def convert(output_type, docx_path, output_path):
if output_type == '--html':
output = PyDocX.to_html(docx_path)
elif output_type == '--markdown':
output = PyDocX.to_markdown(docx_path)
else:
print('Only valid output formats are --html and --markdown')
return 2
with open(output_path, 'wb') as f:
f.write(output.encode('utf-8'))
return 0
def wordtohtml(request):
media_root = os.path.join(settings.BASE_DIR, 'upload/')
if request.method == "POST":
file = request.FILES.get('file')
if file is not None:
t = time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(time.time()))
id = shortuuid.uuid()
word = wordhtml(word=file, time=t, uuid=id)
word.save()
file_path = media_root + str(word.word)
html = PyDocX.to_html(file_path)
html_name = str(word.uuid) + ".html"
txt_name = media_root + "word/" + html_name
f = open(txt_name, 'w', encoding="utf-8")
f.write(html)
f.close()
if settings.DEBUG:
url = "http://127.0.0.1:8000/upload/word/" + html_name
else:
url = "https://www.manjiexiang.cn/upload/word/" + html_name
return HttpResponseRedirect(url)
else:
me = Me.objects.all()
return render(request, "wordtohtml.html", {"msg": me[0]})
else:
me = Me.objects.all()
return render(request, "wordtohtml.html", {"msg": me[0]})
def get_img(file):
html = PyDocX.to_html(file)
soup = BeautifulSoup(html, 'lxml')
images_in_docx = []
images_in_docx.append("aaaaaaaaaaaaaa")
# for img in soup.findAll('img'):
# reg = re.compile('data.*?/(.*?);', re.S)
# style_img = reg.findall(img['src'])[0]
# strg = img['src'].replace("data:image/wmf;base64,", "").replace("data:image/jpeg;base64,", "")
# byte = base64.urlsafe_b64decode(strg)
# t0 = int(round(time.time() * 1000))
# tmp_path = '/tmp/%d.%s' % (t0, str(style_img))
# with open(tmp_path, 'wb') as file:
# file.write(byte)
# if style_img == 'wmf':
# t1 = int(round(time.time() * 1000))
# png_path = '/tmp/%d.png' % t1
# os.system('convert %s %s' % (tmp_path, png_path))
# f = open(png_path, 'rb')
# url = put(f)
# f.close()
# img['src'] = url
# images_in_docx.append(img)
# os.remove(png_path)
# os.remove(tmp_path)
# else:
# f = open(tmp_path, 'rb')
# url = put(f)
# f.close()
# img['src'] = url
# images_in_docx.append(img)
# os.remove(tmp_path)
return images_in_docx
def read_word(file):
proxy = []
doc = docx.Document(file)
for para in doc.paragraphs:
proxy.append(para._element.xml) # 返回docx文档的xml文件
threads = []
# q = Queue
q = {}
t1 = threading.Thread(target=getMathml, args=(proxy, 'mmls_in_para', q))
threads.append(t1)
html = PyDocX.to_html(file)
t2 = threading.Thread(target=get_img, args=(html, 'images_in_para', 'images_in_table', q))
threads.append(t2)
t1.start()
t2.start()
t1.join()
t2.join()
# for t in threads:
# t.setDaemon(True)
# t.start()
# t.join()
mmls_in_para = q.get('mmls_in_para')
images_in_para, images_in_table = q.get('images_in_para'), q.get('images_in_table')
table_html, table_para = get_table(doc, images_in_table) # 返回表格数据
paragraphs = get_para_html(proxy, mmls_in_para, images_in_para, table_html, table_para) # 得到文档的段落信息，返回的是HTML标签
return paragraphs
def docxtract(docxfile, **kwargs):
'''
Get a docx file and extract chapters. Return an array for further processing by the user.
