From: Radek Czajka <radoslaw.czajka@nowoczesnapolska.org.pl>
Date: Thu, 15 Sep 2011 14:56:10 +0000 (+0200)
Subject: function to extract annotations from html
X-Git-Tag: 1.7~198
X-Git-Url: https://git.mdrn.pl/librarian.git/commitdiff_plain/b416c7d130f17ac3191d2ef39492cd7c4f70bef7

function to extract annotations from html
---

diff --git a/librarian/html.py b/librarian/html.py
index 5f832e3..1c141f3 100644
--- a/librarian/html.py
+++ b/librarian/html.py
@@ -263,3 +263,15 @@ def add_table_of_contents(root):
 
     root.insert(0, toc)
 
+
+def extract_annotations(html_path):
+    """For each annotation, yields a tuple: anchor, text, html."""
+    parser = etree.HTMLParser(encoding='utf-8')
+    tree = etree.parse(html_path, parser)
+    for footnote in tree.find('//*[@id="footnotes"]').findall('div'):
+        anchor = footnote.find('a[@href]').get('href')
+        del footnote[:2]
+        text_str = etree.tostring(footnote, method='text', encoding='utf-8')
+        html_str = etree.tostring(footnote, method='html', encoding='utf-8')
+        yield anchor, text_str, html_str
+