def htmldiff(old_html, new_html): try: old_html_tokens = tokenize(old_html, include_hrefs=False) new_html_tokens = tokenize(new_html, include_hrefs=False) except (KeyError, ParserError): return new_html result = htmldiff_tokens(old_html_tokens, new_html_tokens) result = ''.join(result).strip() return fixup_ins_del_tags(result)
def htmldiff(old_html, new_html): try: old_html_tokens = tokenize(old_html, include_hrefs=False) new_html_tokens = tokenize(new_html, include_hrefs=False) except (KeyError, ParserError): return new_html result = htmldiff_tokens(old_html_tokens, new_html_tokens) result = ''.join(result).strip() return fixup_ins_del_tags(result)
def htmldiff(old_html, new_html): """ Modified lxml.html.diff.htmldiff: * include_hrefs=False - it's hard to fix this " Link: href " stuff, and it's not needed (right?) * do not do fixup_ins_del_tags, as it re-parses everything and we don't need it here """ old_html_tokens = lxml_diff.tokenize(old_html, include_hrefs=False) new_html_tokens = lxml_diff.tokenize(new_html, include_hrefs=False) result = lxml_diff.htmldiff_tokens(old_html_tokens, new_html_tokens) result = ''.join(result).strip() return result