ad导出pdf为啥只有一个叫_爬虫-导出Rust官网文档为 PDF

def 

def from_file(input, output_path, options=None, toc=None, cover=None, css=None,
              configuration=None, cover_first=False):
    """
    Convert HTML file or files to PDF document
    :param input: path to HTML file or list with paths or file-like object
    :param output_path: path to output PDF file. False means file will be returned as string.
    :param options: (optional) dict with wkhtmltopdf options, with or w/o '--'
    :param toc: (optional) dict with toc-specific wkhtmltopdf options, with or w/o '--'
    :param cover: (optional) string with url/filename with a cover html page
    :param css: (optional) string with path to css file which will be added to a single input file
    :param configuration: (optional) instance of pdfkit.configuration.Configuration()
    :param configuration_first: (optional) if True, cover always precedes TOC
    Returns: True on success
    """
 
    r = PDFKit(input, 'file', options=options, toc=toc, cover=cover, css=css,
               configuration=configuration, cover_first=cover_first)
 
    return r.to_pdf(output_path)

def 

import pdfkit
pdfkit.from_url("https://rustlang-cn.org/office/rust/book/", 'out.pdf', configuration=pdfkit.configuration(
                wkhtmltopdf="path/to/wkhtmltopdf.exe"))

class DownloadVuePress2Pdf:
 
    def get_content_and_next_url(self, content): # content 为网页内容
         # 获取链接和销毁不必要元素
        navbar = soup.select('.navbar')
        if len(navbar):
            navbar[0].decompose()
 
        sidebar = soup.select('.sidebar')
        if len(sidebar):
            sidebar[0].decompose()
 
        page_edit = soup.select('.page-edit')
        if len(page_edit):
            page_edit[0].decompose()
 
        # 注意下一页链接在底部导航栏元素中,
        # 要先获取链接后,才能销毁元素,顺序不能颠倒
        next_span = soup.select(".next")
        if len(next_span):
            next_span_href = next_span[0].a['href']
        else:
            next_span_href = None
 
        page_nav = soup.select('.page-nav')
        if len(page_nav):
            page_nav[0].decompose()

for link in links:
     if not link['href'].startswith("http"):
        link['href'] = css_domain + link['href'] # css_domain 为 css 默认域名,需要设置,获取方式可见下图

pdfkit.from_file([文件列表], "导出的文件名称.pdf", options=options, configuration=config)