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 08:26:35 浏览: 129
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