release 2012.11.17

--(match|reject)-title utf8 fix

.travis.yml

@@ -0,0 +1,9 @@
+language: python
+#specify the python version
+python:
+  - "2.6"
+  - "2.7"
+#command to install the setup
+install:
+# command to run tests
+script: nosetests test --nocapture

LATEST_VERSION

@@ -1 +1 @@
-2012.10.09
+2012.11.17

Makefile

@@ -5,10 +5,17 @@ clean:
 	rm -f youtube-dl youtube-dl.exe youtube-dl.1 LATEST_VERSION
 
 PREFIX=/usr/local
+BINDIR=$(PREFIX)/bin
+MANDIR=$(PREFIX)/man
+SYSCONFDIR=/etc
+
 install: youtube-dl youtube-dl.1 youtube-dl.bash-completion
-	install -m 755 --owner root --group root youtube-dl $(PREFIX)/bin/
-	install -m 644 --owner root --group root youtube-dl.1 $(PREFIX)/man/man1
-	install -m 644 --owner root --group root youtube-dl.bash-completion /etc/bash_completion.d/youtube-dl
+	install -d $(DESTDIR)$(BINDIR)
+	install -m 755 youtube-dl $(DESTDIR)$(BINDIR)
+	install -d $(DESTDIR)$(MANDIR)/man1
+	install -m 644 youtube-dl.1 $(DESTDIR)$(MANDIR)/man1
+	install -d $(DESTDIR)$(SYSCONFDIR)/bash_completion.d
+	install -m 644 youtube-dl.bash-completion $(DESTDIR)$(SYSCONFDIR)/bash_completion.d/youtube-dl
 
 .PHONY: all clean install README.md youtube-dl.bash-completion
 # TODO un-phony README.md and youtube-dl.bash_completion by reading from .in files and generating from them
@@ -45,3 +52,8 @@ youtube-dl.bash-completion: README.md
 
 LATEST_VERSION: youtube_dl/__init__.py
 	python -m youtube_dl --version > LATEST_VERSION
+
+test:
+	nosetests2 --nocapture test
+
+.PHONY: default compile update update-latest update-readme test clean

README.md

@@ -36,6 +36,7 @@ which means you can modify it, redistribute it or use it however you like.
 
 ## Filesystem Options:
     -t, --title              use title in file name
+    --id                     use video ID in file name
     -l, --literal            use literal title in file name
     -A, --auto-number        number downloaded files starting from 00000
     -o, --output TEMPLATE    output filename template. Use %(stitle)s to get the
@@ -91,7 +92,7 @@ which means you can modify it, redistribute it or use it however you like.
     -n, --netrc              use .netrc authentication data
 
 ## Post-processing Options:
-    --extract-audio          convert video files to audio-only files (requires
+    -x, --extract-audio      convert video files to audio-only files (requires
                              ffmpeg or avconv and ffprobe or avprobe)
     --audio-format FORMAT    "best", "aac", "vorbis", "mp3", "m4a", or "wav";
                              best by default

test/parameters.json

@@ -0,0 +1 @@
+{"username": null, "listformats": null, "skip_download": false, "usenetrc": false, "max_downloads": null, "noprogress": false, "forcethumbnail": false, "forceformat": false, "format_limit": null, "ratelimit": null, "nooverwrites": false, "forceurl": false, "writeinfojson": false, "simulate": false, "playliststart": 1, "continuedl": true, "password": null, "prefer_free_formats": false, "nopart": false, "retries": 10, "updatetime": true, "consoletitle": false, "verbose": true, "forcefilename": false, "ignoreerrors": false, "logtostderr": false, "format": null, "subtitleslang": null, "quiet": false, "outtmpl": "%(id)s.%(ext)s", "rejecttitle": null, "playlistend": -1, "writedescription": false, "forcetitle": false, "forcedescription": false, "writesubtitles": false, "matchtitle": null}

