python实现html网页文件转pdf+html网页文件转png的方法
#将HTML文件导出为PDF
def html_to_pdf(html_path,pdf_path='.\\pdf_new.pdf',html_encoding='UTF-8',path_wkpdf = r'.\Tools\wkhtmltopdf.exe'):
'''
将HTML文件导出为PDF
:param html_path:str类型,目标HTML文件的路径,可以是一个路径,也可以是多个路径,以list方式传入路径;或者一个或者多个网址;或者为一个字符串
:param pdf_path:str类型,需要导出的PDF文件的路径
:param html_encoding:str类型,html的编码格式,具体要看html页面到底是以什么编码格式保存的
:param path_wkpdf:str类型,path_wkpdf = r'.\Tools\wkhtmltopdf.exe' # 工具路径
:return:
'''
cfg = pdfkit.configuration(wkhtmltopdf=path_wkpdf)
options = {
"encoding": html_encoding # 这个具体要看html页面到底是以什么编码格式保存的
}
if 'http' in str(html_path) and ('html' not in str(html_path) or 'HTML' not in str(html_path)): #判断是否为非网址
#从url获取html,再转为pdf
print('http=>pdf')
# pdfkit.from_url('https://httpbin.org/ip', 'ip.pdf', options=options, configuration=cfg)
# pdfkit.from_url(['https://httpbin.org/ip', 'https://httpbin.org/ip'], 'ip.pdf', options=options,configuration=cfg) # 传入列表
pdfkit.from_url(html_path, pdf_path, options=options, configuration=cfg)
elif 'html' in str(html_path) or 'HTML' in str(html_path): #判断是否为HTML文件
#将html文件转为pdf
print('html,str=>pdf')
# pdfkit.from_file(r'./helloworld.html', 'helloworld.pdf',options=options, configuration=cfg)
pdfkit.from_file(html_path, pdf_path, options=options, configuration=cfg)
elif isinstance(html_path, list) and ('html' in str(html_path) or 'HTML' in str(html_path)): #判断html目标是否为list,
# 如:[r'./helloworld.html', r'./111.html', r'./222.html']
print('html,list=>pdf')
pdfkit.from_file(html_path, pdf_path,options=options, configuration=cfg) # 传入列表
else:
#将字符串转为pdf
print('from_string=>pdf')
pdfkit.from_string(html_path, pdf_path,options=options, configuration=cfg)
所需要用的附件程序:
wkhtmltoimage.exe
免费下载地址:https://download.csdn.net/download/zh6526157/75392603https://download.csdn.net/download/zh6526157/75392603
#将HTML文件导出为图片
def html_to_png(html_path,pdf_path='.\\pdf_new.pdf',html_encoding='UTF-8',path_wkpdf = r'.\Tools\wkhtmltoimage.exe'):
'''
将HTML文件导出为图片
:param html_path:str类型,目标HTML文件的路径,可以是一个路径,也可以是多个路径,以list方式传入路径;或者一个或者多个网址;或者为一个字符串
:param pdf_path:str类型,需要导出的图片文件的路径
:param html_encoding:str类型,html的编码格式,具体要看html页面到底是以什么编码格式保存的
:param path_wkpdf:str类型,path_wkpdf = r'.\Tools\wwkhtmltoimage.exe' # 工具路径
:return:
'''
cfg = imgkit.config(wkhtmltoimage=path_wkpdf)
options = {
"encoding": html_encoding # 这个具体要看html页面到底是以什么编码格式保存的
}
if 'http' in str(html_path) and ('html' not in str(html_path) or 'HTML' not in str(html_path)): #判断是否为非网址
#从url获取html,再转为pdf
print('http=>png')
# pdfkit.from_url('https://httpbin.org/ip', 'ip.png', options=options, configuration=cfg)
# pdfkit.from_url(['https://httpbin.org/ip', 'https://httpbin.org/ip'], 'ip.png', options=options,configuration=cfg) # 传入列表
imgkit.from_url(html_path, pdf_path, options=options, config=cfg)
elif 'html' in str(html_path) or 'HTML' in str(html_path): #判断是否为HTML文件
#将html文件转为pdf
print('html,str=>png')
# pdfkit.from_file(r'./helloworld.html', 'helloworld.png',options=options, configuration=cfg)
imgkit.from_file(html_path, pdf_path, options=options, config=cfg)
elif isinstance(html_path, list) and ('html' in str(html_path) or 'HTML' in str(html_path)): #判断html目标是否为list,
# 如:[r'./helloworld.html', r'./111.html', r'./222.html']
print('html,list=>png')
imgkit.from_file(html_path, pdf_path,options=options, config=cfg) # 传入列表
else:
#将字符串转为pdf
print('from_string=>png')
imgkit.from_string(html_path, pdf_path,options=options, config=cfg)
所需要用的附件程序:
wkhtmltopdf.exe
免费下载地址:
https://download.csdn.net/download/zh6526157/75392499https://download.csdn.net/download/zh6526157/75392499