forcetitle: Force printing title.
simulate: Do not download the video files.
format: Video format code.
+ format_limit: Highest quality format to try.
outtmpl: Template for output names.
ignoreerrors: Do not stop on download errors.
ratelimit: Download speed limit, in bytes/sec.
self.to_stdout(u'[download] Download completed')
else:
self.to_stdout(u'')
+
+ def increment_downloads(self):
+ """Increment the ordinal that assigns a number to each file."""
+ self._num_downloads += 1
def process_info(self, info_dict):
"""Process a single dictionary returned by an InfoExtractor."""
try:
(stream, filename) = sanitize_open(filename, open_mode)
self.report_destination(filename)
- self._num_downloads += 1
except (OSError, IOError), err:
self.trouble('ERROR: unable to open for writing: %s' % str(err))
return False
class YoutubeIE(InfoExtractor):
"""Information extractor for youtube.com."""
- _VALID_URL = r'^((?:http://)?(?:\w+\.)?youtube\.com/(?:(?:v/)|(?:(?:watch(?:\.php)?)?[\?#](?:.+&)?v=)))?([0-9A-Za-z_-]+)(?(1).+)?$'
+ _VALID_URL = r'^((?:http://)?(?:youtu\.be/|(?:\w+\.)?youtube\.com/(?:(?:v/)|(?:(?:watch(?:_popup)?(?:\.php)?)?[\?#](?:.+&)?v=))))?([0-9A-Za-z_-]+)(?(1).+)?$'
_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'
- _available_formats = ['37', '22', '35', '18', '34', '5', '17', '13', None] # listed in order of priority for -b flag
+ # Listed in order of priority for the -b option
+ _available_formats = ['38', '37', '22', '45', '35', '34', '43', '18', '6', '5', '17', '13', None]
_video_extensions = {
'13': '3gp',
'17': 'mp4',
'18': 'mp4',
'22': 'mp4',
'37': 'mp4',
+ '38': 'video', # You actually don't know if this will be MOV, AVI or whatever
'43': 'webm',
'45': 'webm',
}
if mobj is None:
self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
return
+
+ # At this point we have a new video
+ if self._downloader is not None:
+ self._downloader.increment_downloads()
video_id = mobj.group(2)
# Downloader parameters
params = self._downloader.params
format_param = params.get('format', None)
if format_param == '0':
+ format_limit = params.get('format_limit', None)
+ if format_limit is not None:
+ try:
+ # Start at a different format if the user has limited the maximum quality
+ quality_index = self._available_formats.index(format_limit)
+ except ValueError:
+ pass
format_param = self._available_formats[quality_index]
best_quality = True
elif format_param == '-1':
return
# Attempt to extract SWF player URL
- mobj = re.search(r'swfConfig.*"(http://.*?watch-.*?\.swf)"', video_webpage)
+ mobj = re.search(r'swfConfig.*"(http://.*?watch.*?-.*?\.swf)"', video_webpage)
if mobj is not None:
player_url = mobj.group(1)
else:
self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % mobj2.group(1))
return
+ # At this point we have a new video
+ if self._downloader is not None:
+ self._downloader.increment_downloads()
+
simple_title = mobj.group(2).decode('utf-8')
video_extension = 'flv'
self._downloader.trouble(u'ERROR: format not available for video')
+class DailymotionIE(InfoExtractor):
+ """Information Extractor for Dailymotion"""
+
+ _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^_/]+)_([^/]+)'
+
+ def __init__(self, downloader=None):
+ InfoExtractor.__init__(self, downloader)
+
+ @staticmethod
+ def suitable(url):
+ return (re.match(DailymotionIE._VALID_URL, url) is not None)
+
+ def report_download_webpage(self, video_id):
+ """Report webpage download."""
+ self._downloader.to_stdout(u'[dailymotion] %s: Downloading webpage' % video_id)
+
+ def report_extraction(self, video_id):
+ """Report information extraction."""
