如何在 Python 中删除文件的前四行和后 12 行？

Posted 2023-03-15

【中文标题】如何在 Python 中删除文件的前四行和后 12 行？

【英文标题】：How to remove the first four lines and the last 12 lines in to a file in Python?

【发布时间】：2016-05-11 15:13:42

【问题描述】：

        h = httplib.HTTPSConnection(host, port)
        h.set_debuglevel(0)

        headers = 

        "Content-Type": "multipart/form-data; boundary=%s" % (boundary,),

        "Connection": "Keep-Alive",

        

        h.request('POST', uri, body, headers)
        res = h.getresponse()
        #print res.read()
        data = """MIME-Version: 1.0
        Content-Type: multipart/mixed; boundary=--Nuance_NMSP_vutc5w1XobDdefsYG3wq
        """ + res.read()

        msg = email.message_from_string(data)
        #print msg

        for index, part in enumerate(msg.walk(), start=1):
            content_type = part.get_content_type()
            #print content_type
            payload = part.get_payload()
            print res.getheaders()

            if content_type == "audio/x-wav" and len(payload):
                with open('output.pcm'.format(index), 'wb') as f_pcm:
                    print f_pcm.write(payload)

我正在向服务器发送请求，服务器正在以.txt 的形式将响应发送回客户端，如上所述。 .txt 包含顶部的信息标题和底部的标题，为文本格式，其余为二进制。

如何编写和解析文本并将其写入单独的.txt文件，并将二进制文件写入.pcm文件？

【问题讨论】：

请您编辑问题以包含您用于获取此问题的代码。

我添加了我的代码，但不是完整的代码。

使用python的email包解析MIME。

你能告诉我怎么做吗？我正在尝试但没有得到。

@sam 你能附上你的文件Output.txt 例如。使用 Skydrive 或 Dropbox，这样我们就有了一个可以使用的示例。使用您发布的文件内容对我不起作用。

【参考方案1】：

以下示例应该适合您。

filecontent = []
with open("Output.txt", "rb") as inputfile:
    for linenr, line in enumerate(inputfile):
        filecontent.append(line)
    linecount = linenr + 1

with open("AsciiOut.txt", "wb") as outputfile, open("BinOut.pcm", "wb") as binoutputfile:
    for linenr, line in enumerate(filecontent):
        if linenr < 4:
            outputfile.write(line)
        elif linenr < linecount - 12:
            binoutputfile.write(line)
        else:
            outputfile.write(line)

【讨论】：

你解决的是症状而不是实际问题；他真正想要的是提取多部分 mime 消息的各个部分。 “行计数”方法必然会在任何最小扰动下中断（包括将附件更改为本身恰好有换行符的文件）。

【参考方案2】：

建议使用 Python 的 email 库尝试解码 MIME 的方法如下：

import ssl
import os
import json
import email
import uuid
from io import BytesIO
import httplib


input_folder = os.path.dirname(os.path.abspath(__file__)) 
output_folder = os.path.join(input_folder, 'output')

def get_filename(ext, base, sub_folder):
    filename = '.'.format(base, ext)
    return os.path.join(output_folder, sub_folder, filename)

def compare_files(file1, file2):
    with open(file1, 'rb') as f_file1, open(file2, 'rb') as f_file2:
        if f_file1.read() == f_file2.read():
            print 'Same:\n  \n  '.format(file1, file2)
        else:
            print 'Different:\n  \n  '.format(file1, file2)

class Part(object):
    """Represent a part in a multipart messsage"""

    def __init__(self, name, contentType, data, paramName=None):
        super(Part, self).__init__()
        self.name = name
        self.paramName = paramName
        self.contentType = contentType
        self.data = data

    def encode(self):
        body = BytesIO()

        if self.paramName:
            body.write('Content-Disposition: form-data; name="%s"; paramName="%s"\r\n' % (self.name, self.paramName))
        else:
            body.write('Content-Disposition: form-data; name="%s"\r\n' % (self.name,))

        body.write("Content-Type: %s\r\n" % (self.contentType,))
        body.write("\r\n")
        body.write(self.data)
        return body.getvalue()

class Request(object):
    """A handy class for creating a request"""

    def __init__(self):    
        super(Request, self).__init__()
        self.parameters = []

    def add_json_parameter(self, name, paramName, data):
        self.parameters.append(Part(name=name, paramName=paramName, contentType="application/json; charset=utf-8", data=data))

    def add_audio_parameter(self, name, paramName, data):
        self.parameters.append(Part(name=name, paramName=paramName, contentType="audio/x-wav;codec=pcm;bit=16;rate=16000", data=data))

    def encode(self):
        boundary = uuid.uuid4().hex
        body = BytesIO()

