X-Git-Url: http://git.cielonegro.org/gitweb.cgi?a=blobdiff_plain;f=youtube-dl;h=91ee099ceab577fb1514eaa52e633fbca9fa2306;hb=1c76e23e0fca5e16a1fc4f0baca58503ba7ec639;hp=545bcb6538643edb87e9e9bd731e5717114a0b7c;hpb=6f21f686293ff94889978c1f39256029d2409d1b;p=youtube-dl.git
diff --git a/youtube-dl b/youtube-dl
index 545bcb653..91ee099ce 100755
--- a/youtube-dl
+++ b/youtube-dl
@@ -52,6 +52,13 @@ class PostProcessingError(Exception):
"""
pass
+class UnavailableFormatError(Exception):
+ """Unavailable Format exception.
+
+ This exception will be thrown when a video is requested
+ in a format that is not available for that video.
+ """
+
class FileDownloader(object):
"""File Downloader class.
@@ -65,9 +72,10 @@ class FileDownloader(object):
For this, file downloader objects have a method that allows
InfoExtractors to be registered in a given order. When it is passed
a URL, the file downloader handles it to the first InfoExtractor it
- finds that reports being able to handle it. The InfoExtractor returns
- all the information to the FileDownloader and the latter downloads the
- file or does whatever it's instructed to do.
+ finds that reports being able to handle it. The InfoExtractor extracts
+ all the information about the video or videos the URL refers to, and
+ asks the FileDownloader to process the video information, possibly
+ downloading the video.
File downloaders accept a lot of parameters. In order not to saturate
the object constructor with arguments, it receives a dictionary of
@@ -189,7 +197,7 @@ class FileDownloader(object):
def to_stdout(self, message, skip_eol=False):
"""Print message to stdout if not in quiet mode."""
if not self.params.get('quiet', False):
- print u'%s%s' % (message, [u'\n', u''][skip_eol]),
+ print (u'%s%s' % (message, [u'\n', u''][skip_eol])).encode(locale.getpreferredencoding()),
sys.stdout.flush()
def to_stderr(self, message):
@@ -243,9 +251,9 @@ class FileDownloader(object):
"""Process a single dictionary returned by an InfoExtractor."""
# Forced printings
if self.params.get('forcetitle', False):
- print info_dict['title']
+ print info_dict['title'].encode(locale.getpreferredencoding())
if self.params.get('forceurl', False):
- print info_dict['url']
+ print info_dict['url'].encode(locale.getpreferredencoding())
# Do nothing else if in simulate mode
if self.params.get('simulate', False):
@@ -259,33 +267,35 @@ class FileDownloader(object):
if self.params['nooverwrites'] and os.path.exists(filename):
self.to_stderr('WARNING: file exists: %s; skipping' % filename)
return
+
try:
self.pmkdir(filename)
except (OSError, IOError), err:
self.trouble('ERROR: unable to create directories: %s' % str(err))
return
+
try:
outstream = open(filename, 'wb')
except (OSError, IOError), err:
self.trouble('ERROR: unable to open for writing: %s' % str(err))
return
+
try:
self._do_download(outstream, info_dict['url'])
outstream.close()
except (OSError, IOError), err:
- self.trouble('ERROR: unable to write video data: %s' % str(err))
- return
+ os.remove(filename)
+ raise UnavailableFormatError
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self.trouble('ERROR: unable to download video data: %s' % str(err))
return
+
try:
self.post_process(filename, info_dict)
except (PostProcessingError), err:
self.trouble('ERROR: postprocessing: %s' % str(err))
return
- return
-
def download(self, url_list):
"""Download a given list of URLs."""
if len(url_list) > 1 and self.fixed_template():
@@ -360,9 +370,10 @@ class InfoExtractor(object):
Information extractors are the classes that, given a URL, extract
information from the video (or videos) the URL refers to. This
information includes the real video URL, the video title and simplified
- title, author and others. It is returned in a list of dictionaries when
- calling its extract() method. It is a list because a URL can refer to
- more than one video (think of playlists). The dictionaries must include
+ title, author and others. The information is stored in a dictionary
+ which is then passed to the FileDownloader. The FileDownloader
+ processes this information possibly downloading the video to the file
+ system, among other possible outcomes. The dictionaries must include
the following fields:
id: Video identifier.
