From 7ba9cc0ecdca695fec3cb90c98dd383e0edb2ba9 Mon Sep 17 00:00:00 2001 From: Michael Williamson Date: Wed, 11 Feb 2015 20:22:54 +0000 Subject: Read anchor from hyperlinks --- mammoth/docx/document_xml.py | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'mammoth/docx/document_xml.py') diff --git a/mammoth/docx/document_xml.py b/mammoth/docx/document_xml.py index 2004948..56298f3 100644 --- a/mammoth/docx/document_xml.py +++ b/mammoth/docx/document_xml.py @@ -176,12 +176,15 @@ def _create_reader(numbering, content_types, relationships, styles, note_element @handler("w:hyperlink") def hyperlink(element): relationship_id = element.attributes.get("r:id") + anchor = element.attributes.get("w:anchor") children_result = _read_xml_elements(element.children) - if relationship_id is None: - return children_result - else: + if relationship_id is not None: href = relationships[relationship_id].target - return children_result.map(lambda children: documents.hyperlink(href, children)) + return children_result.map(lambda children: documents.hyperlink(href=href, children=children)) + elif anchor is not None: + return children_result.map(lambda children: documents.hyperlink(anchor=anchor, children=children)) + else: + return children_result @handler("w:br") def br(element): -- cgit v1.2.3