北屿

北屿小智障

0%

f**k unipus

Posted on Edited on In

Version 1.1

README

忽然想起百度有语音识别的api，果断就用了
这次有依赖ffmpeg
APIKey和SecretKey自己去百度大脑申请一个语音识别的应用就可以了http://ai.baidu.com/
效果的话…还ok.百度的识别是不带标点的，也就是要自己断句咯

1
2
3
4
don't worry madam I'll get you there in time it looks as if most people 
have already gone home today I hope so the plane leaves at seven I don't 
want to arrive in London too late or the hotel will think I'm not coming 
and I might lose my room question where is the man taking the woman to

目前存在的不足：

  • 过长的文件无法翻译(这个我将会在下面的版本修复^^，待我了解一下音频格式再说)

——20200430

CODE

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
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
from bs4 import BeautifulSoup
import re, requests
import os
import wave
import requests
import time
import base64

base_url = "https://openapi.baidu.com/oauth/2.0/token?grant_type=client_credentials&client_id=%s&client_secret=%s"
APIKey = "***"
SecretKey = "***" 

HOST = base_url % (APIKey, SecretKey)


def getToken(host):
    res = requests.post(host)
    return res.json()['access_token']

def get_audio(file):
    with open(file, 'rb') as f:
        data = f.read()
    return data


def speech2text(FILEPATH, dev_pid=1737):
    token = getToken(HOST)
    speech_data = get_audio(FILEPATH)

    FORMAT = 'wav'
    RATE = '16000'
    CHANNEL = 1
    CUID = '*******'
    SPEECH = base64.b64encode(speech_data).decode('utf-8')

    data = {
        'format': FORMAT,
        'rate': RATE,
        'channel': CHANNEL,
        'cuid': CUID,
        'len': len(speech_data),
        'speech': SPEECH,
        'token': token,
        'dev_pid':dev_pid
    }
    url = 'https://vop.baidu.com/server_api'
    headers = {'Content-Type': 'application/json'}
    # r=requests.post(url,data=json.dumps(data),headers=headers)
    
    r = requests.post(url, json=data, headers=headers)
    Result = r.json()
    if 'result' in Result:
        return Result['result'][0]
    else:
        return Result

def main():
    url = "index.html"
    url_voice2text = "https://app.xunjiepdf.com/voice2text/"
    url_translate = "https://translate.google.cn/"
    soup = BeautifulSoup(open(url, encoding='utf-8'))
    allres = soup.find_all(name='div',attrs={"class":"itest-hear-reslist"})
    # print(soup)
    counter = 1
    for res in allres:
        st = res.span.text;
        st = str(st)[1:-1]
        st = st.split(',')
        for est in st:
            if(re.match(r'.*\.mp3.*', est)):
                if(re.match(r'.*question\.mp3+.*', est)):
                    continue
                print(est[1:-1])
                download_addr = est[1:-1]
                print('Downloading...')
                f=requests.get(download_addr)
                with open(str(counter)+".mp3","wb") as code:
                    code.write(f.content)
                print('Downloaded')
                print('Transcoding mp3 to pcm...')
                os.system("ffmpeg -y -i " + str(counter) + ".mp3 -acodec pcm_s16le -f s16le -ac 1 -ar 16000 "  + str(counter) + ".pcm" )
                print('Transcoded mp3 to pcm')
                print('Recognizing...')
                result = speech2text(FILEPATH=str(counter)+".pcm")
                print('-'*48)
                print(result)
                with open(str(counter)+".txt", "w") as ff:
                    print(result, file=ff)
                print('-'*48)
                print('Recognized')
                counter += 1
                print('Finished')

        # print(i.span.text)
    # print(allres)
if __name__ == '__main__':
    main()

REFERENCE

Version 1.0

README

我们英语老师布置的题也太j8多了，70多道题，20多道听力，我都听吐了
U校园单元测试还不能查题
而且U校园只能听一次听力，然后偶然按了一下F12发现了听力链接就在html里，我人晕了
打开链接就能下，但是太j8多了，看得我眼花，就写了这个脚本
本来想一键式直接出中文的，但是实力有限，有空再做吧…语音识别和翻译的网页就是里面的几个url
因为不会模拟登陆，所以还是请把测试网页Ctrl+S保存成index.html，运行这个脚本就会出现很多听力原文
以后如果有时间必会更新
——20200403

CODE

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
from bs4 import BeautifulSoup
import re, requests

def main():
    url = "index.html"
    url_voice2text = "https://app.xunjiepdf.com/voice2text/"
    url_translate = "https://translate.google.cn/"
    soup = BeautifulSoup(open(url, encoding='utf-8'))
    allres = soup.find_all(name='div',attrs={"class":"itest-hear-reslist"})
    # print(soup)
    counter = 1
    for res in allres:
        st = res.span.text;
        st = str(st)[1:-1]
        st = st.split(',')
        for est in st:
            if(re.match(r'.*\.mp3.*', est)):
                if(re.match(r'.*question\.mp3+.*', est)):
                    continue
                print(est[1:-1])
                download_addr = est[1:-1]
                print('downloading...')
                f=requests.get(download_addr)
                with open(str(counter)+".mp3","wb") as code:
                    code.write(f.content)
                counter += 1
                print('downloaded')

        # print(i.span.text)
    # print(allres)
    

if __name__ == '__main__':
    main()
Related Posts
Have fun.