Python 第三方模块之 pdfkit

pdfkit，把 HTML+CSS 格式的文件转换成 PDF 格式文档的一个工具。

其实，pdfkit 是 html 转成 pdf 工具包 wkhtmltopdf 的 Python 封装。所以，首先安装 wkhtmltopdf 。 一般情况下，wkhtmltopdf需要手动安装，网站是 https://wkhtmltopdf.org/downloads.html，根据自己的操作系统下载对应的版本即可。ps：记住安装目录啊，下面要用到。

上面说到了pdfkit这个模块，这个是第三方模块，需要安装，使用pip安装即可。

pip install pdfkit

示例

pdfkit 可以将网页、html文件以及字符串生成pdf文件

 

import pdfkit
 

confg = pdfkit.configuration(wkhtmltopdf='C:\Python35\wkhtmltopdf.exe')# 这里指定一下wkhtmltopdf的路径，这就是我为啥在前面让记住这个路径
url = 'https://blog.csdn.net/fenglepeng/article/details/103670893'
pdfkit.from_url(url, 'aaa.pdf', configuration=confg)
# from_url这个函数是从url里面获取内容
# 这有3个参数，第一个是url，第二个是文件名，第三个就是khtmltopdf的路径
 
pdfkit.from_file('my.html', 'bbb.pdf', configuration=confg)
# from_file这个函数是从文件里面获取内容
# 这有3个参数，第一个是一个html文件，第二个是文生成的pdf的名字，第三个就是khtmltopdf的路径
 
html = '''
<div>
<h1>title</h1>
<p>content</p>
</div>
'''
pdfkit.from_string(html, 'ccc.pdf', configuration=confg)
# from_file这个函数是从一个字符串里面获取内容
# 这有3个参数，第一个是一个字符串，第二个是文生成的pdf的名字，第三个就是khtmltopdf的路径

API

def from_url(url, output_path, options=None, toc=None, cover=None, configuration=None, cover_first=False): 
    """ 
    把从URL获取文件转换为PDF文件 
    :param url: URL 或 URL列表 
    :param output_path: 输出PDF文件的路径。如果是参数等于False，意味着文件将会以字符串的形式返回，得到文本文件。
    :param options: (可选) dict with wkhtmltopdf global and page options, with or w/o '--' 
    :param toc: (可选) dict with toc-specific wkhtmltopdf options, with or w/o '--' 
    :param cover: (可选) string with url/filename with a cover html page 
    :param configuration: (可选)实例化 pdfkit.configuration.Configuration() 
    :param configuration_first: (可选) if True, cover always precedes TOC 
    Returns：成功返回True 
    """ 


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 
    """ 


def from_string(input, output_path, options=None, toc=None, cover=None, css=None, configuration=None, cover_first=False):
    """
    Convert given string or strings to PDF document
    :param input: string with a desired text. Could be a raw text or a html file
    :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 input string
    :param configuration: (optional) instance of pdfkit.configuration.Configuration()
    :param configuration_first: (optional) if True, cover always precedes TOC
    Returns: True on success
    """