R语言获取股票信息进行数据分析

library(rvest)
library(httr)
library(dplyr)

# 亿牛云代理 
# 爬虫代理加强版 设置代理IP的用户名和密码
proxy_username <- "16YUN"
proxy_password <- "16IP"

# 创建用于发送HTTP请求的Session对象，并设置爬虫代理加强版代理IP的服务器和认证信息
session <- html_session(url = "http://guba.eastmoney.com/rank/",
                        proxy = "http://www.16yun.cn:31000",
                        authenticate(proxy_username, proxy_password))

# 定义函数来解析页面并提取股票信息
parse_page <- function(page) {
  page %>% 
    html_nodes("table.table_bg001 tbody tr") %>% 
    html_text() %>% 
    strsplit("\\s{2,}") %>% 
    lapply(function(x) {
      data_frame(
        rank = x[1],
        code = x[2],
        name = x[3],
        price = x[4]
      )
    }) %>% 
    bind_rows()
}

# 定义函数来获取指定页数的股票信息
get_stock_info <- function(page_num) {
  url <- modify_url("http://guba.eastmoney.com/rank/",
                    query = list(pn = page_num))
  
  page <- session %>% GET(url) %>% content() %>% read_html()
  
  stock_info <- parse_page(page)
  
  return(stock_info)
}

# 获取第一页的股票信息
stock_info <- get_stock_info(1)

# 获取总页数
total_pages <- stock_info %>% pull(rank) %>% as.numeric() %>% max()

# 循环获取剩余页面的股票信息
for (page_num in 2:total_pages) {
  stock_info_page <- get_stock_info(page_num)
  stock_info <- bind_rows(stock_info, stock_info_page)
}

# 打印整理后的股票信息
print(stock_info)