Last active
February 27, 2018 17:29
-
-
Save mccalluc/c21d15b3b1784a671fc3d0092c380a03 to your computer and use it in GitHub Desktop.
Download files from Princeton BII, zip, and move to S3
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
.idea/ |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
import argparse | |
import requests | |
import re | |
import shutil | |
from urllib.parse import urlencode | |
from tempfile import mkdtemp | |
import os | |
import urllib3 | |
import zipfile | |
# from boto.s3.key import Key | |
urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning) | |
# TODO: "verify=False" below because "certificate verify failed" | |
def arg_parser(): | |
parser = argparse.ArgumentParser( | |
description='Download files from BII, zip, and move to S3') | |
parser.add_argument('--study_id', type=str, required=True) | |
#parser.add_argument('--bucket', type=str, required=True) | |
return parser | |
def isa_urls(id): | |
query = urlencode({'studyId': id}) | |
front_url = 'https://pentacon-bii.princeton.edu/study.seam?{}'.format(query) | |
front_html = requests.get(front_url, verify=False).text | |
repo_url = re.search(r'href="([^"]+submission_repo[^"]+)', front_html).group(1) | |
print(repo_url) | |
repo_html = requests.get(repo_url, verify=False).text | |
isa_paths = re.findall(r'href="([^"]+\.txt)"', repo_html) | |
print(isa_paths) | |
return [os.path.join(repo_url, path) for path in isa_paths] | |
def download(urls): | |
dir = mkdtemp() | |
for url in urls: | |
local_filename = os.path.join(dir, url.split('/')[-1]) | |
r = requests.get(url, stream=True, verify=False) | |
with open(local_filename, 'wb') as f: | |
shutil.copyfileobj(r.raw, f) | |
return dir | |
def zip(id, dir): | |
os.chdir(dir) | |
paths = os.listdir(dir) | |
zip_filename = '{}.zip'.format(id) | |
with zipfile.ZipFile(zip_filename, mode='w') as z: | |
for path in paths: | |
z.write(path) | |
return os.path.join(dir, zip_filename) | |
# def upload(filename, bucket): | |
# Key(bucket=bucket) | |
def main(args): | |
id = args.study_id | |
urls = isa_urls(id) | |
dir = download(urls) | |
zip_filename = zip(id, dir) | |
print(zip_filename) | |
if __name__ == '__main__': | |
parser = arg_parser() | |
args = parser.parse_args() | |
main(args) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment