index/reindex and search with API

[Andreas Rottmann]

Hy guys

 

is it possible to run a search like search for “dog” via http or php request and get a response with the search-files and there path?

is it possible to index a folder via php/http? i also need to !reindex! it. For example:

reindex it every day via php/url

 

thank you

[Abbie]

Hello,Andreas Rottmann.

Please view the Menu->Help->API

Thank you.

[Andreas Rottmann]

Thank you.

I saw it before, but it won’t work….

 

I’m not sure, what i should add into “id”. What means 123? is it a example?

thank you

 

my curl with php got invalid message:

$ch = curl_init();

curl_setopt($ch, CURLOPT_URL, ‘127.0.0.1:9920’);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_POST, 1);
curl_setopt($ch, CURLOPT_POSTFIELDS, “{\n \”id\”: *,\n \”jsonrpc\”: \”2.0\”,\n \”method\”: \”ATRpcServer.Searcher.V1.GetResult\”,\n \”params\”: {\n \”input\”: {\n \”pattern\”: \”Hello\”,\n \”filterDir\”: \”*\”,\n \”filterExt\”: \”*\”,\n \”lastModifyBegin\”: 0,\n \”lastModifyEnd\”: 2147483647,\n \”limit\”: \”300\”,\n \”offset\”: 0,\n \”order\”: 0 /* 0: Default. 1:lastModify ASC. 2:lastModify DESC. 3: filterDir ASC. 3: filterDir DESC. */\n }\n }\n}”);

$headers = array();
$headers[] = ‘Accept: application/json’;
$headers[] = ‘Content-Type: application/json’;
curl_setopt($ch, CURLOPT_HTTPHEADER, $headers);

$result = curl_exec($ch);
if (curl_errno($ch)) {
echo ‘Error:’ . curl_error($ch);
}
curl_close($ch);

[Andreas Rottmann]

sorry, wrong code

 

this is my test code:

<?php
// Initialize curl session
$curl = curl_init();

// Set the URL
curl_setopt($curl, CURLOPT_URL, ‘http://localhost:9920&#8217;);

// Set the HTTP headers
curl_setopt($curl, CURLOPT_HTTPHEADER, array(
‘Accept: application/json’,
‘Content-Type: application/json’
));

// Set the request method to POST
curl_setopt($curl, CURLOPT_POST, true);

// Set the request body
$data = array(
“id” => 123,
“jsonrpc” => “2.0”,
“method” => “ATRpcServer.Searcher.V1.GetResult”,
“params” => array(
“input” => array(
“pattern” => “*”,
“filterDir” => “*”,
“filterExt” => “*”,
“lastModifyBegin” => 0,
“lastModifyEnd” => 2147483647,
“limit” => “300”,
“offset” => 0,
“order” => 0 // 0: Default. 1:lastModify ASC. 2:lastModify DESC. 3: filterDir ASC. 3: filterDir DESC.
)
)
);
$data_string = json_encode($data);
curl_setopt($curl, CURLOPT_POSTFIELDS, $data_string);

// Return the transfer as a string
curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);

// Execute curl session
$response = curl_exec($curl);

// Close curl session
curl_close($curl);

// Output response
echo $response;
?>

[Andreas Rottmann]

works now!

 

Thank you for this great work!!!!!!!!

i need it for my company. Is there any way to see the soruce code? they want to know if it is safe….

[Abbie]

Hello,friend.

Anytxt is very safe , please feel free to use it.

We are sorry that we cannot provide the source code.

[wang]

import asyncio
import aiohttp
import json
import logging
from functools import partial

# 配置日志记录，设置日志级别为 INFO，并定义日志格式
logging.basicConfig(level=logging.INFO, format=’%(asctime)s – %(levelname)s – %(message)s’)

# 全局计数器
counter = 0

def build_payload(method, params):
“””
构建 JSON-RPC 请求的有效载荷。

参数:
method (str): API 方法名。
params (dict): 请求参数。

返回:
dict: 包含 id、jsonrpc、method 和 params 的字典。
“””
return {
“id”: 123,
“jsonrpc”: “2.0”,
“method”: method,
“params”: {“input”: params}
}

async def make_request(session, url, headers, payload):
“””
发送异步 HTTP POST 请求。

参数:
session (aiohttp.ClientSession): 异步 HTTP 会话。
url (str): 请求的目标 URL。
headers (dict): 请求头信息。
payload (dict): 请求的有效载荷。

