vlambda博客
学习文章列表

#以下安装包不能调用的需要手动安装：install.packages("")rm(list=ls())#清除所有变量library(data.table)library(openxlsx)library(stringr)library(stringi)library(VennDiagram)library(RCurl)library(stringr)library(XML)library(downloader)library("dplyr") # 管道操作符所属的包library("rvest") # 本次爬取网页数据的工具在这里

#准备文件名为“ID.txt”的文件，文件仅有一列，第一行为“ID”#读取文件ZYID <- fread("ID.txt",header = T,stringsAsFactors = F)ZYID<-ZYID[c("ID")]

#开始循环爬取for(i in 1:nrow(ZYID)){#数据清洗，is.na为判别函数，判断是否为空值： if(is.na(ZYID [i,ID])){ print(paste("处理第",i,"个代号时发现,ID为：",ZYID [i,ID],",已经跳过"))#代号为空时打印：处理第i个代号时发现ID为：ZYID [i,ID]已经跳过 next } else { print(paste("开始处理第",i,"个草药,ID为：",ZYID [i,ID]))#开始处理第i个草药,ID为：ZYID [i,CID] }
#下载网页文件file <- paste("./",ZYID [i,ID],".html",sep="")#设置html文件下载地址a<-ZYID [i,ID]url <- paste("http://www.pharmnet.com.cn/tcm/knowledge/detail/",a,".html",sep="")#设置网址#以下5行代码是用于下载html文件，若需要下载可去掉开头的井号符#JudgeHtml<-try(download.file(url, destfile = file, quiet = TRUE),silent=TRUE)#判断下载链接是否可行#ifelse(JudgeHtml==0,'download.file(url, destfile = file, quiet = TRUE)','F')#如果下载链接可行，就下载，否者退出#ifelse(JudgeHtml==0,Html<- 1,Html<- 0)#如果下载链接可行，Html等于1，否则Html为0#cat(ifelse(file.exists(file),"Html文件下载成功!","Html文件下载失败!"))#ZYID [i,"Html"] <- Html# 读取网页源码（read_html())web <- url %>%read_html(encoding = "GBK") # 有时候其他网站是UTF-8是编码方式Title <- web %>% html_node("h1") %>% html_text()#Detail <- web %>% html_node("#fontsize") %>% html_text()#ZYID [i,"Title"] <- TitleZYID [i,"Detail"] <- Detail}write.csv(ZYID,file="./ZYID.csv")#导出数据

#以下安装包不能调用的需要手动安装：install.packages("")rm(list=ls())#清除所有变量library(data.table)library(openxlsx)library(stringr)library(stringi)library(VennDiagram)library(RCurl)library(stringr)library(XML)library(downloader)library("dplyr") # 管道操作符所属的包library("rvest") # 本次爬取网页数据的工具在这里
#准备文件名为“ID.txt”的文件，文件仅有一列，第一行为“ID”#读取文件ZYID <- fread("ID.txt",header = T,stringsAsFactors = F)ZYID<-ZYID[c("ID")]
#开始循环爬取for(i in 1:nrow(ZYID)){#数据清洗，is.na为判别函数，判断是否为空值： if(is.na(ZYID [i,ID])){ print(paste("处理第",i,"个代号时发现,ID为：",ZYID [i,ID],",已经跳过"))#代号为空时打印：处理第i个代号时发现ID为：ZYID [i,ID]已经跳过 next } else { print(paste("开始处理第",i,"个草药,ID为：",ZYID [i,ID]))#开始处理第i个草药,ID为：ZYID [i,CID] }
#下载网页文件file <- paste("./",ZYID [i,ID],".html",sep="")#设置html文件下载地址a<-ZYID [i,ID]url <- paste("http://www.pharmnet.com.cn/tcm/knowledge/detail/",a,".html",sep="")#设置网址#以下5行代码是用于下载html文件，若需要下载可去掉开头的井号符#JudgeHtml<-try(download.file(url, destfile = file, quiet = TRUE),silent=TRUE)#判断下载链接是否可行#ifelse(JudgeHtml==0,'download.file(url, destfile = file, quiet = TRUE)','F')#如果下载链接可行，就下载，否者退出#ifelse(JudgeHtml==0,Html<- 1,Html<- 0)#如果下载链接可行，Html等于1，否则Html为0#cat(ifelse(file.exists(file),"Html文件下载成功!","Html文件下载失败!"))#ZYID [i,"Html"] <- Html# 读取网页源码（read_html())web <- url %>%read_html(encoding = "GBK") # 有时候其他网站是UTF-8是编码方式Title <- web %>% html_node("h1") %>% html_text()#Detail <- web %>% html_node("#fontsize") %>% html_text()#ZYID [i,"Title"] <- TitleZYID [i,"Detail"] <- Detail}write.csv(ZYID,file="./ZYID.csv")#导出数据