def get(archive, provider=None, zipfile=None):
"""
Get a cached copy of the archive's zipfile if it's been cached. Otherwise
create a new zipfile and cache it.
archive: name of the archive (full path, may or may not be a file)
provider: a function that can provide a zipfile associated with 'archive' if we need
to construct one.
zipfile: the zipfile we're currently using. if it differs from what is cached,
close and return the cached copy instead.
"""
if archive in _zipfile_cache:
# TODO(wickman) This is problematic sometimes as the zipfile library has a bug where
# it assumes the underlying zipfile does not change between reads, so its info cache
# gets out of date and throws BadZipfile exceptions (e.g. with EGG-INFO/requires.txt)
if zipfile is not None and _zipfile_cache[archive] != zipfile:
zipfile.close()
zf = _zipfile_cache[archive]
else:
if zipfile is not None:
zf = _zipfile_cache[archive] = zipfile
else:
assert provider is not None
zf = _zipfile_cache[archive] = provider()
_zipfile_namecache[archive] = set(zf.namelist())
# PyPy doesn't allow us to share its builtin_zipimport _zip_directory_cache.
# TODO(wickman) Go back to the delegating proxy for zip directory cache.
# TODO(wickman) Do not leave handles open, as this could cause ulimits to
# be exceeded.
_zip_directory_cache[archive] = ZipFileCache(archive)
return zf
def download_files(item):
updates = []
paths = []
content = requests.get(item['link']).content
soup = BeautifulSoup(content, "html.parser")
links = [l for l in soup.find_all('a') if l.has_attr('href')]
download_url = "/".join(item['link'].split('/')[:-1]) + "/"
link_texts = list(set([link.string for link in links]))
page_text = soup.text
title_dir = item['title']
for filename in link_texts:
try:
if ".zip" in filename: # Only find zip files
if "pcap" in filename: # We don't need pcaps. Those will be recreated in the sandbox
continue
else:
download_link = download_url + filename # Create the download link for each zip
print "Downloading: {}".format(
download_link) # Display what's happening
res = requests.get(
download_link) # Create the download object
# Download the files into the 'malware' directory
zipfile = open(
os.path.join('malware', os.path.basename(filename)),
'wb')
for chunk in res.iter_content(100000):
zipfile.write(chunk)
zipfile.close()
write_append(downloaded_files,
'malware/' + filename + '\n')
except:
pass
def get(archive, provider=None, zipfile=None):
"""
Get a cached copy of the archive's zipfile if it's been cached. Otherwise
create a new zipfile and cache it.
archive: name of the archive (full path, may or may not be a file)
provider: a function that can provide a zipfile associated with 'archive' if we need
to construct one.
zipfile: the zipfile we're currently using. if it differs from what is cached,
close and return the cached copy instead.
"""
if archive in _zipfile_cache:
# TODO(wickman) This is problematic sometimes as the zipfile library has a bug where
# it assumes the underlying zipfile does not change between reads, so its info cache
# gets out of date and throws BadZipfile exceptions (e.g. with EGG-INFO/requires.txt)
if zipfile is not None and _zipfile_cache[archive] != zipfile:
zipfile.close()
zf = _zipfile_cache[archive]
else:
if zipfile is not None:
zf = _zipfile_cache[archive] = zipfile
else:
assert provider is not None
zf = _zipfile_cache[archive] = provider()
_zipfile_namecache[archive] = set(zf.namelist())
# PyPy doesn't allow us to share its builtin_zipimport _zip_directory_cache.
# TODO(wickman) Go back to the delegating proxy for zip directory cache.
# TODO(wickman) Do not leave handles open, as this could cause ulimits to
# be exceeded.
_zip_directory_cache[archive] = ZipFileCache(archive)
return zf
def get_zip_logs(request):
""" Make an archive of logs available to download """
from django.core.servers.basehttp import FileWrapper
import zipfile
try:
compression = zipfile.ZIP_DEFLATED
except:
compression = zipfile.ZIP_STORED
zipPath = "/tmp/logs.zip"
zipfile = zipfile.ZipFile(zipPath, mode="w", allowZip64=True)
files = ["tsconfig_gui.log", "django.log", "celery_w1.log"]
for afile in files:
fullpath = os.path.join("/var/log/ion", afile)
if os.path.exists(fullpath):
zipfile.write(fullpath, arcname=afile, compress_type=compression)
zipfile.close()
# TODO: Include the server serial number in the archive filename.
# One possible source is /etc/torrentserver/tsconf.conf, serialnumber:XXXXXX
archive_filename = "ts_update_logs.zip"
response = http.HttpResponse(FileWrapper(open(zipPath)), mimetype="application/zip")
response["Content-Disposition"] = "attachment; filename=%s" % archive_filename
return response
def get_zip_logs(request):
""" Make an archive of logs available to download """
from django.core.servers.basehttp import FileWrapper
import zipfile
try:
compression = zipfile.ZIP_DEFLATED
except Exception:
compression = zipfile.ZIP_STORED
zipPath = "/tmp/logs.zip"
zipfile = zipfile.ZipFile(zipPath, mode="w", allowZip64=True)
for afile in [
"tsconfig_gui.log",
"django.log",
"celery_w1.log",
"tsconfig_debug.log",
"product_integration.log",
]:
fullpath = os.path.join("/var/log/ion", afile)
if os.path.exists(fullpath):
zipfile.write(fullpath, arcname=afile, compress_type=compression)
zipfile.close()
# TODO: Include the server serial number in the archive filename.
# One possible source is /etc/torrentserver/tsconf.conf, serialnumber:XXXXXX
archive_filename = "ts_update_logs.zip"
response = http.HttpResponse(FileWrapper(open(zipPath)),
mimetype="application/zip")
response[
"Content-Disposition"] = "attachment; filename=%s" % archive_filename
return response
def get(archive, provider=None, zipfile=None):
"""
Get a cached copy of the archive's zipfile if it's been cached. Otherwise
create a new zipfile and cache it.
archive: name of the archive (full path, may or may not be a file)
provider: a function that can provide a zipfile associated with 'archive' if we need
to construct one.
zipfile: the zipfile we're currently using. if it differs from what is cached,
close and return the cached copy instead.
"""
if archive in _zipfile_cache:
if zipfile is not None and _zipfile_cache[archive] != zipfile:
zipfile.close()
zf = _zipfile_cache[archive]
else:
if zipfile is not None:
zf = _zipfile_cache[archive] = zipfile
else:
assert provider is not None
zf = _zipfile_cache[archive] = provider()
_zipfile_namecache[archive] = set(zf.namelist())
# PyPy doesn't allow us to share its builtin_zipimport _zip_directory_cache.
# TODO(wickman) Go back to the delegating proxy for zip directory cache.
# TODO(wickman) Do not leave handles open, as this could cause ulimits to
# be exceeded.
_zip_directory_cache[archive] = ZipFileCache(archive)
return zf
def get(archive, provider=None, zipfile=None):
"""
Get a cached copy of the archive's zipfile if it's been cached. Otherwise
create a new zipfile and cache it.
archive: name of the archive (full path, may or may not be a file)
provider: a function that can provide a zipfile associated with 'archive' if we need
to construct one.
zipfile: the zipfile we're currently using. if it differs from what is cached,
close and return the cached copy instead.
"""
if archive in _zipfile_cache:
if zipfile is not None and _zipfile_cache[archive] != zipfile:
zipfile.close()
zf = _zipfile_cache[archive]
else:
if zipfile is not None:
zf = _zipfile_cache[archive] = zipfile
else:
assert provider is not None
zf = _zipfile_cache[archive] = provider()
_zipfile_namecache[archive] = set(zf.namelist())
# PyPy doesn't allow us to share its builtin_zipimport _zip_directory_cache.
# TODO(wickman) Go back to the delegating proxy for zip directory cache.
# TODO(wickman) Do not leave handles open, as this could cause ulimits to
# be exceeded.
_zip_directory_cache[archive] = ZipFileCache(archive)
return zf
def get_zip_logs(request):
''' Make an archive of logs available to download '''
from django.core.servers.basehttp import FileWrapper
import zipfile
try:
compression = zipfile.ZIP_DEFLATED
except:
compression = zipfile.ZIP_STORED
zipPath = '/tmp/logs.zip'
zipfile = zipfile.ZipFile(zipPath, mode='w', allowZip64=True)
files = ['tsconfig_gui.log', 'django.log', 'celery_w1.log']
for afile in files:
fullpath = os.path.join('/var/log/ion', afile)
if os.path.exists(fullpath):
zipfile.write(fullpath, arcname=afile, compress_type=compression)
zipfile.close()
#TODO: Include the server serial number in the archive filename.
