import requests from urllib.parse import urlencode from openpyxl import Workbook requests = requests.session() login_url = "https://passport.simuwang.com/index.php?m=passport&c=auth&a=login" headers = { "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.122 Safari/537.36", "Referer": "https://dc.simuwang.com/" } data = { "username": "13074703598", "password": "xxxxx", "do_qualified": "1", "reme": "1" } res = requests.post(url=login_url, headers=headers, data=data) def detail(page): params = { "page": "%s" % page, "condition": "fund_type:1,6,4,3,8,2;rating_year:1;istiered:0;company_type:1;city:北京;sort_name:profit_col1;sort_asc:desc;keyword:", "type": "0", "selected": "0" } url = "https://dc.simuwang.com/" url = url + 'ranking/get?%s' % urlencode(params) res1 = requests.get(url, headers=headers) dict1 = res1.json() dict_list = dict1.get('data') dict_strategy = { '1': '股票策略', '8': '复合策略', '7': '组合策略', '6': '固定收益', '2': '宏观策略', '3': '管理期货', '4': '事件驱动', '5': '相对价值' } # print(dict_list) for dict_detail in dict_list: fund_name = dict_detail.get('fund_name') # 基金简称 strategy1 = dict_detail.get('strategy') # 投资策略 strategy = dict_strategy.get(strategy1) company_short_name = dict_detail.get('company_short_name') # 基金公司 profit_col1 = dict_detail.get('profit_col1') # 最新净值 price_date = dict_detail.get('price_date') # 日期 profit_col11 = dict_detail.get('profit_col11') # 年化 profit_col2 = dict_detail.get('profit_col2') # 近一月 profit_col3 = dict_detail.get('profit_col3') # 近三月 profit_col4 = dict_detail.get('profit_col4') # 近半年 profit_col5 = dict_detail.get('profit_col5') # 近一年 profit_col6 = dict_detail.get('profit_col6') # 近两年 wb1.append( [fund_name, strategy, company_short_name, profit_col1, price_date, profit_col11, profit_col2, profit_col3, profit_col4, profit_col5, profit_col6]) print(fund_name, strategy, company_short_name, profit_col1, price_date, profit_col11, profit_col2, profit_col3, profit_col4, profit_col5, profit_col6) wb = Workbook() # 先生成一个工作簿 wb1 = wb.create_sheet('index', 0) wb1.append(['基金简称', '投资策略', '基金公司', '最新净值', '日期', '年化', '近一月', '近三月', '近半年', '近一年', '近两年']) for i in range(1, 158): detail(i) print(i) wb.save('cik.xlsx')
路径编码
>>> from urllib.parse import quote >>> quote('/test') '/test' >>> quote('/test', safe='') '%2Ftest' >>> quote('/El Niño/') '/El%20Ni%C3%B1o/'
携带cookie
import requests session = requests.session() cookie = "addf=54654654654; fgsjsgf=feurgrehgtrhbrtjbrtjh;" def cookie_to_cookiejar(cookies): if not hasattr(cookies, "startswith"): raise TypeError import requests cookiejar = requests.utils.cookiejar_from_dict( {cookie[0]: cookie[1] for cookie in [cookie.split("=", maxsplit=1) for cookie in cookies.split(";")]}) return cookiejar cookiejar = cookie_to_cookiejar(cookie.strip('; ')) session.cookies = cookiejar