def compare_versions():
resource_id_1 = request.form['v_o_id']
resource_id_2 = request.form['v_t_id']
version_1 = request.form['v_o']
version_2 = request.form['v_t']
html_1 = ScriptData.get_html_for_version(resource_id_1, version_1)
html_2 = ScriptData.get_html_for_version(resource_id_2, version_2)
if len(html_1) < 10000 and len(html_2) < 10000:
return diff(html_1, html_2)
begining_string = ''
while '</p>' in html_1:
first_tag = html_1.index('</p>') + 4
if html_1[:first_tag] == html_2[:first_tag]:
begining_string += html_1[:first_tag]
html_1 = html_1[first_tag:]
html_2 = html_2[first_tag:]
else:
break
end_string = ''
while '</p>' in html_1:
last_tag_start = html_1.rfind('<p CLASS=')
length_of_tag = len(html_1) - last_tag_start
if html_1[-length_of_tag:] == html_2[-length_of_tag:]:
end_string = end_string + html_1[-length_of_tag:]
html_1 = html_1[:-length_of_tag]
html_2 = html_2[:-length_of_tag]
else:
break
return begining_string + diff(html_1, html_2) + end_string
def compare_versions():
resource_id_1 = request.form['v_o_id']
resource_id_2 = request.form['v_t_id']
version_1 = request.form['v_o']
version_2 = request.form['v_t']
html_1 = ScriptData.get_html_for_version(resource_id_1, version_1)
html_2 = ScriptData.get_html_for_version(resource_id_2, version_2)
if len(html_1) < 10000 and len(html_2) < 10000:
return diff(html_1, html_2)
begining_string = ''
while '</p>' in html_1:
first_tag = html_1.index('</p>') + 4
if html_1[:first_tag] == html_2[:first_tag]:
begining_string += html_1[:first_tag]
html_1 = html_1[first_tag:]
html_2 = html_2[first_tag:]
else:
break
end_string = ''
while '</p>' in html_1:
last_tag_start = html_1.rfind('<p CLASS=')
length_of_tag = len(html_1) - last_tag_start
if html_1[-length_of_tag:] == html_2[-length_of_tag:]:
end_string = end_string + html_1[-length_of_tag:]
html_1 = html_1[:-length_of_tag]
html_2 = html_2[:-length_of_tag]
else:
break
return begining_string + diff(html_1, html_2) + end_string
def main(argv=None):
if not argv:
argv = sys.argv # pragma: no cover
with codecs.open(argv[1], 'r', 'utf-8') as file_a:
html_a = file_a.read()
with codecs.open(argv[2], 'r', 'utf-8') as file_b:
html_b = file_b.read()
print diff(html_a, html_b, cutoff=0.0, pretty=False)
def main(argv=None):
if not argv:
argv = sys.argv # pragma: no cover
with open(argv[1]) as file_a:
html_a = file_a.read()
with open(argv[2]) as file_b:
html_b = file_b.read()
print diff(html_a, html_b, cutoff=0.0, pretty=True)
def diff_html(ref_path, gen_path):
res = True
with open(ref_path) as ref_file:
ref_html = ref_file.read()
with open(gen_path) as gen_file:
gen_html = gen_file.read()
result = diff(ref_html, gen_html, cutoff=0.0, pretty=True)
with open ('result.html', 'w') as f:
f.write (result)
parser = etree.HTMLParser()
tree = etree.parse ('result.html', parser=parser)
root = tree.getroot()
inserted = root.findall(".//ins")
deleted = root.findall(".//del")
if inserted or deleted:
diff_filename = '%s.diff.html' % gen_path
sys.stderr.write ("There's a difference, you can open %s"
" with your browser to look at it\n" % diff_filename)
with open (diff_filename, 'w') as f:
f.write ('<head><link rel="stylesheet" type="text/css"'
'href="../diff_highlight.css"></head>')
f.write (result)
res = False
os.unlink ('result.html')
return res
def main(argv=None):
if not argv:
argv = sys.argv # pragma: no cover
with open(argv[1]) as file_a:
html_a = file_a.read()
with open(argv[2]) as file_b:
html_b = file_b.read()
print(diff(html_a, html_b, cutoff=0.0, pretty=True))
def main(argv=None):
if not argv:
argv = sys.argv # pragma: no cover
with codecs.open(argv[1], 'r', 'utf-16') as file_a:
html_a = file_a.read()
with codecs.open(argv[2], 'r', 'utf-16') as file_b:
html_b = file_b.read()
with codecs.open('output.html', 'w', 'utf-16') as file_o:
file_o.write(diff(html_a, html_b, cutoff=0.0, pretty=True))
def main(argv=None):
if not argv:
argv = sys.argv # pragma: no cover
with open(argv[1]) as file_a:
html_a = file_a.read()
with open(argv[2]) as file_b:
html_b = file_b.read()
output_filename = f"tmp/doc_diff/output_{secrets.token_urlsafe(6)}.html"
