def download_pdf_file(url: str,
filename: str,
filepath: str = '.',
progress: bool = False) -> None:
"""
This function downloads a PDF from a given DOI.
@:param
----------
url : url
Download url for the article.
filename : str
The filename for the PDF.
filepath : str
The path to store the downloaded PDF.
progress : bool
Whether the progress of the API call should be printed out or not.
"""
try:
headers = {"User-Agent": "python"}
r = requests.get(url, stream=url, headers=headers)
if r.status_code == 200:
file_size = int(r.headers.get('content-length', 0))
block_size = 1024
path = os.path.join(filepath, filename)
if not os.path.exists(filepath):
os.makedirs(filepath)
with open(path, 'wb') as file:
chunk_size = 0
for chunk in r.iter_content(block_size):
if progress and file_size > 0:
chunk_size += len(chunk)
Unpywall._progress(chunk_size / file_size)
file.write(chunk)
else:
logger.warning(
"Not able to download file, Http Response: {}".format(
r.status_code))
except ConnectionError:
logger.warning('Connection error received, will retry after 10 secs')
sleep(10)
Unpywall.download_pdf_file(url, filename, filepath)
except Exception:
logger.warning('Rethrowing error')
raise
def test_progress(self, Unpywall, capfd):
Unpywall._progress(0.5)
captured = capfd.readouterr()
assert len(captured.out) > 0
