1. 提交征信解析第一版版

config/settings.py

+import os
+
+FILE_PATH = os.path.realpath(os.curdir)
+
+FEATURE_HOST = 'http://172.20.1.131:23010'
+FEATURE_HOST_MY = 'http://localhost:23010'
+
+
+url_reportanalysis = '/report'
+

handler/Base_Handler.py

+# -*- coding:utf-8 -*-
+
+import tornado.web
+
+class BaseHandler(tornado.web.RequestHandler):
+    # 初始化映射关系
+    def prepare(self):
+        self.set_header('Content-Type', "application/json; charset=UTF-8")
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+

handler/ReportAnalysis_Handler.py

+# -*- coding:utf-8 -*-
+
+import threading
+from utils import JsonUtil
+from handler.Base_Handler import BaseHandler
+from service.PersonalInformation_Service import PersonalInformation # 个人基本信息
+from service.InformationSummary_Service import InformationSummary # 信息概要
+from service.TransactionDetails_Service import TransactionDetails # 信贷交易明细
+from service.QueryInfomation_Service import QueryInfomation # 查询记录
+
+from service.Base_Service import Result # 返回结果存储
+from service.InitHtml_Service import InitHtml # 初始化HTML
+
+class ReportAnalysis(BaseHandler):
+    def post(self):
+        self._filepath = self.get_argument('filepath', default=None)
+
+        if self._filepath == None or self._filepath == '':
+            self.write(JsonUtil.build_json(code = JsonUtil.Constants.Code_Params_Error,
+                                           mssage=JsonUtil.Constants.Msg_Params_Error.format('filepath',self._filepath)))
+            self.flush()
+
+        else:
+            filepath = self._filepath
+            isFile = False
+            try :
+                with open(filepath, 'rb') as f:
+                    htmlhandle = f.read()
+                    f.close()
+                    isFile = True
+            except IOError as e:
+                self.write(JsonUtil.build_json(code = JsonUtil.Constants.Code_File_Error,
+                                               mssage = JsonUtil.Constants.Msg_File_Error))
+                self.flush()
+
+            if isFile:
+                try :
+                    html = InitHtml(htmlhandle)
+                    asslysis = ['PersonalInformation',
+                                'InformationSummary',
+                                'TransactionDetails',
+                                'QueryInfomation'
+                                ]
+                    maxconnections = len(asslysis) #最大并发数
+                    semlock = threading.BoundedSemaphore(maxconnections)
+                    for i in range(maxconnections):
+                        semlock.acquire()
+                        t = threading.Thread(target=eval(asslysis[i]),args=(html.menu_dict,))
+                        semlock.release()
+                        t.start()
+                    # PersonalInformation(html.menu_dict)
+                    # InformationSummary(html.menu_dict)
+                    # TransactionDetails(html.menu_dict)
+                    # QueryInfomation(html.menu_dict)
+                    result = Result.get_result()
+                    Result.clear_result()
+                    self.write(JsonUtil.build_json(report = result,
+                                                   code=JsonUtil.Constants.Code_Success,
+                                                   mssage=JsonUtil.Constants.Msg_Success))
+                    self.flush()
+                    self.finish()
+                except :
+                    self.write(JsonUtil.build_json(code=JsonUtil.Constants.Code_Analysis_Error,
+                                                   mssage=JsonUtil.Constants.Msg_Analysis_Error
+                                                   ))
+                    self.flush()
+
+
+        # import json
+        # outpath = r'/Users/zhangpengcheng/Documents/量化派代码管理/credit_report/html/provinces.json'
+        # with open(outpath,"w+",encoding="utf-8") as  f:
+        #     _json = json.dumps(Result.get_result())
+        #     f.write(_json)
+        #     f.close()
+
+
+
+        # filepath = r'/Users/zhangpengcheng/Documents/量化派代码管理/credit_report/html/一代征信报告/432325197803211379.html'
+        # filepath = r'/Users/zhangpengcheng/Documents/量化派代码管理/credit_report/html/一代征信报告/13082119950823527X.htm'
+        # filepath = r'/Users/zhangpengcheng/Documents/量化派代码管理/credit_report/html/一代征信报告/32052219780226051X.htm'
+        # filepath = r'/Users/zhangpengcheng/Documents/量化派代码管理/credit_report/html/一代征信报告/140427198607030038.htm'
+        # filepath = r'/Users/zhangpengcheng/Documents/量化派代码管理/credit_report/html/一代征信报告/330682198805122815.htm'
+        # filepath = r'/Users/zhangpengcheng/Documents/量化派代码管理/credit_report/html/一代征信报告/440421198210078001.html'
+
+
+
+    # def run(self):
+    #     if self._target is not None:
+    #         self._return = self._target(*self._args, **self._kwargs)
+    #
+    # def get_return(self):
+    #     try:
+    #         return self._return
+    #     except Exception:
+    #         return None
+    #
+    # def join(self):
+    #     threading.Thread.join(self)
+    #     return self._return
\ No newline at end of file

service/Base_Service.py

+# -*- coding:utf-8 -*-
+
+import bs4
+import re
+from collections import defaultdict
+
+class Result:
+    """html to json"""
+    result = {}
+    html = None
+    @classmethod
+    def set_result(cls,result):
+        cls.result.update(result)
+
+    @classmethod
+    def get_result(cls):
+        return cls.result
+
+    @classmethod
+    def clear_result(cls):
+        cls.result = {}
+        return cls.result
+
+    @classmethod
+    def get_htmlMsg(cls,html):
+        if cls.html == None:
+            cls.html = 1
+        return cls.html
+
+
+class Base(object):
+    def __init__(self,html):
+        self.menu_dict = html
+        pass
+
+    def get_menuDetail(self,tag):
+        """按报告内部小标题拆分"""
+        _dict = defaultdict(list)
+        key = None
+        for i in range(len(tag)):
+            index = []
+            for m in tag[i].stripped_strings:
+                #             ret=re.findall(r'(\（一\）|\（二\）)[\ ]?(\w+)',m)
+                # ret=re.findall(r'(\（\S\）)[\ ]?(\w+)',m)
+                ret=re.findall(r'(\（[\u4E00-\u9FA5]\）)[\ ]?(\w+)',m)
+                if ret:
+                    key = ret[0][1]
+                    index.append(i)
+            if key:
+                if i not in index:
+                    _dict[key].append(tag[i])
+        return dict(_dict)
+
+    def get_menuDetail_personalInformation(self,tag):
+        """按报告内部小标题拆分 - 公共信息明细"""
+        _dict = defaultdict(list)
+        key = None
+        for i in tag:
+            if i.table==None:
+                if i.b:
+                    key = i.b.get_text()
+            else:
+                _dict[key].append( i.table)
+        return _dict
+
+    def get_menuDetail_queryInformation(self,tag):
+        """按报告内部小标题拆分 - """
+        _dict = defaultdict(list)
+        key = None
+        for i in tag:
+            if i.table==None:
+                if i.b:
+                    key = i.b.get_text()
+            else:
+                _dict[key].append( i.table)
+        return _dict
+
+    def get_table(self,tag):
+        """把table 转list"""
+        tag_list = []
+        table = tag.tbody
+        for i,t in enumerate(table):
+            if isinstance(t,bs4.element.Tag):
+                tag_list.append(t)
+        return tag_list
+
+    def get_json(self,tag):
+        """获取table解析后的json , 支持表头与值循环"""
+        result = defaultdict(list)
+        _key = []
+        # _colspan=0
+        index = 0
+        for i,val in enumerate(tag):
+            tds = val.find_all('td')
+            if i %2 == 0:
+                key = []
+                for ii ,td in enumerate(tds):
+                    if isinstance(td,bs4.element.Tag):
+                        # _colspan = td.get('colspan')
+                        tm = ''
+                        for k in td.stripped_strings:
+                            tm+= k
+                    key.append(tm)
+                _key.append(key)
+                index+=1
+            else:
+                if len(_key[index-1]) == len(tds):
+                    for ii ,td in enumerate(tds):
+                        if isinstance(td,bs4.element.Tag):
+                            value = ''
+                            for k in td.stripped_strings:
+                                value+=k
+                        result[_key[index-1][ii]] = value
+                else:
+                    value = []
+                    for ii ,td in enumerate(tds):
+                        value.append(td.get_text().strip())
+                    result[_key[index-1][0]] = value
+        return dict(result)
+
+    # def get_json_tableList(self,tag):
+    #     """支持 table 列表形式 存储
+    #     ::return list
+    #     """
+    #     _result = []
+    #     tag = tag.tbody
+    #     for i in tag:
+    #         td = tag.findAll('td')
+    #         _v = []
+    #         for t in td:
+    #             if t.get('style'):
+    #                 for v in t.stripped_strings:
+    #                     _v.append(v)
+    #         _result.append(_v)
+    #     return _result
\ No newline at end of file

service/InformationSummary_Service.py

+import bs4
+
+from service.Base_Service import Base,Result
+
+
+class InformationSummary(Base):
+    """信息概要"""
+    def __init__(self,filepath):
+        Base.__init__(self,filepath)
+
+        if '信息概要' in self.menu_dict.keys():
+            self.menu_informationSummary = self.get_menuDetail(self.menu_dict['信息概要'])  # 信息概要
+
+            Result.set_result(self.get_Logic(self.menu_informationSummary))
+        else:
+            Result.set_result({'信息概要':None})
+        pass
+
+    def get_Logic(self,tag):
+        result = {}
+        if '信用提示' in tag.keys(): # 信用汇总
+            result.update(self.get_information_creditSummary(tag,'信用提示'))
+            result.update(self.get_numberUnscramble(tag,'信用提示'))
+        if '逾期及违约信息概要' in tag.keys():
+            result.update(self.get_information_overdueAndDefault(tag,'逾期及违约信息概要'))
+
+        if '授信及负债信息概要' in tag.keys(): # 未结清贷款信息汇总 / 未销户贷记卡信息汇总 / 未销户准贷记卡信息汇总
+            result.update(self.get_information_uncLoanSummary(tag,'授信及负债信息概要'))
+
+        return result
+
+    def get_information_creditSummary(self,tag,name):
+        """信用提示 - 信用汇总or信用提示"""
+        result = {'信用汇总':{}}
+        tag = self.menu_informationSummary['信用提示'][0]
+        table_tag = self.get_table(tag)
+        result['信用汇总'].update(self.get_json(table_tag))
+        return result
+
+    def get_numberUnscramble(self,tag,name):
+        """信用提示 - 个人信用报告 “数字解读”"""
+        result = {}
+        tag = tag[name]
+        istrue = False
+        key = ''
+        if tag:
+            for i,t in enumerate(tag):
+                if isinstance(t,bs4.element.Tag):
+                    if '个人信用报告 “数字解读”' in t.td.get_text():
+                        istrue = True
+                        key = t.td.get_text()
+                        table = t.next_sibling.next_sibling
+        if istrue:
+            tag = table
+            if tag:
+                if tag.find_all('tbody'):
+                    for i,t in enumerate(tag):
+                        if isinstance(t,bs4.element.Tag):
+                            table_tag = self.get_table(t)
+                            _json = self.get_json(table_tag)
+                            result[key] = _json
+        return result
+
+    def get_information_uncLoanSummary(self,tag,name):
+        """未结清贷款信息汇总 / 未销户贷记卡信息汇总 / 未销户准贷记卡信息汇总"""
+        result = {}
+        tag = tag[name]
+        if tag:
+            for i,t in enumerate(tag):
+                if isinstance(t,bs4.element.Tag):
+                    if t.td.get('align'):
+                        key = t.td.get_text()
+                    else:
+                        if t.tbody:
+                            table_tag = self.get_table(t)
+                            _json = self.get_json(table_tag)
+                            result[key] = _json
+        return result
+
+    def get_information_overdueAndDefault(self,tag,name):
+        """逾期及违约信息概要"""
+        result = {}
+        tags = tag[name]
+        if tags:
+            for i,tag in enumerate(tags):
+                if isinstance(tag,bs4.element.Tag):
+                    if tag.td.get('align'):
+                        key = tag.td.get_text() # 获取第一行,设置为head
+                    else:
+                        if tag.tbody:
+                            table_tag = self.get_table(tag)
+                            _json = self.get_json_overdueAndDefault(table_tag)
+                            result[key] = _json
+        result['逾期信息汇总'] = result.pop('逾期（透支）信息汇总')
+        return result
+    def get_json_overdueAndDefault(self,tag):
+        """解析table"""
+        column = [] #一共几列
+        head = []
+        key = []
+        body = []
+        line_id = 0 #行
+        row_id = 0 #列
+        values = []
+        result = {}
+        for i,tds in enumerate(tag):
+            tds = tds.children
+            for ii ,td in enumerate(tds):
+                if isinstance(td,bs4.element.Tag):
+                    if td.get('colspan'):
+                        column.append(int(td.get('colspan')))
+                        tm = ''
+                        for k in td.stripped_strings:
+                            tm+=k
+                        head.append(tm)
+                    else:
+                        tm = ''
+                        for k in td.stripped_strings:
+                            tm+=k
+                        values.append(tm)
+                        row_id += 1
+                        if line_id<=1:
+                            if row_id % column[line_id] == 0:
+                                key.append(values)
+                                values = []
+                            #                         print(row_id,line_id,column[line_id])
+                        else:
+                            if row_id % column[line_id] == 0:
+                                body.append(values)
+                                values = []
+            line_id +=1
+        for i,h in enumerate(head):
+            result[h] = dict(zip(key[i],body[i]))
+        return result
+
+
+
+if __name__ == '__main__':
+    InformationSummary()
\ No newline at end of file

service/InitHtml_Service.py

+# -*- coding:utf-8 -*-
+
+from bs4 import BeautifulSoup,Comment
+import bs4,re
+from collections import defaultdict
+
+class InitHtml:
+    """初始化html 文件,拆分标题"""
+
+    def __init__(self,html):
+        htmlhandle = html
+        soup = BeautifulSoup(htmlhandle,'lxml')
+        comments = soup.findAll(text=lambda text: isinstance(text, Comment))
+        [comment.extract() for comment in comments] # 去除注释
+        [s.extract() for s in soup("style")] # 去除指定标签
+        children = self.get_children(soup)
+        # detail = self.children[2].tbody.find_all('tr')
+        # menu_detail = detail[4:]
+        menu_detail = children[2].tbody.children
+        self.menu_dict = self.get_menu(menu_detail) # 获取报告标题信息
+
+    def get_children(self,soup):
+        """获取子节点"""
+        children = []
+        for child in soup.body.children:
+            if child != '\n':
+                children.append(child)
+        return children
+
+
+
+    # def get_menu(self,menu):
+    #     """按报告标题大标题拆分"""
+    #     menu_dict = defaultdict(list)
+    #     index = []
+    #     for i in range(len(menu)):
+    #         for m in menu[i].stripped_strings:
+    #             # #         ret = re.findall(r"[一|二|三|四|五] .*", m)
+    #             # ret=re.findall('(一|二|三|四|五|六|十一)[\ ]{1,1}(\w+)',m)
+    #             ret=re.findall('([\u4E00-\u9FA5])[\ ]{1,1}(\w+)',m)
+    #             if ret:
+    #                 key = ret[0][1]
+    #                 index.append(i)
+    #         if i not in index:
+    #             menu_dict[key].append(menu[i])
+    #     return dict(menu_dict)
+
+    def get_menu(self,menu):
+        """按报告标题大标题拆分"""
+        menu_dict = defaultdict(list)
+        index = []
+        key = None
+        for ii ,i in enumerate(menu):
+            if isinstance(i,bs4.element.Tag):
+                con = i.contents
+                if con :
+                    menu = con[1]
+                    # menu = i.contents[1]
+                    for mm,m in enumerate(menu.stripped_strings):
+                        #                 ret = re.findall(r"[一|二|三|四|五] .*", m)
+                        ret=re.findall('([\u4E00-\u9FA5])[\ ]{1,1}(\w+)',m)
+                        if ret:
+                            key = ret[0][1]
+                            index.append(ii)
+
+                    if key:
+                        if ii not in index:
+                            menu_dict[key].append(i)
+        return dict(menu_dict)
+

