def install_history_financial_crawler(stock_code): baseurl = 'http://quotes.money.163.com' headers = { 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8', 'Accept-Encoding': 'gzip, deflate', 'Accept-Language': 'zh-CN,zh;q=0.8', 'User-Agent': get_user_agent(), } zcfzb_url = baseurl + '/service/zcfzb_%s.html' % stock_code zcfzb_response = requests.get(url=zcfzb_url, headers=headers) zcfzb(zcfzb_response, stock_code) xjllb_url = baseurl + '/service/xjllb_%s.html' % stock_code xjllb_response = requests.get(url=xjllb_url, headers=headers) xjllb(xjllb_response, stock_code) lrb_url = baseurl + '/service/lrb_%s.html' % stock_code lrb_response = requests.get(url=lrb_url, headers=headers) lrb(lrb_response, stock_code) zycwzb_url = baseurl + '/service/zycwzb_%s.html' % stock_code zycwzb_response = requests.get(url=zycwzb_url, headers=headers) zycwzb(zycwzb_response, stock_code) cwbbzy_url = baseurl + '/service/cwbbzy_%s.html' % stock_code cwbbzy_response = requests.get(url=cwbbzy_url, headers=headers) cwbbzy(cwbbzy_response, stock_code) print('%s save history financial of stock successful...' % stock_code)
def install_history_capttal_crawler(code): ''' 爬去到数据后,直接根据stock_code,直接入库 爬取上交所的股本信息,由于上交所更新过慢,则不用 :return: ''' capital_headers = { 'Accept': '*/*', 'Connection': 'keep-alive', 'Referer': 'keep-http://www.sse.com.cn/assortment/stock/list/info/capital/index.shtml', 'Accept-Encoding': 'gzip, deflate', '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', 'User-Agent': get_user_agent() } data_dicts = {} capital_url = 'http://query.sse.com.cn/security/stock/queryEquityChangeAndReason.do?companyCode={}'.format( code) data = requests.get(url=capital_url, headers=capital_headers) data_dict = json.loads(data.text) stock_code = data_dict['companyCode'] history_capital_stock = data_dict['result'] data_list = [ ['realDate', 'changeReasonDesc', 'totalShares'], ] for i in history_capital_stock: data_list.append( [i['realDate'], i['changeReasonDesc'], i['totalShares']]) data_dicts[stock_code] = data_list # write07Excel(data_dicts) BaseCrawlerDB.save_set_result('lm_stock_data', {'code': stock_code}, 'history_capital_stock', history_capital_stock) capttal_xlsx_to_db(code) print('%s save history capital of stock successful...' % code)
Create : 2018/1/2 下午8:31 Author : Richard Chen File : price_data.py Software: IntelliJ IDEA ''' import requests import json from common.db_utils.stock_crawler_inner_db import LmInnerReportDBMgr from conf.requests_useragent import get_user_agent headers = { 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8', 'Accept-Encoding': 'gzip, deflate', 'Accept-Language': 'zh-CN,zh;q=0.8', 'User-Agent': get_user_agent(), } def is_halt(code): url = 'http://mdfm.eastmoney.com/EM_UBG_MinuteApi/Js/Get?style=tail&id={}1&num=1'.format( code) res = requests.get(url, headers=headers) res.encoding = 'utf-8' data_json = json.loads(res.text.split('(')[1].split(')')[0]) if not data_json['result']: if data_json['message'] == '暂无数据': return 0 else: print('未找到股票代码') else: