import requests
from bs4 import BeautifulSoup
site = 'https://basicenglishspeaking.com/daily-english-conversation-topics/'
request = requests.get(site) # requests.get(site,headers=header)
request.text # html 소스를 가져옴
soup = BeautifulSoup(request.text;
soup.find('div', {'class':'thrv-columns'})
😇 크롬드라이버를 직접 설치하는게 아닌 라이브러리 이용 가능
!pip install chromedriver-autoinstaller
import chromedriver_autoinstaller
import time
from selenium import webdriver
from selenium.webdriver.common.by import By
chromedriver_autoinstaller.install()
send_keys
search = driver.find_element('name','q')
search.send_keys('lambda')
search.send_keys(Keys.RETURN) # enter
findAll
soup = BeautifulSoup(driver.page_source)
comment_area = soup.findAll('span',{'class','u_cbox_contents'})
find_elements
driver = webdriver.Chrome()
driver.get('https://www.python.org')
search = driver.find_element('name','q')
to_excel
banapresso.to_excel('banapresso.xlsx')
implicitly_wait(초)
driver = webdriver.Chrome()
driver.implicitly_wait(3)
sleep
url = "https://www.instagram.com/explore/tags/사과/"
driver.get(url)
time.sleep(6)
click
driver.find_element(By.XPATH, '//*[@id="loginForm"]/div/div[3]/button/div').click()
태그 이름에 *를 넣을 경우 전체를 의미함
HTML DOM의 중간부터 시작(본인이 선택한 요소부터
//태그 이름[@attribute = 'Value']/div/div[3]/button/div
문서 앞단부터 경로를 다 지정하는 방법
/html/body/div[2]/div/div[2]/div[1]/div[2]/form/div/input