R/load_test_urls.R

Defines functions load_test_urls

Documented in load_test_urls

#' @title
#' Load sample test URLs from the 1023-EZ forms
#' @description
#' This functions loads in 20 test URLs from the 1023-EZ forms. These URLs are a sample of the entire URLs provided
#' intended to check the functionality of the the other URLs cleaning and scraping functions in the package.
#' @return A data frame of test URLs
#' @export
load_test_urls <- function(){

  sample.urls <<-
	structure(list(EIN = c("01-0278788", "01-0468034", "01-0512631",
	"01-0531578", "01-0533351", "01-0604316", "01-0716774", "01-0764856",
	"01-0791209", "01-0868557", "01-0900532", "01-0963519", "02-0508950",
	"02-0538937", "02-0594382", "02-0653283", "02-0729067", "02-0760556",
	"02-0764719", "02-0785015"),

	ORGNAME = c("GOODWINS MILLS FIREFIGHTERS RELIEFASSOCIATION",
	"MAINE WELFARE DIRECTORS ASSOCIATION ", "MAINE MYCOLOGICAL ASSOCIATION INC ",
	"BUCKSPORT AREA CULTURAL ARTS SOCIETY- BACAS", "PORTLAND RUGBY FOOTBALL CLUB ",
	"KENNESAW MOUNTAIN HIGH SCHOOL TRACKFIELD BOOSTER CLUB INC",
	"WALNUT BEND ELEMENTARY SCHOOL PARENT-TEACHER ORGANIZATION",
	"FLORIDA CERT ASSOCIATION", "LADY EAGLE BASKETBALL BOOSTER CLUB",
	"GRAND FORKS DOG TRAINING CLUB", "YOUTH OF UNITY Y O U INC",
	"LAKEVILLE YOUTH FOOTBALL  CHEERLEADING", "GATE CITY HARLEY OWNERS GROUP",
	"FOREST PRESERVE USERS INC", "THE HERITAGE EDUCATION GROUP",
	"HABITAT FOR HUMANITY OF ELLIS COUNTY INC", "GO SOUNDS PAA INC",
	"NORTHEAST TEXAS EMMAUS INC", "CHIPPEWA FALLS CARDINAL HOOPS",
	"JOE UFF CANCER FOUNDATION INC "),

	ORGURL = c("HTTP://GMFD.ORG/GMFRA/GMFRAINDEX.HTM",
	"WWW.MAINEWELFAREDIRECTORS.ORG", "MAINELYMUSHROOMS.ORG", "WWW.BACASMAINE.ORG",
	"WWW.PORTLANDRFC.COM", "WWW.KMHSTRACKFIELD.COM", "WWW.WBE-PTO.ORG",
	"HTTP://WWW.FLACERTASSOCIATION.ORG", "WWW.LADYEAGLEBASKETBALL.NET",
	"GRANDFORKSDOGTRAININGCLUB.ORG", "WWW.UNITYOFYOUTH.ORG", "HTTP://WWW.LVYOUTH.COM",
	"GATECITYHOG.COM", "WWW.FORESTPRESERVEUSERSSNOWCLUB.COM", "WWW.HERITAGEEDUCATIONGROUP.ORG",
	"HTTPS://WWW.FACEBOOK.COM/HFHEC", "WWW.GOSOUNDSINC.COM", "WWW.NETEMMAUS.ORG",
	"WWW.CARDINALHOOPS.ORG", "WWW.UFFISTOUGH.COM")), class = "data.frame", row.names = c(NA,
	-20L))

}
Nonprofit-Open-Data-Collective/webscraper documentation built on July 19, 2023, 6:09 p.m.