排排网PC分享_彭煜方-CSDN博客

本文链接：https://blog.csdn.net/great_cricus/article/details/118372439
import requests
from bs4 import BeautifulSoup
import pandas as pd
import os
from fake_useragent import UserAgent
import json
ua = UserAgent()
user_id = 00000
# This cookie need to be updated every hour
Cookie = "focus-certification-pop=-1; certification=1; qualified_investor=1; evaluation_result=4; guest_id=1570936362; regsms=1624171892000; http_tK_cache=dbbf8f84c525a7160aaef4d21219b1bed2ecf512; cur_ck_time=1624694453; ck_request_key=WBEyAxdP1u8mGhbq4tWjWHNx4YhYSex9RQY6ddGS0hA%3D; passport=680546%09u9155843295513%09VAcAUwpQA1ZRBlxaVFAGUQICBlACC19TC1YDAgADVAk%3D3ca5bd2f94; rz_rem_u_p=LaeVx12Q0nYPk82vmZjilhpMv68x5o1b7fR0IN4%2FD5k%3D%24kyMzWHKQYikw%2FlAcPA3UxGpNGHTm4lbhwn2a7DpPr78%3D; sensorsdata2015jssdkcross=%7B%22distinct_id%22%3A%22680546%22%2C%22first_id%22%3A%22680546%22%2C%22props%22%3A%7B%22%24latest_traffic_source_type%22%3A%22%E7%9B%B4%E6%8E%A5%E6%B5%81%E9%87%8F%22%2C%22%24latest_search_keyword%22%3A%22%E6%9C%AA%E5%8F%96%E5%88%B0%E5%80%BC_%E7%9B%B4%E6%8E%A5%E6%89%93%E5%BC%80%22%2C%22%24latest_referrer%22%3A%22%22%2C%22%24latest_utm_source%22%3A%2220048%22%2C%22%24latest_utm_campaign%22%3A%22NRYY-media%22%2C%22_latest_utm_sign%22%3A%22zimeiti%22%7D%2C%22%24device_id%22%3A%22179e5ae4c4c135-0119d6070e1a0f-f7f1939-921600-179e5ae4c4d567%22%7D; Hm_lvt_c3f6328a1a952e922e996c667234cdae=1624171597,1624709592,1624894510,1624895262; Hm_lpvt_c3f6328a1a952e922e996c667234cdae=1624896177"
def get_company(scale):
    headers = {"Host":'ppwapi.simuwang.com', "Referer":'https://mobile.simuwang.com/',"User-Agent":ua.random, "Cookie":Cookie}
    main_url = "https://ppwapi.simuwang.com/ranking/company"
    main_web = requests.post(main_url, headers=headers, data={"page":1, "condition":"ret:4;scale:%s;"%scale,"sort_name":"ret","sort_asc":"desc", 'USER_ID':user_id}).text
    soup = BeautifulSoup(main_web,features="lxml")
    company_list = soup.find('p')
    company_list_json = json.loads(company_list.text)['data']
    company_info = company_list_json['list']
    page_num = company_list_json['pages']
    company_df = pd.DataFrame(company_info)
    if page_num < 2:
        pass
    else:
        for page in range(1, page_num):
            main_web = requests.post(main_url, headers=headers,
                                     data={"page": page + 1, "condition": "ret:4;scale:%s;"%scale,
                                           "sort_name": "ret", "sort_asc": "desc", 'USER_ID': user_id}).text
            soup = BeautifulSoup(main_web, features="lxml")
            company_list = soup.find('p')
            company_list_json = json.loads(company_list.text)['data']
            company_info = company_list_json['list']
            company_df = pd.concat([company_df, pd.DataFrame(company_info)])
    return company_df

def get_strategy(id_list, name_list):
    headers = {"Host":'sppwapi.simuwang.com', "Referer":'https://mobile.simuwang.com/',"User-Agent":ua.random, "Cookie":Cookie}
    main_url = "https://sppwapi.simuwang.com/sun/company/allFundList"
    strategy_result = []
    for id in id_list:
        main_web = requests.post(main_url, headers=headers, data={"id":id, 'type':'all', 'USER_ID':user_id}).text
        soup = BeautifulSoup(main_web,features="lxml")
        fund_list = soup.find('p')
        fund_list_json = json.loads(fund_list.contents[0])
        fund_info = fund_list_json['data'][0]['list']
        fund_df = pd.DataFrame(fund_info)[['strategy','substrategy', 'fund_status']]
        fund_df = fund_df.loc[fund_df['fund_status'] == 1, ['strategy','substrategy']]
        fund_strategy = fund_df.apply(lambda x: "+".join(x), axis=1)
        strategy_result.append(fund_strategy.value_counts())
    result = pd.concat(strategy_result, axis=1)
    result.columns = name_list
    return result
# 得到目标公司基金与净值曲线
def get_nav(id_list, fund_list, company_name, fund_name):
    headers = {"Host":'sppwapi.simuwang.com', "Referer":'https://mobile.simuwang.com/',"User-Agent":ua.random, 'Cookie':Cookie}
    fund_result = []
    company_result = []
    for i, id in enumerate(id_list):
        print(id)
        delegate_id = fund_list[i]
        main_url = "https://sppwapi.simuwang.com/sun/chart/fundNavTrend"
        main_web = requests.post(main_url, headers=headers, data={"fund_id":delegate_id, 'compare_id':'IN00000008', 'nav_flag':1, 'period':0, 'USER_ID':user_id}).text
        soup = BeautifulSoup(main_web,features="lxml")
        data_list = soup.find('p')
        data_list_json = json.loads(data_list.text)['data']
        time = data_list_json['categories']
        ret = data_list_json['data']
        # 得到旗舰基金的表现
        ret_fund = pd.DataFrame(index=time, data = {'沪深300':ret['IN00000008'], fund_name[i]:ret[delegate_id]['ret'], 'compare':ret['compare']})    #     fund_info = fund_list_json['data'][0]['list']
        main_url = "https://sppwapi.simuwang.com/sun/chart/companyNavTrend"
        main_web = requests.post(main_url, headers=headers, data={"company_id":id, 'compare_id':'IN00000008', 'nav_flag':1, 'period':0,'USER_ID':user_id}).text
        soup = BeautifulSoup(main_web,features="lxml")
        data_list = soup.find('p')
        data_list_json = json.loads(data_list.text)['data']
        time = data_list_json['categories']
        ret = data_list_json['data']
        ret_company = pd.DataFrame(index=time, data=ret, columns=['沪深300', company_name[i], 'compare'])    #     fund_info = fund_list_json['data'][0]['list']
        fund_result.append(ret_fund)
        company_result.append(ret_company)
    with pd.ExcelWriter('HF_fund.xlsx') as r:
        for i in range(len(id_list)):
            fund_result[i].to_excel(r, sheet_name=company_name[i])
    with pd.ExcelWriter('HF_company.xlsx') as r:
        for i in range(len(id_list)):
            company_result[i].to_excel(r, sheet_name=company_name[i])

def get_quant_fund(scale):
    scale_dict = {'10-20': 3, "20-50": 4, '50-100': 5, '100+': 6}
    company_result = get_company(scale_dict[scale])
    strategy_result = get_strategy(company_result['company_id'], company_result['company_short_name'])
    strategy_result_percent = strategy_result / strategy_result.sum(axis=0)
    quant_fund = strategy_result_percent.transpose()[["股票策略+量化多头", "相对价值+股票市场中性", "相对价值+套利",
                                                      "相对价值+相对价值复合", "管理期货+量化趋势", "管理期货+量化套利", "管理期货+管理期货复合",
                                                      "复合策略+量化多策略"]].sum(axis=1) >= 0.5
    quant_fund = quant_fund[quant_fund == True]
    quant_fund_info = company_result.set_index('company_short_name').loc[quant_fund.index, :]
    quant_fund_strategy = strategy_result[quant_fund.index]
    return quant_fund_info, quant_fund_strategy

def get_funds(id_list):
    headers = {"Host":'sppwapi.simuwang.com', "Referer":'https://mobile.simuwang.com/',"User-Agent":ua.random, "Cookie":Cookie}
    main_url = "https://sppwapi.simuwang.com/sun/company/allFundList"
    strategy_result = []
    for id in id_list:
        main_web = requests.post(main_url, headers=headers, data={"id":id, 'type':'all', 'USER_ID':user_id}).text
        soup = BeautifulSoup(main_web,features="lxml")
        fund_list = soup.find('p')
        fund_list_json = json.loads(fund_list.contents[0])
        fund_info = fund_list_json['data'][0]['list']
        fund_info = pd.DataFrame(fund_info)
        fund_info['company_id'] = id
        strategy_result.append(fund_info)
    return pd.concat(strategy_result)

id_ideal = ['CO00000HWR',
'CO00000HZI',
'CO00000BB6',
'CO000001N7',
'CO000001CM',
'CO000001G0',
'CO000001IQ',
'CO000000S4',
'CO000003KY',
'CO00000FNC',
'CO000001HJ',
'CO00000DOE',
'CO00000VQC',
'CO0000080D',
'CO000003HY',
'CO00000F35',
'CO00000AMA',
'CO0000014J',
'CO00000E66']

name_ideal = ['思勰投资',
'宁波幻方量化',
'幻方量化',
'灵均投资',
'进化论资产',
'明汯投资',
'九坤投资',
'金锝资产',
'因诺资产',
'白鹭资管',
'千象资产',
'锐天投资',
'珠海致诚卓远',
'喜岳投资',
'宽德投资',
'华澄投资',
'念空数据科技',
'富善投资',
'平方和投资']

# result_ideal = get_strategy(id_ideal, name_ideal)
# result_ideal.to_excel('final_result.xlsx')
# get_nav(id_ideal, name_ideal)
# with pd.ExcelWriter('HF_funds.xlsx') as r:
#     for scale in ['10-20', '20-50', '50-100', '100+']:
#         company_list = pd.read_excel("HF_statistics.xlsx", sheet_name='fund_info %s' % scale)['company_id']
#         fund_list = get_funds(company_list)
#         fund_list.to_excel(r, sheet_name="fund_details %s"%scale)

fund_info_list = [pd.read_excel("HF_statistics.xlsx", sheet_name='fund_info %s'%scale) for scale in ['10-20', '20-50', '50-100', '100+']]
fund_info = pd.concat(fund_info_list)
fund_info = fund_info.set_index("company_short_name")
fund_id = fund_info.loc[name_ideal, ['fund_id']]
fund_id.loc['念空数据科技'] = "HF00005L7N"
get_nav(id_ideal, fund_id.values.flatten(), name_ideal, fund_info.loc[name_ideal, ['fund_short_name']].values.flatten())
# with pd.ExcelWriter('HF_statistics.xlsx') as r:
#     for scale in ["10-20", "20-50", "50-100", "100+"]:
#         print(scale)
#         fund_info, fund_strategy = get_quant_fund(scale)
#         fund_info.to_excel(r, sheet_name='fund_info %s' % scale)
#         fund_strategy.to_excel(r, sheet_name='fund_strategy %s' % scale)