#One possible source is /etc/torrentserver/tsconf.conf, serialnumber:XXXXXX
archive_filename = 'ts_update_logs.zip'
response = http.HttpResponse(FileWrapper(open(zipPath)),
mimetype='application/zip')
response[
'Content-Disposition'] = 'attachment; filename=%s' % archive_filename
return response
def _download_and_extract_model_zip(self, url, file_name, force=False):
if file_name:
if os.path.exists(file_name):
if force:
os.remove(file_name)
return
temp_folder = tempfile.mkdtemp()
try:
if file_name != None: # online zip file
# Download and extract zip archive.
zip_file_name = os.path.join(temp_folder, "tmp.zip")
self._download_with_progress_bar(url, zip_file_name)
sys.stdout.write(
"\rDownload complete, decompressing files ... "
)
sys.stdout.flush()
else:
zip_file_name = url
zipfile = ZipFile(zip_file_name, "r")
zipfile.extractall(self.disk_path)
zipfile.close()
sys.stdout.write("\nModel extracted successfully.")
sys.stdout.flush()
except Exception as e:
print("Error encountered, cleaning up and exiting ...")
rmtree(temp_folder, ignore_errors=True)
raise e
# delete temporary folder
rmtree(temp_folder, ignore_errors=True)
def deletable_file(fname, typ, name):
"""Serves and then deletes a zip file"""
cherrypy.response.headers["Content-Type"] = typ
cherrypy.response.headers["Content-Disposition"] = 'attachment; filename="%s"' % (name)
zipfile = open(fname, "r+b")
for line in zipfile:
yield line
zipfile.close()
os.unlink(fname)
def deletable_file(fname, typ, name):
"""Serves and then deletes a zip file"""
cherrypy.response.headers['Content-Type'] = typ
cherrypy.response.headers[
"Content-Disposition"] = 'attachment; filename="%s"' % (name)
zipfile = open(fname, 'r+b')
for line in zipfile:
yield line
zipfile.close()
os.unlink(fname)
def exclude():
for dirname, subdirs, files in os.walk("./"):
if not subdirs:
print(subdirs)
else:
print("There is a directory")
if 'exclude directory' in subdirs:
subdirs.remove('exclude directory')
zf.write(dirname)
for filename in files:
zf.write(os.path.join(dirname, filename))
zf.close()
def EpubToTxt(file):
import os
import zipfile
import re
from bs4 import BeautifulSoup
def PrettifyTxt(text):
lines = text.split('\n')
text = ''
for line in lines:
if line.split():
text = text + ' ' + line.strip() + '\n'
return text
filename = os.path.basename(file)
filebasename = os.path.splitext(filename)[0]
zipfile = zipfile.ZipFile(file)
namelist = zipfile.namelist()
opflist = []
text = ''
for subfile in namelist:
if subfile.endswith('.opf'):
opflist.append(subfile)
opffile = min(opflist, key=len)
folder = opffile.rstrip(os.path.basename(opffile))
opfs = zipfile.open(opffile)
opf = ''
for line in opfs:
opf = opf + str(line, 'utf-8')
ncx = re.search('(?s)<spine.*toc.*=.*"ncx".*>(.*?)</spine>', opf,
re.M).group()
manifest = re.search('(?s)<manifest.*>(.*?)</manifest>', opf, re.M).group()
ids = re.findall(' id="(.*?)"', manifest)
hrefs = re.findall('href="(.*?)"', manifest)
idrefs = re.findall('<itemref.*idref="(.*?)"', ncx)
key = dict(zip(ids, hrefs))
for idref in idrefs:
htmpath = folder + key[idref]
htmopen = zipfile.open(htmpath)
soup = BeautifulSoup(htmopen, 'lxml')
text = text + soup.get_text()
zipfile.close()
return PrettifyTxt(text)
def rezip_one(target_zip, source_zip, compression):
try:
with ZipFile(source_zip).open('data') as f:
data = f.read()
except Exception as e:
print('skipping zip file', source_zip, 'for error', e)
return
# write to intermediate file in case source_dir == target_dir
zf = ZipFile(target_zip + '.new', 'w', compression=compression)
zf.writestr('data', data)
zf.close()
copystat(source_zip, target_zip + '.new')
move(target_zip + '.new', target_zip)
def handle_docs(email, files):
# Assume zipper always succeed
docfiles = list_files_by_extension(files, "docx")
print "List of document files", docfiles
zipper(ZipFileName, docfiles)
zipfile = open(ZipFileName, "rb")
zip = MIMEBase("application", "zip", name=ZipFileName)
zip.set_payload(zipfile.read())
zipfile.close()
encoders.encode_base64(zip)
email.attach(zip)
delete_files(docfiles)
def uncompress(srcfile, destdir):
import gzip
import tarfile, zipfile
file = os.path.basename(srcfile)
if os.path.isfile(file):
shortname, fmt = os.path.splitext(file)
fmt = fmt[1:]
if fmt in ('tgz', 'tar'):
try:
tar = tarfile.open(srcfile)
names = tar.getnames()
