本是同根生，相煎何太急用Google语音识别API破解reCaptcha验证码

./google_speech.py hello.flac 

''' Accessing Google Web Speech API using Pyhon Author : Debasish Mandal  '''  import httplib import sys  print '[+] Sending clean file to Google voice API' f = open(sys.argv[1]) data = f.read() f.close() google_speech = httplib.HTTPConnection('www.google.com') google_speech.request('POST','/speech-api/v1/recognize?xjerr=1&client=chromium&lang=en-US',data,{'Content-type': 'audio/x-flac; rate=16000'}) print google_speech.getresponse().read() google_speech.close() 

debasish@debasish ~/Desktop/audio/heart attack/final $ sox cut_0.wav -r 16000 -b 16 -c 1 cut_0.flac lowpass -2 2500 debasish@debasish ~/Desktop/audio/heart attack/final $ python send.py cut_0.flac  

import wave  f = wave.open('sample.wav', 'r')  print '[+] WAV parameters ',f.getparams()  print '[+] No. of Frames ',f.getnframes()  for i in range(f.getnframes()):      single_frame = f.readframes(1)      print single_frame.encode('hex')  f.close() 

[+] WAV parameters (1, 2, 44100, 937, 'NONE', 'not compressed')   [+] No. of Frames 937   [+] Sample 0 = 62fe    <- Sample 1   [+] Sample 1 = 99fe   <- Sample 2   [+] Sample 2 = c1ff    <- Sample 3   [+] Sample 3 = 9000   [+] Sample 4 = 8700   [+] Sample 5 = b9ff   [+] Sample 6 = 5cfe   [+] Sample 7 = 35fd   [+] Sample 8 = b1fc   [+] Sample 9 = f5fc   [+] Sample 10 = 9afd   [+] Sample 11 = 3cfe   [+] Sample 12 = 83fe   [+] ....   

import wave  import struct   f = wave.open('sample.wav', 'r')  print '[+] WAV parameters ',f.getparams()  print '[+] No. of Frames ',f.getnframes()  for i in range(f.getnframes()):      single_frame = f.readframes(1)      sint = struct.unpack('<h', single_frame) [0]     print "[+] Sample ",i," = ",single_frame.encode('hex')," -> ",sint[0]  f.close() 

[+] WAV parameters (1, 2, 44100, 937, 'NONE', 'not compressed') [+] No. of Frames 937 [+] Sample 0 = 62fe -> -414 [+] Sample 1 = 99fe -> -359 [+] Sample 2 = c1ff -> -63 [+] Sample 3 = 9000 -> 144 [+] Sample 4 = 8700 -> 135 [+] Sample 5 = b9ff -> -71 [+] Sample 6 = 5cfe -> -420 [+] Sample 7 = 35fd -> -715 [+] Sample 8 = b1fc -> -847 [+] Sample 9 = f5fc -> -779 [+] Sample 10 = 9afd -> -614 [+] Sample 11 = 3cfe -> -452 [+] Sample 12 = 83fe -> -381 [+] Sample 13 = 52fe -> -430 [+] Sample 14 = e2fd -> -542 

import wave  import struct  import matplotlib.pyplot as plt   data_set = []  f = wave.open('sample.wav', 'r')  print '[+] WAV parameters ',f.getparams()  print '[+] No. of Frames ',f.getnframes()  for i in range(f.getnframes()):      single_frame = f.readframes(1)     sint = struct.unpack('<h', single_frame)[0]     data_set.append(sint)  f.close()  plt.plot(data_set)  plt.ylabel('Amplitude') plt.xlabel('Time')  plt.show() 

''' 简单的基于音量的音频文件分割程序     作用:     1. 简单的降噪处理   2. 识别文件中的高音量部分   3. 根据高音量部分的数目把文件分割成独立文件       '''    import wave import sys import struct import os import time import httplib from random import randint   ip = wave.open(sys.argv[1], 'r') info = ip.getparams() frame_list = [] for i in range(ip.getnframes()):     sframe = ip.readframes(1)     amplitude = struct.unpack('<h', sframe)[0]     frame_list.append(amplitude) ip.close() for i in range(0,len(frame_list)):     if abs(frame_list[i]) < 25:         frame_list[i] = 0 ################################  Find Out most louder portions of the audio file ########################### thresh = 30 output = [] nonzerotemp = [] length = len(frame_list) i = 0 while i < length:     zeros = []     while i < length and frame_list[i] == 0:         i += 1         zeros.append(0)     if len(zeros) != 0 and len(zeros) < thresh:         nonzerotemp += zeros     elif len(zeros) > thresh:         if len(nonzerotemp) > 0 and i < length:             output.append(nonzerotemp)             nonzerotemp = []     else:         nonzerotemp.append(frame_list[i])         i += 1 if len(nonzerotemp) > 0:     output.append(nonzerotemp)  chunks = [] for j in range(0,len(output)):     if len(output[j]) > 3000:         chunks.append(output[j]) #########################################################################################################  for l in chunks:     for m in range(0,len(l)):         if l[m] == 0:              l[m] = randint(-0,+0)  inc_percent = 1 #10 percent  for l in chunks:     for m in range(0,len(l)):         if l[m] <= 0:             # negative value             l[m] = 0 - abs(l[m]) + abs(l[m])*inc_percent/100         else:             #positive vaule             l[m] =     abs(l[m]) + abs(l[m])*inc_percent/100  ########################################################  # Below code generates separate wav files depending on the number of loud voice detected.  NEW_RATE = 1 #Change it to > 1 if any amplification is required  print '[+] Possibly ',len(chunks),'number of loud voice detected...' for i in range(0, len(chunks)):     new_frame_rate = info[0]*NEW_RATE     print '[+] Creating No. ',str(i),'file..'     split = wave.open('cut_'+str(i)+'.wav', 'w')     split.setparams((info[0],info[1],info[2],0,info[4],info[5])) #   split.setparams((info[0],info[1],new_frame_rate,0,info[4],info[5]))      #Add some silence at start selecting +15 to -15     for k in range(0,10000):         single_frame = struct.pack('<h', randint(-25,+25))         split.writeframes(single_frame)     # Add the voice for the first time     for frames in chunks[i]:         single_frame = struct.pack('<h', frames)         split.writeframes(single_frame)      #Add some silence in between two digits     for k in range(0,10000):         single_frame = struct.pack('<h', randint(-25,+25))         split.writeframes(single_frame)      # Repeat effect :  Add the voice second time     for frames in chunks[i]:         single_frame = struct.pack('<h', frames)         split.writeframes(single_frame)      #Add silence at end     for k in range(0,10000):         single_frame = struct.pack('<h', randint(-25,+25))         split.writeframes(single_frame)      split.close()#Close each files