'''
header = [u'h1', u'h2', u'h3', u'h4']
html = PyDocX.to_html(docxfile)
html = cleanhtml(html, **kwargs)
# Get the tree
p = False
tree = []
for child in html.find_all(True):
if child.name in header:
if p:
tree.append([ptext, p])
p = False
tree.append(["<b>%s</b>" % child.get_text(), unicode(child)])
else:
if child.get_text().strip():
if p:
p = ''.join([p, unicode(child)])
else:
p = unicode(child)
ptext = "%s..." % child.get_text()[:80]
if p:
tree.append([ptext, p])
return tree
def docx2html(file_path):
'''
将一个docx转换成html
:param file_path:
:return:
'''
return PyDocX.to_html(file_path)
def store_document():
sys.setdefaultencoding('utf-8')
# Pass in a path
html = PyDocX.to_html(open('cmpe273-greensheet.docx', 'rb'))
db.docCollection.insert({"HTML": html, "FileName": 'cmpe273-greensheet'})
return "sucess"
def _main_(tournament):
os.chdir('C:\School\Quiz Bowl\Quizbowl Packets\\' + tournament)
files = os.listdir(os.curdir)
q = open(tournament + ' answers.csv', 'w')
writer = csv.DictWriter(q, fieldnames=['Full Answer', 'Underlined Answer', 'Tournament', 'Packet'],
lineterminator='\n')
writer.writeheader()
for f in files:
html = PyDocX.to_html(f).decode('Windows-1252').encode('utf-8')
html = clean_file(html)
answers = re.findall(r'ANSWER: (?P<id>.*?)(?:</li>|<br />|</p>)', html)
und = []
for a in answers:
underlined = re.findall(r'<span class=\"pydocx-underline\">(?P<id>.*?)</span>', a)
output = ""
for u in underlined:
output += ' ' + u.strip()
und.append(output.strip())
for i in range(0, len(answers)):
answer = re.sub(r'<[^>]*>', '', answers[i]).strip()
writer.writerow({'Full Answer': answer.encode('utf-8'), 'Underlined Answer': und[i].encode('utf-8'),
'Tournament': tournament, 'Packet': f})
q.close()
shutil.copy(tournament + ' answers.csv', 'C:\School\Quiz Bowl\Stats\Answers')
os.remove(tournament + ' answers.csv')
def docx_to_html(docx_path):
docx_html = PyDocX.to_html(docx_path)
style_start = docx_html.find("<style>")
style_end = docx_html.find("</style>")
docx_html = docx_html[:style_start] + docx_html[style_end:]
docx_html = '<div>' + docx_html.replace("_", " ") + '</div>'
return docx_html
def main():
#修改为遍历时操作
filelist=os.listdir(config.filepath)
for file in filelist:
if file.endswith(".docx"):
print("start to solve ",file)
filepath=config.filepath+"/"+file
name=os.path.basename(filepath)
temp_photo_path=temppath+os.path.sep+name.replace(".docx","")+os.path.sep
if not os.path.exists(temp_photo_path):
os.makedirs(temp_photo_path)
# 使用pydocx转化为html
html = PyDocX.to_html(filepath)
bsoup = bs4.BeautifulSoup(html, "lxml")
imglist = bsoup.find_all("img")
for img in imglist:
#将html中的图片保存并转换后存入html中
img["src"],path=savephoto(img["src"], temp_photo_path)
with open(temp_photo_path + name.replace(".docx", ".html"), "w", encoding="utf-8") as file:
file.write(bsoup.prettify())
#将html转为docx
#获取所有p标签
dstpath=temp_photo_path + name
newdoc=docx.Document(os.getcwd()+os.path.sep+"docx/templates/default.docx")
bodycontent = bsoup.find("body")
bodychild = bodycontent.contents
for child in bodychild:
handle_tag(child, newdoc,temp_photo_path)
newdoc.save(dstpath)
def insert_document():
msg = ''
if request.method == 'POST':
uploaded_file = request.files['file']
uploaded_file.save(secure_filename(uploaded_file.filename))
html = PyDocX.to_html(open(uploaded_file.filename, 'rb'))
parse_store_content(html)
return "File successfully parsed and uploaded"
def trans_to_html():
for one_file in glob.glob('*.docx'):
name = one_file.replace('.docx', '')
html = PyDocX.to_html(one_file)
f = open(name + '.html' ,'w',encoding = 'utf-8')
f.write(html)
f.close()
def merge_docx(docx_list=None, out_htmlpath=None):
"""
docx_list is a list of strings which contains the (absolute) path of DOC/DOCX files to be merged.
MERGE_DOCX() will follow the index order of docx_list for appending.
Returns the HTML file as string.
If OUT_HTMLPATH is given, write the HTML file out as well.
