Baidu OCR icon

Baidu OCR

使用百度智能云 OCR API 识别图片和文档中的文字

Actions13

通用文字识别（高精度版）

AI-generated

Summary

Extracts text and structured data from images or PDFs using Baidu OCR high‑precision mode.

Inputs

  • inputType — Specifies whether the input is binary image data from a previous node or a public image URL.
  • binaryPropertyName — Comma‑separated list of attribute names that contain the binary image or PDF data.
  • pdfPageRange — Page range to process for PDF files; ignored for image inputs.
  • imageUrl — Public URL of the image to recognize when inputType is 'url'.

Output shape

array of items where each item's json field contains the OCR result including plain text and any extracted key‑value pairs

The operation may return multiple items when several binary attributes are processed; errors are returned as separate items if continueOnFail is enabled.

Examples

Example 1: OCR a binary image supplied by a preceding node

Set inputType to binaryData; optionally adjust binaryPropertyName and pdfPageRange; keep operation set to 高精度版

Example 2: OCR an image loaded from a public URL

Set inputType to url and provide the image URL in imageUrl

Example 3: Extract text from specific PDF pages

Set inputType to binaryData, specify the PDF attribute in binaryPropertyName, and set pdfPageRange to the desired page numbers

Links

Discussion