All geek questions in one place

Scraper with rvest - complete with NA when there is no tag

I want to parse this HTML and get the following elements from it:

a) p, p class: "normal_encontrado".
b) divs class: "price".

Sometimes a tag is pmissing from some products. If so, it should be added to the vector that collects text from these nodes NA.

The idea is to have 2 vectors with the same length and make them after combining data.frame. Any ideas?

HTML part:

<html>
<head></head>
<body>

<div class="product_price" id="product_price_186251">
  <p class="normal_encontrado">
    S/. 2,799.00
  </p>

  <div id="WC_CatalogEntryDBThumbnailDisplayJSPF_10461_div_10" class="price">
    S/. 2,299.00
  </div>    
</div>

<div class="product_price" id="product_price_232046">
  <div id="WC_CatalogEntryDBThumbnailDisplayJSPF_10461_div_10" class="price">
    S/. 4,999.00
  </div>
</div>
</body>
</html>

R Code:

library(rvest)

page_source <- read_html("r.html")

r.precio.antes <- page_source %>%
html_nodes(".normal_encontrado") %>%
html_text()

r.precio.actual <- page_source %>%
html_nodes(".price") %>%
html_text()
+4
source share
4 answers

, rvest (0). , , div.product_price, :

pacman::p_load("rvest", "dplyr")

get_prices <- function(node){
  r.precio.antes <- html_nodes(node, 'p.normal_encontrado') %>% html_text
  r.precio.actual <- html_nodes(node, 'div.price') %>% html_text

  data.frame(
    precio.antes = ifelse(length(r.precio.antes)==0, NA, r.precio.antes),
    precio.actual = ifelse(length(r.precio.actual)==0, NA, r.precio.actual), 
    stringsAsFactors=F
  )

}

doc <- read_html('test.html') %>% html_nodes("div.product_price")
lapply(doc, get_prices) %>%
  rbind_all

: , script html-.

+3

XML, xmlTreeParse, xpathSApply product_price class div. node div p. m DF, , , , , . . , p .

# input

Lines <- '<html>
<head></head>
<body>

<div class="product_price" id="product_price_186251">
  <p class="normal_encontrado">
    S/. 2,799.00
  </p>

  <div id="WC_CatalogEntryDBThumbnailDisplayJSPF_10461_div_10" class="price">
    S/. 2,299.00
  </div>    
</div>

<div class="product_price" id="product_price_232046">
  <div id="WC_CatalogEntryDBThumbnailDisplayJSPF_10461_div_10" class="price">
    S/. 4,999.00
  </div>
</div>
</body>
</html>'

# code to read input and produce a data.frame

library(XML)
doc <- xmlTreeParse(Lines, asText = TRUE, useInternalNodes = TRUE)

m <- xpathSApply(doc, "//div[@class = 'product_price']", function(node) {
  list(p = xmlValue(node[["p"]]), div = xmlValue(node[["div"]])) })

DF <- as.data.frame(t(m), stringsAsFactors = FALSE) # rework into data frame
DF[] <- lapply(DF, function(x) as.numeric(gsub("[^.0-9]|[.]\\D", "", x))) # clean

:

> DF
     p  div
1 2799 2299
2   NA 4999
+4

lapply :

library(xml2)
library(rvest)

pg <- read_html('<html>
<head></head>
<body>

<div class="product_price" id="product_price_186251">
  <p class="normal_encontrado">
    S/. 2,799.00
  </p>

  <div id="WC_CatalogEntryDBThumbnailDisplayJSPF_10461_div_10" class="price">
    S/. 2,299.00
  </div>    
</div>

<div class="product_price" id="product_price_232046">
  <div id="WC_CatalogEntryDBThumbnailDisplayJSPF_10461_div_10" class="price">
    S/. 4,999.00
  </div>
</div>
</body>
</html>')

prod <- html_nodes(pg, "div.product_price")
do.call(rbind, lapply(prod, function(x) {
  norm <- tryCatch(xml_text(xml_node(x, "p.normal_encontrado")),
                   error=function(err) {NA})
  price <- tryCatch(xml_text(xml_node(x, "div.price")),
                    error=function(err) {NA})
  data.frame(norm, price, stringsAsFactors=FALSE)
}))

##                     norm                  price
## 1 \n    S/. 2,799.00\n   \n    S/. 2,299.00\n  
## 2                   <NA> \n    S/. 4,999.00\n

, - , .

+2

, lapply .product_price :

r.precio.antes <- page_source %>% html_nodes(".product_price") %>%
  lapply(. %>% html_nodes(".normal_encontrado") %>% html_text() %>% 
     ifelse(identical(., character(0)), NA, .)) %>% unlist

NA, .normal_encontrado .

r.precio.antes
# [1] "\n                    S/. 2,799.00\n                "
# [2] NA  

length(r.precio.antes) # 2

, , .product_price:

product_nodes <- page_source %>% html_nodes(".product_price")

lapply :

r.precio.antes <- lapply(product_nodes, function(pn) {
  pn %>% html_nodes(".normal_encontrado") %>% html_text()
})
r.precio.antes <- unlist(r.precio.antes)

magrittr lapply, ., , .

, , character(0), NA, . ifelse(identical(., character(0)), NA, .)) , .

0
source

Source: https://habr.com/ru/post/1612522/

More articles:


All Articles