+ self._downloader.to_stdout(u'[dailymotion] %s: Extracting information' % video_id)
+
+ def _real_initialize(self):
+ return
+
+ def _real_extract(self, url):
+ # Extract id and simplified title from URL
+ mobj = re.match(self._VALID_URL, url)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
+ return
+
+ # At this point we have a new video
+ if self._downloader is not None:
+ self._downloader.increment_downloads()
+ video_id = mobj.group(1)
+
+ simple_title = mobj.group(2).decode('utf-8')
+ video_extension = 'flv'
+
+ # Retrieve video webpage to extract further information
+ request = urllib2.Request(url)
+ try:
+ self.report_download_webpage(video_id)
+ webpage = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % str(err))
+ return
+
+ # Extract URL, uploader and title from webpage
+ self.report_extraction(video_id)
+ mobj = re.search(r'(?i)addVariable\(\"video\"\s*,\s*\"([^\"]*)\"\)', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract media URL')
+ return
+ mediaURL = urllib.unquote(mobj.group(1))
+
+ # if needed add http://www.dailymotion.com/ if relative URL
+
+ video_url = mediaURL
+
+ # '<meta\s+name="title"\s+content="Dailymotion\s*[:\-]\s*(.*?)"\s*\/\s*>'
+ mobj = re.search(r'(?im)<title>Dailymotion\s*[\-:]\s*(.+?)</title>', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract title')
+ return
+ video_title = mobj.group(1).decode('utf-8')
+ video_title = sanitize_title(video_title)
+
+ mobj = re.search(r'(?im)<div class="dmco_html owner">.*?<a class="name" href="/.+?">(.+?)</a></div>', webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
+ return
+ video_uploader = mobj.group(1)
+
+ try:
+ # Process video information
+ self._downloader.process_info({
+ 'id': video_id.decode('utf-8'),
+ 'url': video_url.decode('utf-8'),
+ 'uploader': video_uploader.decode('utf-8'),
+ 'title': video_title,
+ 'stitle': simple_title,
+ 'ext': video_extension.decode('utf-8'),
+ 'format': u'NA',
+ 'player_url': None,
+ })
+ except UnavailableFormatError:
+ self._downloader.trouble(u'ERROR: format not available for video')
+
class GoogleIE(InfoExtractor):
"""Information extractor for video.google.com."""
self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
return
+ # At this point we have a new video
+ if self._downloader is not None:
+ self._downloader.increment_downloads()
video_id = mobj.group(1)
video_extension = 'mp4'
self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
return
+ # At this point we have a new video
+ if self._downloader is not None:
+ self._downloader.increment_downloads()
video_id = mobj.group(1)
video_extension = 'flv'
def _real_initialize(self):
return
- def _real_extract(self, url):
+ def _real_extract(self, url, new_video=True):
# Extract ID from URL
mobj = re.match(self._VALID_URL, url)
if mobj is None:
self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
return
+ # At this point we have a new video
+ if self._downloader is not None and new_video:
+ self._downloader.increment_downloads()
video_id = mobj.group(2)
video_extension = 'flv'
yahoo_vid = mobj.group(1)
url = 'http://video.yahoo.com/watch/%s/%s' % (yahoo_vid, yahoo_id)
- return self._real_extract(url)
+ return self._real_extract(url, new_video=False)
# Retrieve video webpage to extract further information
request = urllib2.Request(url)
return
def _real_extract(self, url):
+ # At this point we have a new video
+ if self._downloader is not None:
+ self._downloader.increment_downloads()
+
video_id = url.split('/')[-1]
request = urllib2.Request(url)
try:
action='store_const', dest='format', help='alias for -f 22', const='22')
video_format.add_option('--all-formats',
action='store_const', dest='format', help='download all available video formats', const='-1')
+ video_format.add_option('--max-quality',
+ action='store', dest='format_limit', metavar='FORMAT', help='highest quality format limit for -b')
parser.add_option_group(video_format)
verbosity = optparse.OptionGroup(parser, 'Verbosity / Simulation Options')
# Information extractors
youtube_ie = YoutubeIE()
metacafe_ie = MetacafeIE(youtube_ie)
+ dailymotion_ie = DailymotionIE()
youtube_pl_ie = YoutubePlaylistIE(youtube_ie)
youtube_user_ie = YoutubeUserIE(youtube_ie)
youtube_search_ie = YoutubeSearchIE(youtube_ie)
'forcedescription': opts.getdescription,
'simulate': (opts.simulate or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription),
'format': opts.format,
+ 'format_limit': opts.format_limit,
'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(preferredencoding()))
or (opts.format == '-1' and opts.usetitle and u'%(stitle)s-%(id)s-%(format)s.%(ext)s')
or (opts.format == '-1' and opts.useliteral and u'%(title)s-%(id)s-%(format)s.%(ext)s')
fd.add_info_extractor(youtube_pl_ie)
fd.add_info_extractor(youtube_user_ie)
fd.add_info_extractor(metacafe_ie)
+ fd.add_info_extractor(dailymotion_ie)
fd.add_info_extractor(youtube_ie)
fd.add_info_extractor(google_ie)
fd.add_info_extractor(google_search_ie)
projects / youtube-dl / blobdiff