from bs4 import BeautifulSoup import requests import tushare as ts # #获取2014年第3季度的盈利能力数据 # a = ts.get_profit_data(2014,3) # ROE # print("len a:",len(a)) # print(a) # codelist = [] # roelist = [] # codelist = a.code.tolist() # roelist = a.roe.tolist() # print(ts.get_stock_basics()) #PE PB (市盈率 市净率) # a = ts.get_hist_data('600848', ktype='w',start='2020-06-01') def loadROEts(): codelist = [] roelist = [] a = ts.get_profit_data(2020,1) # ROE # print("len a:",len(a)) # print(a) print('get_profit_data OK') codelist = a.code.tolist() roelist = a.roe.tolist() print('tolist OK') # codelist = ['123','456'] # roelist = [12.3,45.6] import sqlite3 conn = sqlite3.connect('test.db') c = conn.cursor() # c.execute('''CREATE TABLE roe # (code CHAR(6), # ROE REAL);''') for index,code in enumerate(codelist): sqlst = ''' insert into GX values('{}',{}) '''.format(code, roelist[index] if type(roelist[index]) is not str else 0) try: c.execute(sqlst) except: print('err:',sqlst) if index%100 == 0: print('inserting...',index) conn.commit() c.close() conn.commit() conn.close() def loadPEPBts(): pass # 网页的访问 def get_html_text(url): try: headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.106 Safari/537.36', "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3", } # r = requests.get(url, headers=headers) r = requests.get(url) r.raise_for_status() r.encoding = r.apparent_encoding return r.text except requests.RequestException as e: print(e) else: result = r.json() print(type(result), result, sep='\n') # try: # r = requests.get(URL, params={'ip': '8.8.8.8'}, timeout=1) # r.raise_for_status() # 如果响应状态码不是 200，就主动抛出异常 # except requests.RequestException as e: # print(e) # else: # result = r.json() # print(type(result), result, sep='\n') def getEarnings_ratio(): import sqlite3 conn = sqlite3.connect('test.db') c = conn.cursor() # c.execute('''CREATE TABLE pber # (code CHAR(6), # pb REAL, # er REAL);''') # conn.commit() v = c.execute('''select * from GX;''') c = conn.cursor() for index,l in enumerate(v): url = '''http://www.csindex.com.cn/zh-CN/downloads/industry-price-earnings-ratio-detail?date={}&class=1&search=1&csrc_code={}'''.format("2020-11-12", l[0]) # 股息率 html = get_html_text(url) soup = BeautifulSoup(html, "html.parser") td = soup.find_all("td") print(index) if 0!=len(td) : f10 = str(td[10].string) if f10 != " -- ": f10f = float(f10) print('PB:',td[9].string,"er:",td[10].string) try: sqlst = '''insert into pber values('{}',{},{});'''.format(l[0], float(str(td[9].string)), float(str(td[10].string))) c.execute(sqlst) if index%5==0: conn.commit() print(sqlst) except: print('err:',index) c.close() conn.commit() conn.close() # url = '''http://www.csindex.com.cn/zh-CN/downloads/industry-price-earnings-ratio-detail? # date={}&class=1&search=1&csrc_code={}'''.format("2020-11-12",'002242')#股息率 # html = get_html_text(url) # soup = BeautifulSoup(html,"html.parser") # td = soup.find_all("td") # for i,v in enumerate(td): # print(v.string) # return td # url = '''http://quote.eastmoney.com/sh605007.html''' # html = get_html_text(url) # soup = BeautifulSoup(html,"html.parser") # # td = soup.find_all("td") # td = soup.find_all("div",class_='cwzb') # # td = soup.find_all("tbody",id='cwzbDataBox') # for i,v in enumerate(td): # print(v.string) # print('end') if __name__ == '__main__': # loadROEts() getEarnings_ratio()