test/test_div.py

@@ -1,29 +0,0 @@
-# -*- coding: utf-8 -*-
-
-# Various small unit tests
-
-import os,sys
-sys.path.append(os.path.dirname(os.path.dirname(__file__)))
-
-import youtube_dl
-
-def test_simplify_title():
-	assert youtube_dl._simplify_title(u'abc') == u'abc'
-	assert youtube_dl._simplify_title(u'abc_d-e') == u'abc_d-e'
-
-	assert youtube_dl._simplify_title(u'123') == u'123'
-
-	assert u'/' not in youtube_dl._simplify_title(u'abc/de')
-	assert u'abc' in youtube_dl._simplify_title(u'abc/de')
-	assert u'de' in youtube_dl._simplify_title(u'abc/de')
-	assert u'/' not in youtube_dl._simplify_title(u'abc/de///')
-
-	assert u'\\' not in youtube_dl._simplify_title(u'abc\\de')
-	assert u'abc' in youtube_dl._simplify_title(u'abc\\de')
-	assert u'de' in youtube_dl._simplify_title(u'abc\\de')
-
-	assert youtube_dl._simplify_title(u'ä') == u'ä'
-	assert youtube_dl._simplify_title(u'кириллица') == u'кириллица'
-
-	# Strip underlines
-	assert youtube_dl._simplify_title(u'\'a_') == u'a'

test/test_download.py

@@ -0,0 +1,93 @@
+#!/usr/bin/env python2
+import unittest
+import hashlib
+import os
+import json
+
+from youtube_dl.FileDownloader import FileDownloader
+from youtube_dl.InfoExtractors  import YoutubeIE, DailymotionIE
+from youtube_dl.InfoExtractors import  MetacafeIE, BlipTVIE
+
+
+class DownloadTest(unittest.TestCase):
+	PARAMETERS_FILE = "test/parameters.json"
+	#calculated with md5sum:
+	#md5sum (GNU coreutils) 8.19
+
+	YOUTUBE_SIZE = 1993883
+	YOUTUBE_URL = "http://www.youtube.com/watch?v=BaW_jenozKc"
+	YOUTUBE_FILE = "BaW_jenozKc.mp4"
+
+	DAILYMOTION_MD5 = "d363a50e9eb4f22ce90d08d15695bb47"
+	DAILYMOTION_URL = "http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech"
+	DAILYMOTION_FILE = "x33vw9.mp4"
+
+	METACAFE_SIZE = 5754305
+	METACAFE_URL = "http://www.metacafe.com/watch/yt-_aUehQsCQtM/the_electric_company_short_i_pbs_kids_go/"
+	METACAFE_FILE = "_aUehQsCQtM.flv"
+
+	BLIP_MD5 = "93c24d2f4e0782af13b8a7606ea97ba7"
+	BLIP_URL = "http://blip.tv/cbr/cbr-exclusive-gotham-city-imposters-bats-vs-jokerz-short-3-5796352"
+	BLIP_FILE = "5779306.m4v"
+
+	XVIDEO_MD5 = ""
+	XVIDEO_URL = ""
+	XVIDEO_FILE = ""
+
+
+	def test_youtube(self):
+		#let's download a file from youtube
+		with open(DownloadTest.PARAMETERS_FILE) as f:
+			fd = FileDownloader(json.load(f))
+		fd.add_info_extractor(YoutubeIE())
+		fd.download([DownloadTest.YOUTUBE_URL])
+		self.assertTrue(os.path.exists(DownloadTest.YOUTUBE_FILE))
+		self.assertEqual(os.path.getsize(DownloadTest.YOUTUBE_FILE), DownloadTest.YOUTUBE_SIZE)
+
+	def test_dailymotion(self):
+		with open(DownloadTest.PARAMETERS_FILE) as f:
+			fd = FileDownloader(json.load(f))
+		fd.add_info_extractor(DailymotionIE())
+		fd.download([DownloadTest.DAILYMOTION_URL])
+		self.assertTrue(os.path.exists(DownloadTest.DAILYMOTION_FILE))
+		md5_down_file = md5_for_file(DownloadTest.DAILYMOTION_FILE)
+		self.assertEqual(md5_down_file, DownloadTest.DAILYMOTION_MD5)
+
+	def test_metacafe(self):
+		#this emulate a skip,to be 2.6 compatible
+		with open(DownloadTest.PARAMETERS_FILE) as f:
+			fd = FileDownloader(json.load(f))
+		fd.add_info_extractor(MetacafeIE())
+		fd.add_info_extractor(YoutubeIE())
+		fd.download([DownloadTest.METACAFE_URL])
+		self.assertTrue(os.path.exists(DownloadTest.METACAFE_FILE))
+		self.assertEqual(os.path.getsize(DownloadTest.METACAFE_FILE), DownloadTest.METACAFE_SIZE)
+
+	def test_blip(self):
+		with open(DownloadTest.PARAMETERS_FILE) as f:
+			fd = FileDownloader(json.load(f))
+		fd.add_info_extractor(BlipTVIE())
+		fd.download([DownloadTest.BLIP_URL])
+		self.assertTrue(os.path.exists(DownloadTest.BLIP_FILE))
+		md5_down_file = md5_for_file(DownloadTest.BLIP_FILE)
+		self.assertEqual(md5_down_file, DownloadTest.BLIP_MD5)
+
+	def tearDown(self):
+		if os.path.exists(DownloadTest.YOUTUBE_FILE):
+			os.remove(DownloadTest.YOUTUBE_FILE)
+		if os.path.exists(DownloadTest.DAILYMOTION_FILE):
+			os.remove(DownloadTest.DAILYMOTION_FILE)
+		if os.path.exists(DownloadTest.METACAFE_FILE):
+			os.remove(DownloadTest.METACAFE_FILE)
+		if os.path.exists(DownloadTest.BLIP_FILE):
+			os.remove(DownloadTest.BLIP_FILE)
+
+def md5_for_file(filename, block_size=2**20):
+    with open(filename) as f:
+        md5 = hashlib.md5()
+        while True:
+            data = f.read(block_size)
+            if not data:
+                break
+            md5.update(data)
+            return md5.hexdigest()

