Update xhs.py
Browse files
xhs.py
CHANGED
|
@@ -1,151 +1,151 @@
|
|
| 1 |
-
from flask import Flask, request, jsonify
|
| 2 |
-
import re
|
| 3 |
-
import requests
|
| 4 |
-
|
| 5 |
-
app = Flask(__name__)
|
| 6 |
-
|
| 7 |
-
def extract_url(text):
|
| 8 |
-
"""从文本中提取小红书链接（短链接或完整链接）"""
|
| 9 |
-
# 匹配形如 http://xhslink.com/xxxx 的短链接
|
| 10 |
-
short_pattern = r'http://xhslink\.com/\S+'
|
| 11 |
-
# 匹配形如 https://www.xiaohongshu.com/discovery/item/xxx 的完整链接
|
| 12 |
-
full_pattern = r'https://www\.xiaohongshu\.com/\S+'
|
| 13 |
-
|
| 14 |
-
# 先尝试匹配短链接
|
| 15 |
-
short_matches = re.findall(short_pattern, text)
|
| 16 |
-
short_urls = [match.rstrip('，').rstrip(',').rstrip('。').rstrip('.') for match in short_matches]
|
| 17 |
-
|
| 18 |
-
# 再尝试匹配完整链接
|
| 19 |
-
full_matches = re.findall(full_pattern, text)
|
| 20 |
-
full_urls = [match.rstrip('，').rstrip(',').rstrip('。').rstrip('.') for match in full_matches]
|
| 21 |
-
|
| 22 |
-
# 返回所有找到的链接及其类型
|
| 23 |
-
result = []
|
| 24 |
-
for url in short_urls:
|
| 25 |
-
result.append(("short", url))
|
| 26 |
-
for url in full_urls:
|
| 27 |
-
result.append(("full", url))
|
| 28 |
-
|
| 29 |
-
return result
|
| 30 |
-
|
| 31 |
-
def get_redirect_url(short_url):
|
| 32 |
-
"""获取短链接重定向后的真实链接"""
|
| 33 |
-
try:
|
| 34 |
-
headers = {
|
| 35 |
-
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36",
|
| 36 |
-
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
|
| 37 |
-
"Accept-Language": "en-US,en;q=0.9",
|
| 38 |
-
"Connection": "keep-alive",
|
| 39 |
-
}
|
| 40 |
-
response = requests.get(short_url, headers=headers, allow_redirects=False)
|
| 41 |
-
if response.status_code in [301, 302, 307]:
|
| 42 |
-
return response.headers['Location']
|
| 43 |
-
else:
|
| 44 |
-
return f"错误: 无法获取重定向链接，状态码: {response.status_code}"
|
| 45 |
-
except Exception as e:
|
| 46 |
-
return f"错误: 请求失败 - {str(e)}"
|
| 47 |
-
|
| 48 |
-
def convert_links(text):
|
| 49 |
-
"""转换文本中的所有小红书链接"""
|
| 50 |
-
urls = extract_url(text)
|
| 51 |
-
if not urls:
|
| 52 |
-
return {"status": "error", "message": "未找到小红书链接", "results": []}
|
| 53 |
-
|
| 54 |
-
results = []
|
| 55 |
-
for url_type, url in urls:
|
| 56 |
-
if url_type == "short":
|
| 57 |
-
real_url = get_redirect_url(url)
|
| 58 |
-
results.append({
|
| 59 |
-
"type": "short",
|
| 60 |
-
"short_url": url,
