# -*- coding: utf-8 -*-
# ☯ Author: ******
# ☯ Email : ******@****.***
# ☯ Date : 2021/06/24 20:13
import os
import re
import time
import random
import logging
import datetime
import requests
from logging import handlers
from collections import OrderedDict
from urllib3 import encode_multipart_formdata
# 日志模块
class LogGer(object):
def __init__(self, name):
os.makedirs("./log") if not os.path.exists("./log") else None # 创建日志文件文件夹
get_logger_a = logging.getLogger()
get_logger_a.setLevel(logging.INFO) # 设置默认级别
formatter = logging.Formatter('%(levelname)s %(asctime)s %(filename)s[line:%(lineno)d]: %(message)s')
log_file_path = './log/{}_{}.log'.format(name, time.strftime('%Y%m%d'))
rotating_handler = handlers.RotatingFileHandler(
log_file_path, maxBytes=20 * 1024 * 1024, backupCount=10, encoding='utf-8')
rotating_handler.setFormatter(formatter)
get_logger_a.addHandler(rotating_handler)
stream_handler = logging.StreamHandler()
stream_handler.setFormatter(formatter)
get_logger_a.addHandler(stream_handler)
# 过滤级别：控制台输出INFO和WARNING级别，文件只记录WARNING级别
info_filter = logging.Filter()
info_filter.filter = lambda record: record.levelno < logging.WARNING # 设置过滤等级
warn_filter = logging.Filter()
warn_filter.filter = lambda record: record.levelno >= logging.WARNING
# stream_handler.addFilter(info_filter)
rotating_handler.addFilter(warn_filter)
# 爬虫主程序
class TestSpider:
LogGer(str(os.path.basename(__file__))[:-3])
logging.info('system is working now.')
def __init__(self):
pass
# 随机头
@staticmethod
def random_ua():
return "Mozilla/5.0 (Windows NT {}) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/{} Safari/537.36".format(
random.choice([
'10.0; Win64; x64', '10.0; WOW64', '10.0',
'6.2; WOW64', '6.2; Win64; x64', '6.2',
'6.1', '6.1; Win64; x64', '6.1; WOW64'
]), random.choice([
'70.0.3538.16', '70.0.3538.67', '70.0.3538.97', '71.0.3578.137', '71.0.3578.30', '71.0.3578.33',
'71.0.3578.80', '72.0.3626.69', '72.0.3626.7', '73.0.3683.20', '73.0.3683.68', '74.0.3729.6',
'75.0.3770.140', '75.0.3770.8', '75.0.3770.90', '76.0.3809.12', '76.0.3809.126', '76.0.3809.25',
'76.0.3809.68', '77.0.3865.10', '77.0.3865.40', '78.0.3904.105', '78.0.3904.11', '78.0.3904.70',
'79.0.3945.16', '79.0.3945.36', '80.0.3987.106', '80.0.3987.16', '81.0.4044.138', '81.0.4044.20',
'81.0.4044.69', '83.0.4103.14', '83.0.4103.39', '84.0.4147.30', '85.0.4183.38', '85.0.4183.83',
'85.0.4183.87', '86.0.4240.22', '87.0.4280.20', '87.0.4280.88', '88.0.4324.27'
]))
# 下载器
def requester(self, url, retry=3, **kwargs):
"""
:param url: 必须传入的url
:param retry: 不需要自己传，自动忽视
:param kwargs: 传递需要的参数，必须“参数名=参数”
:return: 返回正常访问的内容或者返回None
"""
try:
return requests.request(
url=url,
method=kwargs.get('method') if kwargs.get('method') else 'get',
timeout=kwargs.get('timeout') if kwargs.get('timeout') else 30,
params=kwargs.get('params'),
data=kwargs.get('data'),
files=kwargs.get('files'),
json=kwargs.get('json'),
cookies=kwargs.get('cookies'),
allow_redirects=True if kwargs.get('allow_redirects') in [None, True] else False,
proxies={
'http': 'http://{}'.format(kwargs.get('proxies')),
'https': 'http://{}'.format(kwargs.get('proxies'))
} if kwargs.get('proxies') else None,
headers=kwargs.get('headers') if kwargs.get('headers') else {
'Accept': '*/*',
'Connection': 'close',
'Accept-Encoding': 'gzip, deflate, br',
'User-Agent': self.random_ua()
},
verify=False
)
except Exception as e:
return logging.warning('request error:%s' % e) if retry < 1 else self.requester(url, retry - 1, **kwargs)
def upload(self, file_path: str, **kwargs: any) -> None or dict:
c = str(kwargs.get("code")) if kwargs.get("code") and len(str(kwargs.get("code"))) == 16 else "s4Qyl0knnW8pjpDK"
response = self.requester(
method="post",
url="https://www.iflyrec.com/AudioStreamService/v1/audios",
params={"type": "whole", "folder": f"{random.randint(10000000000000000, 99999999999999999)}"},
headers={
'Host': 'www.iflyrec.com',
'Connection': 'close',
