/alibabacloud-parse-x

name: alibabacloud-parse-x
description: >
  Alibaba Cloud Parse-X intelligent document parsing and extraction tool.
  Supports two capabilities: (1) Parse — convert documents, images, and
  audio/video to structured Markdown/JSON/HTML with layout, table, and
  synopsis support; (2) Extract — schema-driven information extraction with
  citations from parsed or new documents. Uses Parse-X HTTP (Spectrum gateway,
  Bearer token via DASHSCOPE_API_KEY).

  **When to use this skill** — the user asks to:
  - Parse / convert / analyze any document, image, spreadsheet, or media file
    (PDF, Word, PPT, Excel, Markdown, HTML, images, audio, video)
  - Extract structured fields or entities from a document
  - Convert files to Markdown or JSON format
  - Process files with mentions of: 解析, 文档解析, 文件解析, 表格, Excel,
    xlsx, xls, PDF, Word, PPT, 合同, 发票, 报告, 图片, 本地文件, 上传,
    markdown, JSON, 提取, 抽取, 字段, parse, extract, document parsing,
    parse file, 解析文档, 解析文件, 文件转换, 图片解析, 表格提取

Parse-X Document Parsing & Extraction

Two Capabilities

| Capability | Sub-command | Description | |------------|-------------|-------------| | **Parse** | `parse` | Convert documents / images / audio / video to structured output (Markdown, JSON, HTML, visual_layout_info) | | **Extract**| `extract` | Schema-driven information extraction with optional citations, reusing parse results or fresh files |

Invocation Mode

**Parse-X HTTP (Spectrum gateway)**: Authenticate with `DASHSCOPE_API_KEY` Bearer token; simple HTTP calls, no SDK needed. Accepts file URLs or local file paths — local files are automatically uploaded via DashScope file service, parsed, then cleaned up.

Key headers: `X-DashScope-OssResourceResolve: enable` (parse/extract — resolves `oss://bailian` URIs internally), `X-DashScope-Inner-Include-Url: true` (file upload — returns `oss://bailian/{id}` URL).

Environment Variables

| Variable | Description | Required | |----------|-------------|----------| | `DASHSCOPE_API_KEY` | API key for Parse-X HTTP (Bearer token) | **Required** | | `PARSE_X_ENDPOINT` | Parse-X base URL (default: `https://dashscope.aliyuncs.com/api/v2/apps/pre-parse-x`) | Optional | | `SKILL_SESSION_ID` | Session identifier for User-Agent (auto-generated 32-char hex if unset) | Optional |

---

Usage

python scripts/parse_x.py <command> <file_url_or_path> [options]

Parse Examples

# Parse a document URL (PDF)
python scripts/parse_x.py parse https://docmind-api-cn-hangzhou.oss-cn-hangzhou.aliyuncs.com/static/服务采购合同_扫描版.pdf
# Parse a local file (auto-uploads via file service, parses, then cleans up)
python scripts/parse_x.py parse ./contract.pdf --output markdown
# Parse with AUTO enhancement, pages 1-5
python scripts/parse_x.py parse https://docmind-api-cn-hangzhou.oss-cn-hangzhou.aliyuncs.com/static/服务采购合同_扫描版.pdf \
  --enhancement AUTO --pages 1-5
# Parse with visual layout info and markdown tables
python scripts/parse_x.py parse https://docmind-api-cn-hangzhou.oss-cn-hangzhou.aliyuncs.com/static/服务采购合同_扫描版.pdf \
  --visual-layout --layout-table-format markdown --output markdown

# Parse headers and footers with image captions
python scripts/parse_x.py parse https://docmind-api-cn-hangzhou.oss-cn-hangzhou.aliyuncs.com/static/服务采购合同_扫描版.pdf \
  --head-foot --image-caption

# Parse audio/video with synopsis and diarization
python scripts/parse_x.py parse https://docmind-api-cn-hangzhou.oss-cn-hangzhou.aliyuncs.com/static/Wan3.0模型创意视频.mp4 \
  --enable-synopsis --enable-diarization

Extract Examples

# Extract structured fields from a document URL using an inline schema
python scripts/parse_x.py extract https://docmind-api-cn-hangzhou.oss-cn-hangzhou.aliyuncs.com/static/服务采购合同_扫描版.pdf \
  --extract-schema '{"type":"object","properties":{"buyer":{"type":"string"},"total_amount":{"type":"number"}}}'

# Extract using a schema JSON file
python scripts/parse_x.py extract https://docmind-api-cn-hangzhou.oss-cn-hangzhou.aliyuncs.com/static/服务采购合同_扫描版.pdf \
  --extract-schema ./schema.json --user-prompt "金额用小写，用财务规范书写"

# Extract from an already-parsed document (reuse parse biz_id, skip re-parsing)
python scripts/parse_x.py extract \
  --parsed-biz-id parse-x-20260901-xxxx \
  --extract-schema '{"type":"object","properties":{"contract_number":{"type":"string"}}}'

# Extract from a local file (auto-uploads, extracts, then cleans up)
python scripts/parse_x.py extract ./contract.pdf \
  --extract-schema ./schema.json --user-prompt "金额用小写，用财务规范书写"

# Allow inference and disable citations
python scripts/parse_x.py extract https://docmind-api-cn-hangzhou.oss-cn-hangzhou.aliyuncs.com/static/服务采购合同_扫描版.pdf \
  --extract-schema ./schema.json --allow-inference --no-citation

---

Parse Parameters

| Parameter | CLI Flag | Type | Description | |-----------|----------|------|-------------| | `<file_url_or_path>` | positional | string | File URL or local file path (local files are auto-uploaded) | | `processing.enhancement_mode` | `--enhancement` | `BASIC`/`ADVANCE`/`AUTO` | Enhancement mode | | `processing.user_prompt` | `--user-prompt` | string | Custom prompt | | `processing.doc_processing_config.page_index` | `--pages` | string | Page range, e.g. `1-5` | | `processing.doc_processing_config.head_foot` | `--head-foot` | bool | Parse headers/footers | | `processing.doc_processing_config.layout_position` | `--layout-position` | bool | Return bounding box coords | | `processing.doc_processing_config.image_caption` | `--image-caption` | bool | Enable image descriptions | | `processing.media_processing_config.enable_diarization` | `--enable-diarization` | bool | Speaker diarization (audio/video) | | `processing.media_processing_config.enable_synopsis_parse` | `--enable-synopsis` | bool | Synopsis parse + segments + summary (audio/video) | | `output.output_file_format` | `--output` | `markdown`/`json`/`html`/`visual_layout_info` | Output format | | `output.layout_table_format` | `--layout-tabl