#!/usr/bin/env python ## Amazon S3 manager ## Author: Michal Ludvig ## http://www.logix.cz/michal ## License: GPL Version 2 import sys import logging import time import os import re import errno import pwd, grp import glob import traceback from copy import copy from optparse import OptionParser, Option, OptionValueError, IndentedHelpFormatter from logging import debug, info, warning, error from distutils.spawn import find_executable def output(message): print message def check_args_type(args, type, verbose_type): for arg in args: if S3Uri(arg).type != type: raise ParameterError("Expecting %s instead of '%s'" % (verbose_type, arg)) def cmd_du(args): s3 = S3(Config()) if len(args) > 0: uri = S3Uri(args[0]) if uri.type == "s3" and uri.has_bucket(): subcmd_bucket_usage(s3, uri) return subcmd_bucket_usage_all(s3) def subcmd_bucket_usage_all(s3): response = s3.list_all_buckets() buckets_size = 0 for bucket in response["list"]: size = subcmd_bucket_usage(s3, S3Uri("s3://" + bucket["Name"])) if size != None: buckets_size += size total_size, size_coeff = formatSize(buckets_size, Config().human_readable_sizes) total_size_str = str(total_size) + size_coeff output("".rjust(8, "-")) output("%s Total" % (total_size_str.ljust(8))) def subcmd_bucket_usage(s3, uri): bucket = uri.bucket() object = uri.object() if object.endswith('*'): object = object[:-1] try: response = s3.bucket_list(bucket, prefix = object) except S3Error, e: if S3.codes.has_key(e.Code): error(S3.codes[e.Code] % bucket) return else: raise bucket_size = 0 for object in response["list"]: size, size_coeff = formatSize(object["Size"], False) bucket_size += size total_size, size_coeff = formatSize(bucket_size, Config().human_readable_sizes) total_size_str = str(total_size) + size_coeff output("%s %s" % (total_size_str.ljust(8), uri)) return bucket_size def cmd_ls(args): s3 = S3(Config()) if len(args) > 0: uri = S3Uri(args[0]) if uri.type == "s3" and uri.has_bucket(): subcmd_bucket_list(s3, uri) return subcmd_buckets_list_all(s3) def cmd_buckets_list_all_all(args): s3 = S3(Config()) response = s3.list_all_buckets() for bucket in response["list"]: subcmd_bucket_list(s3, S3Uri("s3://" + bucket["Name"])) output("") def subcmd_buckets_list_all(s3): response = s3.list_all_buckets() for bucket in response["list"]: output("%s s3://%s" % ( formatDateTime(bucket["CreationDate"]), bucket["Name"], )) def subcmd_bucket_list(s3, uri): bucket = uri.bucket() object = uri.object() output("Bucket '%s':" % bucket) if object.endswith('*'): object = object[:-1] try: response = s3.bucket_list(bucket, prefix = object) except S3Error, e: if S3.codes.has_key(e.info["Code"]): error(S3.codes[e.info["Code"]] % bucket) return else: raise for object in response["list"]: size, size_coeff = formatSize(object["Size"], Config().human_readable_sizes) output("%s %s%s %s" % ( formatDateTime(object["LastModified"]), str(size).rjust(8), size_coeff.ljust(1), uri.compose_uri(bucket, object["Key"]), )) def cmd_bucket_create(args): uri = S3Uri(args[0]) if not uri.type == "s3" or not uri.has_bucket() or uri.has_object(): raise ParameterError("Expecting S3 URI with just the bucket name set instead of '%s'" % args[0]) try: s3 = S3(Config()) response = s3.bucket_create(uri.bucket(), cfg.bucket_location) except S3Error, e: if S3.codes.has_key(e.info["Code"]): error(S3.codes[e.info["Code"]] % uri.bucket()) return else: raise output("Bucket '%s' created" % uri.bucket()) def cmd_bucket_delete(args): uri = S3Uri(args[0]) if not uri.type == "s3" or not uri.has_bucket() or uri.has_object(): raise ParameterError("Expecting S3 URI with just the bucket name set instead of '%s'" % args[0]) try: s3 = S3(Config()) response = s3.bucket_delete(uri.bucket()) except S3Error, e: if S3.codes.has_key(e.info["Code"]): error(S3.codes[e.info["Code"]] % uri.bucket()) return else: raise output("Bucket '%s' removed" % uri.bucket()) def cmd_object_put(args): s3 = S3(Config()) uri_arg = args.pop() check_args_type(args, 'file', 'filename') uri = S3Uri(uri_arg) if uri.type != "s3": raise ParameterError("Expecting S3 URI instead of '%s'" % uri_arg) if len(args) > 1 and uri.object() != "" and not Config().force: error("When uploading multiple files the last argument must") error("be a S3 URI specifying just the bucket name") error("WITHOUT object name!") error("Alternatively use --force argument and the specified") error("object