wqeq

main.py

@@ -1,151 +1,83 @@
-import xml.etree.ElementTree as ET
-import openpyxl
-import glob
 import os
+import xml.etree.ElementTree as ET
+import pandas as pd
+from pathlib import Path
 
-HEADERS = [
+# === 🔧 НАСТРОЙКИ (меняйте под себя) ===
-    "№ п/п",
+FOLDER_WITH_XMLS = r"C:\Users\jze9\Documents\work\git\kadastr12\test"  # Папка с XML-файлами
-    "Раздел КПТР",
+OUTPUT_XLSX_FILE = r"C:\Users\jze9\Documents\work\git\kadastr12\result.xlsx"  # Куда сохранить результат
-    "Кадастровый номер",
+
-    "Кадастровый квартал",
+# === ⛏ ВСПОМОГАТЕЛЬНЫЕ ФУНКЦИИ ===
-    "Вид объекта",
+def extract_text(elem, tag):
-    "Площадь ЗУ",
+    node = elem.find(f".//{tag}")
-    "Погрешность определения площади",
+    return node.text.strip() if node is not None and node.text else ""
-    "наличие координат",
-    "Пояснения"
-]
 
 def has_spatial(elem):
-    """Проверяет наличие тега SpatialElement в рамках элемента."""
+    return elem.find(".//SpatialElement") is not None
-    return "да" if elem.find(".//SpatialElement") is not None else "нет"
 
-def get_explanation(elem):
+def collect_explanations(elem):
-    """Ищет пояснения в тегах Explanation, ExplanationSection, NameSection"""
+    return " ".join(e.text.strip() for e in elem.findall(".//Explanation") if e.text and e.text.strip())
-    for tag in ["Explanation", "ExplanationSection", "NameSection"]:
-        sub = elem.find(f".//{tag}")
-        if sub is not None and sub.text:
-            return sub.text.strip()
-    return ""
 
-def extract_fields(elem, tag):
+def process_section(tree, tag, label, records, is_zemel=True):
-    """
+    section = tree.find(f".//{tag}")
-    В зависимости от тега-объекта извлекает данные для строки:
+    if section is None:
-    2. Раздел КПТР – устанавливается по тегу
+        return
-    3. Кадастровый номер
+    subtag = next(iter(section), None)
-    4. Кадастровый квартал
+    if subtag is None:
-    5. Вид объекта
+        return
-    6. Площадь ЗУ
+    for item in section.findall(f".//{subtag.tag}"):
-    7. Погрешность определения площади
+        rec = {
-    8. наличие координат
+            "Раздел КПТР": label,
-    9. Пояснения
+            "Кадастровый номер": extract_text(item, "CadastralNumber"),
-    """
+            "Кадастровый квартал": extract_text(item, "CadastralBlock"),
-    if tag in {"NewParcel", "SpecifyParcel"}:
+            "Вид объекта": extract_text(item, "ObjectType"),
-        section = "FormParcels" if tag=="NewParcel" else "SpecifyParcels"
+            "Площадь ЗУ": extract_text(item.find("Area") or item, "Area") if is_zemel else "",
-        cadastral_number = elem.attrib.get("Definition", "")
+            "Погрешность определения площади": extract_text(item.find("Area") or item, "Inaccuracy") if is_zemel else "",
-        if cadastral_number.startswith(":"):
+            "наличие координат": "да" if has_spatial(item) else "нет",
-            cadastral_number = cadastral_number[1:]
+            "Пояснения": collect_explanations(item),
-        cadastral_block = (elem.findtext("CadastralBlock") or "").strip()
+        }
-        # Если внутри есть тег ObjectType – берем его, иначе для ЗУ фиксированное значение
+        records.append(rec)
-        ot = elem.findtext("ObjectType")
-        object_type = ot.strip() if ot else "Земельный участок"
-        area = (elem.findtext("Area/Area") or "").strip()
-        inaccuracy = (elem.findtext("Area/Inaccuracy") or "").strip()
-        coords = has_spatial(elem)
-        explanation = get_explanation(elem)
-        return [None, section, cadastral_number, cadastral_block, object_type,
-                area, inaccuracy, coords, explanation]
 
-    elif tag == "CadastralErrorParcel":
+# === 🚀 ОСНОВНОЙ КОД ===
-        # обрабатываем дочерний элемент CadastralErrorExistParcel
+def main():
-        sub = elem.find("CadastralErrorExistParcel")
+    records = []
-        if sub is None:
+    for file in os.listdir(FOLDER_WITH_XMLS):
-            return None
+        if not file.lower().endswith(".xml"):
-        section = "CadastralErrorsParcels"
+            continue
-        cadastral_number = sub.attrib.get("CadastralNumber", "")
+        xml_path = os.path.join(FOLDER_WITH_XMLS, file)
-        cadastral_block = (sub.findtext("CadastralBlock") or "").strip()
+        try:
-        area = (sub.findtext("Area/Area") or "").strip()
+            tree = ET.parse(xml_path)
-        inaccuracy = (sub.findtext("Area/Inaccuracy") or "").strip()
+        except ET.ParseError as e:
-        coords = has_spatial(sub)
+            print(f"❌ Ошибка в файле {file}: {e}")
-        explanation = get_explanation(sub)
+            continue
-        object_type = "Земельный участок"
-        return [None, section, cadastral_number, cadastral_block, object_type,
-                area, inaccuracy, coords, explanation]
 
