爬虫：在网易财经抓取表格数据案例

library(rvest)
symbol=600550
year=2019
season=3
url=paste0("http://quotes.money.163.com/trade/lsjysj_",symbol,".html?year=",year,"&season=",season)
web=read_html(url)
xpath="/html/body/div[2]/div[4]/table[1]"
web.table=web%>%html_nodes(xpath=xpath)%>%html_table()

library(lubridate)
symbol=600550
from="2001-05-28"
from=as.Date(from)
to=Sys.Date()
time.index=seq(from=from,to=to,by="quarter")#生成以季度为开始的时间序列
year.id=year(time.index)#获取年份
quarter.id=quarter(time.index)#获取季度

price=list()
for(t in 1:length(time.index)){
year=year.id[t]
season=quarter.id[t]
url=paste0("http://quotes.money.163.com/trade/lsjysj_",symbol,".html?year=",year,"&season=",season)
web=read_html(url)
xpath="/html/body/div[2]/div[4]/table[1]"
web.table=web%>%html_nodes(xpath=xpath)%>%html_table()
web.table=web.table[[1]][-1,]
price[[t]]=web.table
}

get.wangyi.stock=function(symbol,from,to){
from=as.Date(from)
to=as.Date(to)
if(mday(from==1)){
from=from-1
}
time.index=seq(from=from,to=to,by="quarter")
year.id=year(time.index)
quarter.id=quarter(time.index)
prices=list()
for(t in 1:length(time.index)){
year=year.id[t]
season=quarter.id[t] url=paste0("http://quotes.money.163.com/trade/lsjysj_",symbol,".html?year=",year,"&season=",season)
web=read_html(url)
xpath="/html/body/div[2]/div[4]/table[1]"
web.table=web%>%html_nodes(xpath=xpath)%>%html_table()
web.table=web.table[[1]][-1,]
prices[[t]]=web.table
}
}
to=Sys.Date()
stock.index=matrix(nrow=6,ncol=2)
stock.index[,1]=c("600550.ss","600192.ss","600152.ss","600644.ss","600885.ss","600151.ss")
stock.index[,2]=c("2017-05-28","2017-05-28","2017-05-28","2017-05-28","2017-05-28","2017-05-28")
for(i in nrow(stock.index)){
symbol=stock.index[i,1]
from=stock.index[i,2]
prices=get.wangyi.stock(symbol,from,to)
filenames=paste0("D://dataset//",symbol,".csv")
}