"""
if docx_list is None:
return None
cleaner = Cleaner()
parser = HTMLParser(encoding='utf-8')
html_list = []
for path in docx_list:
try:
tmp_html = PyDocX.to_html(path)
html_list.append(cleaner.clean_html(lxml.html.fromstring(tmp_html, parser=parser)))
except:
#'MalformedDocxException'
try:
# Pretend it is a html
html_file = '{}.html'.format(path)
with open(html_file, 'rb') as tmp:
tmp_html = tmp.read()
tmp_html = tmp_html.decode('utf-8')
html_list.append(cleaner.clean_html(lxml.html.fromstring(tmp_html, parser=parser)))
except:
# Cannot convert
continue
#print html_list
if len(html_list)>1:
#Append element at the end of first body
main_body = html_list[0].xpath('./body')[0]
for tree in html_list[1:]:
elem_list = tree.xpath('./body/*')
for elem in elem_list:
main_body.append(elem)
elif len(html_list)==1:
main_body = html_list[0].xpath('./body')[0]
else:
try:
main_body = html_list[0].xpath('./body')[0]
except IndexError:
# no body content. Most likely just an image/appendix
return None
# Convert ElementTree back to string
# in this way we will lose the 'style' info in html_list[0][0], which is usually in header,
# but not sure if it will cause any differences to parser later on. Probably not.
html_str = lxml.etree.tostring(main_body)
if out_htmlpath is not None:
with open(out_htmlpath, 'wb') as tmp:
tmp.write(html_str.encode('utf-8'))
return html_str
def file_change(input, output='out.html'):
html = PyDocX.to_html(input)
# the title
html = html.replace('pydocx-center', 'pydocx-center subtitle', -1)
# the subtitle
html = html.replace('pydocx-center subtitle', 'pydocx-center title', 2)
with open(output, 'w', encoding='utf-8') as f:
f.write(html)
f.close
def docx2html(docx_filepath, html_filename=None):
with open(docx_filepath, 'rb') as docx_file:
html = PyDocX.to_html(docx_file)
xmltree = etree.fromstring(html)
prettyxml = etree.tostring(xmltree, pretty_print=True)
if html_filename is None:
html_filename = os.path.splitext(docx_filepath)[0] + '.html'
with open(html_filename, 'w+b') as html_file:
html_file.write(prettyxml)
def docx2pdf(filepath, dirpath, filename):
#结果是html，xswl
# wdFormatPDF = 17
in_file = filepath
out_path = dirpath + '/Webpages'
create_dir(out_path)
html = PyDocX.to_html(in_file)
f = open(filename, 'w', encoding="utf-8")
f.write(html)
f.close()
def insert_document():
msg = ''
if request.method == 'POST':
uploaded_file = request.files['file']
uploaded_file.save(secure_filename(uploaded_file.filename))
html = PyDocX.to_html(open(uploaded_file.filename, 'rb'))
file_name = str(uploaded_file.filename)
db[file_name].insert({"filename": file_name, "HTML": html})
parse_store_content(file_name)
return "File successfully uploaded"
def insert_document():
if request.method == 'POST':
f = request.files['file']
f.save(secure_filename(f.filename))
html = PyDocX.to_html(open(f.filename, 'rb'))
db.greensheetdocs.insert({
"filename":"CMPE273",
"HTML":html
})
return "Successfully Uploaded"
def convert_docx_html(srcfile):
"""
转换docx文件为html文件
:param srcfile: docx文件
:return:
"""
html = PyDocX.to_html(srcfile)
name = srcfile[:srcfile.rfind(".")]
