爬取ncbi页面数据
# install.packages('RSelenium')
#java -Dwebdriver.chrome.driver="chromedriver.exe" -jar selenium-server-standalone-4.0.0-alpha-2.jar -port 4444

library(readxl)
library(RSelenium)
library(rvest)
library(xml2)
library(RS.Driver)
library(tidyverse)
names<-read_excel("names.xlsx")
url<-c()
id<-names$`GenBank Assembly ID (Accession.version)`
for (i in id) {
  url <- c(url,paste('https://www.ncbi.nlm.nih.gov/assembly/',
                     i,sep = ''))
}
RS.OpenChrome()
name<-c()
submitter<-c()
date<-c()
for(i in 1:length(url)){
  RS.open_Url(url[i])
  #RS.OpenChrome(url[i])
  #RS.open_Url(url_200[i])
  Sys.sleep(2.5)
  name <- c(name,RS.get_Text('//*[@id="summary"]/dl/dd[3]'))
  submitter <- c(submitter,RS.get_Text('//*[@id="summary"]/dl/dd[6]'))
  date <- c(date,RS.get_Text('//*[@id="summary"]/dl/dd[7]'))
}
total<-cbind(name,submitter,date)
暂无评论

发送评论 编辑评论


				
|´・ω・)ノ
ヾ(≧∇≦*)ゝ
(☆ω☆)
(╯‵□′)╯︵┴─┴
 ̄﹃ ̄
(/ω\)
∠( ᐛ 」∠)_
(๑•̀ㅁ•́ฅ)
→_→
୧(๑•̀⌄•́๑)૭
٩(ˊᗜˋ*)و
(ノ°ο°)ノ
(´இ皿இ`)
⌇●﹏●⌇
(ฅ´ω`ฅ)
(╯°A°)╯︵○○○
φ( ̄∇ ̄o)
ヾ(´・ ・`。)ノ"
( ง ᵒ̌皿ᵒ̌)ง⁼³₌₃
(ó﹏ò。)
Σ(っ °Д °;)っ
( ,,´・ω・)ノ"(´っω・`。)
╮(╯▽╰)╭
o(*////▽////*)q
>﹏<
( ๑´•ω•) "(ㆆᴗㆆ)
😂
😀
😅
😊
🙂
🙃
😌
😍
😘
😜
😝
😏
😒
🙄
😳
😡
😔
😫
😱
😭
💩
👻
🙌
🖕
👍
👫
👬
👭
🌚
🌝
🙈
💊
😶
🙏
🍦
🍉
😣
Source: github.com/k4yt3x/flowerhd
颜文字
Emoji
小恐龙
花!
上一篇
下一篇