service/PersonalInformation_Service.py

+# -*- coding:utf-8 -*-
+
+import json
+from collections import defaultdict
+import bs4
+import pandas as pd
+from service.Base_Service import Base,Result
+
+
+class PersonalInformation(Base):
+    """个人基本信息"""
+    def __init__(self,html):
+        Base.__init__(self,html)
+
+        if '个人基本信息' in self.menu_dict.keys():
+            self.menu_personalInformation = self.get_menuDetail_personalInformation(self.menu_dict['个人基本信息'])  # 个人基本信息
+            Result.set_result(self.get_Logic(self.menu_personalInformation))
+        else:
+            Result.set_result({'个人基本信息':None})
+    def get_Logic(self,tag):
+        result = {}
+        if '身份信息' in tag.keys():
+            result.update(self.get_information_Identity(tag,'身份信息'))
+        if '居住信息' in tag.keys():
+            result.update(self.get_information_Residential(tag,'居住信息'))
+        if '职业信息' in tag.keys():
+            result.update(self.get_information_Occupation(tag,'职业信息'))
+        return result
+
+    def get_information_Identity(self,tag,name):
+        """身份信息"""
+        result = {name:{}}
+        tag_msg = tag[name][0].tbody.children
+        msg = self.get_json(tag_msg)
+        for k,v in msg.items():
+            for i in v:
+                result[name].update(i)
+        result.update(result)
+        return result
+
+    def get_information_Residential(self,tag,name):
+        """居住信息"""
+        result = {name:{}}
+        tag_msg = tag[name][0].tbody.children
+        msg = self.get_json(tag_msg)
+        result[name] = msg[0]
+        return result
+
+    def get_information_Occupation(self,tag,name):
+        """职业信息"""
+        result = {name:{}}
+        tag_msg = tag[name][0].tbody.children
+        msg = self.get_json(tag_msg)
+        if msg :
+            basic = pd.read_json(json.dumps(msg[0]))
+            details =  pd.read_json(json.dumps(msg[1]))
+            df = pd.merge(basic,details,on='编号',how = 'left')
+            js = df.to_dict(orient='records')
+            result[name] = js
+        return result
+
+    def get_json(self,tag):
+        result = defaultdict(list)
+        key = []
+        _num = 0
+        for tr in tag:
+            index = 0
+            if isinstance(tr,bs4.element.Tag):
+                tds = tr.find_all('td')
+                value = []
+                #         key = []
+                td_num = len(tds)
+                for td in tds:
+                    for m in td.stripped_strings:
+                        if td.get('style') == None:
+                            key.append(m)
+                        else:
+                            value.append(m)
+                        index+=1
+
+                if len(key)!=td_num:
+                    key = key[len(key)-td_num:]
+                    _num += 1
+                if value:
+                    result[_num].append(dict(zip(key,value)))
+        return result
+
+if __name__ == '__main__':
+    PersonalInformation()
\ No newline at end of file

service/QueryInfomation_Service.py

+from collections import defaultdict
+
+import bs4
+
+from service.Base_Service import Base,Result
+
+
+class QueryInfomation(Base):
+    """查询记录"""
+    def __init__(self,filepath):
+        Base.__init__(self,filepath)
+        if '查询记录' in self.menu_dict.keys():
+            self.menu_queryInformation = self.get_menuDetail_personalInformation(self.menu_dict['查询记录'])
+            Result.set_result(self.get_Logic(self.menu_queryInformation))
+        else:
+            Result.set_result({'查询记录':None})
+        pass
+
+    def get_Logic(self,tag):
+        result = {}
+        if '查询记录汇总' in tag.keys():
+            result.update(self.get_querySummary(tag,'查询记录汇总'))
+        if '信贷审批查询记录明细' in tag.keys():
+            result.update(self.get_queryCreditApprovalDetail(tag,'信贷审批查询记录明细'))
+        return result
+
+    def get_querySummary(self,tag,name):
+        """查询记录汇总"""
+        _result = {'最近1个月内的查询机构数':{'贷款审批':None,'信用卡审批':None},
+                  '最近1个月内的查询次数':{'贷款审批':None,'信用卡审批':None,'本人查询':None},
+                  '最近2年内的查询次数':{'贷后管理':None,'担保资格审查':None,'特约商户实名审查':None}
+                  }
+        result = {name:{}}
+        values = []
+        tds = self.get_table(tag[name][0])
+        for i ,td in enumerate(tds[2]):
+            if isinstance(td,bs4.element.Tag):
+                tm = ''
+                for msg in td.stripped_strings:
+                    tm+=msg
+                values.append(tm)
+        index = 0
+        for k ,v in _result.items():
+            for kk,vv in v.items():
+                result[name][kk+k] = values[index]
+                index+=1
+        return result
+
+    def get_queryCreditApprovalDetail(self,tag,name):
+        """信贷审批查询记录明细"""
+        result = {}
+        table = tag[name][0].tbody.children
+        result.update(self.get_json(table))
+        result[name] = result.pop(0)
+        return result
+
+    def get_json(self,tag):
+        result = defaultdict(list)
+        key = []
+        _num = 0
+        for tr in tag:
+            index = 0
+            if isinstance(tr,bs4.element.Tag):
+                tds = tr.find_all('td')
+                value = []
+                #         key = []
+                td_num = len(tds)
+                for td in tds:
+                    for m in td.stripped_strings:
+                        if td.get('style') == None:
+                            key.append(m)
+                        else:
+                            value.append(m)
+                        index+=1
+
+                if len(key)!=td_num:
+                    key = key[len(key)-td_num:]
+                    _num += 1
+                if value:
+                    result[_num].append(dict(zip(key,value)))
+        return result
+
+
+if __name__ == '__main__':
+    QueryInfomation()
\ No newline at end of file

service/TransactionDetails_Service.py

+import re
+from collections import defaultdict
+
+import bs4
+import pandas as pd
+
+from service.Base_Service import Base,Result
+
+
+class TransactionDetails(Base):
+    """信贷交易明细"""
+    def __init__(self,filepath):
+        Base.__init__(self,filepath)
+        if '信贷交易信息明细' in self.menu_dict.keys():
+            self.menu_transactionDetails = self.get_menuDetail(self.menu_dict['信贷交易信息明细'])  # 信贷交易信息明细
+            self.menu_transactionDetailsType = {}
+            for k,value in self.menu_transactionDetails.items():
+                # if k == '贷记卡':
+                self.menu_transactionDetailsType[k] = self.get_menuDetailsList(value)
+            Result.set_result(self.get_Logic(self.menu_transactionDetailsType))
+        else:
+            Result.set_result({'信贷交易信息明细':None})
+
+
+    def get_Logic(self,tag):
+        result = {}
+        if '贷款' in tag.keys():
+            result.update(self.get_Loan_Details(tag['贷款']))
+        if '贷记卡' in tag.keys():
+            result.update(self.get_DebitCard_Details(tag['贷记卡']))
+        if '准贷记卡' in tag.keys():
+            result.update(self.get_DebitCard_Details(tag['准贷记卡']))
+        return result
+
+    def get_menuDetailsList(self,tag):
+        """交易信息明细小标题拆分"""
+        _result = []
+        _temp = []
+        for i in tag:
+            if i.td.attrs:
+                try :
+                    if i.div['align'] == 'left':
+                        #                         print(list( re.findall('([0-9]\d{0,2})[\.]{1}(\S+)',i.div.get_text())[0]))
+                        _temp.extend(list( re.findall('([0-9]\d{0,2})[\.]{1}(\S+)',i.div.get_text())[0]))
+                    elif i.div['align'] == 'center':
+                        _temp.append(i)
+                except:
+                    _temp.append(None)
+            else:
+                if i.table:
+                    _temp.append(i) #
+                if _temp:
+                    _result.append(_temp)
+                _temp = []
+        return _result
+
+    def get_Loan_Details(self,tag):
+        """贷款明细拆分拆分"""
+        result = {'贷款':{}}
+        _result = []
+        for v in tag:
+            _json = {}
+            _json['序号'] =v[0]
+            _json['描述'] =v[0]+'.'+v[1]
+            r1 = re.findall("账户状态为“(\S+)”",v[1])
+            if r1:
+                # r = re.findall("(\d{4}年\d{1,2}月\d{1,2}日)([\S+]*)发放的([\S+]*)元\（([\S+]*)\）([\S+]*)，业务号([\S+]{0,1})，([\S+]*)，([\d]*)期，([\S+]*)。截至(\d{4}年\d{1,2}月\d{1,2}日)[\S+]*账户状态为“(\S+)”",v[1])
+                r = re.findall("(\d{4}年\d{1,2}月\d{1,2}日)([\S+]*)发放的(.*?)元\（([\S+]*)\）(.*?)，业务号(.*?)，(.*?)，(.*?)。截至(.*?)，账户状态为“(.*?)”",v[1])
+                if r:
+                    r = r[0]
+                    _json['银行名称'] = r[1]
+                    _json['贷款金额'] = r[2]
+                    _json['贷款类型'] = r[4]
+                    terms = r[7].split('，')
+                    if len(terms)>1:
+                        term = re.findall('(.*?)期',terms[0])[0]
+                        _json['贷款期数'] = term
+                    else:
+                        _json['贷款期数'] = None
+                    _json['是否抵押'] = r[6]
+                    _json['起始时间'] = r[0]
+                    _json['终止时间'] = r[8]
+                    _json['账户状态'] = r[9]
+            else:
+                # r = re.findall("(\d{4}年\d{1,2}月\d{1,2}日)([\S+]*)发放的([\S+]*)元\（([\S+]*)\）([\S+]*)，业务号([\S+]{0,1})，([\S+]*)，([\d]*)期，([\S+]*)，(\d{4}年\d{1,2}月\d{1,2}日)[\S+]*[\S+]*(\d{4}年\d{1,2}月\d{1,2}日)",v[1])
+                r =  re.findall("(\d{4}年\d{1,2}月\d{1,2}日)([\S+]*)发放的(.*?)元\（([\S+]*)\）(.*?)，业务号(.*?)，(.*?)，(.*?)，(\d{4}年\d{1,2}月\d{1,2}日)到期。截至(\d{4}年\d{1,2}月\d{1,2}日)",v[1])
+                if r:
+                    r = r[0]
+                    _json['银行名称'] = r[1]
+                    _json['贷款金额'] = r[2]
+                    _json['贷款类型'] = r[4]
+                    # _json['贷款期数'] = r[7]
+                    terms = r[7].split('，')
+                    if len(terms)>1:
+                        term = re.findall('(.*?)期',terms[0])[0]
+                        _json['贷款期数'] = term
+                    else:
+                        _json['贷款期数'] = None
+                    _json['是否抵押'] = r[6]
+                    _json['起始时间'] = r[0]
+                    _json['终止时间'] = r[9]
+
+            if v[2] != None:
+                table_tag = self.get_table(v[2])
+                table_json = self.get_json_LoanDetails(table_tag)
+                key_name = table_json.keys()
+                # rename = ''
+                plan = ''
+                overdue = ''
+                temp_json = {}
+                for name in key_name:
+                #     r = re.findall("(\d{4}年\d{1,2}月)-(\d{4}年\d{1,2}月)的([\S+]*)",name)
+                #     if r :
+                #         temp_json['近24个月的还款记录-开始时间'] =r[0][0]
+                #         temp_json['近24个月的还款记录-截至时间'] =r[0][1]
+                #         rename = name
+                # if rename:
+                #     table_json['近24个月的还款记录-各期还款记录'] = table_json.pop(rename)
+                # if temp_json:
+                #     table_json.update(temp_json)
+                    r = re.findall("(\d{4}年\d{1,2}月)-(\d{4}年\d{1,2}月)的([\S+]*)",name)
+                    if r :
+                        if r[0][2] == '还款记录':
+                            temp_json['近24个月的还款记录-开始时间'] =r[0][0]
+                            temp_json['近24个月的还款记录-截至时间'] =r[0][1]
+                            plan = name
+                        if r[0][2] == '逾期记录':
+                            overdue = name
+
+                if plan:
+                    table_json['近24个月的还款记录-各期还款记录'] = table_json.pop(plan)
+                if overdue:
+                    del table_json[overdue]
+
+                if temp_json:
+                    table_json.update(temp_json)
+
+                if '逾期记录' in table_json.keys():
+                    df = pd.DataFrame(table_json['逾期记录'])
+                    df = df.loc[(df['逾期持续月数']!='--')&(df['逾期月份']!='--')&(df['逾期金额']!='--')]
+                    df['逾期金额'] = df['逾期金额'].apply(lambda x : float(x.replace(',','')))
+
+                    table_json['逾期记录'] = df.to_dict(orient='records')
+
+                    table_json['近5年逾期记录'] = table_json.pop('逾期记录')
+
+                _json.update(table_json)
+            _result.append(_json)
+        result['贷款'] = _result
+        return result
+
+    def get_DebitCard_Details(self,tag):
+        """贷记卡明细拆分"""
+        result = {'贷记卡':{}}
+        _result = []
+        for v in tag:
+            _json = {}
+            _json['序号'] =v[0]
+            _json['描述'] =v[0]+'.'+v[1]
+            r =  re.findall("(\d{4}年\d{1,2}月\d{1,2}日)(.*?)发放的(.*?)，业务号(.*?)，授信额度[折合人民币]{0,5}(.*?)元，共享授信额度[折合人民币]{0,5}(.*?)元，(.*?)[，|。]{1}截至(\d{4}年\d{1,2}月\d{1,2}日)，(账户状态为“[\u4E00-\u9FA5]{1,2}”)*",v[1])
+            if r :
+                r = r[0]
+                _json['银行名称'] = r[1]
+                _json['授信金额'] = r[4]
+                _json['共享授信金额'] = r[5]
+                _json['授信时间'] = r[0]
+                _json['截止时间'] = r[7]
+                if r[8]:
+                    r_temp = re.findall('账户状态为“(.*?)”',r[8])[0]
+                    _json['账户状态 '] = r_temp
+
+            if v[2] != None:
+                table_tag = self.get_table(v[2])
+                table_json = self.get_json_DebitCard(table_tag)
+                key_name = table_json.keys()
+                plan = ''
+                overdue = ''
+                temp_json = {}
+                for name in key_name:
+                    r = re.findall("(\d{4}年\d{1,2}月)-(\d{4}年\d{1,2}月)的([\S+]*)",name)
+                    if r :
+                        if r[0][2] == '还款记录':
+                            temp_json['近24个月的还款记录-开始时间'] =r[0][0]
+                            temp_json['近24个月的还款记录-截至时间'] =r[0][1]
+                            plan = name
+                        if r[0][2] == '逾期记录':
+                            overdue = name
+
+                if plan:
+                    table_json['近24个月的还款记录-各期还款记录'] = table_json.pop(plan)
+                if overdue:
+                    del table_json[overdue]
+
+                if temp_json:
+                    table_json.update(temp_json)
+
+                if '逾期记录' in table_json.keys():
+                    df = pd.DataFrame(table_json['逾期记录'])
+                    df = df.loc[(df['逾期持续月数']!='--')&(df['逾期月份']!='--')&(df['逾期金额']!='--')]
+                    df['逾期金额'] = df['逾期金额'].apply(lambda x : float(x.replace(',','')))
+                    table_json['逾期记录'] = df.to_dict(orient='records')
+                    table_json['近5年逾期记录'] = table_json.pop('逾期记录')
+                _json.update(table_json)
+            _result.append(_json)
+        result['贷记卡'] = _result
+        return result
+
+    def get_json_DebitCard(self,tag):
+        result = defaultdict(dict)
+        key = []
+        value = []
+        value_list = []
+
+        temp_key = None
+        for i,val in enumerate(tag):
+            tds = val.find_all('td')
+            # tds_len = len(tds)
+            # next_sibling = val.next_sibling
+            # if (next_sibling == ' ' or next_sibling =='\n' ) and next_sibling!=None:
+            #     next_sibling = val.next_sibling.next_sibling
+                # tds_next = next_sibling.find_all('td')
+                # tds_next_len = len(next_sibling.find_all('td'))
+
+            for ii ,td in enumerate(tds):
+                #             print(tds_len,tds_next_len,'---1---')
+                if isinstance(td,bs4.element.Tag):
+                    if val.get('align') or td.get('colspan') == '24':
+                        tm = ''
+                        for k in td.stripped_strings:
+                            tm+= k
+                        key.append(tm)
+                    else:
+                        tm = ''
+                        for k in td.stripped_strings:
+                            tm+= k
+                        value.append(tm)
+                        if len(key) == 0 and temp_key:
+                            value_list.append(tm)
+                            r = re.findall('\d{4}年\d{1,2}月-\d{4}年\d{1,2}月的([\S+]*)',temp_key)
+                            if r:
+                                r = r[0]
+                                if result[temp_key][ii] not in result[r].keys():
+                                    result[r][result[temp_key][ii]] = []
+                                result[r][result[temp_key][ii]].append(value_list[ii])
+
+            if key and value:
+                if len(key) == len(value):
+                    result.update(dict(zip(key,value)))
+                else:
+                    result.update(dict({key[0]:value}))
+                    temp_key = key[0]
+                key=[]
+                value = []
+        return dict(result)
+
+
+    def get_json_LoanDetails(self,tag):
+        result = defaultdict(dict)
+        key = []
+        value = []
+        value_list = []
+
+        temp_key = None
+        for i,val in enumerate(tag):
+            tds = val.find_all('td')
+            # tds_len = len(tds)
+            # next_sibling = val.next_sibling
+            # if (next_sibling == ' ' or next_sibling =='\n' ) and next_sibling!=None:
+            #     next_sibling = val.next_sibling.next_sibling
+            # tds_next = next_sibling.find_all('td')
+            # tds_next_len = len(next_sibling.find_all('td'))
+
+            for ii ,td in enumerate(tds):
+                #             print(tds_len,tds_next_len,'---1---')
+                if isinstance(td,bs4.element.Tag):
+                    if td.get('align') or td.get('colspan') == '24':
+                        tm = ''
+                        for k in td.stripped_strings:
+                            tm+= k
+                        key.append(tm)
+                    else:
+                        tm = ''
+                        for k in td.stripped_strings:
+                            tm+= k
+                        value.append(tm)
+                        if len(key) == 0 and temp_key:
+                            value_list.append(tm)
+                            r = re.findall('\d{4}年\d{1,2}月-\d{4}年\d{1,2}月的([\S+]*)',temp_key)
+                            if r:
+                                r = r[0]
+                                if result[temp_key][ii] not in result[r].keys():
+                                    result[r][result[temp_key][ii]] = []
+                                result[r][result[temp_key][ii]].append(value_list[ii])
+
+            if key and value:
+                if len(key) == len(value):
+                    result.update(dict(zip(key,value)))
+                else:
+                    result.update(dict({key[0]:value}))
+                    temp_key = key[0]
+                key=[]
+                value = []
+        return dict(result)
+
+if __name__ == '__main__':
+    TransactionDetails()
\ No newline at end of file

