python - 抓住一个或两个单词 IF 在一个模式后大写并将结果与​​另一个列表匹配

Question

我需要从文本中提取具有诸如 Lord|Baroness|Lady|Baron 等标题的唯一名称，并将其与另一个列表匹配。我努力获得正确的结果，希望社区可以帮助我。谢谢！

import re
def get_names(text):
    # find nobel titles and grab it with the following name
    match = re.compile(r'(Lord|Baroness|Lady|Baron) ([A-Z][a-z]+) ([A-Z][a-z]+)')
    names = list(set(match.findall(text)))
    # remove duplicates based on the index in tuples
    names_ = list(dict((v[1],v) for v in sorted(names, key=lambda names: names[0])).values())
    names_lst = list(set([' '.join(map(str, name)) for name in names_]))
    return names_lst

text = 'Baroness Firstname Surname and Baroness who is also known as Lady Anothername and Lady Surname or Lady Firstname.'
names_lst = get_names(text)
print(names_lst)

现在产生：['Baroness Firstname Surname']

期望的输出：['Baroness Firstname Surname', 'Lady Anothername']但不是Lady Surname或Lady Firstname

然后我需要将结果与此列表匹配：

other_names = ['Firstname Surname', 'James', 'Simon Smith']

并从中删除元素'Firstname Surname'，因为它与“所需输出”中男爵夫人的名字和姓氏相匹配。

标签： pythonregexpython-3.x

Answer 1

我建议你以下解决方案：

import re

def get_names(text):
    # find nobel titles and grab it with the following name
    match = re.compile(r'(Lord|Baroness|Lady|Baron) ([A-Z][a-z]+)[ ]?([A-Z][a-z]+)?')
    names = list(match.findall(text))
    # keep only the first title encountered
    d = {}
    for name in names:
        if name[0] not in d:
            d[name[0]] = ' '.join(name[1:3]).strip()
    return d

text = 'Baroness Firstname Surname and Baroness who is also known as Lady Anothername and Lady Surname or Lady Firstname.'
other_names = ['Firstname Surname', 'James', 'Simon Smith']

names_dict = get_names(text)
print(names_dict)
#  {'Baroness': 'Firstname Surname', 'Lady': 'Anothername'}
print([' '.join([k,v]) for k,v in names_dict.items()])
# ['Baroness Firstname Surname', 'Lady Anothername']

other_names_dropped = [name for name in other_names if name not in names_dict.values()]
print(other_names_dropped)
# ['James', 'Simon Smith']