Python 3.x 在Python3中为文件中的字典键分配多个值

我对Python相当陌生，但还没有找到这个问题的答案。 我正在写一个简单的推荐程序，我需要一本字典，其中美食是关键，餐厅名称是价值。在一些情况下，我必须拆分一串几个美食名称，并确保具有相同美食的所有其他餐厅（值）都被分配到相同的美食（键）。以下是文件的一部分：

Georgie Porgie
87%
$$$
Canadian, Pub Food

Queen St. Cafe
82%
$
Malaysian, Thai

Mexican Grill
85%
$$
Mexican

Deep Fried Everything
52%
$
Pub Food

因此，这只是第一个和最后一个有相同的菜肴，但有更多的文件后面。 这是我的代码：

def new(file):
    file = "/.../Restaurants.txt"
    d = {}
    key = []
    with open(file) as file:
        lines = file.readlines()

    for i in range(len(lines)):
        if i % 5 == 0:
            if "," not in lines[i + 3]:
                d[lines[i + 3].strip()] = [lines[i].strip()]
            else:
                key += (lines[i + 3].strip().split(', '))
                for j in key:
                    if j not in d:
                        d[j] = [lines[i].strip()]
                    else:
                        d[j].append(lines[i].strip())
    return d

---

它会打印所有键和值，但不会在应该打印的位置将两个值分配给同一个键。另外，使用最后一个“else”语句，第二个餐厅被分配到错误的键作为第二个值。这不应该发生。如果您有任何意见或帮助，我将不胜感激。

如果只有一个类别，您不检查该关键字是否在词典中。您应该像在多个类别的情况下那样进行类似的操作，然后它就可以正常工作了

我不知道当你有一个文件然后被覆盖时，为什么你有一个文件作为参数

此外，您应该为每个结果设置“键”，而不是+=（将其添加到现有的“键”中）

当您检查j是否在字典中时，最简单的方法是检查j是否在键中（d.keys（））

---

通常，我发现如果您使用字典键的名称，以后处理它们可能会更容易

在下面的示例中，我返回了一系列字典，每个餐厅一个。我还将处理值的功能包装在一个名为add_value（）的方法中，以使代码更具可读性

在我的示例中，我使用编解码器对值进行解码。虽然没有必要，但根据您处理的字符，它可能会很有用。我还使用itertools通过迭代器读取文件行。同样，根据具体情况，也不必这样做，但如果您处理的是非常大的文件，它可能会很有用

import copy, itertools, codecs

class RestaurantListParser(object):

    file_name = "restaurants.txt"

    base_item = {
        "_type": "undefined",
        "_fields": {
            "name": "undefined",
            "nationality": "undefined",
            "rating": "undefined",
            "pricing": "undefined",
        }
    }


    def add_value(self, formatted_item, field_name, field_value):

        if isinstance(field_value, basestring):
            # handle encoding, strip, process the values as you need.
            field_value = codecs.encode(field_value, 'utf-8').strip()
            formatted_item["_fields"][field_name] = field_value
        else:
            print 'Error parsing field "%s", with value: %s' % (field_name, field_value)


    def generator(self, file_name):

        with open(file_name) as file:

            while True:
                lines = tuple(itertools.islice(file, 5))
                if not lines: break


                # Initialize our dictionary for this item
                formatted_item = copy.deepcopy(self.base_item)

                if "," not in lines[3]:
                    formatted_item['_type'] = lines[3].strip()
                else:
                    formatted_item['_type'] = lines[3].split(',')[1].strip()
                    self.add_value(formatted_item, 'nationality', lines[3].split(',')[0])

                self.add_value(formatted_item, 'name', lines[0])
                self.add_value(formatted_item, 'rating', lines[1])
                self.add_value(formatted_item, 'pricing', lines[2])

                yield formatted_item

    def split_by_type(self):

        d = {}
        for restaurant in self.generator(self.file_name):
            if restaurant['_type'] not in d:
                d[restaurant['_type']] = [restaurant['_fields']]
            else:
                d[restaurant['_type']] += [restaurant['_fields']]

        return d

然后，如果您运行：

p = RestaurantListParser()
print p.split_by_type()

你应该得到：

{
    'Mexican': [{
        'name': 'Mexican Grill',
        'nationality': 'undefined',
        'pricing': '$$',
        'rating': '85%'
    }],
    'Pub Food': [{
        'name': 'Georgie Porgie',
        'nationality': 'Canadian',
        'pricing': '$$$',
        'rating': '87%'
    }, {
        'name': 'Deep Fried Everything',
        'nationality': 'undefined',
        'pricing': '$',
        'rating': '52%'
    }],
    'Thai': [{
        'name': 'Queen St. Cafe',
        'nationality': 'Malaysian',
        'pricing': '$',
        'rating': '82%'
    }]
}

---

你的解决方案很简单，所以没关系。我想提一提当我想到这类问题时想到的几个想法。

这里是另一个例子，使用并简化事情

from collections import defaultdict

record_keys = ['name', 'rating', 'price', 'cuisine']


def load(file):
    with open(file) as file:
        data = file.read()

    restaurants = []
    # chop up input on each blank line (2 newlines in a row) 
    for record in data.split("\n\n"):
        fields = record.split("\n")

        # build a dictionary by zipping together the fixed set
        # of field names and the values from this particular record
        restaurant = dict(zip(record_keys, fields))

        # split chops apart the type cuisine on comma, then _.strip()
        # removes any leading/trailing whitespace on each type of cuisine 
        restaurant['cuisine'] = [_.strip() for _ in restaurant['cuisine'].split(",")]
        restaurants.append(restaurant)

    return restaurants


def build_index(database, key, value):
    index = defaultdict(set)
    for record in database:
        for v in record.get(key, []):
            # defaultdict will create a set if one is not present or add to it if one does
            index[v].add(record[value])

    return index


restaurant_db = load('/var/tmp/r')
print(restaurant_db)

by_type = build_index(restaurant_db, 'cuisine', 'name')
print(by_type)

from collections import defaultdict

record_keys = ['name', 'rating', 'price', 'cuisine']


def load(file):
    with open(file) as file:
        data = file.read()

    restaurants = []
    # chop up input on each blank line (2 newlines in a row) 
    for record in data.split("\n\n"):
        fields = record.split("\n")

        # build a dictionary by zipping together the fixed set
        # of field names and the values from this particular record
        restaurant = dict(zip(record_keys, fields))

        # split chops apart the type cuisine on comma, then _.strip()
        # removes any leading/trailing whitespace on each type of cuisine 
        restaurant['cuisine'] = [_.strip() for _ in restaurant['cuisine'].split(",")]
        restaurants.append(restaurant)

    return restaurants


def build_index(database, key, value):
    index = defaultdict(set)
    for record in database:
        for v in record.get(key, []):
            # defaultdict will create a set if one is not present or add to it if one does
            index[v].add(record[value])

    return index


restaurant_db = load('/var/tmp/r')
print(restaurant_db)

by_type = build_index(restaurant_db, 'cuisine', 'name')
print(by_type)