def part03():
return parse_html_file('dicom_standard/standard/part03.html')
def get_table_and_tdiv(
standard: BeautifulSoup) -> Tuple[List[TableDictType], Tag]:
all_tables = standard.find_all('div', class_='table')
html_table = pl.find_tdiv_by_id(all_tables, TABLE_ID)
list_table = attribute_table_to_list(html_table)
table_dict_list = table_to_dict(list_table, COLUMN_TITLES)
return (table_dict_list, html_table)
def generate_ciod_id(name: str) -> str:
cleaned_name = name.split('IOD')[0].strip()
return IOD_ABBREVIATIONS.get(cleaned_name, cleaned_name)
def table_to_json(table: List[TableDictType],
tdiv: Tag) -> List[TableDictType]:
attributes = []
for row in table:
row['ciod'] = generate_ciod_id(row['ciod'])
attributes.append(row)
return attributes
if __name__ == '__main__':
standard = pl.parse_html_file(sys.argv[1])
table, tdiv = get_table_and_tdiv(standard)
parsed_table_data = table_to_json(table, tdiv)
pl.write_pretty_json(parsed_table_data)
for section in all_sections
}
def enclosing_section_from_id(id_div):
# TODO: put example from the standard here
if re.match(r'sect.*', id_div['id']):
return id_div.parent.parent.parent.parent.parent
elif re.match(r'biblio.*', id_div['id']):
return id_div.parent.parent.parent
elif re.match(r'table.*', id_div['id']):
return id_div.parent.parent
elif re.match(r'note.*', id_div['id']):
return id_div.parent.parent.parent.parent.parent.parent
else:
return id_div.parent.parent
if __name__ == '__main__':
# TODO: figure out a way to speed up the parsing; since we only need a
# small portion of the parse tree, we may be able to use:
# https://docs.python.org/3/library/html.parser.html to avoid building the
# full parse tree.
standard = {os.path.basename(f): parse_html_file(f) for f in sys.argv[1:]}
section_ids = extract_section_ids(standard)
sections = {
page: normalize_sections(html)
for page, html in section_ids.items()
}
write_pretty_json(sections)
