raena-crawler-engine/hasaki_crawler_engine/test2.py

43 lines
1.3 KiB
Python

from seleniumwire import webdriver
from selenium.webdriver.chrome.service import Service
from webdriver_manager.chrome import ChromeDriverManager
from fake_useragent import UserAgent
import brotli
import json
def get_raw_product(url):
ua = UserAgent(platforms='mobile')
random_mobile_ua = ua.random
op = webdriver.ChromeOptions()
op.add_argument(f"user-agent={random_mobile_ua}")
op.add_experimental_option("useAutomationExtension", False)
op.add_argument('--no-sandbox')
op.add_argument('--disable-notifications')
op.add_argument("--lang=en-GB")
op.headless = False
driver = webdriver.Chrome(service=Service(ChromeDriverManager().install()), options=op)
driver.get(url)
for request in driver.requests:
if request.response:
if '/wap/v2/product/detail' in request.url:
encoding = request.response.headers.get('content-encoding')
# print(encoding)
if encoding:
iteminfo = brotli.decompress(request.response.body)
else:
iteminfo = request.response.body
driver.quit()
iteminfo_json = json.loads(iteminfo)
return iteminfo_json
print(get_raw_product('https://hasaki.vn/san-pham/nuoc-tay-trang-bioderma-danh-cho-da-nhay-cam-500ml-9740.html'))