def Assess_HTML_SIM(generatedHTML, targetHTML):
from html_similarity import style_similarity, structural_similarity, similarity
print("---------------------------")
print(style_similarity(generatedHTML, targetHTML))
print("---------------------------")
print(structural_similarity(generatedHTML, targetHTML))
print("---------------------------")
print(similarity(generatedHTML, targetHTML))
def compare(html1, html2):
if html1 == html2:
return 1, 1
# print("html1",html1)
# print("html2",html2)
style_rate = style_similarity(html1, html2)
struc_rate = structural_similarity(html1, html2)
return style_rate, struc_rate
def main(lang1, lang2, url1, url2, file1, file2, enc1, enc2):
if url1 and url2:
html1 = requests.get(url1).content.decode(
enc1, "replace").replace("\n", " ").replace("\t", " ")
html2 = requests.get(url2).content.decode(
enc2, "replace").replace("\n", " ").replace("\t", " ")
else:
html1 = open(file1).read().replace("\n", " ").replace("\t", " ")
html2 = open(file2).read().replace("\n", " ").replace("\t", " ")
url1 = "http://test.com/{:s}".format(lang1)
url2 = "http://test.com/{:s}".format(lang2)
print("style_similarity={:f} structural_similarity={:f} similarity={:f}".format(
style_similarity(html1, html2), structural_similarity(html1, html2), similarity(html1, html2)), file=sys.stderr)
print("\t".join(["dummy_key", lang1, url1, html1, lang2, url2, html2]))
def test_no_styles_similarity():
assert 1 == style_similarity('<h1>No class here</h1>', '<h1>Look no css class here</h1>')
def test_style_similarity():
assert 1 == style_similarity(html1, html2)