def _download_url(resp, link, temp_location):
fp = open(temp_location, 'wb')
download_hash = None
if link.hash and link.hash_name:
try:
download_hash = hashlib.new(link.hash_name)
except ValueError:
logger.warn("Unsupported hash name %s for package %s" % (link.hash_name, link))
try:
total_length = int(resp.info()['content-length'])
except (ValueError, KeyError, TypeError):
total_length = 0
downloaded = 0
show_progress = total_length > 40*1000 or not total_length
show_url = link.show_url
try:
if show_progress:
## FIXME: the URL can get really long in this message:
if total_length:
logger.start_progress('Downloading %s (%s): ' % (show_url, format_size(total_length)))
else:
logger.start_progress('Downloading %s (unknown size): ' % show_url)
else:
logger.notify('Downloading %s' % show_url)
logger.info('Downloading from URL %s' % link)
while True:
chunk = resp.read(4096)
if not chunk:
break
downloaded += len(chunk)
if show_progress:
if not total_length:
logger.show_progress('%s' % format_size(downloaded))
else:
logger.show_progress('%3i%% %s' % (100*downloaded/total_length, format_size(downloaded)))
if download_hash is not None:
download_hash.update(chunk)
fp.write(chunk)
fp.close()
finally:
if show_progress:
logger.end_progress('%s downloaded' % format_size(downloaded))
return download_hash
def _copy_file(filename, location, content_type, link):
copy = True
download_location = os.path.join(location, link.filename)
if os.path.exists(download_location):
response = ask_path_exists(
'The file %s exists. (i)gnore, (w)ipe, (b)ackup ' %
display_path(download_location), ('i', 'w', 'b'))
if response == 'i':
copy = False
elif response == 'w':
logger.warn('Deleting %s' % display_path(download_location))
os.remove(download_location)
elif response == 'b':
dest_file = backup_dir(download_location)
logger.warn('Backing up %s to %s'
% (display_path(download_location), display_path(dest_file)))
shutil.move(download_location, dest_file)
if copy:
shutil.copy(filename, download_location)
logger.indent -= 2
logger.notify('Saved %s' % display_path(download_location))
def unpack_http_url(link, location, download_cache=None, download_dir=None):
"""
downloads and unpacks a archive to a directory
link is a index.Link object (with an url)
location is dir where to move files to
download_cache is the dir where the download cache is stored
download_dir is optional a dir where the download is first stored
"""
temp_dir = tempfile.mkdtemp('-unpack', 'xppkg-')
target_url = link.url.split('#', 1)[0]
target_file = None
download_hash = None
if download_cache:
target_file = os.path.join(download_cache,
urllib.quote(target_url, ''))
if not os.path.isdir(download_cache):
create_download_cache_folder(download_cache)
already_downloaded = None
if download_dir:
already_downloaded = os.path.join(download_dir, link.filename)
if not os.path.exists(already_downloaded):
already_downloaded = None
if (target_file
and os.path.exists(target_file)
and os.path.exists(target_file + '.content-type')):
fp = open(target_file+'.content-type')
content_type = fp.read().strip()
fp.close()
if link.hash and link.hash_name:
download_hash = _get_hash_from_file(target_file, link)
temp_location = target_file
logger.notify('Using download cache from %s' % target_file)
elif already_downloaded:
temp_location = already_downloaded
content_type = mimetypes.guess_type(already_downloaded)
if link.hash:
download_hash = _get_hash_from_file(temp_location, link)
logger.notify('File was already downloaded %s' % already_downloaded)
else:
resp = _get_response_from_url(target_url, link)
content_type = resp.info()['content-type']
filename = link.filename # fallback
# Have a look at the Content-Disposition header for a better guess
content_disposition = resp.info().get('content-disposition')
if content_disposition:
type, params = cgi.parse_header(content_disposition)
# We use ``or`` here because we don't want to use an "empty" value
# from the filename param.
filename = params.get('filename') or filename
ext = splitext(filename)[1]
if not ext:
ext = mimetypes.guess_extension(content_type)
if ext:
filename += ext
if not ext and link.url != geturl(resp):
ext = os.path.splitext(geturl(resp))[1]
if ext:
filename += ext
temp_location = os.path.join(temp_dir, filename)
download_hash = _download_url(resp, link, temp_location)
if link.hash and link.hash_name:
_check_hash(download_hash, link)
if download_dir and not already_downloaded:
_copy_file(temp_location, download_dir, content_type, link)
unpack_file(temp_location, location, content_type, link)
if target_file and target_file != temp_location:
cache_download(target_file, temp_location, content_type)
if target_file is None and not already_downloaded:
os.unlink(temp_location)
os.rmdir(temp_dir)