|
| 61 |
-
"real_url": real_url
|
| 62 |
-
})
|
| 63 |
-
else: # url_type == "full"
|
| 64 |
-
results.append({
|
| 65 |
-
"type": "full",
|
| 66 |
-
"url": url
|
| 67 |
-
})
|
| 68 |
-
|
| 69 |
-
return {"status": "success", "message": "链接转换成功", "results": results}
|
| 70 |
-
|
| 71 |
-
@app.route('/api/convert', methods=['POST'])
|
| 72 |
-
def api_convert():
|
| 73 |
-
"""API端点，接收POST请求并转换链接"""
|
| 74 |
-
if not request.is_json:
|
| 75 |
-
return jsonify({"status": "error", "message": "请求必须是JSON格式"}), 400
|
| 76 |
-
|
| 77 |
-
data = request.get_json()
|
| 78 |
-
|
| 79 |
-
if 'text' not in data:
|
| 80 |
-
return jsonify({"status": "error", "message": "请求中必须包含'text'字段"}), 400
|
| 81 |
-
|
| 82 |
-
text = data['text']
|
| 83 |
-
result = convert_links(text)
|
| 84 |
-
|
| 85 |
-
return jsonify(result)
|
| 86 |
-
|
| 87 |
-
@app.route('/api/health', methods=['GET'])
|
| 88 |
-
def health_check():
|
| 89 |
-
"""健康检查端点"""
|
| 90 |
-
return jsonify({"status": "ok", "message": "服务正常运行"})
|
| 91 |
-
|
| 92 |
-
@app.route('/', methods=['GET'])
|
| 93 |
-
def home():
|
| 94 |
-
"""主页，显示简单的使用说明"""
|
| 95 |
-
return """
|
| 96 |
-
<html>
|
| 97 |
-
<head>
|
| 98 |
-
<title>小红书链接转换API</title>
|
| 99 |
-
<style>
|
| 100 |
-
body { font-family: Arial, sans-serif; margin: 40px; line-height: 1.6; }
|
| 101 |
-
h1 { color: #D81E06; }
|
| 102 |
-
code { background: #f4f4f4; padding: 2px 5px; border-radius: 3px; }
|
| 103 |
-
pre { background: #f4f4f4; padding: 15px; border-radius: 5px; overflow-x: auto; }
|
| 104 |
-
</style>
|
| 105 |
-
</head>
|
| 106 |
-
<body>
|
| 107 |
-
<h1>小红书链接转换API</h1>
|
| 108 |
-
<p>这是一个将小红书分享链接转换为真实可访问链接的API服务。</p>
|
| 109 |
-
|
| 110 |
-
<h2>API使用说明</h2>
|
| 111 |
-
<h3>转换链接</h3>
|
| 112 |
-
<p><strong>端点:</strong> <code>/api/convert</code></p>
|
| 113 |
-
<p><strong>方法:</strong> POST</p>
|
| 114 |
-
<p><strong>请求体:</strong></p>
|
| 115 |
-
<pre>
|
| 116 |
-
{
|
| 117 |
-
"text": "包含小红书链接的文本"
|
| 118 |
-
}
|
| 119 |
-
</pre>
|
| 120 |
-
<p><strong>示例响应:</strong></p>
|
| 121 |
-
<pre>
|
| 122 |
-
{
|
| 123 |
-
"status": "success",
|
| 124 |
-
"message": "链接转换成功",
|
| 125 |
-
"results": [
|
| 126 |
-
{
|
| 127 |
-
"type": "short",
|
| 128 |
-
"short_url": "http://xhslink.com/xxxx",
|
| 129 |
-
"real_url": "https://www.xiaohongshu.com/discovery/item/..."
