def get_word_from_html(self, html_string):
document = Document()
new_parser = HtmlToDocx()
new_parser.add_html_to_document(html_string, document)
doc_io = io.BytesIO()
document.save(doc_io)
doc_io.seek(0)
return doc_io
def render_to_docx(context, template, doc_type, opis=''):
tpl = get_template(template)
html_text = tpl.render(context)
document = Document()
style = document.styles['Normal']
font = style.font
font.name = 'Dijakritika'
new_parser = HtmlToDocx()
new_parser.add_html_to_document(html_text, document)
temp_file = tempfile.TemporaryFile()
document.save(temp_file)
novi_dokument = add_file_to_django(doc_type, opis, temp_file, 'docx')
return novi_dokument.rendered_file.name
def generate_word_application(application, request):
# figure out the filename
target_dir = os.path.join(settings.BASE_DIR, 'media', 'temp')
target_file = "temp_export.docx"
target_file_path = os.path.join(target_dir, target_file)
target_url = os.path.join(settings.MEDIA_ROOT, 'temp', target_file)
document = Document()
t = loader.get_template('res/application_print/main_word.html')
context = get_application_context(application, request)
rendered = t.render(context)
new_parser = HtmlToDocx()
new_parser.add_html_to_document(rendered, document)
document.save(target_file_path)
return target_url
def download(request):
"""Download a transliteration as document"""
# Get the download type
qd = request.POST
if 'downloadtype' in qd and 'transliteration' in qd:
# Get the download type and the data itself
dtype = qd['downloadtype']
transliteration = qd['transliteration']
if dtype == "docx":
dext = ".docx"
sContentType = "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
# Transform HTML to DOC
document = Document()
new_parser = HtmlToDocx()
new_parser.add_html_to_document(transliteration, document)
buffer = io.BytesIO() # Start memory stream
document.save(buffer) # Save to memory stream
buffer.seek(0) # Rewind the stream
# Determine a file name
sBase = self.object.name
sFileName = "trans_{}{}".format(sBase, dext)
if dtype == "docx":
response = StreamingHttpResponse(streaming_content=buffer,
content_type=sContentType)
response['Content-Encoding'] = 'UTF-8'
response[
'Content-Disposition'] = 'attachment; filename="{}"'.format(
sFileName)
else:
response = HttpResponse(ddata, content_type=sContentType)
response[
'Content-Disposition'] = 'attachment; filename="{}"'.format(
sFileName)
else:
# Return something else
response = None
# Return the response we have
return response
def create_document(csv_data):
try:
html_file = open("temp.html", "w")
html_file.write("<!DOCTYPE html>\n")
html_file.write("<html>\n")
html_file.write("<head>\n")
html_file.write("<meta charset='utf-8'>\n")
html_file.write("</head>\n")
html_file.write("<body>\n")
row_data = {}
for key, val in inclusion_list.items():
html_file.write(f"<h1> {key} </h1>\n")
for a in val:
for i in csv_data:
if i["Issue key"] == a:
row_data["Issue key"] = check_string(i["Issue key"])
row_data["Summary"] = check_string(i["Summary"])
row_data["Description"] = check_string(
i["Description"])
html_file.write(
f"<h3> {row_data['Issue key']} : {row_data['Summary']} </h3>\n"
)
line = row_data['Description']
line = OrderedBulletList(line).parse_string()
line = UnOrderedBulletList(line).parse_string()
line = replace_image(line)
line = parse_bold(line)
line = parse_heading(line)
html_file.write(f"{line}\n")
html_file.write("</body>\n")
html_file.write("</html>\n")
# Convert HTML file to docx
new_parser = HtmlToDocx()
new_parser.parse_html_file("temp.html", "gaps_items_html_converted")
except Exception as e:
logging.error(str(e))
def genDoc(request):
# print(request.POST.get('ids')[0])
final = ""
parser = HtmlToDocx()
for doc in Document.objects.all():
final += doc.content + "<br/>\n"
# final += "<br/>\n<hr/>\n<h2>References:</h2>"
final += "<br/><h2>References</h2><br/>\n"
for doc in Document.objects.all():
final += doc.reference + "<br/>"
result = parser.parse_html_string(final)
print(parser.parse_html_string(final))
response = HttpResponse(
content_type=
'application/vnd.openxmlformats-officedocument.wordprocessingml.document'
)
response['Content-Disposition'] = 'attachment; filename=download.docx'
result.save(response)
return response
"""
将HTML转为word，注意把源码的编码设为utf-8
"""
from htmldocx import HtmlToDocx
new_parser = HtmlToDocx()
new_parser.parse_html_file('1.html', '1.docx')
from htmldocx import HtmlToDocx new_parser = HtmlToDocx() file = '/home/akshay/MindCodes/writingartist/writing_artist/user_files/1/2021-02-10_10_37_21_211100.html' new_parser.from_file(file)
def insert_text(document, text):
my_parser = HtmlToDocx()
md = MarkdownIt()
md.enable('table')
my_parser.add_html_to_document(md.render(text), document)
def export_docx(path: str, document: Document) -> str:
html = Exporter.render_html(document.content, document.title)
html_parser = HtmlToDocx()
docx = html_parser.parse_html_string(html)
docx.save(path)
return path