script.py

import os
import glob
import pandas as pd
import xmltodict


def flatten(d: dict, parent: str = '', sep: str = '_') -> dict:
    items = {}
    for k, v in d.items():
        key = f"{parent}{sep}{k}" if parent else k
        if isinstance(v, dict):
            items.update(flatten(v, key, sep=sep))
        elif isinstance(v, list):
            if all(not isinstance(i, dict) for i in v):
                items[key] = "|".join(map(str, v))
            else:
                for idx, elt in enumerate(v, 1):
                    if isinstance(elt, dict):
                        items.update(flatten(elt, f"{key}{sep}{idx}", sep=sep))
                    else:
                        items[f"{key}{sep}{idx}"] = elt
        else:
            items[key] = v
    return items


def extrair_records(doc: dict, nome: str) -> list[dict]:
    def com_arquivo(rec):
        rec["__arquivo__"] = nome
        return rec

    if "nfeProc" in doc:
        proc = doc["nfeProc"]
        infNFe = proc["NFe"]["infNFe"]
        header = flatten(infNFe)
        if "protNFe" in proc:
            header.update(flatten(proc["protNFe"]["infProt"]))
        dets = infNFe.get("det", [])
        if isinstance(dets, dict):
            dets = [dets]
        return [com_arquivo({**header, **flatten(det)}) for det in dets]

    if "procEventoNFe" in doc:
        proc = doc["procEventoNFe"]
        rec = flatten(proc["envEvento"]["evento"]["infEvento"])
        rec.update(flatten(proc["retEnvEvento"]["retEvento"]["infEvento"]))
        return [com_arquivo(rec)]

    return [com_arquivo(flatten(doc))]


def processar(folder: str) -> str:
    xml_files = glob.glob(os.path.join(folder, "*.xml"))
    print(f"Encontrados {len(xml_files)} arquivos XML em:\n  {folder}\n")

    records = []
    for path in xml_files:
        nome = os.path.basename(path)
        print("Processando:", nome)
        try:
            with open(path, "r", encoding="utf-8") as f:
                doc = xmltodict.parse(f.read())
            records.extend(extrair_records(doc, nome))
        except Exception as e:
            print(f"Ignorando '{nome}' devido a erro: {e}")

    df = pd.DataFrame(records)
    output_file = os.path.join(folder, "nfe_data_por_item.xlsx")
    df.to_excel(output_file, index=False)
    print(f"\nConcluído! {df.shape[0]} linhas × {df.shape[1]} colunas em:\n  {output_file}")
    return output_file


if __name__ == "__main__":
    folder = input("Caminho da pasta com os XMLs: ").strip()
    processar(folder)