diff options
| author | Paul McGuire <ptmcg@austin.rr.com> | 2019-04-06 23:44:02 -0500 |
|---|---|---|
| committer | Paul McGuire <ptmcg@austin.rr.com> | 2019-04-06 23:44:02 -0500 |
| commit | a2439508ba5c94546db98593cfa676de9b59babe (patch) | |
| tree | 80b02178820811c09b4befc9a9b5efb092813466 /examples/htmlTableParser.py | |
| parent | 832986ffccac943b363da43795c335eafc31b5da (diff) | |
| download | pyparsing-git-a2439508ba5c94546db98593cfa676de9b59babe.tar.gz | |
Fixed dict structure in makeHTMLTags expressions, and added tag_body attribute to the generated start expression giving easy access to a SkipTo(closeTag) that will parse the tag's body text; some code cleanup and removed duplication among examples
Diffstat (limited to 'examples/htmlTableParser.py')
| -rw-r--r-- | examples/htmlTableParser.py | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/examples/htmlTableParser.py b/examples/htmlTableParser.py index 5fe8e5f..35cdd03 100644 --- a/examples/htmlTableParser.py +++ b/examples/htmlTableParser.py @@ -23,12 +23,12 @@ a, a_end = pp.makeHTMLTags('a') strip_html = (pp.anyOpenTag | pp.anyCloseTag).suppress().transformString # expression for parsing <a href="url">text</a> links, returning a (text, url) tuple -link = pp.Group(a + pp.SkipTo(a_end)('text') + a_end.suppress()) +link = pp.Group(a + a.tag_body('text') + a_end.suppress()) link.addParseAction(lambda t: (t[0].text, t[0].href)) # method to create table rows of header and data tags def table_row(start_tag, end_tag): - body = pp.SkipTo(end_tag) + body = start_tag.tag_body body.addParseAction(pp.tokenMap(str.strip), pp.tokenMap(strip_html)) row = pp.Group(tr.suppress() |