def test_lists_with_styles():
file_path = path.join(
path.abspath(path.dirname(__file__)),
'..',
'fixtures',
'lists_with_styles.docx',
)
actual_html = convert(file_path)
assert_html_equal(actual_html, '''
<html>
<ol data-list-type="decimal">
<li>AAA</li>
<li>BBB
<ol data-list-type="lower-roman">
<li>CCC</li>
<li>DDD
<ol data-list-type="upper-alpha">
<li>EEE
<ol data-list-type="lower-alpha">
<li>FFF</li>
</ol>
</li>
</ol>
</li>
</ol>
</li>
</ol>
</html>
''')
def docx_converter():
while True:
docx_path = raw_input('Please enter path to folder containing .docx files:')
docx_path_exists = os.path.exists(docx_path)
if docx_path_exists:
write_path = raw_input('Please enter path to write html files to (conversion begins automatically): ')
write_path_exists = os.path.exists(write_path)
if write_path_exists:
for subdir, dirs, files in os.walk(docx_path):
for file in files:
ext = os.path.splitext(file)[-1].lower()
if ext == '.docx':
file_path = os.path.join(docx_path, file)
html = convert(file_path, image_handler=handle_image)
print 'Converting: ' + file
# Give new html file same name as .docx original
html_file_path = os.path.join(write_path, os.path.splitext(file)[0])
html_file = open(html_file_path, 'w')
html_file.write(html)
html_file.close()
else:
print 'Please enter a valid path.'
else:
print 'Please enter a valid path.'
def test_tables_in_lists():
file_path = path.join(
path.abspath(path.dirname(__file__)),
'..',
'fixtures',
'tables_in_lists.docx',
)
actual_html = convert(file_path)
assert_html_equal(actual_html, '''
<html>
<ol data-list-type="decimal">
<li>AAA</li>
<li>BBB<br />
<table>
<tr>
<td>CCC</td>
<td>DDD</td>
</tr>
<tr>
<td>EEE</td>
<td>FFF</td>
</tr>
</table>
</li>
<li>GGG</li>
</ol>
</html>
''')
def test_bigger_font_size_to_header():
# Show when it is appropriate to convert p tags to h tags based on font
# size.
if not DETECT_FONT_SIZE:
raise SkipTest('Font size detection is disabled.')
file_path = path.join(
path.abspath(path.dirname(__file__)),
'..',
'fixtures',
'bigger_font_size_to_header.docx',
)
actual_html = convert(file_path)
assert_html_equal(actual_html, '''
<html>
<p>Paragraphs:</p>
<h2>Header</h2>
<p>paragraph 1</p>
<p>Lists:</p>
<ol data-list-type="decimal">
<li>bigger</li>
<li>smaller</li>
</ol>
<p>Tables:</p>
<table>
<tr>
<td>bigger</td>
<td>smaller</td>
</tr>
</table>
</html>
''')
def test_shift_enter():
file_path = path.join(
path.abspath(path.dirname(__file__)),
'..',
'fixtures',
'shift_enter.docx',
)
# Test just the convert without clean_html to make sure the first
# break tag is present.
actual_html = convert(file_path)
assert_html_equal(actual_html, '''
<html>
<p>AAA<br />BBB</p>
<p>CCC</p>
<ol data-list-type="decimal">
<li>DDD<br />EEE</li>
<li>FFF</li>
</ol>
<table>
<tr>
<td>GGG<br />HHH</td>
<td>III<br />JJJ</td>
</tr>
<tr>
<td>KKK</td>
<td>LLL</td>
</tr>
</table>
</html>
''')
def test_convert_p_to_h():
# Show when it is correct to convert a p tag to an h tag based on
# bold/italics
file_path = path.join(
path.abspath(path.dirname(__file__)),
'..',
'fixtures',
'convert_p_to_h.docx',
)
actual_html = convert(file_path)
assert_html_equal(actual_html, '''
<html>
<h2>AAA</h2>
<h2>BBB</h2>
<p>CCC</p>
<ol data-list-type="decimal">
<li><strong>DDD</strong></li>
<li><em>EEE</em></li>
<li>FFF</li>
</ol>
<table>
<tr>
<td><strong>GGG</strong></td>
<td><em>HHH</em></td>
</tr>
<tr>
<td>III</td>
<td>JJJ</td>
</tr>
</table>
</html>
''')
def test_fall_back():
file_path = 'test.doc'
def fall_back(*args, **kwargs):
return 'success'
html = convert(file_path, fall_back=fall_back, converter=_converter)
assert html == 'success'
def docxView(request):
#TODO: все к херам переписать по уму
from shutil import copyfile
from docx2html import convert
def handle_image(image_id, relationship_dict):
image_path = relationship_dict[image_id]
