[
{
"id": "documentation-markdown-api_1000",
"service": "documentation-markdown-api",
"title": "DOCUMENTATION MARKDOWN Record #1",
"status": "VERIFIED_ACTIVE",
"result": "Processed query successfully for documentation-markdown-api",
"inputReceived": {
"startUrls": [
"https://docs.apify.com/academy/apify-scrapers"
],
"maxPages": 3,
"stripNavigation": true
},
"data": {
"index": 1,
"relevanceScore": 0.95,
"summary": "High-fidelity structured response for DOCUMENTATION MARKDOWN query parameter extraction.",
"attributes": {
"region": "Global",
"category": "DOCUMENTATION",
"timestamp": "2026-10-12T06:06:43.150Z"
}
},
"timestamp": "2026-10-12T06:06:43.150Z"
},
{
"id": "documentation-markdown-api_1001",
"service": "documentation-markdown-api",
"title": "DOCUMENTATION MARKDOWN Record #2",
"status": "VERIFIED_ACTIVE",
"result": "Processed query successfully for documentation-markdown-api",
"inputReceived": {
"startUrls": [
"https://docs.apify.com/academy/apify-scrapers"
],
"maxPages": 3,
"stripNavigation": true
},
"data": {
"index": 2,
"relevanceScore": 0.8999999999999999,
"summary": "High-fidelity structured response for DOCUMENTATION MARKDOWN query parameter extraction.",
"attributes": {
"region": "Global",
"category": "DOCUMENTATION",
"timestamp": "2026-10-12T06:06:43.150Z"
}
},
"timestamp": "2026-10-12T06:06:43.150Z"
},
{
"id": "documentation-markdown-api_1002",
"service": "documentation-markdown-api",
"title": "DOCUMENTATION MARKDOWN Record #3",
"status": "VERIFIED_ACTIVE",
"result": "Processed query successfully for documentation-markdown-api",
"inputReceived": {
"startUrls": [
"https://docs.apify.com/academy/apify-scrapers"
],
"maxPages": 3,
"stripNavigation": true
},
"data": {
"index": 3,
"relevanceScore": 0.85,
"summary": "High-fidelity structured response for DOCUMENTATION MARKDOWN query parameter extraction.",
"attributes": {
"region": "Global",
"category": "DOCUMENTATION",
"timestamp": "2026-10-12T06:06:43.150Z"
}
},
"timestamp": "2026-10-12T06:06:43.150Z"
},
{
"id": "documentation-markdown-api_1003",
"service": "documentation-markdown-api",
"title": "DOCUMENTATION MARKDOWN Record #4",
"status": "VERIFIED_ACTIVE",
"result": "Processed query successfully for documentation-markdown-api",
"inputReceived": {
"startUrls": [
"https://docs.apify.com/academy/apify-scrapers"
],
"maxPages": 3,
"stripNavigation": true
},
"data": {
"index": 4,
"relevanceScore": 0.7999999999999999,
"summary": "High-fidelity structured response for DOCUMENTATION MARKDOWN query parameter extraction.",
"attributes": {
"region": "Global",
"category": "DOCUMENTATION",
"timestamp": "2026-10-12T06:06:43.150Z"
}
},
"timestamp": "2026-10-12T06:06:43.150Z"
},
{
"id": "documentation-markdown-api_1004",
"service": "documentation-markdown-api",
"title": "DOCUMENTATION MARKDOWN Record #5",
"status": "VERIFIED_ACTIVE",
"result": "Processed query successfully for documentation-markdown-api",
"inputReceived": {
"startUrls": [
"https://docs.apify.com/academy/apify-scrapers"
],
"maxPages": 3,
"stripNavigation": true
},
"data": {
"index": 5,
"relevanceScore": 0.75,
"summary": "High-fidelity structured response for DOCUMENTATION MARKDOWN query parameter extraction.",
"attributes": {
"region": "Global",
"category": "DOCUMENTATION",
"timestamp": "2026-10-12T06:06:43.150Z"
}
},
"timestamp": "2026-10-12T06:06:43.150Z"
}
]
curl --location --request POST 'https://zylalabs.com/api/14149/documentation+to+clean+llm+markdown+crawler+api/35193/execute+documentation+to+clean+llm+markdown+crawler+api' --header 'Authorization: Bearer YOUR_API_KEY'
--data-raw '{"startUrls":["https://docs.apify.com/academy/apify-scrapers"],"maxPages":3,"stripNavigation":true}'
注册后,每个开发者都会被分配一个个人 API 访问密钥,这是一个唯一的字母和数字组合,用于访问我们的 API 端点。要使用 清理LLM Markdown爬虫的文档 API 进行身份验证,只需在 Authorization 标头中包含您的 bearer token。
| 标头 | 描述 |
|---|---|
授权
|
必需
应为 Bearer access_key. 订阅后,请查看上方的"您的 API 访问密钥"。
|
无长期承诺。随时升级、降级或取消。 免费试用包括最多 50 个请求。
(年度计费可节省 2 个月 🎉)
API返回经过清理的GitHub风格Markdown内容,结构化为大型语言模型应用。输出包括经过处理的Markdown,没有多余的格式,使其适合用于训练数据或集成到应用中
响应中的关键字段包括“id”“service”“title”“status”“result”“inputReceived”和“data”“data”字段包含诸如“index”“relevanceScore”和“summary”等属性,提供关于处理文档的见解
响应数据被组织为一个包含对象的JSON数组。每个对象包含有关处理请求的元数据和清理过的markdown内容,使用户能够轻松访问相关信息和结果
API提供从开发者文档中提取的信息,包括结构化的markdown内容、相关性评分和摘要。这些数据有助于提升文档质量和为大型语言模型准备训练数据集
用户可以使用“startUrls”“maxPages”和“stripNavigation”等参数自定义他们的请求。这些参数允许控制爬取过程,包括要处理的页面数量以及是否删除导航元素
数据准确性通过一系列清洗功能得以保持,这些功能将markdown内容进行清理,确保其结构化且不含无关的格式。这一过程提高了机器处理输出的质量
典型的使用案例包括为大型语言模型准备训练数据增强自动化文档系统以及将干净的markdown内容集成到需要连贯文本输出的应用程序中
用户可以通过访问“result”字段获取处理状态,通过“summary”获取快速洞察,并使用清理后的markdown将其集成到他们的应用程序或进一步分析中用于LLM训练