一. 问题：
在写调用谷歌翻译接口的脚本时，老是报错，我使用的的是googletrans这个模块中Translator的translate方法，程序运行以后会报访问超时错误:
Traceback (most recent call last): File "E:/PycharmProjects/MyProject/Translate/translate_test.py", line 3, in <module> result=translator.translate('안녕하세요.') File "D:\python3\lib\site-packages\googletrans\client.py", line 182, in translate data = self._translate(text, dest, src, kwargs) File "D:\python3\lib\site-packages\googletrans\client.py", line 78, in _translate token = self.token_acquirer.do(text) File "D:\python3\lib\site-packages\googletrans\gtoken.py", line 194, in do self._update() File "D:\python3\lib\site-packages\googletrans\gtoken.py", line 54, in _update r = self.client.get(self.host) File "D:\python3\lib\site-packages\httpx\_client.py", line 763, in get timeout=timeout, File "D:\python3\lib\site-packages\httpx\_client.py", line 601, in request request, auth=auth, allow_redirects=allow_redirects, timeout=timeout, File "D:\python3\lib\site-packages\httpx\_client.py", line 621, in send request, auth=auth, timeout=timeout, allow_redirects=allow_redirects, File "D:\python3\lib\site-packages\httpx\_client.py", line 648, in send_handling_redirects request, auth=auth, timeout=timeout, history=history File "D:\python3\lib\site-packages\httpx\_client.py", line 684, in send_handling_auth response = self.send_single_request(request, timeout) File "D:\python3\lib\site-packages\httpx\_client.py", line 719, in send_single_request timeout=timeout.as_dict(), File "D:\python3\lib\site-packages\httpcore\_sync\connection_pool.py", line 153, in request method, url, headers=headers, stream=stream, timeout=timeout File "D:\python3\lib\site-packages\httpcore\_sync\connection.py", line 65, in request self.socket = self._open_socket(timeout) File "D:\python3\lib\site-packages\httpcore\_sync\connection.py", line 86, in _open_socket hostname, port, ssl_context, timeout File "D:\python3\lib\site-packages\httpcore\_backends\sync.py", line 139, in open_tcp_stream return SyncSocketStream(sock=sock) File "D:\python3\lib\contextlib.py", line 130, in __exit__ self.gen.throw(type, value, traceback) File "D:\python3\lib\site-packages\httpcore\_exceptions.py", line 12, in map_exceptions raise to_exc(exc) from None httpcore._exceptions.ConnectTimeout: timed out
二. 解决方法：
1.寻找解决方法
经过多方资料查找，最后才知道google翻译对接口进行了更新，之前用的googletrans已经不能用了。但是网上大神已经开发出了新的方法
https://github.com/lushan88a/google_trans_new
在此道一声感谢！
2.使用解决方法
在cmd中输入以下指令即可。
pip install google_trans_new
三. 代码（优化）
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
|
from google_trans_new import google_translator
from multiprocessing.dummy import Pool as ThreadPool
import time
import re
"""
此版本调用最新版google_trans_new
使用多线程访问谷歌翻译接口
能够翻译len(text)>5000的文本
"""
class Translate(object):
def __init__(self):
#初始化翻译文本路径以及翻译目标语言
self.txt_file='./test.txt'
self.aim_language='zh-CN'
#读入要翻译的文本文件
def read_txt(self):
with open(self.txt_file, 'r',encoding='utf-8')as f:
txt = f.readlines()
return txt
#进行文本处理，此为优化
def cut_text(self,text):
#如果只是一行，就切割成5000字一次来翻译
if len(text)==1:
str_text = ''.join(text).strip()
#筛选是一行但是文本长度大于5000
if len(str_text)>5000:
#使用正则表达式切割超长文本为5000一段的短文本
result = re.findall('.{5000}', str_text)
return result
else:
#如果文本为一行但是这一行文本长度小于5000，则直接返回text
return text
"""
如果不止一行，加以判断
(1)每行字符数都小于5000
（2）有的行字符数小于5000，有的行字符数大于5000
"""
else:
result = []
for line in text:
#第（1）种情况
if len(line)<5000:
result.append(line)
else:
# 第（2）种情况，切割以后，追加到列表中
cut_str=re.findall('.{5000}', line)
result.extend(cut_str)
return result
def translate(self,text):
if text:
aim_lang = self.aim_language
try:
t = google_translator(timeout=10)
translate_text = t.translate(text, aim_lang)
print(translate_text)
return translate_text
except Exception as e:
print(e)
def main():
time1=time.time()
#开启八条线程
pool = ThreadPool(8)
trans = Translate()
txt = trans.read_txt()
texts = trans.cut_text(txt)
try:
pool.map(trans.translate, texts)
except Exception as e:
raise e
pool.close()
pool.join()
time2 = time.time()
print("一共翻译了 {} 个句子，消耗了 {:.2f} s".format(len(texts),time2 - time1))
if __name__ == "__main__" :
main()
|
可自行下载。
四. 运行结果
五. 总结
本篇首先解决了调用googletrans模块的报错问题，然后使用新的google翻译模块编写了代码，并且解决了我这篇文章中翻译文本长度不能大于5000的问题。
原文链接：https://blog.csdn.net/a1397852386/article/details/111479024