[R语言爬虫] 豆瓣网,10月图书抓取

library(xml2)
library(rvest)
library(stringr)
url <- "https://book.douban.com/chart?icn=index-topchart-nonfiction"
web <- read_html(url)
# 获取图书名
title <- web %>% html_nodes("a.fleft") %>% html_text(trim = TRUE)


# 获取作者
author <- web %>% html_nodes("p.subject-abstract") %>% html_text(trim = TRUE)
i=NULL
Author=NULL
for(i in 1:length(author)){
    Author[i] = str_split(author[i],"/")
    Author[i] = Author[[i]][1]
      if(i == length(author)){
        Author = unlist(Author)
        print(Author)
      }
}


# 获取价格
Price=NULL
for(i in 1:length(author)){
  Price[i] = str_split(author[i],"/")
  Price[i] = Price[[i]][4]
  if(i == length(author)){
    Price = unlist(Price)
    print(Price)
  }
}
Price <- as.numeric(str_replace_all(Price,"元",""))


# 获取起始价
startprice <- web %>% html_nodes("span.buy-info") %>% html_text(trim = TRUE)
startprice <- unlist(str_extract_all(startprice,"[0-9|.]+"))
startprice <- as.numeric(startprice)


# 获取评分
score <- web %>% html_nodes("span.font-small") %>% html_text(trim = TRUE)
score <- as.numeric(score)


# 组装成数据框
douban <- data.frame("书名" = title, "作者" = author, "起始价格" = startprice,
                   "豆瓣价" = Price, "评分" =score)
print(douban)


with(douban,{
  plot(起始价格, 评分, main = "起始价格与豆瓣评分",
  xlab = "起始售价:元", col = "blue")}
)