getTaskData.py 文件源码

def getSoupStringConcat(soupTag):
    '''
    Beautiful soup tags return their content text in the .string parameter if there is only one string child.
    Some unfortunate cases on scotus blog have more than one child-string, and this helper just concat's them.
    :param soupTag: a bs4 tag that contains one or more strings
    :return: a string containing all string children of soupTag, concatenated.
    '''
    if isinstance(soupTag, NavigableString): return soupTag.string
    result = ""
    for t in soupTag.descendants:
        if t.string is not None and isinstance(t, NavigableString): # only include NavigableStrings (work around .string default searching behavior)
            if t.parent.name != "script": # prevent reading js
                result = result + t.string
    return result