Question

我有从输入XML文件开始的这段代码，

将标签的子元素的索引和作为键值的子元素存储在字典中；
删除其值包含特定字符串的键；
加入字典值并提取其文本；
用“”替换某些字符串；
计算我指定的某些特定正则表达式的出现次数。

该代码工作正常，但不会删除其值包含字符串“ 10.238”的键。下面是完整的代码：

import re
from xml.dom import minidom
from xml.etree import ElementTree as ET


def filter_values_by_keyword(my_dict, filter_by):
    """
    Return a list of values which contains `filter_by` keyword.

    Arguments:
        my_dict (dict): Dict containing (...data specifics here)
        filter_by (str): Keyword to look for in values of my_dict

    Return:
        List of filtered values
    """
    return [key for key, value in my_dict.items() if filter_by in value]


def get_xml_by_tag_names(xml_path, tag_name_1, tag_name_2):
    """
    Your docstring here.
    """
    data = {}
    xml_tree = minidom.parse(xml_path)
    item_group_nodes = xml_tree.getElementsByTagName(tag_name_1)
    for idx, item_group_node in enumerate(item_group_nodes):
        cl_compile_nodes = item_group_node.getElementsByTagName(tag_name_2)
        for _ in cl_compile_nodes:
            data[idx]=[item_group_node.toxml()]
    return data


def main():
    data = get_xml_by_tag_names('output2.xml', 'new_line', 'text')
    filtered_values = filter_values_by_keyword(data, '10.238')

    for item in filtered_values:
        del data[item]

    mylist = []
    uncinata1 = " < "
    uncinata2 = " >"
    punto = "."
    virgola = ","
    puntoevirgola = ";"
    dash = "-"
    puntoesclamativo = "!"
    duepunti = ":"
    apostrofo = "’"
    puntointerrogativo = "?"
    angolate = "<>"

    for value in data.values():
        myxml = ' '.join(value)
        # print(myxml)

        tree = ET.fromstring(myxml)
        lista = ([text.text for text in tree.findall('text')])
        testo = (' '.join(lista))
        testo = testo.replace(uncinata1, "")
        testo = testo.replace(uncinata2, "")
        testo = testo.replace(punto, "")
        testo = testo.replace(virgola, "")
        testo = testo.replace(puntoevirgola, "")
        testo = testo.replace(dash, "")
        testo = testo.replace(puntoesclamativo, "")
        testo = testo.replace(duepunti, "")
        testo = testo.replace(apostrofo, "")
        testo = testo.replace(puntointerrogativo, "")
        testo = testo.replace(angolate, "")
        print(testo)

        find_prima = re.compile(r"\]\s*prima(?!\S)")
        find_fase_base = re.compile(r"\]\s*AN\s*([\w\s]+)\s*da\scui\sT")  # ] AN parole da cui T
        find_fase_base_2 = re.compile(r"\]\s([\w\s]+)\s[→]\sT")  # ] parole → T
        find_fase_base_3 = re.compile(r"\]\s*([\w\s]+)\s*da\scui\sT")  # ] parole da cui T
        find_fase_12 = re.compile(r"\]\s1\s([\w\s]+)\s2\s([\w\s]+[^T])")  # ] 1 parole 2 parole (esclude T)
        find_fase_12_leo = re.compile(
            r"(?!.*da cui)\]\s+AN\s1\s+([a-zA-Z]+(?:\s+[a-zA-Z]+)*)\s+2\s+([a-zA-Z]+(?:\s+[a-zA-Z]+)*)")  # ] AN 1 parole da cui 2 parole escludendo da cui dopo
        find_fase_12T_leo = re.compile(
            r"\]\s*AN\s*1\s*([\w\s]+)da\s*cui\s*2\s*([\w\s]+)da\s*cui\s*T")  # ] AN 1 parole da cui 2 parole parola da cui T
        matches_prima = re.findall(find_prima, testo)
        lunghezza_prima = len(matches_prima)
        mylist.append(lunghezza_prima)

    count = 0
    for elem in mylist:
        count += elem

    print(count)

if __name__ == "__main__":
    main()

但是重要的是：

def filter_values_by_keyword(my_dict, filter_by):

    return [key for key, value in my_dict.items() if filter_by in value]

，然后在main（）函数中：

filtered_values = filter_values_by_keyword(data, '10.238')

for item in filtered_values:
    del data[item]

它按原样返回文本，我不明白为什么。

编辑：

这是我的XML的示例，它实际上具有重复的pages标签：

<pages>
  <page id="1" bbox="0.000,0.000,462.047,680.315" rotate="0">
    <textbox id="0" bbox="191.745,592.218,249.042,603.578">
<textline>
     <new_line>
              <text font="NUMPTY+ImprintMTnum" bbox="297.284,540.828,300.188,553.310" colourspace="DeviceGray" ncolour="0" size="12.482">della quale non conosce che una parte;] </text>
              <text font="PYNIYO+ImprintMTnum-Italic" bbox="322.455,540.839,328.251,553.566" colourspace="DeviceGray" ncolour="0" size="12.727">prima</text>
              <text font="NUMPTY+ImprintMTnum" bbox="331.206,545.345,334.683,552.834" colourspace="DeviceGray" ncolour="0" size="7.489">1</text>
              <text font="NUMPTY+ImprintMTnum" bbox="177.602,528.028,180.850,540.510" colourspace="DeviceGray" ncolour="0" size="12.482">che nonconosce ancora appieno;</text>
              <text font="NUMPTY+ImprintMTnum" bbox="189.430,532.545,192.908,540.034" colourspace="DeviceGray" ncolour="0" size="7.489">2</text>
              <text font="NUMPTY+ImprintMTnum" bbox="203.879,528.028,208.975,540.510" colourspace="DeviceGray" ncolour="0" size="12.482">che</text>
            </new_line>
</textline>
</textbox>
</page>
</pages>

Answer 1

如果更换，该怎么办

return [key for key, value in my_dict.items() if filter_by in value]

作者：

return [key for key, value in my_dict.items() if filter_by == value]

或（更具可读性的努力）：

更新

输入键是str类型的，根据您的评论，该值也是字符串类型。只需创建一个字符串a="this is my 10.238 number"，操作"10.238" in a就可以得到一个不错的True。

在处理具有“ 10.238”的字符串时，我会仔细检查两个运算符的类型。

my_keys=[]

for key, value in my_dict.items()
  if isinstance(value, list):
    if filter_by in value:
       my_keys.append(key)
  elif isinstance(value, str):
    print("compare {} to {}".format(type(filter_by), type(value)))

    if filter_by in value or value.index(filter_by) > -1:
       my_keys.append(key)
  else:
    print("ops! {}".format(type(value)))


return my_keys

在for循环中删除字典条目不起作用，为什么？

1 个答案: