Commit 7b24f19e by 정용석

clipDownload, title 추출 불가

parent e2ce970e
...@@ -12,15 +12,53 @@ service = Service(ChromeDriverManager().install()) # webdriver-manager로 자 ...@@ -12,15 +12,53 @@ service = Service(ChromeDriverManager().install()) # webdriver-manager로 자
driver = webdriver.Chrome(service=service) driver = webdriver.Chrome(service=service)
driver.get("https://chzzk.naver.com/clips/KWydos957E") driver.get("https://chzzk.naver.com/clips/KWydos957E")
driver.implicitly_wait(300) time.sleep(3)
# iframe으로 전환
iframe = WebDriverWait(driver, 20).until(
EC.presence_of_element_located((By.TAG_NAME, "iframe"))
)
driver.switch_to.frame(iframe)
# video 태그 확인 # video 태그 확인
url_element = driver.find_element(By.TAG_NAME, 'video') # 비디오 태그를 명시적으로 기다림
vid_url = url_element.get_attribute('src') try:
print(vid_url) url_element = WebDriverWait(driver, 20).until(
print("출력") EC.presence_of_element_located((By.TAG_NAME, 'video'))
# 잠시 대기 )
time.sleep(30) print(url_element)
# 비디오 URL 가져오기
vid_url = url_element.get_attribute('src')
except Exception as e:
print("Error:", e)
finally:
print("비디오 URL:", vid_url)
# 잠시 대기
# 제목 추출 -> 보완필요
# try:
# # "si_desc" 클래스가 있는 <p> 태그 찾기
# p_element = WebDriverWait(driver, 10).until(
# EC.presence_of_element_located((By.CLASS_NAME, "si_desc"))
# )
# # 텍스트에서 <a> 태그를 제외하고 텍스트만 추출
# text = p_element.text.strip()
# 브라우저 종료 # # 출력
#driver.quit() # print(p_element)
# print(p_element.text)
# print("추출된 텍스트:", text)
# except Exception as e:
# print("Error:", e)
# finally:
# driver.quit()
# url로 영상 다운로드
from urllib.request import urlretrieve
urlretrieve(vid_url, 'a.mp4')
time.sleep(30)
driver.quit()
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment