跳转到主要内容
POST
https://api.aisa.one/apis/v1
/
dataforseo
/
on_page
/
content_parsing
OnPage API 内容解析
curl --request POST \
  --url https://api.aisa.one/apis/v1/dataforseo/on_page/content_parsing \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "url": "<string>",
  "id": "<string>",
  "markdown_view": true
}
'
import requests

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

payload = {
    "url": "<string>",
    "id": "<string>",
    "markdown_view": True
}
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({url: '<string>', id: '<string>', markdown_view: true})
};

fetch('https://api.aisa.one/apis/v1/dataforseo/on_page/content_parsing', 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/content_parsing",
  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([
    'url' => '<string>',
    'id' => '<string>',
    'markdown_view' => true
  ]),
  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/content_parsing"

	payload := strings.NewReader("{\n  \"url\": \"<string>\",\n  \"id\": \"<string>\",\n  \"markdown_view\": true\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/content_parsing")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"url\": \"<string>\",\n  \"id\": \"<string>\",\n  \"markdown_view\": true\n}")
  .asString();
require 'uri'
require 'net/http'

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

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  \"url\": \"<string>\",\n  \"id\": \"<string>\",\n  \"markdown_view\": true\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.items_count": 123,
  "tasks.result.items": [
    "<string>"
  ],
  "tasks.result.items.type": "<string>",
  "tasks.result.items.fetch_time": "<string>",
  "tasks.result.items.status_code": 123,
  "tasks.result.items.page_content": {},
  "tasks.result.items.page_content.header": {},
  "tasks.result.items.page_content.primary_content": [
    "<string>"
  ],
  "tasks.result.items.page_content.primary_content.text": "<string>",
  "tasks.result.items.page_content.primary_content.url": "<string>",
  "tasks.result.items.page_content.primary_content.urls": [
    "<string>"
  ],
  "tasks.result.items.page_content.primary_content.urls.url": "<string>",
  "tasks.result.items.page_content.primary_content.urls.anchor_text": "<string>",
  "tasks.result.items.page_content.secondary_content": [
    "<string>"
  ],
  "tasks.result.items.page_content.secondary_content.text": "<string>",
  "tasks.result.items.page_content.secondary_content.url": "<string>",
  "tasks.result.items.page_content.secondary_content.urls": [
    "<string>"
  ],
  "tasks.result.items.page_content.secondary_content.urls.url": "<string>",
  "tasks.result.items.page_content.secondary_content.urls.anchor_text": "<string>",
  "tasks.result.items.page_content.table_content": [
    "<string>"
  ],
  "tasks.result.items.page_content.table_content.header": [
    "<string>"
  ],
  "tasks.result.items.page_content.table_content.header.row_cells": [
    "<string>"
  ],
  "tasks.result.items.page_content.table_content.header.row_cells.text": "<string>",
  "tasks.result.items.page_content.table_content.header.row_cells.urls": [
    "<string>"
  ],
  "tasks.result.items.page_content.table_content.header.row_cells.urls.url": "<string>",
  "tasks.result.items.page_content.table_content.header.row_cells.urls.anchor_text": "<string>",
  "tasks.result.items.page_content.table_content.header.row_cells.is_header": true,
  "tasks.result.items.page_content.table_content.body": [
    "<string>"
  ],
  "tasks.result.items.page_content.table_content.body.row_cells": [
    "<string>"
  ],
  "tasks.result.items.page_content.table_content.body.row_cells.text": "<string>",
  "tasks.result.items.page_content.table_content.body.row_cells.urls": [
    "<string>"
  ],
  "tasks.result.items.page_content.table_content.body.row_cells.urls.url": "<string>",
  "tasks.result.items.page_content.table_content.body.row_cells.urls.anchor_text": "<string>",
  "tasks.result.items.page_content.table_content.body.row_cells.is_header": true,
  "tasks.result.items.page_content.table_content.footer": [
    "<string>"
  ],
  "tasks.result.items.page_content.table_content.footer.row_cells": [
    "<string>"
  ],
  "tasks.result.items.page_content.table_content.footer.row_cells.text": "<string>",
  "tasks.result.items.page_content.table_content.footer.row_cells.urls": [
    "<string>"
  ],
  "tasks.result.items.page_content.table_content.footer.row_cells.urls.url": "<string>",
  "tasks.result.items.page_content.table_content.footer.row_cells.urls.anchor_text": "<string>",
  "tasks.result.items.page_content.table_content.footer.row_cells.is_header": true,
  "tasks.result.items.page_content.footer": {},
  "tasks.result.items.page_content.main_topic": [
    "<string>"
  ],
  "tasks.result.items.page_content.main_topic.h_title": "<string>",
  "tasks.result.items.page_content.main_topic.main_title": "<string>",
  "tasks.result.items.page_content.main_topic.author": "<string>",
  "tasks.result.items.page_content.main_topic.language": "<string>",
  "tasks.result.items.page_content.main_topic.level": "<string>",
  "tasks.result.items.page_content.main_topic.primary_content": [
    "<string>"
  ],
  "tasks.result.items.page_content.main_topic.text": "<string>",
  "tasks.result.items.page_content.main_topic.url": "<string>",
  "tasks.result.items.page_content.main_topic.urls": [
    "<string>"
  ],
  "tasks.result.items.page_content.main_topic.urls.url": "<string>",
  "tasks.result.items.page_content.main_topic.urls.anchor_text": "<string>",
  "tasks.result.items.page_content.main_topic.secondary_content": [
    "<string>"
  ],
  "tasks.result.items.page_content.secondary_topic": [
    "<string>"
  ],
  "tasks.result.items.page_content.secondary_topic.h_title": "<string>",
  "tasks.result.items.page_content.secondary_topic.main_title": "<string>",
  "tasks.result.items.page_content.secondary_topic.author": "<string>",
  "tasks.result.items.page_content.secondary_topic.language": "<string>",
  "tasks.result.items.page_content.secondary_topic.level": "<string>",
  "tasks.result.items.page_content.secondary_topic.primary_content": [
    "<string>"
  ],
  "tasks.result.items.page_content.secondary_topic.text": "<string>",
  "tasks.result.items.page_content.secondary_topic.url": "<string>",
  "tasks.result.items.page_content.secondary_topic.urls": [
    "<string>"
  ],
  "tasks.result.items.page_content.secondary_topic.urls.url": "<string>",
  "tasks.result.items.page_content.secondary_topic.urls.anchor_text": "<string>",
  "tasks.result.items.page_content.secondary_topic.secondary_content": [
    "<string>"
  ],
  "tasks.result.items.page_content.ratings": [
    "<string>"
  ],
  "tasks.result.items.page_content.ratings.name": "<string>",
  "tasks.result.items.page_content.ratings.rating_value": 123,
  "tasks.result.items.page_content.ratings.max_rating_value": 123,
  "tasks.result.items.page_content.ratings.rating_count": 123,
  "tasks.result.items.page_content.ratings.relative_rating": 123,
  "tasks.result.items.page_content.offers": [
    "<string>"
  ],
  "tasks.result.items.page_content.offers.name": "<string>",
  "tasks.result.items.page_content.offers.price": 123,
  "tasks.result.items.page_content.offers.price_currency": "<string>",
  "tasks.result.items.page_content.offers.price_valid_until": 123,
  "tasks.result.items.page_content.comments": [
    "<string>"
  ],
  "tasks.result.items.page_content.comments.rating": {},
  "tasks.result.items.page_content.comments.name": "<string>",
  "tasks.result.items.page_content.comments.rating_value": 123,
  "tasks.result.items.page_content.comments.max_rating_value": 123,
  "tasks.result.items.page_content.comments.rating_count": 123,
  "tasks.result.items.page_content.comments.relative rating": 123,
  "tasks.result.items.page_content.comments.title": "<string>",
  "tasks.result.items.page_content.comments.publish_date": "<string>",
  "tasks.result.items.page_content.comments.author": "<string>",
  "tasks.result.items.page_content.comments.primary_content": [
    "<string>"
  ],
  "tasks.result.items.page_content.comments.primary_content.text": "<string>",
  "tasks.result.items.page_content.comments.primary_content.url": "<string>",
  "tasks.result.items.page_content.comments.primary_content.urls": [
    "<string>"
  ],
  "tasks.result.items.page_content.contacts": {},
  "tasks.result.items.page_content.contacts.telephones": [
    "<string>"
  ],
  "tasks.result.items.page_content.contacts.emails": [
    "<string>"
  ],
  "tasks.result.items.page_as_markdown": "<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
​
url
string
必填

