(uri):
         return uri.split(':')[-1]
@@ -39,9 +43,29 @@ class MTVServicesInfoExtractor(InfoExtractor):
         else:
             return thumb_node.attrib['url']
 
-    def _extract_video_formats(self, mdoc):
-        if re.match(r'.*/error_country_block\.swf$', mdoc.find('.//src').text) is not None:
-            raise ExtractorError('This video is not available from your country.', expected=True)
+    def _extract_mobile_video_formats(self, mtvn_id):
+        webpage_url = self._MOBILE_TEMPLATE % mtvn_id
+        req = compat_urllib_request.Request(webpage_url)
+        # Otherwise we get a webpage that would execute some javascript
+        req.add_header('Youtubedl-user-agent', 'curl/7')
+        webpage = self._download_webpage(req, mtvn_id,
+            'Downloading mobile page')
+        metrics_url = unescapeHTML(self._search_regex(r'<a href="(http://metrics.+?)"', webpage, 'url'))
+        req = HEADRequest(metrics_url)
+        response = self._request_webpage(req, mtvn_id, 'Resolving url')
+        url = response.geturl()
+        # Transform the url to get the best quality:
+        url = re.sub(r'.+pxE=mp4', 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=0+_pxK=18639+_pxE=mp4', url, 1)
+        return [{'url': url,'ext': 'mp4'}]
+
+    def _extract_video_formats(self, mdoc, mtvn_id):
+        if re.match(r'.*/(error_country_block\.swf|geoblock\.mp4)$', mdoc.find('.//src').text) is not None:
+            if mtvn_id is not None and self._MOBILE_TEMPLATE is not None:
+                self.to_screen('The normal version is not available from your '
+                    'country, trying with the mobile version')
+                return self._extract_mobile_video_formats(mtvn_id)
+            raise ExtractorError('This video is not available from your country.',
+                expected=True)
 
         formats = []
         for rendition in mdoc.findall('.//rendition'):
@@ -94,9 +118,16 @@ class MTVServicesInfoExtractor(InfoExtractor):
             raise ExtractorError('Could not find video title')
         title = title.strip()
 
+        # This a short id that's used in the webpage urls
+        mtvn_id = None
+        mtvn_id_node = find_xpath_attr(itemdoc, './/{http://search.yahoo.com/mrss/}category',
+                'scheme', 'urn:mtvn:id')
+        if mtvn_id_node is not None:
+            mtvn_id = mtvn_id_node.text
+
         return {
             'title': title,
-            'formats': self._extract_video_formats(mediagen_doc),
+            'formats': self._extract_video_formats(mediagen_doc, mtvn_id),
             'id': video_id,
             'thumbnail': self._get_thumbnail_url(uri, itemdoc),
             'description': description,

youtube_dl/extractor/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/myvideo.py

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

youtube_dl/extractor/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/nbc.py

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

youtube_dl/extractor/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

@@ -1,6 +1,5 @@
 from __future__ import unicode_literals
 
-import json
 import re
 
 from .common import InfoExtractor
@@ -8,38 +7,69 @@ from .common import InfoExtractor
 
 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",
-        "file": "1912.mp4",
         "info_dict": {
+            "id": "1912",
+            "ext": "mp4",
             "description": "This 3-minute video will make you smile and then make you feel untalented and insignificant. Anyway, you should share this awesomeness. (Thanks, Dino!)",
-            "title": "\"People Are Awesome 2013\" Is Absolutely Awesome"
+            "title": "\"People Are Awesome 2013\" Is Absolutely Awesome",
+            "view_count": int,
+            "thumbnail": "re:^https?://",
         },
         'add_ie': ['Youtube']
-    }
+    },
+    {
+        '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)
-        data_json = self._html_search_regex(r'''(?x)
-            <div\s*id="tv-video"\s*data-video-source="youtube"\s*
-                data-video-meta="([^"]+)"''', webpage, 'video metadata')
+        webpage = self._download_webpage(url, display_id)
 
