diff --git a/.gitignore b/.gitignore
index 192dba4..3153580 100755
--- a/.gitignore
+++ b/.gitignore
@@ -1,4 +1,5 @@
 __pycache__/
 webpages/*
 *.html
-*.txt
\ No newline at end of file
+*.txt
+*.log
\ No newline at end of file
diff --git a/README.md b/README.md
index 14af145..b1e28ff 100755
--- a/README.md
+++ b/README.md
@@ -1,47 +1,59 @@
-#### Tips
+# 开源web知识图谱项目
 
+- 爬取百度百科中文页面
+- 解析三元组和网页内容
+- 构建中文知识图谱
+- 构建百科bot（构建中）
+
+##### update 20191121
+
+- 迁移代码到爬虫框架scrapy
+- 优化了抽取部分代码
+- 数据持久化迁移到mongodb
+- 修复chatbot失效问题
+- 开放neo4j后台界面，可以查看知识图谱成型效果
+
+##### Tips
 
 - 如果是项目问题，请提issue。
 - 如果涉及到不方便公开的，请发邮件。
 - ChatBot请访问[链接](http://bot.rubenxiao.com/)
-
-# 开源web知识图谱项目
-
-- 爬取百度百科中文页面
-- 抽取[100W+个三元组](https://raw.githubusercontent.com/lixiang0/WEB_KG/master/kg/triples.txt)
-- 构建中文知识图谱
+- 成型的百科知识图谱访问[链接](http://kg.rubenxiao.com/)，用户名：neo4j,密码：123。
 
 ### 环境
 
 - python 3.6
-- requests:网络请求
 - re:url正则匹配
-- bs4:网页解析
-- pickle:进度保存
-- threading:多线程
+- scrapy:网页爬虫和网页解析
 - neo4j:知识图谱图数据库,安装可以参考[链接](http://blog.rubenxiao.com/posts/install-neo4j.html)
 - pip install neo4j-driver：neo4j python驱动
+- pip install pymongodb：mongodb的python支持
+- mongodb数据库：安装参考[链接](https://docs.mongodb.com/manual/tutorial/install-mongodb-on-ubuntu/)
 
 
-### 代码目錄
+### 代码执行：
 
-- spider/ 抓取原始网页
-- ie/ 从网页中解析正文，从正文中抽取结构化信息
-- kg/ 抽取三元組，存入neo4j数据库
+```
+cd WEB_KG/baike
+scrapy crawl baike
+```
 
-
-### 代码执行顺序：
-
-
-- 1.spider目录下执行：python spider_main.py
-- 2.ie目录下执行：python extract-para.py
-- 3.ie目录下执行：python extract-table.py
-- 4.kg目录下执行：python build-triple-from-table.py
-- 5.kg目录下执行：python insert_to_neo4j.py
-
-第二步本项目可以不执行。
+执行界面(按ctrl+c停止)：
+![](./imgs/kg5.png)
 
 ### 知识图谱效果图
 
-![](./kg/kg.png)
+![](./imgs/kg.png)
+
+### mongodb存储的网页内容
+
+![](./imgs/kg3.png)
+
+### mongodb存储的三元组
+
+![](./imgs/kg4.png)
+
+### neo4j后台界面
+
+![](./imgs/kg2.png)
 
diff --git a/baike/spiders/baike.py b/baike/spiders/baike.py
index 092c171..f284d71 100644
--- a/baike/spiders/baike.py
+++ b/baike/spiders/baike.py
@@ -8,8 +8,13 @@ import re
 import pymongo
 from scrapy.selector import Selector
 from neo4j.v1 import GraphDatabase
-
-
+import logging
+import time
+logfile_name = time.ctime(time.time()).replace(' ', '_')
+if not os.path.exists('logs/'):
+    os.mkdir('logs/')
+logging.basicConfig(filename=f'logs/{logfile_name}.log', filemode='a+',
+                    format='%(levelname)s - %(asctime)s - %(message)s', datefmt='%d-%b-%y %H:%M:%S')
 class BaikeSpider(scrapy.Spider):
     name = 'baike'
     allowed_domains = ['baike.baidu.com']
@@ -59,29 +64,35 @@ class BaikeSpider(scrapy.Spider):
 
         # 处理三元组
         entity = ''.join(response.xpath(
-            '//h1/text()').extract()).replace('/', '')
+            '//h1/text()').getall()).replace('/', '')
         attrs = response.xpath(
-            '//dt[contains(@class,"basicInfo-item name")]').extract()
+            '//dt[contains(@class,"basicInfo-item name")]').getall()
         values = response.xpath(
-            '//dd[contains(@class,"basicInfo-item value")]').extract()
+            '//dd[contains(@class,"basicInfo-item value")]').getall()
+        if len(attrs)!= len(values):
+            return
         with self.driver.session() as session:
-            for i, attr in enumerate(attrs):
+            try:
+                for attr,value in zip(attrs,values):
                     # attr
-                temp = Selector(text=attr).xpath(
-                    '//dt/text()|//dt/a/text()').extract()
-                attr = ''.join(temp).replace('\n', '').replace('：', '').replace(
-                    ':', '').replace('\xa0', '').replace(' ', '').replace('【', '').replace('】', '')
-                # value
-                temp = Selector(text=values[i]).xpath(
-                    '//dd/text()|//dd/a/text()').extract()
-                value = ''.join(temp).replace('\n', '')
-                try:
-                    self.db_triples.insert_one({
-                        "_id": entity+'_'+attr+'_'+value,
-                        "item_name": entity,
-                        "attr": attr,
-                        "value": value, }
-                    )
-                except pymongo.errors.DuplicateKeyError:
-                    pass
-                session.write_transaction(self.add_node, entity, attr, value)
+                    temp = Selector(text=attr).xpath(
+                        '//dt//text()').getall()
+                    attr = ''.join(temp).replace('\xa0', '')
+                    # value
+                    values = Selector(text=value).xpath(
+                        '//dd/text()|//dd/a//text()').getall()
+                    for value in values:
+                        try:
+                            value=value.replace('\n','')
+                            logging.warning(entity+'_'+attr+'_'+value)
+                            self.db_triples.insert_one({
+                                "_id": entity+'_'+attr+'_'+value,
+                                "item_name": entity,
+                                "attr": attr,
+                                "value": value, }
+                            )
+                        except pymongo.errors.DuplicateKeyError:
+                            pass
+                        session.write_transaction(self.add_node, entity, attr, value)
+            except Exception:
+                logging.error('\n---'.join(attrs)+'\n_________________'+'\n---'.join(values))
\ No newline at end of file
diff --git a/imgs/kg.png b/imgs/kg.png
new file mode 100644
index 0000000..0372e42
Binary files /dev/null and b/imgs/kg.png differ
diff --git a/imgs/kg2.png b/imgs/kg2.png
new file mode 100644
index 0000000..58af85e
Binary files /dev/null and b/imgs/kg2.png differ
diff --git a/imgs/kg3.png b/imgs/kg3.png
new file mode 100644
index 0000000..d4df25c
Binary files /dev/null and b/imgs/kg3.png differ
diff --git a/imgs/kg4.png b/imgs/kg4.png
new file mode 100644
index 0000000..add1510
Binary files /dev/null and b/imgs/kg4.png differ
diff --git a/imgs/kg5.png b/imgs/kg5.png
new file mode 100644
index 0000000..6510d03
Binary files /dev/null and b/imgs/kg5.png differ