在文字识别ocr中，这种json格式的东西怎么转换成txt或者work文档？
在文字识别ocr中，这种json格式的东西怎么转换成txt或者work文档？HTTP/1.1 200 OK [Date: Mon, 25 Sep 2023 05:17:28 GMT, Content-Type: application/json;charset=UTF-8, Content-Length: 2519, Connection: keep-alive, Keep-Alive: timeout=25, Vary: Accept-Encoding, Vary: Accept-Encoding, Server: Tengine, X-Ca-Request-Id: 75574F4F-9B3A-4A9C-A460-C883475FC714]
13:17:28.966 [main] DEBUG org.apache.http.wire - << "{"page_list":[{"angle":0,"doc_index":1,"height":524,"orgHeight":524,"orgWidth":761,"page_id":0,"subject_list":[{"content_list_info":[{"doc_index":1,"pos":[{"x":6,"y":0},{"x":0,"y":0},{"x":0,"y":0},{"x":9,"y":0}]}],"ids":[],"is_multipage":false,"prism_wordsInfo":[{"pos":[{"x":5,"y":0},{"x":2,"y":0},{"x":2,"y":0},{"x":6,"y":0}],"word":"5.[0xe8][0x8b][0xa5]"},{"pos":[{"x":2,"y":0},{"x":0,"y":0},{"x":0,"y":0},{"x":2,"y":0}],"word":"x+y=3[0xef][0xbc][0x8c]xy=1[0xef][0xbc][0x8c]"},{"pos":[{"x":0,"y":0},{"x":0,"y":0},{"x":0,"y":0},{"x":0,"y":0}],"word":"[0xef][0xbc][0x8c][0xe5][0x88][0x99]"},{"pos":[{"x":0,"y":0},{"x":0,"y":0},{"x":0,"y":0},{"x":0,"y":0}],"word":"$$x ^ { 2 } + y ^ { 2 } =$$"},{"pos":[{"x":0,"y":0},{"x":0,"y":0},{"x":0,"y":0},{"x":0,"y":0}],"word":"."},{"pos":[{"x":0,"y":0},{"x":0,"y":0},{"x":0,"y":0},{"x":0,"y":0}],"word":"$$\left( x - y \right) ^ { 2 } =$$"}],"text":"5.[0xe8][0x8b][0xa5] x+y=3[0xef][0xbc][0x8c]xy=1[0xef][0xbc][0x8c] [0xef][0xbc][0x8c][0xe5][0x88][0x99] $$x ^ { 2 } + y ^ { 2 } =$$ . $$\left( x - y \right) ^ { 2 } =$$ "},{"content_list_info":[{"doc_index":1,"pos":[{"x":7,"y":0},{"x":0,"y":0},{"x":0,"y":0},{"x":9,"y":0}]}],"ids":[],"is_multipage":false,"prism_wordsInfo":[{"pos":[{"x":8,"y":0},{"x":2,"y":0},{"x":3,"y":0},{"x":9,"y":0}],"word":"6.[0xe8][0x8b][0xa5]"},{"pos":[{"x":2,"y":0},{"x":0,"y":0},{"x":0,"y":0},{"x":3,"y":0}],"word":"$$\left( x + y \right) ^ { 2 } = 9 [0xef][0xbc][0x8c] \left( x - y \right) ^ { 2 } = 5 [0xef][0xbc][0x8c]$$"},{"pos":[{"x":0,"y":0},{"x":0,"y":0},{"x":0,"y":0},{"x":0,"y":0}],"word":"[0xe5][0x88][0x99]xy="}],"text":"6.[0xe8][0x8b][0xa5] $$\left( x + y \right) ^ { 2 } = 9 [0xef][0xbc][0x8c] \left( x - y \right) ^ { 2 } = 5 [0xef][0xbc][0x8c]$$ [0xe5][0x88][0x99]xy= "},{"content_list_info":[{"doc_index":1,"pos":[{"x":11,"y":0},{"x":0,"y":0},{"x":0,"y":0},{"x":13,"y":0}]}],"ids":[],"is_multipage":false,"prism_wordsInfo":[{"pos":[{"x":11,"y":0},{"x":4,"y":0},{"x":4,"y":0},{"x":12,"y":0}],"word":"7.