Bump version number

index.html.in

@@ -96,7 +96,8 @@ is too old.</p>
 
 <li>You can change the file name of the video using the -o option, like in
 <em>youtube-dl -o vid.flv "http://www.youtube.com/watch?v=foobar"</em>.
-Read the <em>Output template</em> section for more details on this.</li>
+Read the <a href="#otpl">Output template</a> section for more details on
+this.</li>
 
 <li>Some videos require an account to be downloaded, mostly because they're
 flagged as mature content. You can pass the program a username and password
@@ -130,15 +131,30 @@ literal title in the filename with the -l or --literal option.</li>
 by using the -f or --format option. This makes it possible to download high
 quality versions of the videos when available.</li>
 
-<li><em>youtube-dl</em> can attempt to download the best quality version of
-a video by using the -b or --best-quality option.</li>
+<li>The -b or --best-quality option is an alias for -f 18.</li>
 
-<li><em>youtube-dl</em> can attempt to download the mobile quality version of
-a video by using the -m or --mobile-version option.</li>
+<li>The -m or --mobile-version option is an alias for -f 17.</li>
 
 <li>Normally, the program will stop on the first error, but you can tell it
 to attempt to download every video with the -i or --ignore-errors option.</li>
 
+<li>The -a or --batch-file option lets you specify a file to read URLs from.
+The file must contain one URL per line.</li>
+
+<li>The program can be told not to overwrite existing files using the -w or
+--no-overwrites option.</li>
+
+<li>For YouTube, you can also use the URL of a playlist, and it will download
+all the videos in that playlist.</li>
+
+<li>For YouTube, you can also use the special word <em>ytsearch</em> to
+download search results. With <em>ytsearch</em> it will download the
+first search result. With <em>ytsearchN</em>, where N is a number, it
+will download the first N results. With <em>ytsearchall</em> it will
+download every result for that search. In most systems you'll need to
+use quotes for multiple words. Example: <em>youtube-dl "ytsearch3:cute
+kittens"</em>.
+
 <li><em>youtube-dl</em> honors the <em>http_proxy</em> environment variable
 if you want to use a proxy. Set it to something like
 <em>http://proxy.example.com:8080</em>, and do not leave the <em>http://</em>
@@ -171,7 +187,7 @@ are using.</p>
         <li><strong>SHA256</strong>: @PROGRAM_SHA256SUM@</li>
 </ul>
 
-<h2>Output template</h2>
+<h2 id="otpl">Output template</h2>
 
 <p>The -o option allows users to indicate a template for the output file names.
 The basic usage is not to set any template arguments when downloading a single
@@ -189,9 +205,9 @@ person who uploaded the video.</li>
 <li><em>title</em>: The sequence will be replaced by the literal video
 title.</li>
 <li><em>stitle</em>: The sequence will be replaced by a simplified video
-title.</li>
+title, restricted to alphanumeric characters and dashes.</li>
 <li><em>ext</em>: The sequence will be replaced by the appropriate
-extension.</li>
+extension (like <em>flv</em> or <em>mp4</em>).</li>
 </ul>
 
 <p>As you may have guessed, the default template is <em>%(id)s.%(ext)s</em>.
@@ -203,6 +219,7 @@ When some command line options are used, it's replaced by other templates like
 <ul>
 <li>Ricardo Garcia Gonzalez: program core, YouTube.com InfoExtractor,
 metacafe.com InfoExtractor and YouTube playlist InfoExtractor.</li>
+<li>Danny Colligan: YouTube search InfoExtractor, ideas and patches.</li>
 <li>Many other people contributing patches, code, ideas and kind messages. Too
 many to be listed here. You know who you are. Thank you very much.</li>
 </ul>

youtube-dl

@@ -1,9 +1,11 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 # Author: Ricardo Garcia Gonzalez
+# Author: Danny Colligan
 # License: Public domain code
 import htmlentitydefs
 import httplib
+import locale
 import math
 import netrc
 import os
@@ -17,7 +19,7 @@ import urllib
 import urllib2
 
