Extract article text
diffbot.x.extract-articleExtracts clean article text, author, date, images, tags, sentiment and NLP facts from a news or blog page
- 价格
- $0.001196/call按供应商原价
- 成功率
- 100%近 30 天 · 57 次
- 延迟 p50
- 3.6 秒p95 6.6 秒
- 最后验证
- 2026年7月28日实测可用
GEThttps://toolswitch.dev/v1/tools/diffbot.x.extract-article?url=https%3A%2F%2Fwww.technologyreview.com%2F2020%2F09%2F04%2F1008156%2Fknowledge-graph-ai-reads-web-machine-learning-natural-language-processing%2F预览- 可用平台额度调用
- 同步返回
- 读取公开数据
参数
different HOST than base_url — api.diffbot.com, not kg.diffbot.com
| 参数 | 类型 | 必填 | 说明 | 示例 |
|---|---|---|---|---|
| 查询参数 | ||||
url | 字符串 | 必填 | target URL to extract | https://www.technologyreview.com/2020/09/04/1008156/knowledge-graph-ai-reads-web-machine-learning-natural-language-processing/ |
proxy | 字符串 | 可选 | ||
fields | 字符串 | 可选 | comma-delimited optional fields: links, extlinks, meta, querystring, breadcrumb, quotes | |
paging | 布尔 | 可选 | pass false to disable automatic concatenation of multi-page articles | true |
scroll | 字符串 | 可选 | 'slow' or 'fast' — triggers lazy-loaded content | |
maxTags | 整数 | 可选 | max automatically-generated tags to return | 10 |
timeout | 整数 | 可选 | 30000 | |
callback | 字符串 | 可选 | ||
useProxy | 字符串 | 可选 | 'default' = datacenter proxy (2 credits/page); 'none' disables | |
proxyAuth | 字符串 | 可选 | ||
discussion | 布尔 | 可选 | pass false to disable automatic comment extraction | true |
renderDelay | 整数 | 可选 | extra rendering ms before DOM extraction, max 180000 | |
tagConfidence | 数字 | 可选 | minimum tag relevance score 0.0-1.0 | 0.5 |
naturalLanguage | 字符串 | 可选 | run text through the NLP API: entities, sentiment, summary, facts, etc. | |
categoryConfidence | 数字 | 可选 | minimum category relevance score 0.0-1.0 | 0.5 |
summaryNumSentences | 整数 | 可选 | max sentences in the generated summary | 3 |
- 查询参数
url字符串必填target URL to extract
示例：
https://www.technologyreview.com/2020/09/04/1008156/knowledge-graph-ai-reads-web-machine-learning-natural-language-processing/proxy字符串可选fields字符串可选comma-delimited optional fields: links, extlinks, meta, querystring, breadcrumb, quotes
paging布尔可选pass false to disable automatic concatenation of multi-page articles
示例：
truescroll字符串可选'slow' or 'fast' — triggers lazy-loaded content
maxTags整数可选max automatically-generated tags to return
示例：
10timeout整数可选示例：
30000callback字符串可选useProxy字符串可选'default' = datacenter proxy (2 credits/page); 'none' disables
proxyAuth字符串可选discussion布尔可选pass false to disable automatic comment extraction
示例：
truerenderDelay整数可选extra rendering ms before DOM extraction, max 180000
tagConfidence数字可选minimum tag relevance score 0.0-1.0
示例：
0.5naturalLanguage字符串可选run text through the NLP API: entities, sentiment, summary, facts, etc.
categoryConfidence数字可选minimum category relevance score 0.0-1.0
示例：
0.5summaryNumSentences整数可选max sentences in the generated summary
示例：
3
代码示例
将 $TOOLSWITCH_KEY 替换为你在控制台创建的密钥。
curl -X GET 'https://toolswitch.dev/v1/tools/diffbot.x.extract-article?url=https%3A%2F%2Fwww.technologyreview.com%2F2020%2F09%2F04%2F1008156%2Fknowledge-graph-ai-reads-web-machine-learning-natural-language-processing%2F' \
-H "X-Toolswitch-Key: $TOOLSWITCH_KEY"import os
import requests
response = requests.request(
"GET",
"https://toolswitch.dev/v1/tools/diffbot.x.extract-article?url=https%3A%2F%2Fwww.technologyreview.com%2F2020%2F09%2F04%2F1008156%2Fknowledge-graph-ai-reads-web-machine-learning-natural-language-processing%2F",
headers={"X-Toolswitch-Key": os.environ["TOOLSWITCH_KEY"]},
)
response.raise_for_status()
print(response.text)const response = await fetch("https://toolswitch.dev/v1/tools/diffbot.x.extract-article?url=https%3A%2F%2Fwww.technologyreview.com%2F2020%2F09%2F04%2F1008156%2Fknowledge-graph-ai-reads-web-machine-learning-natural-language-processing%2F", {
method: "GET",
headers: {
"X-Toolswitch-Key": process.env.TOOLSWITCH_KEY ?? "",
},
});
if (!response.ok) throw new Error(`Request failed: ${response.status}`);
console.log(await response.text());网关接口为预览版，地址与鉴权方式可能调整。 示例参数仅为样例数据。 调用按 $0.001196/call 计费，已含服务费。