问在docx文件中搜索一个单词，并在关键字文件夹中复制该文件。

EN

from docx import Document
from shutil import copyfile
import os, re, random

# Folder which contains all the resumes
ALL_RESUMES = "all_resumes/"
# The folder which will contain the separated resumes
SEGREGATED_RESUMES = "topic_wise_resumes/"

def get_keywords(keywords_file, create_new = False):
    """
    Get all keywords from file keywords_file. We get all keywords in lower case to remove confusion down the line.
    """
    fileOpen  = open(keywords_file, "r")        
    words = [x.strip().lower() for x in fileOpen.readline().split(',')]

    keywords = []
    for keyword in words:
        keywords.append(keyword)
        if(not(os.path.isdir(SEGREGATED_RESUMES))):
            os.makedirs(SEGREGATED_RESUMES + keyword)

    return keywords

def segregate_resumes(keywords):
    """
    Copy the resumes to the appropriate folders
    """
    # The pattern for regex match
    keyword_pattern = "|".join(keywords)

    # All resumes
    for filename in os.listdir(ALL_RESUMES):
        # basic sanity check
        if filename.endswith(".docx"):
            document = Document(ALL_RESUMES + filename)
            all_texts = []
            for p in document.paragraphs:
                all_texts.append(p.text)

            # The entire text in the resume in lowercase
            all_words_in_resume = " ".join(all_texts).lower()

            # The matching keywords
            matches = re.findall(keyword_pattern, all_words_in_resume)

            # Copy the resume to the keyword folder
            for match in matches:
                copyfile(ALL_RESUMES + filename, SEGREGATED_RESUMES + match + "/" + filename)

def create_sample_resumes(keywords, num = 5):
    """
    Function to create sample resumes for testing
    """
    for i in range(num):
        document = Document()
        document.add_heading('RESUME{}'.format(i))
        skills_ = random.sample(keywords, 2)
        document.add_paragraph("I have skills - {} and {}".format(*skills_))
        document.save(ALL_RESUMES + "resume{}.docx".format(i))

keywords = get_keywords("ResumeKeyword.txt")
print(keywords)
# create_sample_resumes(keywords)
segregate_resumes(keywords)