def journal_issn(soup, pub_format, pub_type):
if pub_format is None and pub_type is None:
# return the first issn tag found regardless of which type
return first(extract_nodes(soup, "issn"))
elif pub_format is not None:
return first(
extract_nodes(soup,
"issn",
attr="publication-format",
value=pub_format))
elif pub_type is not None:
return first(
extract_nodes(soup, "issn", attr="pub-type", value=pub_type))
def custom_meta(soup, meta_name=None):
custom_meta_tags = extract_nodes(soup, "custom-meta")
if meta_name is not None:
custom_meta_tags = [
tag for tag in custom_meta_tags if node_contents_str(
first(extract_nodes(tag, "meta-name"))) == meta_name
]
return custom_meta_tags
def research_organism_keywords(soup):
tags = first(
extract_nodes(soup,
"kwd-group",
attr="kwd-group-type",
value="research-organism"))
if not tags:
return None
return [tag for tag in tags if tag.name == "kwd"] or None
def label(soup):
return first(extract_nodes(soup, "label"))
def caption(soup):
return first(extract_nodes(soup, "caption"))
def article_title(soup):
return first(extract_nodes(soup, "article-title"))
def month(soup):
return first(extract_nodes(soup, "month"))
def article_body(soup):
return first(extract_nodes(soup, "body"))
def author_response(soup):
return first(sub_article(soup, "reply"))
def copyright_statement(soup):
return first(extract_nodes(soup, "copyright-statement"))
def publisher_id(soup):
article_id_tags = article_id(soup, pub_id_type="publisher-id")
# the first article-id tag whose parent is article-meta
return first(
[tag for tag in article_id_tags if tag.parent.name == "article-meta"])
def title(soup):
return first(extract_nodes(soup, "title"))
def licence_url(soup):
"License url attribute of the license tag"
if licence(soup):
return first(licence(soup)).get("xlink:href")
def article_permissions(soup):
# a better selector might be "article-meta.permissions"
permissions_tags = permissions(soup)
return first(
[tag for tag in permissions_tags if tag.parent.name == "article-meta"])
def acknowledgements(soup):
return first(extract_nodes(soup, "ack"))
def year(soup):
return first(extract_nodes(soup, "year"))
def author_notes(soup):
return first(extract_nodes(soup, "author-notes"))
def copyright_year(soup):
return first(extract_nodes(soup, "copyright-year"))
def doi(soup):
doi_tags = article_id(soup, pub_id_type="doi")
# the first article-id tag whose parent is article-meta
return first(
[tag for tag in doi_tags if tag.parent.name == "article-meta"])
def copyright_holder(soup):
return first(extract_nodes(soup, "copyright-holder"))
def back(soup):
return first(extract_nodes(soup, "back"))
def funding_statement(soup):
return first(extract_nodes(soup, "funding-statement"))
def decision_letter(soup):
tag = first(sub_article(soup, "article-commentary"))
if not tag:
tag = first(sub_article(soup, "decision-letter"))
return tag
def publisher(soup):
return first(extract_nodes(soup, "publisher-name"))
def journal_title(soup):
return first(extract_nodes(soup, "journal-title"))
def history_date(soup, date_type):
date_tags = date(soup, date_type)
return first([tag for tag in date_tags if tag.parent.name == "history"])
def article_meta(soup):
return first(extract_nodes(soup, "article-meta"))
def day(soup):
return first(extract_nodes(soup, "day"))
def article_type(soup):
# returns raw data, just that the data doesn't contain any BS nodes
return first(extract_nodes(soup, "article")).get("article-type")
def test_first(self, value, expected):
self.assertEqual(utils.first(value), expected)
