selenium网页截图总结

版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。

本文链接： https://blog.csdn.net/weixin_43695063/article/details/100701356

selenium网页截图总结(持续更新)不废话直接上代码

方法一

• 优点:(可视化浏览器)可以截长图

import pdfkit
from selenium import webdriver

driver = webdriver.Chrome(executable_path=r".\chromedriver.exe")
driver.get('https://blog.csdn.net/weixin_43695063/article/details/100701356') # 一篇有滚动条博客的url
ac=driver.current_url 
confg = pdfkit.configuration(wkhtmltopdf=r'E:\install\wkhtmltopdf\bin\wkhtmltopdf.exe')
pdfkit.from_url(ac, './jmeter11.pdf',configuration=confg)
driver.quit()

方法二

• 全网页截图
• 优点:PhantomJS可以截全图
• 缺点:Chrome和Firefox只能截可视区域

from selenium import webdriver

driver = webdriver.Chrome(executable_path=r".\chromedriver.exe")
driver.get('https://blog.csdn.net/weixin_43695063/article/details/100701356') # 一篇带有滚动条博客的url
driver.save_screenshot('screenshot.png')
driver.quit()

方法三

• 定位区块截图
• 优点:PhantomJS可以截全图
• 缺点:Chrome和Firefox只能截可视区域

from selenium import webdriver
from PIL import Image

driver = webdriver.Chrome(executable_path=r".\chromedriver.exe")
driver.get('https://www.baidu.com')
driver.save_screenshot(r'img.png')  	# 截一张全图
baidu = driver.find_element_by_id('su') # 截图按钮百度一下
left = baidu.location['x']  			# 区块截图左上角在网页中的x坐标
top = baidu.location['y']  				# 区块截图左上角在网页中的y坐标
right = left + baidu.size['width'] 		# 区块截图右下角在网页中的x坐标
bottom = top + baidu.size['height']  	# 区块截图右下角在网页中的y坐标
print({"left": left, "top": top, "right": right, "bottom ": bottom})
print("baidu.size['width']:%s" % baidu.size['width'])
print("baidu.size['height']:%s" % baidu.size['height'])
picture = Image.open(r'img.png')
picture = picture.crop((left, top, right, bottom))  # 定位区块截图
picture.save(r'img1.png')
driver.quit()

方法四

• 全网页截图
• 优点:PhantomJS可以截全图
• 缺点:Chrome和Firefox只能截可视区域

from selenium import webdriver

driver = webdriver.Chrome(executable_path=r".\chromedriver.exe")
driver.get('https://blog.csdn.net/weixin_43695063/article/details/100701356') # 一篇带有滚动条博客的url
driver.find_element_by_xpath('//*[@id="container"]').screenshot_as_png
with open('image/img.png', 'wb') as f:
	f.write(img)
driver.quit()

方法五

• 全网页截图
• 优点:模拟鼠标键盘操作浏览器
• 缺点:系统运行期间,不可以动光标和键盘

import time
import pyperclip,pyautogui
import win32api
import win32con
from selenium import webdriver

driver = webdriver.Chrome(executable_path=r".\chromedriver.exe")
driver.get('https://blog.csdn.net/weixin_43695063/article/details/100701356') # 一篇带有滚动条博客的url

def baocun_pdf():
    # ctrl+p
    time.sleep(2)
    win32api.keybd_event(17, 0, 0, 0)
    win32api.keybd_event(80, 0, 0, 0)
    win32api.keybd_event(17, 0, win32con.KEYEVENTF_KEYUP, 0)
    win32api.keybd_event(80, 0, win32con.KEYEVENTF_KEYUP, 0)
    time.sleep(1)
    #两次tap
    win32api.keybd_event(9, 0, 0, 0)
    win32api.keybd_event(9, 0, win32con.KEYEVENTF_KEYUP, 0)
    win32api.keybd_event(9, 0, 0, 0)
    win32api.keybd_event(9, 0, win32con.KEYEVENTF_KEYUP, 0)
    time.sleep(1)
    #一次下
    win32api.keybd_event(40, 0, 0, 0)
    win32api.keybd_event(40, 0, win32con.KEYEVENTF_KEYUP, 0)
    for i in range(7):
        time.sleep(0.3)
        win32api.keybd_event(9, 0, 0, 0)
        win32api.keybd_event(9, 0, win32con.KEYEVENTF_KEYUP, 0)
    time.sleep(3)