test/test_utils.py

@@ -0,0 +1,47 @@
+# -*- coding: utf-8 -*-
+
+# Various small unit tests
+
+import unittest
+
+#from youtube_dl.utils import htmlentity_transform
+from youtube_dl.utils import timeconvert
+from youtube_dl.utils import sanitize_filename
+from youtube_dl.utils import unescapeHTML
+from youtube_dl.utils import orderedSet
+
+
+class TestUtil(unittest.TestCase):
+	def test_timeconvert(self):
+		self.assertTrue(timeconvert('') is None)
+		self.assertTrue(timeconvert('bougrg') is None)
+
+	def test_sanitize_filename(self):
+		self.assertEqual(sanitize_filename(u'abc'), u'abc')
+		self.assertEqual(sanitize_filename(u'abc_d-e'), u'abc_d-e')
+
+		self.assertEqual(sanitize_filename(u'123'), u'123')
+
+		self.assertEqual(u'abc-de', sanitize_filename(u'abc/de'))
+		self.assertFalse(u'/' in sanitize_filename(u'abc/de///'))
+
+		self.assertEqual(u'abc-de', sanitize_filename(u'abc/<>\\*|de'))
+		self.assertEqual(u'xxx', sanitize_filename(u'xxx/<>\\*|'))
+		self.assertEqual(u'yes no', sanitize_filename(u'yes? no'))
+		self.assertEqual(u'this - that', sanitize_filename(u'this: that'))
+
+		self.assertEqual(sanitize_filename(u'ä'), u'ä')
+		self.assertEqual(sanitize_filename(u'кириллица'), u'кириллица')
+
+		for forbidden in u'"\0\\/':
+			self.assertTrue(forbidden not in sanitize_filename(forbidden))
+
+	def test_ordered_set(self):
+		self.assertEqual(orderedSet([1,1,2,3,4,4,5,6,7,3,5]), [1,2,3,4,5,6,7])
+		self.assertEqual(orderedSet([]), [])
+		self.assertEqual(orderedSet([1]), [1])
+		#keep the list ordered
+		self.assertEqual(orderedSet([135,1,1,1]), [135,1])
+
+	def test_unescape_html(self):
+		self.assertEqual(unescapeHTML(u"%20;"), u"%20;")

