from bs4 import BeautifulSoup from pandas import DataFrame, Series import requests as re import pandas as pd import json import sqlite3 import requests class FnGuideCrawler: header = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36'} def getStockInfo(self): #code_df = pd.read_html('http://kind.krx.co.kr/corpgeneral/corpList.do?method=download&searchType=13', header=0)[0] code_df = pd.read_html(requests.get('http://kind.krx.co.kr/corpgeneral/corpList.do?method=download&searchType=13', headers=self.header).text) # 종목코드가 6자리이기 때문에 6자리를 맞춰주기 위해 설정해줌 code_df.종목코드 = code_df.종목코드.map('{:06d}'.format) # 우리가 필요한 것은 회사명과 종목코드이기 때문에 필요없는 column들은 제외해준다. code_df = code_df[['회사명', '종목코드']] # 한글로된 컬럼명을 영어로 바꿔준다. code_df = code_df.rename(columns={'회사명': 'name', '종목코드': 'code'}) ###print (code_df.head()) return code_df # FnGuide에서 크롤링한 KOSPI 상장기업의 재무제표 # http://blog.naver.com/PostView.nhn?blogId=koko8624&logNo=221294884955&parentCategoryNo=&categoryNo=&viewDate=&isShowPopularPosts=false&from=postView def get_fnguide_table(self, code): url = re.get('http://comp.fnguide.com/SVO2/ASP/SVD_main.asp?pGB=1&gicode=A%s'%(code.strip())) url = url.content html = BeautifulSoup(url,'html.parser') body = html.find('body') try: fn_body = body.find('div', {'class': 'fng_body asp_body'}) ur_table = fn_body.find('div', {'id': 'div15'}) table = ur_table.find('div', {'id': 'highlight_D_Y'}) tbody = table.find('tbody') tr = tbody.find_all('tr') Table = DataFrame() except: return {} for i in tr: ''' 자료 항목 가져오기''' category = i.find('span', {'class': 'txt_acd'}) if category == None: category = i.find('th') category = category.text.strip() '''값 가져오기''' value_list = [] j = i.find_all('td', {'class': 'r'}) for value in j: temp = value.text.replace(',', '').strip() try: temp = float(temp) value_list.append(temp) except: value_list.append(0) Table['%s' % (category)] = value_list ''' 기간 가져오기 ''' thead = table.find('thead') tr_2 = thead.find('tr', {'class': 'td_gapcolor2'}).find_all('th') year_list = [] for i in tr_2: try: temp_year = i.find('span', {'class': 'txt_acd'}).text except: temp_year = i.text temp_year = temp_year.replace("/",".")+".01" year_list.append(temp_year) Table.index = year_list return Table.T.to_dict() def crawl_fnguide(self, inFileName): tableName = 'fnguide' conn = sqlite3.connect(inFileName, isolation_level=None) cursor = conn.cursor() cursor.execute("CREATE TABLE IF NOT EXISTS "+tableName+" (CODE text PRIMARY KEY, NAME text, PRICE text)") code_df = self.getStockInfo() idx = 0 for item in code_df.values: item_name = item[0] item_code = item[1] idx += 1 print(idx, item_name) fnGuideData = self.get_fnguide_table(item_code) text = json.dumps(fnGuideData, ensure_ascii=False) cursor.execute('SELECT * FROM '+tableName+' WHERE CODE=?', (item_code, )) result = cursor.fetchone() if result == None: cursor.execute("INSERT INTO "+tableName+"(CODE, NAME, PRICE) VALUES(?, ?, ?)", (item_code, item_name, text)) else: cursor.execute("UPDATE "+tableName+" SET PRICE=? WHERE CODE=?", (text, item_code)) cursor.close() conn.close() return if __name__ == "__main__": crawler = FnGuideCrawler() crawler.get_fnguide_table('155660')