'Sören Schulze',
'Kevin Ngo',
'Ori Avtalion',
+ 'shizeeg',
)
__license__ = 'Public Domain'
-__version__ = '2011.10.19'
+__version__ = '2011.11.23'
UPDATE_URL = 'https://raw.github.com/rg3/youtube-dl/master/youtube-dl'
'Accept-Language': 'en-us,en;q=0.5',
}
-simple_title_chars = string.ascii_letters.decode('ascii') + string.digits.decode('ascii')
-
try:
import json
except ImportError: # Python <2.6, use trivialjson (https://github.com/phihag/trivialjson):
return timestamp
def _simplify_title(title):
- return re.sub(ur'[^\w\d_\-]+', u'_', title)
+ expr = re.compile(ur'[^\w\d_\-]+', flags=re.UNICODE)
+ return expr.sub(u'_', title).strip(u'_')
class DownloadError(Exception):
"""Download Error exception.
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
+
filename = self.prepare_filename(info_dict)
# Forced printings
video_title = sanitize_title(video_title)
# simplified title
- simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
- simple_title = simple_title.strip(ur'_')
+ simple_title = _simplify_title(video_title)
# thumbnail image
if 'thumbnail_url' not in video_info:
return
video_title = mobj.group(1).decode('utf-8')
video_title = sanitize_title(video_title)
- simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+ simple_title = _simplify_title(video_title)
# Extract video description
mobj = re.search(r'<span id=short-desc-content>([^<]*)</span>', webpage)
return
video_title = mobj.group(1).decode('utf-8')
video_title = sanitize_title(video_title)
- simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+ simple_title = _simplify_title(vide_title)
video_uploader = mobj.group(2).decode('utf-8')
self._downloader.trouble(u'ERROR: unable to extract video title')
return
video_title = mobj.group(1).decode('utf-8')
- simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+ simple_title = _simplify_title(video_title)
mobj = re.search(r'<h2 class="ti-5"><a href="http://video\.yahoo\.com/(people|profile)/[0-9]+" beacon=".*">(.*)</a></h2>', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract video title')
return
video_title = mobj.group(1).decode('utf-8')
- simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+ simple_title = _simplify_title(video_title)
# Extract uploader
mobj = re.search(r'<uploader_url>http://vimeo.com/(.*?)</uploader_url>', webpage)
return
video_title = mobj.group(1).decode('utf-8')
video_title = sanitize_title(video_title)
- simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+ simple_title = _simplify_title(video_title)
# video uploader is domain name
mobj = re.match(r'(?:https?://)?([^/]*)/.*', url)
video_title = video_title.decode('utf-8')
video_title = sanitize_title(video_title)
- # simplified title
- simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
- simple_title = simple_title.strip(ur'_')
+ simple_title = _simplify_title(video_title)
# thumbnail image
if 'thumbnail' not in video_info:
"""Report information extraction."""
self._downloader.to_screen(u'[%s] %s: Direct download detected' % (self.IE_NAME, title))
- def _simplify_title(self, title):
- res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title)
- res = res.strip(ur'_')
- return res
-
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
if urlh.headers.get('Content-Type', '').startswith('video/'): # Direct download
basename = url.split('/')[-1]
title,ext = os.path.splitext(basename)
+ title = title.decode('UTF-8')
ext = ext.replace('.', '')
self.report_direct_download(title)
info = {
'id': title,
'url': url,
'title': title,
- 'stitle': self._simplify_title(title),
+ 'stitle': _simplify_title(title),
'ext': ext,
'urlhandle': urlh
}
'uploader': data['display_name'],
'upload_date': upload_date,
'title': data['title'],
- 'stitle': self._simplify_title(data['title']),
+ 'stitle': _simplify_title(data['title']),
'ext': ext,
'format': data['media']['mimeType'],
'thumbnail': data['thumbnailUrl'],
return
video_id = mobj.group(1)
- simple_title = mobj.group(2).decode('utf-8')
- # should actually not be necessary
- simple_title = sanitize_title(simple_title)
- simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', simple_title)
# Get video webpage
request = urllib2.Request('http://www.myvideo.de/watch/%s' % video_id)
video_title = mobj.group(1)
video_title = sanitize_title(video_title)
+ simple_title = _simplify_title(video_title)
+
try:
self._downloader.process_info({
'id': video_id,
def report_player_url(self, episode_id):
self._downloader.to_screen(u'[comedycentral] %s: Determining player URL' % episode_id)
- def _simplify_title(self, title):
- res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title)
- res = res.strip(ur'_')
- return res
-
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
if mobj.group('shortname'):
if mobj.group('shortname') in ('tds', 'thedailyshow'):
- url = 'http://www.thedailyshow.com/full-episodes/'
+ url = u'http://www.thedailyshow.com/full-episodes/'
else:
- url = 'http://www.colbertnation.com/full-episodes/'
+ url = u'http://www.colbertnation.com/full-episodes/'
mobj = re.match(self._VALID_URL, url)
assert mobj is not None
self._downloader.increment_downloads()
- effTitle = showId + '-' + epTitle
+ effTitle = showId + u'-' + epTitle
info = {
'id': shortMediaId,
'url': video_url,
'uploader': showId,
'upload_date': officialDate,
'title': effTitle,
- 'stitle': self._simplify_title(effTitle),
+ 'stitle': _simplify_title(effTitle),
'ext': 'mp4',
'format': format,
'thumbnail': None,
def report_config_download(self, showName):
self._downloader.to_screen(u'[escapist] %s: Downloading configuration' % showName)
- def _simplify_title(self, title):
- res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title)
- res = res.strip(ur'_')
- return res
-
def _real_extract(self, url):
htmlParser = HTMLParser.HTMLParser()
'uploader': showName,
'upload_date': None,
'title': showName,
- 'stitle': self._simplify_title(showName),
+ 'stitle': _simplify_title(showName),
'ext': 'flv',
'format': 'flv',
'thumbnail': imgUrl,
"""Report information extraction."""