name will be prefixed to all stored filenames.") sys.exit(1) seq = 0 total = len(args) for file in args: seq += 1 uri_arg_final = str(uri) if len(args) > 1 or uri.object() == "": uri_arg_final += os.path.basename(file) uri_final = S3Uri(uri_arg_final) extra_headers = {} real_filename = file if Config().encrypt: exitcode, real_filename, extra_headers["x-amz-meta-s3tools-gpgenc"] = gpg_encrypt(file) try: response = s3.object_put_uri(real_filename, uri_final, extra_headers) except S3UploadError, e: error("Upload of '%s' failed too many times. Skipping that file." % real_filename) continue speed_fmt = formatSize(response["speed"], human_readable = True, floating_point = True) output("File '%s' stored as %s (%d bytes in %0.1f seconds, %0.2f %sB/s) [%d of %d]" % (file, uri_final, response["size"], response["elapsed"], speed_fmt[0], speed_fmt[1], seq, total)) if Config().acl_public: output("Public URL of the object is: %s" % (uri_final.public_url())) if Config().encrypt and real_filename != file: debug("Removing temporary encrypted file: %s" % real_filename) os.remove(real_filename) def cmd_object_get(args): s3 = S3(Config()) if not S3Uri(args[0]).type == 's3': raise ParameterError("Expecting S3 URI instead of '%s'" % args[0]) destination_dir = None destination_file = None if len(args) > 1: if S3Uri(args[-1]).type == 's3': # all S3, use object names to local dir check_args_type(args, type="s3", verbose_type="S3 URI") # May raise ParameterError else: if (len(args) > 2): # last must be dir, all preceding S3 if not os.path.isdir(args[-1]): raise ParameterError("Last parameter must be a directory") destination_dir = args.pop() check_args_type(args, type="s3", verbose_type="S3 URI") # May raise ParameterError else: # last must be a dir or a filename if os.path.isdir(args[-1]): destination_dir = args.pop() else: destination_file = args.pop() while (len(args)): uri_arg = args.pop(0) uri = S3Uri(uri_arg) if destination_file: destination = destination_file elif destination_dir: destination = destination_dir + "/" + uri.object() else: # By default the destination filename is the object name destination = uri.object() if destination == "-": ## stdout dst_stream = sys.stdout else: ## File if not Config().force and os.path.exists(destination): raise ParameterError("File %s already exists. Use --force to overwrite it" % destination) try: dst_stream = open(destination, "wb") except IOError, e: error("Skipping %s: %s" % (destination, e.strerror)) continue response = s3.object_get_uri(uri, dst_stream) if response["headers"].has_key("x-amz-meta-s3tools-gpgenc"): gpg_decrypt(destination, response["headers"]["x-amz-meta-s3tools-gpgenc"]) response["size"] = os.stat(destination)[6] if destination != "-": speed_fmt = formatSize(response["speed"], human_readable = True, floating_point = True) output("Object %s saved as '%s' (%d bytes in %0.1f seconds, %0.2f %sB/s)" % (uri, destination, response["size"], response["elapsed"], speed_fmt[0], speed_fmt[1])) def cmd_object_del(args): s3 = S3(Config()) while (len(args)): uri_arg = args.pop(0) uri = S3Uri(uri_arg) if uri.type != "s3" or not uri.has_object(): raise ParameterError("Expecting S3 URI instead of '%s'" % uri_arg) response = s3.object_delete_uri(uri) output("Object %s deleted" % uri) def cmd_info(args): s3 = S3(Config()) while (len(args)): uri_arg = args.pop(0) uri = S3Uri(uri_arg) if uri.type != "s3" or not uri.has_bucket(): raise ParameterError("Expecting S3 URI instead of '%s'" % uri_arg) try: if uri.has_object(): info = s3.object_info(uri) output("%s (object):" % uri.uri()) output(" File size: %s" % info['headers']['content-length']) output(" Last mod: %s" % info['headers']['last-modified']) output(" MIME type: %s" % info['headers']['content-type']) output(" MD5 sum: %s" % info['headers']['etag'].strip('"')) else: info = s3.bucket_info(uri) output("%s (bucket):" % uri.uri()) output(" Location: %s" % info['bucket-location']) acl = s3.get_acl(uri) for user in acl.keys(): output(" ACL: %s: %s" % (user, acl[user])) except S3Error, e: if S3.codes.has_key(e.info["Code"]): error(S3.codes[e.info["Code"]] % uri.bucket()) return else: raise def _get_filelist_local(local_uri): output("Compiling list of local files...") local_path = local_uri.path() if os.path.isdir(local_path): loc_base = os.path.join(local_path, "") filelist = os.walk(local_path) else: loc_base = "./" filelist = [( '.', [], [local_path] )] loc_base_len = len(loc_base) loc_list = {} for root, dirs, files in filelist: ## TODO: implement explicit exclude for f in files: full_name = os.path.join(root, f) if not os.path.isfile(full_name): continue if os.path.islink(full_name): ## Synchronize symlinks... one day ## for now skip over continue file = full_name[loc_base_len:] sr = os.stat_result(os.lstat(full_name)) loc_list[file] = { 'full_name' : full_name, 'size' : sr.st_size, 'mtime' : sr.st_mtime, ## TODO: Possibly more to save here... } return loc_list def _get_filelist_remote(remote_uri): output("Retrieving list of remote files...") s3 = S3(Config()) response = s3.bucket_list(remote_uri.bucket(), prefix = remote_uri.object()) rem_base = remote_uri.object() rem_base_len = len(rem_base) rem_list = {} for object in response['list']: key = object['Key'][rem_base_len:].encode('utf-8') rem_list[key] = { 'size' : int(object['Size']), # 'mtime' : dateS3toUnix(object['LastModified']), ## That's upload time, not our lastmod time :-( 'md5' : object['ETag'][1:-1], 'object_key' : object['Key'].encode('utf-8'), } return rem_list def _compare_filelists(src_list, dst_list, src_is_local_and_dst_is_remote): output("Verifying checksums...") cfg = Config() exists_list = {} exclude_list = {} if cfg.debug_syncmatch: logging.root.setLevel(logging.DEBUG) for file in src_list.keys(): if not cfg.debug_syncmatch: debug("CHECK: %s" % (os.sep + file)) excluded = False for r in cfg.exclude: ## all paths start with '/' from the base dir if r.search(os.sep + file): ## Can't directly 'continue' to the outer loop ## therefore this awkward excluded switch :-( excluded = True if cfg.debug_syncmatch: debug("EXCL: %s" % (os.sep + file)) debug("RULE: '%s'" % (cfg.debug_exclude[r])) else: info("%s: excluded" % file) break if excluded: exclude_list = src_list[file] del(src_list[file]) continue else: debug("PASS: %s" % (os.sep + file)) if dst_list.has_key(file): ## Check size first if dst_list[file]['size'] == src_list[file]['size']: #debug("%s same size: %s" % (file, dst_list[file]['size'])) ## ... same size, check MD5 if src_is_local_and_dst_is_remote: src_md5 = Utils.hash_file_md5(src_list[file]['full_name']) dst_md5 = dst_list[file]['md5'] else: src_md5 = src_list[file]['md5'] dst_md5 = Utils.hash_file_md5(dst_list[file]['full_name']) if src_md5 == dst_md5: #debug("%s md5 matches: %s" % (file, dst_md5)) ## Checksums are the same. ## Remove from source-list, all that is left there will be transferred debug("IGNR: %s (transfer not needed: MD5 OK, Size OK)" % file) exists_list[file] = src_list[file] del(src_list[file]) else: debug("XFER: %s (md5 mismatch: src=%s dst=%s)" % (file, src_md5, dst_md5)) else: debug("XFER: %s (size mismatch: src=%s dst=%s)" % (file, src_list[file]['size'], dst_list[file]['size'])) ## Remove from destination-list, all that is left there will be deleted #debug("%s removed from destination list" % file) del(dst_list[file]) if cfg.debug_syncmatch: warning("Exiting because of --debug-syncmatch") sys.exit(0) return src_list, dst_list, exists_list, exclude_list def cmd_sync_remote2local(src, dst): def _parse_attrs_header(attrs_header): attrs = {} for attr in attrs_header.split("/"): key, val = attr.split(":") attrs[key] = val return attrs s3 = S3(Config()) src_uri = S3Uri(src) dst_uri = S3Uri(dst) rem_list = _get_filelist_remote(src_uri) rem_count = len(rem_list) loc_list = _get_filelist_local(dst_uri) loc_count = len(loc_list) output("Found %d remote files, %d local files" % (rem_count, loc_count)) _compare_filelists(rem_list, loc_list, False) output("Summary: %d remote files to download, %d local files to delete" % (len(rem_list), len(loc_list))) for file in loc_list: if cfg.delete_removed: # os.unlink(file) output("deleted '%s'" % file) else: output("not-deleted '%s'" % file) total_size = 0 total_count = len(rem_list) total_elapsed = 0.0 timestamp_start = time.time() seq = 0 dir_cache = {} src_base = src_uri.uri() dst_base = dst_uri.path() if not src_base[-1] == "/": src_base += "/" file_list = rem_list.keys() file_list.sort() for file in file_list: seq += 1 uri = S3Uri(src_base + file) dst_file = dst_base + file try: dst_dir = os.path.dirname(dst_file) if not dir_cache.has_key(dst_dir): dir_cache[dst_dir] = Utils.mkdir_with_parents(dst_dir) if dir_cache[dst_dir] == False: warning("%s: destination