def _download(self, url, folder='', filename='', retried=0):
logger.info('Starting to download {0} ...'.format(url))
filename = filename if filename else os.path.basename(
urlparse(url).path)
base_filename, extension = os.path.splitext(filename)
try:
if os.path.exists(
os.path.join(folder,
base_filename.zfill(3) + extension)):
logger.warning('File: {0} exists, ignoring'.format(
os.path.join(folder,
base_filename.zfill(3) + extension)))
return 1, url
with open(os.path.join(folder,
base_filename.zfill(3) + extension),
"wb") as f:
i = 0
while i < 10:
try:
response = request('get',
url,
stream=True,
timeout=self.timeout)
except Exception as e:
i += 1
if not i < 10:
logger.critical(str(e))
return 0, None
continue
break
if response.status_code != 200:
raise NhentaiImageNotExistException
length = response.headers.get('content-length')
if length is None:
f.write(response.content)
else:
for chunk in response.iter_content(2048):
f.write(chunk)
except (requests.HTTPError, requests.Timeout) as e:
if retried < 3:
logger.warning('Warning: {0}, retrying({1}) ...'.format(
str(e), retried))
return 0, self._download(url=url,
folder=folder,
filename=filename,
retried=retried + 1)
else:
return 0, None
except NhentaiImageNotExistException as e:
os.remove(os.path.join(folder, base_filename.zfill(3) + extension))
return -1, url
except Exception as e:
logger.critical(str(e))
return 0, None
return 1, url
def _download(self, url, folder='', filename='', retried=0):
logger.info('Start downloading: {0} ...'.format(url))
filename = filename if filename else os.path.basename(urlparse(url).path)
base_filename, extension = os.path.splitext(filename)
try:
with open(os.path.join(folder, base_filename.zfill(3) + extension), "wb") as f:
response = request('get', url, stream=True, timeout=self.timeout)
if response.status_code != 200:
raise NhentaiImageNotExistException
length = response.headers.get('content-length')
if length is None:
f.write(response.content)
else:
for chunk in response.iter_content(2048):
f.write(chunk)
except (requests.HTTPError, requests.Timeout) as e:
if retried < 3:
logger.warning('Warning: {0}, retrying({1}) ...'.format(str(e), retried))
return 0, self._download(url=url, folder=folder, filename=filename, retried=retried+1)
else:
return 0, None
except NhentaiImageNotExistException as e:
os.remove(os.path.join(folder, base_filename.zfill(3) + extension))
return -1, url
except Exception as e:
logger.critical(str(e))
return 0, None
return 1, url
def _download(self, url, folder='', filename='', retried=False):
logger.info('Start downloading: {0} ...'.format(url))
filename = filename if filename else os.path.basename(
urlparse(url).path)
base_filename, extension = os.path.splitext(filename)
try:
with open(os.path.join(folder,
base_filename.zfill(3) + extension),
"wb") as f:
response = request('get',
url,
stream=True,
timeout=self.timeout)
length = response.headers.get('content-length')
if length is None:
f.write(response.content)
else:
for chunk in response.iter_content(2048):
f.write(chunk)
except requests.HTTPError as e:
if not retried:
logger.error('Error: {0}, retrying'.format(str(e)))
return self._download(url=url,
folder=folder,
filename=filename,
retried=True)
else:
return None
except Exception as e:
logger.critical(str(e))
return None
return url
