"""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
+ footnotes = tree.find('//*[@id="footnotes"]')
+ if footnotes is not None:
+ for footnote in footnotes.findall('div'):
+ anchor = footnote.find('a[@href]').get('href')
+ del footnote[:2]
+ text_str = etree.tostring(footnote, method='text', encoding='utf-8').strip()
+ html_str = etree.tostring(footnote, method='html', encoding='utf-8')
+ yield anchor, text_str, html_str