Python实现html转png的完美方案介绍

try:
    with sync_playwright() as p:
        try:
            browser = p.chromium.launch(headless=True)  # 强制无头模式
            page = browser.new_page()
            page.goto(" os.path.abspath(temp_html_path))  # 标准化路径
            
            # 使用智能等待代替固定等待
            page.wait_for_selector(".main-body", state="attached", timeout=10000)
            
            # 添加渲染完成检查
            page.wait_for_function(
                "document.querySelector('.main-body').clientHeight > 0",
                timeout=10000
            )
            
            # 截图操作增加区域检查
            if page.locator(".main-body").count() == 0:
                raise Exception("目标元素不存在")
            
            page.locator(".main-body").screenshot(path=output_path)
        except PlaywrightTimeoutError as e:
            print(f"元素加载超时：{str(e)}")
            return False
        except Error as e:  # Playwright通用错误
            print(f"浏览器操作异常：{str(e)}")
            return False
        finally:
            browser.close()
except Exception as e:
    print(f"Playwright初始化失败：{str(e)}")
    return False

browser = p.chromium.launch(
    headless=True,
    args=[
        "--disable-gpu",
        "--no-sandbox",
        "--disable-dev-shm-usage"
    ]
)

page.locator(".main-body").screenshot(
    path=output_path,
    type="png",
    quality=100,
    omit_background=True
)

page.emulate_media(media="screen")
page.evaluate("() => { document.body.style.background = 'transparent'; }")

from pathlib import Path
temp_html_path = str(Path(temp_html_path).resolve())

file_url = f" if sys.platform == "win32" else f"

if not Path(output_path).exists():
    print(f"截图失败，可能原因：\n1. 图表元素未正确渲染\n2. 文件路径权限问题\n3. 浏览器配置错误")
    print("建议检查：\n- 使用page.content()输出当前页面HTML\n- 验证CSS选择器有效性")

from pyecharts import options as opts
from pyecharts.charts import Table
from pyecharts.render import make_snapshot
from snapshot_phantomjs import snapshot

from pyecharts.options import ComponentTitleOpts

table = Table()

​​​​​​​headers = ["City name", "Area", "Population", "Annual Rainfall"]
rows = [
    ["Brisbane", 5905, 1857594, 1146.4],
    ["Adelaide", 1295, 1158259, 600.5],
    ["Darwin", 112, 120900, 1714.7],
    ["Hobart", 1357, 205556, 619.5],
    ["Sydney", 2058, 4336374, 1214.8],
    ["Melbourne", 1566, 3806092, 646.9],
    ["Perth", 5386, 1554769, 869.4],
]
table.add(headers, rows)
table.set_global_opts(
    title_opts=ComponentTitleOpts(title="Table-基本示例", subtitle="我是副标题支持换行哦")
)
table.render("table_base.html")

file_path = "{}/".format(os.path.dirname(os.path.abspath("/root/echarts.min.js")))
Table(init_opts=opts.InitOpts(js_host=file_path))
make_snapshot(snapshot,table.render(),"table0.pdf")

import aspose.words as aw
doc = aw.Document("table_base.html")
imageOptions = aw.saving.ImageSaveOptions(aw.SaveFormat.JPEG)
imageOptions.jpeg_quality = 10
imageOptions.horizontal_resolution = 72

# Save the pages as JPG
for page in range(0, doc.page_count):
extractedPage = doc.extract_pages(page, 1)
extractedPage.save(f"C:\\Files\\Images\\Page_{page + 1}.jpg", imageOptions)

import imgkit
 
path_wkimg = r'D:\Program Files\wkhtmltopdf\bin\wkhtmltoimage.exe'  # 工具路径
cfg = imgkit.config(wkhtmltoimage=path_wkimg)
#可以修改参数，图片大小、语言等
# options={
#     page-size:""
# }
# 将html文件转为图片
imgkit.from_file('table_base.html', 'hellotable.jpg', config=cfg)