from cgi import parse_qs
std_headers = {
- 'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.2) Gecko/20100115 Firefox/3.6',
+ 'User-Agent': 'Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.2.7) Gecko/20100720 Firefox/3.6.7',
'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': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
'Accept-Language': 'en-us,en;q=0.5',
}
return (stream, filename)
except (IOError, OSError), err:
# In case of error, try to remove win32 forbidden chars
- filename = re.sub(ur'[<>:"\|\?\*]', u'#', filename)
+ filename = re.sub(ur'[/<>:"\|\?\*]', u'#', filename)
# An exception here should be caught in the caller
stream = open(filename, open_mode)
"""
pass
-class UnavailableFormatError(Exception):
+class UnavailableVideoError(Exception):
"""Unavailable Format exception.
This exception will be thrown when a video is requested
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:
self.verify_url(info_dict['url'].encode('utf-8')).decode('utf-8')
except (OSError, IOError, urllib2.URLError, httplib.HTTPException, socket.error), err:
- raise UnavailableFormatError
+ raise UnavailableVideoError
# Forced printings
if self.params.get('forcetitle', False):
try:
success = self._do_download(filename, info_dict['url'].encode('utf-8'), info_dict.get('player_url', None))
except (OSError, IOError), err:
- raise UnavailableFormatError
+ raise UnavailableVideoError
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self.trouble('ERROR: unable to download video data: %s' % str(err))
return
if content_length is not None and long(content_length) == resume_len:
# Because the file had already been fully downloaded
self.report_file_already_downloaded(filename)
- self._num_downloads += 1
return True
else:
# Because the server didn't let us
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).+)?$'
- _LANG_URL = r'http://uk.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
+ _VALID_URL = r'^((?:http://)?(?:youtu\.be/|(?:\w+\.)?youtube\.com/(?:(?:v/)|(?:(?:watch(?:_popup)?(?:\.php)?)?[\?#](?:.+&)?v=))))?([0-9A-Za-z_-]+)(?(1).+)?$'
+ _LANG_URL = r'http://www.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 quality
+ _available_formats = ['38', '37', '22', '45', '35', '34', '43', '18', '6', '5', '17', '13']
_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',
}
return
video_id = mobj.group(2)
- # Downloader parameters
- best_quality = False
- all_formats = False
- format_param = None
- quality_index = 0
- if self._downloader is not None:
- params = self._downloader.params
- format_param = params.get('format', None)
- if format_param == '0':
- format_param = self._available_formats[quality_index]
- best_quality = True
- elif format_param == '-1':
- format_param = self._available_formats[quality_index]
- all_formats = True
-
- while True:
- # Extension
- video_extension = self._video_extensions.get(format_param, 'flv')
+ # Get video webpage
+ self.report_video_webpage_download(video_id)
+ request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en' % video_id, None, std_headers)
+ try:
+ video_webpage = urllib2.urlopen(request).read()
+ except (urllib2.URLError, httplib.HTTPException, socket.error), err:
+ self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
+ return
- # Get video webpage
- self.report_video_webpage_download(video_id)
- request = urllib2.Request('http://www.youtube.com/watch?v=%s&gl=US&hl=en' % video_id, None, std_headers)
+ # Attempt to extract SWF player URL
+ mobj = re.search(r'swfConfig.*"(http://.*?watch.*?-.*?\.swf)"', video_webpage)
+ if mobj is not None:
+ player_url = mobj.group(1)
+ else:
+ player_url = None
+
+ # Get video info
+ self.report_video_info_webpage_download(video_id)
+ for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']:
+ video_info_url = ('http://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
+ % (video_id, el_type))
+ request = urllib2.Request(video_info_url, None, std_headers)
try:
- video_webpage = urllib2.urlopen(request).read()
+ video_info_webpage = urllib2.urlopen(request).read()
+ video_info = parse_qs(video_info_webpage)
+ if 'token' in video_info:
+ break
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
+ self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err))
return
+ self.report_information_extraction(video_id)
+
+ # uploader
+ if 'author' not in video_info:
+ self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
+ return
+ video_uploader = urllib.unquote_plus(video_info['author'][0])
- # Attempt to extract SWF player URL
- mobj = re.search(r'swfConfig.*"(http://.*?watch-.*?\.swf)"', video_webpage)
+ # title
+ if 'title' not in video_info:
+ self._downloader.trouble(u'ERROR: unable to extract video title')
+ return
+ video_title = urllib.unquote_plus(video_info['title'][0])
+ 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'_')
+
+ # thumbnail image
+ if 'thumbnail_url' not in video_info:
+ self._downloader.trouble(u'WARNING: unable to extract video thumbnail')
+ video_thumbnail = ''
+ else: # don't panic if we can't find it
+ video_thumbnail = urllib.unquote_plus(video_info['thumbnail_url'][0])
+
+ # description
+ video_description = 'No description available.'
