Added extraction of wiki_url from DublinCore.

[wolnelektury.git] / lib / librarian / html.py

diff --git a/lib/librarian/html.py b/lib/librarian/html.py
index 8d256ee..b279e5d 100644 (file)
--- a/lib/librarian/html.py
+++ b/lib/librarian/html.py
@@ -53,7 +53,7 @@ def transform(input_filename, output_filename):
     doc = etree.parse(doc_file, parser)
 
     result = doc.xslt(style)
     doc = etree.parse(doc_file, parser)
 
     result = doc.xslt(style)

-    if result.find('//h1') is not None:
+    if result.find('//p') is not None:

         add_anchors(result.getroot())
         add_table_of_contents(result.getroot())
         result.write(output_filename, xml_declaration=False, pretty_print=True, encoding='utf-8')
         add_anchors(result.getroot())
         add_table_of_contents(result.getroot())
         result.write(output_filename, xml_declaration=False, pretty_print=True, encoding='utf-8')


@@ -212,7 +212,7 @@ def add_table_of_contents(root):
     counter = 1
     for element in root.iterdescendants():
         if element.tag in ('h2', 'h3'):
     counter = 1
     for element in root.iterdescendants():
         if element.tag in ('h2', 'h3'):

-            if any_ancestor(element, lambda e: e.get('id') in ('footnotes',)):
+            if any_ancestor(element, lambda e: e.get('id') in ('footnotes',) or e.get('class') in ('person-list',)):

                 continue
             
             if element.tag == 'h3' and len(sections) and sections[-1][1] == 'h2':
                 continue
             
             if element.tag == 'h3' and len(sections) and sections[-1][1] == 'h2':