f = open(name.encode("gbk") + ".html", 'w')
f.write(html.encode("utf-8"))
f.close()
def docx2html(_path_docx):
# html = PyDocX.to_html("test.docx")
# html = PyDocX.to_html(r'E:\\3101A0CV-20170615-H3C RPS800-A 用户手册-6PW101\06-正文.docx')
html = PyDocX.to_html(_path_docx)
# f = open("test.html", 'w', encoding="utf-8")
path_html = _path_docx.split("\\")[-1].split(".")[0] + ".html"
f = open(path_html, 'w', encoding="utf-8")
f.write(html)
f.close()
return path_html
def get_img(file):
"""
:param file:文件对象
:return:返回文档中的图片
"""
html = PyDocX.to_html(file)
print('html{}'.format(html))
soup = BeautifulSoup(html, 'lxml')
images_in_para = []
images_in_table = []
for img in soup.find_all('img'):
if img.find_parents('table') != []:
img['src'] = "$$$$$$$$$$$$$$$$"
images_in_table.append(str(img))
else:
img['src'] = "aaaaaaaaaaaa"
images_in_para.append(str(img))
# reg = re.compile('data.*?/(.*?);', re.S)
# style_img = reg.findall(img['src'])[0]
# strg = img['src'].replace("data:image/wmf;base64,", "").replace("data:image/jpeg;base64,", "")
# byte = base64.urlsafe_b64decode(strg)
# t0 = int(round(time.time() * 1000))
# tmp_path = '/tmp/%d.%s' % (t0, str(style_img))
# with open(tmp_path, 'wb') as file:
# file.write(byte)
# if style_img == 'wmf':
# t1 = int(round(time.time() * 1000))
# png_path = '/tmp/%d.png' % t1
# os.system('convert %s %s' % (tmp_path, png_path))
# f = open(png_path, 'rb')
# url = put(f)
# f.close()
# img['src'] = url
# if img.find_parents('table') != []:
# images_in_table.append(img)
# else:
# images_in_para.append(img)
# os.remove(png_path)
# os.remove(tmp_path)
# else:
# f = open(tmp_path, 'rb')
# url = put(f)
# f.close()
# img['src'] = url
# if img.find_parents('table') != []:
# images_in_table.append(img)
# else:
# images_in_para.append(img)
# os.remove(tmp_path)
return images_in_para, images_in_table
def to_html():
#transfer all docx files into html through this for loop.
for one_file in glob.glob('*.docx'):
#extract the name of each employee
name = re.compile(r'(.*?)员工履历').findall(one_file)[0]
#extract content of docx file
html = PyDocX.to_html(one_file)
#create a html file
f = open(name + '.html', 'w', encoding='utf-8')
#save the content into this html file.
f.write(html)
#save and close the html file.
f.close()
def docx_ol(request, file_id):
file_info = FileInfo.objects.get(id=file_id)
init_path = file_info.file_path
html_path = file_info.file_path.split('.')[0] + '.html'
html_name = file_info.file_name.split('.')[0] + '.html'
# if file_info.file_type =='doc':
# doc2x(file_info.file_path)
# init_path=file_info.file_path.split('.')[0]+'.docx'
# pythoncom.CoInitialize()
html = PyDocX.to_html(init_path)
f = open(html_path, 'w', encoding="utf-8")
f.write(html)
f.close()
shutil.copy(html_path,
'D:\\python\\jzyy\\fileserver\\templates\\fileserver\\ol')
return render(request, 'fileserver/ol/%s' % html_name)
def upload(request):
if request.method == 'POST': # 获取对象
file = request.FILES.get("file", None)
print(file.name)
bs = base64.b64decode(file.name)
filename = str(bs, 'ISO-8859-1')
print(filename)
extension = fileExtension(filename)
print(extension)
html = None
if (extension == '.docx' or extension == '.doc'):
html = PyDocX.to_html(file)
if (extension == '.xls' or extension == '.xlsx'):
xd = pd.ExcelFile(file)
df = xd.parse()
html = df.to_html(header=True, index=False)
return HttpResponse(html)
def docx_to_html(filepath, overwrite=False):
"""
Converts docx file to in-memory html string
:param filepath: full path to the file to convert
:return: unicode string
"""
html_file = '{}.html'.format(filepath)
if not os.path.exists(html_file) or overwrite:
#res = pydocx.docx2html(filepath)
res = PyDocX.to_html(filepath)
with open(html_file, 'wb') as tmp:
tmp.write(res.encode('utf-8'))
else:
with open(html_file, 'rb') as tmp:
res = tmp.read().decode('utf-8')
return res
def index(request):
if request.method == "GET":
papername = request.GET.get('filename', None)
paper = PaperGrade.objects.get(PaperName=papername)
username = request.session.get('username', None)
user = UserInfo.objects.get(Name=username)
user.PaperChecking = papername
user.save()
if paper.file_type() is 'docx':
html = PyDocX.to_html(paper)
return render(request, html) #不知对错
