|
| 1 | +from PIL import ImageGrab |
| 2 | +import requests |
| 3 | +import base64 |
| 4 | +from urllib.parse import quote_plus |
| 5 | + |
| 6 | + |
| 7 | +def tuling(text): |
| 8 | + """ |
| 9 | + 图灵机器人 |
| 10 | + :return: |
| 11 | + """ |
| 12 | + |
| 13 | + host = 'http://openapi.tuling123.com/openapi/api/v2' |
| 14 | + data = { |
| 15 | + "reqType":0, # 输入类型:0-文本(默认)、1-图片、2-音频 |
| 16 | + "perception": { # 输入信息 |
| 17 | + "inputText": { # 文本信息 |
| 18 | + "text": text |
| 19 | + } |
| 20 | + }, |
| 21 | + "userInfo": { # 用户信息 |
| 22 | + "apiKey": "8d78a28535c947e69c2ddbcc5efeed51", |
| 23 | + "userId": "1234567" |
| 24 | + } |
| 25 | + } |
| 26 | + response = requests.post(host, json=data) |
| 27 | + if response: |
| 28 | + return response.json()['results'][0]['values']['text'] |
| 29 | + else: |
| 30 | + return '错误了!' |
| 31 | + |
| 32 | +def fetch_token(): |
| 33 | + """ |
| 34 | + 获取语音合成 token |
| 35 | + :return: token |
| 36 | + """ |
| 37 | + |
| 38 | + access_token = "" |
| 39 | + |
| 40 | + api_key = 'Pd4uoyvt1cwD7n2sHtLd5Ov0' |
| 41 | + secret_key = '8BnaPRcv3tTNa94eaFVfFy1pW2UkmvrO' |
| 42 | + |
| 43 | + token_url = 'http://openapi.baidu.com/oauth/2.0/token' |
| 44 | + params = {'grant_type': 'client_credentials', |
| 45 | + 'client_id': api_key, |
| 46 | + 'client_secret': secret_key} |
| 47 | + response = requests.post(token_url, params) |
| 48 | + if response: |
| 49 | + access_token = response.json()['access_token'] |
| 50 | + return access_token |
| 51 | + |
| 52 | + |
| 53 | +def synthesized_speech(text, token): |
| 54 | + """ |
| 55 | + 合成语音 |
| 56 | + """ |
| 57 | + |
| 58 | + mp3_path = "/Users/xx/Desktop/siri/result.mp3" |
| 59 | + |
| 60 | + tts_url = 'http://tsn.baidu.com/text2audio' |
| 61 | + |
| 62 | + tex = quote_plus(text) # 此处TEXT需要两次urlencode |
| 63 | + # tok:token,tex:文本,per:发音人,spd:语速(0-15)默认 5,pit:音调(0-15)默认 5, |
| 64 | + # vol:音量(0-9)默认 5,aue:下载的文件格式, 3 mp3(default)、4 pcm-16k、5 pcm-8k、6 wav, |
| 65 | + # cuid:用户唯一标识,lan ctp 固定参数 |
| 66 | + params = {'tok': token, 'tex': tex, 'per': 4, 'spd': 5, 'pit': 5, 'vol': 5, 'aue': 3, 'cuid': "pythonjishu", 'lan': 'zh', 'ctp': 1} |
| 67 | + |
| 68 | + response = requests.post(tts_url, params) |
| 69 | + if response: |
| 70 | + with open(mp3_path, 'wb') as of: |
| 71 | + of.write(response.content) |
| 72 | + |
| 73 | + |
| 74 | +def grab_img(): |
| 75 | + """ |
| 76 | + 截图 |
| 77 | + :return: |
| 78 | + """ |
| 79 | + |
| 80 | + img_path = "/Users/xx/Desktop/siri/grab.png" |
| 81 | + # bbbox 的参数为截取屏幕的一部分,距离左边像素,上边像素,右边像素,下边像素 |
| 82 | + |
| 83 | + img = ImageGrab.grab(bbox=(2630,80,3330,1290)) |
| 84 | + img.save(img_path) |
| 85 | + return img_path |
| 86 | + |
| 87 | +def fench_ocr_token(): |
| 88 | + """ |
| 89 | + 获取ocr token |
| 90 | + :return: token |
| 91 | + """ |
| 92 | + |
| 93 | + api_key = 'ioE84jDQmGNLG7heN6rovF9Q' |
| 94 | + secret_key = 'qGVyAobVtCGKdD1Ncz60IvGMdf3dP1ct' |
| 95 | + |
| 96 | + access_token = "" |
| 97 | + url = 'https://aip.baidubce.com/oauth/2.0/token?grant_type=client_credentials&client_id='+api_key+'&client_secret='+secret_key |
| 98 | + response = requests.get(url) |
| 99 | + if response: |
| 100 | + access_token = response.json()['access_token'] |
| 101 | + return access_token |
| 102 | + |
| 103 | +def ocr(img_path, access_token): |
| 104 | + """ |
| 105 | + 通用文字识别 |
| 106 | + :return: 识别后的文字 |
| 107 | + """ |
| 108 | + |
| 109 | + text = "" |
| 110 | + request_url = "https://aip.baidubce.com/rest/2.0/ocr/v1/general_basic" |
| 111 | + # 二进制方式打开图片文件 |
| 112 | + f = open(img_path, 'rb') |
| 113 | + img = base64.b64encode(f.read()) |
| 114 | + |
| 115 | + params = {"image":img} |
| 116 | + request_url = request_url + "?access_token=" + access_token |
| 117 | + headers = {'content-type': 'application/x-www-form-urlencoded'} |
| 118 | + response = requests.post(request_url, data=params, headers=headers) |
| 119 | + if response: |
| 120 | + words_result = response.json()['words_result'] |
| 121 | + print(words_result) |
| 122 | + text = words_result[-1]['words'] |
| 123 | + return text |
| 124 | + |
| 125 | + |
| 126 | +if __name__ == '__main__': |
| 127 | + token = fetch_token() |
| 128 | + ocr_token = fench_ocr_token() |
| 129 | + siri_speak_text = "嗨,机器人!" |
| 130 | + while 1: |
| 131 | + text = tuling(siri_speak_text) |
| 132 | + synthesized_speech(text, token) |
| 133 | + img_path = grab_img() |
| 134 | + siri_speak_text = ocr(img_path, ocr_token) |
| 135 | + |
| 136 | + |
0 commit comments