X-Git-Url: https://git.jankratochvil.net/?a=blobdiff_plain;f=youtube_dl%2F__init__.py;h=3fed554df0d3d7878bd728a2b85172cea2ef3356;hb=3e0ea7d07ab0eb649edae89d6fbac827f2af6478;hp=042b852671b01e5f12092d5a980337360129199d;hpb=40fd4cb86ae4b99e1fb0572e5e24f85a4782a07d;p=youtube-dl.git

diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py
index 042b852..3fed554 100755
--- a/youtube_dl/__init__.py
+++ b/youtube_dl/__init__.py
@@ -282,6 +282,14 @@ def _simplify_title(title):
 	expr = re.compile(ur'[^\w\d_\-]+', flags=re.UNICODE)
 	return expr.sub(u'_', title).strip(u'_')
 
+def _orderedSet(iterable):
+	""" Remove all duplicates from the input iterable """
+	res = []
+	for el in iterable:
+		if el not in res:
+			res.append(el)
+	return res
+
 class DownloadError(Exception):
 	"""Download Error exception.
 
@@ -309,6 +317,10 @@ class PostProcessingError(Exception):
 	"""
 	pass
 
+class MaxDownloadsReached(Exception):
+	""" --max-downloads limit has been reached. """
+	pass
+
 
 class UnavailableVideoError(Exception):
 	"""Unavailable Format exception.
@@ -722,8 +734,7 @@ class FileDownloader(object):
 		max_downloads = self.params.get('max_downloads')
 		if max_downloads is not None:
 			if self._num_downloads > int(max_downloads):
-				self.to_screen(u'[download] Maximum number of downloads reached. Skipping ' + info_dict['title'])
-				return
+				raise MaxDownloadsReached()
 
 		filename = self.prepare_filename(info_dict)
 		
@@ -3744,6 +3755,124 @@ class MixcloudIE(InfoExtractor):
 		except UnavailableVideoError, err:
 			self._downloader.trouble(u'ERROR: unable to download file')
 
+class StanfordOpenClassroomIE(InfoExtractor):
+	"""Information extractor for Stanford's Open ClassRoom"""
+
+	_VALID_URL = r'^(?:https?://)?openclassroom.stanford.edu(?P<path>/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P<course>[^&]+)(&video=(?P<video>[^&]+))?(&.*)?)?))$'
+	IE_NAME = u'stanfordoc'
+
+	def report_download_webpage(self, objid):
+		"""Report information extraction."""
+		self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, objid))
+
+	def report_extraction(self, video_id):
+		"""Report information extraction."""
+		self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
+
+	def _real_extract(self, url):
+		mobj = re.match(self._VALID_URL, url)
+		if mobj is None:
+			self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+			return
+
+		if mobj.group('course') and mobj.group('video'): # A specific video
+			course = mobj.group('course')
+			video = mobj.group('video')
+			info = {
+				'id': _simplify_title(course + '_' + video),
+			}
+	
+			self.report_extraction(info['id'])
+			baseUrl = 'http://openclassroom.stanford.edu/MainFolder/courses/' + course + '/videos/'
+			xmlUrl = baseUrl + video + '.xml'
+			try:
+				metaXml = urllib2.urlopen(xmlUrl).read()
+			except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+				self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % unicode(err))
+				return
+			mdoc = xml.etree.ElementTree.fromstring(metaXml)
+			try:
+				info['title'] = mdoc.findall('./title')[0].text
+				info['url'] = baseUrl + mdoc.findall('./videoFile')[0].text
+			except IndexError:
+				self._downloader.trouble(u'\nERROR: Invalid metadata XML file')
+				return
+			info['stitle'] = _simplify_title(info['title'])
+			info['ext'] = info['url'].rpartition('.')[2]
+			info['format'] = info['ext']
+			self._downloader.increment_downloads()
+			try:
+				self._downloader.process_info(info)
+			except UnavailableVideoError, err:
+				self._downloader.trouble(u'\nERROR: unable to download video')
+		elif mobj.group('course'): # A course page
+			unescapeHTML = HTMLParser.HTMLParser().unescape
+
+			course = mobj.group('course')
+			info = {
+				'id': _simplify_title(course),
+				'type': 'playlist',
+			}
+
+			self.report_download_webpage(info['id'])
+			try:
+				coursepage = urllib2.urlopen(url).read()
+			except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+				self._downloader.trouble(u'ERROR: unable to download course info page: ' + unicode(err))
+				return
+
+			m = re.search('<h1>([^<]+)</h1>', coursepage)
+			if m:
+				info['title'] = unescapeHTML(m.group(1))
+			else:
+				info['title'] = info['id']
+			info['stitle'] = _simplify_title(info['title'])
+
+			m = re.search('<description>([^<]+)</description>', coursepage)
+			if m:
+				info['description'] = unescapeHTML(m.group(1))
+
+			links = _orderedSet(re.findall('<a href="(VideoPage.php\?[^"]+)">', coursepage))
+			info['list'] = [
+				{
+					'type': 'reference',
+					'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(vpage),
+				}
+					for vpage in links]
+
+			for entry in info['list']:
+				assert entry['type'] == 'reference'
+				self.extract(entry['url'])
+		else: # Root page
+			unescapeHTML = HTMLParser.HTMLParser().unescape
+
+			info = {
+				'id': 'Stanford OpenClassroom',
+				'type': 'playlist',
+			}
+
+			self.report_download_webpage(info['id'])
+			rootURL = 'http://openclassroom.stanford.edu/MainFolder/HomePage.php'
+			try:
+				rootpage = urllib2.urlopen(rootURL).read()
+			except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+				self._downloader.trouble(u'ERROR: unable to download course info page: ' + unicode(err))
+				return
+
+			info['title'] = info['id']
+			info['stitle'] = _simplify_title(info['title'])
+
+			links = _orderedSet(re.findall('<a href="(CoursePage.php\?[^"]+)">', rootpage))
+			info['list'] = [
+				{
+					'type': 'reference',
+					'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(cpage),
+				}
+					for cpage in links]
+
+			for entry in info['list']:
+				assert entry['type'] == 'reference'
+				self.extract(entry['url'])
 
