【URL 转换为PDF】HTML转换为PDF

1、方法1 pdfkit

安装依赖

# 安装 wkhtmltopdf（系统级）
# Ubuntu/Debian
sudo apt install wkhtmltopdf

# macOS
brew install wkhtmltopdf

# Windows 下载安装：https://wkhtmltopdf.org/downloads.html

# 安装 Python 库
pip install pdfkit

import pdfkit

# 将网页转为 PDF
def url_to_pdf(url, output_path):
    try:
        pdfkit.from_url(url, output_path)
        print(f"PDF 已保存为: {output_path}")
    except Exception as e:
        print(f"转换失败: {e}")

# 示例调用（替换为你的链接）
url_to_pdf(
    "https://etcnew.sdut.edu.cn/meol/common/script/preview/download_preview.jsp?fileid=15400633&resid=1451996&lid=65791&preview=preview",
    "水泥工艺学-第五章硅酸盐水泥熟料的煅烧.pdf"
)

方法2：pyppeteer （很高级）适用于JavaScript渲染的网页（如Vue、React页面）。

import asyncio
from pyppeteer import launch

async def html_to_pdf(url, output_path):
    browser = await launch(headless=True)
    page = await browser.newPage()
    await page.goto(url, {'waitUntil': 'networkidle2'})
    await page.pdf({'path': output_path, 'format': 'A4', 'printBackground': True})
    await browser.close()

# 使用示例
asyncio.run(html_to_pdf("https://example.com", "output.pdf"))

方法3：playwright （最高级，最稳定版本）

# 更新 pip
python3 -m pip install -U pip

# 安装 Playwright Python 库
pip install playwright

# 下载并安装所需的浏览器（Chromium、Firefox、WebKit）
playwright install


playwright --version

from playwright.sync_api import sync_playwright

with sync_playwright() as p:
    browser = p.chromium.launch(headless=True)
    page = browser.new_page()
    page.goto("https://example.com")
    page.pdf(path="page.pdf", format="A4")
    browser.close()