import os import csv from bs4 import BeautifulSoup # 设置文件夹路径 folder_path = 'C:/Users/test/Desktop/DIDItest' # 遍历文件夹中的所有文件和子文件夹 for root, dirs, files in os.walk(folder_path): for file_name in files: if file_name.endswith('.html'): file_path = os.path.join(root, file_name) # 打开HTML文件并读取源代码 with open(file_path, 'r', encoding='utf-8') as file: html_content = file.read() # 在这里可以对源代码进行进一步的操作和提取 soup = BeautifulSoup(html_content, 'html.parser') messages = soup.find_all('p') for message in messages: talk_id_tag = message.find_previous('a') if talk_id_tag: talk_id = talk_id_tag.text.strip()[1:] time = message.contents[0].strip().split(',')[0][1:] send_phone = message.find('span', class_='hint-success').text.strip() receive_phone = message.find_all('span', class_='hint-success')[1].text.strip() content_tag = message.find('a') if content_tag: content = content_tag['href'] content_type = '音频' else: content = message.text.strip() content_type = '文本' print("talkid:", talk_id) print("时间:", time) print("发送号码:", send_phone) print("接收号码:", receive_phone) print("发送内容:", content) print()

这段代码有一个缩进问题，最后的`print`语句没有在正确的位置，应该在`for`循环内，以便在每次迭代时打印出提取的信息。请将最后的`print`语句缩进到正确的位置。以下是修改后的代码：

import os
import csv
from bs4 import BeautifulSoup

# 设置文件夹路径
folder_path = 'C:/Users/test/Desktop/DIDItest'

# 遍历文件夹中的所有文件和子文件夹
for root, dirs, files in os.walk(folder_path):
    for file_name in files:
        if file_name.endswith('.html'):
            file_path = os.path.join(root, file_name)

            # 打开HTML文件并读取源代码
            with open(file_path, 'r', encoding='utf-8') as file:
                html_content = file.read()

            # 在这里可以对源代码进行进一步的操作和提取

            soup = BeautifulSoup(html_content, 'html.parser')

            messages = soup.find_all('p')

            for message in messages:
                talk_id_tag = message.find_previous('a')
                if talk_id_tag:
                    talk_id = talk_id_tag.text.strip()[1:]
                    time = message.contents[0].strip().split(',')[0][1:]
                    send_phone = message.find('span', class_='hint-success').text.strip()
                    receive_phone = message.find_all('span', class_='hint-success')[1].text.strip()
                    content_tag = message.find('a')
                    if content_tag:
                        content = content_tag['href']
                        content_type = '音频'
                    else:
                        content = message.text.strip()
                        content_type = '文本'

                    print("talkid:", talk_id)
                    print("时间:", time)
                    print("发送号码:", send_phone)
                    print("接收号码:", receive_phone)
                    print("发送内容:", content)
                    print()

请注意，这段代码还没有将提取到的信息写入CSV文件，你可以根据需要进一步完善代码来实现写入CSV的功能。