        for parameter in self.parameters:
            body.write("--%s\r\n" % (boundary,))
            body.write(parameter.encode())
            body.write("\r\n")

        body.write("--%s--\r\n" % (boundary,))
        return body.getvalue(), boundary


def get_tts(required_text, LNG):
    required_text = required_text.strip()
    output_filename = "".join([x if x.isalnum() else "_" for x in required_text[:80]]) 

    host = "mtldev08.nuance.com"
    port = 443
    uri = "/NmspServlet/"

    if LNG == "ENG":
        parameters = 'lang' : 'eng_GBR', 'location' : '47.4925, 19.0513'

    if LNG == "GED":
        parameters = 'lang' : 'deu-DEU', 'location' : '48.396231, 9.972909'

    RequestData = """
        "appKey": "9c9fa7201e90d3d96718bc3f36ce4cfe1781f2e82f4e5792996623b3b474fee2c77699eb5354f2136063e1ff19c378f0f6dd984471a38ca5c393801bffb062d6",
        "appId": "NMDPTRIAL_AutomotiveTesting_NCS61HTTP",
        "uId": "Alexander",
        "inCodec": "PCM_16_8K",
        "outCodec": "PCM_16_8K",
        "cmdName": "NVC_TTS_CMD",
        "appName": "Python",
        "appVersion": "1",
        "language": "%(lang)s",
        "carrier": "carrier",
        "deviceModel": "deviceModel",
        "cmdDict": 
            "tts_voice": "Serena",
            "tts_language": "%(lang)s",
            "locale": "canada",
            "application_name": "Testing Python Script",
            "organization_id": "NUANCE",
            "phone_OS": "4.0",
            "phone_network": "wifi",
            "audio_source": "SpeakerAndMicrophone",
            "location": "%(location)s",
            "application_session_id": "1234567890",
            "utterance_number": "5",
            "ui_langugage": "en",
            "phone_submodel": "nmPhone2,1",
            "application_state_id": "45"        
        
    """ % (parameters)

    TEXT_TO_READ = """
        "tts_type": "text"
    """

    TEXT_TO_READ = json.loads(TEXT_TO_READ)
    TEXT_TO_READ["tts_input"] = required_text
    TEXT_TO_READ = json.dumps(TEXT_TO_READ)

    request = Request()
    request.add_json_parameter("RequestData", None, RequestData)
    request.add_json_parameter("TtsParameter", "TEXT_TO_READ", TEXT_TO_READ)

    #ssl._create_default_https_context = ssl._create_unverified_context
    body, boundary = request.encode()
    h = httplib.HTTPSConnection(host, port)
    #h.set_debuglevel(1)

    headers = 
        "Content-Type": "multipart/form-data; boundary=%s" % (boundary,),
        "Connection": "Keep-Alive",
    

    h.request('POST', uri, body, headers)
    res = h.getresponse()

    data = """MIME-Version: 1.0
Content-Type: multipart/mixed; boundary=--Nuance_NMSP_vutc5w1XobDdefsYG3wq
""" + res.read()

    msg = email.message_from_string(data)

    for part in msg.walk():
        content_type = part.get_content_type()
        payload = part.get_payload()

        if content_type == "audio/x-wav" and len(payload):
            ref_filename = get_filename('pcm', output_filename + '_ref', LNG)
            if not os.path.exists(ref_filename):
                with open(ref_filename, 'wb') as f_pcm:
                    f_pcm.write(payload)

            cur_filename = get_filename('pcm', output_filename, LNG)
            with open(cur_filename, 'wb') as f_pcm:
                f_pcm.write(payload)

            compare_files(ref_filename, cur_filename)

        elif content_type == "application/json":
            with open(get_filename('json', output_filename, LNG), 'w') as f_json:
                f_json.write(payload)


filename = r'input.txt'

with open(filename) as f_input:
    for line in f_input:
        LNG, text = line.strip().split('|')
        print "Getting : ".format(LNG, text)
        get_tts(text, LNG)

这假设您的 input.txt 文件具有以下格式：

ENG|I am tired
GED|Ich gehe nach hause

这将为每行文本生成一个输出 pcm 和 json 文件。它适用于多种文件/语言。

【讨论】：

它正在生成plain1.txt。它正在读取完整的 .txt 文件 res.read 是什么，但它可以解析它。你能帮帮我吗？

为了进一步帮助（并且能够运行脚本），我需要知道调用h.request 所需的参数。您复制粘贴在问题中的数据不合适。

你能看一次吗？

我添加了一种将原始 pcm 提取到文件中的简单方法，我能够听到返回的单词。

谢谢，但是如何读取 res 中的剩余文本并将其写入另一个文件？