zy123/zbparse
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

12.12 豆包测试

Browse Source
This commit is contained in:
zy123 2024-12-12 10:59:51 +08:00
parent 0b85d3a2fd
commit dc30de3087
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
flask_app/general/file2markdown.py
View File

@ -50,12 +50,12 @@ def convert_pdf_to_markdown(file_path):
resp = textin.recognize_pdf2md(image, { resp = textin.recognize_pdf2md(image, {
'page_start': 0, 'page_start': 0,
'page_count': 50, # 设置解析页数为50页 'page_count': 50, # 设置解析页数为50页
'table_flavor': 'md', # html 按html语法输出表格 'table_flavor': 'html', # html 按html语法输出表格
'parse_mode': 'scan', # 设置解析模式为scan模式 'parse_mode': 'auto', # 设置解析模式为scan模式
'page_details': 0, # 不包含页面细节 'page_details': 0, # 不包含页面细节
'markdown_details': 1, 'markdown_details': 1,
'apply_document_tree': 1, 'apply_document_tree': 1,
'dpi': 144 # 分辨率设置为144 dpi 'dpi': 216 # 分辨率设置默认为144 dpi
}) })
print("request time: ", resp.elapsed.total_seconds()) print("request time: ", resp.elapsed.total_seconds())
data = json.loads(resp.text) data = json.loads(resp.text)