self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
- def _simplify_title(self, title):
- res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title)
- res = res.strip(ur'_')
- return res
-
def _real_extract(self, url):
htmlParser = HTMLParser.HTMLParser()
videoNode = mdoc.findall('./video')[0]
info['description'] = videoNode.findall('./description')[0].text
info['title'] = videoNode.findall('./caption')[0].text
- info['stitle'] = self._simplify_title(info['title'])
+ info['stitle'] = _simplify_title(info['title'])
info['url'] = videoNode.findall('./file')[0].text
info['thumbnail'] = videoNode.findall('./thumbnail')[0].text
info['ext'] = info['url'].rpartition('.')[2]
"""Report information extraction."""
self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
- def _simplify_title(self, title):
- res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title)
- res = res.strip(ur'_')
- return res
-
def _real_extract(self, url):
htmlParser = HTMLParser.HTMLParser()
'uploader': None,
'upload_date': None,
'title': video_title,
- 'stitle': self._simplify_title(video_title),
+ 'stitle': _simplify_title(video_title),
'ext': 'flv',
'format': 'flv',
'thumbnail': video_thumbnail,
if mobj:
try:
upload_date = datetime.datetime.strptime(mobj.group(1), '%B %d, %Y %H:%M').strftime('%Y%m%d')
- except Exception as e:
+ except Exception, e:
print str(e)
# for soundcloud, a request to a cross domain is required for cookies
"""Report information extraction."""
self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id))
- def _simplify_title(self, title):
- res = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', title)
- res = res.strip(ur'_')
- return res
-
def _real_extract(self, url):
htmlParser = HTMLParser.HTMLParser()
'uploader': None,
'upload_date': None,
'title': video_title,
- 'stitle': self._simplify_title(video_title),
+ 'stitle': _simplify_title(video_title),
'ext': extension,
'format': extension, # Extension is always(?) mp4, but seems to be flv
'thumbnail': None,
except UnavailableVideoError, err:
self._downloader.trouble(u'\nERROR: unable to download ' + video_url)
+class MixcloudIE(InfoExtractor):
+ """Information extractor for www.mixcloud.com"""
+ _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([\w\d-]+)/([\w\d-]+)'
+ IE_NAME = u'mixcloud'
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ def report_download_json(self, file_id):
+ """Report JSON download."""
+ self._downloader.to_screen(u'[%s] Downloading json' % self.IE_NAME)
+
+ def report_extraction(self, file_id):
+ """Report information extraction."""
+ self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, file_id))
+
+ def get_urls(self, jsonData, fmt, bitrate='best'):
+ """Get urls from 'audio_formats' section in json"""
+ file_url = None
+ try:
+ bitrate_list = jsonData[fmt]
+ if bitrate is None or bitrate == 'best' or bitrate not in bitrate_list:
+ bitrate = max(bitrate_list) # select highest
+
+ url_list = jsonData[fmt][bitrate]
+ except TypeError: # we have no bitrate info.