 
 class PostProcessor(object):
@@ -3839,8 +3968,13 @@ class FFmpegExtractAudioPP(PostProcessor):
 			return None
 
 		more_opts = []
-		if self._preferredcodec == 'best' or self._preferredcodec == filecodec:
-			if filecodec in ['aac', 'mp3', 'vorbis']:
+		if self._preferredcodec == 'best' or self._preferredcodec == filecodec or (self._preferredcodec == 'm4a' and filecodec == 'aac'):
+			if self._preferredcodec == 'm4a' and filecodec == 'aac':
+				# Lossless, but in another container
+				acodec = 'copy'
+				extension = self._preferredcodec
+				more_opts = ['-absf', 'aac_adtstoasc']
+			elif filecodec in ['aac', 'mp3', 'vorbis']:
 				# Lossless if possible
 				acodec = 'copy'
 				extension = filecodec
@@ -3857,13 +3991,15 @@ class FFmpegExtractAudioPP(PostProcessor):
 					more_opts += ['-ab', self._preferredquality]
 		else:
 			# We convert the audio (lossy)
-			acodec = {'mp3': 'libmp3lame', 'aac': 'aac', 'vorbis': 'libvorbis'}[self._preferredcodec]
+			acodec = {'mp3': 'libmp3lame', 'aac': 'aac', 'm4a': 'aac', 'vorbis': 'libvorbis'}[self._preferredcodec]
 			extension = self._preferredcodec
 			more_opts = []
 			if self._preferredquality is not None:
 				more_opts += ['-ab', self._preferredquality]
 			if self._preferredcodec == 'aac':
 				more_opts += ['-f', 'adts']
+			if self._preferredcodec == 'm4a':
+				more_opts += ['-absf', 'aac_adtstoasc']
 			if self._preferredcodec == 'vorbis':
 				extension = 'ogg'
 
@@ -4110,7 +4246,7 @@ def parseOpts():
 	postproc.add_option('--extract-audio', action='store_true', dest='extractaudio', default=False,
 			help='convert video files to audio-only files (requires ffmpeg and ffprobe)')
 	postproc.add_option('--audio-format', metavar='FORMAT', dest='audioformat', default='best',
-			help='"best", "aac", "vorbis" or "mp3"; best by default')
+			help='"best", "aac", "vorbis", "mp3", or "m4a"; best by default')
 	postproc.add_option('--audio-quality', metavar='QUALITY', dest='audioquality', default='128K',
 			help='ffmpeg audio bitrate specification, 128k by default')
 	postproc.add_option('-k', '--keep-video', action='store_true', dest='keepvideo', default=False,
@@ -4166,6 +4302,7 @@ def gen_extractors():
 		SoundcloudIE(),
 		InfoQIE(),
 		MixcloudIE(),
+		StanfordOpenClassroomIE(),
 
 		GenericIE()
 	]
@@ -4255,7 +4392,7 @@ def _real_main():
 	except (TypeError, ValueError), err:
 		parser.error(u'invalid playlist end number specified')
 	if opts.extractaudio:
-		if opts.audioformat not in ['best', 'aac', 'mp3', 'vorbis']:
+		if opts.audioformat not in ['best', 'aac', 'mp3', 'vorbis', 'm4a']:
 			parser.error(u'invalid audio format specified')
 
 	# File downloader
@@ -4320,7 +4457,12 @@ def _real_main():
 			parser.error(u'you must provide at least one URL')
 		else:
 			sys.exit()
-	retcode = fd.download(all_urls)
+	
+	try:
+		retcode = fd.download(all_urls)
+	except MaxDownloadsReached:
+		fd.to_screen(u'--max-download limit reached, aborting.')
+		retcode = 101
 
 	# Dump cookie jar if requested
 	if opts.cookiefile is not None: