import urllib2
std_headers = {
- 'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US; rv:1.9.0.8) Gecko/2009032609 Firefox/3.0.8',
+ 'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US; rv:1.9.1.2) Gecko/20090729 Firefox/3.5.2',
'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-Language': 'en-us,en;q=0.5',
simple_title_chars = string.ascii_letters.decode('ascii') + string.digits.decode('ascii')
+def preferredencoding():
+ """Get preferred encoding.
+
+ Returns the best encoding scheme for the system, based on
+ locale.getpreferredencoding() and some further tweaks.
+ """
+ def yield_preferredencoding():
+ try:
+ pref = locale.getpreferredencoding()
+ u'TEST'.encode(pref)
+ except:
+ pref = 'UTF-8'
+ while True:
+ yield pref
+ return yield_preferredencoding().next()
+
class DownloadError(Exception):
"""Download Error exception.
This exception will be thrown when a video is requested
in a format that is not available for that video.
"""
+ pass
+
+class ContentTooShortError(Exception):
+ """Content Too Short exception.
+
+ This exception may be raised by FileDownloader objects when a file they
+ download is too small for what the server announced first, indicating
+ the connection was probably interrupted.
+ """
+ # Both in bytes
+ downloaded = None
+ expected = None
+
+ def __init__(self, downloaded, expected):
+ self.downloaded = downloaded
+ self.expected = expected
class FileDownloader(object):
"""File Downloader class.
ignoreerrors: Do not stop on download errors.
ratelimit: Download speed limit, in bytes/sec.
nooverwrites: Prevent overwriting files.
+ continuedl: Try to continue downloads if possible.
"""
params = None
def format_bytes(bytes):
if bytes is None:
return 'N/A'
- if bytes == 0:
+ if type(bytes) is str:
+ bytes = float(bytes)
+ if bytes == 0.0:
exponent = 0
else:
- exponent = long(math.log(float(bytes), 1024.0))
+ exponent = long(math.log(bytes, 1024.0))
suffix = 'bkMGTPEZY'[exponent]
converted = float(bytes) / float(1024**exponent)
return '%.2f%s' % (converted, suffix)
new_min = max(bytes / 2.0, 1.0)
new_max = min(max(bytes * 2.0, 1.0), 4194304) # Do not surpass 4 MB
if elapsed_time < 0.001:
- return int(new_max)
+ return long(new_max)
rate = bytes / elapsed_time
if rate > new_max:
- return int(new_max)
+ return long(new_max)
if rate < new_min:
- return int(new_min)
- return int(rate)
+ return long(new_min)
+ return long(rate)
@staticmethod
def parse_bytes(bytestr):
multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower())
return long(round(number * multiplier))
+ @staticmethod
+ def verify_url(url):
+ """Verify a URL is valid and data could be downloaded. Return real data URL."""
+ request = urllib2.Request(url, None, std_headers)
+ data = urllib2.urlopen(request)
+ data.read(1)
+ url = data.geturl()
+ data.close()
+ return url
+
def add_info_extractor(self, ie):
"""Add an InfoExtractor object to the end of the list."""
self._ies.append(ie)
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])).encode(locale.getpreferredencoding()),
+ print (u'%s%s' % (message, [u'\n', u''][skip_eol])).encode(preferredencoding()),
sys.stdout.flush()
def to_stderr(self, message):
"""Print message to stderr."""
- print >>sys.stderr, message
+ print >>sys.stderr, message.encode(preferredencoding())
def fixed_template(self):
"""Checks if the output template is fixed."""
"""Report download progress."""
self.to_stdout(u'\r[download] %s of %s at %s ETA %s' %
(percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
+
+ def report_resuming_byte(self, resume_len):
+ """Report attemtp to resume at given byte."""
+ self.to_stdout(u'[download] Resuming download at byte %s' % resume_len)
+
+ def report_file_already_downloaded(self, file_name):
+ """Report file has already been fully downloaded."""
+ self.to_stdout(u'[download] %s has already been downloaded' % file_name)
+
+ def report_unable_to_resume(self):
+ """Report it was impossible to resume download."""
+ self.to_stdout(u'[download] Unable to resume')
def report_finish(self):
"""Report download finished."""
def process_info(self, info_dict):
"""Process a single dictionary returned by an InfoExtractor."""
- # Forced printings
- if self.params.get('forcetitle', False):
- print info_dict['title'].encode(locale.getpreferredencoding())
- if self.params.get('forceurl', False):
- print info_dict['url'].encode(locale.getpreferredencoding())
-
# Do nothing else if in simulate mode
if self.params.get('simulate', False):
- return
+ try:
+ info_dict['url'] = self.verify_url(info_dict['url'].encode('utf-8')).decode('utf-8')
+ except (OSError, IOError, urllib2.URLError, httplib.HTTPException, socket.error), err:
+ raise UnavailableFormatError
+
+ # Forced printings
+ if self.params.get('forcetitle', False):
+ print info_dict['title'].encode(preferredencoding())
+ if self.params.get('forceurl', False):
+ print info_dict['url'].encode(preferredencoding())
+ return
+
try:
template_dict = dict(info_dict)
template_dict['epoch'] = unicode(long(time.time()))
filename = self.params['outtmpl'] % template_dict
- self.report_destination(filename)
except (ValueError, KeyError), err:
self.trouble('ERROR: invalid output template or system charset: %s' % str(err))
- if self.params['nooverwrites'] and os.path.exists(filename):
- self.to_stderr('WARNING: file exists: %s; skipping' % filename)
+ if self.params.get('nooverwrites', False) and os.path.exists(filename):
+ self.to_stderr(u'WARNING: file exists: %s; skipping' % filename)
return
try:
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()
+ success = self._do_download(filename, info_dict['url'].encode('utf-8'))
except (OSError, IOError), err:
- outstream.close()
- 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))
+ except (ContentTooShortError, ), err:
+ self.trouble('ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
return
+ if success:
+ try:
+ self.post_process(filename, info_dict)
+ except (PostProcessingError), err:
+ self.trouble('ERROR: postprocessing: %s' % str(err))
+ return
+
def download(self, url_list):
"""Download a given list of URLs."""
if len(url_list) > 1 and self.fixed_template():
if info is None:
break
- def _do_download(self, stream, url):
+ def _do_download(self, filename, url):
+ stream = None
+ open_mode = 'ab'
+
+ basic_request = urllib2.Request(url, None, std_headers)
request = urllib2.Request(url, None, std_headers)
- data = urllib2.urlopen(request)
+
+ # Attempt to resume download with "continuedl" option
+ if os.path.isfile(filename):
+ resume_len = os.path.getsize(filename)
+ else:
+ resume_len = 0
+ if self.params.get('continuedl', False) and resume_len != 0:
+ self.report_resuming_byte(resume_len)
+ request.add_header('Range','bytes=%d-' % resume_len)
+
+ # Establish connection
+ try:
+ data = urllib2.urlopen(request)
+ except (urllib2.HTTPError, ), err:
+ if err.code != 416: # 416 is 'Requested range not satisfiable'
+ raise
+ data = urllib2.urlopen(basic_request)
+ content_length = data.info()['Content-Length']
+ if content_length is not None and long(content_length) == resume_len:
+ self.report_file_already_downloaded(filename)
+ return True
+ else:
+ self.report_unable_to_resume()
+ open_mode = 'wb'
+
data_len = data.info().get('Content-length', None)
data_len_str = self.format_bytes(data_len)
byte_counter = 0
block_size = 1024
start = time.time()
while True:
- # Progress message
- percent_str = self.calc_percent(byte_counter, data_len)
- eta_str = self.calc_eta(start, time.time(), data_len, byte_counter)
- speed_str = self.calc_speed(start, time.time(), byte_counter)
- self.report_progress(percent_str, data_len_str, speed_str, eta_str)
-
# Download and write
before = time.time()
data_block = data.read(block_size)
if data_block_len == 0:
break
byte_counter += data_block_len
+
+ # Open file just in time
+ if stream is None:
+ try:
+ stream = open(filename, open_mode)
+ self.report_destination(filename)
+ except (OSError, IOError), err:
+ self.trouble('ERROR: unable to open for writing: %s' % str(err))
+ return False
stream.write(data_block)
block_size = self.best_block_size(after - before, data_block_len)
+ # Progress message
+ percent_str = self.calc_percent(byte_counter, data_len)
+ eta_str = self.calc_eta(start, time.time(), data_len, byte_counter)
+ speed_str = self.calc_speed(start, time.time(), byte_counter)
+ self.report_progress(percent_str, data_len_str, speed_str, eta_str)
+
# Apply rate limit
self.slow_down(start, byte_counter)
self.report_finish()
if data_len is not None and str(byte_counter) != data_len:
- raise ValueError('Content too short: %s/%s bytes' % (byte_counter, data_len))
+ raise ContentTooShortError(byte_counter, long(data_len))
+ return True
class InfoExtractor(object):
"""Information Extractor class.
