广期所爬虫

guangzhou_qihuo.py

@@ -0,0 +1,55 @@
+import base64
+import os
+import time
+from time import sleep
+
+import numpy as np
+from PIL import Image
+from selenium import webdriver
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.webdriver import ActionChains
+
+from selenium.webdriver.chrome.options import Options
+
+from selenium.common.exceptions import WebDriverException
+
+# 设置Chrome浏览器选项
+from selenium.webdriver.chrome.service import Service
+
+# 调用截图函数
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.wait import WebDriverWait
+
+if __name__ == "__main__":
+    # 创建一个 Chrome WebDriver 实例
+    options = webdriver.ChromeOptions()
+    # options.add_argument("headless")
+    # options.add_argument(" window-size=1920,1080")
+    prefs = {'download.prompt_for_download': False, 'download.default_directory': '/Users/xiexiaoyuan/Downloads/'}
+    options.add_experimental_option('prefs', prefs)
+    s = Service(executable_path='/Users/xiexiaoyuan/chromedriver_mac64_111/chromedriver')
+    driver = webdriver.Chrome(service=s, options=options)
+    # driver.maximize_window()
+    driver.get('http://www.gfex.com.cn/gfex/rihq/hqsj_tjsj.shtml')
+    driver.execute_cdp_cmd("Page.addScriptToEvaluateOnNewDocument", {
+        "source": """
+                 Object.defineProperty(navigator, 'webdriver', {
+                   get: () => undefined
+                 })
+               """
+    })
+    sleep(2)
+    WebDriverWait(driver, 10).until(
+        EC.element_to_be_clickable((By.XPATH, '//div[@id="tradeType"]/ul/li[1]/a'))).click()
+
+    sleep(5)
+    WebDriverWait(driver, 10).until(
+        EC.element_to_be_clickable((By.XPATH, '//button[@id="export_excel"]'))).click() # 点击导出excel
+
+    # b = driver.find_element(By.XPATH, '//button[@id="export_excel"]')
+    # print(b.text)
+    # b.click()
+    sleep(10)
+    # 等待文件下载完成
+    driver.implicitly_wait(10)  # 等待10秒
+    driver.quit()