for name in names:
tar.extract(name, destdir)
tar.close()
except Exception as e:
print("Can't uncompress {} for {}".format(file, e))
elif fmt == 'zip':
try:
zipfile = zipfile.ZipFile(srcfile)
for names in zipfile.namelist():
zipfile.extract(names, destdir)
zipfile.close()
except Exception as e:
print("Can't uncompress {} for {}".format(file, e))
elif fmt == 'gz':
try:
fname = os.path.join(destdir, os.path.basename(srcfile))
gfile = gzip.GzipFile(srcfile)
open(fname, "w+").write(gfile.read())
# gzip对象用read()打开后，写入open()建立的文件中。
gfile.close()
# 关闭gzip对象
except Exception as e:
return False, e, fmt
'''
elif fmt == 'rar':
try:
rar = rarfile.RarFile(srcfile)
os.chdir(destdir)
rar.extractall()
rar.close()
except Exception as e :
return (False, e, filefmt)
'''
else:
print('文件格式不支持或者不是压缩文件')
return None
def download_ftp(remote_path, file, ftp_ip, ftp_user, ftp_pass):
zipfile = open(file, 'wb')
ftp = ftplib.FTP(ftp_ip)
ftp.login(ftp_user, ftp_pass)
size = ftp.size(remote_path)
global pbar
pbar = 0
def file_write(data):
zipfile.write(data)
global pbar
pbar += len(data)
zipfile.flush()
print("\r%3.2f %%" % (pbar * 100.0 / size), end='')
ftp.retrbinary("RETR " + remote_path, file_write)
zipfile.close()
print('')
def full_backup():
import zipfile
logger.info('Running full_backup')
from django.utils import timezone
from django.core.management import call_command
now = timezone.now()
file_name = 'backup-%s-%s-%s-%s-%s.json' % (now.year, now.month, now.day, now.hour, now.minute)
file_path = os.path.join(PROJECT_ROOT, 'backups', file_name)
dir = os.path.dirname(file_path)
try:
os.stat(dir)
except:
os.mkdir(dir)
# we will temporarilly redirect stdout to a file to capture the data from the dumpdata cmd
stdout = sys.stdout
try:
sys.stdout = open(file_path, 'w')
call_command('dumpdata', use_natural_foreign_keys=True, use_natural_primary_keys=True)
sys.stdout.close()
except Exception as exc:
logger.error(exc)
# Put stdout back to what it was
sys.stdout = stdout
# Now zip the file
zip_file_path = os.path.join(PROJECT_ROOT, 'backups', file_name + '.gz')
zipfile = gzip.GzipFile(zip_file_path, "wb")
try:
inputFile = open(file_path,"r")
zipfile.write(inputFile.read())
finally:
zipfile.close()
# Delete the original uncompressed file
os.remove(file_path)
def full_backup():
import zipfile
logger.info('Running full_backup')
from django.utils import timezone
from django.core.management import call_command
now = timezone.now()
file_name = 'backup-%s-%s-%s-%s-%s.json' % (now.year, now.month, now.day, now.hour, now.minute)
file_path = os.path.join(PROJECT_ROOT, 'backups', file_name)
dir = os.path.dirname(file_path)
try:
os.stat(dir)
except:
os.mkdir(dir)
# we will temporarilly redirect stdout to a file to capture the data from the dumpdata cmd
stdout = sys.stdout
try:
sys.stdout = open(file_path, 'w')
call_command('dumpdata', use_natural_foreign_keys=True, use_natural_primary_keys=True)
sys.stdout.close()
except Exception as exc:
logger.error(exc)
# Put stdout back to what it was
sys.stdout = stdout
# Now zip the file
zip_file_path = os.path.join(PROJECT_ROOT, 'backups', file_name + '.gz')
zipfile = gzip.GzipFile(zip_file_path, "wb")
try:
inputFile = open(file_path,"r")
zipfile.write(inputFile.read())
finally:
zipfile.close()
# Delete the original uncompressed file
os.remove(file_path)
def _mark_as_ended(self):
if not self.alive:
LOGGER.debug("Skipping creating the offline archive as we are not alive")
return
LOGGER.info("Starting saving the offline archive")
self.stop_time = local_timestamp()
self._write_experiment_meta_file()
try:
zipfile = self._get_offline_archive(self.offline_directory, self.id)
except (OSError, IOError) as exc:
# Use a temporary directory if we came so far to not lose the information
old_dir = self.offline_directory
self.offline_directory = tempfile.mkdtemp()
zipfile = self._get_offline_archive(self.offline_directory, self.id)
LOGGER.warning(
OFFLINE_EXPERIMENT_TEMPORARY_DIRECTORY,
old_dir,
str(exc),
self.offline_directory,
)
for file in os.listdir(self.tmpdir):
zipfile.write(os.path.join(self.tmpdir, file), file)
zipfile.close()
# Clean the tmpdir to avoid filling up the disk
try:
shutil.rmtree(self.tmpdir)
except OSError:
# We made our best effort to clean ourselves
msg = "Error cleaning offline experiment tmpdir %r"