返回:
dict or None: 请求成功时返回响应的 JSON 数据，失败时返回 None。
“””
try:
async with session.post(url, headers=headers, data=json.dumps(payload)) as response:
response.raise_for_status()
return await response.json()
except (aiohttp.ClientError, json.JSONDecodeError) as e:
logging.error(f”请求异常: {e}, Payload: {payload}”)
return None
except Exception as e:
logging.error(f”未知异常: {e}, Payload: {payload}”)
return None

async def get_result(url, headers, text, Dir, filterExt, max_concurrent_requests=1):
“””
获取搜索结果并处理文件片段。

参数:
url (str): 请求的目标 URL。
headers (dict): 请求头信息。
text (str): 搜索文本。
Dir (str): 目录过滤条件。
filterExt (str): 文件扩展名过滤条件。
max_concurrent_requests (int): 最大并发请求数，默认为 10。
“””
params = {
“pattern”: text,
“filterDir”: Dir,
“filterExt”: filterExt,
“lastModifyBegin”: 0,
“lastModifyEnd”: 2147483647,
“limit”: 300,
“offset”: 0,
“order”: 0
}
payload = build_payload(“ATRpcServer.Searcher.V1.GetResult”, params)

async with aiohttp.ClientSession() as session:
result = await make_request(session, url, headers, payload)
if not result:
return

output = result.get(‘result’, {}).get(‘data’, {}).get(‘output’, ‘无输出’)
logging.info(” 找到{}个”.format(output.get(‘count’,  0)))
if output:
files = output.get(‘files’, [])
fids = [file[0] for file in files]
if fids:
#logging.info(“提取的 fids: %s”, fids)
semaphore = asyncio.Semaphore(max_concurrent_requests)
tasks = [get_fragment(session, url, headers, fid, semaphore, text) for fid in fids]
await asyncio.gather(*tasks)
else:
logging.info(“没有找到文件信息”)
else:
logging.info(output)

async def get_fragment(session, url, headers, fid, semaphore, text):
“””
获取指定文件 ID 的片段内容。

参数:
session (aiohttp.ClientSession): 异步 HTTP 会话。
url (str): 请求的目标 URL。
headers (dict): 请求头信息。
fid (str): 文件 ID。
semaphore (asyncio.Semaphore): 控制并发数的信号量。
text (str): 搜索文本。
“””
async with semaphore:
params = {
“fid”: fid,
“pattern”: text
}
payload = build_payload(“ATRpcServer.Searcher.V1.GetFragment”, params)

result = await make_request(session, url, headers, payload)
if not result:
return

output = result.get(‘result’, {}).get(‘data’, {}).get(‘output’, ‘无输出’)
if isinstance(output, dict) and ‘text’ in output:
# 使用全局计数器
global counter
counter += 1
logging.info(“片段内容(%d): %s”, counter, output[‘text’])
else:
logging.info(“文件ID: %s, 输出: %s”, fid, output)

if __name__ == “__main__”:
# 主程序入口，配置请求 URL、请求头、搜索文本、目录和文件扩展名过滤条件
url = “http://localhost:9920&#8221;
headers = {
“Accept”: “application/json”,
“Content-Type”: “application/json”
}
text = “””智能数据库”””
Dir = “E:\\学习资料\\教材\\”  # E:\\学习资料\\教材\\
filterExt = “*.epub”

# 运行异步主函数
asyncio.run(get_result(url, headers, text, Dir, filterExt))

[wang]

How to achieve accurate search?

[wang]

import asyncio
import aiohttp
import json
import logging
import uuid

logging.basicConfig(
level=logging.INFO,
format=’%(asctime)s – %(levelname)s – %(message)s’,
datefmt=’%Y-%m-%d %H:%M:%S’
)

# 线程安全的计数器
counter_lock = asyncio.Lock()
counter = 0

def build_payload(method, params):
“””
构建 JSON-RPC 请求的有效载荷。

参数:
method (str): API 方法名。
params (dict): 请求参数。

返回:
dict: 包含 id、jsonrpc、method 和 params 的字典。
“””
return {
“id”: str(uuid.uuid4()),
“jsonrpc”: “2.0”,
“method”: method,
“params”: {“input”: params}
}

async def make_request(session, url, headers, payload):
“””
发送异步 HTTP POST 请求。

参数:
session (aiohttp.ClientSession): 异步 HTTP 会话。
url (str): 请求的目标 URL。
headers (dict): 请求头信息。
payload (dict): 请求的有效载荷。

返回:
dict or None: 请求成功时返回响应的 JSON 数据，失败时返回 None。
“””
try:
async with session.post(url, headers=headers, data=json.dumps(payload)) as response:
response.raise_for_status()
return await response.json()
except (aiohttp.ClientError, json.JSONDecodeError) as e:
logging.error(f”请求异常: {e}, Payload: {payload}”)
return None
except aiohttp.ClientResponseError as e:
logging.error(f”HTTP 响应错误: {e}, Payload: {payload}”)
return None
except aiohttp.ClientConnectionError as e:
logging.error(f”连接错误: {e}, Payload: {payload}”)
return None
except Exception as e:
logging.error(f”未知异常: {e}, Payload: {payload}”)
return None

async def get_result(url, headers, text, Dir, filterExt, max_concurrent_requests=1):
“””
获取搜索结果并处理文件片段。

参数:
url (str): 请求的目标 URL。
headers (dict): 请求头信息。
text (str): 搜索文本。
Dir (str): 目录过滤条件。
filterExt (str): 文件扩展名过滤条件。
max_concurrent_requests (int): 最大并发请求数，默认为 10。
“””
params = {
“pattern”: text,
“filterDir”: Dir,
“filterExt”: filterExt,
“lastModifyBegin”: 0,
“lastModifyEnd”: 2147483647,
“limit”: 300,
“offset”: 0,
“order”: 0
}
payload = build_payload(“ATRpcServer.Searcher.V1.GetResult”, params)

async with aiohttp.ClientSession() as session:
result = await make_request(session, url, headers, payload)
if not result:
return

output = result.get(‘result’, {}).get(‘data’, {}).get(‘output’, ‘无输出’)
if isinstance(output, dict):
logging.info(“找到 %s 个”, output.get(‘count’, 0))
files = output.get(‘files’, [])
fids = [file[0] for file in files]
if fids:
semaphore = asyncio.Semaphore(max_concurrent_requests)
tasks = [get_fragment(session, url, headers, fid, semaphore, text) for fid in fids]
await asyncio.gather(*tasks)
else:
logging.info(“没有找到文件信息”)
else:
logging.info(“无效的输出格式”)

async def get_fragment(session, url, headers, fid, semaphore, text):
“””
获取指定文件 ID 的片段内容。

参数:
session (aiohttp.ClientSession): 异步 HTTP 会话。
url (str): 请求的目标 URL。
headers (dict): 请求头信息。
fid (str): 文件 ID。
semaphore (asyncio.Semaphore): 控制并发数的信号量。
text (str): 搜索文本。
“””
async with semaphore:
params = {
“fid”: fid,
“pattern”: text
}
payload = build_payload(“ATRpcServer.Searcher.V1.GetFragment”, params)

result = await make_request(session, url, headers, payload)
if not result:
return

output = result.get(‘result’, {}).get(‘data’, {}).get(‘output’, ‘无输出’)
if isinstance(output, dict) and ‘text’ in output:
global counter
async with counter_lock:
counter += 1
logging.info(f”片段内容({counter}): {output[‘text’]}”)
else:
logging.info(“文件ID: %s, 输出: %s”, fid, output)

if __name__ == “__main__”:
# 配置请求 URL、请求头、搜索文本、目录和文件扩展名过滤条件
url = “http://localhost:9920&#8221;
headers = {
“Accept”: “application/json”,
“Content-Type”: “application/json”
}
text = “\”智能数据库\”” #”\”智能数据库\””
Dir = “E:\\学习资料\\教材\\”
filterExt = “*.epub”

# 运行异步主函数
asyncio.run(get_result(url, headers, text, Dir, filterExt))

[Abbie]

您好，请联系客服微信longmate4U为您解答使用问题

 

[Author]

Posts