    #点击保存
    win32api.keybd_event(13, 0, 0, 0)
    win32api.keybd_event(13, 0, win32con.KEYEVENTF_KEYUP, 0)

    time.sleep(1)
    #将地址以及文件名复制
    pic_dir = r'C:\install\.pdf'
    pyperclip.copy(pic_dir)
    #粘贴
    pyautogui.hotkey('ctrlleft','V')
    time.sleep(1)
    #确认保存
    pyautogui.press('enter')
    time.sleep(1)
    try:
        win32api.keybd_event(37, 0, 0, 0)
        win32api.keybd_event(37, 0, win32con.KEYEVENTF_KEYUP, 0)
        time.sleep(1)
        pyautogui.press('enter')
    except:
        pass
   
baocun_pdf()
driver.quit()

方法六

• 可视化浏览器截图
• 优点:可视化浏览器截带有滚动条的长图
• 缺点: 自定义截取高度和次数,图片与图片之间可能会有重复部分,完美衔接需要调试滑动的高度

import fitz
import pdfkit
import requests
from selenium import webdriver
import time
import glob
import os

import warnings
warnings.simplefilter("ignore", ResourceWarning)

chrome_options =webdriver.ChromeOptions()
chrome_options.add_argument('--start-maximized ')
# chrome_options.add_argument('--headless')
# chrome_options.add_argument('--disable-gpu')
# chrome_options.add_argument("window-size=1920,1080")
driver = webdriver.Chrome(executable_path=r".\chromedriver.exe",options=chrome_options)

driver.get('https://blog.csdn.net/weixin_43695063/article/details/100701356') # 一篇带有滚动条博客的url
driver.maximize_window()
driver.fullscreen_window()


def get_img_pdf_return_url(driver):
    num=0
    num_while=936 #每次截取的后,滚动条滚动的高度,根据可视化浏览器的高度拟定(自己定)
    while True:
        driver.save_screenshot("C:/Users/Administrator/Desktop/img_pdf/img{}.png".format(num))
        js="var q=document.documentElement.scrollTop={}".format(num_while)
        driver.execute_script(js)
        time.sleep(0.2)
        print("截图:",num_while,"成功")
        # print(driver.title)
        num+=1
        if num_while >7198: # 滑动总高度之后,退出循环截取(总高度自己定)
            break
        num_while+=936 

    doc = fitz.open()
    # print("doc:", f)
    # 从规定路径下读取图片，确保按文件名排序
    for img in sorted(glob.glob(r"C:\Users\Administrator\Desktop\img_pdf\*.png")):
        print(img)
        imgdoc = fitz.open(img)
        # print("imgdoc",imgdoc)
        # 使用图片创建单页的 PDF
        pdfbytes = imgdoc.convertToPDF()
        # print("pdfbytes", pdfbytes)
        # 将当前页插入文档
        imgpdf = fitz.open("pdf", pdfbytes)
        doc.insertPDF(imgpdf)
    if os.path.exists(r"C:\Users\Administrator\Desktop\img_pdf\aa.pdf"): #根据自己的路径自定义
        os.remove(r"C:\Users\Administrator\Desktop\img_pdf\aa.pdf")
    doc.save(r"C:\Users\Administrator\Desktop\img_pdf\aa.pdf")
    doc.close()
    
get_img_pdf_return_url(driver)
driver.quit()

方法七(明天写…)

• 优点:
• 缺点: