From 7d8e8197b03f87a8cac2eed8f75e8a41136cc760 Mon Sep 17 00:00:00 2001 From: Michael Williamson Date: Wed, 15 Jul 2015 16:19:37 +0100 Subject: Split off raw_text module --- mammoth/raw_text.py | 12 ++++++++++++ 1 file changed, 12 insertions(+) create mode 100644 mammoth/raw_text.py (limited to 'mammoth/raw_text.py') diff --git a/mammoth/raw_text.py b/mammoth/raw_text.py new file mode 100644 index 0000000..fb39acf --- /dev/null +++ b/mammoth/raw_text.py @@ -0,0 +1,12 @@ +from . import documents + + +def extract_raw_text_from_element(element): + if isinstance(element, documents.Text): + return element.value + else: + text = "".join(map(extract_raw_text_from_element, element.children)) + if isinstance(element, documents.Paragraph): + return text + "\n\n" + else: + return text -- cgit v1.2.3