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.
"""
pass
+class MaxDownloadsReached(Exception):
+ """ --max-downloads limit has been reached. """
+ pass
+
class UnavailableVideoError(Exception):
"""Unavailable Format exception.
return u'"' + title + '" title matched reject pattern "' + rejecttitle + '"'
return None
- def process_dict(self, info_dict):
- """ Download and handle the extracted information.
- For details on the specification of the various types of content, refer to the _process_* functions. """
- if info_dict['type'] == 'playlist':
- self._process_playlist(info_dict)
- elif info_dict['type'] == 'legacy-video':
- self.process_info(info_dict)
- else:
- raise ValueError('Invalid item type')
-
- def _process_playlist(self, info_dict):
- assert info_dict['type'] == 'playlist'
- assert 'title' in info_dict
- assert 'stitle' in info_dict
- entries = info_dict['list']
-
- for e in entries:
- self.process_dict(e)
-
def process_info(self, info_dict):
"""Process a single dictionary returned by an InfoExtractor."""
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)
_NETRC_MACHINE = 'youtube'
# Listed in order of quality
_available_formats = ['38', '37', '22', '45', '35', '44', '34', '18', '43', '6', '5', '17', '13']
+ _available_formats_prefer_free = ['38', '37', '45', '22', '44', '35', '43', '34', '18', '6', '5', '17', '13']
_video_extensions = {
'13': '3gp',
'17': 'mp4',
url_map = dict((ud['itag'][0], ud['url'][0]) for ud in url_data)
format_limit = self._downloader.params.get('format_limit', None)
- if format_limit is not None and format_limit in self._available_formats:
- format_list = self._available_formats[self._available_formats.index(format_limit):]
+ available_formats = self._available_formats_prefer_free if self._downloader.params.get('prefer_free_formats', False) else self._available_formats
+ if format_limit is not None and format_limit in available_formats:
+ format_list = available_formats[available_formats.index(format_limit):]
else:
- format_list = self._available_formats
+ format_list = available_formats
existing_formats = [x for x in format_list if x in url_map]
if len(existing_formats) == 0:
self._downloader.trouble(u'ERROR: no known formats available for video')
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>[^&]+))?(&.*)?)?))$'
+ _VALID_URL = r'^(?:https?://)?openclassroom.stanford.edu(?P<path>/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P<course>[^&]+)(&video=(?P<video>[^&]+))?(&.*)?)?))$'
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))
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' % str(err))
+ self._downloader.trouble(u'ERROR: unable to download video info XML: %s' % unicode(err))
return
mdoc = xml.etree.ElementTree.fromstring(metaXml)
try:
self._downloader.process_info(info)
except UnavailableVideoError, err:
self._downloader.trouble(u'\nERROR: unable to download video')
- else:
- print('TODO: Not yet implemented')
- 1/0
+ 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):
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
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'
action='store', dest='format', metavar='FORMAT', help='video format code')
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',
+ action='store_true', dest='prefer_free_formats', default=False, help='prefer free video formats unless a specific one is requested')
video_format.add_option('--max-quality',
action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download')
video_format.add_option('-F', '--list-formats',
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,
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
'matchtitle': opts.matchtitle,
'rejecttitle': opts.rejecttitle,
'max_downloads': opts.max_downloads,
+ 'prefer_free_formats': opts.prefer_free_formats,
})
for extractor in extractors:
fd.add_info_extractor(extractor)
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:
git://git.jankratochvil.net / youtube-dl.git / blobdiff