HTML转PDF

1. 安装必要的包:

pip install pdfkit

pip install wkhtmltopdf

apt-get install wkhtmltopdf

2. 关闭display配置：

vim ~/.bashrc

export QT_QPA_PLATFORM='offscreen'

source ~/.bashrc

3. 代码（需要注意html编码方式）：

# -*- coding: utf-8 -*-
# @Time    : 2021/9/26 10:49
# @Author  : lijun
import pdfkit
import os
import re


def rectify_charset(html, charset='utf-8'):
    if '', '', html)
    else:
        if '' in html and '' in html:
            re.sub(r'', 'nn', html)
        else:
            html = 'nnn' + html
    return html


def main():
    options = {
        'page-size': 'Letter',
        'margin-top': '0.75in',
        'margin-right': '0.75in',
        'margin-bottom': '0.75in',
        'margin-left': '0.75in',
        'encoding': "utf-8",
        'custom-header': [('Accept-Encoding', 'gzip')],
        'cookie': [
            ('cookie-name1', 'cookie-value1'),
            ('cookie-name2', 'cookie-value2'),
        ],
        'no-outline': None
    }

    base_path = './'
    in_html_name_list = os.listdir(base_path + '/test_data/my_html_0/')
    out_path = base_path + '/test_out/my_html_0/'

    for idx, html_name in enumerate(in_html_name_list):
        # pdfkit.from_file(
        #     base_path + '/test_data/my_html_0/' + html_name,
        #     out_path + html_name[::-1].split('.', 1)[-1][::-1] + '.pdf',
        #     options=options)

        html = ''.join(open(base_path + '/test_data/my_html_0/' + html_name, 'r', encoding='utf-8').readlines())
        html = rectify_charset(html, 'utf-8')
        pdfkit.from_string(
            html,
            out_path + html_name[::-1].split('.', 1)[-1][::-1] + '.pdf',
            options=options)

        # pdfkit.from_string(
        #     'hello',
        #     out_path + html_name[::-1].split('.', 1)[-1][::-1] + '.pdf',
        #     options=options)

        print('current processed num: ', idx + 1)


if __name__ == '__main__':
    main()

4.相关链接：

安装wkhtmltopdf：Installing wkhtmltopdf · JazzCore/python-pdfkit Wiki · GitHub