INNER CODE UNIT · Python

_gather_parents

pingbird/puro · website/pm_attr_list.py:90

def _gather_parents(parents, parent, elem):
    # print(parent, elem, elem.tag, 'text='+repr(elem.text), 'tail='+repr(elem.tail))
    if parent is not None:
        parents[elem] = parent
    tag = elem.tag
    if tag in ['ol', 'ul', 'dl', 'table']:
        parent = elem
    for child in elem:
        _gather_parents(parents, parent, child)
    return parents


def gather_parents(doc):
    parents = {}
    for elem in doc.findall('.'):
        _gather_parents(parents, None, elem)
    return parents

View source record →

📰 Research Paper
Loading…
⏳ Fetching content…