跳转到主要内容
POST
https://api.aisa.one/apis/v1
/
dataforseo
/
on_page
/
uncrawlable_resources
无法抓取的资源
curl --request POST \
  --url https://api.aisa.one/apis/v1/dataforseo/on_page/uncrawlable_resources \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "id": "<string>",
  "limit": 123,
  "offset": 123,
  "order_by": [
    "<string>"
  ],
  "filters": [
    "<string>"
  ]
}
'
import requests

url = "https://api.aisa.one/apis/v1/dataforseo/on_page/uncrawlable_resources"

payload = {
"id": "<string>",
"limit": 123,
"offset": 123,
"order_by": ["<string>"],
"filters": ["<string>"]
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)
const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({
id: '<string>',
limit: 123,
offset: 123,
order_by: ['<string>'],
filters: ['<string>']
})
};

fetch('https://api.aisa.one/apis/v1/dataforseo/on_page/uncrawlable_resources', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));
<?php

$curl = curl_init();

curl_setopt_array($curl, [
CURLOPT_URL => "https://api.aisa.one/apis/v1/dataforseo/on_page/uncrawlable_resources",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'id' => '<string>',
'limit' => 123,
'offset' => 123,
'order_by' => [
'<string>'
],
'filters' => [
'<string>'
]
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}
package main

import (
"fmt"
"strings"
"net/http"
"io"
)

func main() {

url := "https://api.aisa.one/apis/v1/dataforseo/on_page/uncrawlable_resources"

payload := strings.NewReader("{\n \"id\": \"<string>\",\n \"limit\": 123,\n \"offset\": 123,\n \"order_by\": [\n \"<string>\"\n ],\n \"filters\": [\n \"<string>\"\n ]\n}")

req, _ := http.NewRequest("POST", url, payload)

req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")

res, _ := http.DefaultClient.Do(req)

defer res.Body.Close()
body, _ := io.ReadAll(res.Body)

fmt.Println(string(body))

}
HttpResponse<String> response = Unirest.post("https://api.aisa.one/apis/v1/dataforseo/on_page/uncrawlable_resources")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"id\": \"<string>\",\n \"limit\": 123,\n \"offset\": 123,\n \"order_by\": [\n \"<string>\"\n ],\n \"filters\": [\n \"<string>\"\n ]\n}")
.asString();
require 'uri'
require 'net/http'

url = URI("https://api.aisa.one/apis/v1/dataforseo/on_page/uncrawlable_resources")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"id\": \"<string>\",\n \"limit\": 123,\n \"offset\": 123,\n \"order_by\": [\n \"<string>\"\n ],\n \"filters\": [\n \"<string>\"\n ]\n}"

response = http.request(request)
puts response.read_body
{
  "version": "<string>",
  "status_code": 123,
  "status_message": "<string>",
  "time": "<string>",
  "cost": 123,
  "tasks_count": 123,
  "tasks_error": 123,
  "tasks": [
    "<string>"
  ],
  "tasks.id": "<string>",
  "tasks.status_code": 123,
  "tasks.status_message": "<string>",
  "tasks.time": "<string>",
  "tasks.cost": 123,
  "tasks.result_count": 123,
  "tasks.path": [
    "<string>"
  ],
  "tasks.data": {},
  "tasks.result": [
    "<string>"
  ],
  "tasks.result.crawl_progress": "<string>",
  "tasks.result.crawl_status": {},
  "tasks.result.crawl_status.max_crawl_pages": 123,
  "tasks.result.crawl_status.pages_in_queue": 123,
  "tasks.result.crawl_status.pages_crawled": 123,
  "tasks.result.total_items_count": 123,
  "tasks.result.items_count": 123,
  "tasks.result.items": [
    "<string>"
  ],
  "tasks.result.items.url": "<string>",
  "tasks.result.items.reason": "<string>",
  "tasks.result.items.status_code": 123,
  "tasks.result.items.fetch_time": "<string>",
  "tasks.result.items.meta": {},
  "tasks.result.items.meta.content_type": "<string>",
  "tasks.result.items.meta.expected_content_types": [
    "<string>"
  ]
}

