edsu

column	before	after
title	891351 (93%)	804262 (99.9%)
pub_year	893340 (99.8%)	803930 (99.9%)
open_access	589300 (65.8%)	618291 (76.8%)
apc	265024 (29.6%)	274282 (34.0%)
types	894525 (99.9%)	804498 (100%)
publisher	638311 (71.3%)	588595 (73.15%)
doi	553661 (61.8%)	563544 (70.0%)

edsu

edsu

import requests
import json

print(len(requests.get("https://api.openalex.org/w4223476900").json()["authorships"]))
print(len(requests.get("https://api.openalex.org/w4223476900?data-version=1").json()["authorships"]))

edsu

#!/usr/bin/env python3

#
# This program will introspect on an OpenAlex API filter call and try to
# determine what record in the cursored result set is causing a problem.
#
# ./openalexbug.py https://api.openalex.org/works?filter=author.id:https://openalex.org/A5003671931&cursor=&per-page=200
# problem record: https://openalex.org/W3200281942
# 121 records
#

edsu

openpgp4fpr:DD11F92F1E44644183C06961D012FF557AFFF80A

edsu

#!/usr/bin/env python3

#
# This program demonstrates using the Tableau REST API to print out our embedding settings. 
# To run it you will need to create a Personal Access Token by:
#
# 1. visiting https://tableau-uat.stanford.edu/
# 2. clicking on your user name in the top right
# 3. select "My Settings"
# 4. scrolling to the "Personal Access Tokens" section

edsu

import dotenv
from podbucket import oai
from podbucket.oai import XML_NS

dotenv.load_dotenv()

for count, rec in enumerate(oai.list_records("503")):
    ds = rec.find(".//oai:header/oai:datestamp", namespaces=XML_NS).text
    print(ds, count)

edsu

If you execute ./run.sh browsertrix-crawler will be started up to crawl https://www.trm.dk/nyheder and run a behaviour to fetch all the page results and then feed all the discovered URLs to the crawl queue.

edsu

import requests
import pandas

url = "https://flotilla-orpin.vercel.app/api/vessel"

df = pandas.DataFrame.from_records(requests.get(url).json()["vessels"]["232057367"]["positions"]) 

df.last_position_UTC = pandas.to_datetime(df.last_position_UTC)

print(df)

edsu

docker run \
    --publish 9037:9037 \
    -v $PWD/crawls:/crawls/ \
    webrecorder/browsertrix-crawler crawl \
    --seeds https://www.womenonweb.org/af/ \
    --seeds https://www.womenonweb.org/ar/ \
    --seeds https://www.womenonweb.org/de/ \
    --seeds https://www.womenonweb.org/en/ \
    --seeds https://www.womenonweb.org/es/ \
    --seeds https://www.womenonweb.org/fa/ \