Files
Wusunjiance/ocr_work/inspect_ocr.py
T

44 lines
1.4 KiB
Python

import json
json_path = r'D:\mineru_home\doclib\parsed\d9\d991db7dc971c6655661492bb28129f2089d03222b439064e30b7156ff1ba848\flash\1-10_1794301361022.json'
with open(json_path, 'r', encoding='utf-8') as f:
data = json.load(f)
def extract_text(content_list, depth=0):
"""Recursively extract text from content structure"""
result = []
for item in content_list:
if isinstance(item, dict):
if item.get('type') == 'text' and 'content' in item:
text = item['content']
if isinstance(text, str):
result.append(text)
elif 'content' in item:
result.extend(extract_text(item['content'], depth+1))
return result
# Check page 2
page2 = data['pages'][1]
print(f"=== Page 2 ===")
for i, block in enumerate(page2['blocks']):
btype = block.get('type', '?')
texts = extract_text(block.get('content', []))
full_text = ' '.join(texts)
if len(full_text) > 300:
full_text = full_text[:300] + '...'
print(f"[{btype}] {full_text}")
print()
# Also check page 3
page3 = data['pages'][2]
print(f"=== Page 3 ===")
for i, block in enumerate(page3['blocks']):
btype = block.get('type', '?')
texts = extract_text(block.get('content', []))
full_text = ' '.join(texts)
if len(full_text) > 300:
full_text = full_text[:300] + '...'
print(f"[{btype}] {full_text}")
print()