本文目录导读：
方法1：使用Python脚本（推荐）
安装依赖
pip install requests pandas
基础版脚本
import requests
import pandas as pd
from concurrent.futures import ThreadPoolExecutor, as_completed
import time
def unshorten_url(url, timeout=5):
"""
还原单个短链接
"""
try:
response = requests.head(url, allow_redirects=True, timeout=timeout)
return response.url
except requests.exceptions.RequestException as e:
return f"Error: {str(e)}"
def batch_unshorten(url_list, max_workers=10):
"""
批量还原短链接（使用线程池加速）
"""
results = []
with ThreadPoolExecutor(max_workers=max_workers) as executor:
future_to_url = {executor.submit(unshorten_url, url): url for url in url_list}
for future in as_completed(future_to_url):
original_url = future_to_url[future]
try:
result = future.result()
results.append({
'original_short_url': original_url,
'expanded_url': result
})
except Exception as e:
results.append({
'original_short_url': original_url,
'expanded_url': f"Error: {str(e)}"
})
return results
# 使用示例
if __name__ == "__main__":
# 从文件读取短链接
with open('short_urls.txt', 'r', encoding='utf-8') as f:
urls = [line.strip() for line in f if line.strip()]
# 执行批量还原
print(f"开始还原 {len(urls)} 个短链接...")
results = batch_unshorten(urls, max_workers=10)
# 保存结果到CSV文件
df = pd.DataFrame(results)
df.to_csv('expanded_urls.csv', index=False, encoding='utf-8-sig')
print(f"结果已保存到 expanded_urls.csv")
# 显示部分结果
print("\n前10条结果预览:")
for i, result in enumerate(results[:10]):
print(f"{i+1}. {result['original_short_url']} -> {result['expanded_url']}")
增强版脚本（支持多种短链接服务）
import requests
import re
import json
from urllib.parse import urlparse
class URLUnshortener:
def __init__(self):
self.session = requests.Session()
self.session.headers.update({
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'
})
def unshorten(self, url, max_redirects=5):
"""
追踪重定向链，支持多层重定向
"""
try:
response = self.session.head(
url,
allow_redirects=True,
timeout=5,
max_redirects=max_redirects
)
# 获取最终URL
final_url = response.url
# 获取重定向历史
redirect_chain = [r.url for r in response.history] + [final_url]
return {
'original': url,
'final': final_url,
'redirect_count': len(response.history),
'redirect_chain': redirect_chain,
'status_code': response.status_code
}
except requests.exceptions.TooManyRedirects:
return {
'original': url,
'final': 'Too many redirects',
'redirect_count': -1,
'redirect_chain': [],
'status_code': None
}
except Exception as e:
return {
'original': url,
'final': f'Error: {str(e)}',
'redirect_count': -1,
'redirect_chain': [],
'status_code': None
}
def batch_unshorten_enhanced(urls):
"""
增强版批量还原函数
"""
unshortener = URLUnshortener()
results = []
for url in urls:
result = unshortener.unshorten(url)
results.append(result)
print(f"处理: {url} -> {result['final']}")
time.sleep(0.1) # 避免请求过快
return results
方法2：使用Bash脚本（Linux/Mac）
#!/bin/bash
# 批量还原短链接的bash脚本
# 使用方法: ./unshorten.sh short_urls.txt
INPUT_FILE="$1"
OUTPUT_FILE="expanded_urls.txt"
if [ -z "$INPUT_FILE" ]; then
echo "请指定包含短链接的文件路径"
echo "使用: $0 <urls_file>"
exit 1
fi
echo "开始还原短链接..."
echo "原链接 | 还原后链接" > "$OUTPUT_FILE"
echo "-----------------------------------" >> "$OUTPUT_FILE"
while IFS= read -r url; do
if [ -n "$url" ]; then
# 使用curl获取重定向后的URL
expanded=$(curl -s -L -o /dev/null -w "%{url_effective}" "$url" 2>/dev/null)
echo "$url -> $expanded"
echo "$url | $expanded" >> "$OUTPUT_FILE"
# 添加延迟避免请求过快
sleep 0.5
fi
done < "$INPUT_FILE"
echo "完成！结果已保存到 $OUTPUT_FILE"
方法3：使用Node.js脚本
// unshorten.js
const axios = require('axios');
const fs = require('fs').promises;
const path = require('path');
async function unshortenURL(url) {
try {
const response = await axios.head(url, {
maxRedirects: 10,
timeout: 5000,
headers: {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'
}
});
return {
original: url,
final: response.request.res.responseUrl || response.config.url,
success: true
};
} catch (error) {
return {
original: url,
final: `Error: ${error.message}`,
success: false
};
}
}
async function batchUnshorten(inputFile) {
try {
// 读取URL列表
const content = await fs.readFile(inputFile, 'utf8');
const urls = content.split('\n').filter(url => url.trim());
console.log(`开始处理 ${urls.length} 个短链接...`);
// 批量处理（使用Promise控制并发）
const results = [];
const concurrency = 5;
for (let i = 0; i < urls.length; i += concurrency) {
const batch = urls.slice(i, i + concurrency);
const batchResults = await Promise.all(
batch.map(url => unshortenURL(url.trim()))
);
results.push(...batchResults);
// 显示进度
console.log(`处理进度: ${i + batch.length}/${urls.length}`);
}
// 保存结果
const outputPath = 'expanded_urls.json';
await fs.writeFile(outputPath, JSON.stringify(results, null, 2));
console.log(`结果已保存到 ${outputPath}`);
// 输出摘要
results.forEach(result => {
console.log(`${result.original} -> ${result.final}`);
});
} catch (error) {
console.error('处理失败:', error);
}
}
// 运行脚本
const inputFile = process.argv[2];
if (!inputFile) {
console.log('请指定输入文件路径');
console.log('使用: node unshorten.js <urls_file>');
process.exit(1);
}
batchUnshorten(inputFile);
使用建议
-
输入文件格式：每行一个短链接
https://bit.ly/xxxx https://t.cn/xxxx https://url.cn/xxxx -
性能优化：
- 使用线程池/并发控制提高速度
- 添加适当的延迟避免被限流
- 设置合理的超时时间
-
注意事项：
- 部分短链接服务可能有API限制
- 某些短链接可能已过期或失效
- HTTPS证书问题可能需要特殊处理
-
安装Python依赖（如果使用Python脚本）：
pip install requests pandas
选择适合你技术栈的方法,建议使用Python版本，因为它功能最完整且易于定制。