|
| 130 |
-
}
|
| 131 |
-
]
|
| 132 |
-
}
|
| 133 |
-
</pre>
|
| 134 |
-
|
| 135 |
-
<h3>健康检查</h3>
|
| 136 |
-
<p><strong>端点:</strong> <code>/api/health</code></p>
|
| 137 |
-
<p><strong>方法:</strong> GET</p>
|
| 138 |
-
<p><strong>示例响应:</strong></p>
|
| 139 |
-
<pre>
|
| 140 |
-
{
|
| 141 |
-
"status": "ok",
|
| 142 |
-
"message": "服务正常运行"
|
| 143 |
-
}
|
| 144 |
-
</pre>
|
| 145 |
-
</body>
|
| 146 |
-
</html>
|
| 147 |
-
"""
|
| 148 |
-
|
| 149 |
-
if __name__ == '__main__':
|
| 150 |
-
# 默认运行在7860端口，适配Hugging Face Spaces
|
| 151 |
-
app.run(host='0.0.0.0', port=7860, debug=False)
|
|
|
|
| 1 |
+
from flask import Flask, request, jsonify
|
| 2 |
+
import re
|
| 3 |
+
import requests
|
| 4 |
+
|
| 5 |
+
app = Flask(__name__)
|
| 6 |
+
|
| 7 |
+
def extract_url(text):
|
| 8 |
+
"""从文本中提取小红书链接（短链接或完整链接）"""
|
| 9 |
+
# 匹配形如 http://xhslink.com/xxxx 的短链接
|
| 10 |
+
short_pattern = r'http://xhslink\.com/\S+'
|
| 11 |
+
# 匹配形如 https://www.xiaohongshu.com/discovery/item/xxx 的完整链接
|
| 12 |
+
full_pattern = r'https://www\.xiaohongshu\.com/\S+'
|
| 13 |
+
|
| 14 |
+
# 先尝试匹配短链接
|
| 15 |
+
short_matches = re.findall(short_pattern, text)
|
| 16 |
+
short_urls = [match.rstrip('，').rstrip(',').rstrip('。').rstrip('.') for match in short_matches]
|
| 17 |
+
|
| 18 |
+
# 再尝试匹配完整链接
|
| 19 |
+
full_matches = re.findall(full_pattern, text)
|
| 20 |
+
full_urls = [match.rstrip('，').rstrip(',').rstrip('。').rstrip('.') for match in full_matches]
|
| 21 |
+
|
| 22 |
+
# 返回所有找到的链接及其类型
|
| 23 |
+
result = []
|
| 24 |
+
for url in short_urls:
|
| 25 |
+
result.append(("short", url))
|
| 26 |
+
for url in full_urls:
|
| 27 |
+
result.append(("full", url))
|
| 28 |
+
|
| 29 |
+
return result
|
| 30 |
+
|
| 31 |
+
def get_redirect_url(short_url):
|
| 32 |
+
"""获取短链接重定向后的真实链接"""
|
| 33 |
+
try:
|
| 34 |
+
headers = {
|
| 35 |
+
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36",
|
| 36 |
+
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
|
| 37 |
+
"Accept-Language": "en-US,en;q=0.9",
|
| 38 |
+
"Connection": "keep-alive",
|
| 39 |
+
}
|
| 40 |
+
response = requests.get(short_url, headers=headers, allow_redirects=False)
|
| 41 |
+
if response.status_code in [301, 302, 307]:
|
| 42 |
+
return response.headers['Location']
|
| 43 |
+
else:
|
| 44 |
+
return f"错误: 无法获取重定向链接，状态码: {response.status_code}"
|
| 45 |
+
except Exception as e:
|
| 46 |
+
return f"错误: 请求失败 - {str(e)}"
|
| 47 |
+
|
| 48 |
+
def convert_links(text):
|
| 49 |
+
"""转换文本中的所有小红书链接"""
|
| 50 |
+
urls = extract_url(text)
|
| 51 |
+
if not urls:
|
| 52 |
+
return {"status": "error", "message": "未找到小红书链接", "results": []}
|
| 53 |
+
|
| 54 |
+
results = []
|
| 55 |
+
for url_type, url in urls:
|
| 56 |
+
if url_type == "short":
|
| 57 |
+
real_url = get_redirect_url(url)
|
| 58 |
+
results.append({
|
| 59 |
+
"type": "short",
|
| 60 |
+
"short_url": url,
|
| 61 |
+
"real_url": real_url
|