_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', '35', '18', '17', '13'] # listed in order of priority for -b flag
+ _available_formats = ['22', '35', '18', '5', '17', '13', None] # listed in order of priority for -b flag
_video_extensions = {
'13': '3gp',
'17': 'mp4',
"""Report attempt to confirm age."""
self._downloader.to_stdout(u'[youtube] Confirming age')
- def report_webpage_download(self, video_id):
- """Report attempt to download webpage."""
- self._downloader.to_stdout(u'[youtube] %s: Downloading video webpage' % video_id)
+ def report_video_info_webpage_download(self, video_id):
+ """Report attempt to download video info webpage."""
+ self._downloader.to_stdout(u'[youtube] %s: Downloading video info webpage' % video_id)
def report_information_extraction(self, video_id):
"""Report attempt to extract video information."""
self._downloader.to_stdout(u'[youtube] %s: Extracting video information' % video_id)
- def report_video_url(self, video_id, video_real_url):
- """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))
best_quality = True
while True:
+ # Extension
+ video_extension = self._video_extensions.get(format_param, 'flv')
+
+ # Get video info
+ video_info_url = 'http://www.youtube.com/get_video_info?&video_id=%s&el=detailpage&ps=default&eurl=&gl=US&hl=en' % video_id
+ request = urllib2.Request(video_info_url, None, std_headers)
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)
+ self.report_video_info_webpage_download(video_id)
+ video_info_webpage = urllib2.urlopen(request).read()
+ 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)
- # uploader
- mobj = re.search(r"var watchUsername = '([^']+)';", video_webpage)
+ # "t" param
+ mobj = re.search(r'(?m)&token=([^&]+)(?:&|$)', video_info_webpage)
+ if mobj is None:
+ # Attempt to see if YouTube has issued an error message
+ mobj = re.search(r'(?m)&reason=([^&]+)(?:&|$)', video_info_webpage)
if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
- return
- video_uploader = mobj.group(1)
+ 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(mobj.group(1))
+ self._downloader.trouble(u'ERROR: YouTube said: %s' % reason.decode('utf-8'))
+ return
+ token = urllib.unquote(mobj.group(1))
+ 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)
+
+ # uploader
+ mobj = re.search(r'(?m)&author=([^&]+)(?:&|$)', video_info_webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
+ return
+ video_uploader = urllib.unquote(mobj.group(1))
- # title
- mobj = re.search(r'(?im)<title>YouTube - ([^<]*)</title>', video_webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract video title')
- return
- video_title = mobj.group(1).decode('utf-8')
- video_title = re.sub(ur'(?u)&(.+?);', self.htmlentity_transform, video_title)
- video_title = video_title.replace(os.sep, u'%')
+ # title
+ mobj = re.search(r'(?m)&title=([^&]*)(?:&|$)', video_info_webpage)
+ if mobj is None:
+ self._downloader.trouble(u'ERROR: unable to extract video title')
+ return
+ video_title = urllib.unquote_plus(mobj.group(1))
+ video_title = video_title.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'_')
+ # simplified title
+ simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+ simple_title = simple_title.strip(ur'_')
+ try:
# Process video information
self._downloader.process_info({
'id': video_id.decode('utf-8'),
# 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=([^&]+)', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract media URL')
return
mediaURL = urllib.unquote(mobj.group(1))
- mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
- if mobj is None:
- self._downloader.trouble(u'ERROR: unable to extract gdaKey')
- return
- gdaKey = mobj.group(1)
+ #mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
+ #if mobj is None:
+ # self._downloader.trouble(u'ERROR: unable to extract gdaKey')
+ # return
+ #gdaKey = mobj.group(1)
+ #
+ #video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
- video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
+ video_url = mediaURL
mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage)
if mobj is None:
_VALID_QUERY = r'ytsearch(\d+|all)?:[\s\S]+'
_TEMPLATE_URL = 'http://www.youtube.com/results?search_query=%s&page=%s&gl=US&hl=en'
_VIDEO_INDICATOR = r'href="/watch\?v=.+?"'
- _MORE_PAGES_INDICATOR = r'>Next</a>'
+ _MORE_PAGES_INDICATOR = r'(?m)>\s*Next\s*</a>'
_youtube_ie = None
_max_youtube_results = 1000
return
else:
try:
- n = int(prefix)
+ n = long(prefix)
if n <= 0:
self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
return
n = self._max_youtube_results
self._download_n_results(query, n)
return
- except ValueError: # parsing prefix as int fails
+ except ValueError: # parsing prefix as integer fails
self._download_n_results(query, 1)
return
self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
return
- if self._MORE_PAGES_INDICATOR not in page:
+ if re.search(self._MORE_PAGES_INDICATOR, page) is None:
for id in video_ids:
self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
return
class YoutubePlaylistIE(InfoExtractor):
"""Information Extractor for YouTube playlists."""
