数据分析——爬取股票数据

from urllib.parse import urlencode
import pandas as pd
import requests
import timedef gen_secid(rawcode: str) -> str:'''生成东方财富专用的secidParameters----------rawcode : 6 位股票代码Return------str: 指定格式的字符串'''# 沪市指数if rawcode[:3] == '000':return f'1.{rawcode}'# 深证指数if rawcode[:3] == '399':return f'0.{rawcode}'# 沪市股票if rawcode[0] != '6':return f'0.{rawcode}'# 深市股票return f'1.{rawcode}'def get_k_history(code: str, beg: str = '16000101', end: str = '20500101', klt: int = 1, fqt: int = 1) -> pd.DataFrame:'''功能获取k线数据Parameters----------code : 6 位股票代码beg: 开始日期 例如 20200101end: 结束日期 例如 20200201klt: k线间距 默认为 101 即日kklt:1 1 分钟klt:5 5 分钟klt:101 日klt:102 周fqt: 复权方式不复权 : 0前复权 : 1后复权 : 2 Return------DateFrame : 包含股票k线数据'''EastmoneyKlines = {'f51': '日期','f52': '开盘','f53': '收盘','f54': '最高','f55': '最低','f56': '成交量','f57': '成交额','f58': '振幅','f59': '涨跌幅','f60': '涨跌额','f61': '换手率',}EastmoneyHeaders = {'Host': '19.push2.eastmoney.com','User-Agent': 'Mozilla/5.0 (Windows NT 6.3; WOW64; Trident/7.0; Touch; rv:11.0) like Gecko','Accept': '*/*','Accept-Language': 'zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2','Referer': 'http://quote.eastmoney.com/center/gridlist.html',}fields = list(EastmoneyKlines.keys())columns = list(EastmoneyKlines.values())fields2 = ",".join(fields)secid = gen_secid(code)params = (('fields1', 'f1,f2,f3,f4,f5,f6,f7,f8,f9,f10,f11,f12,f13'),('fields2', fields2),('beg', beg),('end', end),('rtntype', '6'),('secid', secid),('klt', f'{klt}'),('fqt', f'{fqt}'),)params = dict(params)base_url = 'https://push2his.eastmoney.com/api/qt/stock/kline/get'url = base_url+'?'+urlencode(params)json_response: dict = requests.get(url, headers=EastmoneyHeaders).json()data = json_response.get('data')if data is None:if secid[0] == '0':secid = f'1.{code}'else:secid = f'0.{code}'params['secid'] = secidurl = base_url+'?'+urlencode(params)json_response: dict = requests.get(url, headers=EastmoneyHeaders).json()data = json_response.get('data')if data is None:print('股票代码:', code, '可能有误')return pd.DataFrame(columns=columns)klines = data['klines']rows = []for _kline in klines:kline = _kline.split(',')rows.append(kline)df = pd.DataFrame(rows, columns=columns)return dfif __name__ == "__main__":# 重复 1000 次for _ in range(1000):# 股票代码code = '002273'# 根据股票代码、开始日期、结束日期获取指定股票代码指定日期区间的k线数据df = get_k_history(code)# 保存k线数据到表格里面df.to_csv(f'{code}.csv', encoding='utf-8-sig', index=None)print(f'股票代码：{code} k线数据已保存到 {code}.csv 文件中')time.sleep(60)