要解析的内容的 URL，必填字段；要解析的页面 URL；示例：https://dataforseo.com/blog/a-versatile-alternative-to-google-trends-exploring-the-power-of-dataforseo-trends-api

​
id
string
必填

任务 ID。必填字段。您可以从 Task POST 端点的响应中获取此 ID。注意：POST 请求中的 enable_content_parsing 参数必须设置为 true。示例："07131248-1535-0216-1000-17384017ad04"

​
markdown_view
boolean

以 Markdown 格式返回页面内容。可选字段；如果设置为 true，页面的 Markdown 格式内容将在响应的 page_as_markdown 字段中返回；默认值：false

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.items_count
integer

results 数组中的项目数量

​
tasks.result.items
string[]

items 数组

​
tasks.result.items.type
string

返回项的类型 = ‘сontent_parsing_element’

​
tasks.result.items.fetch_time
string

内容获取的日期和时间，示例："2022-11-01 10:02:52 +00:00"

​
tasks.result.items.status_code
integer

页面状态码

​
tasks.result.items.page_content
object

页面的解析内容

​
tasks.result.items.page_content.header
object

解析后的标头内容

​
tasks.result.items.page_content.primary_content
string[]

页面上的主要内容；有关内容优先级计算的更多信息，请参阅此帮助中心文章

​
tasks.result.items.page_content.primary_content.text
string

内容文本

​
tasks.result.items.page_content.primary_content.url
string

当文本为链接锚文本时显示的页面 URL

​
tasks.result.items.page_content.primary_content.urls
string[]

包含在内容元素中找到的其他 URL 和锚文本

​
tasks.result.items.page_content.primary_content.urls.url
string

在 content 元素中找到的其他 URL

​
tasks.result.items.page_content.primary_content.urls.anchor_text
string

URL 的锚文本

​
tasks.result.items.page_content.secondary_content
string[]

页面上的次要内容；有关内容优先级计算的更多信息，请参阅此帮助中心文章

​
tasks.result.items.page_content.secondary_content.text
string

内容文本

​
tasks.result.items.page_content.secondary_content.url
string

当文本为链接锚文本时显示的页面 URL

​
tasks.result.items.page_content.secondary_content.urls
string[]

包含在内容元素中找到的其他 URL 和锚文本

​
tasks.result.items.page_content.secondary_content.urls.url
string

在 content 元素中找到的其他 URL

​
tasks.result.items.page_content.secondary_content.urls.anchor_text
string

URL 的锚文本

​
tasks.result.items.page_content.table_content
string[]

页面上的表格内容

​
tasks.result.items.page_content.table_content.header
string[]

表格的表头内容

​
tasks.result.items.page_content.table_content.header.row_cells
string[]

表头行单元格的内容

​
tasks.result.items.page_content.table_content.header.row_cells.text
string

行单元格中的文本

​
tasks.result.items.page_content.table_content.header.row_cells.urls
string[]