else:
return render(
request, 'All/index.html',
{'filename': r'/File/' + paper.PaperName}) #url写法自我怀疑人生中
else:
return render(request, 'All/index.html')
return render(request, 'All/index.html')
def _create_pdf(self, file):
_, extension = os.path.splitext(file.file.name)
aws_response = requests.get(self._get_aws_url(file.file, 5))
content = ContentFile(aws_response.content)
if extension in ['.xlsx', '.xls', '.xlb']:
preview_file = f'preview;name;data:application/vnd.openxmlformats-officedocument.spreadsheetml.sheet;base64,{base64.b64encode(content.read()).decode("utf-8")}'
return Response(
{
'preview': preview_file,
'extension': extension,
'title': file.name
},
status=status.HTTP_200_OK)
elif extension == '.pdf':
preview_file = f'preview;name;data:application/pdf;base64,{base64.b64encode(content.read()).decode("utf-8")}'
return Response(
{
'preview': preview_file,
'extension': extension,
'title': file.name
},
status=status.HTTP_200_OK)
elif extension == '.docx':
html = PyDocX.to_html(content)
elif extension == '.rtf':
html = rtf.getHtml(content.read().decode('UTF-8'))
else:
raise ValidationError(
"File is required, expected format: pdf, doc, docx, xls, xlsx, rtf"
)
response = HttpResponse()
response['Content-Disposition'] = 'attachment; filename="report.pdf"'
pisa.CreatePDF(html, dest=response)
preview_file = f'preview;name;data:application/pdf;base64,{base64.b64encode(response.content).decode("utf-8")}'
return Response(
{
'preview': preview_file,
'extension': extension,
'title': file.name
},
status=status.HTTP_200_OK)
def get_img(file):
html = PyDocX.to_html(file)
soup = BeautifulSoup(html, 'lxml')
images_in_para = []
images_in_table = []
for img in soup.find_all('img'):
reg = re.compile('data.*?/(.*?);', re.S)
style_img = reg.findall(img['src'])[0]
strg = img['src'].replace("data:image/wmf;base64,", "").replace("data:image/jpeg;base64,", "")
byte = base64.urlsafe_b64decode(strg)
t0 = int(round(time.time() * 1000))
tmp_path = '/tmp/%d.%s' % (t0, str(style_img))
with open(tmp_path, 'wb') as file:
file.write(byte)
if style_img == 'wmf':
t1 = int(round(time.time() * 1000))
png_path = '/tmp/%d.png' % t1
os.system('convert %s %s' % (tmp_path, png_path))
f = open(png_path, 'rb')
url = put(f)
f.close()
img['src'] = url
if img.find_parents('table') != []:
images_in_table.append(img)
else:
images_in_para.append(img)
os.remove(png_path)
os.remove(tmp_path)
else:
f = open(tmp_path, 'rb')
url = put(f)
f.close()
img['src'] = url
if img.find_parents('table') != []:
images_in_table.append(img)
else:
images_in_para.append(img)
os.remove(tmp_path)
return images_in_para, images_in_table
def get_img(file):
html = PyDocX.to_html(file)
soup = BeautifulSoup(html, 'lxml')
images_in_para = []
images_in_table = []
for img in soup.find_all('img'):
reg = re.compile('data.*?/(.*?);', re.S)
style_img = reg.findall(img['src'])[0]
strg = re.sub(re.compile("data:[/\w]*;base64,", re.S | re.I), '',
img['src'])
byte = base64.urlsafe_b64decode(strg)
t0 = str(uuid.uuid4()) or int(round(time.time() * 1000))
tmp_path = '/tmp/{}.{}'.format(t0, str(style_img))
with open(tmp_path, 'wb') as file:
file.write(byte)
if style_img == 'wmf':
t1 = str(uuid.uuid4()) or int(round(time.time() * 1000))
png_path = '/tmp/{}.png'.format(t1)
os.system('convert %s %s' % (tmp_path, png_path))
with open(png_path, 'rb') as f:
url = put(f)
img['src'] = url
if img.find_parents('table'):
images_in_table.append(img)
else:
images_in_para.append(img)
os.remove(png_path)
os.remove(tmp_path)
else:
with open(tmp_path, 'rb') as f:
url = put(f)
img['src'] = url
if img.find_parents('table'):
images_in_table.append(img)
else:
images_in_para.append(img)
os.remove(tmp_path)
return images_in_para, images_in_table
def word2html(htmlfile, wordfile):
html = PyDocX.to_html(wordfile)
f = open(htmlfile, 'w', encoding="utf-8")
f.write(html)
f.close()
print("data end")
def gui_parse():
global __file__ # to fix stupid
__file__ = os.path.abspath(__file__) # __file__ handling
_file_ = os.path.basename(__file__) # in python 2
global debug
root = Tk()
root.withdraw()
sys.stderr = codecs.getwriter('utf8')(sys.stderr)
parser = argparse.ArgumentParser()
parser.add_argument('filename', nargs='?')
