html2img 将HTML转化为图片

步骤

1. 用浏览器显示html

2. 截屏

3. 后处理，截取有效部分

代码

import os
import pyppeteer
from pyppeteer import launch
import asyncio
import cv2

async def get_jpgs(html_path, img_path):
    browser = await launch()
    page = await browser.newPage()
    await asyncio.wait_for(page.goto('file://'+ html_path), timeout=30)
    await page.screenshot({'path': img_path})

    # 关闭浏览器
    await page.close()
    await browser.close()


def postprocess(img_path):
    img = cv2.imread(img_path)
    height, width, channel = img.shape
    for i in range(width):
        if img[:,i,:].min() < 255:
            min_x = i
            break

    j = width-1
    while(j>0):
        if img[:,j,:].min() < 255:
            max_x = j
            break
        j -= 1

    for k in range(height):
        if img[k,:,:].min() < 255:
            min_y = k
            break

    l = height - 1
    while(l>0):
        if img[l,:,:].min() < 255:
            max_y = l
            break
        l -= 1

    img_table = img[min_y-2:max_y+2, min_x-2:max_x+2,:]
    cv2.imwrite(img_path, img_table)

if __name__ == "__main__":
    import glob
    html_path_list = glob.glob('/home/mi/下载/不合格/不合格/htmls/*.html')
    # html_path必须为绝对路径
    for html_path in html_path_list:
        img_path = html_path.replace("htmls", "imgs").replace(".html", ".jpg")
        asyncio.get_event_loop().run_until_complete(get_jpgs(html_path, img_path))
        postprocess(img_path)

效果图

输入的html内容如下：