def make_keywords_list(academy_xlsx_path, comp_academy_path, stock_title_path, NaverTrend_path, array2D_path,
start_date, end_date, use_navertrend, use_downloaded_navertrend):
compressed_words = comp_text.extract_keyword(dir_path=academy_xlsx_path, return_num=5, freq_ctr=0.75)
comp_compressed_words = comp_text.extract_keyword(dir_path=comp_academy_path, return_num=100, freq_ctr=0.0)
stock_name_list = read_stockname(academy_xlsx_path)
compressed_only_words = pinset(compressed_words)
comp_only_words = pinset(comp_compressed_words)
print("compressed only words")
print(compressed_only_words)
print("comp only words")
print(comp_only_words)
print('')
# def Remove_words(stock_title_dir_path, stock_file_name, keywords_dir_path, comp_dir_path, array2D_xlsx_path, array2D_xlsx_name)
convert_to_str(compressed_only_words)
convert_to_str(comp_only_words)
search_words, removed_words = remove_useless_words.Remove_words(stock_title_dir_path=stock_title_path,
stock_file_name='stock_title',
keywords=compressed_only_words,
comp_list=comp_only_words)
print(" search_words : ")
print(search_words)
print(" removed_words : ")
print(removed_words)
result = []
if use_navertrend == True:
download_xlsx_from_NaverTrend.download_xlsx(search_words=search_words, start_date=start_date, end_date=end_date,
download_path=NaverTrend_path)
slope_list = comp_NaverTrend.comp_NaverTrend_xls(dir_path=NaverTrend_path, array2D_xlsx_path=array2D_path)
print("slope_list : ")
print(slope_list)
print(slope_list[:(int)(len(slope_list) / 2)])
for i in range(0, len(slope_list), 1):
result.append(slope_list[i][0])
else:
result = search_words
if use_downloaded_navertrend == True:
slope_list = comp_NaverTrend.comp_NaverTrend_xls(dir_path=NaverTrend_path, array2D_xlsx_path=array2D_path)
print("slope_list : ")
print(slope_list)
print(slope_list[:(int)(len(slope_list) / 2)])
for i in range(0, len(slope_list), 1):
result.append(slope_list[i][0])
return stock_name_list, result # [[키워드1, 검색어 트래픽], [키워드2, 검색어 트래픽] ... ]으로 초기화 되어있는 리스트를 return합니다.
def Set_comp_keywords_list(self, comp_dir_path, array2D_xlsx_path,
array2D_xlsx_name):
print("Set comp_keywords_list")
comp_dir_path = comp_dir_path + '/' + 'NaverTrend'
self.comp_keywords_list = comp_NaverTrend.comp_NaverTrend_xls(
dir_path=comp_dir_path,
array2D_xlsx_path=array2D_xlsx_path,
array2D_xlsx_name=array2D_xlsx_name)
def Set_keywords_list(self, dir_path, array2D_xlsx_path,
array2D_xlsx_name):
# comp_NaverTrend.py 의
# def comp_NaverTrend_xls(dir_path = None, array2D_xlsx_path=None, array2D_xlsx_name='2D_array.xlsx'): 을 call하여 사용합니다.
self.keywords_list = comp_NaverTrend.comp_NaverTrend_xls(
dir_path=dir_path,
array2D_xlsx_path=array2D_xlsx_path,
array2D_xlsx_name=array2D_xlsx_name)
def Keywords(start_date,
end_date,
word_list,
comp_word_list,
chrome_path='c:\\data\\chromedriver.exe',
default_path='',
academy_xlsx_path='',
NaverTrend_path='',
array2D_path='',
stock_title_path='',
original_stock_title_path='C:/data/Keywords/Stock_title',
update_stock_title=False):
if default_path == '': # 기본경로를 설정해줍니다.
default_path = 'C:/data/' + 'Keywords/' + datetime.datetime.now(
).strftime('%Y-%m-%d_%H-%M-%S') + word_list[0] + '_포함_' + str(
len(word_list)) + '_종목'
# 경로설정하는 부분.
academy_xlsx_path, NaverTrend_path, array2D_path, stock_title_path = path_controller(
default_path, academy_xlsx_path, NaverTrend_path, array2D_path,
stock_title_path)
comp_default_path = default_path + '/' + 'Comp_data'
comp_academy_path, comp_NaverTrend_path, comp_array2D_path, comp_stock_title_path = path_controller(
comp_default_path)
# 분석하려고 하는 그룹의 데이터를 받아옴
get_keyword_from_academy_re.download_keywords(
start_date=start_date,
end_date=end_date,
search_key=word_list,
ID='academy',
PWD='academy123',
download_path=academy_xlsx_path,
chrome_path=chrome_path)
# 비교 대조군을 만들기 위한 데이터를 받아옴
get_keyword_from_academy_re.download_keywords(
start_date=start_date,
end_date=end_date,
search_key=comp_word_list,
ID='academy',
PWD='academy123',
download_path=comp_academy_path,
chrome_path=chrome_path)
compressed_words = comp_text.extract_keyword(dir_path=academy_xlsx_path,
return_num=5,
freq_ctr=0.75)
comp_compressed_words = comp_text.extract_keyword(
dir_path=comp_academy_path, return_num=100, freq_ctr=0.0)
compressed_only_words = pinset(compressed_words)
comp_only_words = pinset(comp_compressed_words)
print("compressed only words")
print(compressed_only_words)
print("comp only words")
print(comp_only_words)
print('')
get_keyword_from_academy_re.dir_path_check(
array2D_path) #2D_array_path check and make directory
get_keyword_from_academy_re.dir_path_check(comp_array2D_path)
if update_stock_title: # 기업명을 네이버에서 새로 받아오도록 하는 설정
get_stock_title.Make_Stock_title_xlsx(
dir_path=stock_title_path) # 기업명을 네이버에서 모두 가져옴
else:
get_stock_title.Copy_Stock_title_xlsx(
original_path=original_stock_title_path,
copy_path=stock_title_path,
file_name='stock_title.xlsx')
# def Remove_words(stock_title_dir_path, stock_file_name, keywords_dir_path, comp_dir_path, array2D_xlsx_path, array2D_xlsx_name)
convert_to_str(compressed_only_words)
convert_to_str(comp_only_words)
search_words, removed_words = remove_useless_words.Remove_words(
stock_title_dir_path=stock_title_path,
stock_file_name='stock_title',
keywords=compressed_only_words,
comp_list=comp_only_words)
print(" search_words : ")
print(search_words)
print(" removed_words : ")
print(removed_words)
download_xlsx_from_NaverTrend.download_xlsx(search_words=search_words,
start_date=start_date,
end_date=end_date,
download_path=NaverTrend_path)
slope_list = comp_NaverTrend.comp_NaverTrend_xls(
dir_path=NaverTrend_path, array2D_xlsx_path=array2D_path)
print("slope_list : ")
print(slope_list)
print(slope_list[:(int)(len(slope_list) / 2)])
return slope_list # [[키워드1, 검색어 트래픽], [키워드2, 검색어 트래픽] ... ]으로 초기화 되어있는 리스트를 return합니다.