授权

Authorization
string
header
必填

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

请求体

application/json
id
string
必填

任务 ID,必填字段;你可以从 Task POST 端点的响应中获取此 ID,例如:"07131248-1535-0216-1000-17384017ad04"

limit
integer

返回的不可抓取资源的最大数量,可选字段,默认值:100,最大值:1000

offset
integer

返回的不可抓取资源在 results 数组中的偏移量。可选字段,默认值:0。如果指定值 10,则会省略 results 数组中的前十个无效资源,并提供后续无效资源的数据。

order_by
string[]

结果排序规则;可选字段;您可以使用与 filters 数组中相同的值对结果进行排序;可用的排序类型:asc - 结果将按升序排列;desc - 结果将按降序排列;应使用逗号设置排序类型;示例:["meta.content_type,desc"];请注意,单个请求最多可设置三条排序规则;应使用逗号分隔多条排序规则;示例:["meta.content_type,asc","fetch_time,desc"]

filters
string[]

结果过滤参数数组,可选字段。可以同时添加多个过滤器(最多 8 个)。应在条件之间设置逻辑运算符 and、or。支持以下运算符:regex、not_regex、 、 、>、>=、=、 、in、not_in、like、not_like。可以将 % 运算符与 like 和 not_like 配合使用,以匹配由零个或多个字符组成的任意字符串。示例:[["meta.content_type","=","image/jpeg"], "and", ["url","not_like","%/help-center/%"]]。可通过此链接查看所有可用过滤器的完整列表。

响应

成功响应

version
string

API 的当前版本

status_code
integer

通用状态码;您可以在此处查看完整的响应码列表。注意:我们强烈建议设计必要的系统来处理相关异常或错误情况

status_message
string

常规信息消息;可在此处查看常规信息消息的完整列表

time
string

执行时间(秒)

cost
number

任务总成本(美元)

tasks_count
integer

tasks 数组中的任务数量

tasks_error
integer

返回错误的 tasks 数组中的任务数量

tasks
string[]

任务数组

tasks.id
string

任务标识符,系统中采用 UUID 格式的唯一任务标识符

tasks.status_code
integer

DataForSEO 生成的任务状态码;范围为:10000-60000;完整响应代码列表可在此处查看

tasks.status_message
string

任务的信息性消息,你可以在此处查看通用信息性消息的完整列表

tasks.time
string

执行时间(秒)

tasks.cost
number

任务成本(美元)

tasks.result_count
integer

结果数组中的元素数量

tasks.path
string[]

URL 路径

tasks.data
object

包含您在 POST 请求中指定的相同参数

tasks.result
string[]

结果数组

tasks.result.crawl_progress
string

抓取会话的状态,可能的值:in_progress、finished

tasks.result.crawl_status
object

抓取会话的详细信息

tasks.result.crawl_status.max_crawl_pages
integer

最大抓取页面数,表示设置任务时指定的 max_crawl_pages 限制

tasks.result.crawl_status.pages_in_queue
integer

当前位于抓取队列中的页面数量

tasks.result.crawl_status.pages_crawled
integer

已抓取页面数

tasks.result.total_items_count
integer

发现的不可抓取资源总数,在目标域名抓取期间发现的不可抓取资源总数

tasks.result.items_count
integer

items 数组中无法抓取的资源数量

tasks.result.items
string[]

无法抓取的资源数组

tasks.result.items.url
string

无法抓取的资源的 URL

tasks.result.items.reason
string

资源无法抓取的原因,可取以下值:content_type_inconsistency

tasks.result.items.status_code
integer

无法抓取的资源返回的 HTTP 响应代码,可能的值:200

tasks.result.items.fetch_time
string

获取资源的日期和时间,采用 UTC 格式:“yyyy-mm-dd hh-mm-ss +00:00”;示例:2026-03-09 18:20:32 +00:00

tasks.result.items.meta
object

无法抓取的资源的元数据

tasks.result.items.meta.content_type
string

资源的实际内容类型

tasks.result.items.meta.expected_content_types
string[]

资源的预期内容类型列表,即爬虫根据页面上引用资源的方式所预期的内容类型