知微
fa45d8aa5f
- health_checklist.json: 192.168.1.122→node122
- ocr_client.py: docstring IP→node122
- docs/market-data-requirements.md: IP→node122
- 所有API调用通过ProxyHandler({})绕过系统代理
Privoxy对node122:18003返回500，直连正常
69 lines
2.4 KiB
Python
Executable File
69 lines
2.4 KiB
Python
Executable File
#!/usr/bin/env python3
|
|
"""
|
|
ocr_client.py — 通过小果网关（node122:18003）的 GLM-OCR-8bit 做截图OCR
|
|
|
|
用法：
|
|
python3 ocr_client.py <image_path>
|
|
python3 ocr_client.py <image_path> "自定义提问"
|
|
|
|
返回 dict {"success": bool, "text": "...", "raw": "..."}
|
|
"""
|
|
import sys
|
|
import json
|
|
import base64
|
|
import urllib.request
|
|
|
|
OCR_URL = "http://node122:18003/v1/chat/completions"
|
|
OCR_MODEL = "GLM-OCR-8bit"
|
|
|
|
def ocr_image(image_path, prompt="请详细识别这张图片中的所有文字，包括数字、股票名称、金额等。用中文回复。"):
|
|
"""发送截图到小果的GLM-OCR-8bit识别文字"""
|
|
try:
|
|
with open(image_path, 'rb') as f:
|
|
img_b64 = base64.b64encode(f.read()).decode()
|
|
except FileNotFoundError:
|
|
return {"success": False, "text": f"文件不存在: {image_path}"}
|
|
except Exception as e:
|
|
return {"success": False, "text": f"读取文件失败: {e}"}
|
|
|
|
payload = json.dumps({
|
|
"model": OCR_MODEL,
|
|
"messages": [{
|
|
"role": "user",
|
|
"content": [
|
|
{"type": "text", "text": prompt},
|
|
{"type": "image_url", "image_url": {"url": f"data:image/png;base64,{img_b64}"}}
|
|
]
|
|
}],
|
|
"max_tokens": 1500,
|
|
"temperature": 0.1,
|
|
}).encode()
|
|
|
|
req = urllib.request.Request(OCR_URL, data=payload, headers={"Content-Type": "application/json"})
|
|
try:
|
|
resp = urllib.request.urlopen(req, timeout=60)
|
|
data = json.loads(resp.read().decode())
|
|
text = data.get("choices", [{}])[0].get("message", {}).get("content", "")
|
|
return {"success": True, "text": text, "raw": data}
|
|
except urllib.error.URLError as e:
|
|
return {"success": False, "text": f"请求失败: {e}"}
|
|
except Exception as e:
|
|
return {"success": False, "text": f"解析失败: {e}"}
|
|
|
|
|
|
if __name__ == "__main__":
|
|
args = sys.argv[1:]
|
|
if not args:
|
|
print("用法: python3 ocr_client.py <图片路径> [自定义提示]")
|
|
sys.exit(1)
|
|
|
|
img_path = args[0]
|
|
prompt = args[1] if len(args) > 1 else "请详细识别这张图片中的所有文字，包括数字、股票名称、金额等。用中文回复。"
|
|
|
|
result = ocr_image(img_path, prompt)
|
|
if result["success"]:
|
|
print(result["text"])
|
|
else:
|
|
print(f"OCR失败: {result['text']}", file=sys.stderr)
|
|
sys.exit(1)
|