| 62 |
+
})
|
| 63 |
+
else: # url_type == "full"
|
| 64 |
+
results.append({
|
| 65 |
+
"type": "full",
|
| 66 |
+
"url": url
|
| 67 |
+
})
|
| 68 |
+
|
| 69 |
+
return {"status": "success", "message": "链接转换成功", "results": results}
|
| 70 |
+
|
| 71 |
+
@app.route('/api/convert', methods=['POST'])
|
| 72 |
+
def api_convert():
|
| 73 |
+
"""API端点，接收POST请求并转换链接"""
|
| 74 |
+
if not request.is_json:
|
| 75 |
+
return jsonify({"status": "error", "message": "请求必须是JSON格式"}), 400
|
| 76 |
+
|
| 77 |
+
data = request.get_json()
|
| 78 |
+
|
| 79 |
+
if 'text' not in data:
|
| 80 |
+
return jsonify({"status": "error", "message": "请求中必须包含'text'字段"}), 400
|
| 81 |
+
|
| 82 |
+
text = data['text']
|
| 83 |
+
result = convert_links(text)
|
| 84 |
+
|
| 85 |
+
return jsonify(result)
|
| 86 |
+
|
| 87 |
+
@app.route('/api/health', methods=['GET'])
|
| 88 |
+
def health_check():
|
| 89 |
+
"""健康检查端点"""
|
| 90 |
+
return jsonify({"status": "ok", "message": "服务正常运行"})
|
| 91 |
+
|
| 92 |
+
@app.route('/', methods=['GET'])
|
| 93 |
+
def home():
|
| 94 |
+
"""主页，显示简单的使用说明"""
|
| 95 |
+
return """
|
| 96 |
+
<html>
|
| 97 |
+
<head>
|
| 98 |
+
<title>小红书链接转换API</title>
|
| 99 |
+
<style>
|
| 100 |
+
body { font-family: Arial, sans-serif; margin: 40px; line-height: 1.6; }
|
| 101 |
+
h1 { color: #D81E06; }
|
| 102 |
+
code { background: #f4f4f4; padding: 2px 5px; border-radius: 3px; }
|
| 103 |
+
pre { background: #f4f4f4; padding: 15px; border-radius: 5px; overflow-x: auto; }
|
| 104 |
+
</style>
|
| 105 |
+
</head>
|
| 106 |
+
<body>
|
| 107 |
+
<h1>小红书链接转换API</h1>
|
| 108 |
+
<p>这是一个将小红书分享链接转换为真实可访问链接的API服务。</p>
|
| 109 |
+
|
| 110 |
+
<h2>API使用说明</h2>
|
| 111 |
+
<h3>转换链接</h3>
|
| 112 |
+
<p><strong>端点:</strong> <code>/api/convert</code></p>
|
| 113 |
+
<p><strong>方法:</strong> POST</p>
|
| 114 |
+
<p><strong>请求体:</strong></p>
|
| 115 |
+
<pre>
|
| 116 |
+
{
|
| 117 |
+
"text": "包含小红书链接的文本"
|
| 118 |
+
}
|
| 119 |
+
</pre>
|
| 120 |
+
<p><strong>示例响应:</strong></p>
|
| 121 |
+
<pre>
|
| 122 |
+
{
|
| 123 |
+
"status": "success",
|
| 124 |
+
"message": "链接转换成功",
|
| 125 |
+
"results": [
|
| 126 |
+
{
|
| 127 |
+
"type": "short",
|
| 128 |
+
"short_url": "http://xhslink.com/xxxx",
|
| 129 |
+
"real_url": "https://www.xiaohongshu.com/discovery/item/..."
|
| 130 |
+
}
|
| 131 |
+
]
|
| 132 |
+
}
|
| 133 |
+
</pre>
|
| 134 |
+
|
| 135 |
+
<h3>健康检查</h3>
|
| 136 |
+
<p><strong>端点:</strong> <code>/api/health</code></p>
|
| 137 |
+
<p><strong>方法:</strong> GET</p>
|
| 138 |
+
<p><strong>示例响应:</strong></p>
|
| 139 |
+
<pre>
|
| 140 |
+
{
|
| 141 |
+
"status": "ok",
|
| 142 |
+
"message": "服务正常运行"
|
| 143 |
+
}
|
| 144 |
+
</pre>
|
| 145 |
+
</body>
|
| 146 |
+
</html>
|
| 147 |
+
"""
|
| 148 |
+
|
| 149 |
+
if __name__ == '__main__':
|
| 150 |
+
# 默认运行在7860端口，适配Hugging Face Spaces
|
| 151 |
+
app.run(host='0.0.0.0', port=7860, debug=False,threaded=True)
|