[0xe8][0x8b][0xa5]"},{"pos":[{"x":3,"y":0},{"x":1,"y":0},{"x":1,"y":0},{"x":4,"y":0}],"word":"$$x ^ { 2 } + k x + 1 6$$"},{"pos":[{"x":1,"y":0},{"x":0,"y":0},{"x":0,"y":0},{"x":1,"y":0}],"word":"[0xe6][0x98][0xaf][0xe5][0xae][0x8c][0xe5][0x85][0xa8][0xe5][0xb9][0xb3][0xe6][0x96][0xb9][0xe5][0x85][0xac][0xe5][0xbc][0x8f][0xef][0xbc][0x8c][0xe5][0x88][0x99][0xe6][0x95][0xb4][0xe6][0x95][0xb0]"},{"pos":[{"x":0,"y":0},{"x":0,"y":0},{"x":0,"y":0},{"x":0,"y":0}],"word":"k="}],"text":"7.[0xe8][0x8b][0xa5] $$x ^ { 2 } + k x + 1 6$$ [0xe6][0x98][0xaf][0xe5][0xae][0x8c][0xe5][0x85][0xa8][0xe5][0xb9][0xb3][0xe6][0x96][0xb9][0xe5][0x85][0xac][0xe5][0xbc][0x8f][0xef][0xbc][0x8c][0xe5][0x88][0x99][0xe6][0x95][0xb4][0xe6][0x95][0xb0] k= "},{"content_list_info":[{"doc_index":1,"pos":[{"x":15,"y":0},{"x":0,"y":0},{"x":0,"y":0},{"x":16,"y":0}]}],"ids":[],"is_multipage":false,"prism_wordsInfo":[{"pos":[{"x":14,"y":0},{"x":0,"y":0},{"x":0,"y":0},{"x":15,"y":0}],"word":"8.[0xe8][0xaf][0xa5][0xe5][0x9b][0xbe][0xe5][0x8f][0xaf][0xe4][0xbb][0xa5][0xe7][0x94][0xa8][0xe6][0x9d][0xa5][0xe9][0xaa][0x8c][0xe8][0xaf][0x81][0xe6][0x88][0x91][0xe4][0xbb][0xac][0xe5][0xad][0xa6][0xe8][0xbf][0x87][0xe7][0x9a][0x84][0xe4][0xb9][0x98][0xe6][0xb3][0x95][0xe5][0x85][0xac][0xe5][0xbc][0x8f]"}],"text":"8.[0xe8][0xaf][0xa5][0xe5][0x9b][0xbe][0xe5][0x8f][0xaf][0xe4][0xbb][0xa5][0xe7][0x94][0xa8][0xe6][0x9d][0xa5][0xe9][0xaa][0x8c][0xe8][0xaf][0x81][0xe6][0x88][0x91][0xe4][0xbb][0xac][0xe5][0xad][0xa6][0xe8][0xbf][0x87][0xe7][0x9a][0x84][0xe4][0xb9][0x98][0xe6][0xb3][0x95][0xe5][0x85][0xac][0xe5][0xbc][0x8f] "}],"width":761}],"requestId":"75574F4F-9B3A-4A9C-A460-C883475FC714"}"
13:17:28.967 [main] DEBUG org.apache.http.impl.conn.BasicClientConnectionManager - Releasing connection org.apache.http.impl.conn.ManagedClientConnectionImpl@19d37183
13:17:28.967 [main] DEBUG org.apache.http.impl.conn.BasicClientConnectionManager - Connection can be kept alive for 25000 MILLISECONDS
写回答
-
-
要将JSON格式的数据转换为txt或word文档，你需要首先解析JSON数据，然后将识别到的文本提取出来。以下是一个使用Python进行解析和转换的简单示例：
import json # 假设这是你的JSON数据 json_data = '{"page_list":[{"angle":0,"doc_index":1,"height":524,"orgHeight":524,"orgWidth":761,"page_id":0,"subject_list":[{"content_list_info":[{"doc_index":1,"pos":[{"x":6,"y":0},{"x":0,"y":0},{"x":0,"y":0},{"x":9,"y":0}]}],"ids":[],"is_multipage":false,"prism_wordsInfo":[{"pos":[{"x":5,"y":0},{"x":2,"y":0},{"x":2,"y":0},{"x":6,"y":0}],"word":"5.[0xe8][0x8b][0xa5]"},{"pos":[{"x":2,"y":0},{"x":0,"y":0},{"x":0,"y":0},{"x":2,"y":0}],"word":"x+y=3[0xef][0xbc][0x8c]xy=1[0xef][0xbc][0x8c]"},{"pos":[{"x":0,"y":0},{"x":0,"y":0},{"x":0,"y":0},{"x":0,"y":0}],"word":"[0xef][0xbc][0x8c][0xe5][0x88][0x99]"},{"pos":[{"x":0,"y":0},{"x":0,"y":0},{"x":0,"y":0},{"x":0,"y":0}],"word":"$$x ^ { 2 } + y ^ { 2 } =$$"},{"pos":[{"x":0,"y":0},{"x":0,"y":0},{"x":0,"y":0},{"x":0,"y":0}],"word":"."