使用R中的正则表达式将一列分割为多列

您可以使用for循环来提取服务和相应的项.在result中，项目之间用,分隔.

library(tidyverse)
library(rvest)

url <- "https://npin.cdc.gov/search?=type%3Aorganization&page=0"
content <- read_html(url)

services <- content %>% html_nodes(".services-fieldset")
org_name <- content %>% html_nodes(".block-field-blocknodeorganizationtitle") %>% html_text2()


result <- data.frame(org_name = as.integer(), service = as.character(), item = as.character())

for (i in 1:length(services)) {
  temp <- services[i] %>% html_nodes(".field__items")
  for (j in 2:length(temp)) {
    label <- temp[j] %>% html_nodes(".field-label") %>% html_text() %>% gsub(":", "", .)
    items <- temp[j] %>% html_nodes(".field__item") %>% html_text()
    result[nrow(result) +1, ] <- c(org_name[i], label, paste0(items, collapse = ","))
  }
}

result |> tibble()
#> # A tibble: 32 × 3
#>    org_name                          service                     item           
#>    <chr>                             <chr>                       <chr>          
#>  1 Eastport Health Care Incorporated Testing Services            Gonorrhea Test…
#>  2 Eastport Health Care Incorporated Care and Treatment Services Family Plannin…
#>  3 Alamosa County Public Health      Testing Services            TB Testing     
#>  4 Alamosa County Public Health      Care and Treatment Services Mpox Vaccine,H…
#>  5 Alamo Navajo Health Center        Testing Services            TB Testing,Gon…
#>  6 Alamo Navajo Health Center        Prevention Services         TB Prevention/…
#>  7 Alamo Navajo Health Center        Care and Treatment Services Family Plannin…
#>  8 AIDS Resource Group               Testing Services            Hepatitis C Te…
#>  9 AIDS Resource Group               Prevention Services         STD/STI Preven…
#> 10 AIDS Resource Group               Support Services            Support Groups…
#> # ℹ 22 more rows

^{创建于2024—03—14，reprex v2.1.0}