WorldTeacher
0406fe4f6f
- Updated the `from_tuple` method in `Prof` class to specify return type. - Added type hints for various methods in `LehmannsClient`, `OpenAI`, `WebRequest`, and `ZoteroController` classes to improve code clarity and type safety. - Modified `pdf_to_csv` function to return a string instead of a DataFrame. - Enhanced error handling and type hints in `wordparser` and `xmlparser` modules. - Removed unused UI file `Ui_medianadder.ts`. - Improved the layout and structure of the `semesterapparat_ui` to enhance user experience. - Updated file picker to support `.doc` files in addition to `.docx`. - Added unique item handling in `Ui` class to prevent duplicates in apparat list. - General code cleanup and consistency improvements across various files.
24 lines
561 B
Python
24 lines
561 B
Python
# add depend path to system path
|
|
|
|
from pdfquery import PDFQuery
|
|
|
|
|
|
def pdf_to_csv(path: str) -> str:
|
|
"""
|
|
Extracts the data from a pdf file and returns it as a pandas dataframe
|
|
"""
|
|
file = PDFQuery(path)
|
|
file.load()
|
|
# get the text from the pdf file
|
|
text_elems = file.extract([("with_formatter", "text"), ("all_text", "*")])
|
|
extracted_text = text_elems["all_text"]
|
|
|
|
return extracted_text
|
|
|
|
|
|
if __name__ == "__main__":
|
|
text = pdf_to_csv("54_pdf.pdf")
|
|
# remove linebreaks
|
|
text = text.replace("\n", "")
|
|
# print(text)
|