X-Git-Url: https://git.mdrn.pl/wolnelektury.git/blobdiff_plain/40a66c8feb465a5d40035272bfd2b95e9027b7dd..933a58adfc8abf2d4c9843afb7fda4cb4d06d030:/lib/librarian/html.py diff --git a/lib/librarian/html.py b/lib/librarian/html.py index bb5a637a2..94514df3c 100644 --- a/lib/librarian/html.py +++ b/lib/librarian/html.py @@ -53,9 +53,13 @@ def transform(input_filename, output_filename): doc = etree.parse(doc_file, parser) result = doc.xslt(style) - add_anchors(result.getroot()) - add_table_of_contents(result.getroot()) - result.write(output_filename, xml_declaration=True, pretty_print=True, encoding='utf-8') + if result.find('//h1') 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') + return True + else: + return False class Fragment(object): @@ -109,7 +113,7 @@ def extract_fragments(input_filename): for event, element in etree.iterparse(input_filename, events=('start', 'end')): # Process begin and end elements - if element.tag == 'span' and element.get('class', '') in ('theme-begin', 'theme-end'): + if element.get('class', '') in ('theme-begin', 'theme-end'): if not event == 'end': continue # Process elements only once, on end event # Open new fragment @@ -117,9 +121,9 @@ def extract_fragments(input_filename): fragment = Fragment(id=element.get('fid'), themes=element.text) # Append parents - if element.getparent().tag != 'body': + if element.getparent().get('id', None) != 'book-text': parents = [element.getparent()] - while parents[-1].getparent().tag != 'body': + while parents[-1].getparent().get('id', None) != 'book-text': parents.append(parents[-1].getparent()) parents.reverse()