startup.py

+# -*- coding:utf-8 -*-
+
+'''
+服务启动接口
+'''
+from tornado.web import Application
+from tornado.httpserver import HTTPServer
+from tornado.ioloop import IOLoop
+import tornado.log
+import logging
+import tornado.options
+from config import settings as URL
+
+# from handler import LoanDueRateHandler
+from tornado.options import define, options
+
+from handler import ReportAnalysis_Handler
+
+from tornado.options import define, options
+define("port", default=23010, help="run on the given port ", type=int)
+define("log_path", default='/tmp', help="log path ", type=str)
+
+class LogFormatter(tornado.log.LogFormatter):
+    def __init__(self):
+        print('%(color)s[%(asctime)s %(filename)s:%(funcName)s:%(lineno)d %(levelname)s]%(end_color)s %(message)s')
+        super(LogFormatter, self).__init__(
+                fmt='%(color)s[%(asctime)s %(filename)s:%(funcName)s:%(lineno)d %(levelname)s]%(end_color)s %(message)s',
+                datefmt='%Y-%m-%d %H:%M:%S'
+        )
+
+def apps():
+    return Application([
+        (URL.url_reportanalysis, ReportAnalysis_Handler.ReportAnalysis),
+
+    ])
+
+if __name__ == "__main__":
+
+    # app = apps()
+    # server = HTTPServer(app)
+    # [i.setFormatter(LogFormatter()) for i in logging.getLogger().handlers]
+    # tornado.options.parse_command_line()
+    #
+    # # #== 本地调试
+    # app.listen(23011)
+    # IOLoop.instance().start()
+
+
+    tornado.options.parse_command_line()
+    app = apps()
+    http_server = tornado.httpserver.HTTPServer(app)
+    http_server.bind(options.port)
+    http_server.start()
+    tornado.ioloop.IOLoop.instance().start()

testfile/analysis.py

+# -*- coding:utf-8 -*-
+
+from bs4 import BeautifulSoup,Comment
+from abc import ABCMeta,abstractmethod
+import re
+from lxml import etree
+# path = "/Users/zhangpengcheng/Documents/量化派代码管理/credit_report/html/一代征信报告/432325197803211379.html"
+# path = "/Users/zhangpengcheng/Documents/量化派代码管理/credit_report/html/一代征信报告/32052219780226051X.htm"
+path = "/Users/zhangpengcheng/Documents/量化派代码管理/credit_report/html/一代征信报告/test.html"
+
+htmlfile = open(path, 'rb')
+# print(htmlfile)
+htmlhandle = htmlfile.read()
+soup = BeautifulSoup(htmlhandle,'lxml')
+
+class Base(object):
+    def __init__(self):
+        self.path = "/Users/zhangpengcheng/Documents/量化派代码管理/credit_report/html/一代征信报告/test.html"
+        htmlfile = open(path, 'rb')
+        htmlhandle = htmlfile.read()
+        soup = BeautifulSoup(htmlhandle,'lxml')
+        comments = soup.findAll(text=lambda text: isinstance(text, Comment))
+        [comment.extract() for comment in comments] # 去除注释
+        # [s.extract() for s in soup("style")] # 去除指定标签
+        self.children = self.get_children(soup)
+
+        pass
+
+    def get_children(self,soup):
+        children = []
+        for child in soup.body.children:
+            if child != '\n':
+                children.append(child)
+        return children
+    @abstractmethod
+    def get_json(self,detail,msgJson):
+        return msgJson
+
+class ReportDetail(Base):
+    """报告详情"""
+    def __init__(self):
+        Base.__init__(self)
+        detail = self.children[1].find_all('b')
+        msgJson = {'报告编号':None,'查询请求时间':None,'报告时间':None}
+        self.result = {'报告详情':self.get_json(detail,msgJson)}
+        pass
+
+    def get_json(self,detail,msgJson):
+        for hl in detail:
+            text = hl.get_text()
+            for k,v in msgJson.items():
+                if k in text:
+                    msgJson[k] = text.split(k+':')[1]
+        return msgJson
+
+class SelectDetail(Base):
+    """查询信息"""
+    def __init__(self):
+        Base.__init__(self)
+        detail = self.children[2].table.find_all('tr')
+        msgJson = {}
+        self.result = {'查询信息':self.get_json(detail,msgJson)}
+        pass
+
+
+
+# r = ReportDetail()
+# s = SelectDetail()
+a = AllDatail()
+
+
+
+children = []
+
+for child in soup.body.children:
+    if child != '\n':
+        children.append(child)
+
+d_identity = {}
+table = soup.table
+
+tbody = table.find_all('tbody')
+
+
+tr_arr = table.find_all("tr")
+
+tds = []
+for tr in tr_arr:
+    tds.append(tr.find_all('td'))
+
+# print(tds[0][0].get_text())
+#
+# print(tds[1][0].table['class'])
+#
+# print(tds[1][0].tr.contents[3])
+name = []
+value = []
+tds[0][0].div.get_text()
+for i in range(len(tds[1][0].find_all('tr'))):
+    if tds[1][0].find_all('tr')[i].find(style="WORD-BREAK: break-all") == None:
+        span = tds[1][0].find_all('tr')[i].find_all('div')
+        for s in span:
+            name.append(s.get_text())
+    else:
+        span = tds[1][0].find_all('tr')[i].find_all('div')
+        for s in span:
+            value.append(s.get_text())
+d_identity = dict(zip(name,value))
+
+
+# for child in children:
+#
+#     # print(type(child))
+#     tr_arr = child.find_all("tr")
+#     for tr in tr_arr:
+#         print(tr)
+#
+#     # print(child.find_all(text="性别"))
+#     print('----------')
+# #     print('--------')
+
+
+# from lxml import etree
+# html=etree.HTML(htmlhandle,etree.HTMLParser())
+# print(html.text())
+# print(html.xpath("//b[contains(text(),'一 个人基本信息')]"))
+
+

testfile/test.py

+import urllib3
+import sys
+import bs4
+import chardet
+# reload(sys)
+# sys.setdefaultencoding('utf-8')
+def download(url):
+    htmlfile = open('/Users/zhangpengcheng/Documents/量化派代码管理/credit_report/html/一代征信报告/432325197803211379_1.html','w')
+    try:
+        # result = urllib3.urlopen(url)
+        result = open('/Users/zhangpengcheng/Documents/量化派代码管理/credit_report/html/一代征信报告/432325197803211379.html', 'rb')
+        content = result.read()
+        info = result.info()
+        result.close()
+    except Exception as e:
+        print ('download error!!!')
+        print (e)
+    else:
+        if content != None:
+            charset1 = (chardet.detect(content))['encoding'] #real encoding type
+            charset2 = info.getparam('charset') #declared encoding type
+            print (charset1,' ', charset2)
+            # case1: charset is not None.
+            if charset1 != None and charset2 != None and charset1.lower() != charset2.lower():
+                newcont = bs4.BeautifulSoup(content, from_encoding='GB18030')  #coding: GB18030
+                for cont in newcont:
+                    htmlfile.write('%s\n'%cont)
+            # case2: either charset is None, or charset is the same.
+            else:
+                #print sys.getdefaultencoding()
+                htmlfile.write(content) #default coding: utf-8
+    htmlfile.close()
+if __name__ == "__main__":
+    url = '//www.jb51.net'
+    download(url)
\ No newline at end of file

testfile/征信报告.ipynb

+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 81,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from bs4 import BeautifulSoup,Comment\n",
+    "import bs4\n",
+    "from abc import ABCMeta,abstractmethod\n",
+    "from collections import defaultdict\n",
+    "import re\n",
+    "from lxml import etree"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 82,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_children(soup):\n",
+    "        children = []\n",
+    "        for child in soup.body.children:\n",
+    "            if child != '\\n':\n",
+    "                children.append(child)\n",
+    "        return children\n",
+    "\n",
+    "def get_menu(menu):\n",
+    "    \"\"\"按报告标题大标题拆分\"\"\"\n",
+    "    menu_dict = defaultdict(list)\n",
+    "    index = []\n",
+    "    key = None\n",
+    "    for ii ,i in enumerate(menu):\n",
+    "        if isinstance(i,bs4.element.Tag):\n",
+    "            con = i.contents\n",
+    "            if con :\n",
+    "                menu = con[1]\n",
+    "                # menu = i.contents[1]\n",
+    "                for mm,m in enumerate(menu.stripped_strings):\n",
+    "                    #                 ret = re.findall(r\"[一|二|三|四|五] .*\", m)\n",
+    "                    ret=re.findall('([\\u4E00-\\u9FA5])[\\ ]{1,1}(\\w+)',m)\n",
+    "                    if ret:\n",
+    "                        key = ret[0][1]\n",
+    "                        index.append(ii)\n",
+    "\n",
+    "                if key:\n",
+    "                    if ii not in index:\n",
+    "                        menu_dict[key].append(i)\n",
+    "    return dict(menu_dict)\n",
+    "    \n",
+    "def get_menuDetail(tag):\n",
+    "    \"\"\"按报告内部小标题拆分\"\"\"\n",
+    "    _dict = defaultdict(list)\n",
+    "    key = None\n",
+    "    for i in range(len(tag)):\n",
+    "        index = []\n",
+    "        for m in tag[i].stripped_strings:\n",
+    "            #             ret=re.findall(r'(\\（一\\）|\\（二\\）)[\\ ]?(\\w+)',m)\n",
+    "            # ret=re.findall(r'(\\（\\S\\）)[\\ ]?(\\w+)',m)\n",
+    "            ret=re.findall(r'(\\（[\\u4E00-\\u9FA5]\\）)[\\ ]?(\\w+)',m)\n",
+    "            if ret:\n",
+    "                key = ret[0][1]\n",
+    "                index.append(i)\n",
+    "        if key:\n",
+    "            if i not in index:\n",
+    "                _dict[key].append(tag[i])\n",
+    "    return dict(_dict)\n",
+    "\n",
+    "def get_menuDetail_personalInformation(tag):\n",
+    "    \"\"\"按报告内部小标题拆分 - 个人基本信息\"\"\"\n",
+    "    _dict = defaultdict(list)\n",
+    "    key = None\n",
+    "    for i in tag:\n",
+    "        if i.table==None:\n",
+    "            if i.b:\n",
+    "                key = i.b.get_text()\n",
+    "        else:\n",
+    "            _dict[key].append( i.table)\n",
+    "    return _dict"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 83,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "path = r\"/Users/zhangpengcheng/Documents/量化派代码管理/credit_report/html/一代征信报告/test.html\"\n",
+    "# path = r'/Users/zhangpengcheng/Documents/量化派代码管理/credit_report/html/一代征信报告/440421198210078001.html'\n",
+    "# path = r'/Users/zhangpengcheng/Documents/量化派代码管理/credit_report/html/一代征信报告/432325197803211379.html'\n",
+    "# path = r'/Users/zhangpengcheng/Documents/量化派代码管理/credit_report/html/一代征信报告/330682198805122815.htm'\n",
+    "htmlfile = open(path, 'rb')\n",
+    "htmlhandle = htmlfile.read()\n",
+    "htmlfile.close()\n",
+    "soup = BeautifulSoup(htmlhandle,'lxml')\n",
+    "comments = soup.findAll(text=lambda text: isinstance(text, Comment))\n",
+    "[comment.extract() for comment in comments] # 去除注释\n",
+    "[s.extract() for s in soup(\"style\")] # 去除指定标签\n",
+    "children = get_children(soup)\n",
+    "# detail = self.children[2].tbody.find_all('tr')\n",
+    "# detail = self.children[2].tbody.find_all('tr')\n",
+    "# menu_detail = detail[4:]\n",
+    "menu_detail = children[2].tbody.children\n",
+    "menu_dict = get_menu(menu_detail) # 获取报告标题信息\n",
+    "menu_list = list(menu_dict.keys()) # 获取报告标题列表\n",
+    "\n",
+    "menu_personalInformation = get_menuDetail_personalInformation(menu_dict[menu_list[0]])  # 个人基本信息\n",
+    "menu_informationSummary = get_menuDetail(menu_dict[menu_list[1]])  # 信息概要\n",
+    "menu_transactionDetails = get_menuDetail(menu_dict[menu_list[2]])   # 交易信息明细\n",
+    "# menu_queryInformation = get_menuDetail_personalInformation(menu_dict[menu_list[4]])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 84,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import bs4\n",
+    "def get_detailsList(tag): # 交易信息明细拆分\n",
+    "    \"\"\"交易信息明细小标题拆分\"\"\"\n",
+    "    _result = []\n",
+    "    _temp = []\n",
+    "    for i in tag:\n",
+    "        if i.td.attrs:\n",
+    "            try :\n",
+    "                if i.div['align'] == 'left':\n",
+    "                    #                         print(list( re.findall('([0-9]\\d{0,2})[\\.]{1}(\\S+)',i.div.get_text())[0]))\n",
+    "                    _temp.extend(list( re.findall('([0-9]\\d{0,2})[\\.]{1}(\\S+)',i.div.get_text())[0]))\n",
+    "                elif i.div['align'] == 'center':\n",
+    "                    _temp.append(i)\n",
+    "            except:\n",
+    "                _temp.append(None)\n",
+    "        else:\n",
+    "            if i.table:\n",
+    "                _temp.append(i)\n",
+    "            if _temp:\n",
+    "                _result.append(_temp)\n",
+    "            _temp = []\n",
+    "    return _result\n",
+    "menu_transactionDetailsType = {}\n",
+    "for k,value in menu_transactionDetails.items():\n",
+    "    menu_transactionDetailsType[k] = get_detailsList(value)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 85,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_LoanDetails(self,tag):\n",
+    "        \"\"\"贷款明细拆分拆分\"\"\"\n",
+    "        result = {'贷款':{}}\n",
+    "        _result = []\n",
+    "        for v in tag:\n",
+    "            _json = {}\n",
+    "            _json['序号'] =v[0]\n",
+    "            r1 = re.findall(\"账户状态为“(\\S+)”\",v[1])\n",
+    "            if r1:\n",
+    "                # r = re.findall(\"(\\d{4}年\\d{1,2}月\\d{1,2}日)([\\S+]*)发放的([\\S+]*)元\\（([\\S+]*)\\）([\\S+]*)，业务号([\\S+]{0,1})，([\\S+]*)，([\\d]*)期，([\\S+]*)。截至(\\d{4}年\\d{1,2}月\\d{1,2}日)[\\S+]*账户状态为“(\\S+)”\",v[1])\n",
+    "                r = re.findall(\"(\\d{4}年\\d{1,2}月\\d{1,2}日)([\\S+]*)发放的(.*?)元\\（([\\S+]*)\\）(.*?)，业务号(.*?)，(.*?)，(.*?)。截至(.*?)，账户状态为“(.*?)”\",v[1])\n",
+    "                if r:\n",
+    "                    r = r[0]\n",
+    "                    _json['银行名称'] = r[1]\n",
+    "                    _json['贷款金额'] = r[2]\n",
+    "                    _json['贷款类型'] = r[4]\n",
+    "                    terms = r[7].split('，')\n",
+    "                    if len(terms)>1:\n",
+    "                        term = re.findall('(.*?)期',terms[0])[0]\n",
+    "                        _json['贷款期数'] = term\n",
+    "                    else:\n",
+    "                        _json['贷款期数'] = None\n",
+    "\n",
+    "                    _json['起始时间'] = r[0]\n",
+    "                    _json['终止时间'] = r[8]\n",
+    "                    _json['账户状态'] = r[9]\n",
+    "            else:\n",
+    "                # r = re.findall(\"(\\d{4}年\\d{1,2}月\\d{1,2}日)([\\S+]*)发放的([\\S+]*)元\\（([\\S+]*)\\）([\\S+]*)，业务号([\\S+]{0,1})，([\\S+]*)，([\\d]*)期，([\\S+]*)，(\\d{4}年\\d{1,2}月\\d{1,2}日)[\\S+]*[\\S+]*(\\d{4}年\\d{1,2}月\\d{1,2}日)\",v[1])\n",
+    "                r =  re.findall(\"(\\d{4}年\\d{1,2}月\\d{1,2}日)([\\S+]*)发放的(.*?)元\\（([\\S+]*)\\）(.*?)，业务号(.*?)，(.*?)，(.*?)，(\\d{4}年\\d{1,2}月\\d{1,2}日)到期。截至(\\d{4}年\\d{1,2}月\\d{1,2}日)\",v[1])\n",
+    "                if r:\n",
+    "                    r = r[0]\n",
+    "                    _json['银行名称'] = r[1]\n",
+    "                    _json['贷款金额'] = r[2]\n",
+    "                    _json['贷款类型'] = r[4]\n",
+    "                    # _json['贷款期数'] = r[7]\n",
+    "                    terms = r[7].split('，')\n",
+    "                    if len(terms)>1:\n",
+    "                        term = re.findall('(.*?)期',terms[0])[0]\n",
+    "                        _json['贷款期数'] = term\n",
+    "                    else:\n",
+    "                        _json['贷款期数'] = None\n",
+    "                    _json['起始时间'] = r[0]\n",
+    "                    _json['终止时间'] = r[9]\n",
+    "            if v[2] != None:\n",
+    "                table_tag = get_table(v[2])\n",
+    "                table_json = get_json(table_tag)\n",
+    "                key_name = table_json.keys()\n",
+    "                rename = ''\n",
+    "                temp_json = {}\n",
+    "                for name in key_name:\n",
+    "                    r = re.findall(\"(\\d{4}年\\d{1,2}月)-(\\d{4}年\\d{1,2}月)的([\\S+]*)\",name)\n",
+    "                    if r :\n",
+    "                        temp_json['近24个月的还款记录-开始时间'] =r[0][0]\n",
+    "                        temp_json['近24个月的还款记录-截至时间'] =r[0][1]\n",
+    "                        rename = name\n",
+    "                if rename:\n",
+    "                    table_json['近24个月的还款记录-各期还款记录'] = table_json.pop(rename)\n",
+    "                if temp_json:\n",
+    "                    table_json.update(temp_json)\n",
+    "\n",
+    "                _json.update(table_json)\n",
+    "            _result.append(_json)\n",
+    "        result['贷款'] = _result\n",
+    "        return result"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 86,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_table(tag):\n",
+    "    tag_list = []\n",
+    "    table = tag.tbody\n",
+    "    for i,t in enumerate(table):\n",
+    "        if isinstance(t,bs4.element.Tag):\n",
+    "            tag_list.append(t)\n",
+    "    return tag_list\n",
+    "\n",
+    "def get_json(table):\n",
+    "    result = defaultdict(list)\n",
+    "    _key = []\n",
+    "#     _colspan = 0\n",
+    "    index = 0\n",
+    "    for i,val in enumerate(table):\n",
+    "        tds = val.find_all('td')\n",
+    "        if i %2 == 0:\n",
+    "            key = []\n",
+    "            for ii ,td in enumerate(tds):\n",
+    "                if isinstance(td,bs4.element.Tag):\n",
+    "#                     _colspan = td.get('colspan')\n",
+    "                    tm = ''\n",
+    "                    for k in td.stripped_strings:\n",
+    "                        tm+= k\n",
+    "                key.append(tm)\n",
+    "            _key.append(key)\n",
+    "            index+=1\n",
+    "        else:\n",
+    "            if len(_key[index-1]) == len(tds):\n",
+    "                for ii ,td in enumerate(tds):\n",
+    "                    if isinstance(td,bs4.element.Tag):\n",
+    "                        value = ''\n",
+    "                        for k in td.stripped_strings:\n",
+    "                            value+=k\n",
+    "                    result[_key[index-1][ii]] = value\n",
+    "            else:\n",
+    "                value = []\n",
+    "                for ii ,td in enumerate(tds):\n",
+    "                    value.append(td.get_text().strip())\n",
+    "                result[_key[index-1][0]] = value\n",
+    "    return dict(result)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 87,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'2017年05月07日小额信贷公司“BF”发放的139,934元（人民币）个人消费贷款，业务号X，信用/免担保，34期，按月归还，2020年03月05日到期。截至2019年03月31日，'"
+      ]
+     },
+     "execution_count": 87,
+     "output_type": "execute_result",
+     "metadata": {}
+    }
+   ],
+   "source": [
+    "tag = menu_transactionDetailsType['贷款'][1][2]\n",
+    "table_tag = get_table(tag)\n",
+    "_json = get_json(table_tag)\n",
+    "menu_transactionDetailsType['贷款'][1][1]\n",
+    "# table_tag"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 88,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<tr>\n",
+       "<td>\n",
+       "<div align=\"center\">\n",
+       "<table align=\"center\" cellpadding=\"2\" cellspacing=\"0\" class=\"tableStyle\" width=\"620\">\n",
+       "<tbody>\n",
+       "<tr>\n",
+       "<td class=\"tdStyle\" width=\"10%\">\n",
+       "<div align=\"center\" class=\"high\"><b><font color=\"#0066cc\"><span class=\"high\">个人住房贷款笔数</span></font></b></div></td>\n",
+       "<td class=\"tdStyle\" width=\"10%\">\n",
+       "<div align=\"center\" class=\"high\"><b><font color=\"#0066cc\"><span class=\"high\">个人商用房（包括商住两用）贷款笔数</span></font></b></div></td>\n",
+       "<td class=\"tdStyle\" width=\"10%\">\n",
+       "<div align=\"center\" class=\"high\"><b><font color=\"#0066cc\"><span class=\"high\">其他贷款笔数</span></font></b></div></td>\n",
+       "<td class=\"tdStyle\" width=\"10%\">\n",
+       "<div align=\"center\" class=\"high\"><b><font color=\"#0066cc\"><span class=\"high\">首笔贷款发放月份</span></font></b></div></td>\n",
+       "<td class=\"tdStyle\" width=\"10%\">\n",
+       "<div align=\"center\" class=\"high\"><b><font color=\"#0066cc\"><span class=\"high\">贷记卡账户数</span></font></b></div></td>\n",
+       "<td class=\"tdStyle\" width=\"10%\">\n",
+       "<div align=\"center\" class=\"high\"><b><font color=\"#0066cc\"><span class=\"high\">首张贷记卡发卡月份</span></font></b></div></td>\n",
+       "<td class=\"tdStyle\" width=\"10%\">\n",
+       "<div align=\"center\" class=\"high\"><b><font color=\"#0066cc\"><span class=\"high\">准贷记卡账户数</span></font></b></div></td>\n",
+       "<td class=\"tdStyle\" width=\"10%\">\n",
+       "<div align=\"center\" class=\"high\"><b><font color=\"#0066cc\"><span class=\"high\">首张准贷记卡发卡月份</span></font></b></div></td>\n",
+       "<td class=\"tdStyle\" width=\"10%\">\n",
+       "<div align=\"center\" class=\"high\"><b><font color=\"#0066cc\"><span class=\"high\">本人声明数目</span></font></b></div></td>\n",
+       "<td class=\"tdStyle\" width=\"10%\">\n",
+       "<div align=\"center\" class=\"high\"><b><font color=\"#0066cc\"><span class=\"high\">异议标注数目</span></font></b></div></td></tr>\n",
+       "<tr>\n",
+       "<td class=\"tdStyle\" width=\"10%\">\n",
+       "<div align=\"center\" class=\"high\"><font color=\"#0066cc\">0</font></div></td>\n",
+       "<td class=\"tdStyle\" width=\"10%\">\n",
+       "<div align=\"center\" class=\"high\"><font color=\"#0066cc\">0</font></div></td>\n",
+       "<td class=\"tdStyle\" width=\"10%\">\n",
+       "<div align=\"center\" class=\"high\"><font color=\"#0066cc\">97</font></div></td>\n",
+       "<td class=\"tdStyle\" width=\"10%\">\n",
+       "<div align=\"center\" class=\"high\"><font color=\"#0066cc\">2016.03</font></div></td>\n",
+       "<td class=\"tdStyle\" width=\"10%\">\n",
+       "<div align=\"center\" class=\"high\"><font color=\"#0066cc\">10</font></div></td>\n",
+       "<td class=\"tdStyle\" width=\"10%\">\n",
+       "<div align=\"center\" class=\"high\"><font color=\"#0066cc\">2007.07</font></div></td>\n",
+       "<td class=\"tdStyle\" width=\"10%\">\n",
+       "<div align=\"center\" class=\"high\"><font color=\"#0066cc\">0</font></div></td>\n",
+       "<td class=\"tdStyle\" width=\"10%\">\n",
+       "<div align=\"center\" class=\"high\"><font color=\"#0066cc\">--</font></div></td>\n",
+       "<td class=\"tdStyle\" width=\"10%\">\n",
+       "<div align=\"center\" class=\"high\"><font color=\"#0066cc\">0</font></div></td>\n",
+       "<td class=\"tdStyle\" width=\"10%\">\n",
+       "<div align=\"center\" class=\"high\"><font color=\"#0066cc\">0</font></div></td></tr></tbody></table></div></td></tr>"
+      ]
+     },
+     "execution_count": 88,
+     "output_type": "execute_result",
+     "metadata": {}
+    }
+   ],
+   "source": [
+    "def get_json(table):\n",
+    "    result = defaultdict(dict)\n",
+    "    key = []\n",
+    "    value = []\n",
+    "    value_list = []\n",
+    " \n",
+    "    temp_key = None\n",
+    "    for i,val in enumerate(table):\n",
+    "        tds = val.find_all('td') \n",
+    "        tds_len = len(tds)\n",
+    "        next_sibling = val.next_sibling\n",
+    "        tds_next_len = tds_len\n",
+    "        if (next_sibling == ' ' or next_sibling =='\\n' ) and next_sibling!=None:\n",
+    "            next_sibling = val.next_sibling.next_sibling\n",
+    "            tds_next = next_sibling.find_all('td')\n",
+    "            tds_next_len = len(next_sibling.find_all('td'))\n",
+    "        \n",
+    "        for ii ,td in enumerate(tds):\n",
+    "#             print(tds_len,tds_next_len,'---1---')\n",
+    "            if isinstance(td,bs4.element.Tag):\n",
+    "                if val.get('align') or td.get('colspan') == '24':\n",
+    "                    tm = ''\n",
+    "                    for k in td.stripped_strings:\n",
+    "                        tm+= k\n",
+    "                    key.append(tm)\n",
+    "                else:\n",
+    "                    tm = ''\n",
+    "                    for k in td.stripped_strings:\n",
+    "                        tm+= k\n",
+    "                    value.append(tm)\n",
+    "                    if len(key) == 0 and temp_key:\n",
+    "                        value_list.append(tm)\n",
+    "                        r = re.findall('\\d{4}年\\d{1,2}月-\\d{4}年\\d{1,2}月的([\\S+]*)',temp_key)\n",
+    "                        if r:\n",
+    "                            r = r[0]\n",
+    "                            if result[temp_key][ii] not in result[r].keys():\n",
+    "                                result[r][result[temp_key][ii]] = []\n",
+    "                            result[r][result[temp_key][ii]].append(value_list[ii])\n",
+    "                    \n",
+    "#                             result[r].append({result[temp_key][ii]:value_list[ii]})\n",
+    "                        \n",
+    "        if key and value:\n",
+    "            if len(key) == len(value):\n",
+    "                print(key,value)\n",
+    "                result.update(dict(zip(key,value)))\n",
+    "            else:\n",
+    "                result.update(dict({key[0]:value}))\n",