# Now do something to the image. Let's move it somewhere.
_, filename = os.path.split(image_path)
destination_path = os.path.join(MEDIA_ROOT, filename)
copyfile(image_path, destination_path)
# Return the `src` attribute to be used in the img tag
return '/protected%s%s' % (MEDIA_URL, filename)
fp = request.GET.get('f', None)
html = None
if fp:
try:
pm_file = PM_Files.objects.get(pk=int(fp))
if pm_file.type == 'docx':
html = convert(str(pm_file.file.path),
image_handler=handle_image)
elif pm_file.type == 'xlsx':
html = excelToHtml(str(pm_file.file.path))
except PM_Files.DoesNotExist:
pass
return HttpResponse(html)
def test_nested_tables():
file_path = path.join(
path.abspath(path.dirname(__file__)),
'..',
'fixtures',
'nested_tables.docx',
)
actual_html = convert(file_path)
# Find out why br tag is there.
assert_html_equal(actual_html, '''
<html>
<table>
<tr>
<td>AAA</td>
<td>BBB</td>
</tr>
<tr>
<td>CCC</td>
<td>
<table>
<tr>
<td>DDD</td>
<td>EEE</td>
</tr>
<tr>
<td>FFF</td>
<td>GGG</td>
</tr>
</table>
<br />
</td>
</tr>
</table>
</html>
''')
def test_list_to_header():
file_path = path.join(
path.abspath(path.dirname(__file__)),
'..',
'fixtures',
'list_to_header.docx',
)
actual_html = convert(file_path)
# It should be noted that list item `GGG` is upper roman in the word
# document to show that only top level upper romans get converted.
assert_html_equal(actual_html, '''
<html>
<h2>AAA</h2>
<ol data-list-type="decimal">
<li>BBB</li>
</ol>
<h2>CCC</h2>
<ol data-list-type="decimal">
<li>DDD</li>
</ol>
<h2>EEE</h2>
<ol data-list-type="decimal">
<li>FFF
<ol data-list-type="upper-roman">
<li>GGG</li>
</ol>
</li>
</ol>
</html>
''')
def test_extract_html():
file_path = path.join(
path.abspath(path.dirname(__file__)),
'..',
'fixtures',
'simple.docx',
)
actual_html = convert(file_path)
assert_html_equal(actual_html, '''
<html>
<p>
Simple text
</p>
<ol data-list-type="decimal">
<li>one</li>
<li>two</li>
<li>three</li>
</ol>
<table>
<tr>
<td>Cell1</td>
<td>Cell2</td>
</tr>
<tr>
<td>Cell3</td>
<td>cell4</td>
</tr>
</table>
</html>
''')
def test_nested_table_rowspan():
file_path = path.join(
path.abspath(path.dirname(__file__)),
'..',
'fixtures',
'nested_table_rowspan.docx',
)
actual_html = convert(file_path)
assert_html_equal(actual_html, '''
<html>
<table>
<tr>
<td colspan="2">AAA</td>
</tr>
<tr>
<td>BBB</td>
<td>
<table>
<tr>
<td rowspan="2">CCC</td>
<td>DDD</td>
</tr>
<tr>
<td>EEE</td>
</tr>
</table>
<br />
</td>
</tr>
</table>
</html>
''')
def test_has_title():
file_path = path.join(
path.abspath(path.dirname(__file__)),
'..',
'fixtures',
'has_title.docx',
)
actual_html = convert(file_path)
assert_html_equal(actual_html, '''<html><p>Text</p></html>''')
def test_unicode():
file_path = path.join(
path.abspath(path.dirname(__file__)),
'..',
'fixtures',
'greek_alphabet.docx',
)
actual_html = convert(file_path)
assert actual_html is not None
def convert_doc_to_html(input, outdir): # LibreOffice
print(input, '-->', outdir)