-        data = json.loads(data_json)
+        youtube_id = self._html_search_regex(
+            r'(?s)id="jsid-video-post-container".*?data-external-id="([^"]+)"',
+            webpage, 'video ID')
+        title = self._html_search_regex(
+            r'(?s)id="jsid-video-post-container".*?data-title="([^"]+)"',
+            webpage, 'title', default=None)
+        if not title:
+            title = self._og_search_title(webpage)
+        description = self._html_search_regex(
+            r'(?s)<div class="video-caption">.*?<p>(.*?)</p>', webpage,
+            'description', fatal=False)
+        view_count_str = self._html_search_regex(
+            r'<p><b>([0-9][0-9,]*)</b> views</p>', webpage, 'view count',
+            fatal=False)
+        view_count = (
+            None if view_count_str is None
+            else int(view_count_str.replace(',', '')))
 
         return {
             '_type': 'url_transparent',
-            'url': data['youtubeVideoId'],
+            'url': youtube_id,
             'ie_key': 'Youtube',
             'id': video_id,
-            'title': data['title'],
-            'description': data['description'],
-            'view_count': int(data['view_count']),
-            'like_count': int(data['statistic']['like']),
-            'dislike_count': int(data['statistic']['dislike']),
-            'thumbnail': data['thumbnail_url'],
+            'display_id': display_id,
+            'title': title,
+            'description': description,
+            'view_count': view_count,
+            'thumbnail': self._og_search_thumbnail(webpage),
         }

youtube_dl/extractor/normalboots.py

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

youtube_dl/extractor/novamov.py

@@ -9,14 +9,26 @@ from ..utils import (
 )
 
 
-class NovamovIE(InfoExtractor):
-    _VALID_URL = r'http://(?:(?:www\.)?novamov\.com/video/|(?:(?:embed|www)\.)novamov\.com/embed\.php\?v=)(?P<videoid>[a-z\d]{13})'
+class NovaMovIE(InfoExtractor):
+    IE_NAME = 'novamov'
+    IE_DESC = 'NovaMov'
+
+    _VALID_URL_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'
+
+    _FILE_DELETED_REGEX = r'This file no longer exists on our servers!</h2>'
+    _FILEKEY_REGEX = r'flashvars\.filekey="(?P<filekey>[^"]+)";'
+    _TITLE_REGEX = r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>([^<]+)</h3>'
+    _DESCRIPTION_REGEX = r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>[^<]+</h3><p>([^<]+)</p>'
 
     _TEST = {
         'url': 'http://www.novamov.com/video/4rurhn9x446jj',
-        'file': '4rurhn9x446jj.flv',
         'md5': '7205f346a52bbeba427603ba10d4b935',
         'info_dict': {
+            'id': '4rurhn9x446jj',
+            'ext': 'flv',
             'title': 'search engine optimization',
             'description': 'search engine optimization is used to rank the web page in the google search engine'
         },
@@ -25,33 +37,27 @@ 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://www.novamov.com/video/%s' % video_id,
-                                      video_id, 'Downloading video page')
+        page = self._download_webpage(
+            'http://%s/video/%s' % (self._HOST, video_id), video_id, 'Downloading video page')
 
-        if re.search(r'This file no longer exists on our servers!</h2>', page) is not None:
-            raise ExtractorError(u'Video %s does not exist' % video_id, expected=True)
+        if re.search(self._FILE_DELETED_REGEX, page) is not None:
+            raise ExtractorError('Video %s does not exist' % video_id, expected=True)
 
-        filekey = self._search_regex(
-            r'flashvars\.filekey="(?P<filekey>[^"]+)";', page, 'filekey')
+        filekey = self._search_regex(self._FILEKEY_REGEX, page, 'filekey')
 
-        title = self._html_search_regex(
-            r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>([^<]+)</h3>',
-            page, 'title', fatal=False)
-
-        description = self._html_search_regex(
-            r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>[^<]+</h3><p>([^<]+)</p>',
-            page, 'description', fatal=False)
+        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(
-            'http://www.novamov.com/api/player.api.php?key=%s&file=%s' % (filekey, video_id),
-            video_id, 'Downloading video api response')
+            'http://%s/api/player.api.php?key=%s&file=%s' % (self._HOST, filekey, video_id), video_id,
+            'Downloading video api response')
 
         response = compat_urlparse.parse_qs(api_response)
 
         if 'error_msg' in response:
-            raise ExtractorError('novamov returned error: %s' % response['error_msg'][0], expected=True)
+            raise ExtractorError('%s returned error: %s' % (self.IE_NAME, response['error_msg'][0]), expected=True)
 
         video_url = response['url'][0]
 
@@ -60,4 +66,4 @@ class NovamovIE(InfoExtractor):
             'url': video_url,
             'title': title,
             'description': description
-        }
+        }