Created
August 25, 2022 11:59
-
-
Save cthoyt/ac2a95058f43a4845df075514cfca061 to your computer and use it in GitHub Desktop.
Extract Journal of Cheminformatics DOIs from https://github.com/egonw/jcheminform-kb
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
"""Get Journal of Cheminformatics DOIs.""" | |
import requests | |
import pystow | |
MODULE = pystow.module("jcheminf", "volumes") | |
USER = "egonw" # alternative use first-party jcheminform if it ever gets updated | |
REPO = "jcheminform-kb" | |
BRANCH = "main" | |
PREFIX = "https://doi.org/10.1186/" | |
def main(): | |
response = requests.get(f"https://api.github.com/repos/{USER}/{REPO}/git/trees/{BRANCH}?recursive=1") | |
response.raise_for_status() | |
results = set() | |
for element in response.json()["tree"]: | |
if not element["path"].endswith(".ttl"): | |
continue | |
graph = MODULE.ensure_rdf( | |
url=f'https://raw.githubusercontent.com/{USER}/{REPO}/{BRANCH}/{element["path"]}', | |
parse_kwargs={"format": "turtle"}, | |
) | |
for entity in graph.subjects(): | |
if entity.startswith(PREFIX): | |
results.add(entity.removeprefix(PREFIX)) | |
results = sorted(results) | |
MODULE.join(name="dois.txt").write_text("\n".join(results)) | |
if __name__ == '__main__': | |
main() |
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
1758-2946-1-1 | |
1758-2946-1-10 | |
1758-2946-1-11 | |
1758-2946-1-12 | |
1758-2946-1-13 | |
1758-2946-1-14 | |
1758-2946-1-15 | |
1758-2946-1-16 | |
1758-2946-1-17 | |
1758-2946-1-18 | |
1758-2946-1-19 | |
1758-2946-1-2 | |
1758-2946-1-20 | |
1758-2946-1-21 | |
1758-2946-1-22 | |
1758-2946-1-3 | |
1758-2946-1-4 | |
1758-2946-1-5 | |
1758-2946-1-6 | |
1758-2946-1-7 | |
1758-2946-1-8 | |
1758-2946-1-9 | |
1758-2946-2-1 | |
1758-2946-2-10 | |
1758-2946-2-11 | |
1758-2946-2-2 | |
1758-2946-2-3 | |
1758-2946-2-4 | |
1758-2946-2-5 | |
1758-2946-2-6 | |
1758-2946-2-7 | |
1758-2946-2-8 | |
1758-2946-2-9 | |
1758-2946-3-1 | |
1758-2946-3-10 | |
1758-2946-3-11 | |
1758-2946-3-12 | |
1758-2946-3-13 | |
1758-2946-3-14 | |
1758-2946-3-15 | |
1758-2946-3-16 | |
1758-2946-3-17 | |
1758-2946-3-18 | |
1758-2946-3-19 | |
1758-2946-3-2 | |
1758-2946-3-20 | |
1758-2946-3-21 | |
1758-2946-3-22 | |
1758-2946-3-23 | |
1758-2946-3-24 | |
1758-2946-3-25 | |
1758-2946-3-26 | |
1758-2946-3-27 | |
1758-2946-3-28 | |
1758-2946-3-29 | |
1758-2946-3-3 | |
1758-2946-3-30 | |
1758-2946-3-31 | |
1758-2946-3-32 | |
1758-2946-3-33 | |
1758-2946-3-34 | |
1758-2946-3-35 | |
1758-2946-3-36 | |
1758-2946-3-37 | |
1758-2946-3-38 | |
1758-2946-3-39 | |
1758-2946-3-4 | |
1758-2946-3-40 | |
1758-2946-3-41 | |
1758-2946-3-42 | |
1758-2946-3-43 | |
1758-2946-3-44 | |
1758-2946-3-45 | |
1758-2946-3-46 | |
1758-2946-3-47 | |
1758-2946-3-48 | |
1758-2946-3-49 | |
1758-2946-3-5 | |
1758-2946-3-50 | |
1758-2946-3-51 | |
1758-2946-3-52 | |
1758-2946-3-53 | |
1758-2946-3-54 | |
1758-2946-3-6 | |
1758-2946-3-7 | |
1758-2946-3-8 | |
1758-2946-3-9 | |
s13321-018-0323-6 | |
s13321-018-0324-5 | |
s13321-018-0325-4 | |
s13321-018-0326-3 | |
s13321-018-0327-2 | |
s13321-019-0328-9 | |
s13321-019-0329-8 | |
s13321-019-0330-2 | |
s13321-019-0331-1 | |
s13321-019-0332-0 | |
s13321-019-0333-z | |
s13321-019-0334-y | |
s13321-019-0335-x | |
s13321-019-0336-9 | |
s13321-019-0337-8 | |
s13321-019-0338-7 | |
s13321-019-0339-6 | |
s13321-019-0340-0 | |
s13321-019-0341-z | |
s13321-019-0342-y | |
s13321-019-0343-x | |
s13321-019-0344-9 | |
s13321-019-0345-8 | |
s13321-019-0346-7 | |
s13321-019-0347-6 | |
s13321-019-0348-5 | |
s13321-019-0349-4 | |
s13321-019-0350-y | |
s13321-019-0351-x | |
s13321-019-0352-9 | |
s13321-019-0353-8 | |
s13321-019-0354-7 | |
s13321-019-0355-6 | |
s13321-019-0356-5 | |
s13321-019-0357-4 | |
s13321-019-0358-3 | |
s13321-019-0359-2 | |
s13321-019-0360-9 | |
s13321-019-0361-8 | |
s13321-019-0362-7 | |
s13321-019-0363-6 | |
s13321-019-0364-5 | |
s13321-019-0365-4 | |
s13321-019-0366-3 | |
s13321-019-0367-2 | |
s13321-019-0368-1 | |
s13321-019-0369-0 | |
s13321-019-0370-7 | |
s13321-019-0371-6 | |
s13321-019-0372-5 | |
s13321-019-0373-4 | |
s13321-019-0374-3 | |
s13321-019-0375-2 | |
s13321-019-0376-1 | |
s13321-019-0377-0 | |
s13321-019-0378-z | |
s13321-019-0380-5 | |
s13321-019-0381-4 | |
s13321-019-0382-3 | |
s13321-019-0383-2 | |
s13321-019-0384-1 | |
s13321-019-0385-0 | |
s13321-019-0386-z | |
s13321-019-0387-y | |
s13321-019-0388-x | |
s13321-019-0389-9 | |
s13321-019-0390-3 | |
s13321-019-0391-2 | |
s13321-019-0392-1 | |
s13321-019-0393-0 | |
s13321-019-0394-z | |
s13321-019-0395-y | |
s13321-019-0396-x | |
s13321-019-0397-9 | |
s13321-019-0398-8 | |
s13321-019-0399-7 | |
s13321-019-0400-5 | |
s13321-019-0401-4 | |
s13321-019-0402-3 | |
s13321-019-0403-2 | |
s13321-020-00448-1 | |
s13321-020-00464-1 | |
s13321-020-00467-y | |
s13321-020-00474-z | |
s13321-020-00478-9 | |
s13321-021-00489-0 | |
s13321-021-00491-6 | |
s13321-021-00515-1 | |
s13321-021-00520-4 | |
s13321-021-00521-3 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment