diff --git a/README.md b/README.md
index 8df0858..9540b6e 100644
--- a/README.md
+++ b/README.md
@@ -16,3 +16,6 @@
 **技术选型**
 - python version  2.7.11
 - python version  3.4.0
+
+
+http://ns.giit.us/htm_data/7/1706/2470604.html
\ No newline at end of file
diff --git a/WebScrapingWithPython/python-scraping b/WebScrapingWithPython/python-scraping
new file mode 160000
index 0000000..cec78b7
--- /dev/null
+++ b/WebScrapingWithPython/python-scraping
@@ -0,0 +1 @@
+Subproject commit cec78b7cadf16f45249c443248f918d6efaee6d3
diff --git a/WebScrapingWithPython/remark b/WebScrapingWithPython/remark
index a2051d1..6df378d 100644
--- a/WebScrapingWithPython/remark
+++ b/WebScrapingWithPython/remark
@@ -62,3 +62,31 @@ Tesseract 文档： https://github.com/tesseract-ocr/tesseract/wiki
 
 
 EditThis cookie http://www.editthiscookie.com
+
+
+分布式计算    distributed computing
+Tor代理服务器
+    
+PySocks python 代理服务器通信模埠  https://pypi.python.org/pypi/PySocks
+
+搜索引擎优化：  Search Engine Optimization,SEO
+    robots.txt
+
+机器人排除标准：  Robots Exclusion Standard    robots.txt
+
+
+#
+# robots.txt for PHPWIND BOARD
+# Version 5.x
+#
+
+User-agent: *
+Disallow: /admin/
+Disallow: /require/
+Disallow: /hack/
+Disallow: /attachment/
+Disallow: /images/
+Disallow: /data/
+Disallow: /ipdata/
+Disallow: /template/
+
diff --git a/WebScrapingWithPython/yaoshe1/index.py b/WebScrapingWithPython/yaoshe1/index.py
new file mode 100644
index 0000000..53368a4
--- /dev/null
+++ b/WebScrapingWithPython/yaoshe1/index.py
@@ -0,0 +1,115 @@
+#!/usr/bin/python
+# -*- coding: UTF-8 -*-
+# @Filename: index
+# @Date    : 2017-09-14 23:15
+# @Author  : zzl
+"""
+   python_version  2.7.11
+
+   import package:   bs4,requests,html5lib
+
+"""
+from urllib2 import urlopen
+# from urllib2 import open
+from bs4 import BeautifulSoup
+import requests
+# import urllib
+import re
+import os
+
+downLoadFile = 'D:\\happy\\yaoshe6' ##要下载到的目录
+isdebug = True
+
+
+def getFile(url):
+    if(requests.get(url).status_code == 404):
+        print('这是个错误网址')
+        return []
+    #print ('正在打开 ',url)
+    file_name = url.split('/')[-1]
+    file_s = downLoadFile  + file_name
+    if os.path.exists(file_s):
+        print("file exists = " + file_name)
+        return
+    u = urlopen(url)
+    # u = requests.urlopen(url)
+
+    f = open(file_s, 'wb')
+
+    block_sz = 8192
+    while True:
+        buffer = u.read(block_sz)
+        if not buffer:
+            break
+
+        f.write(buffer)
+    f.close()
+    print("Sucessful to download = " + file_name)
+
+def getHtml(url):
+    page = urlopen(url)
+    html = page.read()
+    page.close()
+    return html
+
+# compile the regular expressions and find
+# all stuff we need
+def getUrl(html):
+    reg = r'(?:href|HREF)="?((?:http://)?.+?\.pdf)'
+    url_re = re.compile(reg)
+    url_lst = re.findall(url_re,html)
+    return(url_lst)
+
+def opeVideoUrl(url):
+    html = urlopen(url).read()
+    ss = html.replace(" ","")
+    urls = re.findall(r"(http://www.yaoshe2.com/get_file/.*?mp4).*?",ss,re.I)
+    for i in urls:
+        print(i)
+        # try:
+        getFile(i);
+        # except Exception,e:
+        #     print e.message
+    # else:
+        # print 'this is over'
+    # bsObj = BeautifulSoup(html, "html5lib")
+    # print bsObj
+
+def eachLatestUpdates():
+    currPage = 2
+    print "eachLatestUpdates"
+    while currPage < 100:
+        startOpenPage("http://www.yaoshe6.com/latest-updates/" + str(currPage) + "/")
+        currPage = currPage + 1
+
+
+
+
+def startOpenPage(url):
+    print "base url  ==============  " + url
+    html = urlopen(url)
+    if isdebug == True:
+        print(html.read())
+    bsObj = BeautifulSoup(html, "html5lib")
+    itemsDivObj = bsObj.findAll("div",{"class":re.compile("^(item)((?!:).)*$")})
+    print "itemsDivObj div  item  = ",len(itemsDivObj)
+    for obj in itemsDivObj:
+        videosObjs = obj.findAll("a",{"href":re.compile("^(http://www.yaoshe6.com/videos/)((?!:).)*$")})
+        print "videosObjs a  videos  = ",len(videosObjs)
+        if len(videosObjs) != 0:
+            strHref = videosObjs[0].attrs["href"]
+            # print strHref
+            count = 0
+            while count < 1:
+                count = count+1
+                print("url = " + strHref)
+                opeVideoUrl(strHref)
+
+
+startOpenPage("http://www.yaoshe6.com/")
+eachLatestUpdates()
+
+
+
+
+
diff --git a/WebScrapingWithPython/yaoshe1/index2.py b/WebScrapingWithPython/yaoshe1/index2.py
new file mode 100644
index 0000000..2d4c4b3
--- /dev/null
+++ b/WebScrapingWithPython/yaoshe1/index2.py
@@ -0,0 +1,74 @@
+#!/usr/bin/python
+# -*- coding: UTF-8 -*-
+# @Filename: index
+# @Date    : 2017-09-14 23:15
+# @Author  : zzl
+"""
+   python_version  2.7.11
+"""
+from urllib2 import urlopen
+# from urllib2 import open
+from bs4 import BeautifulSoup
+# import urllib
+import re
+
+def getFile(url):
+    file_name = url.split('/')[-1]
+    u = urlopen(url)
+    f = open(file_name, 'wb')
+
+    block_sz = 8192
+    while True:
+        buffer = u.read(block_sz)
+        if not buffer:
+            break
+
+        f.write(buffer)
+    f.close()
+    print "Sucessful to download" + " " + file_name
+
+def getHtml(url):
+    page = urlopen(url)
+    html = page.read()
+    page.close()
+    return html
+
+# compile the regular expressions and find
+# all stuff we need
+def getUrl(html):
+    reg = r'(?:href|HREF)="?((?:http://)?.+?\.pdf)'
+    url_re = re.compile(reg)
+    url_lst = re.findall(url_re,html)
+    return(url_lst)
+
+def opeVideoUrl(url):
+    html = urlopen(url).read()
+    ss = html.replace(" ","")
+    urls = re.findall(r"(http://www.yaoshe1.com/get_file/.*?mp4).*?",ss,re.I)
+    for i in urls:
+        print i
+        getFile(i);
+    # else:
+        # print 'this is over'
+    # bsObj = BeautifulSoup(html, "html5lib")
+    # print bsObj
+
+
+html = urlopen("http://www.yaoshe1.com/")
+# print(html.read())
+bsObj = BeautifulSoup(html, "html5lib")
+itemsDivObj = bsObj.findAll("div",{"class":re.compile("^(item)((?!:).)*$")})
+for obj in itemsDivObj:
+    videosObjs = obj.findAll("a",{"href":re.compile("^(http://www.yaoshe1.com/videos/)((?!:).)*$")})
+    # print("==================")
+    strHref = videosObjs[0].attrs["href"]
+    # print strHref
+    count = 0
+    while count < 1:
+        count = count+1
+        print("url = " + strHref)
+        opeVideoUrl(strHref)
+
+
+
+
diff --git a/web_crawle/book/demo1.py b/web_crawle/book/demo1.py
new file mode 100644
index 0000000..74239fa
--- /dev/null
+++ b/web_crawle/book/demo1.py
@@ -0,0 +1,94 @@
+#!/usr/bin/python
+# -*- coding: UTF-8 -*-
+# @Filename: demo1
+# @Date    : 2017-09-24 11:32
+# @Author  : zzl
+# from  http://blog.csdn.net/actanble/article/details/52347458
+
+"""
+   python_version  3.4
+"""
+import re  
+import urllib.request as request    
+from bs4 import BeautifulSoup    
+import requests
+
+'''全局变量声明， 下载其它小说请注意修改 [下载到的本地目录, 书号, 起始index号]'''
+downLoadFile = 'G:\\github.com\\python\\web_crawle\\book\\' ##要下载到的目录
+shuhao = '2_2970' ## 书号就是http://www.biquge.com/2_2970/2456497.html; com后面的那个。
+start, end = 2456497,100000
+
+def setSrr(url):  
+    if(requests.get(url).status_code == 404):  
+        print('这是个错误网址')  
+        return []  
+    print ('正在打开 ',url)      
+ 
+    l  = []  
+    '''''请求响应和不响应的处理'''  
+    response = request.urlopen(url)  
+      
+    html = response.read()    
+    soup = BeautifulSoup(html,"html5lib")
+    item = soup.findAll('h1')   
+    title = re.match(r'(.*)<h1> (.*)</h1>(.*)', str(item) ,re.M|re.I).group(2)  
+    l.append(title.split(' ')[0])  
+    l.append(title)  
+    strings = soup.findAll('div', id="content")[0];  
+    for string in strings:  
+        st = string.__str__()  
+        if (len(st.split('<br/>')) > 1):  
+            pass  
+        else:  
+            l.append(st)  
+    return l  
+#strings.split()  
+ 
+#穿入字符串 写入文件；标题为l[0]  
+def setDoc(l):  
+    if(len(l) < 2):  
+        return  
+    file_s = downLoadFile  + l[0] + '.txt'  
+    file = open(file_s, 'w+', encoding='utf-8')  
+    for i in l:  
+        file.write('\t')  
+        for ii in i.split('    '):  
+            file.write(ii)  
+        file.write('\n')  
+ 
+#开始自加数值；读取新文档；如果没有；那么跳过  
+''''' 最开始设置为1066142，100  '''  
+def setNum(num,n):  
+    l = [(num + i) for i in range(n)]  
+    sl = [str(l[i]) for i in range(len(l))]  
+    return sl  
+      
+'''''自动产生新的url'''  
+
+'''''  自己观察到： 第一章的地址http://www.biquge.com/2_2970/2456497.html
+最后一张的地址 http://www.biquge.com/2_2970/3230837.html'''  
+def setNewUrl(sl):  
+    urls = []  
+    for x in sl:  
+        xsr = 'http://www.biquge.com/'+ shuhao +'/'+ x +'.html'  #对应的单章html
+        urls.append(xsr)  
+    return urls  
+ 
+
+
+def setTxts(urls):  
+    for url in urls:  
+        setDoc(setSrr(url))
+        
+print(  
+'''''
+--------------
+开始下载超品相师
+--------------
+——actanble 手打——
+如果要下载其他的txt文件: 请修改——
+URL 和 对应的起始html的index号。
+'''  
+)  
+setTxts(setNewUrl(setNum(start, end))) 
+
diff --git a/web_crawle/book/demo2.py b/web_crawle/book/demo2.py
new file mode 100644
index 0000000..6ee3783
--- /dev/null
+++ b/web_crawle/book/demo2.py
@@ -0,0 +1,134 @@
+#!/usr/bin/python
+# -*- coding: UTF-8 -*-
+# @Filename: demo2
+# @Date    : 2017-09-24 11:56
+# @Author  : zzl
+#from   http://blog.csdn.net/cellurs/article/details/69367635s
+"""
+   python_version  3.4
+"""
+import time,os,traceback,random
+import requests,re
+from bs4 import BeautifulSoup
+
+#define
+Agent =['Mozilla/5.0 (Windows; U; Windows NT 5.2) Gecko/2008070208 Firefox/3.0.1'
+        ,'Opera/9.27 (Windows NT 5.2; U; zh-cn)'
+        ,'Mozilla/5.0 (iPhone; U; CPU like Mac OS X) AppleWebKit/420.1 (KHTML, like Gecko) Version/3.0'
+        ]
+def ProcName(name):#清洗目录名
+    pat = r'[<|>|/|\|||:|"|*|?]+|（提示：已启用缓存技术，最新章节可能会延时显示，登录书架即可实时查看。）'
+    pat = re.compile(pat)
+    return pat.sub('',name)
+
+def log(url):
+    path = "\home\Rullec\log.txt"
+    with open(path,'w') as f:
+        f.write(str(url))
+        f.close()
+
+def GetHtmlText(url):#获得HTML页面内容 此处可以增加proxies代理服务器，只不过目前还没有
+    try:
+        r = requests.get(url,headers={'User-Agent':Agent[random.randint(0,Agent.__len__()-1)]},timeout = 20)
+        r.raise_for_status()
+        r.encoding = 'utf-8'
+        return r.text
+    except requests.exceptions.ReadTimeout|requests.exceptions.ConnectTimeout:
+        traceback.print_exc() #如果出现超时错误
+        #log(url)
+        waittime = random.randint(10, 20)
+        print("出现超时错误！等待"+str(waittime)+"秒!\n")
+        time.sleep(waittime)
+        return None
+
+def FindIndex(name):#获得目标小说目录页
+    url = "http://zhannei.baidu.com/cse/search?&s=287293036948159515&q="+str(name)+"&click="+str(random.randint(1,3))+'&nsid='
+    text = GetHtmlText(url)
+    if text==None:
+        print("文本为空，无法解析")
+        return None
+    soup = BeautifulSoup(text.encode('utf-8'),'html.parser')
+    list = soup.find_all(name = 'a',attrs = {"cpos" :"title","title":name})#一个list
+    url = []
+    for i in list:
+        url.append(i["href"])
+    return url
+
+def ProcTxt(text):
+    text = text[9:]
+    pat = r'    '
+    pat = re.compile(pat)
+    return pat.sub("\n",text)
+
+def Write(storpath,tag):#进行小说的存储
+    if None==tag:
+        print('小说写入失败，原因是小说最后一层超链接无法获取')
+        return 1
+    a = tag.a#标签的属性使用tag['title']来获得，标签下的搜索使用tag.children来实现
+    storpath += "/"+ProcName(a.string)+".txt"
+    while os.path.exists(storpath):
+        if time.time()-os.path.getctime(storpath)<100 :
+            newpath = storpath.split('.')
+            storpath = newpath[0] + "#.txt"
+        else:
+            return 1
+    url = 'http://www.biquge.com/'+a['href']
+    text = GetHtmlText(url)
+    if text==None or len(text)==0:
+        print("最后一层文本获取失败!")
+        return 1
+    soup = BeautifulSoup(text.encode('utf-8'),'html5lib')
+    novel = soup.find_all("div",attrs={"id":"content"})
+    text = novel[0].text
+    #开始写入
+    with open(storpath,'w',encoding='utf-8') as f:
+        text = ProcTxt(str(text))
+        f.write(text)
+        f.close()
+    return 0
+
+def Spider(url,path):#爬取小说目录页
+    text = ""
+    #while len(text) or text==None:
+    text = GetHtmlText(url)
+    num = 0
+    soup = BeautifulSoup(text,'html5lib')
+    list = soup.find_all(["dd","dt"])
+    nowpath = ""
+    flag = 0
+    for i in list:
+        if i.name == "dt":
+            nowpath = path+"/"+ProcName(i.string)
+            if os.path.exists(nowpath):
+                pass
+            else:
+                os.mkdir(nowpath)
+        else:
+            flag = Write(nowpath,i)
+            num+=1
+            if num%10==0 and (not flag):
+                time.sleep(random.randint(3,10))#爬虫每爬几个就休眠
+        print("\r当前进度: {:.2f}%".format(num * 100 / len(list)), end="")
+    return ""
+
+def main():#主函数
+    name = ProcName(input("请输入要爬取的小说的名字:"))
+    url = FindIndex(name)#爬取搜索结果，在其中查找目录页，并且返回
+    if 0==len(url):
+        print("查无此小说")
+        exit()
+    path = "E:\小说\\"
+    #path = "\home\Rullec\小说\\"
+    if os.path.exists(path):
+        pass
+    else:
+        os.mkdir(path)
+    path = path +name
+    if os.path.exists(path):
+        pass
+    else:
+        os.mkdir(path)
+    Spider(url[0],path)
+main()
+
+
diff --git a/web_crawle/book/file.py b/web_crawle/book/file.py
new file mode 100644
index 0000000..ccdf2a5
--- /dev/null
+++ b/web_crawle/book/file.py
@@ -0,0 +1,8 @@
+#!/usr/bin/python
+# -*- coding: UTF-8 -*-
+# @Filename: file
+# @Date    : 2017-09-25 09:35
+# @Author  : zzl
+"""
+   python_version  2.7.11
+"""
\ No newline at end of file