edsu

edsu

research.noaa.gov
epic.noaa.gov
adp.noaa.gov
ci.noaa.gov
oeab.noaa.gov
orta.research.noaa.gov
testbeds.noaa.gov
qosap.research.noaa.gov
oss.research.noaa.gov
eeo.oar.noaa.gov

edsu

#!/usr/bin/env python3

import fileinput
import re
import subprocess
from functools import cache


@cache
def ips(hostname):

edsu

Traceback (most recent call last):
  File "/Users/edsu/.pyenv/versions/3.13.0/bin/sciop", line 8, in <module>
    sys.exit(_main())
             ~~~~~^^
  File "/Users/edsu/Projects/sciop/src/sciop/cli/main.py", line 16, in _main
    main(max_content_width=100)
    ~~~~^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/edsu/.pyenv/versions/3.13.0/lib/python3.13/site-packages/click/core.py", line 1161, in __call__
    return self.main(*args, **kwargs)
           ~~~~~~~~~^^^^^^^^^^^^^^^^^

edsu

#!/usr/bin/env python3

# The program will read WARC or WACZ data looking for Browsertrix text records
# and print them out as files using the archived URL as the path.
#
# You can run it right here from Gist using pipx:
#
#     pipx run https://gist.githubusercontent.com/edsu/89bd2844b9d3d4536e68956b3a16eaef/raw/warc_text.py file1.warc.gz file2.warc.gz
#
# If you give it a WACZ file it will read any WARC files contained in the WACZ:

edsu

Diagram:

flowchart TB
  
  subgraph Harvest-by-ORCID
    direction RL
    Dimensions-by-ORCID
    OpenAlex-by-ORCID
 PubMed-by-ORCID

edsu

#!/usr/bin/env python3

# This program will fetch the first page of recently updated Library of Congress
# Subject Headings from id.loc.gov and print out the MARC records for them.
# 
# /// script
# dependencies = ["requests", "pymarc"]
# ///
#
# see PEP 723

edsu

#!/usr/bin/env python3

import getpass

print(f"Hello {getpass.getuser()}!")

edsu

#!/usr/bin/env -S pipx run

# This program walks through the URLs in the sitemap and checks to see if they
# are in the Internet Archive Wayback Machine.
#
# You can run it like:
#
#     pipx run data-usaid-gov-check.py > results.csv
#
#

edsu

#!/usr/bin/env python3

"""
Look up a URL in swap.stanford.edu and print out the collections and crawl
SDR object identifiers that contain a snapshot of the URL.
"""

import sys
import json
import collections