python批量讀取文本文件合並寫入到一個html，方便全文搜索

 

from io import open
import os

def  file_name(file_dir):
    """
    獲取某文件夾下，特定擴展名的文件名，
    返回特定擴展名文件列表
    """
    L=[]
    for root, dirs, files in os.walk(file_dir):
        for  file  in files:
            if os.path.splitext(file)[1] ==  '.txt': #os.path.splitext()函數將路徑拆分為文件名+擴展名
                L.append(file)
    return L






filedir = 'E:/pdfTotxt/txt/'
L = file_name(file_dir=filedir)
index=0
htmlFile= 'E:/pdfTotxt/txt/txt.html'
for i in range(len(L)):
    if index<500 :
        fineName=L[i]
        txtFile=filedir+'/'+L[i]
        f = open(txtFile, 'r', encoding='UTF-8')
        content = f.read()
        print(content)
        index=index+1
        with open(htmlFile, mode='a',encoding='UTF-8') as filename:
            filename.write('<li>')
            filename.write('<a target=_blank  href=http://xxx/jimage/pdf/%E9%A1%B5%E9%9D%A2_'+fineName[3:6]+'.jpg >'+L[i]+'</a></br>')
            filename.write('<pre>')
            filename.write(content)  # 換行
            filename.write('</pre>')
            filename.write('</li>')
            filename.write('\n')  # 換行