R rvest html_element 从 HTML 文档中选择元素

html_element(x, css, xpath)

html_elements(x, css, xpath)

html <- minimal_html("
  <h1>This is a heading</h1>
  <p id='first'>This is a paragraph</p>
  <p class='important'>This is an important paragraph</p>
")

html %>% html_element("h1")
#> {html_node}
#> <h1>
html %>% html_elements("p")
#> {xml_nodeset (2)}
#> [1] <p id="first">This is a paragraph</p>
#> [2] <p class="important">This is an important paragraph</p>
html %>% html_elements(".important")
#> {xml_nodeset (1)}
#> [1] <p class="important">This is an important paragraph</p>
html %>% html_elements("#first")
#> {xml_nodeset (1)}
#> [1] <p id="first">This is a paragraph</p>

# html_element() vs html_elements() --------------------------------------
html <- minimal_html("
  <ul>
    <li><b>C-3PO</b> is a <i>droid</i> that weighs <span class='weight'>167 kg</span></li>
    <li><b>R2-D2</b> is a <i>droid</i> that weighs <span class='weight'>96 kg</span></li>
    <li><b>Yoda</b> weighs <span class='weight'>66 kg</span></li>
    <li><b>R4-P17</b> is a <i>droid</i></li>
  </ul>
")
li <- html %>% html_elements("li")

# When applied to a node set, html_elements() returns all matching elements
# beneath any of the inputs, flattening results into a new node set.
li %>% html_elements("i")
#> {xml_nodeset (3)}
#> [1] <i>droid</i>
#> [2] <i>droid</i>
#> [3] <i>droid</i>

# When applied to a node set, html_element() always returns a vector the
# same length as the input, using a "missing" element where needed.
li %>% html_element("i")
#> {xml_nodeset (4)}
#> [1] <i>droid</i>
#> [2] <i>droid</i>
#> [3] <NA>
#> [4] <i>droid</i>
# and html_text() and html_attr() will return NA
li %>% html_element("i") %>% html_text2()
#> [1] "droid" "droid" NA      "droid"
li %>% html_element("span") %>% html_attr("class")
#> [1] "weight" "weight" "weight" NA