R rvest html_text 獲取元素文本

html_text(x, trim = FALSE)

html_text2(x, preserve_nbsp = FALSE)

# To understand the difference between html_text() and html_text2()
# take the following html:

html <- minimal_html(
  "<p>This is a paragraph.
    This another sentence.<br>This should start on a new line"
)

# html_text() returns the raw underlying text, which includes whitespace
# that would be ignored by a browser, and ignores the <br>
html %>% html_element("p") %>% html_text() %>% writeLines()
#> This is a paragraph.
#>     This another sentence.This should start on a new line

# html_text2() simulates what a browser would display. Non-significant
# whitespace is collapsed, and <br> is turned into a line break
html %>% html_element("p") %>% html_text2() %>% writeLines()
#> This is a paragraph. This another sentence.
#> This should start on a new line

# By default, html_text2() also converts non-breaking spaces to regular
# spaces:
html <- minimal_html("<p>x&nbsp;y</p>")
x1 <- html %>% html_element("p") %>% html_text()
x2 <- html %>% html_element("p") %>% html_text2()

# When printed, non-breaking spaces look exactly like regular spaces
x1
#> [1] "x y"
x2
#> [1] "x y"
# But aren't actually the same:
x1 == x2
#> [1] FALSE
# Which you can confirm by looking at their underlying binary
# representaion:
charToRaw(x1)
#> [1] 78 c2 a0 79
charToRaw(x2)
#> [1] 78 20 79