directory not writable: %s" % (file, dst_dir)) continue try: open_flags = os.O_CREAT if cfg.force: open_flags |= os.O_TRUNC else: open_flags |= os.O_EXCL debug("dst_file=%s" % dst_file) # This will have failed should the file exist os.open(dst_file, open_flags) # Yeah I know there is a race condition here. Sadly I don't know how to open() in exclusive mode. dst_stream = open(dst_file, "wb") response = s3.object_get_uri(uri, dst_stream) dst_stream.close() if response['headers'].has_key('x-amz-meta-s3cmd-attrs') and cfg.preserve_attrs: attrs = _parse_attrs_header(response['headers']['x-amz-meta-s3cmd-attrs']) if attrs.has_key('mode'): os.chmod(dst_file, int(attrs['mode'])) if attrs.has_key('mtime') or attrs.has_key('atime'): mtime = attrs.has_key('mtime') and int(attrs['mtime']) or int(time.time()) atime = attrs.has_key('atime') and int(attrs['atime']) or int(time.time()) os.utime(dst_file, (atime, mtime)) ## FIXME: uid/gid / uname/gname handling comes here! TODO except OSError, e: try: dst_stream.close() except: pass if e.errno == errno.EEXIST: warning("%s exists - not overwriting" % (dst_file)) continue if e.errno in (errno.EPERM, errno.EACCES): warning("%s not writable: %s" % (dst_file, e.strerror)) continue raise except KeyboardInterrupt: try: dst_stream.close() except: pass warning("Exiting after keyboard interrupt") return except Exception, e: try: dst_stream.close() except: pass error("%s: %s" % (file, e)) continue # We have to keep repeating this call because # Python 2.4 doesn't support try/except/finally # construction :-( try: dst_stream.close() except: pass except S3DownloadError, e: error("%s: download failed too many times. Skipping that file." % file) continue speed_fmt = formatSize(response["speed"], human_readable = True, floating_point = True) output("File '%s' stored as %s (%d bytes in %0.1f seconds, %0.2f %sB/s) [%d of %d]" % (uri, dst_file, response["size"], response["elapsed"], speed_fmt[0], speed_fmt[1], seq, total_count)) total_size += response["size"] total_elapsed = time.time() - timestamp_start speed_fmt = formatSize(total_size/total_elapsed, human_readable = True, floating_point = True) output("Done. Downloaded %d bytes in %0.1f seconds, %0.2f %sB/s" % (total_size, total_elapsed, speed_fmt[0], speed_fmt[1])) def cmd_sync_local2remote(src, dst): def _build_attr_header(src): attrs = {} st = os.stat_result(os.stat(src)) for attr in cfg.preserve_attrs_list: if attr == 'uname': try: val = pwd.getpwuid(st.st_uid).pw_name except KeyError: attr = "uid" val = st.st_uid warning("%s: Owner username not known. Storing UID=%d instead." % (src, val)) elif attr == 'gname': try: val = grp.getgrgid(st.st_gid).gr_name except KeyError: attr = "gid" val = st.st_gid warning("%s: Owner groupname not known. Storing GID=%d instead." % (src, val)) else: val = getattr(st, 'st_' + attr) attrs[attr] = val result = "" for k in attrs: result += "%s:%s/" % (k, attrs[k]) return { 'x-amz-meta-s3cmd-attrs' : result[:-1] } s3 = S3(Config()) src_uri = S3Uri(src) dst_uri = S3Uri(dst) loc_list = _get_filelist_local(src_uri) loc_count = len(loc_list) rem_list = _get_filelist_remote(dst_uri) rem_count = len(rem_list) output("Found %d local files, %d remote files" % (loc_count, rem_count)) _compare_filelists(loc_list, rem_list, True) output("Summary: %d local files to upload, %d remote files to delete" % (len(loc_list), len(rem_list))) for file in rem_list: uri = S3Uri("s3://" + dst_uri.bucket()+"/"+rem_list[file]['object_key']) if cfg.delete_removed: response = s3.object_delete_uri(uri) output("deleted '%s'" % uri) else: output("not-deleted '%s'" % uri) total_size = 0 total_count = len(loc_list) total_elapsed = 0.0 timestamp_start = time.time() seq = 0 dst_base = dst_uri.uri() if not dst_base[-1] == "/": dst_base += "/" file_list = loc_list.keys() file_list.sort() for file in file_list: seq += 1 src = loc_list[file]['full_name'] uri = S3Uri(dst_base + file) if cfg.preserve_attrs: attr_header = _build_attr_header(src) debug(attr_header) try: response = s3.object_put_uri(src, uri, attr_header) except S3UploadError, e: error("%s: upload failed too many times. Skipping that file." % src) continue speed_fmt = formatSize(response["speed"], human_readable = True, floating_point = True) output("File '%s' stored as %s (%d bytes in %0.1f seconds, %0.2f %sB/s) [%d of %d]" % (src, uri, response["size"], response["elapsed"], speed_fmt[0], speed_fmt[1], seq, total_count)) total_size += response["size"] total_elapsed = time.time() - timestamp_start speed_fmt = formatSize(total_size/total_elapsed, human_readable = True, floating_point = True) output("Done. Uploaded %d bytes in %0.1f seconds, %0.2f %sB/s" % (total_size, total_elapsed, speed_fmt[0], speed_fmt[1])) def cmd_sync(args): src = args.pop(0) dst = args.pop(0) if (len(args)): raise ParameterError("Too many parameters! Expected: %s" % commands['sync']['param']) if S3Uri(src).type == "s3" and not src.endswith('/'): src += "/" if not dst.endswith('/'): dst += "/" if S3Uri(src).type == "file" and S3Uri(dst).type == "s3": return cmd_sync_local2remote(src, dst) if S3Uri(src).type == "s3" and S3Uri(dst).type == "file": return cmd_sync_remote2local(src, dst) def resolve_list(lst, args): retval = [] for item in lst: retval.append(item % args) return retval def gpg_command(command, passphrase = ""): p_in, p_out = os.popen4(command) if command.count("--passphrase-fd"): p_in.write(passphrase+"\n") p_in.flush() for line in p_out: info(line.strip()) p_pid, p_exitcode = os.wait() return p_exitcode def gpg_encrypt(filename): tmp_filename = Utils.mktmpfile() args = { "gpg_command" : cfg.gpg_command, "passphrase_fd" : "0", "input_file" : filename, "output_file" : tmp_filename, } info("Encrypting file %(input_file)s to %(output_file)s..." % args) command = resolve_list(cfg.gpg_encrypt.split(" "), args) code = gpg_command(command, cfg.gpg_passphrase) return (code, tmp_filename, "gpg") def gpg_decrypt(filename, gpgenc_header = "", in_place = True): tmp_filename = Utils.mktmpfile(filename) args = { "gpg_command" : cfg.gpg_command, "passphrase_fd" : "0", "input_file" : filename, "output_file" : tmp_filename, } info("Decrypting file %(input_file)s to %(output_file)s..." % args) command = resolve_list(cfg.gpg_decrypt.split(" "), args) code = gpg_command(command, cfg.gpg_passphrase) if code == 0 and in_place: debug("Renaming %s to %s" % (tmp_filename, filename)) os.unlink(filename) os.rename(tmp_filename, filename) tmp_filename = filename return (code, tmp_filename) def run_configure(config_file): cfg = Config() options = [ ("access_key", "Access Key", "Access key and Secret key are your identifiers for Amazon S3"), ("secret_key", "Secret Key"), ("gpg_passphrase", "Encryption password", "Encryption password is used to protect your files from reading\nby unauthorized persons while in transfer to S3"), ("gpg_command", "Path to GPG program"), ("use_https", "Use HTTPS protocol", "When using secure HTTPS protocol all communication with Amazon S3\nservers is protected from 3rd party eavesdropping. This method is\nslower than plain HTTP and can't be used if you're behind a proxy"), ("proxy_host", "HTTP Proxy server name", "On some networks all internet access must go through a HTTP proxy.\nTry setting it here if you can't conect to S3 directly"), ("proxy_port", "HTTP Proxy server port"), ] ## Option-specfic defaults if getattr(cfg, "gpg_command") == "": setattr(cfg, "gpg_command", find_executable("gpg")) if getattr(cfg, "proxy_host") == "" and os.getenv("http_proxy"): re_match=re.match("(http://)?([^:]+):(\d+)", os.getenv("http_proxy")) if re_match: setattr(cfg, "proxy_host", re_match.groups()[1]) setattr(cfg, "proxy_port", re_match.groups()[2]) try: while 1: output("\nEnter new values or accept defaults in brackets with Enter.") output("Refer to user manual for detailed description of all options.") for option in options: prompt = option[1] ## Option-specific handling if option[0] == 'proxy_host' and getattr(cfg, 'use_https') == True: setattr(cfg, option[0], "") continue if option[0] == 'proxy_port' and getattr(cfg, 'proxy_host') == "": setattr(cfg, option[0], 0) continue try: val = getattr(cfg, option[0]) if type(val) is bool: val = val and "Yes" or "No" if val not in (None, ""): prompt += " [%s]" % val except AttributeError: pass if len(option) >= 3: output("\n%s" % option[2]) val = raw_input(prompt + ": ") if val != "": if type(getattr(cfg, option[0])) is bool: # Turn 'Yes' into True, everything else into False val = val.lower().startswith('y') setattr(cfg, option[0], val) output("\nNew settings:") for option in options: output(" %s: %s" % (option[1], getattr(cfg, option[0]))) val = raw_input("\nTest access with supplied credentials? [Y/n] ") if val.lower().startswith("y") or