'User-Agent': self.random_ua(),
'X-Biz-Id': 'xftj',
'Content-Type': f'multipart/form-data; boundary=----WebKitFormBoundary{c}',
'Accept': '*/*',
'Origin': 'https://www.iflyrec.com',
'Referer': 'https://www.iflyrec.com/html/addMachineOrder.html',
'Accept-Encoding': 'gzip, deflate',
'Accept-Language': 'zh-CN,zh;q=0.9'
},
data=encode_multipart_formdata(OrderedDict([
("language", (None, 1, 'multipart/form-data')),
("id", (None, 'WU_FILE_0', 'multipart/form-data')),
('name', (None, os.path.basename(file_path), 'multipart/form-data')),
('type', (None, 'audio/wav', 'multipart/form-data')),
('lastModifiedDate', (
None, datetime.datetime.utcnow().strftime('%a %b %d %Y %H:%M:%S GMT+0800') + " (中国标准时间)",
'multipart/form-data'
)),
('size', (None, os.path.getsize(file_path), 'multipart/form-data')),
('file', (os.path.basename(file_path), open(file_path, "rb").read(), 'audio/wav')),
]), boundary=f'----WebKitFormBoundary{c}')[0],
proxies=kwargs.get('proxies')
)
# request error
if response is None:
return logging.warning(f"上传失败了，请测试网络连接情况,file:{file_path}")
# response error
if "uploadedSize" not in response.text:
return logging.warning(f"上传响应结果中不不包含关键字,file:{file_path}")
elif response.json().get('biz').get('uploadedSize') is None:
return logging.warning(f"上传响应中关键值缺失,file:{file_path}")
return response.json()
def crc32check(self, fileid: str, crc32: str) -> None or bool:
response = self.requester(
url=f"https://www.iflyrec.com/TranscriptOrderService/v1/tempAudios/{fileid}/initAudioInfo?crc32={crc32}",
method="post",
headers={
'Host': 'www.iflyrec.com',
'Connection': 'close',
'Accept': 'application/json, text/javascript, */*; q=0.01',
'X-Requested-With': 'XMLHttpRequest',
'User-Agent': self.random_ua(),
'X-Biz-Id': 'xftj',
'Origin': 'https://www.iflyrec.com',
'Referer': 'https://www.iflyrec.com/html/addMachineOrder.html',
'Accept-Encoding': 'gzip, deflate',
'Accept-Language': 'zh-CN,zh;q=0.9',
})
if response is None:
return logging.warning("校验失败：网络不通...")
return True if "000000" in response.text else False
def distinguish(self, path, mode=False):
response = self.requester(
method="get" if mode else "post",
url="https://www.iflyrec.com/TranscriptPreviewService/v1/aiTranscriptPreviews",
headers={
'Host': 'www.iflyrec.com',
'Connection': 'close',
'Accept': 'application/json',
'X-Requested-With': 'XMLHttpRequest',
'User-Agent': "Mozilla/5.0 (Windows NT 6.2; Win64; x64) AppleWebKit/537.36",
'X-Biz-Id': 'xftj',
'Content-Type': 'application/json;charset=UTF-8',
'Origin': 'https://www.iflyrec.com',
'Referer': 'https://www.iflyrec.com/html/addMachineOrder.html',
'Accept-Encoding': 'gzip, deflate',
'Accept-Language': 'zh-CN,zh;q=0.9'
},
params={"filePath": path, "transcriptLanguage": 1},
json={"filePath": path, "transcriptLanguage": 1} if mode is False else None,
)
if response is None:
return logging.warning("识别失败:网络故障")
if mode is False and "true" in response.text:
return self.distinguish(path, True)
if mode is True and "speaker" in response.text:
info = response.json()['biz']['transcriptResult']
return "".join([i.strip() for i in re.findall(r'''"content":"([\S\s]*?)"''', info)])
else:
return logging.warning("识别失败:未知错误")
@staticmethod
def write2txt(path, content):
with open(path, "a+", encoding="utf-8") as f:
f.write(content + "\n")
# 运行入口
def run(self):
# 提交数据
res = self.upload(r"C:\Users\Administrator\Desktop\英语\4.wav")
if res is None:
return
# crc32 验证
msg = self.crc32check(**{"fileid": res['biz']['fileId'], "crc32": res['biz']['crc32']})
if msg is not True:
return
# 开始识别
text = self.distinguish(res['biz']['transPreviewPath'])
print(f"获取响应结果：{text}")
if __name__ == '__main__':
start = TestSpider()
start.run()
自己写的玩的，见笑了......开发30分钟，调试3小时................无奈 无奈------------- 评分啥 你随意......留言回复是对我最大的鼓励......
这个只能 转录 中文 和 英文，免费的嘛多多少少有限制的哇， 还有最大限制，不能超过3分钟哦，是不是很鸡肋，我那个音频实际是日文的，没英文的，日文在这里肯定转录不对撒，只是做个测试，大家自由玩耍.....
上图：
[复制链接]
发表于 2021-6-24 21:49
|
发表于 2021-6-25 11:30