parser.add_argument('--debug', '-d', action='store_true')
args = parser.parse_args()
if args.debug:
debug = True
if args.filename is None:
args.filename = tkFileDialog.askopenfilename(
filetypes=[
('Word 2007+','*.docx'),
('Plain text','*.txt'),
])
os.chdir(os.path.dirname(os.path.abspath(args.filename)))
if os.path.splitext(args.filename)[1] == '.txt':
with codecs.open(args.filename, 'r', 'utf8') as input_file:
input_text = input_file.read()
input_text = input_text.replace('\r','')
final_structure = chgk_parse(input_text)
elif os.path.splitext(args.filename)[1] == '.docx':
from pydocx import PyDocX
from bs4 import BeautifulSoup
from parse import parse
import base64
import html2text
input_docx = PyDocX.to_html(args.filename)
bsoup = BeautifulSoup(input_docx)
if args.debug:
with codecs.open('debug.pydocx', 'w', 'utf8') as dbg:
dbg.write(input_docx)
def generate_imgname(ext):
imgcounter = 1
while os.path.isfile('{:03}.{}'
.format(imgcounter, ext)):
imgcounter += 1
return '{:03}.{}'.format(imgcounter, ext)
for tag in bsoup.find_all('style'):
tag.extract()
for tag in bsoup.find_all('p'):
if tag.string:
tag.string = tag.string + SEP
for tag in bsoup.find_all('b'):
tag.unwrap()
for tag in bsoup.find_all('strong'):
tag.unwrap()
for tag in bsoup.find_all('i'):
tag.string = '_' + tag.string + '_'
tag.unwrap()
for tag in bsoup.find_all('em'):
tag.string = '_' + tag.string + '_'
tag.unwrap()
for tag in bsoup.find_all('li'):
if tag.string:
tag.string = '- ' + tag.string
for tag in bsoup.find_all('img'):
imgparse = parse('data:image/{ext};base64,{b64}', tag['src'])
imgname = generate_imgname(imgparse['ext'])
tag.insert_before('(img {})'.format(imgname))
if not args.debug:
with open(imgname, 'wb') as f:
f.write(base64.b64decode(imgparse['b64']))
tag.extract()
for tag in bsoup.find_all('a'):
if rew(tag.string) == '':
tag.extract()
else:
tag.string = tag['href']
tag.unwrap()
h = html2text.HTML2Text()
h.body_width = 0
txt = (h.handle(bsoup.prettify())
.replace('\\-','')
.replace('\\.','.')
.replace('( ', '(')
.replace('[ ', '[')
.replace(' )', ')')
.replace(' ]', ']')
.replace(' :', ':')
)
if args.debug:
with codecs.open('debug.debug', 'w', 'utf8') as dbg:
dbg.write(txt)
final_structure = chgk_parse(txt)
else:
sys.stderr.write('Error: unsupported file format.' + SEP)
sys.exit()
os.chdir(os.path.dirname(os.path.abspath(__file__)))
with codecs.open(
make_filename(args.filename), 'w', 'utf8') as output_file:
output_file.write(
compose_4s(final_structure))
print('Please review the resulting file {}:'.format(
make_filename(args.filename)))
subprocess.call(shlex.split('{} "{}"'
.format(
TEXTEDITOR,
make_filename(args.filename)).encode('cp1251',errors='replace')))
from pydocx import PyDocX
html = PyDocX.to_html("111.docx")
f = open("test.html", 'w', encoding="utf-8")
f.write(html)
f.close()
def convert(self): self._raw = PyDocX.to_html(self.path) bs = BeautifulSoup(self._raw, 'html.parser') self.data = bs.body
def papertest():
html = PyDocX.to_html('./paperPDF/' + 'bitcoin.docx')
print(html)
return html
import os, sys
import os
from pydocx import PyDocX
html = PyDocX.to_html("2.docx")
print(html)
from pydocx import PyDocX
"""
旧包：docx2html，此包要求python版本较低
新包路径如下：
https://github.com/CenterForOpenScience/pydocx
"""
docx_file = r'D:\十二刻度-个人信息及隐私政策.docx'
html_fle = r'D:\result.html'
html = PyDocX.to_html(docx_file)
with open(html_fle, encoding='UTF-8', mode='w') as f:
f.write(html)