LOGGER.debug(msg, self.tmpdir, exc_info=True)
# Display the full command to upload the offline experiment
LOGGER.info(OFFLINE_EXPERIMENT_END, zipfile.filename)
def decrypt_sound_found_in_memory(self, in_file_path):
with open(in_file_path, 'rb') as in_file:
file_size = struct.unpack('<Q',
in_file.read(struct.calcsize('<Q')))[0]
iv = in_file.read(16)
aes = AES.new(self.key, AES.MODE_CBC, iv)
out_file = tempfile.NamedTemporaryFile(delete=False)
while True:
data = in_file.read(self.size_chunk)
n = len(data)
if n == 0:
break
decode = aes.decrypt(data)
n = len(decode)
if file_size > n:
out_file.write(decode)
else:
out_file.write(
decode[:file_size]) # <- remove padding on last block
file_size -= n
temp_path = out_file.name[:out_file.name.rfind('\\')]
import zipfile
zipfile = zipfile.ZipFile(out_file)
zipfile.extractall(temp_path)
zipfile.close()
info_zipfile = zipfile.infolist()
if len(info_zipfile) < 2:
info_file_path = info_zipfile[0].filename.replace('/', '\\')
print(info_file_path)
sf_path = temp_path + '\\' + info_file_path
print(sf_path)
return sf_path
def get_zip_logs(request):
""" Make an archive of logs available to download """
from django.core.servers.basehttp import FileWrapper
import zipfile
try:
compression = zipfile.ZIP_DEFLATED
except:
compression = zipfile.ZIP_STORED
zipPath = '/tmp/logs.zip'
zipfile = zipfile.ZipFile(zipPath, mode='w', allowZip64=True)
for afile in ['tsconfig_gui.log', 'django.log', 'celery_w1.log', 'tsconfig_debug.log', 'product_integration.log']:
fullpath = os.path.join('/var/log/ion', afile)
if os.path.exists(fullpath):
zipfile.write(fullpath, arcname=afile, compress_type=compression)
zipfile.close()
#TODO: Include the server serial number in the archive filename.
#One possible source is /etc/torrentserver/tsconf.conf, serialnumber:XXXXXX
archive_filename = 'ts_update_logs.zip'
response = http.HttpResponse(FileWrapper (open(zipPath)), mimetype='application/zip')
response['Content-Disposition'] = 'attachment; filename=%s' % archive_filename
return response
def run_model_tracking (server, user, password, zipath, projectname, modelname):
'''
Given server and project params,
create a project and register the model in SAS Model manager
:param server:
:param user:
:param password:
:param project:
:param model:
:return: None
'''
with Session(hostname=server, username=user, password=password, verify_ssl=False):
zipfile = open(zipath, 'rb')
model_repository.import_model_from_zip(modelname,
projectname,
file=zipfile,
version='new'
)
zipfile.close()
return 0
#!/usr/bin/python
# http://www.pythonchallenge.com/pc/def/channel.html
import urllib, zipfile, re
fileUrl = 'http://www.pythonchallenge.com/pc/def/channel.zip'
(filename, ignore) = urllib.urlretrieve(fileUrl)
zipfile = zipfile.ZipFile(filename)
startingPattern = re.compile('start from ([0-9]*)')
linkingNumberPattern = re.compile('Next nothing is ([0-9]*)')
number = startingPattern.search(zipfile.read('readme.txt')).group(1)
while number:
filename = number + '.txt'
fileContents = zipfile.read(filename)
info = zipfile.getinfo(filename)
print info.comment,
numberMatch = linkingNumberPattern.search(fileContents)
if numberMatch:
number = numberMatch.group(1)
else:
number = None
zipfile.close()
def assemble(filenames, outputdir, sizes, lowResComp=85, hiResComp=70,
customCaptions={}, logger = printLogger):
global directories_json, filenames_json, captions_json, resolutions_json, info_json, captions
current_dir = os.getcwd()
os.chdir(os.path.join(outputdir, "slides"))
subdirs = []
for x,y in sizes:
if x < 0 or y < 0:
name = "original_size"
else:
name = str(x) + "x" + str(y)
os.mkdir(name)
subdirs.append(name)
directories_json = toJSON(subdirs)
f = open("directories.json", "w")
try:
f.write(directories_json)
finally:
f.close()
if quick_scaling:
scaling_method = Image.BICUBIC # alt: Image.BICUBIC or Image.BILINEAR
else:
scaling_method = Image.ANTIALIAS
files = []
captions.update(customCaptions)
resolutions = {}
if create_picture_archive:
zipfile = ZipFile("../pictures.zip", "w")
pool = Pool()
for name in filenames:
logger(name)
basename = os.path.basename(name)
im = Image.open(name)
if create_picture_archive:
if archive_quality < 100:
fname = os.path.join(tempfile.gettempdir(),
"gwtphotoalbum_temporary_image.jpg")
im.load()
#ImageFile.MAXBLOCK = 1000000