- _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/view_play_list\?p=(.+)'
+ _VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/(?:view_play_list|my_playlists)\?.*?p=([^&]+).*'
_TEMPLATE_URL = 'http://www.youtube.com/view_play_list?p=%s&page=%s&gl=US&hl=en'
_VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
- _MORE_PAGES_INDICATOR = r'/view_play_list?p=%s&page=%s'
+ _MORE_PAGES_INDICATOR = r'/view_play_list?p=%s&page=%s'
_youtube_ie = None
def __init__(self, youtube_ie, downloader=None):
ids_in_page.append(mobj.group(1))
video_ids.extend(ids_in_page)
- if (self._MORE_PAGES_INDICATOR % (playlist_id, pagenum + 1)) not in page:
+ if (self._MORE_PAGES_INDICATOR % (playlist_id.upper(), pagenum + 1)) not in page:
break
pagenum = pagenum + 1
import getpass
import optparse
+ # Function to update the program file with the latest version from bitbucket.org
+ def update_self(downloader, filename):
+ # Note: downloader only used for options
+ if not os.access (filename, os.W_OK):
+ sys.exit('ERROR: no write permissions on %s' % filename)
+
+ downloader.to_stdout('Updating to latest stable version...')
+ latest_url = 'http://bitbucket.org/rg3/youtube-dl/raw/tip/LATEST_VERSION'
+ latest_version = urllib.urlopen(latest_url).read().strip()
+ prog_url = 'http://bitbucket.org/rg3/youtube-dl/raw/%s/youtube-dl' % latest_version
+ newcontent = urllib.urlopen(prog_url).read()
+ stream = open(filename, 'w')
+ stream.write(newcontent)
+ stream.close()
+ downloader.to_stdout('Updated to version %s' % latest_version)
+
# General configuration
urllib2.install_opener(urllib2.build_opener(urllib2.ProxyHandler()))
urllib2.install_opener(urllib2.build_opener(urllib2.HTTPCookieProcessor()))
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', '--update',
+ action='store_true', dest='update_self', help='update this program to latest stable version')
parser.add_option('-i', '--ignore-errors',
action='store_true', dest='ignoreerrors', help='continue on download errors', default=False)
parser.add_option('-r', '--rate-limit',
video_format = optparse.OptionGroup(parser, 'Video Format Options')
video_format.add_option('-f', '--format',
- action='append', dest='format', metavar='FMT', help='video format code')
+ 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')
video_format.add_option('-m', '--mobile-version',
dest='batchfile', metavar='F', help='file containing URLs to download')
filesystem.add_option('-w', '--no-overwrites',
action='store_true', dest='nooverwrites', help='do not overwrite files', default=False)
+ filesystem.add_option('-c', '--continue',
+ action='store_true', dest='continue_dl', help='resume partially downloaded files', default=False)
parser.add_option_group(filesystem)
(opts, args) = parser.parse_args()
-
+
# Batch file verification
batchurls = []
if opts.batchfile is not None:
all_urls = batchurls + args
# Conflicting, missing and erroneous options
- if len(all_urls) < 1:
- 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):
parser.error(u'using .netrc conflicts with giving username/password')
if opts.password is not None and opts.username is None:
if numeric_limit is None:
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()
'forceurl': opts.geturl,
'forcetitle': opts.gettitle,
'simulate': (opts.simulate or opts.geturl or opts.gettitle),
- 'format': real_format,
- 'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(locale.getpreferredencoding()))
+ 'format': opts.format,
+ 'outtmpl': ((opts.outtmpl is not None and opts.outtmpl.decode(preferredencoding()))
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'),
'ignoreerrors': opts.ignoreerrors,
'ratelimit': opts.ratelimit,
'nooverwrites': opts.nooverwrites,
+ 'continuedl': opts.continue_dl,
})
fd.add_info_extractor(youtube_search_ie)
fd.add_info_extractor(youtube_pl_ie)
fd.add_info_extractor(metacafe_ie)
fd.add_info_extractor(youtube_ie)
+
+ # Update version
+ if opts.update_self:
+ update_self(fd, sys.argv[0])
+
+ # Maybe do nothing
+ if len(all_urls) < 1:
+ if not opts.update_self:
+ parser.error(u'you must provide at least one URL')
+ else:
+ sys.exit()
retcode = fd.download(all_urls)
sys.exit(retcode)