包含单元格中发现的其他 URL 和锚点

​
tasks.result.items.page_content.table_content.header.row_cells.urls.url
string

单元格中找到的 URL

​
tasks.result.items.page_content.table_content.header.row_cells.urls.anchor_text
string

URL 的锚文本

​
tasks.result.items.page_content.table_content.header.row_cells.is_header
boolean

指示文本是否属于标题

​
tasks.result.items.page_content.table_content.body
string[]

表格主体内容

​
tasks.result.items.page_content.table_content.body.row_cells
string[]

表头行单元格的内容

​
tasks.result.items.page_content.table_content.body.row_cells.text
string

行单元格中的文本

​
tasks.result.items.page_content.table_content.body.row_cells.urls
string[]

包含单元格中发现的其他 URL 和锚点

​
tasks.result.items.page_content.table_content.body.row_cells.urls.url
string

单元格中找到的 URL

​
tasks.result.items.page_content.table_content.body.row_cells.urls.anchor_text
string

URL 的锚文本

​
tasks.result.items.page_content.table_content.body.row_cells.is_header
boolean

指示文本是否属于标题

​
tasks.result.items.page_content.table_content.footer
string[]

表格页脚的内容

​
tasks.result.items.page_content.table_content.footer.row_cells
string[]

表头行单元格的内容

​
tasks.result.items.page_content.table_content.footer.row_cells.text
string

行单元格中的文本

​
tasks.result.items.page_content.table_content.footer.row_cells.urls
string[]

包含单元格中发现的其他 URL 和锚点

​
tasks.result.items.page_content.table_content.footer.row_cells.urls.url
string

单元格中找到的 URL

​
tasks.result.items.page_content.table_content.footer.row_cells.urls.anchor_text
string

URL 的锚文本

​
tasks.result.items.page_content.table_content.footer.row_cells.is_header
boolean

指示文本是否属于标题

​
tasks.result.items.page_content.footer
object

页脚的解析内容

​
tasks.result.items.page_content.main_topic
string[]

页面上的主要主题；可在此帮助中心文章中了解有关主题优先级计算的更多信息

​
tasks.result.items.page_content.main_topic.h_title
string

元标题

​
tasks.result.items.page_content.main_topic.main_title
string

区块主标题

​
tasks.result.items.page_content.main_topic.author
string

内容作者姓名

​
tasks.result.items.page_content.main_topic.language
string

内容语言

​
tasks.result.items.page_content.main_topic.level
string

HTML 层级

​
tasks.result.items.page_content.main_topic.primary_content
string[]

页面上的主要内容；有关内容优先级计算的更多信息，请参阅此帮助中心文章

​
tasks.result.items.page_content.main_topic.text
string

内容文本

​
tasks.result.items.page_content.main_topic.url
string

当文本为链接锚文本时显示的页面 URL

​
tasks.result.items.page_content.main_topic.urls
string[]

包含在内容元素中找到的其他 URL 和锚文本

​
tasks.result.items.page_content.main_topic.urls.url
string

在 content 元素中找到的其他 URL

​
tasks.result.items.page_content.main_topic.urls.anchor_text
string

URL 的锚文本

​
tasks.result.items.page_content.main_topic.secondary_content
string[]

页面上的次要内容；有关内容优先级计算的更多信息，请参阅此帮助中心文章

​
tasks.result.items.page_content.secondary_topic
string[]

页面上的次要主题；有关主题优先级计算的更多信息，请参阅此帮助中心文章

​
tasks.result.items.page_content.secondary_topic.h_title
string

元标题

​
tasks.result.items.page_content.secondary_topic.main_title
string

区块主标题

​
tasks.result.items.page_content.secondary_topic.author
string

内容作者姓名

​
tasks.result.items.page_content.secondary_topic.language
string

内容语言

​
tasks.result.items.page_content.secondary_topic.level
string

HTML 层级

​
tasks.result.items.page_content.secondary_topic.primary_content
string[]

