import os import re from bs4 import BeautifulSoup # 设置html文件路径 folder_path = r'C:\Users\test\Desktop\DIDItest' # 提取html文件内所需要数据 def extract_html_info(file_path): with open(file_path, 'r', encoding='utf-8') as file: # 读取HTML源代码 html = file.read() soup = BeautifulSoup(html, 'html.parser') # 提取所有的<p>标签 p_tags = soup.find_all('p') for p_tag in p_tags: # 提取ID talk_id = p_tag.find_previous(string=lambda text: isinstance(text, str) and '[talkid:' in text) talk_id = talk_id.strip('[talkid:]') # 提取时间 timestamp = p_tag.find_previous('body').find_previous('head').find('meta', {'http-equiv': 'Content=-Type'})[ 'content'] # 提取发送号码 send_number = p_tag.find('span', {'class': 'hint-success'}).text # 提取接收号码 receive_number = p_tag.find_all('span', {'class': 'hint-success'})[1].text # 提取信息内容 message = p_tag.previous_sibling.strip() # 遍历文件夹及子文件夹,提取HTML文件信息 for root, dirs, files in os.walk(folder_path): for file in files: if file.endswith('.html'): file_path = os.path.join(root, file) extract_html_info(file_path) # 判断是否是音频 if '音频' in message: file_url = p_tag.find('a')['href'] print( f"ID: {talk_id}, 时间: {timestamp}, 发送号码: {send_number}, 接收号码: {receive_number}, 音频文件地址: {file_url}") else: print( f"ID: {talk_id}, 时间: {timestamp}, 发送号码: {send_number}, 接收号码: {receive_number}, 信息内容: {message}")
时间: 2024-04-14 18:26:35 浏览: 169
你的代码有一些缩进错误,导致无法正确运行。以下是修正后的代码:
```python
import os
import re
from bs4 import BeautifulSoup
# 设置html文件路径
folder_path = r'C:\Users\test\Desktop\DIDItest'
# 提取html文件内所需要数据
def extract_html_info(file_path):
with open(file_path, 'r', encoding='utf-8') as file:
# 读取HTML源代码
html = file.read()
soup = BeautifulSoup(html, 'html.parser')
# 提取所有的<p>标签
p_tags = soup.find_all('p')
for p_tag in p_tags:
# 提取ID
talk_id = p_tag.find_previous(string=lambda text: isinstance(text, str) and '[talkid:' in text)
talk_id = talk_id.strip('[talkid:]')
# 提取时间
timestamp = p_tag.find_previous('body').find_previous('head').find('meta', {'http-equiv': 'Content=-Type'})['content']
# 提取发送号码
send_number = p_tag.find('span', {'class': 'hint-success'}).text
# 提取接收号码
receive_number = p_tag.find_all('span', {'class': 'hint-success'})[1].text
# 提取信息内容
message = p_tag.previous_sibling.strip()
# 判断是否是音频
if '音频' in message:
file_url = p_tag.find('a')['href']
print(f"ID: {talk_id}, 时间: {timestamp}, 发送号码: {send_number}, 接收号码: {receive_number}, 音频文件地址: {file_url}")
else:
print(f"ID: {talk_id}, 时间: {timestamp}, 发送号码: {send_number}, 接收号码: {receive_number}, 信息内容: {message}")
# 遍历文件夹及子文件夹,提取HTML文件信息
for root, dirs, files in os.walk(folder_path):
for file in files:
if file.endswith('.html'):
file_path = os.path.join(root, file)
extract_html_info(file_path)
```
在这个修正后的代码中,我将提取HTML文件信息的部分封装到了一个函数`extract_html_info`中。然后,我使用`os.walk`函数遍历了指定文件夹及其子文件夹,找到所有的HTML文件,并调用`extract_html_info`函数来提取信息。
希望这次能够顺利运行!如果你还有其他问题,请随时提问。
阅读全文
相关推荐



import os from bs4 import BeautifulSoup import re # 指定文件夹路径 folder_path = "C:/Users/test/Desktop/DIDItest" # 正则表达式模式 pattern = r'<body>(.*?)<\/body>' # 遍历文件夹中的所有文件 for root, dirs, files in os.walk(folder_path): for file in files: # 读取html文件 file_path = os.path.join(root, file) with open(file_path, "r", encoding="utf-8") as f: html_code = f.read() # 使用正则表达式匹配<body>标签内的数据 body_data = re.findall(pattern, html_code, re.DOTALL) # 剔除和() body_data = body_data[0].replace("", "").replace("()", "") # 使用正则表达式提取talk_id、时间、发送者ID和接收者ID matches = re.findall(r'\[talkid:(\d+)\](\d+年\d+月\d+日 \d+:\d+:\d+).*?<span.*?>(\d+)<.*?>(.*?)<', body_data) # 提取唯一ID,时间,发送号码和私聊群聊关键词 matches1 = re.findall(r'<span.*?hint-success.*?>(\d+)<.*?>', body_data) # match = re.search('(中发言|发送)\s(.*?)\s', body_data) # if match: # content = match.group(2) matches2 = re.findall('(中发言|发送)\s(.*?)\s', body_data) for match in matches2: content = match[1] soup = BeautifulSoup(content, 'html.parser') if soup.find('= 2: receive_id = matches1[3] # 处理匹配结果 for match in matches: talk_id = match[0] time = match[1] send_id = match[2] talk_type = match[3] # 进行时间格式转换,将time转换为"0000-00-00"格式 time = time.replace('年', '-').replace('月', '-').replace('日', '') talk_type = talk_type.replace('向', '私聊').replace('在群', '群聊') # 打印结果 print("Talk ID:", talk_id) print("Time:", time) print("Sender ID:", send_id) print("Receive_id:", receive_id) print("Talk_type:", talk_type) print("Content:",content) print("---")导入至csv






from bs4 import BeautifulSoup import csv import os import re # 设置文件夹路径 folder_path = 'C:/Users/test/Desktop/DIDItest' # 创建CSV文件 csv_file = open('output.csv', 'w', newline='') csv_writer = csv.writer(csv_file) csv_writer.writerow(['ID', '时间', '发送号码', '接收号码', '发送内容']) # 遍历文件夹下的所有文件 for root, dirs, files in os.walk(folder_path): for file in files: if file.endswith('.html'): file_path = os.path.join(root, file) # 打开文件并解析HTML源代码 with open(file_path, 'r', encoding='utf-8') as f: soup = BeautifulSoup(f, 'html.parser') # 提取talkid、时间、发送号码、接收号码、信息类型和消息内容的正则表达式模式 pattern = r'\[talkid:(\d+)\](.*?) 向 (.*?) 发送 (.*?):\[(.*?)\]' matches = re.findall(pattern, soup) # 遍历匹配结果并输出 for match in matches: talkid = match[0] time = match[1].strip() sender = match[2].strip() receiver = match[3].strip() type = match[4].strip() content = re.findall(r'', match[5])[0] if type in ['音频', '图片'] else match[5] # 写入CSV文件 csv_writer.writerow([talkid, time, sender, receiver, content]) # 关闭CSV文件 csv_file.close() print("数据已成功写入CSV文件。")







