Why Use DrissionPage

try:
    Auth = os.environ.get("PROXY_AUTH")
    CafeSDK.Log.info(f"Current browser authentication info: {Auth}")
except Exception as e:
    CafeSDK.Log.error(f"Failed to obtain browser authentication info: {e}")
    Auth = None
    return

browser_url = f"ws://chrome-ws-inner.cafescraper.com/ws?apiKey={Auth}"
rest_item = {"url": url, "html": "", "resp_status": "200"}

CafeSDK.Log.info("Connecting to fingerprint browser...")

co = ChromiumOptions()
co.set_address(browser_url)

try:
    browser = Chromium(co)
    CafeSDK.Log.info("Fingerprint browser connected successfully")
except Exception:
    CafeSDK.Log.error("Failed to connect to fingerprint browser")
    rest_item["resp_status"] = "403"
    return

try:
    page = browser.new_tab()
    page.get(url)
    page.wait.doc_loaded()
    html = page.html
    rest_item["html"] = html
    CafeSDK.Result.push_data(rest_item)
except Exception as e:
    CafeSDK.Log.info(f"[Error] Failed to retrieve page HTML: {e}")
    rest_item["resp_status"] = "500"

import asyncio, sys, traceback, re
import random
import time
import os

from lxml import etree
from urllib.parse import urlparse, urlencode
import hashlib
from DrissionPage import ChromiumOptions, Chromium, errors

from sdk import CafeSDK

async def run():
    CafeSDK.Log.info("🚀 Init...")
    CafeSDK.Log.info("====================================================")
    CafeSDK.Log.info("🚀 CafeScraper TikTok Shop Information Scraper")
    CafeSDK.Log.info("====================================================")

    headers = [
        {"label": "url", "key": "url", "format": "text"},
        {"label": "html", "key": "html", "format": "text"},
        {"label": "resp_status", "key": "resp_status", "format": "text"},
    ]

    CafeSDK.Result.set_table_header(headers)

    input_json_dict = CafeSDK.Parameter.get_input_json_dict()
    CafeSDK.Log.debug(f"======input_json_dict====== {input_json_dict}")
    url = input_json_dict['url']

    try:
        Auth = os.environ.get("PROXY_AUTH")
        CafeSDK.Log.info(f"Current browser authentication info: {Auth}")
    except Exception as e:
        CafeSDK.Log.error(f"Failed to obtain browser authentication info: {e}")
        return

    browser_url = f"ws://chrome-ws-inner.cafescraper.com/ws?apiKey={Auth}"
    rest_item = {"url": url, "html": "", "resp_status": "200"}

    CafeSDK.Log.info("Connecting to fingerprint browser...")
    co = ChromiumOptions()
    co.set_address(browser_url)

    try:
        browser = Chromium(co)
        CafeSDK.Log.info("Fingerprint browser connected successfully")
    except Exception:
        CafeSDK.Log.error("Failed to connect to fingerprint browser")
        rest_item["resp_status"] = "403"
        return

    try:
        page = browser.new_tab()
        page.get(url)
        page.wait.doc_loaded()
        html = page.html
        rest_item["html"] = html
        CafeSDK.Result.push_data(rest_item)
    except Exception as e:
        CafeSDK.Log.info(f"[Error] Failed to retrieve page HTML: {e}")
        rest_item["resp_status"] = "500"

if __name__ == "__main__":
    asyncio.run(run())

# Method 1: CSS selector (recommended)
element = page.ele('.product-title')
element = page.ele('#main-content')
element = page.ele('tag:h1')

# Method 2: XPath
element = page.ele('xpath://div[@class="container"]')

# Method 3: Text matching
element = page.ele('text:Buy Now')

# Check if element exists
if element:
    text = element.text
    html = element.html
    attrs = element.attrs
    class_name = element.attr('class')

# Retrieve all matching elements
product_items = page.eles('.product-item')
CafeSDK.Log.info(f"Found {len(product_items)} products")

products_data = []
for item in product_items:
    product = {
        'name': item.ele('.name').text if item.ele('.name') else '',
        'price': item.ele('.price').text if item.ele('.price') else '',
        'link': item.ele('.link').attr('href') if item.ele('.link') else '',
    }
    products_data.append(product)

# List comprehension (concise)
names = [item.ele('.name').text for item in product_items if item.ele('.name')]

import time
page.get(url)
time.sleep(5)

requests.get(url, headers=headers)