R rvest html_attr 獲取元素屬性

html_attr(x, name, default = NA_character_)

html_attrs(x)

html <- minimal_html('<ul>
  <li><a href="https://a.com" class="important">a</a></li>
  <li class="active"><a href="https://c.com">b</a></li>
  <li><a href="https://c.com">b</a></li>
  </ul>')

html %>% html_elements("a") %>% html_attrs()
#> [[1]]
#>            href           class 
#> "https://a.com"     "important" 
#> 
#> [[2]]
#>            href 
#> "https://c.com" 
#> 
#> [[3]]
#>            href 
#> "https://c.com" 
#> 

html %>% html_elements("a") %>% html_attr("href")
#> [1] "https://a.com" "https://c.com" "https://c.com"
html %>% html_elements("li") %>% html_attr("class")
#> [1] NA       "active" NA      
html %>% html_elements("li") %>% html_attr("class", default = "inactive")
#> [1] "inactive" "active"   "inactive"