商品拇指图

from selenium import webdriver

from selenium.webdriver.chrome.service import Service

from selenium.webdriver.chrome.options import Options

from bs4 import BeautifulSoup

url = input(“请输入你要访问的网址: “)

user_agent = ‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/137.0.0.0 Safari/537.36’

chrome_options = Options()

chrome_options.add_argument(“–log-level=3”)

chrome_options.add_argument(“–disable-logging”)

chrome_options.add_argument(“–user-data-dir=C:/selenium-profile”)

chrome_options.add_argument(“–profile-directory=Default”)

chrome_options.add_argument(f’user-agent={user_agent}’)

driver = webdriver.Chrome(options=chrome_options)

service = Service(r”C:\Windows\System32\chromedriver.exe”, log_path=”NUL”)

driver.get(url)

html_source = driver.page_source

with open(“rendered.html”, “w”, encoding=”utf-8″) as f:

f.write(html_source)

with open(“rendered.html”, “r”, encoding=”utf-8″) as f:

soup = BeautifulSoup(f, “html.parser”)

for img in (img for img in soup.find_all(“img”, src=True, placeholder=True, class_=True) if len(img.attrs) == 3):

print(img[“src”])

driver.quit()

一条评论