解析浏览器导出的har文件

harAnalyze.py

#!/usr/bin/python
# -*- coding: UTF-8 -*-

import json


def readHarFile():
    hostList = []
    outputPath = ''
    filePath = raw_input('输入文件路径+名字：')
    outputType = raw_input('1.直接输出为txt文件；2.直接输出在控制台；(请输入 1 or 2 )')

    if str(outputType) is '1':
        outputPath = raw_input('输出文件路径+名字：')

    with open(filePath, 'r') as readObj:
        harDirct = json.loads(readObj.read())
        requestList = harDirct['log']['entries']

        for item in requestList:
            urlString = (item['request']['url'])

            start = urlString.index('://')
            tempStr = urlString[start + 3:]
            end = tempStr.index('/')
            resultStr = tempStr[:end]

            # 判断是否是www开头的域名
            if 'www' in resultStr:
                resultStr = resultStr[4:]
            if resultStr not in hostList:
                hostList.append(resultStr)

    if str(outputType) is '1':
        with open(outputPath, 'w') as ff:
            for item in hostList:
                ff.write('"' + item + '",' + '\n')
    else:
        print '//=============host start=============='
        for item in hostList:
            print '"' + item + '",'

        print '//=============host end================'


if __name__ == '__main__':
    readHarFile()