+ url_list = jsonData[fmt]
+
+ return url_list
+
+ def check_urls(self, url_list):
+ """Returns 1st active url from list"""
+ for url in url_list:
+ try:
+ urllib2.urlopen(url)
+ return url
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ url = None
+
+ return None
+
+ def _print_formats(self, formats):
+ print 'Available formats:'
+ for fmt in formats.keys():
+ for b in formats[fmt]:
+ try:
+ ext = formats[fmt][b][0]
+ print '%s\t%s\t[%s]' % (fmt, b, ext.split('.')[-1])
+ except TypeError: # we have no bitrate info
+ ext = formats[fmt][0]
+ print '%s\t%s\t[%s]' % (fmt, '??', ext.split('.')[-1])
+ break
+
+ 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
+ # extract uploader & filename from url
+ uploader = mobj.group(1).decode('utf-8')
+ file_id = uploader + "-" + mobj.group(2).decode('utf-8')
+
+ # construct API request
+ file_url = 'http://www.mixcloud.com/api/1/cloudcast/' + '/'.join(url.split('/')[-3:-1]) + '.json'
+ # retrieve .json file with links to files
+ request = urllib2.Request(file_url)
+ try:
+ self.report_download_json(file_url)
+ jsonData = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: Unable to retrieve file: %s' % str(err))
+ return
+
+ # parse JSON
+ json_data = json.loads(jsonData)
+ player_url = json_data['player_swf_url']
+ formats = dict(json_data['audio_formats'])
+
+ req_format = self._downloader.params.get('format', None)
+ bitrate = None
+
+ if self._downloader.params.get('listformats', None):
+ self._print_formats(formats)
+ return
+
+ if req_format is None or req_format == 'best':
+ for format_param in formats.keys():
+ url_list = self.get_urls(formats, format_param)
+ # check urls
+ file_url = self.check_urls(url_list)
+ if file_url is not None:
+ break # got it!
+ else:
+ if req_format not in formats.keys():
+ self._downloader.trouble(u'ERROR: format is not available')
+ return
+
+ url_list = self.get_urls(formats, req_format)
+ file_url = self.check_urls(url_list)
+ format_param = req_format
+
+ # We have audio
+ self._downloader.increment_downloads()
+ try:
+ # Process file information
+ self._downloader.process_info({
+ 'id': file_id.decode('utf-8'),
+ 'url': file_url.decode('utf-8'),
+ 'uploader': uploader.decode('utf-8'),
+ 'upload_date': u'NA',
+ 'title': json_data['name'],
+ 'stitle': _simplify_title(json_data['name']),
+ 'ext': file_url.split('.')[-1].decode('utf-8'),
+ 'format': (format_param is None and u'NA' or format_param.decode('utf-8')),
+ 'thumbnail': json_data['thumbnail_url'],
+ 'description': json_data['description'],
+ 'player_url': player_url.decode('utf-8'),
+ })
+ except UnavailableVideoError, err:
+ self._downloader.trouble(u'ERROR: unable to download file')
+
class PostProcessor(object):
# Deferred imports
import getpass
import optparse
+ import shlex
+
+ def _readOptions(filename):
+ try:
+ optionf = open(filename)
+ except IOError:
+ return [] # silently skip if file is not present
+ try:
+ res = []
+ for l in optionf:
+ res += shlex.split(l, comments=True)
+ finally:
+ optionf.close()
+ return res
def _format_option_string(option):
''' ('-o', '--option') -> -o, --format METAVAR'''
dest='playlistend', metavar='NUMBER', help='playlist video to end at (default is last)', default=-1)
selection.add_option('--match-title', dest='matchtitle', metavar='REGEX',help='download only matching titles (regex or caseless sub-string)')
selection.add_option('--reject-title', dest='rejecttitle', metavar='REGEX',help='skip download for matching titles (regex or caseless sub-string)')
+ selection.add_option('--max-downloads', metavar='NUMBER', dest='max_downloads', help='Abort after downloading NUMBER files', default=None)
authentication.add_option('-u', '--username',
dest='username', metavar='USERNAME', help='account username')
action='store_true', dest='autonumber',
help='number downloaded files starting from 00000', default=False)
filesystem.add_option('-o', '--output',
- dest='outtmpl', metavar='TEMPLATE', help='output filename template. Use %(stitle)s to get the title, %(uploader)s for the uploader name, %(autonumber)s to get an automatically incremented number, %(ext)s for the filename extension, and %% for a literal percent')
+ dest='outtmpl', metavar='TEMPLATE', help='output filename template. Use %(stitle)s to get the title, %(uploader)s for the uploader name, %(autonumber)s to get an automatically incremented number, %(ext)s for the filename extension, %(upload_date)s for the upload date (YYYYMMDD), and %% for a literal percent')
filesystem.add_option('-a', '--batch-file',
dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)')
filesystem.add_option('-w', '--no-overwrites',
parser.add_option_group(authentication)
parser.add_option_group(postproc)
- opts, args = parser.parse_args()
+ argv = _readOptions('/etc/youtube-dl.conf') + _readOptions(os.path.expanduser('~/.youtube-dl.conf')) + sys.argv[1:]
+ opts, args = parser.parse_args(argv)
return parser, opts, args
XVideosIE(),
SoundcloudIE(),
InfoQIE(),
+ MixcloudIE(),
GenericIE()
]
'writeinfojson': opts.writeinfojson,
'matchtitle': opts.matchtitle,
'rejecttitle': opts.rejecttitle,
+ 'max_downloads': opts.max_downloads,
})
for extractor in extractors:
fd.add_info_extractor(extractor)