@@ -422,6 +433,13 @@ class YoutubeIE(InfoExtractor):
_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 = ['22', '18', '17', '13'] # listed in order of priority for -b flag
+ _video_extensions = {
+ '13': '3gp',
+ '17': 'mp4',
+ '18': 'mp4',
+ '22': 'mp4',
+ }
@staticmethod
def suitable(url):
@@ -474,6 +492,10 @@ class YoutubeIE(InfoExtractor):
"""Report extracted video URL."""
self._downloader.to_stdout(u'[youtube] %s: URL: %s' % (video_id, video_real_url))
+ def report_unavailable_format(self, video_id, format):
+ """Report extracted video URL."""
+ self._downloader.to_stdout(u'[youtube] %s: Format %s not available' % (video_id, format))
+
def _real_initialize(self):
if self._downloader is None:
return
@@ -552,76 +574,98 @@ class YoutubeIE(InfoExtractor):
video_id = mobj.group(2)
# Downloader parameters
+ best_quality = 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
- # Extension
- video_extension = {
- '17': '3gp',
- '18': 'mp4',
- '22': 'mp4',
- }.get(format_param, 'flv')
-
- # Normalize URL, including format
- normalized_url = 'http://www.youtube.com/watch?v=%s&gl=US&hl=en' % video_id
- if format_param is not None:
- normalized_url = '%s&fmt=%s' % (normalized_url, format_param)
- request = urllib2.Request(normalized_url, None, std_headers)
- try:
- self.report_webpage_download(video_id)
- 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
- self.report_information_extraction(video_id)
-
- # "t" param
- mobj = re.search(r', "t": "([^"]+)"', video_webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract "t" parameter')
- return
- video_real_url = 'http://www.youtube.com/get_video?video_id=%s&t=%s&el=detailpage&ps=' % (video_id, mobj.group(1))
- if format_param is not None:
- video_real_url = '%s&fmt=%s' % (video_real_url, format_param)
- self.report_video_url(video_id, video_real_url)
+ while True:
+ try:
+ # Extension
+ video_extension = self._video_extensions.get(format_param, 'flv')
+
+ # Normalize URL, including format
+ normalized_url = 'http://www.youtube.com/watch?v=%s&gl=US&hl=en' % video_id
+ if format_param is not None:
+ normalized_url = '%s&fmt=%s' % (normalized_url, format_param)
+ request = urllib2.Request(normalized_url, None, std_headers)
+ try:
+ self.report_webpage_download(video_id)
+ 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
+ self.report_information_extraction(video_id)
+
+ # "t" param
+ mobj = re.search(r', "t": "([^"]+)"', video_webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract "t" parameter')
+ return
+ video_real_url = 'http://www.youtube.com/get_video?video_id=%s&t=%s&el=detailpage&ps=' % (video_id, mobj.group(1))
+ if format_param is not None:
+ video_real_url = '%s&fmt=%s' % (video_real_url, format_param)
+ self.report_video_url(video_id, video_real_url)
+
+ # uploader
+ mobj = re.search(r"var watchUsername = '([^']+)';", video_webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
+ return
+ video_uploader = mobj.group(1)
- # uploader
- mobj = re.search(r"var watchUsername = '([^']+)';", video_webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
- return
- video_uploader = mobj.group(1)
+ # title
+ mobj = re.search(r'(?im)
YouTube - ([^<]*)', video_webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video title')
+ return
+ video_title = mobj.group(1).decode('utf-8')
+ video_title = re.sub(ur'(?u)&(.+?);', self.htmlentity_transform, video_title)
+ video_title = video_title.replace(os.sep, u'%')
+
+ # simplified title
+ simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+ simple_title = simple_title.strip(ur'_')
+
+ # Process video information
+ self._downloader.process_info({
+ 'id': video_id.decode('utf-8'),
+ 'url': video_real_url.decode('utf-8'),
+ 'uploader': video_uploader.decode('utf-8'),
+ 'title': video_title,
+ 'stitle': simple_title,
+ 'ext': video_extension.decode('utf-8'),
+ })
+
+ return
+
+ except UnavailableFormatError, err:
+ if best_quality:
+ if quality_index == len(self._available_formats) - 1:
+ # I don't ever expect this to happen
+ self._downloader.trouble(u'ERROR: no known formats available for video')
+ return
+ else:
+ self.report_unavailable_format(video_id, format_param)
+ quality_index += 1
+ format_param = self._available_formats[quality_index]
+ continue
+ else:
+ self._downloader.trouble('ERROR: format not available for video')
+ return
- # title
- mobj = re.search(r'(?im)YouTube - ([^<]*)', video_webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video title')
- return
- video_title = mobj.group(1).decode('utf-8')
- video_title = re.sub(ur'(?u)&(.+?);', self.htmlentity_transform, video_title)
- video_title = video_title.replace(os.sep, u'%')
-
- # simplified title
- simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
- simple_title = simple_title.strip(ur'_')
-
- # Process video information
- self._downloader.process_info({
- 'id': video_id.decode('utf-8'),
- 'url': video_real_url.decode('utf-8'),
- 'uploader': video_uploader.decode('utf-8'),
- 'title': video_title,
- 'stitle': simple_title,
- 'ext': video_extension.decode('utf-8'),
- })
class MetacafeIE(InfoExtractor):
"""Information Extractor for metacafe.com."""
_VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*'
_DISCLAIMER = 'http://www.metacafe.com/family_filter/'
+ _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
_youtube_ie = None
def __init__(self, youtube_ie, downloader=None):
@@ -663,7 +707,7 @@ class MetacafeIE(InfoExtractor):
'filters': '0',
'submit': "Continue - I'm over 18",
}
- request = urllib2.Request('http://www.metacafe.com/', urllib.urlencode(disclaimer_form), std_headers)
+ request = urllib2.Request(self._FILTER_POST, urllib.urlencode(disclaimer_form), std_headers)
try:
self.report_age_confirmation()
disclaimer = urllib2.urlopen(request).read()
@@ -700,13 +744,13 @@ class MetacafeIE(InfoExtractor):
# Extract URL, uploader and title from webpage
self.report_extraction(video_id)
- mobj = re.search(r'(?m)"mediaURL":"(http.*?\.flv)"', webpage)
+ mobj = re.search(r'(?m)&mediaURL=(http.*?\.flv)', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract media URL')
return
- mediaURL = mobj.group(1).replace('\\', '')
+ mediaURL = urllib.unquote(mobj.group(1))
- mobj = re.search(r'(?m)"gdaKey":"(.*?)"', webpage)
+ mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract gdaKey')
return
@@ -720,21 +764,24 @@ class MetacafeIE(InfoExtractor):
return
video_title = mobj.group(1).decode('utf-8')
- mobj = re.search(r'(?m).*?Submitter:
(.*?)', webpage)
+ mobj = re.search(r'(?ms).*?Submitter:.*?(.*?)<', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
return
- video_uploader = re.sub(r'<.*?>', '', mobj.group(1))
-
- # 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'),
+ 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'),
})
+ except UnavailableFormatError:
+ self._downloader.trouble(u'ERROR: format not available for video')
class YoutubeSearchIE(InfoExtractor):
@@ -916,7 +963,7 @@ class PostProcessor(object):
"""Run the PostProcessor.
The "information" argument is a dictionary like the ones
- returned by InfoExtractors. The only difference is that this
+ composed by InfoExtractors. The only difference is that this
one has an extra field called "filepath" that points to the
downloaded file.
@@ -946,77 +993,102 @@ if __name__ == '__main__':
# Parse command line
parser = optparse.OptionParser(
- usage='Usage: %prog [options] url...',
- version='INTERNAL',
- conflict_handler='resolve',
- )
+ usage='Usage: %prog [options] url...',
+ version='INTERNAL',
+ conflict_handler='resolve',
+ )
+
parser.add_option('-h', '--help',
action='help', help='print this help text and exit')
parser.add_option('-v', '--version',
action='version', help='print program version and exit')
- parser.add_option('-u', '--username',
+ 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)')
+
+ authentication = optparse.OptionGroup(parser, 'Authentication Options')
+ authentication.add_option('-u', '--username',
dest='username', metavar='UN', help='account username')
- parser.add_option('-p', '--password',
+ authentication.add_option('-p', '--password',
dest='password', metavar='PW', help='account password')
- parser.add_option('-o', '--output',
- dest='outtmpl', metavar='TPL', help='output filename template')
- parser.add_option('-q', '--quiet',
+ 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='append', dest='format', metavar='FMT', help='video format code')
+ video_format.add_option('-b', '--best-quality',
+ action='append_const', dest='format', help='download the best quality video possible', const='0')
+ video_format.add_option('-m', '--mobile-version',
+ action='append_const', dest='format', help='alias for -f 17', const='17')
+ video_format.add_option('-d', '--high-def',
+ action='append_const', dest='format', help='alias for -f 22', const='22')
+ parser.add_option_group(video_format)
+
+ verbosity = optparse.OptionGroup(parser, 'Verbosity / Simulation Options')
+ verbosity.add_option('-q', '--quiet',
action='store_true', dest='quiet', help='activates quiet mode', default=False)
- parser.add_option('-s', '--simulate',
+ verbosity.add_option('-s', '--simulate',
action='store_true', dest='simulate', help='do not download video', default=False)
- parser.add_option('-t', '--title',
- action='store_true', dest='usetitle', help='use title in file name', default=False)
- parser.add_option('-l', '--literal',
- action='store_true', dest='useliteral', help='use literal title in file name', default=False)
- parser.add_option('-n', '--netrc',
- action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False)
- parser.add_option('-g', '--get-url',
+ verbosity.add_option('-g', '--get-url',
action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False)
- parser.add_option('-e', '--get-title',
+ verbosity.add_option('-e', '--get-title',
action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False)
- parser.add_option('-f', '--format',
- dest='format', metavar='FMT', help='video format code')
- parser.add_option('-m', '--mobile-version',
- action='store_const', dest='format', help='alias for -f 17', const='17')
- parser.add_option('-d', '--high-def',
- action='store_const', dest='format', help='alias for -f 22', const='22')
- 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)')
- parser.add_option('-a', '--batch-file',
+ parser.add_option_group(verbosity)
+
+ filesystem = optparse.OptionGroup(parser, 'Filesystem Options')
+ filesystem.add_option('-t', '--title',
+ action='store_true', dest='usetitle', help='use title in file name', default=False)
+ 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')
+ filesystem.add_option('-a', '--batch-file',
dest='batchfile', metavar='F', help='file containing URLs to download')
- parser.add_option('-w', '--no-overwrites',
+ filesystem.add_option('-w', '--no-overwrites',
action='store_true', dest='nooverwrites', help='do not overwrite files', default=False)
+ parser.add_option_group(filesystem)
+
(opts, args) = parser.parse_args()
# Batch file verification
batchurls = []
if opts.batchfile is not None:
try:
- batchurls = [line.strip() for line in open(opts.batchfile, 'r')]
+ batchurls = open(opts.batchfile, 'r').readlines()
+ batchurls = [x.strip() for x in batchurls]
+ batchurls = [x for x in batchurls if len(x) > 0]
except IOError:
sys.exit(u'ERROR: batch file could not be read')
all_urls = batchurls + args
# Conflicting, missing and erroneous options
if len(all_urls) < 1:
- sys.exit(u'ERROR: you must provide at least one URL')
+ parser.error(u'you must provide at least one URL')
if opts.usenetrc and (opts.username is not None or opts.password is not None):
- sys.exit(u'ERROR: using .netrc conflicts with giving username/password')
+ parser.error(u'using .netrc conflicts with giving username/password')
if opts.password is not None and opts.username is None:
- sys.exit(u'ERROR: account username missing')
+ parser.error(u'account username missing')
if opts.outtmpl is not None and (opts.useliteral or opts.usetitle):
- sys.exit(u'ERROR: using output template conflicts with using title or literal title')
+ parser.error(u'using output template conflicts with using title or literal title')
if opts.usetitle and opts.useliteral:
- sys.exit(u'ERROR: using title conflicts with using literal title')
+ parser.error(u'using title conflicts with using literal title')
if opts.username is not None and opts.password is None:
opts.password = getpass.getpass(u'Type account password and press return:')
if opts.ratelimit is not None:
numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
if numeric_limit is None:
- sys.exit(u'ERROR: invalid rate limit specified')
+ parser.error(u'invalid rate limit specified')
opts.ratelimit = numeric_limit
+ if opts.format is not None and len(opts.format) > 1:
+ parser.error(u'pass at most one of the video format option flags (-f, -b, -m, -d)')
+ if opts.format is None:
+ real_format = None
+ else:
+ real_format = opts.format[0]
+
# Information extractors
youtube_ie = YoutubeIE()
@@ -1025,9 +1097,6 @@ if __name__ == '__main__':
youtube_search_ie = YoutubeSearchIE(youtube_ie)
# File downloader
- charset = locale.getpreferredencoding()
- if charset is None:
- charset = 'ascii'
fd = FileDownloader({
'usenetrc': opts.usenetrc,
'username': opts.username,
@@ -1036,8 +1105,8 @@ if __name__ == '__main__':
'forceurl': opts.geturl,
'forcetitle': opts.gettitle,
'simulate': (opts.simulate or opts.geturl or opts.gettitle),
- 'format': opts.format,
- 'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(charset))
+ 'format': real_format,
+ 'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(locale.getpreferredencoding()))
or (opts.usetitle and u'%(stitle)s-%(id)s.%(ext)s')
or (opts.useliteral and u'%(title)s-%(id)s.%(ext)s')
or u'%(id)s.%(ext)s'),