页面上的主要内容；有关内容优先级计算的更多信息，请参阅此帮助中心文章

​
tasks.result.items.page_content.secondary_topic.text
string

内容文本

​
tasks.result.items.page_content.secondary_topic.url
string

当文本为链接锚文本时显示的页面 URL

​
tasks.result.items.page_content.secondary_topic.urls
string[]

包含在内容元素中找到的其他 URL 和锚文本

​
tasks.result.items.page_content.secondary_topic.urls.url
string

在 content 元素中找到的其他 URL

​
tasks.result.items.page_content.secondary_topic.urls.anchor_text
string

URL 的锚文本

​
tasks.result.items.page_content.secondary_topic.secondary_content
string[]

页面上的次要内容；有关内容优先级计算的更多信息，请参阅此帮助中心文章

​
tasks.result.items.page_content.ratings
string[]

包含页面所展示产品的评分信息对象

​
tasks.result.items.page_content.ratings.name
string

rating 名称。注意：此字段未在此特定对象中使用，其值始终设为 null

​
tasks.result.items.page_content.ratings.rating_value
integer

评级值

​
tasks.result.items.page_content.ratings.max_rating_value
integer

评分的最大值

​
tasks.result.items.page_content.ratings.rating_count
integer

反馈数量

​
tasks.result.items.page_content.ratings.relative_rating
number

相对评分的取值范围为 0 到 1

​
tasks.result.items.page_content.offers
string[]

页面上展示的产品数组，其中包含具有页面所展示产品相关信息的对象

​
tasks.result.items.page_content.offers.name
string

产品名称

​
tasks.result.items.page_content.offers.price
integer

产品价格

​
tasks.result.items.page_content.offers.price_currency
string

价格币种

​
tasks.result.items.page_content.offers.price_valid_until
integer

显示价格有效期截止的日期和时间，采用 UTC 格式：“yyyy-mm-dd hh-mm-ss +00:00”，示例："2022-11-01 10:02:52 +00:00"

​
tasks.result.items.page_content.comments
string[]

页面上显示的评论数组，包含与所展示产品相关的评论信息对象

​
tasks.result.items.page_content.comments.rating
object

产品评分，包含客户为该产品给出的评分信息

​
tasks.result.items.page_content.comments.name
string

评分名称。注意：此字段未在此特定对象中使用，其值始终为 null

​
tasks.result.items.page_content.comments.rating_value
integer

评级值

​
tasks.result.items.page_content.comments.max_rating_value
integer

评分的最大值

​
tasks.result.items.page_content.comments.rating_count
integer

反馈数量。注意：此字段未在此特定对象中使用，其值始终为 null

​
tasks.result.items.page_content.comments.relative rating
number

相对评分的取值范围为 0 到 1

​
tasks.result.items.page_content.comments.title
string

客户评论的标题

​
tasks.result.items.page_content.comments.publish_date
string

评论发布日期

​
tasks.result.items.page_content.comments.author
string

评论作者

​
tasks.result.items.page_content.comments.primary_content
string[]

页面上的主要内容；有关内容优先级计算的更多信息，请参阅此帮助中心文章

​
tasks.result.items.page_content.comments.primary_content.text
string

评论文本

​
tasks.result.items.page_content.comments.primary_content.url
string

当文本为链接锚文本时显示

​
tasks.result.items.page_content.comments.primary_content.urls
string[]

包含在内容元素中找到的其他 URL 和锚文本

​
tasks.result.items.page_content.contacts
object

联系信息，包含页面上显示的联系信息

​
tasks.result.items.page_content.contacts.telephones
string[]

电话号码数组

​
tasks.result.items.page_content.contacts.emails
string[]

电子邮件数组

​
tasks.result.items.page_as_markdown
string

Markdown 格式的页面内容 text-to-HTML Markdown 格式的页面内容；在请求中将 markdown_view 指定为 true 以返回该值