#subprocess.call(['soffice', '--headless', '--convert-to','html:XHTML Writer File:UTF8','--outdir', outdir, input])
#args = ['soffice', '--headless', '--convert-to', 'html:XHTML Writer File:UTF8', '--outdir', outdir, input]
#call_soffice(args)
html_parser = HTMLParser.HTMLParser()
html = convert(input) #使用docx2html模块将docx文件转成html串，随后你想干嘛都行
html_parser.unescape(html) #这句非常关键，docx2html模块将中文进行了转义，所以要将生成的字符串重新转义回来！
def test_special_chars():
file_path = path.join(
path.abspath(path.dirname(__file__)),
'..',
'fixtures',
'special_chars.docx',
)
actual_html = convert(file_path)
assert_html_equal(actual_html, '''
<html><p>& < > <a href="https://www.google.com/?test=1&more=2">link</a></p></html>''') # noqa
def test_inline_tags():
file_path = path.join(
path.abspath(path.dirname(__file__)),
'..',
'fixtures',
'inline_tags.docx',
)
actual_html = convert(file_path)
assert_html_equal(actual_html, '''
<html><p>This sentence has some <strong>bold</strong>, some <em>italics</em> and some <strong>underline</strong>, as well as a <a href="http://www.google.com/">hyperlink</a>.</p></html>''') # noqa
def readdoc(sfp, dfp):
print(sfp)
print(dfp)
docn = convert(sfp)
html_parser = HTMLParser.HTMLParser()
htmltemp = html_parser.enescape(docn)
print('读取docx文件成功')
with open(dfp, 'w', encoding='utf-8') as f:
f.write(htmltemp)
print('写入docx文件成功')
pass #对读取的world文件输出成html文件还要进行优化，按照客户的需求
def test_html_files(patch_zip_handler, patch_read):
def raise_assertion(*args, **kwargs):
raise AssertionError('Should not have called get_zip_file_handler')
patch_zip_handler.side_effect = raise_assertion
def return_text(*args, **kwargs):
return 'test'
patch_read.side_effect = return_text
# Try with an html file
file_path = 'test.html'
html = convert(file_path)
assert html == 'test'
# Try again with an htm file.
file_path = 'test.htm'
html = convert(file_path)
assert html == 'test'
def test_table_col_row_span():
file_path = path.join(
path.abspath(path.dirname(__file__)),
'..',
'fixtures',
'table_col_row_span.docx',
)
actual_html = convert(file_path)
assert_html_equal(actual_html, '''
<html>
<table>
<tr>
<td colspan="2">AAA</td>
</tr>
<tr>
<td rowspan="2">BBB</td>
<td>CCC</td>
</tr>
<tr>
<td>DDD</td>
</tr>
<tr>
<td>EEE</td>
<td rowspan="2">FFF</td>
</tr>
<tr>
<td>GGG</td>
</tr>
</table>
<table>
<tr>
<td>1</td>
<td>2</td>
<td>3</td>
<td>4</td>
</tr>
<tr>
<td>5</td>
<td colspan="2" rowspan="2">6</td>
<td>7</td>
</tr>
<tr>
<td>8</td>
<td>9</td>
</tr>
<tr>
<td>10</td>
<td>11</td>
<td>12</td>
<td>13</td>
</tr>
</table>
</html>
''')
def test_track_changes_on():
file_path = path.join(
path.abspath(path.dirname(__file__)),
'..',
'fixtures',
'track_changes_on.docx',
)
actual_html = convert(file_path)
assert_html_equal(actual_html, '''
<html><p>This was some content.</p></html>
''')
def save_editor(self, request, pk=None, *args, **kwargs):
file_res = File.objects.get(id=pk)
decrypt_file(
os.path.join(settings.MEDIA_ROOT + str(
crud.get(self.table, "*", 'where id=' +
