#参考了http://www.cnblogs.com/weibaar/p/4824578.html的思路
#代码目的是发现亚马逊Kindle热销榜中5元以下书籍都有哪些
#槽点：中国顾客对价格这么敏感亚马逊同学居然没有直接对价格筛选的功能...
#不然原作者应该不会整这个案例

library(stringr)
library(rvest)

data.frame()->alldata
url="https://www.amazon.cn/gp/movers-and-shakers/digital-text/#"

for(i in 1:5)
{
 page=str_c(url,i)
 read_html(page)->website

 html_nodes(website,"div.zg_itemRow div div div a div") %>% html_text()->book
 gsub("\n","",book)->book
 str_trim(book)->book

 html_nodes(website,"div.zg_itemRow div div div div.a-row span span") %>% html_text()->price
 gsub("￥","",price)->price

 cbind(book,price)->bp
 rbind(alldata,bp)->alldata
 Sys.sleep(2)    #听说太快了会被封IP所以要手动加延迟
}

alldata$price=as.numeric(alldata$price)
alldata[alldata$price<5,]->newdata
newdata[order(newdata$book),]
newdata[order(newdata$price),]
ITPub博客

[R爬虫]亚马逊Kindle热销榜价格排序

最新文章
