pytho 解析fiddler 导出的har文件代码，自动录入api

参考：https://testerhome.com/topics/5276

har导出格式如下：

{

'log':

{

'pages': [],

'comment':

'exported @ 2019/6/28 15:01:27',

'entries':

[

{

'time': ,

'connection':

'ClientPort:50377;

EgressPort:53633',

'comment': '[#43]',

'request':

{

'headersSize': ,

'postData': {

'text': '{

"checksum":"1557025867",

"language":""

}',

'mimeType': 'application/json'

},

'queryString': [],

'headers': [

{

'name': 'Host',

'value': 'bankpreidc.zatech.com'

},

{

'name': 'Content-Type',

'value': 'application/json'

},

{

'name': 'channelId',

'value': '10000'

},

{'name': 'Accept', 'value':'heheh'},

{'name': 'timestamp', 'value': '1561693450'},

{'name': 'appVersion', 'value': 'v1.0.0'},

{'name': 'OS', 'value': 'iOS'},

{'name': 'Accept-Encoding', 'value': 'gzip;q=1.0, compress;q=0.5'},

{'name': 'apiVersion', 'value': 'v1.0.0'},

{'name': 'Accept-Language', 'value': 'zh-Hans-CN;q=1.0'},

{'name': 'language', 'value': 'zh'},

{'name': 'did', 'value': 'NTIzOTIxNDYwMzMyM2NjZjk1OGM5NjBmYzNlNzg2OTYtZTkxNzg1MzYzNjA4NGM0Mjg4Njg3MmFhNzExMDE1YTgwMDAyLXIwWUtuK0MrS1Y2eDBteWs3WnhDYmQ2ZnovTT0='}, {'name': 'User-Agent', 'value': 'AnAnLifeInsurance_iOS/1.0.0 (com.zhonganio.zabank; build:357; iOS 11.4.1) Alamofire/4.8.2'},

{'name': 'Content-Length', 'value': '39'},

{'name': 'Connection','value': 'keep-alive'},

{'name': 'reqSeq', 'value': '9d3157c83dc46cd64cc65694c39163ba'},

{'name': 'OSVersion', 'value': '11.4.1'}

],

'bodySize': ,

'url': 'https://XXXXX/ci/dict/find',

'cookies': [],

'method': 'POST',

'httpVersion': 'HTTP/1.1'

},

'timings':

{

'blocked': -1,

'ssl': ,

'receive': ,

'wait': ,

'dns': ,

'send': , 'connect':

},

'response':

{

'headersSize': ,

'bodySize': ,

'statusText': '200',

'redirectURL': '',

'status': ,

'httpVersion': 'HTTP/1.1',

'cookies': [],

'content':

{

'compression': -259,

'comment': 'Body length exceeded fiddler.importexport.HTTPArchiveJSON.MaxTextBodyLength, so body was omitted.',

'size': ,

'mimeType': 'application/json;charset=UTF-8'

},

'headers':

[

{'name': 'Server', 'value': 'nginx'},

{'name': 'Date', 'value': 'Fri, 28 Jun 2019 03:44:13 GMT'},

{'name': 'Content-Type', 'value': 'application/json;charset=UTF-8'},

{'name': 'Transfer-Encoding', 'value': 'chunked'},

{'name': 'Connection', 'value': 'keep-alive'},

{'name': 'X-Application-Context', 'value': 'za-bank-gateway:8080'}

]

},

'startedDateTime': '2019-06-28T11:43:16.0675861+08:00',

'cache': {}

},

{

XXXX

}，

。。。

],

'creator':

{

'name': 'Fiddler',

'comment': 'https://fiddler2.com',

'version': '5.0.20182.28034'

},

'version': '1.2'

}

}

代码如下：

#!/usr/bin/env python
# -*- coding: utf-8 -*-
from optparse import OptionParser
import os
import sys
import json

# check env
if sys.version_info < (3, 4):
    raise RuntimeError('At least Python 3.4 is required.')

restype = ('js', 'css', 'jpg', 'gif', 'ico', 'png')

def list2dic(headers):
    header_dic = dict()
    for head in headers:
        if head['name'] in header_dic:
            header_dic[head['name']] = header_dic[head['name']] + ',' + head['value']
        else:
            header_dic[head['name']] = head['value']
    return header_dic

def dictoand(dct):
    res_list = list()
    for tp in dct:
        res_list.append('%s=%s' % (tp['name'], tp['value']))
    return '&'.join(res_list)

def dict2lr(lrsc):
    tmpl = '''
    web_custom_request("%(name)s",
        "URL=%(url)s",
        "Method=%(method)s",
        "Resource=%(res)s",
        "Referer=%(referer)s",
        "EncType=%(enctype)s",
        "Body=%(body)s",
        LAST);'''
    # url
    url = lrsc['url']
    method = lrsc['method']
    name = url.split('/')[-1]
    name = name.split('?')[0]
    suff = url.split('.')[-1]
    # Resource type
    global restype
    res = '0'
    if suff in restype:
        res = '1'

    # Content-Type
    enctype = ''
    if 'Content-Type' in lrsc:
        enctype = lrsc['Content-Type']
    # Referer
    referer = ''
    if 'Referer' in lrsc:
        referer = lrsc['Referer']

    # Body
    body = ''
    if 'posttext' in lrsc:
        body = lrsc['posttext']
    elif 'postparams' in lrsc:
        body = dictoand(lrsc['postparams'])
    body = body.replace('"', '\\"')
    res = tmpl % {'name': name, 'url': url, 'method': method, 'enctype': enctype, 'referer': referer, 'res': res,
                  'body': body}
    # Head
    if 'SOAPAction' in lrsc:
        res = ("\n" + ' web_add_header("SOAPAction", "%s")' + ";\n" + res) % lrsc['SOAPAction']
    return res

def parhar(harfile):
    print('harfile:',harfile)
    res = list()
    try:
        import codecs
        # with codecs.open(harfile, 'r', 'utf-8-sig') as in_file:
        #     for line in in_file.readlines():
        #         print(line)
        FH = codecs.open(harfile, mode='r', encoding='utf-8-sig')
        # FH = open(harfile, mode='r')
        print('FH:',FH)
        all = json.load(FH)
        FH.close()
    except Exception as ex:
        print('Open har file errr: %s' % ex)
        quit()

    print(all)
    har_ver = all['log']['version']
    creater = all['log']['creator']['name']
    entries = all['log']['entries']
    ct = len(entries) # 请求实体数据
    for et in entries:
        stm = et['startedDateTime']
        req = et['request'] # 请求数据
        rsp = et['response'] # 返回数据
        lrsc = dict()
        if '_charlesStatus' in rsp and rsp['_charlesStatus'] != 'Complete':
            continue
        # 获取请求入参的主要数据
        lrsc['method'] = req['method']
        lrsc['url'] = req['url']
        headers = req['headers']
        print('headers:', headers)
        # http head
        header_dic = list2dic(headers)
        print('headers dict:', header_dic)
        if 'SOAPAction' in header_dic:
            lrsc['SOAPAction'] = header_dic['SOAPAction'].replace('"', '\\"')
        if 'Referer' in header_dic:
            lrsc['Referer'] = header_dic['Referer']
        if 'Content-Type' in header_dic:
            lrsc['Content-Type'] = header_dic['Content-Type']
        if lrsc['method'] == 'GET':
            pass
        elif lrsc['method'] == 'POST':
            if 'postData' in req:
                if 'text' in req['postData']:
                    lrsc['posttext'] = req['postData']['text']
                if 'params' in req['postData']:
                    lrsc['postparams'] = req['postData']['params']
                if 'mimeType' in req['postData']:
                    lrsc['postmime'] = req['postData']['mimeType']
        else:
            continue
        print('V:',lrsc)
        res.append(dict2lr(lrsc))
    return res

if __name__ == '__main__':
    parse = OptionParser()
    parse.add_option("-f", action="store", dest="harfile", help='harfile path')
    parse.add_option("-o", action="store", dest="lrfile", help='action.c path')
    (options, args) = parse.parse_args()
    print('-----------------------')
    print(options)
    print('-----------------------')
    print(args)

    if options.harfile is None or options.lrfile is None:
        parse.print_help()
        quit()
    if not os.path.exists(options.harfile):
        print('Har file %s not exist' % options.harfile)
        quit()
    print("1")
    res = parhar(options.harfile)
    print("**********************************8888888")
    print(res)
    file = open(options.lrfile, mode='w', encoding='utf-8')
    for sc in res:
        file.write(sc)
        file.write("\n")
    file.close()
    print('Output to %s' % options.lrfile)