项目初始化

.gitignore

@@ -0,0 +1,3 @@
+/tmp
+/driver
+*.pyc

README.MD

@@ -0,0 +1,2 @@
+### chrome driver 下载地址
+https://googlechromelabs.github.io/chrome-for-testing/#stable

main.py

@@ -0,0 +1,38 @@
+from selenium import webdriver
+from selenium.webdriver.support.ui import WebDriverWait
+import time
+
+import utils
+
+options = webdriver.ChromeOptions()
+options.add_argument('lang=zh-CN')
+options.add_argument(
+    'user-agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36')
+# options.add_argument('--user-data-dir=./UserData/Google/Chrome/Default')
+options.add_argument('--disable-gpu')  # 如果不加这个选项，有时定位会出现问题
+# options.add_argument('--headless')  # 增加无界面选项
+
+service = webdriver.ChromeService(r"./driver/chromedriver.exe")
+driver = webdriver.Chrome(service=service,options=options)
+driver.maximize_window()
+# driver.execute_cdp_cmd("Page.addScriptToEvaluateOnNewDocument", {
+#     "source": """
+#             Object.defineProperty(navigator, 'webdriver', {
+#               get: () => undefined
+#             })
+#             """
+# })
+with open("./stealth.min.js") as f:
+    driver.execute_cdp_cmd("Page.addScriptToEvaluateOnNewDocument", {
+        "source": f.read()
+    })
+
+driver.get("https://bot.sannysoft.com/")
+time.sleep(5)
+width = driver.execute_script("return document.documentElement.scrollWidth")
+height = driver.execute_script("return document.documentElement.scrollHeight")
+print(width, height)
+utils.screenshot(driver=driver, save_path="./screenshot.png")
+driver.set_window_size(width, height)
+driver.save_screenshot('result.png')
+time.sleep(30)

utils/__init__.py

@@ -0,0 +1,49 @@
+from selenium.webdriver.remote.webdriver import WebDriver
+from selenium.webdriver.common.by import By
+from PIL import Image
+import time
+import os
+_scroll_to_bottom = "window.scroll({top:document.body.clientHeight,left:0,behavior:'auto'});"
+_scroll_to_y = "window.scroll({top:%d,left:0,behavior:'auto'});"
+_tmp_dir = "./tmp"
+_tmp_file = "%s/%%s_%%s.png" % _tmp_dir
+_body = "//body"
+def screenshot(driver:WebDriver, save_path):
+    file_name = os.path.basename(save_path)
+    if not os.path.exists(_tmp_dir):
+        os.mkdir(_tmp_dir)
+        
+    tmp_file_list = []
+    try:
+        tmp_file = _tmp_file % (file_name, 0)
+        driver.save_screenshot(tmp_file)
+        tmp_file_list.append(tmp_file)
+        body_h = driver.execute_script("return document.documentElement.scrollHeight")
+        current_h = driver.execute_script("return document.documentElement.clientHeight")
+        for i in range(1, int(body_h / current_h)):
+            driver.execute_script(_scroll_to_y % (current_h * i))
+            time.sleep(0.2)
+            driver.save_screenshot(_tmp_file % (file_name, i))
+            tmp_file_list.append(_tmp_file % (file_name, i))
+            merge_images(tmp_file, _tmp_file % (file_name, i), tmp_file)
+
+        driver.execute_script(_scroll_to_bottom)
+        end_file = _tmp_file % (file_name, "bottom")
+        driver.save_screenshot(end_file)
+        tmp_file_list.append(end_file)
+        merge_images(tmp_file, end_file,save_path,int(current_h - int(body_h % current_h)))
+    finally:
+        # 删除临时文件
+        for tmp in tmp_file_list:
+            os.remove(tmp)
+    
+
+def merge_images(image1: str, image2: str,output: str,overlap_size=0):
+    size = overlap_size * 2
+    img1,img2 = Image.open(image1), Image.open(image2)
+    size1, size2 = img1.size, img2.size
+    merge = Image.new("RGB", (size1[0], size1[1] + size2[1] - size))
+    loc1, loc2 = (0, 0), (0, size1[1] - size)
+    merge.paste(img1, loc1)
+    merge.paste(img2, loc2)
+    merge.save(output)