youtube-dl.1

@@ -48,6 +48,7 @@ redistribute it or use it however you like.
 .nf
 \f[C]
 -t,\ --title\ \ \ \ \ \ \ \ \ \ \ \ \ \ use\ title\ in\ file\ name
+--id\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ use\ video\ ID\ in\ file\ name
 -l,\ --literal\ \ \ \ \ \ \ \ \ \ \ \ use\ literal\ title\ in\ file\ name
 -A,\ --auto-number\ \ \ \ \ \ \ \ number\ downloaded\ files\ starting\ from\ 00000
 -o,\ --output\ TEMPLATE\ \ \ \ output\ filename\ template.\ Use\ %(stitle)s\ to\ get\ the
@@ -119,7 +120,7 @@ redistribute it or use it however you like.
 .IP
 .nf
 \f[C]
---extract-audio\ \ \ \ \ \ \ \ \ \ convert\ video\ files\ to\ audio-only\ files\ (requires
+-x,\ --extract-audio\ \ \ \ \ \ convert\ video\ files\ to\ audio-only\ files\ (requires
 \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ ffmpeg\ or\ avconv\ and\ ffprobe\ or\ avprobe)
 --audio-format\ FORMAT\ \ \ \ "best",\ "aac",\ "vorbis",\ "mp3",\ "m4a",\ or\ "wav";
 \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ best\ by\ default

youtube-dl.bash-completion

@@ -3,7 +3,7 @@ __youtube-dl()
     local cur prev opts
     COMPREPLY=()
     cur="${COMP_WORDS[COMP_CWORD]}"
-    opts="--all-formats --audio-format --audio-quality --auto-number --batch-file --console-title --continue --cookies --dump-user-agent --extract-audio --format --get-description --get-filename --get-format --get-thumbnail --get-title --get-url --help --ignore-errors --keep-video --list-extractors --list-formats --literal --match-title --max-downloads --max-quality --netrc --no-continue --no-mtime --no-overwrites --no-part --no-progress --output --password --playlist-end --playlist-start --prefer-free-formats --quiet --rate-limit --reject-title --retries --simulate --skip-download --srt-lang --title --update --user-agent --username --verbose --version --write-description --write-info-json --write-srt"
+    opts="--all-formats --audio-format --audio-quality --auto-number --batch-file --console-title --continue --cookies --dump-user-agent --extract-audio --format --get-description --get-filename --get-format --get-thumbnail --get-title --get-url --help --id --ignore-errors --keep-video --list-extractors --list-formats --literal --match-title --max-downloads --max-quality --netrc --no-continue --no-mtime --no-overwrites --no-part --no-progress --output --password --playlist-end --playlist-start --prefer-free-formats --quiet --rate-limit --reject-title --retries --simulate --skip-download --srt-lang --title --update --user-agent --username --verbose --version --write-description --write-info-json --write-srt"
 
     if [[ ${cur} == * ]] ; then
         COMPREPLY=( $(compgen -W "${opts}" -- ${cur}) )

youtube_dl/FileDownloader.py

@@ -13,7 +13,7 @@ import urllib2
 
 if os.name == 'nt':
 	import ctypes
-	
+
 from utils import *
 
 
@@ -173,7 +173,6 @@ class FileDownloader(object):
 		if not self.params.get('quiet', False):
 			terminator = [u'\n', u''][skip_eol]
 			output = message + terminator
-
 			if 'b' not in self._screen_file.mode or sys.version_info[0] < 3: # Python 2 lies about the mode of sys.stdout/sys.stderr
 				output = output.encode(preferredencoding(), 'ignore')
 			self._screen_file.write(output)
@@ -334,11 +333,15 @@ class FileDownloader(object):
 
 		title = info_dict['title']
 		matchtitle = self.params.get('matchtitle', False)
-		if matchtitle and not re.search(matchtitle, title, re.IGNORECASE):
-			return u'[download] "' + title + '" title did not match pattern "' + matchtitle + '"'
+		if matchtitle:
+			matchtitle = matchtitle.decode('utf8')
+			if not re.search(matchtitle, title, re.IGNORECASE):
+				return u'[download] "' + title + '" title did not match pattern "' + matchtitle + '"'
 		rejecttitle = self.params.get('rejecttitle', False)
-		if rejecttitle and re.search(rejecttitle, title, re.IGNORECASE):
-			return u'"' + title + '" title matched reject pattern "' + rejecttitle + '"'
+		if rejecttitle:
+			rejecttitle = rejecttitle.decode('utf8')
+			if re.search(rejecttitle, title, re.IGNORECASE):
+				return u'"' + title + '" title matched reject pattern "' + rejecttitle + '"'
 		return None
 
