爬取股票数据

爬取股票数据

目录

• 爬取股票数据
  • • 1 爬取前的分析
    • 2 爬取流程

1 爬取前的分析

技术路线：使用 requests + bs4 + re

数据网站选取原则：股票信息静态存在于 HTML 页面中，非 js 代码生成没有 Robots 协议限制

获取股票列表：
东方财富网：http://quote.eastmoney.com/stock_list.html
获取个股信息：
百度股票：https://gupiao.baidu.com/stock/
单个股票：https://gupiao.baidu.com/stock/szee2439.html

2 爬取流程

步骤1：从东方财富网获取股票列表
步骤2：根据股票列表逐个到百度股票获取个股信息
步骤3：将结果存储到文件

# -*- coding: utf-8 -*-
# @Time    : 2019/8/30 15:39
# @Author  : banshaohuan
# @Site    : 
# @File    : gupiao_baidu_youhua.py
# @Software: PyCharm
import requests
from bs4 import BeautifulSoup
import re


def getHTMLText(url, code="utf-8"):
    try:
        r = requests.get(url, timeout=30)
        r.raise_for_status()
        r.encoding = code
        return r.text
    except:
        return ""


def get_stock_list(lst, stock_url):
    html = getHTMLText(stock_url, "GB2312")
    soup = BeautifulSoup(html, 'html.parser')
    a = soup.find_all('a')
    for i in a:
        try:
            href = i.attrs['href']
            lst.append(re.findall(r"[s][hz]\d{6}", href)[0])
        except:
            continue


def get_stock_info(lst, stock_url, file_path):
    count = 0
    for stock in lst:
        url = stock_url + stock + '.html'
        html = getHTMLText(url)
        try:
            if html == "":
                continue
            info_dict = {}
            soup = BeautifulSoup(html, 'html.parser')
            stock_info = soup.find('div', attrs={"class":"stock-bets"})

            name = stock_info.find_all(attrs={"class":"bets-name"})[0]
            info_dict.update({'股票名称': name.text.split()[0]})

            key_list = stock_info.find_all('dt')
            value_list = stock_info.find_all('dd')

            for i in range(len(key_list)):
                key = key_list[i].text
                val = value_list[i].text
                info_dict[key] = val

            with open(file_path, 'a', encoding='utf-8') as f:
                f.write(str(info_dict) + '\n')
                count += 1
                print("\r当前进度：{:.2f}%".format(count*100/len(lst)), end="")
        except:
            count += 1
            print("\r当前进度：{:.2f}%".format(count * 100 / len(lst)), end="")
            continue


def main():
    stock_list_url = 'https://quote.eastmoney.com/stock_list.html'
    stock_info_url = 'https://gupiao.baidu.com/stock/'
    output_file = 'D:/BaiduStockInfo.txt'
    stock_list = []

    get_stock_list(stock_list, stock_list_url)
    get_stock_info(stock_list, stock_info_url, output_file)


if __name__ == '__main__':
    main()

本文参考嵩天老师在中国 MOOC 大学的课程《python 网络爬虫与信息提取》