多线程爬取豆瓣图书TOP250源码示例及并行处理

install.packages("RCurl")
install.packages("XML")
install.packages("parallel")
install.packages("stringr")
install.packages("ggplot2")
install.packages("dplyr")
library(tcltk)
library(dplyr)
#top250豆瓣书籍
library(parallel)
library(ggplot2)
t<-0
books<-function(t){
  library(RCurl)
  library(stringr)
  library(XML)
  dg<-debugGatherer()
  mheader<-c("User-Agent"="Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36",
             "Accept"="texthtml,applicationxhtml+xml,applicationxml;q=0.9,;q=0.8",
             "Accept-Language"="en-us",
             "Connection"="keep-alive",
             "Accept-Charset"="GB2312,utf-8;q=0.7,;q=0.7")
  topurl<-"https://book.douban.com/top250?start="
  tcurl<-str_c(topurl,t*25,sep="")
  topbook<-getURL(tcurl,httpheader=mheader,debugfunction=dg$update,verbose=TRUE)
  acbook<-htmlParse(topbook,encoding ="UTF-8")
  tname<-xpathSApply(acbook,"//*/div[@class='pl2']/a[1]",xmlValue)
  tfname<-str_trim(str_replace_all(tname,"[:space:]",""))
  alias<-xpathSApply(acbook,"//*/div[@class='pl2']/span",xmlValue)
  tlink<-xpathSApply(acbook,"//*/a[@class='nbg']",xmlAttrs,'href')