 	def process_info(self, info_dict):
@@ -357,7 +360,7 @@ class FileDownloader(object):
 				raise MaxDownloadsReached()
 
 		filename = self.prepare_filename(info_dict)
-		
+
 		# Forced printings
 		if self.params.get('forcetitle', False):
 			print info_dict['title'].encode(preferredencoding(), 'xmlcharrefreplace')
@@ -399,10 +402,10 @@ class FileDownloader(object):
 			except (OSError, IOError):
 				self.trouble(u'ERROR: Cannot write description file ' + descfn)
 				return
-				
+
 		if self.params.get('writesubtitles', False) and 'subtitles' in info_dict and info_dict['subtitles']:
 			# subtitles download errors are already managed as troubles in relevant IE
-			# that way it will silently go on when used with unsupporting IE 
+			# that way it will silently go on when used with unsupporting IE
 			try:
 				srtfn = filename.rsplit('.', 1)[0] + u'.srt'
 				self.report_writesubtitles(srtfn)
@@ -448,7 +451,7 @@ class FileDownloader(object):
 				except (ContentTooShortError, ), err:
 					self.trouble(u'ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
 					return
-	
+
 			if success:
 				try:
 					self.post_process(filename, info_dict)

youtube_dl/InfoExtractors.py

@@ -102,6 +102,7 @@ class YoutubeIE(InfoExtractor):
 	                     (?:https?://)?                                       # http(s):// (optional)
 	                     (?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/|
 	                     	tube\.majestyc\.net/)                             # the various hostnames, with wildcard subdomains
+	                     (?:.*?\#/)?                                          # handle anchor (#/) redirect urls
 	                     (?!view_play_list|my_playlists|artist|playlist)      # ignore playlist URLs
 	                     (?:                                                  # the various things that can precede the ID:
 	                         (?:(?:v|embed|e)/)                               # v/ or embed/ or e/
@@ -413,6 +414,12 @@ class YoutubeIE(InfoExtractor):
 			except Trouble as trouble:
 				self._downloader.trouble(trouble[0])
 
+		if 'length_seconds' not in video_info:
+			self._downloader.trouble(u'WARNING: unable to extract video duration')
+			video_duration = ''
+		else:
+			video_duration = urllib.unquote_plus(video_info['length_seconds'][0])
+
 		# token
 		video_token = urllib.unquote_plus(video_info['token'][0])
 
@@ -479,7 +486,8 @@ class YoutubeIE(InfoExtractor):
 				'thumbnail':	video_thumbnail.decode('utf-8'),
 				'description':	video_description,
 				'player_url':	player_url,
-				'subtitles':	video_subtitles
+				'subtitles':	video_subtitles,
+				'duration':		video_duration
 			})
 		return results
 
@@ -595,7 +603,7 @@ class MetacafeIE(InfoExtractor):
 			return
 		video_title = mobj.group(1).decode('utf-8')
 
-		mobj = re.search(r'(?ms)By:\s*<a .*?>(.+?)<', webpage)
+		mobj = re.search(r'submitter=(.*?);', webpage)
 		if mobj is None:
 			self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
 			return
@@ -684,9 +692,14 @@ class DailymotionIE(InfoExtractor):
 		video_title = unescapeHTML(mobj.group('title').decode('utf-8'))
 
 		video_uploader = u'NA'
-		mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a></span>', webpage)
+		mobj = re.search(r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a>', webpage)
 		if mobj is None:
-			self._downloader.trouble(u'WARNING: unable to extract uploader nickname')
+			# lookin for official user
+			mobj_official = re.search(r'<span rel="author"[^>]+?>([^<]+?)</span>', webpage)
+			if mobj_official is None:
+				self._downloader.trouble(u'WARNING: unable to extract uploader nickname')
+			else:
+				video_uploader = mobj_official.group(1)
 		else:
 			video_uploader = mobj.group(1)
 