f = open(output_filename, "w")
f.write(diff(html_a, html_b, cutoff=0.0, pretty=True))
f.close()
print(output_filename)
def html_tree_diff(a_text, b_text):
css = """
diffins {text-decoration : none; background-color: #d4fcbc;}
diffdel {text-decoration : none; background-color: #fbb6c2;}
diffins * {text-decoration : none; background-color: #d4fcbc;}
diffdel * {text-decoration : none; background-color: #fbb6c2;}
"""
d = htmltreediff.diff(a_text,
b_text,
ins_tag='diffins',
del_tag='diffdel',
pretty=True)
return insert_style(d, css)
def html_tree_diff(a_text, b_text):
color_palette = get_color_palette()
css = f'''
diffins {{text-decoration : none; background-color:
{color_palette['differ_insertion']};}}
diffdel {{text-decoration : none; background-color:
{color_palette['differ_deletion']};}}
diffins * {{text-decoration : none; background-color:
{color_palette['differ_insertion']};}}
diffdel * {{text-decoration : none; background-color:
{color_palette['differ_deletion']};}}
'''
d = htmltreediff.diff(a_text, b_text,
ins_tag='diffins', del_tag='diffdel',
pretty=True)
# TODO Count number of changes.
return {'diff': insert_style(d, css)}
def diff(a_text, b_text):
"""
Wraps the ``htmltreediff`` package with the standard arguments and output
format used by all diffs in ``web-monitoring-diff``.
``htmltreediff`` parses HTML documents into an XML DOM and attempts to diff
the document *structures*, rather than look at streams of tags & text
(like ``htmldiffer``) or the readable text content of the HTML (like
``web_monitoring_diff.html_render_diff``). Because of this, it can give
extremely accurate and detailed information for documents that are very
similar, but its output gets complicated or opaque as the two documents
diverge in structure. It can also be very slow.
In practice, we've found that many real-world web pages vary their
structure enough (over periods as short as a few months) to reduce the
value of this diff. It's best used for narrowly-defined scenarios like:
- Comparing versions of a page that are very similar, often at very close
points in time.
- Comparing XML structures you can expect to be very similar, like XML API
responses, RSS documents, etc.
- Comparing two documents that were generated from the same template with
differing underlying data. (Assuming the template is fairly rigid, and
does not leave too much document structure up to the underlying data.)
``htmltreediff`` is no longer under active development; we maintain a fork
with minimal fixes and Python 3 support. It is not available on PyPI, so
you must install via git::
$ pip install git+https://github.com/danielballan/htmltreediff@customize
You can also install all experimental differs with::
$ pip install -r requirements-experimental.txt
Parameters
----------
a_text : string
Source HTML of one document to compare
b_text : string
Source HTML of the other document to compare
Returns
-------
dict
"""
color_palette = get_color_palette()
css = f'''
diffins {{text-decoration : none; background-color:
{color_palette['differ_insertion']};}}
diffdel {{text-decoration : none; background-color:
{color_palette['differ_deletion']};}}
diffins * {{text-decoration : none; background-color:
{color_palette['differ_insertion']};}}
diffdel * {{text-decoration : none; background-color:
{color_palette['differ_deletion']};}}
'''
d = htmltreediff.diff(a_text,
b_text,
ins_tag='diffins',
del_tag='diffdel',
pretty=True)
# TODO Count number of changes.
return {'diff': insert_style(d, css)}
from htmltreediff import diff
from kitchen.text.converters import to_unicode
f1 = open('test1.html', 'r')
f2 = open('test2.html', 'r')
v1 = f1.read()
v2 = f2.read()
print diff(to_unicode(v1), to_unicode(v2), pretty=True)
f1.close()
f2.close()
from htmltreediff import diff
from kitchen.text.converters import to_unicode
f1 = open('test1.html', 'r')
f2 = open('test2.html', 'r')
v1 = f1.read()
v2 = f2.read()
print diff(to_unicode(v1), to_unicode(v2), pretty=True)
f1.close()
f2.close()
from htmltreediff import diff
print diff('<h1>...one...</h1>', '<h1...two...</h1>', pretty=True)