 std_headers = {	
-	'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.9.0.1) Gecko/2008070208 Firefox/3.0.1',
+	'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.9.0.5) Gecko/2008120122 Firefox/3.0.5',
 	'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
 	'Accept': 'text/xml,application/xml,application/xhtml+xml,text/html;q=0.9,text/plain;q=0.8,image/png,*/*;q=0.5',
 	'Accept-Language': 'en-us,en;q=0.5',
@@ -87,6 +89,7 @@ class FileDownloader(object):
 	outtmpl:	Template for output names.
 	ignoreerrors:	Do not stop on download errors.
 	ratelimit:	Download speed limit, in bytes/sec.
+	nooverwrites:	Prevent overwriting files.
 	"""
 
 	_params = None
@@ -284,6 +287,9 @@ class FileDownloader(object):
 					except (ValueError, KeyError), err:
 						retcode = self.trouble('ERROR: invalid output template or system charset: %s' % str(err))
 						continue
+					if self._params['nooverwrites'] and os.path.exists(filename):
+						self.to_stderr('WARNING: file exists: %s; skipping' % filename)
+						continue
 					try:
 						self.pmkdir(filename)
 					except (OSError, IOError), err:
@@ -430,14 +436,19 @@ class YoutubeIE(InfoExtractor):
 	"""Information extractor for youtube.com."""
 
 	_VALID_URL = r'^((?:http://)?(?:\w+\.)?youtube\.com/(?:(?:v/)|(?:(?:watch(?:\.php)?)?\?(?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$'
-	_LOGIN_URL = 'http://www.youtube.com/login?next=/'
-	_AGE_URL = 'http://www.youtube.com/verify_age?next_url=/'
+	_LANG_URL = r'http://uk.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
+	_LOGIN_URL = 'http://www.youtube.com/signup?next=/&gl=US&hl=en'
+	_AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
 	_NETRC_MACHINE = 'youtube'
 
 	@staticmethod
 	def suitable(url):
 		return (re.match(YoutubeIE._VALID_URL, url) is not None)
 
+	def report_lang(self):
+		"""Report attempt to set language."""
+		self.to_stdout(u'[youtube] Setting language')
+
 	def report_login(self):
 		"""Report attempt to log in."""
 		self.to_stdout(u'[youtube] Logging in')
@@ -486,6 +497,15 @@ class YoutubeIE(InfoExtractor):
 		if username is None:
 			return
 
+		# Set language
+		request = urllib2.Request(self._LOGIN_URL, None, std_headers)
+		try:
+			self.report_lang()
+			urllib2.urlopen(request).read()
+		except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+			self.to_stderr(u'WARNING: unable to set language: %s' % str(err))
+			return
+
 		# Log in
 		login_form = {
 				'current_form': 'loginForm',
@@ -536,7 +556,7 @@ class YoutubeIE(InfoExtractor):
 		video_extension = {'18': 'mp4', '17': '3gp'}.get(format_param, 'flv')
 
 		# Normalize URL, including format
-		normalized_url = 'http://www.youtube.com/watch?v=%s' % video_id
+		normalized_url = 'http://www.youtube.com/watch?v=%s&gl=US&hl=en' % video_id
 		if format_param is not None:
 			normalized_url = '%s&fmt=%s' % (normalized_url, format_param)
 		request = urllib2.Request(normalized_url, None, std_headers)
@@ -592,7 +612,7 @@ class MetacafeIE(InfoExtractor):
 	"""Information Extractor for metacafe.com."""
 
 	_VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*'
-	_DISCLAIMER = 'http://www.metacafe.com/disclaimer'
+	_DISCLAIMER = 'http://www.metacafe.com/family_filter/'
 	_youtube_ie = None
 
 	def __init__(self, youtube_ie, downloader=None):
@@ -631,10 +651,10 @@ class MetacafeIE(InfoExtractor):
 
