设置下载json 下载

config/settings.py

@@ -7,4 +7,5 @@ FEATURE_HOST_MY = 'http://localhost:23010'
 
 
 url_reportanalysis = '/report'
+TO_JSON = FILE_PATH+'/to_json'
 

handler/ReportAnalysis_Handler.py

@@ -3,6 +3,8 @@
 import threading
 from utils import JsonUtil
 from handler.Base_Handler import BaseHandler
+import json
+from config import settings
 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
@@ -14,7 +16,7 @@ from service.InitHtml_Service import InitHtml # 初始化HTML
 class ReportAnalysis(BaseHandler):
     def post(self):
         self._filepath = self.get_argument('filepath', default=None)
-
+        self._isdownload = self.get_argument('isdownload',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)))
@@ -54,6 +56,13 @@ class ReportAnalysis(BaseHandler):
                     # QueryInfomation(html.menu_dict)
                     result = Result.get_result()
                     Result.clear_result()
+
+                    # '/Users/zhangpengcheng/Documents/量化派代码管理/credit-report-api/html/data.json'
+                    if self._isdownload:
+                        with open(settings.TO_JSON+'/'+self._filepath.split('/')[-1]+'.json', 'w',encoding='utf8') as file_obj:
+                            file_obj.write(json.dumps(result,ensure_ascii=False))
+                            file_obj.close()
+
                     self.write(JsonUtil.build_json(report = result,
                                                    code=JsonUtil.Constants.Code_Success,
                                                    mssage=JsonUtil.Constants.Msg_Success))

requirements.txt

 tornado==5.0.1
-logging
 redis
 PyMysql==0.8.0
 pandas==0.22.0

startup.py

@@ -17,7 +17,7 @@ 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("port", default=20010, help="run on the given port ", type=int)
 define("log_path", default='/tmp', help="log path ", type=str)
 
 class LogFormatter(tornado.log.LogFormatter):
@@ -36,19 +36,19 @@ def apps():
 
 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()
+    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(20011)
+    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()
+
+    # 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')]"))
-
-