【R】爬虫案例

爬取豆瓣相册

library(RCurl)
library(XML)

myHttpheader <- c("User-Agent"="Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9.1.6) ",
                  "Accept"="text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
                  "Accept-Language"="en-us",
                  "Connection"="keep-alive",
                  "Accept-Charset"="GB2312,utf-8;q=0.7,*;q=0.7")

ye<-c(1,seq(18,630,18))
info<-NULL

for(i in ye){
  url<-paste("https://www.douban.com/photos/album/50903114/?start=",i,sep="")
  web<-getURL(url,httpheader=myHttpheader)
  doc<- htmlTreeParse(web,encoding="UTF-8", error=function(...){}, useInternalNodes = TRUE,trim=TRUE)
  node<-getNodeSet(doc, "//div[@class='photo_wrap']/a")
  info=c(info,sapply(node,xmlGetAttr,"href"))
}

x<-1
dir.create("./image1/")
for(urlweb in info){
  web1<-getURL(urlweb,httpheader=myHttpheader)
  doc1<- htmlTreeParse(web1,encoding="UTF-8", error=function(...){}, useInternalNodes = TRUE,trim=TRUE)
  node1<-getNodeSet(doc1, "//div[@class='photo-edit']/a")
  info1=sapply(node1,xmlGetAttr,"href")
  web2<-getURL(info1,httpheader=myHttpheader)
  doc2<- htmlTreeParse(web2,encoding="UTF-8", error=function(...){}, useInternalNodes = TRUE,trim=TRUE)
  node2<-getNodeSet(doc2, "//td[@id='pic-viewer']/a/img")
  info2=sapply(node2,xmlGetAttr,"src")
  y<-paste("./image1/",x,".jpg")
  tryCatch({
    download.file(info2,y,mode="wb")
    x<-x+1},error=function(e){
      cat("ERROR:",conditionMessage(e),"\n")
      print("loser")})
}