im.save(fname, "JPEG", optimize=1, quality=archive_quality,
progressive=1)
zipfile.write(fname, os.path.join(os.path.basename(outputdir),
basename))
os.remove(fname)
else:
zipfile.write(name, os.path.join(os.path.basename(outputdir),
basename))
if not customCaptions:
comment = read_caption(name)
if comment: captions[basename] = comment
files.append(basename)
compression = {}
comp = float(lowResComp)
if len(sizes) > 1:
delta = float((hiResComp-lowResComp))/(len(sizes)-1)
else: delta = 0.0
for dim in sizes:
compression[dim] = int(comp+0.5)
comp += delta
pool = Pool()
res = []
for dimensions, dirname in zip(sizes, subdirs):
if tuple(dimensions) == tuple(FULLSIZE):
shutil.copy(name, dirname);
res.append([im.size[0], im.size[1]])
else:
x, y = dimensions
w, h = adjustSize(im.size, (x, y))
filename = os.path.join(dirname, basename)
pool.apply_async(resizeAndSave, (im, w, h, scaling_method,
os.path.join(dirname, basename),
compression[dimensions]))
#resizeAndSave(im, w, h, scaling_method,
# os.path.join(dirname, basename),
# compression[dimensions])
res.append([w,h])
#if tuple(dimensions) == tuple(sizes[-1]) \
# and basename in captions:
# pass
#write_caption(os.path.join(dirname, basename),
# captions[basename])
pool.close()
pool.join()
resolutions[basename] = checkInRes(res)
if create_picture_archive:
zipfile.close()
pool.close()
pool.join()
filenames_json = toJSON(files)
f = open("filenames.json", "w")
try:
f.write(filenames_json)
finally:
f.close()
strippedCaptions = {}
for fn in files:
if fn in captions:
strippedCaptions[fn] = captions[fn]
captions_json = toJSON(strippedCaptions)
f = open("captions.json", "w")
try:
f.write(captions_json)
finally:
f.close()
res_jsn = [invertedResDict(), resolutions]
resolutions_json = toJSON(res_jsn, None)
f = open("resolutions.json", "w")
try:
f.write(resolutions_json)
finally:
f.close()
info_json = toJSON(info)
f = open("info.json", "w")
try:
f.write(info_json)
finally:
f.close()
os.chdir(current_dir)
import zipfile as zf
SOURCE = r'<path_to_zip'
DESTINATION = r'<path_to_dest>'
with zf.ZipFile(SOURCE, 'r') as zf:
zf.extractall(DESTINATION)
zf.close() #cleanup
f2.close()
# Set it to be viewed "inline"
img1.add_header('Content-Disposition', 'inline', filename='Odin Jobseeker.png')
img2.add_header('Content-Disposition', 'inline', filename='Thor Job Hunter.png')
msg.attach(img1)
msg.attach(img2)
#
def zipper(zipname, files):
z = zipfile.ZipFile(zipname, 'w')
for f in files:
z.write(f)
z.close()
zipper("cv.zip", cvs)
zipfile = open("cv.zip","rb")
zip = MIMEBase('application', 'zip', name="cv.zip")
zip.set_payload(zipfile.read())
zipfile.close()
#
encoders.encode_base64(zip)
msg.attach(zip)
# File deletion
def delete_files(files):
for f in files:
os.remove(f)
files = [cvs, images]
delete_files(files)
# Send the message
s = smtplib.SMTP("blast.sit.rp.sg")
s.sendmail(sender, recipient, msg.as_string())
def __init__(
self,
project_name=None, # type: Optional[str]
workspace=None, # type: Optional[str]
log_code=True, # type: Optional[bool]
log_graph=True, # type: Optional[bool]
auto_param_logging=True, # type: Optional[bool]
auto_metric_logging=True, # type: Optional[bool]
parse_args=True, # type: Optional[bool]
auto_output_logging="default", # type: Optional[str]
log_env_details=True, # type: Optional[bool]
log_git_metadata=True, # type: Optional[bool]
log_git_patch=True, # type: Optional[bool]
disabled=False, # type: Optional[bool]
offline_directory=None, # type: Optional[str]
log_env_gpu=True, # type: Optional[bool]
log_env_host=True, # type: Optional[bool]
api_key=None, # type: Optional[str]
display_summary=None, # type: Optional[bool]
log_env_cpu=True, # type: Optional[bool]
display_summary_level=None, # type: Optional[int]
auto_weight_logging=None, # type: Optional[bool]
auto_log_co2=False, # type: Optional[bool]
auto_metric_step_rate=10, # type: Optional[int]
auto_histogram_tensorboard_logging=False, # type: Optional[bool]
auto_histogram_epoch_rate=1, # type: Optional[int]
auto_histogram_weight_logging=False, # type: Optional[bool]
auto_histogram_gradient_logging=False, # type: Optional[bool]
auto_histogram_activation_logging=False, # type: Optional[bool]
):
# type: (...) -> None
"""
Creates a new experiment and serialize it on disk. The experiment file will need to be
upload manually later to appears on the frontend.
