问从字符串中删除短语列表

EN

In [116]: removed = ['range', 'drinks', 'food and drinks', 'summer drinks']
     ...: removed = sorted(removed, key=len, reverse=True)
     ...: sentence = 'Oranges are the main ingredient for a wide range of food and drinks'
     ...: new_sentence = sentence
     ...: import re
     ...: removals = [r'\b' + phrase + r'\b' for phrase in removed]
     ...: for removal in removals:
     ...:     new_sentence = re.sub(removal, '', new_sentence)
     ...: new_sentence = ' '.join(new_sentence.split())
     ...: print(sentence)
     ...: print(new_sentence)
Oranges are the main ingredient for a wide range of food and drinks
Oranges are the main ingredient for a wide of

>>> removed = ['range', 'drinks', 'food and drinks', 'summer drinks']
>>> sentence = 'Oranges are the main ingredient for a wide range of food and drinks'
>>> words = sentence.split()
>>> for ngram in sorted([r.split() for r in removed], key=len, reverse=True):
...     for i in range(len(words) - len(ngram)+1):
...         if words[i:i+len(ngram)] == ngram:
...             words = words[:i] + words[i+len(ngram):]
...             break
...
>>> " ".join(words)
'Oranges are the main ingredient for a wide of'

    import re

    removed = ['range', 'drinks', 'food and drinks', 'summer drinks']
    sentence = 'Oranges are the main ingredient for a wide range of food and drinks'

    # sort the removed tokens according to their length,
    removed = sorted(removed, key=len, reverse=True)

    # using word boundaries
    for r in removed:
        sentence = re.sub(r"\b{}\b".format(r), " ", sentence)

    # replace multiple whitspaces with a single one   
    sentence = re.sub(' +',' ',sentence)