},{"pos":[{"x":0,"y":0},{"x":0,"y":0},{"x":0,"y":0},{"x":0,"y":0}],"word":"$$\left( x - y \right) ^ { 2 } =$$"}],"text":"5.[0xe8][0x8b][0xa5] x+y=3[0xef][0xbc][0x8c]xy=1[0xef][0xbc][0x8c] [0xef][0xbc][0x8c][0xe5][0x88][0x99] $$x ^ { 2 } + y ^ { 2 } =$$ . $$\left( x - y \right) ^ { 2 } =$$ "},{"content_list_info":[{"doc_index":1,"pos":[{"x":7,"y":0},{"x":0,"y":0},{"x":0,"y":0},{"x":9,"y":0}]}],"ids":[],"is_multipage":false,"prism_wordsInfo":[{"pos":[{"x":8,"y":0},{"x":2,"y":0},{"x":3,"y":0},{"x":9,"y":0}],"word":"6.[0xe8][0x8b][0xa5]"},{"pos":[{"x":2,"y":0},{"x":0,"y":0},{"x":0,"y":0},{"x":3,"y":0}],"word":"$$\left( x + y \right) ^ { 2 } = 9 [0xef][0xbc][0x8c] \left( x - y \right) ^ { 2 } = 5 [0xef][0xbc][0x8c]$$"},{"pos":[{"x":0,"y":0},{"x":0,"y":0},{"x":0,"y":0},{"x":0,"y":0}],"word":"[0xe5][0x88][0x99]xy="}],"text":"6.[0xe8][0x8b][0xa5] "},{"content_list_info":[{"doc_index":1,"pos":[{"x":0,"y":0},{"x":0,"y":0},{"x":0,"y":0},{"x":0,"y":0}]}],"ids":[],"is_multipage":false,"prism_wordsInfo":[{"pos":[{"x":0,"y":0},{"x":0,"y":0},{"x":0,"y":0},{"x":0,"y":0}],"word":"[0xef][0xbc][0x8c][0xe5][0x88][0x99]"},{"pos":[{"x":0,"y":0},{"x":0,"y":0},{"x":0,"y":0},{"x":0,"y":0}],"word":"$$x ^ { 2 } + y ^ { 2 } =$$"},{"pos":[{"x":0,"y":0},{"x":0,"y":0},{"x":0,"y":0},{"x":0,"y":0}],"word":"."},{"pos":[{"x":0,"y":0},{"x":0,"y":0},{"x":0,"y":0},{"x":0,"y":0}],"word":"$$\left( x - y \right) ^ { 2 } =$$"}],"text":"[0xef][0xbc][0x8c][0xe5][0x88][0x99] $$x ^ { 2 } + y ^ { 2 } =$$ . $$\left( x - y \right) ^ { 2 } =$$ "}],"page_count":1,"total_page_count":1,"word_count":5}' # 定义一个函数来转换JSON数据 def convert_json_to_txt(json_data): text_list = [] # 遍历每一页的识别结果 for page in json_data['page_list']: angle = page['angle'] doc_index = page['doc_index'] height = page['height'] orgHeight = page['orgHeight'] orgWidth = page['orgWidth'] page_id = page['page_id'] # 遍历每一行的识别结果 for line in page['subject_list']: content_list_info = line['content_list_info'] ids = line['ids'] is_multipage = line['is_multipage'] # 遍历每一行的识别结果 for word in content_list_info: pos = word['pos'] word_text = word['word'] text_list.append(f'{angle}.{doc_index}.{height}.{orgHeight}.{orgWidth}.{page_id}.{word_text}') # 将识别结果合并为一个字符串 text = ' '.join(text_list) # 将识别结果转换为txt文档 with open('recognized_text.txt', 'w', encoding='utf-8') as f: f.write(text) # 调用函数来转换JSON数据 convert_json_to_txt(json_data)这个程序首先解析JSON数据，然后遍历每一页的识别结果，再遍历每一行的识别结果，最后将识别结果合并为一个字符串并保存为txt文档。
2023-10-04 16:45:40赞同 展开评论 打赏
版权声明：本文内容由阿里云实名注册用户自发贡献，版权归原作者所有，阿里云开发者社区不拥有其著作权，亦不承担相应法律责任。具体规则请查看《阿里云开发者社区用户服务协议》和《阿里云开发者社区知识产权保护指引》。如果您发现本社区中有涉嫌抄袭的内容，填写侵权投诉表单进行举报，一经查实，本社区将立刻删除涉嫌侵权内容。
