From 41c2b7c056e73c63c872eeb0a5e3a1f65473eaf0 Mon Sep 17 00:00:00 2001 From: Leonard Richardson Date: Sun, 21 Jul 2019 15:50:49 -0400 Subject: Implemented line number tracking for html5lib. --- bs4/builder/_htmlparser.py | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'bs4/builder/_htmlparser.py') diff --git a/bs4/builder/_htmlparser.py b/bs4/builder/_htmlparser.py index e2c87c1..cd50eb0 100644 --- a/bs4/builder/_htmlparser.py +++ b/bs4/builder/_htmlparser.py @@ -99,9 +99,10 @@ class BeautifulSoupHTMLParser(HTMLParser): attr_dict[key] = value attrvalue = '""' #print "START", name - lineno, offset = self.getpos() + sourceline, sourcepos = self.getpos() tag = self.soup.handle_starttag( - name, None, None, attr_dict, lineno=lineno, offset=offset + name, None, None, attr_dict, sourceline=sourceline, + sourcepos=sourcepos ) if tag and tag.is_empty_element and handle_empty_element: # Unlike other parsers, html.parser doesn't send separate end tag @@ -218,7 +219,7 @@ class HTMLParserTreeBuilder(HTMLTreeBuilder): features = [NAME, HTML, STRICT] # The html.parser knows which line number and position in the - # original file is the source of a document. + # original file is the source of an element. TRACKS_LINE_NUMBERS = True def __init__(self, parser_args=None, parser_kwargs=None, **kwargs): -- cgit v1.2.3