 		# Confirm age
 		disclaimer_form = {
-			'allowAdultContent': '1',
+			'filters': '0',
 			'submit': "Continue - I'm over 18",
 			}
-		request = urllib2.Request('http://www.metacafe.com/watch/', urllib.urlencode(disclaimer_form), std_headers)
+		request = urllib2.Request('http://www.metacafe.com/', urllib.urlencode(disclaimer_form), std_headers)
 		try:
 			self.report_age_confirmation()
 			disclaimer = urllib2.urlopen(request).read()
@@ -684,7 +704,7 @@ class MetacafeIE(InfoExtractor):
 
 		video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
 
-		mobj = re.search(r'(?im)<meta name="title" content="Metacafe - ([^"]+)"', webpage)
+		mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage)
 		if mobj is None:
 			self.to_stderr(u'ERROR: unable to extract title')
 			return [None]
@@ -706,11 +726,95 @@ class MetacafeIE(InfoExtractor):
 			'ext':		video_extension.decode('utf-8'),
 			}]
 
+
+class YoutubeSearchIE(InfoExtractor):
+	"""Information Extractor for YouTube search queries."""
+	_VALID_QUERY = r'ytsearch(\d+|all)?:[\s\S]+'
+	_TEMPLATE_URL = 'http://www.youtube.com/results?search_query=%s&page=%s&gl=US&hl=en'
+	_VIDEO_INDICATOR = r'href="/watch\?v=.+?"'
+	_MORE_PAGES_INDICATOR = r'>Next</a>'
+	_youtube_ie = None
+
+	def __init__(self, youtube_ie, downloader=None): 
+		InfoExtractor.__init__(self, downloader)
+		self._youtube_ie = youtube_ie
+	
+	@staticmethod
+	def suitable(url):
+		return (re.match(YoutubeSearchIE._VALID_QUERY, url) is not None)
+
+	def report_download_page(self, query, pagenum):
+		"""Report attempt to download playlist page with given number."""
+		self.to_stdout(u'[youtube] query "%s": Downloading page %s' % (query, pagenum))
+
+	def _real_initialize(self):
+		self._youtube_ie.initialize()
+	
+	def _real_extract(self, query):
+		mobj = re.match(self._VALID_QUERY, query)
+		if mobj is None:
+			self.to_stderr(u'ERROR: invalid search query "%s"' % query)
+			return [None]
+
+		prefix, query = query.split(':')
+		prefix = prefix[8:]
+		if prefix == '': 
+			return self._download_n_results(query, 1)
+		elif prefix == 'all': 
+			return self._download_n_results(query, -1)
+		else: 
+			try:
+				n = int(prefix)
+				if n <= 0:
+					self.to_stderr(u'ERROR: invalid download number %s for query "%s"' % (n, query))
+					return [None]
+				return self._download_n_results(query, n)
+			except ValueError: # parsing prefix as int fails
+				return self._download_n_results(query, 1)
+
+	def _download_n_results(self, query, n):
+		"""Downloads a specified number of results for a query"""
+
+		video_ids = []
+		already_seen = set()
+		pagenum = 1
+
+		while True:
+			self.report_download_page(query, pagenum)
+			result_url = self._TEMPLATE_URL % (urllib.quote_plus(query), pagenum)
+			request = urllib2.Request(result_url, None, std_headers)
+			try:
+				page = urllib2.urlopen(request).read()
+			except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+				self.to_stderr(u'ERROR: unable to download webpage: %s' % str(err))
+				return [None]
+
+			# Extract video identifiers
+			for mobj in re.finditer(self._VIDEO_INDICATOR, page):
+				video_id = page[mobj.span()[0]:mobj.span()[1]].split('=')[2][:-1]
+				if video_id not in already_seen:
+					video_ids.append(video_id)
+					already_seen.add(video_id)
+					if len(video_ids) == n:
+						# Specified n videos reached
+						information = []
+						for id in video_ids:
+							information.extend(self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id))
+						return information
+
+			if self._MORE_PAGES_INDICATOR not in page:
+				information = []
+				for id in video_ids:
+					information.extend(self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id))
+				return information
+
+			pagenum = pagenum + 1
+
 class YoutubePlaylistIE(InfoExtractor):
 	"""Information Extractor for YouTube playlists."""
 
