【R语言爬虫】网贷天眼数据平台表格数据抓取2

本文主要是介绍【R语言爬虫】网贷天眼数据平台表格数据抓取2，希望对大家解决编程问题提供一定的参考价值，需要的开发者们随着小编来一起学习吧！

一、需求分析
抓取url:
http://www.p2peye.com/shuju/ptsj/
昨日数据：
字段：排序平台名称成交额综合利率投资人借款周期借款人满标速度累计贷款余额资金净流入

这里写图片描述

二、rvest爬虫实现源代码

rm(list=ls())
gc()
options(scipen = 200)
library('rvest')
timestart<-Sys.time()url="http://www.p2peye.com/shuju/ptsj/"#从网站中读取HTML代码
webpage <- read_html(url)#使用CSS选择器来爬取排名部分
rank_data_html <- html_nodes(webpage,'.num')
#将排名数据转化为文本
rank_data <- html_text(rank_data_html)
#数据预处理：将排名转换为数字格式
rank_data<-as.numeric(rank_data[2:length(rank_data)])name <- html_nodes(webpage,'.name')
name_data <- html_text(name[2:length(name)])
#数据预处理：去掉'\n'
name_data<-gsub("\n","",name_data)
#数据预处理：去掉多余的空格
name_data<-gsub(" ","",name_data)total <- html_nodes(webpage,'.total')
total_data <- html_text(total[2:length(total)])rate <- html_nodes(webpage,'.rate')
rate_data <- html_text(rate[2:length(rate)])pnum <- html_nodes(webpage,'.pnum')
pnum_data <- html_text(pnum[2:length(pnum)])cycle <- html_nodes(webpage,'.cycle')
cycle_data <- html_text(cycle[2:length(cycle)])p1num <- html_nodes(webpage,'.p1num')
p1num_data <- html_text(p1num[2:length(p1num)])fuload <- html_nodes(webpage,'.fuload')
fuload_data <- html_text(fuload[2:length(fuload)])alltotal <- html_nodes(webpage,'.alltotal')
alltotal_data <- html_text(alltotal[2:length(alltotal)])capital <- html_nodes(webpage,'.capital')
capital_data <- html_text(capital[2:length(capital)])data <- data.frame("排序"=rank_data,"平台名称"=name_data,"成交额"=total_data,"综合利率"=rate_data,"投资人"=pnum_data,"借款周期"=cycle_data,"借款人"=pnum_data,"满标速度"=fuload_data,"累计贷款余额"=alltotal_data,"资金净流入"=capital_data)###############写出数据到excel
library(xlsx)
write.xlsx(data,"C:\\mydata.xlsx",row.names = F)  
timeend<-Sys.time()
runningtime<-timeend-timestart
print(runningtime)