pk)[0].get('owner_id')) + '/' +
base64.b16encode(file_res.modified_file_name)),
os.path.join(settings.MEDIA_ROOT + file_res.modified_file_name),
'123')
self.org_data = convert(settings.MEDIA_ROOT +
FileSerializer(File.objects.get(
id=pk)).data.get('modified_file_name'))
os.remove(
os.path.join(settings.MEDIA_ROOT + file_res.modified_file_name))
if self.org_data != request.data:
# Activity log
request_data = {}
param = {'field': 'file_id', 'file_id': pk, 'label': 'version'}
track_fields = {
c.can_read: c.read,
c.can_write: c.write,
c.can_delete: c.delete
}
request_data.update({'user_id': request.user.id})
log_view = LogView()
log_view.generate_log(request_data, param, "", track_fields)
f = open(
settings.MEDIA_ROOT + str(
crud.get(self.table, "*",
'where id=' + pk)[0].get('owner_id')) + '/' +
file_res.modified_file_name.split('.')[0] + '.html', 'w')
f.write(request.data['data'].encode())
f.close()
os.chdir(settings.MEDIA_ROOT + str(
crud.get(self.table, "*", 'where id=' +
pk)[0].get('owner_id')))
os.system('unoconv --format=' + file_res.name.split('.')[-1] +
' ' + settings.MEDIA_ROOT + str(
crud.get(self.table, "*", 'where id=' +
pk)[0].get('owner_id')) + '/' +
file_res.modified_file_name.split('.')[0] + '.html')
time.sleep(3)
os.remove(settings.MEDIA_ROOT + str(
crud.get(self.table, "*", 'where id=' +
pk)[0].get('owner_id')) + '/' +
file_res.modified_file_name.split('.')[0] + '.html')
encrypt_file(
os.getcwd() + '/' + file_res.modified_file_name,
os.getcwd() + '/' +
base64.b16encode(file_res.modified_file_name), '123')
os.remove(os.getcwd() + '/' + file_res.modified_file_name)
return Response({"hai": 'hai'})
def main():
if len(sys.argv) < 3:
DocxToPdf(sys.argv[1])
if len(sys.argv) < 3:
sys.exit(
"Usage: filename.py mypresentation.pdf / mypresentation.docx Method#"
)
src = sys.argv[1]
ParseMethod = sys.argv[2]
if "docx" in src:
html = convert(src)
Var_E = DataComputer(html)
if ParseMethod == 1:
Method1(html, Var_E)
else:
Method2(html, Var_E)
else:
basedir = os.path.dirname(os.path.realpath(__file__))
pdfdir = os.path.normpath(basedir + '/pdf')
docdir = os.path.normpath(basedir + '/doc')
docxdir = os.path.normpath(basedir + '/docx')
lowriter = '/usr/bin/soffice'
outfilter = ':"MS Word 2007 XML"'
outfilter = "'writer_pdf_import'"
abspath_pdf = os.path.normpath(os.path.join(pdfdir, src))
subprocess.call(
'{0} --infilter={1} --convert-to docx "{3}" --outdir "{2}"'.format(
lowriter, outfilter, docxdir, abspath_pdf),
shell=True)
time.sleep(5)
new_src = docxdir + '/' + src.split(".pdf")[0] + '.docx'
html = convert(new_src)
Var_E = DataComputer(html)
if ParseMethod == 1:
Method1(html, Var_E)
else:
Method2(html, Var_E)
def test_upper_alpha_all_bold():
file_path = path.join(
path.abspath(path.dirname(__file__)),
'..',
'fixtures',
'upper_alpha_all_bold.docx',
)
actual_html = convert(file_path)
assert_html_equal(actual_html, '''
<html>
<h2>AAA</h2>
<h2>BBB</h2>
<h2>CCC</h2>
</html>
''')
def test_headers_with_full_line_styles():