-    elif tag == "ExistParcel":
+        root = tree.getroot()
-        # элемент имеет атрибут CadastralNumber
+        process_section(root, "FormParcels", "Образование ЗУ", records)
-        section = "ExistParcels"
+        process_section(root, "SpecifyParcels", "Уточнение ЗУ", records)
-        cadastral_number = elem.attrib.get("CadastralNumber", "")
+        process_section(root, "CadastralErrorsParcels", "Исправление ЗУ", records)
-        cadastral_block = (elem.findtext("CadastralBlock") or "").strip()
+        process_section(root, "ExistNewObjectsRealty", "Уточнение ОКС", records, is_zemel=False)
-        area = (elem.findtext("Area/Area") or "").strip()
+        process_section(root, "CadastralErrorsOKS", "Исправление ОКС", records, is_zemel=False)
-        inaccuracy = (elem.findtext("Area/Inaccuracy") or "").strip()
-        coords = has_spatial(elem)
-        explanation = get_explanation(elem)
-        object_type = "Земельный участок"
-        return [None, section, cadastral_number, cadastral_block, object_type,
-                area, inaccuracy, coords, explanation]
 
-    elif tag == "ExistNewObjectRealty":
+    if not records:
-        section = "ExistNewObjectsRealty"
+        print("⚠️ Нет данных для экспорта.")
-        cadastral_number = (elem.findtext("CadastralNumber") or "").strip()
+        return
-        ot = elem.findtext("ObjectType")
-        object_type = ot.strip() if ot else "Объект недвижимости"
-        cb_elem = elem.find("CadastralBlocks/CadastralBlock")
-        cadastral_block = cb_elem.text.strip() if cb_elem is not None else ""
-        # Пытаемся взять площадь из <Area/Area> или альтернативный тег
-        area = (elem.findtext("Area/Area") or elem.findtext("AreaInGKN") or "").strip()
-        inaccuracy = (elem.findtext("Area/Inaccuracy") or "").strip()
-        coords = has_spatial(elem)
-        explanation = get_explanation(elem)
-        return [None, section, cadastral_number, cadastral_block, object_type,
-                area, inaccuracy, coords, explanation]
 
-    elif tag == "CadastralErrorOKS":
+    for i, rec in enumerate(records, 1):
-        section = "CadastralErrorsOKS"
+        rec["№ п/п"] = i
-        cadastral_number = elem.attrib.get("CadastralNumber", "")
-        cb_elem = elem.find("CadastralBlocks/CadastralBlock")
-        cadastral_block = cb_elem.text.strip() if cb_elem is not None else ""
-        # Возможно в данном разделе площадь находится в дочернем теге Area
-        area = (elem.findtext("Area/Area") or "").strip()
-        inaccuracy = (elem.findtext("Area/Inaccuracy") or "").strip()
-        coords = has_spatial(elem)
-        explanation = get_explanation(elem)
-        object_type = "Объект недвижимости"
-        return [None, section, cadastral_number, cadastral_block, object_type,
-                area, inaccuracy, coords, explanation]
-    else:
-        return None
 
-def parse_all_stream(xml_file):
+    df = pd.DataFrame(records, columns=[
-    """
+        "№ п/п",
-    Унифицированный итеративный парсинг.
+        "Раздел КПТР",
-    Обрабатываются объекты, у которых тег относится к:
+        "Кадастровый номер",
-    NewParcel, SpecifyParcel, CadastralErrorParcel, ExistParcel,
+        "Кадастровый квартал",
-    ExistNewObjectRealty, CadastralErrorOKS.
+        "Вид объекта",
-    """
+        "Площадь ЗУ",
-    TARGET_TAGS = {"NewParcel", "SpecifyParcel", "CadastralErrorParcel",
+        "Погрешность определения площади",
-                   "ExistParcel", "ExistNewObjectRealty", "CadastralErrorOKS"}
+        "наличие координат",
-    context = ET.iterparse(xml_file, events=("end",))
+        "Пояснения",
-    for event, elem in context:
+    ])
-        if elem.tag in TARGET_TAGS:
+    df.to_excel(OUTPUT_XLSX_FILE, index=False)
-            row = extract_fields(elem, elem.tag)
+    print(f"✔️ Файл успешно сохранён: {OUTPUT_XLSX_FILE}")
-            if row:
-                yield row
-            elem.clear()
-
-def main(xml_folder, output_excel):
-    wb = openpyxl.Workbook()
-    ws = wb.active
-    ws.append(HEADERS)
-    row_num = 1
-    xml_files = glob.glob(os.path.join(xml_folder, "*.xml"))
-    for xml_file in xml_files:
-        for row in parse_all_stream(xml_file):
-            row[0] = row_num  # заполняем № п/п
-            ws.append(row)
-            row_num += 1
-    wb.save(output_excel)
-    print(f"Excel-файл сохранён: {output_excel}")
 
 if __name__ == "__main__":
-    # Папка с XML-файлами, измените при необходимости.
+    main()
-    main("./test", "kptr_table.xlsx")

main1.py

@@ -0,0 +1,21 @@
+import xml.etree.ElementTree as ET
+from bs4 import BeautifulSoup
+
+def open_file(file_path):
+    
+    
+
+    with open(file_path, 'r') as f:
+        data = f.read()
+    Bs_data = BeautifulSoup(data, "xml")
+    b_unique = Bs_data.find_all('unique')
+    
+    print(b_unique)
+    b_name = Bs_data.find('child', {'name':'Frank'})
+    
+    print(b_name)
+    value = b_name.get('test')
+    
+    print(value)
+    
+open_file("C:/Users/jze9/Documents/work/git/kadastr12/test/MapPlanTerritory_E2DF5B75-E136-48DA-BB4C-8887BA4ABF46.xml")

pyproject.toml

@@ -4,4 +4,6 @@ version = "0.1.0"
 description = "Add your description here"
 readme = "README.md"
 requires-python = ">=3.12"
-dependencies = []
+dependencies = [
+    "bs4>=0.0.2",
+]

uv.lock

@@ -0,0 +1,57 @@
+version = 1
+revision = 2
+requires-python = ">=3.12"
+
+[[package]]
+name = "beautifulsoup4"
+version = "4.13.4"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "soupsieve" },
+    { name = "typing-extensions" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/d8/e4/0c4c39e18fd76d6a628d4dd8da40543d136ce2d1752bd6eeeab0791f4d6b/beautifulsoup4-4.13.4.tar.gz", hash = "sha256:dbb3c4e1ceae6aefebdaf2423247260cd062430a410e38c66f2baa50a8437195", size = 621067, upload-time = "2025-04-15T17:05:13.836Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/50/cd/30110dc0ffcf3b131156077b90e9f60ed75711223f306da4db08eff8403b/beautifulsoup4-4.13.4-py3-none-any.whl", hash = "sha256:9bbbb14bfde9d79f38b8cd5f8c7c85f4b8f2523190ebed90e950a8dea4cb1c4b", size = 187285, upload-time = "2025-04-15T17:05:12.221Z" },
+]
+
+[[package]]
+name = "bs4"
+version = "0.0.2"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "beautifulsoup4" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/c9/aa/4acaf814ff901145da37332e05bb510452ebed97bc9602695059dd46ef39/bs4-0.0.2.tar.gz", hash = "sha256:a48685c58f50fe127722417bae83fe6badf500d54b55f7e39ffe43b798653925", size = 698, upload-time = "2024-01-17T18:15:47.371Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/51/bb/bf7aab772a159614954d84aa832c129624ba6c32faa559dfb200a534e50b/bs4-0.0.2-py2.py3-none-any.whl", hash = "sha256:abf8742c0805ef7f662dce4b51cca104cffe52b835238afc169142ab9b3fbccc", size = 1189, upload-time = "2024-01-17T18:15:48.613Z" },
+]
+
+[[package]]
+name = "soupsieve"
+version = "2.7"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/3f/f4/4a80cd6ef364b2e8b65b15816a843c0980f7a5a2b4dc701fc574952aa19f/soupsieve-2.7.tar.gz", hash = "sha256:ad282f9b6926286d2ead4750552c8a6142bc4c783fd66b0293547c8fe6ae126a", size = 103418, upload-time = "2025-04-20T18:50:08.518Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/e7/9c/0e6afc12c269578be5c0c1c9f4b49a8d32770a080260c333ac04cc1c832d/soupsieve-2.7-py3-none-any.whl", hash = "sha256:6e60cc5c1ffaf1cebcc12e8188320b72071e922c2e897f737cadce79ad5d30c4", size = 36677, upload-time = "2025-04-20T18:50:07.196Z" },
+]
+
+[[package]]
+name = "test12"
+version = "0.1.0"
+source = { virtual = "." }
+dependencies = [
+    { name = "bs4" },
+]
+
+[package.metadata]
+requires-dist = [{ name = "bs4", specifier = ">=0.0.2" }]
+
+[[package]]
+name = "typing-extensions"
+version = "4.14.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/d1/bc/51647cd02527e87d05cb083ccc402f93e441606ff1f01739a62c8ad09ba5/typing_extensions-4.14.0.tar.gz", hash = "sha256:8676b788e32f02ab42d9e7c61324048ae4c6d844a399eebace3d4979d75ceef4", size = 107423, upload-time = "2025-06-02T14:52:11.399Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/69/e0/552843e0d356fbb5256d21449fa957fa4eff3bbc135a74a691ee70c7c5da/typing_extensions-4.14.0-py3-none-any.whl", hash = "sha256:a1514509136dd0b477638fc68d6a91497af5076466ad0fa6c338e44e359944af", size = 43839, upload-time = "2025-06-02T14:52:10.026Z" },
+]