chunzhi/chatgpt_academic
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

update error message

Browse Source
This commit is contained in:
qingxu fu 2023-07-07 17:41:43 +08:00
parent be96232127
commit 67d9051890
1 changed files with 13 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
crazy_functions/总结word文档.py
View File

@ -14,17 +14,19 @@ def 解析docx(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot
doc = Document(fp) doc = Document(fp)
file_content = "\n".join([para.text for para in doc.paragraphs]) file_content = "\n".join([para.text for para in doc.paragraphs])
else: else:
try:
import win32com.client import win32com.client
word = win32com.client.Dispatch("Word.Application") word = win32com.client.Dispatch("Word.Application")
word.visible = False word.visible = False
# 打开文件 # 打开文件
print('fp', os.getcwd())
doc = word.Documents.Open(os.getcwd() + '/' + fp) doc = word.Documents.Open(os.getcwd() + '/' + fp)
# file_content = doc.Content.Text # file_content = doc.Content.Text
doc = word.ActiveDocument doc = word.ActiveDocument
file_content = doc.Range().Text file_content = doc.Range().Text
doc.Close() doc.Close()
word.Quit() word.Quit()
except:
raise RuntimeError('请先将.doc文档转换为.docx文档。')
print(file_content) print(file_content)
# private_upload里面的文件名在解压zip后容易出现乱码（rar和7z格式正常），故可以只分析文章内容，不输入文件名 # private_upload里面的文件名在解压zip后容易出现乱码（rar和7z格式正常），故可以只分析文章内容，不输入文件名