# Show that if a natural header is completely bold/italics that
# bold/italics will get stripped out.
file_path = path.join(
path.abspath(path.dirname(__file__)),
'..',
'fixtures',
'headers_with_full_line_styles.docx',
)
actual_html = convert(file_path)
assert_html_equal(actual_html, '''
<html>
<h2>AAA</h2>
<h2>BBB</h2>
<h2><strong>C</strong><em>C</em>C</h2>
</html>
''')
def test_simple_list():
file_path = path.join(
path.abspath(path.dirname(__file__)),
'..',
'fixtures',
'simple_lists.docx',
)
actual_html = convert(file_path)
assert_html_equal(actual_html, '''
<html>
<ol data-list-type="decimal">
<li>One</li>
</ol>
<ul>
<li>two</li>
</ul>
</html>
''')
def test_split_headers():
filename = 'split_header.docx'
file_path = path.join(
path.abspath(path.dirname(__file__)),
'..',
'fixtures',
'split_header.docx',
)
# preserve_images must be true in order for the image to not be removed.
# This is handled in build_import, however here we need to manually set it
# to True.
new_file_path, _ = _copy_file_to_tmp_dir(file_path, filename)
def image_handler(*args, **kwargs):
return 'test'
actual_html = convert(new_file_path, image_handler=image_handler)
assert_html_equal(actual_html, '''
<html><h2>AAA</h2><p>BBB</p><h2>CCC</h2></html>
''')
def test_has_image():
filename = 'has_image.docx'
file_path = path.join(
path.abspath(path.dirname(__file__)),
'..',
'fixtures',
'has_image.docx',
)
# preserve_images must be true in order for the image to not be removed.
# This is handled in build_import, however here we need to manually set it
# to True.
new_file_path, dp = _copy_file_to_tmp_dir(file_path, filename)
actual_html = convert(new_file_path)
assert_html_equal(actual_html, '''
<html>
<p>AAA<img src="%s/word/media/image1.gif" height="55" width="260" /></p>
</html>
''' % dp)
def test_nested_list():
file_path = path.join(
path.abspath(path.dirname(__file__)),
'..',
'fixtures',
'nested_lists.docx',
)
actual_html = convert(file_path)
assert_html_equal(actual_html, '''
<html>
<ol data-list-type="decimal">
<li>one</li>
<li>two</li>
<li>three
<ol data-list-type="decimal">
<li>AAA</li>
<li>BBB</li>
<li>CCC
<ol data-list-type="decimal">
<li>alpha</li>
</ol>
</li>
</ol>
</li>
<li>four</li>
</ol>
<ol data-list-type="decimal">
<li>xxx
<ol data-list-type="decimal">
<li>yyy</li>
</ol>
</li>
</ol>
<ul>
<li>www
<ul>
<li>zzz</li>
</ul>
</li>
</ul>
</html>
''')
def test_has_image_using_image_handler():
filename = 'has_image.docx'
file_path = path.join(
path.abspath(path.dirname(__file__)),
'..',
'fixtures',
'has_image.docx',
)
# preserve_images must be true in order for the image to not be removed.
# This is handled in build_import, however here we need to manually set it
# to True.
new_file_path, _ = _copy_file_to_tmp_dir(file_path, filename)
def image_handler(*args, **kwargs):
return 'test'
actual_html = convert(new_file_path, image_handler=image_handler)
assert_html_equal(actual_html, '''
<html><p>AAA<img src="test" height="55" width="260" /></p></html>
''')
def test_fake_headings_by_length():