@@ -1087,21 +1100,32 @@ class VimeoIE(InfoExtractor):
 		timestamp = config['request']['timestamp']
 
 		# Vimeo specific: extract video codec and quality information
+		# First consider quality, then codecs, then take everything
 		# TODO bind to format param
 		codecs = [('h264', 'mp4'), ('vp8', 'flv'), ('vp6', 'flv')]
-		for codec in codecs:
-			if codec[0] in config["video"]["files"]:
-				video_codec = codec[0]
-				video_extension = codec[1]
-				if 'hd' in config["video"]["files"][codec[0]]: quality = 'hd'
-				else: quality = 'sd'
+		files = { 'hd': [], 'sd': [], 'other': []}
+		for codec_name, codec_extension in codecs:
+			if codec_name in config["video"]["files"]:
+				if 'hd' in config["video"]["files"][codec_name]:
+					files['hd'].append((codec_name, codec_extension, 'hd'))
+				elif 'sd' in config["video"]["files"][codec_name]:
+					files['sd'].append((codec_name, codec_extension, 'sd'))
+				else:
+					files['other'].append((codec_name, codec_extension, config["video"]["files"][codec_name][0]))
+
+		for quality in ('hd', 'sd', 'other'):
+			if len(files[quality]) > 0:
+				video_quality = files[quality][0][2]
+				video_codec = files[quality][0][0]
+				video_extension = files[quality][0][1]
+				self._downloader.to_screen(u'[vimeo] %s: Downloading %s file at %s quality' % (video_id, video_codec.upper(), video_quality))
 				break
 		else:
 			self._downloader.trouble(u'ERROR: no known codec found')
 			return
 
 		video_url = "http://player.vimeo.com/play_redirect?clip_id=%s&sig=%s&time=%s&quality=%s&codecs=%s&type=moogaloop_local&embed_location=" \
-					%(video_id, sig, timestamp, quality, video_codec.upper())
+					%(video_id, sig, timestamp, video_quality, video_codec.upper())
 
 		return [{
 			'id':		video_id,
@@ -1508,9 +1532,9 @@ class YahooSearchIE(InfoExtractor):
 class YoutubePlaylistIE(InfoExtractor):
 	"""Information Extractor for YouTube playlists."""
 
-	_VALID_URL = r'(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?:course|view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)(?:PL)?([0-9A-Za-z-_]+)(?:/.*?/([0-9A-Za-z_-]+))?.*'
+	_VALID_URL = r'(?:(?:https?://)?(?:\w+\.)?youtube\.com/(?:(?:course|view_play_list|my_playlists|artist|playlist)\?.*?(p|a|list)=|user/.*?/user/|p/|user/.*?#[pg]/c/)(?:PL|EC)?|PL|EC)([0-9A-Za-z-_]+)(?:/.*?/([0-9A-Za-z_-]+))?.*'
 	_TEMPLATE_URL = 'http://www.youtube.com/%s?%s=%s&page=%s&gl=US&hl=en'
-	_VIDEO_INDICATOR_TEMPLATE = r'/watch\?v=(.+?)&amp;list=.*?%s'
+	_VIDEO_INDICATOR_TEMPLATE = r'/watch\?v=(.+?)&amp;([^&"]+&amp;)*list=.*?%s'
 	_MORE_PAGES_INDICATOR = r'yt-uix-pager-next'
 	IE_NAME = u'youtube:playlist'
 
