knbknb

######  Spider Websites with Wget  20 Practical Examples
# original, from 2019: 
# https://www.labnol.org/software/wget-command-examples/28750/
######  Spider Websites with Wget  20 Practical Examples

# wget is extremely powerful, but like with most other command line programs, 
# the plethora of options it supports can be intimidating to new users. 
# Thus what we have here are a collection of wget commands that you can use
# to accomplish common tasks from downloading single files to mirroring entire websites. 
# It will help if you can read through the wget manual but for the busy souls,

knbknb

# show all graphs accessiblefrom a SPARQL endpoint
# no "base" prefix is needed
#
#
# from anzograph tutorial.
# query works in anzograph running on localhost,
# but not on dbpedia.org, wikidata and other public endpoints
# on dbpedia running on localhost:8890/sparql this returns 54261 rows
SELECT DISTINCT ?graph
WHERE {

knbknb

#!/usr/bin/env bash
##### Query Wikidata Entities from bash - alternative
# returns only very basic graphs NOT via the SPARQL endpoint
# knb 2020
WDURL='https://www.wikidata.org/w/api.php'
WDQS='action=wbgetentities&format=json&sites=enwiki'
WGE="$WDURL?$WDQS"
echo $WGE >&2
#curl -s: means --silent
WDITEM=Solar_System

knbknb

#  more RDF prefixes, also very common
base <http://localhost:8180/sparql/> # anzograph
PREFIX : <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>
PREFIX skos: <http://www.w3.org/2004/02/skos/core#>
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
PREFIX owl: <http://www.w3.org/2002/07/owl#>

PREFIX hint: <http://www.bigdata.com/queryHints#>

knbknb

<!-- saved here as a gist, for reference in case it gets changed or is taken offline -->
<?xml version="1.0" encoding="UTF-8"?>
<xs:schema xmlns:xs="http://www.w3.org/2001/XMLSchema" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://schema.igsn.org/description/1.0" targetNamespace="http://schema.igsn.org/description/1.0" elementFormDefault="qualified" xml:lang="EN" version="1.0">

  <xs:include schemaLocation="include/accessType.xsd"/>
  <xs:include schemaLocation="include/collectionType.xsd"/>
  <xs:include schemaLocation="include/contributorType.xsd"/>
  <xs:include schemaLocation="include/featureType.xsd"/>
  <xs:include schemaLocation="include/geometryType.xsd"/>
  <xs:include schemaLocation="include/identifierType.xsd"/>

knbknb

# https://www.wikidata.org/wiki/Wikidata:SPARQL_query_service/query_optimization
# if previous statement is rangeSafe , add:
hint:Prior hint:rangeSafe true.

# This tells the optimizer that ?dateOfBirth doesn’t mix 
# dates, strings, integers or other data types, 
# which simplifies the range comparison. 
# This is almost always true on Wikidata, 
# so the main reason not to use this optimizer hint all the time is
#  that it’s a bit inconvenient. 

knbknb

# from someone's Twitter timeline, Dec 2022
# Wikidata: search for emigrants during Nazi era
SELECT DISTINCT ?category ?person ?description  WHERE { 
  ?category a skos:Concept . 
  ?category skos:prefLabel ?label . 
  FILTER (CONTAINS(?label, "Zeit des Nationalsozialismus")) 
?person dct:subject ?category. 
?person rdfs:comment ?description . 
      FILTER (LANG(?description) = 'de') . }

knbknb

# for more prefixes
# (wikidata, common)
# see also https://gist.github.com/knbknb/081ee7af40a01a0a365d0df5f49acd7c
# 
# "Notable works" of a writer
#
PREFIX :     <http://dbpedia.org/resource/>
PREFIX rdf:  <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
PREFIX dbo:  <http://dbpedia.org/ontology/>

knbknb

# Writing Frictionless R Package Wrappers — Building A Basic R Package
# https://rud.is/b/2020/01/03/writing-frictionless-r-package-wrappers-building-a-basic-r-package/#fnref-12609-2

# in any RStudio R Console session
devtools::create("~/packages/THE-PACKAGE-NAME")

# in the newly created package RStudio R Console session:
usethis::use_mit_license()       # need a LICENSE file
usethis::use_roxygen_md()        # use {roxygen2} for documentation and configuration
usethis::use_package_doc()       # setup a package-level manual page

knbknb

Bash COurse on edX

Shell Command Language

Which option of the uniq command allows you to specify the number of fields to ignore in its comparisons?

uniq -f

  -f, --skip-fields=N   avoid comparing the first N fields