Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| from selenium import webdriver | |
| from selenium.common.exceptions import WebDriverException | |
| from PIL import Image | |
| from io import BytesIO | |
| def web_scrape(url): | |
| options = webdriver.ChromeOptions() | |
| options.add_argument('--headless') | |
| options.add_argument('--no-sandbox') | |
| options.add_argument('--disable-dev-shm-usage') | |
| try: | |
| wd = webdriver.Chrome(options=options) | |
| wd.set_window_size(1080, 720) # Adjust the window size here | |
| wd.get(url) | |
| wd.implicitly_wait(10) | |
| meta_element = wd.find_element_by_tag_name("meta") | |
| #content_value = meta_element.get_attribute("name") | |
| return meta_element | |
| except WebDriverException as e: | |
| return "error handle website" | |
| finally: | |
| if wd: | |
| wd.quit() | |
| return Image.open(BytesIO(screenshot)) | |
| iface = gr.Interface( | |
| fn=web_scrape, | |
| inputs=gr.inputs.Textbox(label="Website URL", default="https://stock.adobe.com/stock-photo/id/621214874"), | |
| outputs=gr.outputs.Textbox(label="Web Content"), | |
| title="Web Scraping with Selenium (Body Tag)", | |
| description="Scrape the content of a website's <body> tag using Selenium.", | |
| ) | |
| iface.launch() |