+    "                temp_key = key[0]\n",
+    "#                 print(key,value)\n",
+    "            key=[]\n",
+    "            value = []\n",
+    "    return dict(result)\n",
+    "\n",
+    "# table_tag = get_table(menu_transactionDetailsType['贷记卡'][0][2])\n",
+    "# get_json(table_tag)\n",
+    "\n",
+    "tag = menu_informationSummary['信用提示'][0]\n",
+    "# table_tag = get_table(tag)\n",
+    "# _json = get_json(table_tag)\n",
+    "# _json\n",
+    "\n",
+    "tag"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 103,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'个人信用报告 “数字解读”': {'余额': '381,170',\n",
+       "  '合同总额': '455,783',\n",
+       "  '最近6个月平均应还款': '16,911',\n",
+       "  '笔数': '21',\n",
+       "  '贷款机构数': '12',\n",
+       "  '贷款法人机构数': '12'}}"
+      ]
+     },
+     "execution_count": 103,
+     "output_type": "execute_result",
+     "metadata": {}
+    }
+   ],
+   "source": [
+    "def get_json(tag):\n",
+    "    \"\"\"获取table解析后的json , 支持表头与值循环\"\"\"\n",
+    "    result = defaultdict(list)\n",
+    "    _key = []\n",
+    "    # _colspan=0\n",
+    "    index = 0\n",
+    "    for i,val in enumerate(tag):\n",
+    "        tds = val.find_all('td')\n",
+    "        if i %2 == 0:\n",
+    "            key = []\n",
+    "            for ii ,td in enumerate(tds):\n",
+    "                if isinstance(td,bs4.element.Tag):\n",
+    "                    # _colspan = td.get('colspan')\n",
+    "                    tm = ''\n",
+    "                    for k in td.stripped_strings:\n",
+    "                        tm+= k\n",
+    "                key.append(tm)\n",
+    "            _key.append(key)\n",
+    "            index+=1\n",
+    "        else:\n",
+    "            if len(_key[index-1]) == len(tds):\n",
+    "                for ii ,td in enumerate(tds):\n",
+    "                    if isinstance(td,bs4.element.Tag):\n",
+    "                        value = ''\n",
+    "                        for k in td.stripped_strings:\n",
+    "                            value+=k\n",
+    "                    result[_key[index-1][ii]] = value\n",
+    "            else:\n",
+    "                value = []\n",
+    "                for ii ,td in enumerate(tds):\n",
+    "                    value.append(td.get_text().strip())\n",
+    "                result[_key[index-1][0]] = value\n",
+    "    return dict(result)\n",
+    "def get_numberUnscramble(tag,name):\n",
+    "    result = {}\n",
+    "    tag = tag[name]\n",
+    "    istrue = False\n",
+    "    key = ''\n",
+    "    if tag:\n",
+    "        for i,t in enumerate(tag):\n",
+    "            if isinstance(t,bs4.element.Tag):\n",
+    "                if '个人信用报告 “数字解读”' in t.td.get_text():\n",
+    "                    istrue = True\n",
+    "                    key = t.td.get_text()\n",
+    "                    table = t.next_sibling.next_sibling\n",
+    "    if istrue:\n",
+    "        tag = table\n",
+    "        if tag:\n",
+    "            if tag.find_all('tbody'):\n",
+    "                for i,t in enumerate(tag):\n",
+    "                    if isinstance(t,bs4.element.Tag):\n",
+    "                        table_tag = get_table(t)\n",
+    "                        _json = get_json(table_tag)\n",
+    "                        result[key] = _json\n",
+    "    return result\n",
+    "get_numberUnscramble(menu_informationSummary,'信用提示')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 57,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<tr>\n",
+       "<td>\n",
+       "<div align=\"center\">\n",
+       "<table align=\"center\" cellpadding=\"2\" cellspacing=\"0\" class=\"tableStyle\" width=\"620\">\n",
+       "<tbody>\n",
+       "<tr>\n",
+       "<td class=\"tdStyle\" width=\"10%\">\n",
+       "<div align=\"center\" class=\"high\"><b><font color=\"#0066cc\"><span class=\"high\">个人住房贷款笔数</span></font></b></div></td>\n",
+       "<td class=\"tdStyle\" width=\"10%\">\n",
+       "<div align=\"center\" class=\"high\"><b><font color=\"#0066cc\"><span class=\"high\">个人商用房（包括商住两用）贷款笔数</span></font></b></div></td>\n",
+       "<td class=\"tdStyle\" width=\"10%\">\n",
+       "<div align=\"center\" class=\"high\"><b><font color=\"#0066cc\"><span class=\"high\">其他贷款笔数</span></font></b></div></td>\n",
+       "<td class=\"tdStyle\" width=\"10%\">\n",
+       "<div align=\"center\" class=\"high\"><b><font color=\"#0066cc\"><span class=\"high\">首笔贷款发放月份</span></font></b></div></td>\n",
+       "<td class=\"tdStyle\" width=\"10%\">\n",
+       "<div align=\"center\" class=\"high\"><b><font color=\"#0066cc\"><span class=\"high\">贷记卡账户数</span></font></b></div></td>\n",
+       "<td class=\"tdStyle\" width=\"10%\">\n",
+       "<div align=\"center\" class=\"high\"><b><font color=\"#0066cc\"><span class=\"high\">首张贷记卡发卡月份</span></font></b></div></td>\n",
+       "<td class=\"tdStyle\" width=\"10%\">\n",
+       "<div align=\"center\" class=\"high\"><b><font color=\"#0066cc\"><span class=\"high\">准贷记卡账户数</span></font></b></div></td>\n",
+       "<td class=\"tdStyle\" width=\"10%\">\n",
+       "<div align=\"center\" class=\"high\"><b><font color=\"#0066cc\"><span class=\"high\">首张准贷记卡发卡月份</span></font></b></div></td>\n",
+       "<td class=\"tdStyle\" width=\"10%\">\n",
+       "<div align=\"center\" class=\"high\"><b><font color=\"#0066cc\"><span class=\"high\">本人声明数目</span></font></b></div></td>\n",
+       "<td class=\"tdStyle\" width=\"10%\">\n",
+       "<div align=\"center\" class=\"high\"><b><font color=\"#0066cc\"><span class=\"high\">异议标注数目</span></font></b></div></td></tr>\n",
+       "<tr>\n",
+       "<td class=\"tdStyle\" width=\"10%\">\n",
+       "<div align=\"center\" class=\"high\"><font color=\"#0066cc\">0</font></div></td>\n",
+       "<td class=\"tdStyle\" width=\"10%\">\n",
+       "<div align=\"center\" class=\"high\"><font color=\"#0066cc\">0</font></div></td>\n",
+       "<td class=\"tdStyle\" width=\"10%\">\n",
+       "<div align=\"center\" class=\"high\"><font color=\"#0066cc\">97</font></div></td>\n",
+       "<td class=\"tdStyle\" width=\"10%\">\n",
+       "<div align=\"center\" class=\"high\"><font color=\"#0066cc\">2016.03</font></div></td>\n",
+       "<td class=\"tdStyle\" width=\"10%\">\n",
+       "<div align=\"center\" class=\"high\"><font color=\"#0066cc\">10</font></div></td>\n",
+       "<td class=\"tdStyle\" width=\"10%\">\n",
+       "<div align=\"center\" class=\"high\"><font color=\"#0066cc\">2007.07</font></div></td>\n",
+       "<td class=\"tdStyle\" width=\"10%\">\n",
+       "<div align=\"center\" class=\"high\"><font color=\"#0066cc\">0</font></div></td>\n",
+       "<td class=\"tdStyle\" width=\"10%\">\n",
+       "<div align=\"center\" class=\"high\"><font color=\"#0066cc\">--</font></div></td>\n",
+       "<td class=\"tdStyle\" width=\"10%\">\n",
+       "<div align=\"center\" class=\"high\"><font color=\"#0066cc\">0</font></div></td>\n",
+       "<td class=\"tdStyle\" width=\"10%\">\n",
+       "<div align=\"center\" class=\"high\"><font color=\"#0066cc\">0</font></div></td></tr></tbody></table></div></td></tr>"
+      ]
+     },
+     "execution_count": 57,
+     "output_type": "execute_result",
+     "metadata": {}
+    }
+   ],
+   "source": [
+    "menu_informationSummary['信用提示'][0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 104,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>逾期持续月数</th>\n",
+       "      <th>逾期月份</th>\n",
+       "      <th>逾期金额</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>2016.07</td>\n",
+       "      <td>755</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>1</td>\n",
+       "      <td>2014.12</td>\n",
+       "      <td>497</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>1</td>\n",
+       "      <td>2016.07</td>\n",
+       "      <td>755</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>1</td>\n",
+       "      <td>2014.12</td>\n",
+       "      <td>497</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ]
+     },
+     "output_type": "execute_result",
+     "metadata": {}
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "aa = {'逾期持续月数': ['1', '1', '1', '1'],\n",
+    "  '逾期月份': ['2016.07', '2014.12', '2016.07', '2014.12'],\n",
+    "  '逾期金额': ['755', '497', '755', '497']}\n",
+    "pd.DataFrame(aa)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 105,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{}"
+      ]
+     },
+     "execution_count": 105,
+     "output_type": "execute_result",
+     "metadata": {}
+    }
+   ],
+   "source": [
+    "tag = menu_informationSummary['授信及负债信息概要'][1]\n",
+    "def get_table(tag):\n",
+    "        \"\"\"把table 转list\"\"\"\n",
+    "        tag_list = []\n",
+    "        table = tag.tbody\n",
+    "        for i,t in enumerate(table):\n",
+    "            if isinstance(t,bs4.element.Tag):\n",
+    "                tag_list.append(t)\n",
+    "        return tag_list\n",
+    "\n",
+    "table_tag = get_table(tag)\n",
+    "_json = get_json(table_tag)\n",
+    "_json"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 106,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'未结清贷款信息汇总': {}, '未销户贷记卡信息汇总': {}}\n"
+     ]
+    }
+   ],
+   "source": [
+    "result = {}\n",
+    "for i,tag in enumerate(menu_informationSummary['授信及负债信息概要']):\n",
+    "    if  isinstance(tag,bs4.element.Tag):\n",
+    "        if tag.td.get('align'):\n",
+    "            key = tag.td.get_text()\n",
+    "        else:\n",
+    "            if tag.tbody:\n",
+    "                table_tag = get_table(tag)\n",
+    "                _json = get_json(table_tag)\n",
+    "                result[key] = _json\n",
+    "print(result)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 107,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# _key = menu_personalInformation.keys()\n",
+    "# for k in _key:\n",
+    "    \n",
+    "#     table_tagmsg_tag = menu_personalInformation[k][0]\n",
+    "#     table_tagmsg = get_table(table_tagmsg_tag)\n",
+    "#     _json = get_json(table_tagmsg)\n",
+    "#     print(_json)\n",
+    "\n",
+    "table_tag_live = menu_personalInformation['居住信息'][0]\n",
+    "# table_tagmsg = get_table(table_tagmsg_tag)\n",
+    "# _json = get_json(table_tagmsg)\n",
+    "# _json"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 108,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tag = table_tag_live.tbody"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 109,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "_result = []\n",
+    "for i in tag:\n",
+    "    td = tag.findAll('td')\n",
+    "    _v = []\n",
+    "    for t in td:\n",
+    "        if t.get('style'):\n",
+    "            for v in t.stripped_strings:\n",
+    "                _v.append(v)\n",
+    "    _result.append(_v)\n",
+    " \n",
+    "    \n",
+    "#     if isinstance(i,bs4.element.Tag):\n",
+    "#         if i.td.get('colspan') == None:\n",
+    "#             print(i)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 110,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[['1', '浙xxxxxxxx司', '浙xxxxxxxxx9号'], ['2', '浙xxxxxxxxxx中心', '--'], ['3', '浙xxx司', '浙xxxxxxxx9号'], ['4', '杭xxxxxx络', '浙xxxxxxxxxxx902'], ['5', '杭xxxxxxxx公司', '浙xxxxxxxxxxxx际'], ['1', '--'], ['--', '--', '--'], ['1900', '2019.02.20', '2'], ['--', '租赁和商务服务业', '--'], ['--', '--', '2018.09.28'], ['3', '--', '--'], ['--', '--', '2017'], ['2018.03.05', '4', '--'], ['信息传输、计算机服务和软件业', '--', '无'], ['--', '2018.02.24', '5'], ['--', '信息传输、计算机服务和软件业', '一般员工'], ['--', '--', '2018.01.16']]\n"
+     ]
+    }
+   ],
+   "source": [
+    "table = menu_personalInformation['职业信息']\n",
+    "result = []\n",
+    "bodys= []\n",
+    "heads = {}\n",
+    "\n",
+    "def get_head(tag):\n",
+    "    num = 0\n",
+    "    for i,k in enumerate(table[0].tr.children):\n",
+    "        if isinstance(k,bs4.element.Tag):\n",
+    "            num+=1\n",
+    "    return num\n",
+    "result_2 = defaultdict(list)\n",
+    "\n",
+    "for i,val in enumerate(table):\n",
+    "    tds = val.find_all('td')\n",
+    "    index = 0\n",
+    "    _i = 0\n",
+    "    for ii,td in enumerate(tds):\n",
+    "        if isinstance(td,bs4.element.Tag):\n",
+    "#             print(td)\n",
+    "            td_num = get_head(val)\n",
+    "            \n",
+    "            if td.get('style') == None:\n",
+    "                for h in td.stripped_strings:\n",
+    "                    heads[h] = []\n",
+    "\n",
+    "            else:\n",
+    "                for v in td.stripped_strings:\n",
+    "                    bodys.append(v)\n",
+    "            index +=1\n",
+    "        if index%td_num == 0 :\n",
+    "#             print(td)\n",
+    "            if bodys:\n",
+    "                result.append(bodys)\n",
+    "                bodys = []\n",
+    "#             for mm, m in enumerate(td.stripped_strings):\n",
+    "#                 if td.get('style') == None:\n",
+    "#                     key.append(m)\n",
+    "#                 else:\n",
+    "#                     result_2[key[index%td_num]].append(m)\n",
+    "#                 index +=1\n",
+    "\n",
+    "print(result)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 111,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# table = menu_personalInformation['身份信息']\n",
+    "table = menu_transactionDetailsType['贷款'][1][2]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 65,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "table = menu_personalInformation['职业信息']\n",
+    "tag = table[0].tbody.children\n",
+    "def get_json(tag):\n",
+    "    result = defaultdict(list)\n",
+    "    key = []\n",
+    "    _num = 0\n",
+    "    for tr in tag:\n",
+    "        _re = []\n",
+    "        index = 0\n",
+    "        if isinstance(tr,bs4.element.Tag):\n",
+    "            tds = tr.find_all('td')\n",
+    "            value = []\n",
+    "    #         key = []\n",
+    "            td_num = len(tds)\n",
+    "            for td in tds:\n",
+    "                for m in td.stripped_strings:\n",
+    "                    if td.get('style') == None:\n",
+    "                        key.append(m)\n",
+    "                    else:\n",
+    "                        value.append(m)\n",
+    "                    index+=1\n",
+    "\n",
+    "            if len(key)!=td_num:\n",
+    "                key = key[len(key)-td_num:]\n",
+    "                _num += 1\n",
+    "            if value:\n",
+    "                result[_num].append(dict(zip(key,value)))\n",
+    "    return dict(result)\n",
+    "_identity = get_json(tag)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 113,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# 11.查询记录汇总\n",
+    "querySummary = menu_queryInformation['查询记录汇总'][0]\n",
+    "query_Detail = get_table(querySummary)\n",
+    "query_Detail[1]\n",
+    "_result = {'最近1个月内的查询机构数':{'贷款审批':None,'信用卡审批':None},\n",
+    "                  '最近1个月内的查询次数':{'贷款审批':None,'信用卡审批':None,'本人查询':None},\n",
+    "                  '最近2年内的查询次数':{'贷后管理':None,'担保资格审查':None,'特约商户实名审查':None}\n",
+    "                  }\n",
+    "values = []\n",
+    "\n",
+    "for i ,td in enumerate(query_Detail[2]):\n",
+    "    if isinstance(td,bs4.element.Tag):\n",
+    "        tm = ''\n",
+    "        for msg in td.stripped_strings:\n",
+    "            tm+=msg\n",
+    "        values.append(tm)\n",
+    "result = {'查询记录汇总':{}}\n",
+    "index = 0\n",
+    "for k ,v in _result.items():\n",
+    "    for kk,vv in v.items():\n",
+    "        result['查询记录汇总'][kk+k] = values[index]\n",
+    "        index+=1"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 114,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'查询记录汇总': {'信用卡审批最近1个月内的查询机构数': '0',\n",
+       "  '信用卡审批最近1个月内的查询次数': '0',\n",
+       "  '担保资格审查最近2年内的查询次数': '0',\n",
+       "  '本人查询最近1个月内的查询次数': '0',\n",
+       "  '特约商户实名审查最近2年内的查询次数': '0',\n",
+       "  '贷后管理最近2年内的查询次数': '24',\n",
+       "  '贷款审批最近1个月内的查询机构数': '2',\n",
+       "  '贷款审批最近1个月内的查询次数': '2'}}"
+      ]
+     },
+     "execution_count": 114,
+     "output_type": "execute_result",
+     "metadata": {}
+    }
+   ],
+   "source": [
+    "result"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 116,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{0: [{'查询原因': '贷款审批', '查询操作员': 'VB', '查询日期': '2019.05.07', '编号': '1'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'XZ', '查询日期': '2019.04.21', '编号': '2'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'ZV', '查询日期': '2019.04.08', '编号': '3'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'OX', '查询日期': '2019.04.01', '编号': '4'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'YM', '查询日期': '2019.03.05', '编号': '5'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'YP', '查询日期': '2019.03.05', '编号': '6'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'SC', '查询日期': '2019.03.04', '编号': '7'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'VB', '查询日期': '2019.03.01', '编号': '8'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'OX', '查询日期': '2019.02.26', '编号': '9'},\n",
+       "  {'查询原因': '信用卡审批', '查询操作员': 'RZ', '查询日期': '2019.02.20', '编号': '10'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'JJ', '查询日期': '2019.02.18', '编号': '11'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'YP', '查询日期': '2019.01.08', '编号': '12'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'OX', '查询日期': '2018.12.05', '编号': '13'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'DG', '查询日期': '2018.11.14', '编号': '14'},\n",
+       "  {'查询原因': '信用卡审批', '查询操作员': 'RZ', '查询日期': '2018.11.14', '编号': '15'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'YM', '查询日期': '2018.11.07', '编号': '16'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'YP', '查询日期': '2018.11.07', '编号': '17'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'TX', '查询日期': '2018.11.07', '编号': '18'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'XZ', '查询日期': '2018.11.07', '编号': '19'},\n",
+       "  {'查询原因': '信用卡审批', '查询操作员': 'OO', '查询日期': '2018.10.29', '编号': '20'},\n",
+       "  {'查询原因': '信用卡审批', '查询操作员': 'HR', '查询日期': '2018.10.12', '编号': '21'},\n",
+       "  {'查询原因': '信用卡审批', '查询操作员': 'NP', '查询日期': '2018.10.08', '编号': '22'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'DG', '查询日期': '2018.10.08', '编号': '23'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'OX', '查询日期': '2018.10.01', '编号': '24'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'XZ', '查询日期': '2018.09.28', '编号': '25'},\n",
+       "  {'查询原因': '信用卡审批', '查询操作员': 'ZH', '查询日期': '2018.09.27', '编号': '26'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'ZV', '查询日期': '2018.09.09', '编号': '27'},\n",
+       "  {'查询原因': '信用卡审批', '查询操作员': 'ZH', '查询日期': '2018.09.05', '编号': '28'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'ZZ', '查询日期': '2018.09.04', '编号': '29'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'XZ', '查询日期': '2018.08.17', '编号': '30'},\n",
+       "  {'查询原因': '信用卡审批', '查询操作员': 'OO', '查询日期': '2018.08.14', '编号': '31'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'PP', '查询日期': '2018.08.08', '编号': '32'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'QC', '查询日期': '2018.08.07', '编号': '33'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'ZV', '查询日期': '2018.07.31', '编号': '34'},\n",
+       "  {'查询原因': '信用卡审批', '查询操作员': 'GH', '查询日期': '2018.07.12', '编号': '35'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'ZV', '查询日期': '2018.06.25', '编号': '36'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'GH', '查询日期': '2018.06.25', '编号': '37'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'GZ', '查询日期': '2018.06.25', '编号': '38'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'XZ', '查询日期': '2018.06.20', '编号': '39'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'PK', '查询日期': '2018.06.07', '编号': '40'},\n",
+       "  {'查询原因': '信用卡审批', '查询操作员': 'ZH', '查询日期': '2018.06.05', '编号': '41'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'BM', '查询日期': '2018.05.26', '编号': '42'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'XZ', '查询日期': '2018.05.14', '编号': '43'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'ZF', '查询日期': '2018.05.12', '编号': '44'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'ZV', '查询日期': '2018.05.10', '编号': '45'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'RZ', '查询日期': '2018.05.09', '编号': '46'},\n",
+       "  {'查询原因': '信用卡审批', '查询操作员': 'RF', '查询日期': '2018.03.09', '编号': '47'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'XZ', '查询日期': '2018.03.07', '编号': '48'},\n",
+       "  {'查询原因': '信用卡审批', '查询操作员': 'BU', '查询日期': '2018.02.28', '编号': '49'},\n",
+       "  {'查询原因': '信用卡审批', '查询操作员': 'XZ', '查询日期': '2018.01.14', '编号': '50'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'YM', '查询日期': '2017.12.14', '编号': '51'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'XZ', '查询日期': '2017.11.05', '编号': '52'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'YM', '查询日期': '2017.11.01', '编号': '53'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'ZN', '查询日期': '2017.11.01', '编号': '54'},\n",
+       "  {'查询原因': '信用卡审批', '查询操作员': 'CB', '查询日期': '2017.10.18', '编号': '55'},\n",
+       "  {'查询原因': '信用卡审批', '查询操作员': 'ZH', '查询日期': '2017.10.17', '编号': '56'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'PZ', '查询日期': '2017.10.14', '编号': '57'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'ST', '查询日期': '2017.09.28', '编号': '58'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'ZN', '查询日期': '2017.09.25', '编号': '59'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'YM', '查询日期': '2017.09.24', '编号': '60'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'JJ', '查询日期': '2017.09.12', '编号': '61'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'RC', '查询日期': '2017.09.10', '编号': '62'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'GH', '查询日期': '2017.08.21', '编号': '63'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'YM', '查询日期': '2017.08.21', '编号': '64'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'RC', '查询日期': '2017.07.13', '编号': '65'},\n",
+       "  {'查询原因': '贷款审批', '查询操作员': 'YM', '查询日期': '2017.05.18', '编号': '66'}]}"
+      ]
+     },
+     "execution_count": 116,
+     "output_type": "execute_result",
+     "metadata": {}
+    }
+   ],
+   "source": [
+    "# 12.信贷审批查询记录明细\n",
+    "queryCreditApprovalDetail = menu_queryInformation['信贷审批查询记录明细'][0]\n",
+    "\n",
+    "tag = queryCreditApprovalDetail.tbody.children\n",
+    "def get_json(tag):\n",
+    "    result = defaultdict(list)\n",
+    "    key = []\n",
+    "    _num = 0\n",
+    "    for tr in tag:\n",
+    "        _re = []\n",
+    "        index = 0\n",
+    "        if isinstance(tr,bs4.element.Tag):\n",
+    "            tds = tr.find_all('td')\n",
+    "            value = []\n",
+    "    #         key = []\n",
+    "            td_num = len(tds)\n",
+    "            for td in tds:\n",
+    "                for m in td.stripped_strings:\n",
+    "                    if td.get('style') == None:\n",
+    "                        key.append(m)\n",
+    "                    else:\n",
+    "                        value.append(m)\n",
+    "                    index+=1\n",
+    "\n",
+    "            if len(key)!=td_num:\n",
+    "                key = key[len(key)-td_num:]\n",
+    "                _num += 1\n",
+    "            if value:\n",
+    "                result[_num].append(dict(zip(key,value)))\n",
+    "    return dict(result)\n",
+    "get_json(tag)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 117,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'逾期（透支）信息汇总': {'准贷记卡60天以上透支': {'单月最高透支余额': '0',\n",
+       "   '最长透支月数': '0',\n",
+       "   '月份数': '0',\n",
+       "   '账户数': '0'},\n",
+       "  '贷款逾期': {'单月最高逾期总额': '3,119', '最长逾期月数': '1', '月份数': '1', '笔数': '1'},\n",
+       "  '贷记卡逾期': {'单月最高逾期总额': '0', '最长逾期月数': '1', '月份数': '2', '账户数': '2'}}}"
+      ]
+     },
+     "execution_count": 117,
+     "output_type": "execute_result",
+     "metadata": {}
+    }
+   ],
+   "source": [
+    "# 逾期及违约信息概要\n",
+    "def get_information_overdueAndDefault(tag,name):\n",
+    "    \"\"\"逾期及违约信息概要\"\"\"\n",
+    "    result = {}\n",
+    "    tags = tag[name]\n",
+    "    if tags:\n",
+    "        for i,tag in enumerate(tags):\n",
+    "            if isinstance(tag,bs4.element.Tag):\n",
+    "                if tag.td.get('align'):\n",
+    "                    key = tag.td.get_text()\n",
+    "                else:\n",
+    "                    if tag.tbody:\n",
+    "                        table_tag = get_table(tag)\n",
+    "                        _json = get_json_overdueAndDefault(table_tag)\n",
+    "                        result[key] = _json\n",
+    "\n",
+    "    return result\n",
+    "def get_json_overdueAndDefault(tag):\n",
+    "    column = [] #一共几列\n",
+    "    head = []\n",
+    "    key = []\n",
+    "    body = []\n",
+    "    line_id = 0 #行\n",
+    "    row_id = 0 #列\n",
+    "    values = []\n",
+    "    result = {}\n",
+    "    for i,tds in enumerate(tag):\n",
+    "        tds = tds.children\n",
+    "        for ii ,td in enumerate(tds):\n",
+    "            if isinstance(td,bs4.element.Tag):\n",
+    "                if td.get('colspan'):\n",
+    "                    column.append(int(td.get('colspan')))\n",
+    "                    tm = ''\n",
+    "                    for k in td.stripped_strings:\n",
+    "                        tm+=k\n",
+    "                    head.append(tm)\n",
+    "                else:\n",
+    "                    tm = ''\n",
+    "                    for k in td.stripped_strings:\n",
+    "                        tm+=k\n",
+    "                    values.append(tm)\n",
+    "                    row_id += 1\n",
+    "                    if line_id<=1:\n",
+    "                        if row_id % column[line_id] == 0:\n",
+    "                            key.append(values)\n",
+    "                            values = []\n",
+    "#                         print(row_id,line_id,column[line_id])\n",
+    "                    else:\n",
+    "                        if row_id % column[line_id] == 0:\n",
+    "                            body.append(values)\n",
+    "                            values = []\n",
+    "        line_id +=1\n",
+    "    for i,h in enumerate(head):\n",
+    "        result[h] = dict(zip(key[i],body[i]))\n",
+    "    return result\n",
+    "get_information_overdueAndDefault(menu_informationSummary,'逾期及违约信息概要')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 118,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_DebitCard_Details(tag):\n",
+    "        \"\"\"贷记卡明细拆分\"\"\"\n",
+    "        result = {'贷记卡':{}}\n",
+    "        _result = []\n",
+    "        for v in tag:\n",
+    "            _json = {}\n",
+    "            _json['序号'] =v[0]\n",
+    "            _json['描述'] =v[0]+'.'+v[1]\n",
+    "            r =  re.findall(\"(\\d{4}年\\d{1,2}月\\d{1,2}日)(.*?)发放的(.*?)，业务号(.*?)，授信额度[折合人民币]{0,5}(.*?)元，共享授信额度[折合人民币]{0,5}(.*?)元，(.*?)[，|。]{1}截至(\\d{4}年\\d{1,2}月\\d{1,2}日)，(账户状态为“[\\u4E00-\\u9FA5]{1,2}”)*\",v[1])\n",
+    "            if r :\n",
+    "                r = r[0]\n",
+    "                _json['银行名称'] = r[1]\n",
+    "                _json['授信金额'] = r[4]\n",
+    "                _json['共享授信金额'] = r[5]\n",
+    "                _json['授信时间'] = r[0]\n",
+    "                _json['截止时间'] = r[7]\n",
+    "                if r[8]:\n",
+    "                    r_temp = re.findall('账户状态为“(.*?)”',r[8])[0]\n",
+    "                    _json['账户状态 '] = r_temp\n",
+    "\n",
+    "            if v[2] != None:\n",
+    "                table_tag = get_table(v[2])\n",
+    "                \n",
+    "                table_json = get_json_DebitCard(table_tag)\n",
+    "                key_name = table_json.keys()\n",
+    "                plan = ''\n",
+    "                overdue = ''\n",
+    "                temp_json = {}\n",
+    "                for name in key_name:\n",
+    "                    r = re.findall(\"(\\d{4}年\\d{1,2}月)-(\\d{4}年\\d{1,2}月)的([\\S+]*)\",name)\n",
+    "                    if r :\n",
+    "                        if r[0][2] == '还款记录':\n",
+    "                            temp_json['近24个月的还款记录-开始时间'] =r[0][0]\n",
+    "                            temp_json['近24个月的还款记录-截至时间'] =r[0][1]\n",
+    "                            plan = name\n",
+    "                        if r[0][2] == '逾期记录':\n",
+    "                            overdue = name\n",
+    "\n",
+    "                if plan:\n",
+    "                    table_json['近24个月的还款记录-各期还款记录'] = table_json.pop(plan)\n",
+    "                if overdue:\n",
+    "                    del table_json[overdue]\n",
+    "\n",
+    "                if temp_json:\n",
+    "                    table_json.update(temp_json)\n",
+    "\n",
+    "                if '逾期记录' in table_json.keys():\n",
+    "                    table_json['近5年逾期记录'] = table_json.pop('逾期记录')\n",
+    "\n",
+    "                _json.update(table_json)\n",
+    "            _result.append(_json)\n",
+    "        result['贷记卡'] = _result\n",
+    "        return result\n",
+    "\n",
+    "table_tag_new = None\n",
+    "def get_json_DebitCard(tag):\n",
+    "    result = defaultdict(dict)\n",
+    "    key = []\n",
+    "    value = []\n",
+    "    value_list = []\n",
+    "\n",
+    "    temp_key = None\n",
+    "    for i,val in enumerate(tag):\n",
+    "        tds = val.find_all('td')\n",
+    "        # tds_len = len(tds)\n",
+    "        next_sibling = val.next_sibling\n",
+    "        if (next_sibling == ' ' or next_sibling =='\\n' ) and next_sibling!=None:\n",
+    "            next_sibling = val.next_sibling.next_sibling\n",
+    "            # tds_next = next_sibling.find_all('td')\n",
+    "            # tds_next_len = len(next_sibling.find_all('td'))\n",
+    "\n",
+    "        for ii ,td in enumerate(tds):\n",
+    "            #             print(tds_len,tds_next_len,'---1---')\n",
+    "            if isinstance(td,bs4.element.Tag):\n",
+    "                if val.get('align') or td.get('colspan') == '24':\n",
+    "                    tm = ''\n",
+    "                    for k in td.stripped_strings:\n",
+    "                        tm+= k\n",
+    "                    key.append(tm)\n",
+    "                else:\n",
+    "                    tm = ''\n",
+    "                    for k in td.stripped_strings:\n",
+    "                        tm+= k\n",
+    "                    value.append(tm)\n",
+    "                    if len(key) == 0 and temp_key:\n",
+    "                        value_list.append(tm)\n",
+    "                        r = re.findall('\\d{4}年\\d{1,2}月-\\d{4}年\\d{1,2}月的([\\S+]*)',temp_key)\n",
+    "                        if r:\n",
+    "                            r = r[0]\n",
+    "                            if result[temp_key][ii] not in result[r].keys():\n",
+    "                                result[r][result[temp_key][ii]] = []\n",
+    "                            result[r][result[temp_key][ii]].append(value_list[ii])\n",
+    "\n",
+    "        if key and value:\n",
+    "            if len(key) == len(value):\n",
+    "                result.update(dict(zip(key,value)))\n",
+    "            else:\n",
+    "                result.update(dict({key[0]:value}))\n",
+    "                temp_key = key[0]\n",
+    "            key=[]\n",
+    "            value = []\n",
+    "    return dict(result)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 122,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "menu_transactionDetailsType = {}\n",
+    "for k,value in menu_transactionDetails.items():\n",
+    "    menu_transactionDetailsType[k] = get_detailsList(value)\n",
+    "# get_DebitCard_Details(menu_transactionDetailsType['贷款'])\n",
+    "tag = None\n",
+    "for t in menu_transactionDetailsType['贷款']:\n",
+    "    if t[0] == '1':\n",
+    "        tag = t\n",
+    "table_tag = get_table(tag[2])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 123,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[<tr>\n",
+       " <td align=\"center\" class=\"tdStyle\" colspan=\"3\">\n",
+       " <div align=\"center\" class=\"high\"><b><font color=\"#0066cc\"><span class=\"high\">账户状态</span></font></b></div></td>\n",
+       " <td align=\"center\" class=\"tdStyle\" colspan=\"3\">\n",
+       " <div align=\"center\" class=\"high\"><b><font color=\"#0066cc\"><span class=\"high\">五级分类</span></font></b></div></td>\n",
+       " <td align=\"center\" class=\"tdStyle\" colspan=\"3\">\n",
+       " <div align=\"center\" class=\"high\"><b><font color=\"#0066cc\"><span class=\"high\">本金余额</span></font></b></div></td>\n",
+       " <td align=\"center\" class=\"tdStyle\" colspan=\"3\">\n",
+       " <div align=\"center\" class=\"high\"><b><font color=\"#0066cc\"><span class=\"high\">剩余还<br/>款期数</span></font></b></div></td>\n",
+       " <td align=\"center\" class=\"tdStyle\" colspan=\"3\"><b><font color=\"#0066cc\"><span class=\"high\">本月应还款</span></font></b> </td>\n",
+       " <td align=\"center\" class=\"tdStyle\" colspan=\"3\"><b><font color=\"#0066cc\"><span class=\"high\">应还款日</span></font></b> </td>\n",
+       " <td align=\"center\" class=\"tdStyle\" colspan=\"3\"><b><font color=\"#0066cc\"><span class=\"high\">本月实还款</span></font></b> </td>\n",
+       " <td align=\"center\" class=\"tdStyle\" colspan=\"3\" style=\"BORDER-RIGHT-WIDTH: 1px\"><b><font color=\"#0066cc\"><span class=\"high\">最近一次<br/>还款日期</span></font></b> </td></tr>,\n",
+       " <tr>\n",
+       " <td class=\"tdStyle\" colspan=\"3\" style=\"WORD-BREAK: break-all\">\n",
+       " <div align=\"center\" class=\"high\"><font color=\"#0066cc\"><span class=\"high\">正常</span></font></div></td>\n",
+       " <td class=\"tdStyle\" colspan=\"3\" style=\"WORD-BREAK: break-all\">\n",
+       " <div align=\"center\" class=\"high\"><font color=\"#0066cc\"><span class=\"high\">正常</span></font></div></td>\n",
+       " <td class=\"tdStyle\" colspan=\"3\" style=\"WORD-BREAK: break-all\">\n",
+       " <div align=\"center\" class=\"high\"><font color=\"#0066cc\"><span class=\"high\">327,097</span></font></div></td>\n",
+       " <td class=\"tdStyle\" colspan=\"3\" style=\"WORD-BREAK: break-all\">\n",
+       " <div align=\"center\" class=\"high\"><font color=\"#0066cc\"><span class=\"high\">136</span></font></div></td>\n",
+       " <td class=\"tdStyle\" colspan=\"3\" style=\"WORD-BREAK: break-all\">\n",
+       " <div align=\"center\" class=\"high\"><font color=\"#0066cc\"><span class=\"high\">3,119</span></font></div></td>\n",
+       " <td class=\"tdStyle\" colspan=\"3\" style=\"WORD-BREAK: break-all\">\n",
+       " <div align=\"center\" class=\"high\"><font color=\"#0066cc\"><span class=\"high\">2019.04.14</span></font></div></td>\n",
+       " <td class=\"tdStyle\" colspan=\"3\" style=\"WORD-BREAK: break-all\">\n",
+       " <div align=\"center\" class=\"high\"><font color=\"#0066cc\"><span class=\"high\">3,119</span></font></div></td>\n",
+       " <td class=\"tdStyle\" colspan=\"3\" style=\"BORDER-RIGHT-WIDTH: 1px; WORD-BREAK: break-all\">\n",
+       " <div align=\"center\" class=\"high\"><font color=\"#0066cc\"><span class=\"high\">2019.04.14</span></font></div></td></tr>,\n",
+       " <tr>\n",
+       " <td align=\"center\" class=\"tdStyle\" colspan=\"4\">\n",
+       " <div align=\"center\" class=\"high\"><b><font color=\"#0066cc\"><span class=\"high\">当前逾期期数</span></font></b></div></td>\n",
+       " <td align=\"center\" class=\"tdStyle\" colspan=\"4\">\n",
+       " <div align=\"center\" class=\"high\"><b><font color=\"#0066cc\"><span class=\"high\">当前逾期金额</span></font></b></div></td>\n",
+       " <td align=\"center\" class=\"tdStyle\" colspan=\"4\">\n",
+       " <div align=\"center\" class=\"high\"><b><font color=\"#0066cc\"><span class=\"high\">逾期31-60天<br/>未还本金</span></font></b></div></td>\n",
+       " <td align=\"center\" class=\"tdStyle\" colspan=\"4\">\n",
+       " <div align=\"center\" class=\"high\"><b><font color=\"#0066cc\"><span class=\"high\">逾期61－90天<bt>未还本金</bt></span></font></b></div></td>\n",
+       " <td align=\"center\" class=\"tdStyle\" colspan=\"4\">\n",
+       " <div align=\"center\" class=\"high\"><b><font color=\"#0066cc\"><span class=\"high\">逾期91－180天<br/>未还本金</span></font></b></div></td>\n",
+       " <td align=\"center\" class=\"tdStyle\" colspan=\"4\" style=\"BORDER-RIGHT-WIDTH: 1px\">\n",
+       " <div align=\"center\" class=\"high\"><b><font color=\"#0066cc\"><span class=\"high\">逾期180天以<br/>上未还本金</span></font></b></div></td></tr>,\n",
+       " <tr>\n",
+       " <td class=\"tdStyle\" colspan=\"4\">\n",
+       " <div align=\"center\" class=\"high\"><font color=\"#0066cc\"><span class=\"high\">0</span></font></div></td>\n",
+       " <td class=\"tdStyle\" colspan=\"4\">\n",
+       " <div align=\"center\" class=\"high\"><font color=\"#0066cc\"><span class=\"high\">0</span></font></div></td>\n",
+       " <td class=\"tdStyle\" colspan=\"4\">\n",
+       " <div align=\"center\" class=\"high\"><font color=\"#0066cc\"><span class=\"high\">0</span></font></div></td>\n",
+       " <td class=\"tdStyle\" colspan=\"4\">\n",
+       " <div align=\"center\" class=\"high\"><font color=\"#0066cc\"><span class=\"high\">0</span></font></div></td>\n",
+       " <td class=\"tdStyle\" colspan=\"4\">\n",
+       " <div align=\"center\" class=\"high\"><font color=\"#0066cc\"><span class=\"high\">0</span></font></div></td>\n",
+       " <td class=\"tdStyle\" colspan=\"4\" style=\"BORDER-RIGHT-WIDTH: 1px\">\n",
+       " <div align=\"center\" class=\"high\"><font color=\"#0066cc\"><span class=\"high\">0</span></font></div></td></tr>,\n",
+       " <tr>\n",
+       " <td class=\"tdStyle\" colspan=\"24\" style=\"BORDER-RIGHT-WIDTH: 1px\">\n",
+       " <div align=\"center\" class=\"high\"><font color=\"#0066cc\"><strong><b>2017年05月-2019年04月的还款记录</b></strong></font></div></td></tr>,\n",
+       " <tr>\n",
+       " <td class=\"tdStyle\" width=\"37\">\n",
+       " <div align=\"center\" class=\"high\"><font color=\"#0066cc\"><span class=\"high\">N</span></font></div></td>\n",
+       " <td class=\"tdStyle\" width=\"37\">\n",
+       " <div align=\"center\" class=\"high\"><font color=\"#0066cc\"><span class=\"high\">N</span></font></div></td>\n",
+       " <td class=\"tdStyle\" width=\"38\">\n",
+       " <div align=\"center\" class=\"high\"><font color=\"#0066cc\"><span class=\"high\">N</span></font></div></td>\n",
+       " <td class=\"tdStyle\" width=\"38\">\n",
+       " <div align=\"center\" class=\"high\"><font color=\"#0066cc\"><span class=\"high\">N</span></font></div></td>\n",
+       " <td class=\"tdStyle\" width=\"38\">\n",
+       " <div align=\"center\" class=\"high\"><font color=\"#0066cc\"><span class=\"high\">N</span></font></div></td>\n",
+       " <td class=\"tdStyle\" width=\"38\">\n",
+       " <div align=\"center\" class=\"high\"><font color=\"#0066cc\"><span class=\"high\">N</span></font></div></td>\n",
+       " <td class=\"tdStyle\" width=\"38\">\n",
+       " <div align=\"center\" class=\"high\"><font color=\"#0066cc\"><span class=\"high\">N</span></font></div></td>\n",
+       " <td class=\"tdStyle\" width=\"38\">\n",
+       " <div align=\"center\" class=\"high\"><font color=\"#0066cc\"><span class=\"high\">N</span></font></div></td>\n",
+       " <td class=\"tdStyle\" width=\"38\">\n",
+       " <div align=\"center\" class=\"high\"><font color=\"#0066cc\"><span class=\"high\">N</span></font></div></td>\n",
+       " <td class=\"tdStyle\" width=\"38\">\n",
+       " <div align=\"center\" class=\"high\"><font color=\"#0066cc\"><span class=\"high\">N</span></font></div></td>\n",
+       " <td class=\"tdStyle\" width=\"38\">\n",
+       " <div align=\"center\" class=\"high\"><font color=\"#0066cc\"><span class=\"high\">N</span></font></div></td>\n",
+       " <td class=\"tdStyle\" width=\"38\">\n",
+       " <div align=\"center\" class=\"high\"><font color=\"#0066cc\"><span class=\"high\">N</span></font></div></td>\n",
+       " <td class=\"tdStyle\" width=\"38\">\n",
+       " <div align=\"center\" class=\"high\"><font color=\"#0066cc\"><span class=\"high\">N</span></font></div></td>\n",
+       " <td class=\"tdStyle\" width=\"38\">\n",
+       " <div align=\"center\" class=\"high\"><font color=\"#0066cc\"><span class=\"high\">N</span></font></div></td>\n",
+       " <td class=\"tdStyle\" width=\"38\">\n",
+       " <div align=\"center\" class=\"high\"><font color=\"#0066cc\"><span class=\"high\">N</span></font></div></td>\n",
+       " <td class=\"tdStyle\" width=\"38\">\n",
+       " <div align=\"center\" class=\"high\"><font color=\"#0066cc\"><span class=\"high\">N</span></font></div></td>\n",
+       " <td class=\"tdStyle\" width=\"38\">\n",
+       " <div align=\"center\" class=\"high\"><font color=\"#0066cc\"><span class=\"high\">N</span></font></div></td>\n",
+       " <td class=\"tdStyle\" width=\"38\">\n",
+       " <div align=\"center\" class=\"high\"><font color=\"#0066cc\"><span class=\"high\">N</span></font></div></td>\n",
+       " <td class=\"tdStyle\" width=\"38\">\n",
+       " <div align=\"center\" class=\"high\"><font color=\"#0066cc\"><span class=\"high\">N</span></font></div></td>\n",
+       " <td class=\"tdStyle\" width=\"38\">\n",
+       " <div align=\"center\" class=\"high\"><font color=\"#0066cc\"><span class=\"high\">N</span></font></div></td>\n",
+       " <td class=\"tdStyle\" width=\"38\">\n",
+       " <div align=\"center\" class=\"high\"><font color=\"#0066cc\"><span class=\"high\">N</span></font></div></td>\n",
+       " <td class=\"tdStyle\" width=\"38\">\n",
+       " <div align=\"center\" class=\"high\"><font color=\"#0066cc\"><span class=\"high\">N</span></font></div></td>\n",
+       " <td class=\"tdStyle\" width=\"38\">\n",
+       " <div align=\"center\" class=\"high\"><font color=\"#0066cc\"><span class=\"high\">N</span></font></div></td>\n",
+       " <td class=\"tdStyle\" style=\"BORDER-RIGHT-WIDTH: 1px\" width=\"28\">\n",
+       " <div align=\"center\" class=\"high\"><font color=\"#0066cc\"><span class=\"high\">N</span></font></div></td></tr>,\n",
+       " <tr>\n",
+       " <td class=\"tdStyle\" colspan=\"24\" style=\"BORDER-RIGHT-WIDTH: 1px\">\n",
+       " <div align=\"center\" class=\"high\"><b><font color=\"#0066cc\"><span class=\"high\">2015年08月-2017年04月的逾期记录 </span></font></b></div></td></tr>,\n",
+       " <tr>\n",
+       " <td class=\"tdStyle\" colspan=\"4\">\n",
+       " <div align=\"center\" class=\"high\"><b><font color=\"#0066cc\"><span class=\"high\">逾期月份</span></font></b></div></td>\n",
+       " <td class=\"tdStyle\" colspan=\"4\">\n",
+       " <div align=\"center\" class=\"high\"><b><font color=\"#0066cc\"><span class=\"high\">逾期持续月数</span></font></b></div></td>\n",
+       " <td class=\"tdStyle\" colspan=\"4\">\n",
+       " <div align=\"center\" class=\"high\"><b><font color=\"#0066cc\"><span class=\"high\">逾期金额</span></font></b></div></td>\n",
+       " <td class=\"tdStyle\" colspan=\"4\">\n",
+       " <div align=\"center\" class=\"high\"><b><font color=\"#0066cc\"><span class=\"high\">逾期月份</span></font></b></div></td>\n",
+       " <td class=\"tdStyle\" colspan=\"4\">\n",
+       " <div align=\"center\" class=\"high\"><b><font color=\"#0066cc\"><span class=\"high\">逾期持续月数</span></font></b></div></td>\n",
+       " <td class=\"tdStyle\" colspan=\"4\" style=\"BORDER-RIGHT-WIDTH: 1px\">\n",
+       " <div align=\"center\" class=\"high\"><b><font color=\"#0066cc\"><span class=\"high\">逾期金额</span></font></b></div></td></tr>,\n",
+       " <tr>\n",
+       " <td class=\"tdStyle\" colspan=\"4\">\n",
+       " <div align=\"center\" class=\"high\"><font color=\"#0066cc\"><span class=\"high\">2016.12</span></font></div></td>\n",
+       " <td class=\"tdStyle\" colspan=\"4\">\n",
+       " <div align=\"center\" class=\"high\"><font color=\"#0066cc\"><span class=\"high\">1</span></font></div></td>\n",
+       " <td class=\"tdStyle\" colspan=\"4\">\n",
+       " <div align=\"center\" class=\"high\"><font color=\"#0066cc\"><span class=\"high\">3,119</span></font></div></td>\n",
+       " <td class=\"tdStyle\" colspan=\"4\">\n",
+       " <div align=\"center\" class=\"high\"><font color=\"#0066cc\"><span class=\"high\">--</span></font></div></td>\n",
+       " <td class=\"tdStyle\" colspan=\"4\">\n",
+       " <div align=\"center\" class=\"high\"><font color=\"#0066cc\"><span class=\"high\">--</span></font></div></td>\n",
+       " <td class=\"tdStyle\" colspan=\"4\" style=\"BORDER-RIGHT-WIDTH: 1px\">\n",
+       " <div align=\"center\" class=\"high\"><font color=\"#0066cc\"><span class=\"high\">--</span></font></div></td></tr>]"
+      ]
+     },
+     "execution_count": 123,
+     "output_type": "execute_result",
+     "metadata": {}
+    }
+   ],
+   "source": [
+    "table_tag"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 310,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "IndexError",
+     "evalue": "list index out of range",
+     "output_type": "error",
+     "traceback": [
+      "---------------------------------------------------------------------------",
+      "IndexError                                Traceback (most recent call last)",
+      "<ipython-input-310-6f3d66682be4> in <module>()\n     65 #                 _k = []\n     66     return dict(result)\n---> 67 get_json_DebitCard(table_tag)\n",
+      "<ipython-input-310-6f3d66682be4> in get_json_DebitCard(tag)\n     35                         if r:\n     36                             r = r[0]\n---> 37                             if result[temp_key][ii] not in result[r].keys():\n     38                                 result[r][result[temp_key][ii]] = []\n     39                             result[r][result[temp_key][ii]].append(value_list[ii])\n",
+      "IndexError: list index out of range"
+     ]
+    }
+   ],
+   "source": [
+    "def get_json_DebitCard(tag):\n",
+    "    result = defaultdict(dict)\n",
+    "    key = []\n",
+    "    value = []\n",
+    "    value_list = []\n",
+    "    _k = []\n",
+    "    _v = []\n",
+    "\n",
+    "    temp_key = None\n",
+    "    for i,val in enumerate(tag):\n",
+    "        tds = val.find_all('td')\n",
+    "        # tds_len = len(tds)\n",
+    "#         next_sibling = val.next_sibling\n",
+    "#         if (next_sibling == ' ' or next_sibling =='\\n' ) and next_sibling!=None:\n",
+    "#             next_sibling = val.next_sibling.next_sibling\n",
+    "#             # tds_next = next_sibling.find_all('td')\n",
+    "#             # tds_next_len = len(next_sibling.find_all('td'))\n",
+    "\n",
+    "        for ii ,td in enumerate(tds):\n",
+    "            #             print(tds_len,tds_next_len,'---1---')\n",
+    "            if isinstance(td,bs4.element.Tag):\n",
+    "                if td.get('align') or td.get('colspan') == '24':\n",
+    "                        tm = ''\n",
+    "                        for k in td.stripped_strings:\n",
+    "                            tm+= k\n",
+    "                        key.append(tm)\n",
+    "                    else:\n",
+    "                        tm = ''\n",
+    "                        for k in td.stripped_strings:\n",
+    "                            tm+= k\n",
+    "                        value.append(tm)\n",
+    "                        if len(key) == 0 and temp_key:\n",
+    "                            value_list.append(tm)\n",
+    "                            r = re.findall('\\d{4}年\\d{1,2}月-\\d{4}年\\d{1,2}月的([\\S+]*)',temp_key)\n",
+    "                            if r:\n",
+    "                                r = r[0]\n",
+    "                                if result[temp_key][ii] not in result[r].keys():\n",
+    "                                    result[r][result[temp_key][ii]] = []\n",
+    "                                result[r][result[temp_key][ii]].append(value_list[ii])\n",
+    "\n",
+    "            if key and value:\n",
+    "                if len(key) == len(value):\n",
+    "                    result.update(dict(zip(key,value)))\n",
+    "                else:\n",
+    "                    result.update(dict({key[0]:value}))\n",
+    "                    temp_key = key[0]\n",
+    "                key=[]\n",
+    "                value = []\n",
+    "                        \n",
+    "                      \n",
+    "                        \n",
+    "#         if key and value_list:\n",
+    "#             print(len(next_sibling.find_all('td')))\n",
+    "#             print(next_sibling.find_all('td'))\n",
+    "#             key = []\n",
+    "#             value_list = []\n",
+    "#         if len(key)==0 and len(value_list)==0:\n",
+    "#             if value and len(value)<= len(tds):\n",
+    "#                 _k=value\n",
+    "#             else :\n",
+    "#                 _v = value[len(tds):]\n",
+    "#                 result.update(dict(zip(_k,_v)))\n",
+    "                \n",
+    "#                 value = []\n",
+    "#                 _k = []\n",
+    "#     return dict(result)\n",
+    "get_json_DebitCard(table_tag)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 312,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'2015年08月-2017年04月的逾期记录': ['逾期月份',\n",
+       "  '逾期持续月数',\n",
+       "  '逾期金额',\n",
+       "  '逾期月份',\n",
+       "  '逾期持续月数',\n",
+       "  '逾期金额'],\n",
+       " '2017年05月-2019年04月的还款记录': ['N',\n",
+       "  'N',\n",
+       "  'N',\n",
+       "  'N',\n",
+       "  'N',\n",
+       "  'N',\n",
+       "  'N',\n",
+       "  'N',\n",
+       "  'N',\n",
+       "  'N',\n",
+       "  'N',\n",
+       "  'N',\n",
+       "  'N',\n",
+       "  'N',\n",
+       "  'N',\n",
+       "  'N',\n",
+       "  'N',\n",
+       "  'N',\n",
+       "  'N',\n",
+       "  'N',\n",
+       "  'N',\n",
+       "  'N',\n",
+       "  'N',\n",
+       "  'N'],\n",
+       " '五级分类': '正常',\n",
+       " '剩余还款期数': '136',\n",
+       " '应还款日': '2019.04.14',\n",
+       " '当前逾期期数': '0',\n",
+       " '当前逾期金额': '0',\n",
+       " '最近一次还款日期': '2019.04.14',\n",
+       " '本月实还款': '3,119',\n",
+       " '本月应还款': '3,119',\n",
+       " '本金余额': '327,097',\n",
+       " '账户状态': '正常',\n",
+       " '逾期180天以上未还本金': '0',\n",
+       " '逾期31-60天未还本金': '0',\n",
+       " '逾期61－90天未还本金': '0',\n",
+       " '逾期91－180天未还本金': '0',\n",
+       " '逾期记录': {'逾期持续月数': ['1', '--'],\n",
+       "  '逾期月份': ['2016.12', '--'],\n",
+       "  '逾期金额': ['3,119', '--']}}"
+      ]
+     },
+     "execution_count": 312,
+     "output_type": "execute_result",
+     "metadata": {}
+    }
+   ],
+   "source": [
+    "def get_json_DebitCard(tag):\n",
+    "    result = defaultdict(dict)\n",
+    "    key = []\n",
+    "    value = []\n",
+    "    value_list = []\n",
+    "\n",
+    "    temp_key = None\n",
+    "    for i,val in enumerate(tag):\n",
+    "        tds = val.find_all('td')\n",
+    "        # tds_len = len(tds)\n",
+    "        # next_sibling = val.next_sibling\n",
+    "        # if (next_sibling == ' ' or next_sibling =='\\n' ) and next_sibling!=None:\n",
+    "        #     next_sibling = val.next_sibling.next_sibling\n",
+    "            # tds_next = next_sibling.find_all('td')\n",
+    "            # tds_next_len = len(next_sibling.find_all('td'))\n",
+    "\n",
+    "        for ii ,td in enumerate(tds):\n",
+    "            #             print(tds_len,tds_next_len,'---1---')\n",
+    "            if isinstance(td,bs4.element.Tag):\n",
+    "                if td.get('align') or td.get('colspan') == '24':\n",
+    "                    tm = ''\n",
+    "                    for k in td.stripped_strings:\n",
+    "                        tm+= k\n",
+    "                    key.append(tm)\n",
+    "                else:\n",
+    "                    tm = ''\n",
+    "                    for k in td.stripped_strings:\n",
+    "                        tm+= k\n",
+    "                    value.append(tm)\n",
+    "                    if len(key) == 0 and temp_key:\n",
+    "                        value_list.append(tm)\n",
+    "                        r = re.findall('\\d{4}年\\d{1,2}月-\\d{4}年\\d{1,2}月的([\\S+]*)',temp_key)\n",
+    "                        if r:\n",
+    "                            r = r[0]\n",
+    "                            if result[temp_key][ii] not in result[r].keys():\n",
+    "                                result[r][result[temp_key][ii]] = []\n",
+    "                            result[r][result[temp_key][ii]].append(value_list[ii])\n",
+    "\n",
+    "        if key and value:\n",
+    "            if len(key) == len(value):\n",
+    "                result.update(dict(zip(key,value)))\n",
+    "            else:\n",
+    "                result.update(dict({key[0]:value}))\n",
+    "                temp_key = key[0]\n",
+    "            key=[]\n",
+    "            value = []\n",
+    "    return dict(result)\n",
+    "get_json_DebitCard(table_tag)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 315,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>逾期持续月数</th>\n",
+       "      <th>逾期月份</th>\n",
+       "      <th>逾期金额</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>2016.12</td>\n",
+       "      <td>3,119</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ]
+     },
+     "output_type": "execute_result",
+     "metadata": {}
+    }
+   ],
+   "source": [
+    "aa = [{'逾期持续月数': '1', '逾期月份': '2016.12', '逾期金额': '3,119'},{'逾期持续月数':2}]\n",
+    "\n",
+    "pd.DataFrame("
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 317,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<filter at 0x10b612048>"
+      ]
+     },
+     "execution_count": 317,
+     "output_type": "execute_result",
+     "metadata": {}
+    }
+   ],
+   "source": [
+    "aa =  '3,119'\n",
+    "filter (lambda x:x,aa)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3.0
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.0"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
\ No newline at end of file

utils/JsonUtil.py

+# -*- coding:utf-8 -*-
+
+'''
+json 组装
+'''
+import json
+
+
+## 常数变量定义
+## json 返回中的 错误码定义
+class Constants:
+    Code_Success = 200
+    Msg_Success = 'SUCCESS'
+
+    Code_Fail = 1
+    Msg_Fail = '失败'
+
+    Code_Param_Error = -1
+    Msg_Param_Error = '参数错误'
+
+    Code_LoginToken_Auth_Error = -2
+    Msg_LoginToken_Auth_Error = 'token登陆认证错误'
+
+
+    Code_Error = -3
+    Msg_Error = '数据异常'
+
+    Code_Params_Error = -4
+    Msg_Params_Error = '{0} is error,{0} is {1}'
+
+    Code_File_Error = -5
+    Msg_File_Error = '文件读取错误'
+
+    Code_Analysis_Error = -6
+    Msg_Analysis_Error = 'html 解析错误'
+
+    Code_Error_Value = 506
+    Msg_Error_Value = '没找到指定参数的返回值'
+
+
+
+def build_json(code=None,report=None,mssage=None,**kwargs):
+
+    if report == None:
+        report = []
+
+    body = {}
+    for key,value in kwargs.items():
+        body[str(key)] = value
+    try :
+        if body:
+            ddata = {'code':code,'mssage':mssage,'body':body}
+        else:
+            ddata = {'code':code,'mssage':mssage,'result':report}
+    except Exception as e:
+        print(e.args)
+
+    return json.dumps(ddata,ensure_ascii=False)
+
+# businessType=int(_business_type), orderId=_orderId, loanId=_loanId,uuid = _uuid,
+# data=_result, flag=True)
+#
+# def build_json_feature (features=None, code=Constants.Code_Success, msg=Constants.Msg_Success):
+#
+#     if data == None:
+#         data = []
+#     ddata = dict(code=code, businessCode=code, msg=msg, features=features)
+#
+# def build_json_feature_two(data):
+#     return json.dumps(data,ensure_ascii=False)
+#
+# """
+# 只返回 错误码 + 错误提示
+# """
+#
+#
+# def build_json(code, msg):
+#     ddata = dict(code=code, msg=msg, businessCode=code)
+#     # return json.dumps(ddata,encoding='UTF-8',ensure_ascii=False) #python2
+#     return json.dumps(ddata, ensure_ascii=False)  # python3
+#
+#
+# """
+# 错误码 默认为 成功；
+# data may be dict array
+# """
+#
+#
+# def build_json_with_data(data=None, code=Constants.Code_Success, msg=Constants.Msg_Success):
+#     if data == None:
+#         data = []
+#     ddata = dict(code=code, businessCode=code, msg=msg, data=data)
+#     # return json.dumps(ddata,encoding='UTF-8',ensure_ascii=False) # python2
+#     return json.dumps(ddata, ensure_ascii=False)  # python3
+#
+#
+# def build_json_with_data_page(data=None, total=0, page_no=1, page_size=20, code=Constants.Code_Success,
+#                               msg=Constants.Msg_Success):
+#     page_no = int(page_no)
+#     page_size = int(page_size)
+#     total = int(total)
+#     if total % page_size == 0:
+#         _page_total = total / page_size
+#     else:
+#         _page_total = total / page_size + 1
+#     # ==没有查询到数据，则data 为空
+#     if total == 0:
+#         data = []
+#     _data = dict(data=data, page_no=int(page_no), page_size=int(page_size), page_total=int(_page_total),
+#                  total=int(total))
+#     ddata = dict(code=code, businessCode=code, msg=msg, data=_data)
+#     # return json.dumps(ddata,encoding='UTF-8',ensure_ascii=False) # python2
+#     return json.dumps(ddata, ensure_ascii=False)  # python3
+#
+#
+# def build_json_with_block(data=None, code=Constants.Code_Success, msg=Constants.Msg_Success):
+#     ddata = dict(code=code, businessCode=code, msg=msg, data=data)
+#     # return json.dumps(ddata,encoding='UTF-8',ensure_ascii=False) # python2
+#     return json.dumps(ddata, ensure_ascii=False)  # python3
+#
+#
+# """
+# 转换为 dict 对象; 直接 json.key 获取数据
+# 如果data 为空，返回一个空的data数据
+# """
+#
+#
+# def str_parse_json(data):
+#     if any(data):
+#         return json.loads(data, encoding='UTF-8')
+#     return dict()