word = chunk[start:i_space].decode("utf-8", errors=unicode_errors) UnicodeDecodeError: 'utf-8' codec can't decode byte 0x80 in position 1: invalid start byte
时间: 2023-07-24 13:15:11 浏览: 67
这个错误是由于在使用 utf-8 编码方式解码字节流时出现问题,具体来说,是因为字节流中包含了无效的 utf-8 字符。utf-8 编码是一种变长编码方式,每个字符的编码长度不同,因此如果字节流中包含了不符合 utf-8 编码规则的字节,解码时就会出现错误。
解决这个问题的方法有以下几种:
1. 检查源数据是否包含非 utf-8 编码的字符。可以使用其他编码方式(如 GB18030)重新编码源数据,再进行训练。
2. 使用 `errors='ignore'` 参数忽略无法解码的字节,但这种方法会造成信息的丢失。
3. 使用 `errors='replace'` 参数将无法解码的字节替换为 `U+FFFD`,表示 Unicode 替代字符。
```python
word = chunk[start:i_space].decode("utf-8", errors='replace')
```
4. 可以使用 `chardet` 库自动检测文件的编码格式,再使用正确的编码格式解码字节流。例如:
```python
import chardet
# 自动检测文件编码格式
with open(file_path, 'rb') as f:
encoding = chardet.detect(f.read())['encoding']
# 使用正确的编码方式解码字节流
word = chunk[start:i_space].decode(encoding)
```
其中,`chardet.detect` 方法可以自动检测文件的编码格式,并返回一个包含编码格式信息的字典。然后,使用正确的编码方式解码字节流即可。
相关推荐
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
import re,tkinter,requests,threading,tqdm as tt root = tkinter.Tk() root.title('在线视频解析') root.geometry('500x590+550+350') headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:109.0) Gecko/20100101 Firefox/115.0'} ac = tkinter.Listbox(root, width=50, height=20, font=('黑体', 12)) ac.grid(row=2, columnspan=10, sticky="n" + "s" + "w" + "e") def sousuo(): i = b1.get() ac.delete(0, 'end') def extract_music_info(content): p = '|' content = re.sub(p, '', content, flags=re.S) pattern = re.compile('subject.*?href="(.*?)">(.*?)
', flags=re.S) return pattern.findall(content) def search_music(): url = 'https://www.hifini.com/search-' + i + '-1.htm' response = requests.get(url=url, headers=headers) return response.text def update_listbox(music_list): for music in music_list: pppp = music[1] + ":" + music[0] ac.insert('end', pppp) content = search_music() music_list = extract_music_info(content) update_listbox(music_list) def xiazzi(): def download_music(): ppp = ac.get(ac.curselection()) pp = re.search('thread.*?htm', ppp) v = pp.group() url1 = 'https://www.hifini.com/' + v response = requests.get(url=url1, headers=headers) ppp = response.text l2 = re.search('<script>.*?title:..(.*?).,.*?author:.(.*?).,.*?url:..(.*?).,', ppp, flags=re.S) p = 'https://www.hifini.com/' + l2.group(3) response = requests.get(url=p, headers=headers, stream=True) # 设置 stream=True 以启用流式下载 total_size = int(response.headers.get('Content-Length')) music_name = '{}-{}.mp3'.format(l2.group(2), l2.group(1)) progress_bar = tt.tqdm(total=total_size, unit='B', unit_scale=True) # 创建进度条 with open(music_name, 'wb') as f: for data in response.iter_content(chunk_size=1024): progress_bar.update(len(data)) # 更新进度条 f.write(data) progress_bar.close() # 关闭进度条 print(music_name) threading.Thread(target=download_music).start() a1 = tkinter.Label(root, text='音乐下载器', anchor="center", font=('黑体', 24)) a1.grid(row=0, columnspan=10, sticky="n" + "s" + "w" + "e") b1 = tkinter.Entry(root, width=35, font=('黑体', 16), ) b1.grid(row=1, column=3, padx=15) search_button = tkinter.Button(root, text='搜索', command=sousuo) search_button.grid(row=1, column=4) download_button = tkinter.Button(root, text='下载', command=xiazzi) download_button.grid(row=3, column=4) root.mainloop() 添加 判断下载的文件是不是m4a如果就转为MP3,root上添加下载进度条![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
帮我增加进度条import io import re import tkinter import requests import threading from pydub import AudioSegment root = tkinter.Tk() root.title('在线视频解析') root.geometry('500x590+550+350') headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:109.0) Gecko/20100101 Firefox/115.0'} ac = tkinter.Listbox(root, width=50, height=20, font=('黑体', 12)) ac.grid(row=2, columnspan=10, sticky="n" + "s" + "w" + "e") def sousuo(): i = b1.get() ac.delete(0, 'end') def extract_music_info(content): p = '|' content = re.sub(p, '', content, flags=re.S) pattern = re.compile('subject.*?href="(.*?)">(.*?)
', flags=re.S) return pattern.findall(content) def search_music(): url = 'https://www.hifini.com/search-' + i + '-1.htm' response = requests.get(url=url, headers=headers) return response.text def update_listbox(music_list): for music in music_list: pppp = music[1] + ":" + music[0] ac.insert('end', pppp) content = search_music() music_list = extract_music_info(content) update_listbox(music_list) def xiazzi(): def download_music(): ppp = ac.get(ac.curselection()) pp = re.search('thread.*?htm', ppp) v = pp.group() url1 = 'https://www.hifini.com/' + v response = requests.get(url=url1, headers=headers) ppp = response.text l2 = re.search('<script>.*?title:..(.*?).,.*?author:.(.*?).,.*?url:..(.*?).,', ppp, flags=re.S) p = 'https://www.hifini.com/' + l2.group(3) response = requests.get(url=p, headers=headers) l3 = response.content music_name = '{}-{}.mp3'.format(l2.group(2), l2.group(1)) if l3.startswith(b'\x00\x00\x00\x20\x66\x74\x79\x70'): audio = AudioSegment.from_file(io.BytesIO(l3), format='m4a') audio.export(music_name, format='mp3') else: with open(music_name, 'wb') as f: f.write(l3) print(music_name) threading.Thread(target=download_music).start() a1 = tkinter.Label(root, text='音乐下载器', anchor="center", font=('黑体', 24)) a1.grid(row=0, columnspan=10, sticky="n" + "s" + "w" + "e") b1 = tkinter.Entry(root, width=35, font=('黑体', 16), ) b1.grid(row=1, column=3, padx=15) search_button = tkinter.Button(root, text='搜索', command=sousuo) search_button.grid(row=1, column=4) download_button = tkinter.Button(root, text='下载', command=xiazzi) download_button.grid(row=3, column=4) root.mainloop()![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)