 	_VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/view_play_list\?p=(.+)'
-	_TEMPLATE_URL = 'http://www.youtube.com/view_play_list?p=%s&page=%s'
+	_TEMPLATE_URL = 'http://www.youtube.com/view_play_list?p=%s&page=%s&gl=US&hl=en'
 	_VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
 	_MORE_PAGES_INDICATOR = r'/view_play_list?p=%s&amp;page=%s'
 	_youtube_ie = None
@@ -752,10 +856,11 @@ class YoutubePlaylistIE(InfoExtractor):
 				return [None]
 
 			# Extract video identifiers
-			ids_in_page = set()
+			ids_in_page = []
 			for mobj in re.finditer(self._VIDEO_INDICATOR, page):
-				ids_in_page.add(mobj.group(1))
-			video_ids.extend(list(ids_in_page))
+				if mobj.group(1) not in ids_in_page:
+					ids_in_page.append(mobj.group(1))
+			video_ids.extend(ids_in_page)
 
 			if (self._MORE_PAGES_INDICATOR % (playlist_id, pagenum + 1)) not in page:
 				break
@@ -836,7 +941,7 @@ if __name__ == '__main__':
 		# Parse command line
 		parser = optparse.OptionParser(
 				usage='Usage: %prog [options] url...',
-				version='2008.08.09',
+				version='2009.02.07',
 				conflict_handler='resolve',
 				)
 		parser.add_option('-h', '--help',
@@ -873,10 +978,23 @@ if __name__ == '__main__':
 				action='store_true', dest='ignoreerrors', help='continue on download errors', default=False)
 		parser.add_option('-r', '--rate-limit',
 				dest='ratelimit', metavar='L', help='download rate limit (e.g. 50k or 44.6m)')
+		parser.add_option('-a', '--batch-file',
+				dest='batchfile', metavar='F', help='file containing URLs to download')
+		parser.add_option('-w', '--no-overwrites',
+				action='store_true', dest='nooverwrites', help='do not overwrite files', default=False)
 		(opts, args) = parser.parse_args()
 
+		# Batch file verification
+		batchurls = []
+		if opts.batchfile is not None:
+			try:
+				batchurls = [line.strip() for line in open(opts.batchfile, 'r')]
+			except IOError:
+				sys.exit(u'ERROR: batch file could not be read')
+		all_urls = batchurls + args
+
 		# Conflicting, missing and erroneous options
-		if len(args) < 1:
+		if len(all_urls) < 1:
 			sys.exit(u'ERROR: you must provide at least one URL')
 		if opts.usenetrc and (opts.username is not None or opts.password is not None):
 			sys.exit(u'ERROR: using .netrc conflicts with giving username/password')
@@ -898,8 +1016,12 @@ if __name__ == '__main__':
 		youtube_ie = YoutubeIE()
 		metacafe_ie = MetacafeIE(youtube_ie)
 		youtube_pl_ie = YoutubePlaylistIE(youtube_ie)
+		youtube_search_ie = YoutubeSearchIE(youtube_ie)
 
 		# File downloader
+		charset = locale.getdefaultlocale()[1]
+		if charset is None:
+			charset = 'ascii'
 		fd = FileDownloader({
 			'usenetrc': opts.usenetrc,
 			'username': opts.username,
@@ -909,17 +1031,19 @@ if __name__ == '__main__':
 			'forcetitle': opts.gettitle,
 			'simulate': (opts.simulate or opts.geturl or opts.gettitle),
 			'format': opts.format,
-			'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode())
+			'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(charset))
 				or (opts.usetitle and u'%(stitle)s-%(id)s.%(ext)s')
 				or (opts.useliteral and u'%(title)s-%(id)s.%(ext)s')
 				or u'%(id)s.%(ext)s'),
 			'ignoreerrors': opts.ignoreerrors,
 			'ratelimit': opts.ratelimit,
+			'nooverwrites': opts.nooverwrites,
 			})
+		fd.add_info_extractor(youtube_search_ie)
 		fd.add_info_extractor(youtube_pl_ie)
 		fd.add_info_extractor(metacafe_ie)
 		fd.add_info_extractor(youtube_ie)
-		retcode = fd.download(args)
+		retcode = fd.download(all_urls)
 		sys.exit(retcode)
 
 	except DownloadError: