zrd-nb666/campus_health_app/analytics/scan_health.py

"""
扫描 Apple Health export.xml，统计所有 Record type 和 Workout 的数量与时间范围。
流式解析，不吃内存。
"""
import sys
from collections import Counter
from pathlib import Path
from xml.etree.ElementTree import iterparse

xml_path = Path(r"D:\workspace\Agi\zrd-nb666\campus_health_app\analytics\apple_health\apple_health_export\瀵煎嚭.xml")

print(f"Parsing {xml_path.name} ({xml_path.stat().st_size/1024/1024:.1f} MB)...")

record_types = Counter()
workout_types = Counter()
date_min = None
date_max = None
# 关心的类型样本
samples = {}

context = iterparse(str(xml_path), events=("end",))
for event, elem in context:
    tag = elem.tag
    if tag == "Record":
        rtype = elem.get("type", "")
        record_types[rtype] += 1
        # 时间范围
        sd = elem.get("startDate", "")
        if sd:
            if date_min is None or sd < date_min:
                date_min = sd
            if date_max is None or sd > date_max:
                date_max = sd
        # 样本
        if rtype not in samples:
            samples[rtype] = {
                "source": elem.get("sourceName"),
                "value": elem.get("value"),
                "unit": elem.get("unit"),
                "date": sd,
            }
    elif tag == "Workout":
        wtype = elem.get("workoutActivityType", "")
        workout_types[wtype] += 1
    elem.clear()

print(f"\n=== 时间范围 ===")
print(f"最早: {date_min}")
print(f"最新: {date_max}")

print(f"\n=== Record 类型（共 {len(record_types)} 种）===")
for rtype, cnt in record_types.most_common():
    s = samples.get(rtype, {})
    print(f"{cnt:>8}  {rtype:60s}  e.g. {s.get('value','')} {s.get('unit','')}  via {s.get('source','')}")

print(f"\n=== Workout 类型（共 {len(workout_types)} 种）===")
for wtype, cnt in workout_types.most_common():
    print(f"{cnt:>8}  {wtype}")