Args:
project_name: Optional. Send your experiment to a specific project. Otherwise will be sent to `Uncategorized Experiments`.
If project name does not already exists Comet.ml will create a new project.
workspace: Optional. Attach an experiment to a project that belongs to this workspace
log_code: Default(True) - allows you to enable/disable code logging
log_graph: Default(True) - allows you to enable/disable automatic computation graph logging.
auto_param_logging: Default(True) - allows you to enable/disable hyper parameters logging
auto_metric_logging: Default(True) - allows you to enable/disable metrics logging
auto_metric_step_rate: Default(10) - controls how often batch metrics are logged
auto_histogram_tensorboard_logging: Default(False) - allows you to enable/disable automatic histogram logging
auto_histogram_epoch_rate: Default(1) - controls how often histograms are logged
auto_histogram_weight_logging: Default(False) - allows you to enable/disable automatic histogram logging of biases and weights
auto_histogram_gradient_logging: Default(False) - allows you to enable/disable automatic histogram logging of gradients
auto_histogram_activation_logging: Default(False) - allows you to enable/disable automatic histogram logging of activations
auto_output_logging: Default("default") - allows you to select
which output logging mode to use. You can pass `"native"`
which will log all output even when it originated from a C
native library. You can also pass `"simple"` which will work
only for output made by Python code. If you want to disable
automatic output logging, you can pass `False`. The default is
`"default"` which will detect your environment and deactivate
the output logging for IPython and Jupyter environment and
sets `"native"` in the other cases.
auto_log_co2: Default(True) - automatically tracks the CO2 emission of
this experiment if `codecarbon` package is installed in the environment
parse_args: Default(True) - allows you to enable/disable automatic parsing of CLI arguments
log_env_details: Default(True) - log various environment
information in order to identify where the script is running
log_env_gpu: Default(True) - allow you to enable/disable the
automatic collection of gpu details and metrics (utilization, memory usage etc..).
`log_env_details` must also be true.
log_env_cpu: Default(True) - allow you to enable/disable the
automatic collection of cpu details and metrics (utilization, memory usage etc..).
`log_env_details` must also be true.
log_env_host: Default(True) - allow you to enable/disable the
automatic collection of host information (ip, hostname, python version, user etc...).
`log_env_details` must also be true.
log_git_metadata: Default(True) - allow you to enable/disable the
automatic collection of git details
display_summary_level: Default(1) - control the summary detail that is
displayed on the console at end of experiment. If 0, the summary
notification is still sent. Valid values are 0 to 2.
disabled: Default(False) - allows you to disable all network
communication with the Comet.ml backend. It is useful when you
want to test to make sure everything is working, without actually
logging anything.
offline_directory: the directory used to save the offline archive
for the experiment.