+ if self._downloader.params.get('forcedescription', False):
+ mobj = re.search(r'<meta name="description" content="(.*)"(?:\s*/)?>', video_webpage)
if mobj is not None:
- player_url = mobj.group(1)
+ video_description = mobj.group(1)
+
+ # Decide which formats to download
+ if 'fmt_url_map' in video_info:
+ url_map = dict(tuple(pair.split('|')) for pair in video_info['fmt_url_map'][0].split(','))
+ 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):]
else:
- player_url = None
-
- # Get video info
- self.report_video_info_webpage_download(video_id)
- for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']:
- video_info_url = ('http://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
- % (video_id, el_type))
- request = urllib2.Request(video_info_url, None, std_headers)
- try:
- video_info_webpage = urllib2.urlopen(request).read()
- video_info = parse_qs(video_info_webpage)
- if 'token' in video_info:
- break
- except (urllib2.URLError, httplib.HTTPException, socket.error), err:
- self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err))
- return
- self.report_information_extraction(video_id)
-
- # "t" param
- if 'token' not in video_info:
- # Attempt to see if YouTube has issued an error message
- if 'reason' not in video_info:
- self._downloader.trouble(u'ERROR: unable to extract "t" parameter for unknown reason')
- stream = open('reportme-ydl-%s.dat' % time.time(), 'wb')
- stream.write(video_info_webpage)
- stream.close()
- else:
- reason = urllib.unquote_plus(video_info['reason'][0])
- self._downloader.trouble(u'ERROR: YouTube said: %s' % reason.decode('utf-8'))
- return
- token = urllib.unquote_plus(video_info['token'][0])
- video_real_url = 'http://www.youtube.com/get_video?video_id=%s&t=%s&eurl=&el=detailpage&ps=default&gl=US&hl=en' % (video_id, token)
- if format_param is not None:
- video_real_url = '%s&fmt=%s' % (video_real_url, format_param)
-
- # Check possible RTMP download
- if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
- self.report_rtmp_download()
- video_real_url = video_info['conn'][0]
-
- # uploader
- if 'author' not in video_info:
- self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
+ format_list = self._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')
return
- video_uploader = urllib.unquote_plus(video_info['author'][0])
+ requested_format = self._downloader.params.get('format', None)
+ if requested_format is None:
+ video_url_list = [(existing_formats[0], url_map[existing_formats[0]])] # Best quality
+ elif requested_format == '-1':
+ video_url_list = url_map.items() # All formats
+ else:
+ if requested_format not in existing_formats:
+ self._downloader.trouble(u'ERROR: format not available for video')
+ return
+ video_url_list = [(requested_format, url_map[requested_format])] # Specific format
+ elif 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
+ self.report_rtmp_download()
+ video_url_list = [(None, video_info['conn'][0])]
+ else:
+ self._downloader.trouble(u'ERROR: no fmt_url_map or conn information found in video info')
+ return
- # title
- if 'title' not in video_info:
- self._downloader.trouble(u'ERROR: unable to extract video title')
- return
- video_title = urllib.unquote_plus(video_info['title'][0])
- 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'_')
-
- # thumbnail image
- if 'thumbnail_url' not in video_info:
- self._downloader.trouble(u'WARNING: unable to extract video thumbnail')
- video_thumbnail = ''
- else: # don't panic if we can't find it
- video_thumbnail = urllib.unquote_plus(video_info['thumbnail_url'][0])
-
- # description
- video_description = 'No description available.'
