基于R语言抓取豆瓣电影 Top 250

获取目标： 1，电影名称(中文)；2，导演以及主演；3，年代； 4，国别；5，评分；6，评价人数；7，是否可播放； 8，电影类型

readLines版本，造福厂财人

运行结果

源代码

url0 = "https://movie.douban.com/top250?start="
for(i in seq(0,225,25))
{
  url=paste(url0,as.character(i),"&filter=",sep="")
  web =readLines(url,encoding ='UTF-8')
  #电影名称
  moviename=web[grep("",director)-1)
  age0=web[grep("导演: ",web)+1]
  age0=gsub(" ", "", age0)
  #年代
  age=substr(age0,0,4)
  #国别
  country0=substr(age0,18,100)
  country=substr(country0,1,regexpr(" ",country0)-1)
  #评分
  scoure=web[grep("
",web)+2]
  scoure=gsub(" ","",scoure)
  scoure=substr(scoure,regexpr("average\">",scoure)+9,regexpr("",scoure)-1)
  #评价人数
  number=web[grep("
",web)+4]
  number=gsub(" ","",number)
  number=substr(number,regexpr("",number)+6,regexpr("人",number)-1)
  #是否可播放
  play=web[grep("
",web)+8]
  play=gsub(" ","",play)
  play=gsub("
","[不可播放]",play)
  play=gsub("","[不可播放]",play)
  play=substr(play,regexpr("\\[",play)+1,regexpr("]",play)-1)
  #电影类型
  class=substr(country0,regexpr(" / ",country0)+13,100)
  #储存
  TOP250=data.frame(
    "电影名称"=moviename,
    "导演以及主演"=director,
    "年代"=age,
    "国别"=country,
    "评分"=scoure,
    "评分人数"=number,
    "是否可播放"=play,
    "电影类型"=class)
  if(i==0)
    write.table(TOP250,"D:TOP250.csv",append=TRUE,row.names=F,col.names=T,sep = ",")
  else
    write.table(TOP250,"D:TOP250.csv",append=TRUE,row.names=F,col.names=F,sep = ",")
}