val == "": try: output("Please wait...") S3(Config()).bucket_list("", "") output("Success. Your access key and secret key worked fine :-)") output("\nNow verifying that encryption works...") if not getattr(cfg, "gpg_command") or not getattr(cfg, "gpg_passphrase"): output("Not configured. Never mind.") else: if not getattr(cfg, "gpg_command"): raise Exception("Path to GPG program not set") if not os.path.isfile(getattr(cfg, "gpg_command")): raise Exception("GPG program not found") filename = Utils.mktmpfile() f = open(filename, "w") f.write(os.sys.copyright) f.close() ret_enc = gpg_encrypt(filename) ret_dec = gpg_decrypt(ret_enc[1], ret_enc[2], False) hash = [ Utils.hash_file_md5(filename), Utils.hash_file_md5(ret_enc[1]), Utils.hash_file_md5(ret_dec[1]), ] os.unlink(filename) os.unlink(ret_enc[1]) os.unlink(ret_dec[1]) if hash[0] == hash[2] and hash[0] != hash[1]: output ("Success. Encryption and decryption worked fine :-)") else: raise Exception("Encryption verification error.") except Exception, e: error("Test failed: %s" % (e)) val = raw_input("\nRetry configuration? [Y/n] ") if val.lower().startswith("y") or val == "": continue val = raw_input("\nSave settings? [y/N] ") if val.lower().startswith("y"): break val = raw_input("Retry configuration? [Y/n] ") if val.lower().startswith("n"): raise EOFError() ## Overwrite existing config file, make it user-readable only old_mask = os.umask(0077) try: os.remove(config_file) except OSError, e: if e.errno != errno.ENOENT: raise f = open(config_file, "w") os.umask(old_mask) cfg.dump_config(f) f.close() output("Configuration saved to '%s'" % config_file) except (EOFError, KeyboardInterrupt): output("\nConfiguration aborted. Changes were NOT saved.") return except IOError, e: error("Writing config file failed: %s: %s" % (config_file, e.strerror)) sys.exit(1) def process_exclude_from_file(exf, exclude_array): exfi = open(exf, "rt") for ex in exfi: ex = ex.strip() if re.match("^#", ex) or re.match("^\s*$", ex): continue debug("adding rule: %s" % ex) exclude_array.append(ex) commands = {} commands_list = [ {"cmd":"mb", "label":"Make bucket", "param":"s3://BUCKET", "func":cmd_bucket_create, "argc":1}, {"cmd":"rb", "label":"Remove bucket", "param":"s3://BUCKET", "func":cmd_bucket_delete, "argc":1}, {"cmd":"ls", "label":"List objects or buckets", "param":"[s3://BUCKET[/PREFIX]]", "func":cmd_ls, "argc":0}, {"cmd":"la", "label":"List all object in all buckets", "param":"", "func":cmd_buckets_list_all_all, "argc":0}, {"cmd":"put", "label":"Put file into bucket", "param":"FILE [FILE...] s3://BUCKET[/PREFIX]", "func":cmd_object_put, "argc":2}, {"cmd":"get", "label":"Get file from bucket", "param":"s3://BUCKET/OBJECT LOCAL_FILE", "func":cmd_object_get, "argc":1}, {"cmd":"del", "label":"Delete file from bucket", "param":"s3://BUCKET/OBJECT", "func":cmd_object_del, "argc":1}, #{"cmd":"mkdir", "label":"Make a virtual S3 directory", "param":"s3://BUCKET/path/to/dir", "func":cmd_mkdir, "argc":1}, {"cmd":"sync", "label":"Synchronize a directory tree to S3", "param":"LOCAL_DIR s3://BUCKET[/PREFIX] or s3://BUCKET[/PREFIX] LOCAL_DIR", "func":cmd_sync, "argc":2}, {"cmd":"du", "label":"Disk usage by buckets", "param":"[s3://BUCKET[/PREFIX]]", "func":cmd_du, "argc":0}, {"cmd":"info", "label":"Get various information about Buckets or Objects", "param":"s3://BUCKET[/OBJECT]", "func":cmd_info, "argc":1}, #{"cmd":"setacl", "label":"Modify Access control list for Bucket or Object", "param":"s3://BUCKET[/OBJECT]", "func":cmd_setacl, "argc":1}, ] def format_commands(progname): help = "Commands:\n" for cmd in commands_list: help += " %s\n %s %s %s\n" % (cmd["label"], progname, cmd["cmd"], cmd["param"]) return help class OptionMimeType(Option): def check_mimetype(option, opt, value): if re.compile("^[a-z0-9]+/[a-z0-9+\.-]+$", re.IGNORECASE).match(value): return value raise OptionValueError("option %s: invalid MIME-Type format: %r" % (opt, value)) TYPES = Option.TYPES + ("mimetype",) TYPE_CHECKER = copy(Option.TYPE_CHECKER) TYPE_CHECKER["mimetype"] = check_mimetype class MyHelpFormatter(IndentedHelpFormatter): def format_epilog(self, epilog): if epilog: return "\n" + epilog + "\n" else: return "" def main(): global cfg if float("%d.%d" %(sys.version_info[0], sys.version_info[1])) < 2.4: sys.stderr.write("ERROR: Python 2.4 or higher required, sorry.