- if self._downloader.params.get('forcedescription', False):
- mobj = re.search(r'<meta name="description" content="(.*)"(?:\s*/)?>', video_webpage)
- if mobj is not None:
- video_description = mobj.group(1)
+ for format_param, video_real_url in video_url_list:
+ # At this point we have a new video
+ self._downloader.increment_downloads()
+
+ # Extension
+ video_extension = self._video_extensions.get(format_param, 'flv')
+ # Find the video URL in fmt_url_map or conn paramters
try:
# Process video information
self._downloader.process_info({
'description': video_description.decode('utf-8'),
'player_url': player_url,
})
-
- if all_formats:
- quality_index += 1
- if quality_index == len(self._available_formats):
- # None left to get
- return
- else:
- format_param = self._available_formats[quality_index]
- continue
- return
-
- except UnavailableFormatError, err:
- if best_quality or all_formats:
- quality_index += 1
- if quality_index == len(self._available_formats):
- # I don't ever expect this to happen
- if not all_formats:
- self._downloader.trouble(u'ERROR: no known formats available for video')
- return
- else:
- self.report_unavailable_format(video_id, format_param)
- format_param = self._available_formats[quality_index]
- continue
- else:
- self._downloader.trouble('ERROR: format not available for video')
- return
+ except UnavailableVideoError, err:
+ self._downloader.trouble(u'ERROR: unable to download video')
class MetacafeIE(InfoExtractor):
self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % mobj2.group(1))
return
+ # At this point we have a new video
+ self._downloader.increment_downloads()
+
simple_title = mobj.group(2).decode('utf-8')
video_extension = 'flv'
'format': u'NA',
'player_url': None,
})
- except UnavailableFormatError:
- self._downloader.trouble(u'ERROR: format not available for video')
+ except UnavailableVideoError:
+ self._downloader.trouble(u'ERROR: unable to download 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
+ 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 UnavailableVideoError:
+ self._downloader.trouble(u'ERROR: unable to download 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
+ self._downloader.increment_downloads()
video_id = mobj.group(1)
video_extension = 'mp4'
'format': u'NA',
'player_url': None,
})
- except UnavailableFormatError:
- self._downloader.trouble(u'ERROR: format not available for video')
+ except UnavailableVideoError:
+ self._downloader.trouble(u'ERROR: unable to download video')
class PhotobucketIE(InfoExtractor):
self._downloader.trouble(u'ERROR: Invalid URL: %s' % url)
return
+ # At this point we have a new video
+ self._downloader.increment_downloads()
video_id = mobj.group(1)
video_extension = 'flv'
'format': u'NA',
'player_url': None,
})
- except UnavailableFormatError:
- self._downloader.trouble(u'ERROR: format not available for video')
+ except UnavailableVideoError:
+ self._downloader.trouble(u'ERROR: unable to download video')
class YahooIE(InfoExtractor):
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
+ 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)
'description': video_description,
'player_url': None,
})
- except UnavailableFormatError:
- self._downloader.trouble(u'ERROR: format not available for video')
+ except UnavailableVideoError:
+ self._downloader.trouble(u'ERROR: unable to download video')
class GenericIE(InfoExtractor):
return
def _real_extract(self, url):
+ # At this point we have a new video
+ self._downloader.increment_downloads()
+
video_id = url.split('/')[-1]
request = urllib2.Request(url)
try:
'format': u'NA',
'player_url': None,
})
- except UnavailableFormatError:
- self._downloader.trouble(u'ERROR: format not available for video')
+ except UnavailableVideoError, err:
+ self._downloader.trouble(u'ERROR: unable to download video')
class YoutubeSearchIE(InfoExtractor):
# Parse command line
parser = optparse.OptionParser(
usage='Usage: %prog [options] url...',
- version='2010.06.06',
+ version='2010.07.22',
conflict_handler='resolve',
)
parser.add_option('-i', '--ignore-errors',
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)')
+ dest='ratelimit', metavar='LIMIT', help='download rate limit (e.g. 50k or 44.6m)')
parser.add_option('-R', '--retries',
- dest='retries', metavar='T', help='number of retries (default is 10)', default=10)
+ dest='retries', metavar='RETRIES', help='number of retries (default is 10)', default=10)
authentication = optparse.OptionGroup(parser, 'Authentication Options')
authentication.add_option('-u', '--username',
- dest='username', metavar='UN', help='account username')
+ dest='username', metavar='USERNAME', help='account username')
authentication.add_option('-p', '--password',
- dest='password', metavar='PW', help='account password')
+ dest='password', metavar='PASSWORD', help='account password')
authentication.add_option('-n', '--netrc',
action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False)
parser.add_option_group(authentication)
video_format = optparse.OptionGroup(parser, 'Video Format Options')
video_format.add_option('-f', '--format',
- action='store', dest='format', metavar='FMT', help='video format code')
- video_format.add_option('-b', '--best-quality',
- action='store_const', dest='format', help='download the best quality video possible', const='0')
+ action='store', dest='format', metavar='FORMAT', help='video format code')
video_format.add_option('-m', '--mobile-version',
action='store_const', dest='format', help='alias for -f 17', const='17')
- video_format.add_option('-d', '--high-def',
- 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 to download')
parser.add_option_group(video_format)
verbosity = optparse.OptionGroup(parser, 'Verbosity / Simulation Options')
filesystem.add_option('-l', '--literal',
action='store_true', dest='useliteral', help='use literal title in file name', default=False)
filesystem.add_option('-o', '--output',
- dest='outtmpl', metavar='TPL', help='output filename template')
+ dest='outtmpl', metavar='TEMPLATE', help='output filename template')
filesystem.add_option('-a', '--batch-file',
- dest='batchfile', metavar='F', help='file containing URLs to download (\'-\' for stdin)')
+ dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)')
filesystem.add_option('-w', '--no-overwrites',
action='store_true', dest='nooverwrites', help='do not overwrite files', default=False)
filesystem.add_option('-c', '--continue',
# 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)