Python - 小玩意 - html 转 pdf

骑猪看日落 2023-10-16 13:38 51阅读 0赞

## 本地文件 ##

import pdfkit
    import os
    
    
    def convert_html_to_pdf(html_file, output_directory, pdfkit_config):
        base_name = os.path.basename(html_file)
        file_name_without_extension = os.path.splitext(base_name)[0]
        pdf_file = os.path.join(output_directory, f"{file_name_without_extension}.pdf")
    
        try:
            pdfkit.from_file(html_file, pdf_file, configuration=pdfkit_config)
            print(f"Converted {html_file} to {pdf_file}")
        except Exception as e:
            print(f"Failed to convert {html_file} to PDF: {str(e)}")
    
    
    if __name__ == '__main__':
    	# html存放路径
        input_directory = 'htmls'
        # pdf 存放路径
        output_directory = 'pdfs'
        # wkhtmltopdf安装路径
        wkhtmltopdf_path = r'D:\install_address\wkhtmltopdf\bin\wkhtmltopdf.exe'
    
        config = pdfkit.configuration(wkhtmltopdf=wkhtmltopdf_path)
    
        html_files = [os.path.join(input_directory, file) for file in os.listdir(input_directory) if file.endswith('.html')]
    
        for html_file in html_files:
            convert_html_to_pdf(html_file, output_directory, config)

## 本地文件 & 网络链接 ##

import os
    import pdfkit
    
    def convert_html_to_pdf(source, output_directory, pdfkit_config):
        if source.startswith('http'):
            # 处理来自网址的HTML
            pdf_file_name = source.split('/')[-1].split('?')[0] + '.pdf'
            pdf_file = os.path.join(output_directory, pdf_file_name)
    
            try:
                pdfkit.from_url(source, pdf_file, configuration=pdfkit_config)
                print(f"Converted URL '{source}' to {pdf_file}")
            except Exception as e:
                print(f"Failed to convert URL '{source}' to PDF: {str(e)}")
        elif os.path.isfile(source):
            # 处理本地HTML文件
            base_name = os.path.basename(source)
            file_name_without_extension = os.path.splitext(base_name)[0]
            pdf_file = os.path.join(output_directory, f"{file_name_without_extension}.pdf")
    
            try:
                pdfkit.from_file(source, pdf_file, configuration=pdfkit_config)
                print(f"Converted {source} to {pdf_file}")
            except Exception as e:
                print(f"Failed to convert {source} to PDF: {str(e)}")
        else:
            print(f"Unsupported source: {source}")
    
    
    if __name__ == '__main__':
        input_sources = [
            'https://lfsun666.blog.csdn.net/article/details/133148657?ydreferer'
            '=aHR0cHM6Ly9tcC5jc2RuLm5ldC9tcF9ibG9nL21hbmFnZS9hcnRpY2xlP3NwbT0xMDAxLjIwMTQuMzAwMS41NDQ4?ydreferer'
            '=aHR0cHM6Ly9tcC5jc2RuLm5ldC9tcF9ibG9nL21hbmFnZS9hcnRpY2xlP3NwbT0xMDAxLjIwMTQuMzAwMS41NDQ4',  # 网络链接
            'htmls/report.html',  # 本地HTML文件
            # 可以添加更多的链接或本地文件路径
        ]
        output_directory = 'pdfs'
        wkhtmltopdf_path = r'D:\install_address\wkhtmltopdf\bin\wkhtmltopdf.exe'
    
        config = pdfkit.configuration(wkhtmltopdf=wkhtmltopdf_path)
    
        for source in input_sources:
            convert_html_to_pdf(source, output_directory, config)