Qyir
53160420d1
Features: - Douyin play count scraper using Selenium + Chrome DevTools Protocol - Automated scheduler for daily data collection - MongoDB data storage - Mini-program API server - Data analysis and visualization tools 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
55 lines
2.0 KiB
Python
55 lines
2.0 KiB
Python
#!/usr/bin/env python3
|
|
# -*- coding: utf-8 -*-
|
|
"""
|
|
查看MongoDB最新数据 - 始终按时间倒序排列
|
|
"""
|
|
|
|
from pymongo import MongoClient
|
|
from datetime import datetime
|
|
|
|
def view_latest_data(limit=20):
|
|
"""查看最新数据"""
|
|
try:
|
|
client = MongoClient('localhost', 27017)
|
|
db = client['douyin_data']
|
|
collection = db['play_vv_records']
|
|
|
|
print("=== 抖音播放量最新数据 ===")
|
|
print(f"显示最新 {limit} 条记录（按时间倒序排列）")
|
|
print("=" * 80)
|
|
|
|
# 获取最新数据，按时间倒序排列
|
|
latest_docs = list(collection.find().sort('batch_time', -1).limit(limit))
|
|
|
|
if not latest_docs:
|
|
print("没有找到数据")
|
|
return
|
|
|
|
for i, doc in enumerate(latest_docs, 1):
|
|
print(f"\n记录 #{i}")
|
|
print("-" * 50)
|
|
print(f"合集名称: {doc.get('mix_name', '未知')}")
|
|
print(f"播放量: {doc.get('play_vv', 0):,} ({doc.get('playcount', '')})")
|
|
print(f"合集链接: {doc.get('video_url', '')}")
|
|
print(f"保存时间: {doc.get('batch_time', '')}")
|
|
print(f"视频ID数: {len(doc.get('aweme_ids', []))}")
|
|
print(f"封面图片: {'有' if doc.get('cover_image_url') else '无'}")
|
|
|
|
# 显示统计信息
|
|
total_count = collection.count_documents({})
|
|
today_start = datetime.now().replace(hour=0, minute=0, second=0, microsecond=0)
|
|
today_count = collection.count_documents({'batch_time': {'$gte': today_start}})
|
|
|
|
print(f"\n" + "=" * 80)
|
|
print(f"统计信息:")
|
|
print(f"- 总记录数: {total_count}")
|
|
print(f"- 今天记录数: {today_count}")
|
|
print(f"- 最新记录时间: {latest_docs[0].get('batch_time')}")
|
|
|
|
except Exception as e:
|
|
print(f"查看数据时出错: {e}")
|
|
|
|
if __name__ == '__main__':
|
|
import sys
|
|
limit = int(sys.argv[1]) if len(sys.argv) > 1 else 20
|
|
view_latest_data(limit) |