# Show that converting p tags to h tags has a length limit. If the p tag is
# supposed to be converted to an h tag but has more than seven words in the
# paragraph do not convert it.
file_path = path.join(
path.abspath(path.dirname(__file__)),
'..',
'fixtures',
'fake_headings_by_length.docx',
)
actual_html = convert(file_path)
assert_html_equal(actual_html, '''
<html>
<h2>Heading.</h2>
<h2>Still a heading.</h2>
<p>
<strong>This is not a heading because it is too many words.</strong>
</p>
</html>
''')
def course_syllabus(request, slug):
course = Course.objects.get(slug=slug)
syllabus = Syllabus.objects.filter(course=course,user=request.user)
SyllabusFormset = modelformset_factory(Syllabus, form=SyllabusForm, extra=1, max_num=1)
formset_syl = SyllabusFormset(request.POST or None, request.FILES or None, queryset=syllabus)
BASE_DIR = os.path.dirname(os.path.dirname(__file__))
print tempfile.gettempdir()
if request.method == 'POST':
if formset_syl.is_valid():
for form in formset_syl:
form1 = form.save(commit=False)
form1.user = request.user
form1.path = request.get_full_path()
form1.course = course
if '.docx' in str(form1.syllabus):
form1.save()
else:
data = {}
data['response'] = False
new_data = json.dumps(data)
return HttpResponse(new_data, content_type='application/json')
AWS_KEY = #key
AWS_SECRET = #secret
aws_connection = S3Connection(AWS_KEY, AWS_SECRET)
obj = Syllabus.objects.get(course=course,user=request.user)
bucket_name = #bucket
key = aws_connection.get_bucket(bucket_name).get_key('media/' + str(obj.syllabus))
res = key.get_contents_to_filename(BASE_DIR +'/'+key.name)
html = convert(BASE_DIR +'/'+key.name)
obj.html = html
obj.save()
response_data = {}
response_data['response'] = True
new_data = json.dumps(response_data)
return HttpResponse(new_data, content_type='application/json')
def test_headers():
file_path = path.join(
path.abspath(path.dirname(__file__)),
'..',
'fixtures',
'headers.docx',
)
actual_html = convert(file_path)
assert_html_equal(actual_html, '''
<html>
<h2>This is an H1</h2>
<h3>This is an H2</h3>
<h4>This is an H3</h4>
<h5>This is an H4</h5>
<h6>This is an H5</h6>
<h6>This is an H6</h6>
<h6>This is an H7</h6>
<h6>This is an H8</h6>
<h6>This is an H9</h6>
<h6>This is an H10</h6>
</html>
''')
def conv_core(docx_filename_path,docx_filename,op_mode):
if os.path.isfile(docx_filename_path):
def handle_image(image_id, relationship_dict):
image_path = relationship_dict[image_id]
# Now do something to the image. Let's move it somewhere.
_, filename = os.path.split(image_path)
#extension = os.path.splitext(filename)[1]
#new_filename= os.path.splitext(filename)[0]
filename=filename.replace('image','%s_'%docx_filename)
destination_path = os.path.join('html/images/screenshots/',filename)
copyfile(image_path, destination_path)
# Return the `src` attribute to be used in the img tag
return 'images/screenshots/%s'%filename
html = convert(docx_filename_path, image_handler=handle_image)
html=html.replace('<html>','').replace('</html>','').replace('<p>Group type</p>','')
html=html.replace('<p>','<h3>',1).replace('</p>','</h3>',1).replace(' ',' ')
html=html.replace('<ol','<ul').replace('</ol>','</ul>').replace('data-list-type="decimal"','class="number-list"')
html=html.replace('“','“').replace('<table>','<table border="0" cellpadding="0">')
html=html.replace('<img','<img class="img-responsive"').replace('height="157" width="624" />','/>')
with open('template.html', 'r') as myfile:
data=myfile.read().replace('<!--conv_active_link-->', '<li class="active-topic"><span><a href="%(1)s.html">%(2)s</a></span></li>'%{"1" : docx_filename, "2" : docx_filename}).replace('<!--conv_content-->',html)
fo = open("html/%s.html"%docx_filename, "wb")
fo.write(data)
fo.close()
shutil.rmtree('docx/word')
print '******************************************************'
progressbar('Converting:','Complete')
print '******************************************************'
print 'TASK COMPLETED SUCCESSFULLY :)'
print '-Output path :html/%s.html'%docx_filename
if op_mode:
raw_input()
else:
print '******************************************************'
print 'ERROR:'
print '-File not found in path %s'%docx_filename_path
print '-Also make sure that the file extension is ".docx"'
convert_engine()
from docx2html import convert
html = convert('./Geit (utkast).docx')
myfile = open('testfile.txt', 'rw+')
myfile.write(html)
myfile.close()
