#!/usr/bin/python3
# -*- coding:utf-8 -*-
import time
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from PIL import Image
def screenshot_to_pdf_and_png(link):
''' 参数：网址
功能: 保存网址截图
解决了截图不全问题
解决了懒加载问题
保存俩种图片格式
'''
path = './'
# 1> 获取chrome参数对象
chrome_options = Options()
# 2> 添加无头参数r,一定要使用无头模式，不然截不了全页面，只能截到你电脑的高度
chrome_options.add_argument('--headless')
# 3> 为了解决一些莫名其妙的问题关闭 GPU 计算
chrome_options.add_argument('--disable-gpu')
# 4> 为了解决一些莫名其妙的问题浏览器不动
chrome_options.add_argument('--no-sandbox')
# 5> 添加驱动地址。 由于在函数内，设置参数chrome_options需要再导入
driver = webdriver.Chrome(service=r'D:\银联工作\test\chromedriver.exe' ,chrome_options=chrome_options)
# 6> 模仿手动滑动滚动条，解决懒加载问题
try:
driver.implicitly_wait(20)
driver.get(link)
# 模拟人滚动滚动条,处理图片懒加载问题
js_height = "return document.body.clientHeight"
driver.get(link)
k = 1
height = driver.execute_script(js_height)
while True:
if k * 500 < height:
js_move = "window.scrollTo(0,{})".format(k * 500)
print(js_move)
driver.execute_script(js_move)
time.sleep(0.2)
height = driver.execute_script(js_height)
k += 1
else:
break
time.sleep(1)
# 7> # 直接截图截不全，调取最大网页截图
width = driver.execute_script(
"return Math.max(document.body.scrollWidth, document.body.offsetWidth, document.documentElement.clientWidth, document.documentElement.scrollWidth, document.documentElement.offsetWidth);")
height = driver.execute_script(
"return Math.max(document.body.scrollHeight, document.body.offsetHeight, document.documentElement.clientHeight, document.documentElement.scrollHeight, document.documentElement.offsetHeight);")
print(width, height)
# 将浏览器的宽高设置成刚刚获取的宽高
driver.set_window_size(width + 100, height + 100)
time.sleep(1)
png_path = path + '/{}.png'.format('xx网址截图')
# 截图并关掉浏览器
driver.save_screenshot(png_path)
driver.close()
# png转pdf
image1 = Image.open(png_path)
im1 = image1.convert('RGB')
pdf_path = png_path.replace('.png', '.pdf')
im1.save(pdf_path)
except Exception as e:
print(e)
if __name__ == '__main__':
screenshot_to_pdf_and_png("http://www.douban.com")