@@ -1578,6 +1602,56 @@ class YoutubePlaylistIE(InfoExtractor):
 		return
 
 
+class YoutubeChannelIE(InfoExtractor):
+	"""Information Extractor for YouTube channels."""
+
+	_VALID_URL = r"^(?:https?://)?(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/([0-9A-Za-z_-]+)(?:/.*)?$"
+	_TEMPLATE_URL = 'http://www.youtube.com/channel/%s/videos?sort=da&flow=list&view=0&page=%s&gl=US&hl=en'
+	_MORE_PAGES_INDICATOR = r'yt-uix-button-content">Next' # TODO
+	IE_NAME = u'youtube:channel'
+
+	def report_download_page(self, channel_id, pagenum):
+		"""Report attempt to download channel page with given number."""
+		self._downloader.to_screen(u'[youtube] Channel %s: Downloading page #%s' % (channel_id, pagenum))
+
+	def _real_extract(self, url):
+		# Extract channel id
+		mobj = re.match(self._VALID_URL, url)
+		if mobj is None:
+			self._downloader.trouble(u'ERROR: invalid url: %s' % url)
+			return
+
+		# Download channel pages
+		channel_id = mobj.group(1)
+		video_ids = []
+		pagenum = 1
+
+		while True:
+			self.report_download_page(channel_id, pagenum)
+			url = self._TEMPLATE_URL % (channel_id, pagenum)
+			request = urllib2.Request(url)
+			try:
+				page = urllib2.urlopen(request).read()
+			except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+				self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
+				return
+
+			# Extract video identifiers
+			ids_in_page = []
+			for mobj in re.finditer(r'href="/watch\?v=([0-9A-Za-z_-]+)&', page):
+				if mobj.group(1) not in ids_in_page:
+					ids_in_page.append(mobj.group(1))
+			video_ids.extend(ids_in_page)
+
+			if re.search(self._MORE_PAGES_INDICATOR, page) is None:
+				break
+			pagenum = pagenum + 1
+
+		for id in video_ids:
+			self._downloader.download(['http://www.youtube.com/watch?v=%s' % id])
+		return
+
+
 class YoutubeUserIE(InfoExtractor):
 	"""Information Extractor for YouTube users."""
 

youtube_dl/PostProcessor.py

@@ -73,7 +73,7 @@ class FFmpegExtractAudioPP(PostProcessor):
 	def detect_executables():
 		def executable(exe):
 			try:
-				subprocess.check_output([exe, '-version'])
+				subprocess.Popen([exe, '-version'], stdout=subprocess.PIPE, stderr=subprocess.PIPE).communicate()
 			except OSError:
 				return False
 			return exe
@@ -146,7 +146,7 @@ class FFmpegExtractAudioPP(PostProcessor):
 					if int(self._preferredquality) < 10:
 						more_opts += [self._exes['avconv'] and '-q:a' or '-aq', self._preferredquality]
 					else:
-						more_opts += [self._exes['avconv'] and '-b:a' or '-ab', self._preferredquality]
+						more_opts += [self._exes['avconv'] and '-b:a' or '-ab', self._preferredquality + 'k']
 		else:
 			# We convert the audio (lossy)
 			acodec = {'mp3': 'libmp3lame', 'aac': 'aac', 'm4a': 'aac', 'vorbis': 'libvorbis', 'wav': None}[self._preferredcodec]
@@ -156,7 +156,7 @@ class FFmpegExtractAudioPP(PostProcessor):
 				if int(self._preferredquality) < 10:
 					more_opts += [self._exes['avconv'] and '-q:a' or '-aq', self._preferredquality]
 				else:
-					more_opts += [self._exes['avconv'] and '-b:a' or '-ab', self._preferredquality]
+					more_opts += [self._exes['avconv'] and '-b:a' or '-ab', self._preferredquality + 'k']
 			if self._preferredcodec == 'aac':
 				more_opts += ['-f', 'adts']
 			if self._preferredcodec == 'm4a':

youtube_dl/__init__.py

@@ -1,6 +1,8 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 
+from __future__ import with_statement
+
 __authors__  = (
 	'Ricardo Garcia Gonzalez',
 	'Danny Colligan',
@@ -19,7 +21,7 @@ __authors__  = (
 	)
 
 __license__ = 'Public Domain'
-__version__ = '2012.10.09'
+__version__ = '2012.11.17'
 
 UPDATE_URL = 'https://raw.github.com/rg3/youtube-dl/master/youtube-dl'
 UPDATE_URL_VERSION = 'https://raw.github.com/rg3/youtube-dl/master/LATEST_VERSION'
@@ -263,6 +265,8 @@ def parseOpts():
 
 	filesystem.add_option('-t', '--title',
 			action='store_true', dest='usetitle', help='use title in file name', default=False)
+	filesystem.add_option('--id',
+			action='store_true', dest='useid', help='use video ID in file name', default=False)
 	filesystem.add_option('-l', '--literal',
 			action='store_true', dest='useliteral', help='use literal title in file name', default=False)
 	filesystem.add_option('-A', '--auto-number',
@@ -294,7 +298,7 @@ def parseOpts():
 			help='write video metadata to a .info.json file', default=False)
 
