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

edsu

import csv
import sys
from itertools import batched

import pyarrow
from pyarrow.parquet import ParquetWriter

csv.field_size_limit(sys.maxsize)

def csv_to_parquet(csv_file, parquet_file, batch_size=10_000):

edsu

.env

edsu

import requests

author_id = 'https://openalex.org/A5067004024'

url = 'https://api.openalex.org/works'

params = {
    'filter': f'author.id:{author_id}',
    'cursor': '*'
}

edsu

#!/usr/bin/env python3

"""
Run this program with an institution name and see the institutions and the count
of publications in OpenAlex.

$ ./openalex_counts "stanford"

Stanford University (I97018004): 430550
Stanford Medicine (I4210137306): 32576

edsu

edsu

{
  "l": "1",
  "p": "https://lh3.googleusercontent.com/-XdUIqdMkCWA/AAAAAAAAAAI/AAAAAAAAAAA/4252rscbv5M/s64-c-mo/photo.jpg",
  "r": [
    {
      "t": "The Internet Archive and the socio-technical construction of historical facts",
      "u": "https://scholar.google.com/scholar_url?url=https://www.tandfonline.com/doi/abs/10.1080/24701475.2018.1455412&hl=en&sa=T&oi=gsr-r&ct=res&cd=0&d=3272375975175528132&ei=YBH7ZeXNA4Cb6rQPmrOdoA8&scisig=AFWwaeb_dRhXurIfWX0NXA2y4G9I",
      "x": "",
      "m": "A Ben-David, A Amram - Internet Histories, 2018",
      "s": "This article analyses the socio-technical epistemic processes behind the construction of historical facts by the Internet Archive Wayback Machine (IAWM). Grounded in theoretical debates in Science and Technology Studies about digital and algorithmic platforms as “black boxes”, this article uses provenance information and other data traces provided by the IAWM to uncover specific epistemic processes embedded at its back-end, through a case study on the archiv

edsu

filename	count
data.zip	22397
data_EPSG_4326.zip	22397
preview.jpg	22397
index_map.json	147
Beechey_WGS.tif.xml	1
Beechey_WGS-iso19139.xml	1
Beechey_WGS-fgdc.xml	1
bathy20.txt	1

edsu

#!/usr/bin/env python3

"""
A small command line tool to get the JSON-LD for a Library of Congress authority
record by first looking up the authority as a string using the label lookup
service and then getting the JSON-LD for the authority and writing it out using
a JSON-LD frame where the SKOS is the default vocabulary.
"""

import sys

edsu

#!/usr/bin/env python3

import sys
import requests

title = sys.argv[1]
api_url = "https://api.crossref.org/works"

response = requests.get(api_url, params={"query.title": title})