主页 / 问题 / 1557252
Accepted
Михаил Ширшов
Asked:2023-12-14 21:40:41 +0000 UTC2023-12-14 21:40:41 +0000 UTC

不输出 xml 中的所有元素

  • 772

我需要从 Rosreestr KPT 的 xml 中在一列中显示所有具有坐标的地籍编号，第二列和第三列是坐标本身（x 和 y）。接下来是代码：

from bs4 import BeautifulSoup
from pathlib import Path
import pandas as pd

def ordinates(ordinates):
    ordinate_list = []
    for x in ordinates:
        cad_number = [s.find('cad_number').text for s in x.find_all('common_data')
        # for ordinate in x.find_all('ordinate'):
        xx = [cad.text for cad in x.find_all('x')]
        yy = [cad.text for cad in x.find_all('y')]
        ordinate_list.extend([(d,f,a) for d,f,a in zip(cad_number,xx,yy)])
    
    return ordinate_list

for path in Path(file_path).rglob('*.XML'):
    with open(path, 'r', encoding='utf-8') as parse:
        xml = parse.read()
        soup = BeautifulSoup(xml, features="lxml")
        ordinate = ordinates(soup.find_all('base_data'))
        for k in ordinate:
            data = {'Кадастровый номер':k[0],
                    'Координаты по X': k[2],
                    'Координаты по Y': k[2]}

显示以下信息（1个地籍编号和1个x和y坐标，尽管这些坐标的地籍编号可能有，例如9个）。然后是以下版本的代码：

def ordinates(ordinates):
    ordinate_list = []
    value_list_1 = []
    for x in ordinates:
        cad_number = ([s.find('cad_number').text for s in x.find_all('common_data')])
        value_list = ([s.find('value').text for s in x.find_all('common_data')])
        value_list_1.extend([(v,b) for v,b in zip(cad_number,value_list)])
        for ordinate in x.find_all('ordinate'):
            xx = [cad.text for cad in ordinate.find_all('x')]
            yy = [cad.text for cad in ordinate.find_all('y')]
            ordinate_list.extend([(d,f) for d,f in zip(xx,yy)])
     
    return ordinate_list

for path in Path(file_path).rglob('*.XML'):
    with open(path, 'r', encoding='utf-8') as parse:
        xml = parse.read()
        soup = BeautifulSoup(xml, features="lxml")
        ordinate = ordinates(soup.find_all('base_data'))
        for k in ordinate:
            data = {'Кадастровый номер':k[0],
                    'Вид объекта':k[1]}

这里 def ordords 函数显示所有坐标（如果你输入 return itude_list）或所有地籍数字（如果你输入 return value_list_1），但是如何同时输出所有内容并将其写入：

data = {'Кадастровый номер':k[0],
        'Координаты по X': k[2],
        'Координаты по Y': k[2]}

链接到 xml 格式的 CBT

python

2 个回答

  1. 
from bs4 import BeautifulSoup
from pathlib import Path
import pandas as pd

def ordinates(ordinates):
    ordinate_list = []
    for x in ordinates:
        cad_number = [s.find('cad_number').text for s in x.find_all('common_data')]
        for ordinate in x.find_all('ordinate'):
            xx = [cad.text for cad in ordinate.find_all('x')]
            yy = [cad.text for cad in ordinate.find_all('y')]
            ordinate_list.extend([(d,f,a) for d,f,a in zip(cad_number,xx,yy)])
    return ordinate_list

data_list = []
for path in Path(file_path).rglob('*.XML'):
    with open(path, 'r', encoding='utf-8') as parse:
        xml = parse.read()
        soup = BeautifulSoup(xml, features="lxml")
        ordinate = ordinates(soup.find_all('base_data'))
        for k in ordinate:
            data = {'Кадастровый номер':k[0],
                    'Координаты по X': k[1],
                    'Координаты по Y': k[2]}
            data_list.append(data)

df = pd.DataFrame(data_list)
    • 0
  2. Best Answer

    我不得不仔细地再次重写它......结果是我想要的））这里是代码：

    for path in Path(file_path).rglob('*.XML'):
    with open(path, 'r',encoding='utf-8-sig') as parse: 
        xml = parse.read()
        soup = BeautifulSoup(xml, features="xml")
        child_ZY = soup.find_all('land_record')
        data_excel = []
        for value in child_ZY:
            if value.select_one('contours_location x') is not None:
                cad_n = (value.select_one('common_data cad_number').text)
                x = [cad.text for cad in value.find_all('x')]
                y = [cad.text for cad in value.find_all('y')]
                pairs = list(zip(x, y))
                coords = [{"Кадастровый номер": cad_n, "Координаты x": pair[0], "Координаты y": pair[1]} for pair in pairs]
                data_excel.extend(coords)
        df = pd.DataFrame(data_excel)
        columns = ["Кадастровый номер", "Координаты x", "Координаты y"]
        df = pd.DataFrame(data_excel, columns=columns)
        df.to_excel(excel_file, index=False)
    • 0

相关问题