def _parse(soup):
# journal
journal_name = ElsevierReadMetaData.get_text_or_none(soup, 'xocs:srctitle') or \
ElsevierReadMetaData.get_text_or_none(soup, 'prism:publicationName')
doi = ElsevierReadMetaData.get_text_or_none(soup, 'xocs:doi')
# https://www.elsevier.com/__data/assets/pdf_file/0003/58872/ja5_tagbytag5_v1.9.5.pdf
# Elsevier XML definition pp. 46
head_node = soup.find('head')
title = ElsevierReadMetaData.get_text_or_none(head_node, 'ce:title', extract_ce_title) or \
ElsevierReadMetaData.get_text_or_none(soup, 'dc:title')
keywords = []
if head_node is not None:
# Elsevier XML definition pp. 366
for node in head_node.find_all('ce:keyword'):
text_node = node.find('ce:text')
if text_node is not None:
keyword = remove_consecutive_whitespaces(
extract_ce_text(text_node),
keep_newline=False).strip()
keywords.append(keyword)
if len(keywords) == 0:
for subject in soup.find_all('dcterms:subject'):
keywords.append(subject.get_text().strip())
return soup, {
'Journal': journal_name,
'DOI': doi,
'Title': title,
'Keywords': keywords
}
def test_simple_text(self):
xml_string = """<root xmlns:ce="http://www.elsevier.com/xml/common/dtd">
<ce:text>Example</ce:text>
</root>"""
tag = BeautifulSoup(xml_string, 'xml').find('ce:text')
text = extract_ce_text(tag)
self.assertEqual(text, 'Example')
def test_space(self):
xml_string = """<root xmlns:ce="http://www.elsevier.com/xml/common/dtd">
<ce:text>Sub-2<ce:hsp sp="0.25"/>μm core–shell particles</ce:text>
</root>"""
tag = BeautifulSoup(xml_string, 'xml').find('ce:text')
text = extract_ce_text(tag)
self.assertEqual(text, 'Sub-2 μm core–shell particles')
def test_named_entities(self):
xml_string = """<root xmlns:ce="http://www.elsevier.com/xml/common/dtd">
<ce:text>&z.dshfnc; ◻ ⊨ 𝓇 ј</ce:text>
</root>"""
tag = BeautifulSoup(resolve_elsevier_entities(xml_string),
'xml').find('ce:text')
text = extract_ce_text(tag)
self.assertEqual(text, '┆ ◻ ⊨ 𝓇 ј')
def test_named_entity(self):
xml_string = """<root xmlns:ce="http://www.elsevier.com/xml/common/dtd">
<ce:text>é é é</ce:text>
</root>"""
tag = BeautifulSoup(resolve_elsevier_entities(xml_string),
'xml').find('ce:text')
text = extract_ce_text(tag)
self.assertEqual(text, 'é é é')
def test_font_change(self):
xml_string = '<root xmlns:ce="http://www.elsevier.com/xml/common/dtd">' \
'<ce:text>Test for <ce:bold>bold</ce:bold> ' \
'<ce:italic>italic</ce:italic> <ce:monospace>monospace</ce:monospace> ' \
'<ce:sans-serif>sans-serif</ce:sans-serif> <ce:small-caps>small-caps</ce:small-caps> ' \
'</ce:text></root>'
tag = BeautifulSoup(xml_string, 'xml').find('ce:text')
text = extract_ce_text(tag)
self.assertEqual(
text, 'Test for bold italic monospace sans-serif small-caps ')