Added -c option (--continue)

interrupted downloads will properly resume and append to the previously downloaded data, instead of overwriting the file.

There's some error checking - if the length of the file to be download matches the length of the previously downloaded data, we report that this file has already been downloaded and do nothing.

If there is some other HTTP 416 'Requested range not satisfiable' error, we simply re-download the whole file (reverting to the original functionality)

All other HTTP errors are simply raised.

Resuming does not override -w (--nooverwrite), since it is not clear what should happen if file on disk is larger than file to be downloaded.

Thus, -c does nothing if -w is present.

diff --git a/youtube-dl b/youtube-dl
index 9d84c3560b5131d5aca4800f59a38c5714b40732..026073e4872e87ff7a3659b13ad362ab868a09d5 100755 (executable)
--- a/youtube-dl
+++ b/youtube-dl
@@ -306,7 +306,7 @@ class FileDownloader(object):
                        return
 
                try:
-                       outstream = open(filename, 'wb')
+                       outstream = open(filename, 'ab')
                except (OSError, IOError), err:
                        self.trouble('ERROR: unable to open for writing: %s' % str(err))
                        return
@@ -368,7 +368,27 @@ class FileDownloader(object):
        
        def _do_download(self, stream, url):
                request = urllib2.Request(url, None, std_headers)
-               data = urllib2.urlopen(request)
+               # Resume transfer if filesize is non-zero
+               resume_len = stream.tell()
+               if self.params["continue"] and resume_len != 0:
+                       print "[download] Resuming download at byte %d" % resume_len
+                       request.add_header("Range","bytes=%d-" % resume_len)
+               else:
+                       stream.close()
+                       stream = open(stream.name,'wb')
+               try:
+                       data = urllib2.urlopen(request)
+               except urllib2.HTTPError, e:
+                       if not e.code == 416: #  416 is 'Requested range not satisfiable'
+                               raise
+                       data = urllib2.urlopen(url)
+                       if int(data.info()['Content-Length']) == resume_len:
+                               print '[download] %s has already been downloaded' % stream.name
+                               return
+                       else:
+                               print "[download] Unable to resume, restarting download from the beginning"
+                               stream.close()
+                               stream = open(stream.name,'wb')
                data_len = data.info().get('Content-length', None)
                data_len_str = self.format_bytes(data_len)
                byte_counter = 0
@@ -1084,6 +1104,8 @@ if __name__ == '__main__':
                                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()
@@ -1141,6 +1163,7 @@ if __name__ == '__main__':
                        'ignoreerrors': opts.ignoreerrors,
                        'ratelimit': opts.ratelimit,
                        'nooverwrites': opts.nooverwrites,
+                       'continue': opts.continue_dl,
                        })
                fd.add_info_extractor(youtube_search_ie)
                fd.add_info_extractor(youtube_pl_ie)