def test_read_style_iter(tmpdir): ''' Test if cell styles are read properly in iter mode. ''' tmpdir.chdir() from openpyexcel import Workbook from openpyexcel.styles import Font FONT_NAME = "Times New Roman" FONT_SIZE = 15 ft = Font(name=FONT_NAME, size=FONT_SIZE) wb = Workbook() ws = wb.worksheets[0] cell = ws['A1'] cell.font = ft xlsx_file = "read_only_styles.xlsx" wb.save(xlsx_file) wb_iter = load_workbook(xlsx_file, read_only=True) ws_iter = wb_iter.worksheets[0] cell = ws_iter['A1'] assert cell.font == ft
def __init__(self): super().__init__() self.filename = "coin.xlsx" try: self.wb = load_workbook(filename=self.filename) self.current_columns = len(self.wb.active[1]) + 1 except FileNotFoundError: wb = Workbook() wb.save(self.filename) self.wb = load_workbook(filename=self.filename) self.current_columns = 1
from selenium import webdriver from openpyexcel import Workbook driver = webdriver.Chrome('chromedriver') url = "https://search.naver.com/search.naver?where=news&sm=tab_jum&query=추석" driver.get(url) req = driver.page_source soup = BeautifulSoup(req, 'html.parser') articles = soup.select( "#main_pack > div.news.mynews.section._prs_nws > ul > li") wb = Workbook() ws1 = wb.active ws1.title = "articles" ws1.append(["제목", "링크", "신문사"]) for article in articles: title = article.select_one('dl > dt > a').text url = article.select_one('dl > dt > a')['href'] comp = article.select_one("span._sp_each_source").text.split( ' ')[0].replace('언론사', '') ws1.append([title, url, comp]) #print(title, url, comp) #print(comp) driver.quit() wb.save(filename='articles.xlsx')