获取doc/docx/pdf文件中第一行的字数

from docx import Document

def get_first_line_word_count(file_path):
    doc = Document(file_path)
    first_paragraph = doc.paragraphs[0].text
    word_count = len(first_paragraph.split())
    return word_count

file_path = "path/to/your/doc/docx/file.docx"
word_count = get_first_line_word_count(file_path)
print("The word count of the first line is:", word_count)

import PyPDF2

def get_first_line_word_count(file_path):
    with open(file_path, "rb") as file:
        pdf = PyPDF2.PdfFileReader(file)
        first_page = pdf.getPage(0)
        first_line = first_page.extractText().split("\n")[0]
        word_count = len(first_line.split())
        return word_count

file_path = "path/to/your/pdf/file.pdf"
word_count = get_first_line_word_count(file_path)
print("The word count of the first line is:", word_count)

from pdfminer.high_level import extract_text

def get_first_line_word_count(file_path):
    text = extract_text(file_path)
    first_line = text.split("\n")[0]
    word_count = len(first_line.split())
    return word_count

file_path = "path/to/your/pdf/file.pdf"
word_count = get_first_line_word_count(file_path)
print("The word count of the first line is:", word_count)