\n") sys.exit(1) ## Populate "commands" from "commands_list" for cmd in commands_list: if cmd.has_key("cmd"): commands[cmd["cmd"]] = cmd default_verbosity = Config().verbosity optparser = OptionParser(option_class=OptionMimeType, formatter=MyHelpFormatter()) #optparser.disable_interspersed_args() if os.getenv("HOME"): optparser.set_defaults(config=os.getenv("HOME")+"/.s3cfg") optparser.set_defaults(verbosity = default_verbosity) optparser.add_option( "--configure", dest="run_configure", action="store_true", help="Invoke interactive (re)configuration tool.") optparser.add_option("-c", "--config", dest="config", metavar="FILE", help="Config file name. Defaults to %default") optparser.add_option( "--dump-config", dest="dump_config", action="store_true", help="Dump current configuration after parsing config files and command line options and exit.") #optparser.add_option("-n", "--dry-run", dest="dry_run", action="store_true", help="Only show what should be uploaded or downloaded but don't actually do it. May still perform S3 requests to get bucket listings and other information though.") optparser.add_option("-e", "--encrypt", dest="encrypt", action="store_true", help="Encrypt files before uploading to S3.") optparser.add_option( "--no-encrypt", dest="encrypt", action="store_false", help="Don't encrypt files.") optparser.add_option("-f", "--force", dest="force", action="store_true", help="Force overwrite and other dangerous operations.") optparser.add_option("-P", "--acl-public", dest="acl_public", action="store_true", help="Store objects with ACL allowing read for anyone.") optparser.add_option( "--acl-private", dest="acl_public", action="store_false", help="Store objects with default ACL allowing access for you only.") optparser.add_option( "--delete-removed", dest="delete_removed", action="store_true", help="Delete remote objects with no corresponding local file [sync]") optparser.add_option( "--no-delete-removed", dest="delete_removed", action="store_false", help="Don't delete remote objects.") optparser.add_option("-p", "--preserve", dest="preserve_attrs", action="store_true", help="Preserve filesystem attributes (mode, ownership, timestamps). Default for [sync] command.") optparser.add_option( "--no-preserve", dest="preserve_attrs", action="store_false", help="Don't store FS attributes") optparser.add_option( "--exclude", dest="exclude", action="append", metavar="GLOB", help="Filenames and paths matching GLOB will be excluded from sync") optparser.add_option( "--exclude-from", dest="exclude_from", action="append", metavar="FILE", help="Read --exclude GLOBs from FILE") optparser.add_option( "--rexclude", dest="rexclude", action="append", metavar="REGEXP", help="Filenames and paths matching REGEXP (regular expression) will be excluded from sync") optparser.add_option( "--rexclude-from", dest="rexclude_from", action="append", metavar="FILE", help="Read --rexclude REGEXPs from FILE") optparser.add_option( "--debug-syncmatch", "--debug-exclude", dest="debug_syncmatch", action="store_true", help="Output detailed information about remote vs. local filelist matching and --exclude processing and then exit") optparser.add_option( "--bucket-location", dest="bucket_location", help="Datacentre to create bucket in. Either EU or US (default)") optparser.add_option("-m", "--mime-type", dest="default_mime_type", type="mimetype", metavar="MIME/TYPE", help="Default MIME-type to be set for objects stored.") optparser.add_option("-M", "--guess-mime-type", dest="guess_mime_type", action="store_true", help="Guess MIME-type of files by their extension. Falls back to default MIME-Type as specified by --mime-type option") optparser.add_option("-H", "--human-readable-sizes", dest="human_readable_sizes", action="store_true", help="Print sizes in human readable form.") optparser.add_option("-v", "--verbose", dest="verbosity", action="store_const", const=logging.INFO, help="Enable verbose output.") optparser.add_option("-d", "--debug", dest="verbosity", action="store_const", const=logging.DEBUG, help="Enable debug output.") optparser.add_option( "--version", dest="show_version", action="store_true", help="Show s3cmd version (%s) and exit." % (PkgInfo.version)) optparser.set_usage(optparser.usage + " COMMAND [parameters]") optparser.set_description('S3cmd is a tool for managing objects in '+ 'Amazon S3 storage. It allows for making and removing '+ '"buckets" and uploading, downloading and removing '+ '"objects" from these buckets.') optparser.epilog = format_commands(optparser.get_prog_name()) optparser.epilog += ("\nSee program homepage for more information at\n%s\n" % PkgInfo.url) (options, args) = optparser.parse_args() ## Some mucking with logging levels to enable ## debugging/verbose output for config file parser on request logging.basicConfig(level=options.verbosity, format='%(levelname)s: %(message)s') if options.show_version: output("s3cmd version %s" % PkgInfo.version) sys.exit(0) ## Now finally parse the config file if not options.config: error("Can't find a config file. Please use --config option.") sys.exit(1) try: cfg = Config(options.config) except IOError, e: if options.run_configure: cfg = Config() else: error("%s: %s" % (options.config, e.strerror)) error("Configuration file not available.") error("Consider using --configure parameter to create one.") sys.exit(1) ## And again some logging level adjustments ## according to configfile and command line parameters if options.verbosity != default_verbosity: cfg.verbosity = options.verbosity logging.root.setLevel(cfg.verbosity) ## Update Config with other parameters for option in cfg.option_list(): try: if getattr(options, option) != None: debug("Updating %s -> %s" % (option, getattr(options, option))) cfg.update_option(option, getattr(options, option)) except AttributeError: ## Some Config() options are not settable from command line pass ## Process GLOB (shell wildcard style) excludes if options.exclude is None: options.exclude = [] if options.exclude_from: for exf in options.exclude_from: debug("processing --exclude-from %s" % exf) process_exclude_from_file(exf, options.exclude) if options.exclude: for ex in options.exclude: debug("processing rule: %s" % ex) exc = re.compile(glob.fnmatch.translate(ex)) cfg.exclude.append(exc) if options.debug_syncmatch: cfg.debug_exclude[exc] = ex ## Process REGEXP style excludes if options.rexclude is None: options.rexclude = [] if options.rexclude_from: for exf in options.rexclude_from: debug("processing --rexclude-from %s" % exf) process_exclude_from_file(exf, options.rexclude) if options.rexclude: for ex in options.rexclude: debug("processing rule: %s" % ex) exc = re.compile(ex) cfg.exclude.append(exc) if options.debug_syncmatch: cfg.debug_exclude[exc] = ex if cfg.encrypt and cfg.gpg_passphrase == "": error("Encryption requested but no passphrase set in config file.") error("Please re-run 's3cmd --configure' and supply it.") sys.exit(1) if options.dump_config: cfg.dump_config(sys.stdout) sys.exit(0) if options.run_configure: run_configure(options.config) sys.exit(0) if len(args) < 1: error("Missing command. Please run with --help for more information.") sys.exit(1) command = args.pop(0) try: debug("Command: " + commands[command]["cmd"]) ## We must do this lookup in extra step to ## avoid catching all KeyError exceptions ## from inner functions. cmd_func = commands[command]["func"] except KeyError, e: error("Invalid command: %s" % e) sys.exit(1) if len(args) < commands[command]["argc"]: error("Not enough paramters for command '%s'" % command) sys.exit(1) try: cmd_func(args) except S3Error, e: error("S3 error: " + str(e)) sys.exit(1) except ParameterError, e: error("Parameter problem: " + str(e)) sys.exit(1) if __name__ == '__main__': try: ## Our modules ## Keep them in try/except block to ## detect any syntax errors in there from S3 import PkgInfo from S3.S3 import * from S3.Config import Config from S3.S3Uri import * from S3 import Utils from S3.Exceptions import * main() sys.exit(0) except SystemExit, e: sys.exit(e.code) except Exception, e: sys.stderr.write(""" !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! An unexpected error has occurred. Please report the following lines to: s3tools-general@lists.sourceforge.net !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! """) sys.stderr.write("S3cmd: %s\n" % PkgInfo.version) sys.stderr.write("Python: %s\n" % sys.version.replace('\n', ' ')) sys.stderr.write("\n") sys.stderr.write(traceback.format_exc(sys.exc_info())+"\n") sys.stderr.write(""" !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! An unexpected error has occurred. Please report the above lines to: s3tools-general@lists.sourceforge.net !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! """) sys.exit(1)