"""
self.config = get_config()
self.api_key = get_api_key(
api_key, self.config
) # optional, except for on-line operations
if offline_directory is None:
offline_directory = self.config["comet.offline_directory"]
if offline_directory is None:
raise ValueError("OfflineExperiment needs an offline directory")
self.offline_directory = offline_directory
# Start and ends time
self.start_time = None
self.stop_time = None
self.mode = "create"
super(OfflineExperiment, self).__init__(
project_name=project_name,
workspace=workspace,
log_code=log_code,
log_graph=log_graph,
auto_param_logging=auto_param_logging,
auto_metric_logging=auto_metric_logging,
parse_args=parse_args,
auto_output_logging=auto_output_logging,
log_env_details=log_env_details,
log_git_metadata=log_git_metadata,
log_git_patch=log_git_patch,
disabled=disabled,
log_env_gpu=log_env_gpu,
log_env_host=log_env_host,
display_summary=display_summary,
display_summary_level=display_summary_level,
log_env_cpu=log_env_cpu,
auto_weight_logging=auto_weight_logging,
auto_log_co2=auto_log_co2,
auto_metric_step_rate=auto_metric_step_rate,
auto_histogram_epoch_rate=auto_histogram_epoch_rate,
auto_histogram_tensorboard_logging=auto_histogram_tensorboard_logging,
auto_histogram_weight_logging=auto_histogram_weight_logging,
auto_histogram_gradient_logging=auto_histogram_gradient_logging,
auto_histogram_activation_logging=auto_histogram_activation_logging,
)
if not self.disabled:
# Check that the offline directory is usable
try:
# Try to create the archive now
zipfile = self._get_offline_archive(self.offline_directory, self.id)
# Close the file handle, it will be reopened later
zipfile.close()
except (OSError, IOError) as exc:
raise InvalidOfflineDirectory(self.offline_directory, str(exc))
if self.disabled is not True:
if api_key is not None:
self._log_once_at_level(
logging.WARNING,
"api_key was given, but is ignored in OfflineExperiment(); remember to set when you upload",
)
elif self.api_key is not None:
self._log_once_at_level(
logging.INFO,
"COMET_API_KEY was set, but is ignored in OfflineExperiment(); remember to set when you upload",
)
self._start()
if self.alive is True:
self._report(event_name=EXPERIMENT_CREATED)
def EpubToTxt(file):
import os
import zipfile
import re
import html2text
from bs4 import BeautifulSoup
def PrettifyTxt(text):
lines = text.split('\n')
text = ''
for line in lines:
if line.split():
text = text + ' ' + line.strip() + '\n'
return text
filename = os.path.basename(file)
filebasename = os.path.splitext(filename)[0]
path = file.strip('/' + filename)
savepath = path + filebasename
zipfile = zipfile.ZipFile(file)
namelist = zipfile.namelist()
subfilelist = []
flag = {}
text = ''
for subfile in namelist:
flag1 = subfile.endswith('.html')
flag2 = subfile.endswith('.htm')
flag3 = subfile.endswith('.xhtml')
if flag1 or flag2 or flag3:
flag[subfile] = True
for subfile in namelist:
if subfile.endswith('.opf'):
folder = subfile.rstrip(os.path.basename(subfile))
opfs = zipfile.open(subfile)
opf = ''
for line in opfs:
opf = opf + str(line, 'utf-8')
left1 = re.search('<spine toc="ncx">', opf).span()[0]
left2 = re.search('<manifest>', opf).span()[0]
right1 = re.search('</spine>', opf).span()[1]
right2 = re.search('</manifest>', opf).span()[1]
ncx = opf[left1:right1]
manifest = opf[left2:right2]
ids = re.findall('id="(.*?)"', manifest)
hrefs = re.findall('href="(.*?)"', manifest)
idrefs = re.findall('<itemref idref="(.*?)"', ncx)
key = {}
for i in range(0, len(ids)):
key[ids[i]] = hrefs[i]
for idref in idrefs:
htmpath = folder + key[idref]
if htmpath in flag.keys() and flag[htmpath]:
htmopen = zipfile.open(htmpath)
soup = BeautifulSoup(htmopen, 'lxml')
text = text + soup.get_text()
flag[htmpath] = False
else:
pass
zipfile.close()
return PrettifyTxt(text)
# 定义备份目标
target_dir = 'D:\Transfer\SkyDrive\\backup'
# 用time包里的日期函数链接目标文件夹位置，作为每日不同的备份文件夹名称
today = target_dir + os.sep + time.strftime('%Y%m%d')
# 返回备份时间，写压缩包名字用
now = time.strftime('%H%M%S')
# 允许在文件名中产生一个注释
comment = input('Enter a comment --> ')
if len(comment) == 0: # 若无注释
target = today + os.sep + '文献翻译' + now + '.zip'
else: # 若有注释，把注释也置于文件名中
target = today + os.sep + '文献翻译' + now + '_' +\
comment.replace(' ', '_') + '.zip'
# 每日生成一个新的文件夹
if not os.path.exists(today):
os.mkdir(today)
print('Successfully created directory', today)
zipfile = zipfile.ZipFile(target,'w',compression=zipfile.ZIP_DEFLATED)
# 写入一个zip文件
trav(source) # 调用递归函数
zipfile.close() # 关闭之
# 输出一个提示
print('Successful backup to', target)