 
-	postproc.add_option('--extract-audio', action='store_true', dest='extractaudio', default=False,
+	postproc.add_option('-x', '--extract-audio', action='store_true', dest='extractaudio', default=False,
 			help='convert video files to audio-only files (requires ffmpeg or avconv and ffprobe or avprobe)')
 	postproc.add_option('--audio-format', metavar='FORMAT', dest='audioformat', default='best',
 			help='"best", "aac", "vorbis", "mp3", "m4a", or "wav"; best by default')
@@ -328,6 +332,7 @@ def gen_extractors():
 	"""
 	return [
 		YoutubePlaylistIE(),
+		YoutubeChannelIE(),
 		YoutubeUserIE(),
 		YoutubeSearchIE(),
 		YoutubeIE(),
@@ -421,10 +426,14 @@ def _real_main():
 		parser.error(u'using .netrc conflicts with giving username/password')
 	if opts.password is not None and opts.username is None:
 		parser.error(u'account username missing')
-	if opts.outtmpl is not None and (opts.useliteral or opts.usetitle or opts.autonumber):
-		parser.error(u'using output template conflicts with using title, literal title or auto number')
+	if opts.outtmpl is not None and (opts.useliteral or opts.usetitle or opts.autonumber or opts.useid):
+		parser.error(u'using output template conflicts with using title, literal title, video ID or auto number')
 	if opts.usetitle and opts.useliteral:
 		parser.error(u'using title conflicts with using literal title')
+	if opts.usetitle and opts.useid:
+		parser.error(u'using title conflicts with using video ID')
+	if opts.useliteral and opts.useid:
+		parser.error(u'using literal 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:')
 	if opts.ratelimit is not None:
@@ -482,6 +491,7 @@ def _real_main():
 			or (opts.useliteral and opts.autonumber and u'%(autonumber)s-%(title)s-%(id)s.%(ext)s')
 			or (opts.usetitle and u'%(stitle)s-%(id)s.%(ext)s')
 			or (opts.useliteral and u'%(title)s-%(id)s.%(ext)s')
+			or (opts.useid and u'%(id)s.%(ext)s')
 			or (opts.autonumber and u'%(autonumber)s-%(id)s.%(ext)s')
 			or u'%(id)s.%(ext)s'),
 		'ignoreerrors': opts.ignoreerrors,

youtube_dl/utils.py

@@ -83,7 +83,7 @@ class IDParser(HTMLParser.HTMLParser):
 		HTMLParser.HTMLParser.__init__(self)
 
 	def error(self, message):
-		print >> sys.stderr, self.getpos()
+		#print >> sys.stderr, self.getpos()
 		if self.error_count > 10 or self.started:
 			raise HTMLParser.HTMLParseError(message, self.getpos())
 		self.rawdata = '\n'.join(self.html.split('\n')[self.getpos()[0]:]) # skip one line
@@ -194,10 +194,20 @@ def timeconvert(timestr):
 def sanitize_filename(s):
 	"""Sanitizes a string so it could be used as part of a filename."""
 	def replace_insane(char):
-		if char in u' .\\/|?*<>:"' or ord(char) < 32:
-			return '_'
+		if char == '?' or ord(char) < 32 or ord(char) == 127:
+			return ''
+		elif char == '"':
+			return '\''
+		elif char == ':':
+			return ' -'
+		elif char in '\\/|*<>':
+			return '-'
 		return char
-	return u''.join(map(replace_insane, s)).strip('_')
+
+	result = u''.join(map(replace_insane, s))
+	while '--' in result:
+		result = result.replace('--', '-')
+	return result.strip('-')
 
 def orderedSet(iterable):
 	""" Remove all duplicates from the input iterable """