基金检索2

import os.path
import pandas as pd
import re
from datetime import datetime
import os
import tkinter as tk
from tkinter import filedialog

def get_folder():
    root = tk.Tk()
    root.withdraw()
    folder_path = filedialog.askdirectory()
    return folder_path

def count_files_in_folder(folder_path):
    try:
        # 使用 os.listdir 获取文件夹内所有文件和文件夹的列表
        files_list = os.listdir(folder_path)

        # 使用 len 函数获取列表的长度，即文件的数量
        file_count = len(files_list)

        return file_count
    except FileNotFoundError:
        print(f"文件夹 '{folder_path}' 不存在")
        return None

def create_dataframe_adjacent_pairs(names):
    df = pd.DataFrame({'a': names[:-1], 'b': names[1:]})
    return df

def read_html(html_file):
    # 打开HTML文件
    with open(html_file, 'r', encoding='utf-8') as file:
        # 读取文件内容
        html_content = file.read()
    return html_content

def get_links(pattern,html_content):
    # # 使用正则表达式提取 <!-- 和 --> 之间的内容
    matches = re.findall(pattern, html_content, re.DOTALL)

    # 存储提取的内容
    extracted_content_list = [match.strip() for match in matches]
    # for mylink in extracted_content_list:
    #     print(mylink)
    return extracted_content_list

data_list = []

# 获取当前时间
current_time = datetime.now()

html_path = get_folder()
file_count = count_files_in_folder(html_path)
print(file_count)

index1 = 0
for k in range(1,file_count+1):
    print(k)
    file_name = str(k)+'.html'
    html_file = os.path.join(html_path,file_name)
    html_content = read_html(html_file)

    # 使用正则表达式提取链接和文本
    matches = re.finditer(r'<strong\s.*?><a\s.*?href="(.*?)".*?>(.*?)</a></strong>', html_content)

    pattern2 = r'<p>负责人：(.*?)</p>'
    fzr = get_links(pattern2,html_content)

    pattern3 = r'<span class="goUnit">单位：(.*?)</span>'
    dw = get_links(pattern3,html_content)

    pattern4 = r'<p>金额：(.*?)</p>'
    je = get_links(pattern4,html_content)

    pattern5 = r'<p>类型：(.*?)</p>'
    lx = get_links(pattern5,html_content)

    pattern6 = r'<p>学科代码：(.*?)</p>'
    xkdm = get_links(pattern6,html_content)

    pattern7 = r'<p>开始时间：(.*?)</p>'
    sj = get_links(pattern7,html_content)

    for match, fzr1, dw1, je1, lx1, xkdm1, sj1 in zip(matches, fzr, dw, je, lx, xkdm, sj):
        index1 = index1 + 1

        print('--'+str(index1))
        print(match.group(2))
        print(match.group(1))
        print(fzr1)
        print(dw1)
        print(je1)
        print(lx1)
        print(xkdm1)
        print(sj1)
        data_list.append([str(index1),match.group(2),fzr1, dw1, je1, lx1, xkdm1, sj1,match.group(1)])


# 创建DataFrame
columns = ['No','标题','负责人', '单位', '金额', '类型', '代码', '时间','链接']
df = pd.DataFrame(data_list, columns=columns)

# 格式化为指定的字符串
formatted_time = current_time.strftime("%Y-%m-%d %H_%M_%S")

print(formatted_time)
file_out = 'output '+formatted_time+'.xlsx'
# 保存为xlsx文件
df.to_excel(file_out, index=False)
print("已保存为"+file_out+"文件")