模仿主站模板首页内页代码,Python代码库,德仔网

代码语言
代码分类
【Python】模仿主站模板首页内页
作者:cqwck / 发布于2015/5/19/ 717

	#!/usr/local/bin/python
	#-*- coding: UTF-8 -*-
	#模仿主站模板
	#QQ29295842
	##################################################
	import threading
	import httplib
	import re
	#import php_data
	#import g
	import sys
	import base64
	#import eval
	#import list
	import httplib,StringIO,gzip,urllib,re
	import binascii
	import chardet
	import ConfigParser #读取INI配置信息
	import random #打乱数组排序
	import os
	#import sc_html #生成HTML
	import urllib2
	import time
	import Queue
	#import sitemap_xml #生成站点地图
	#import shell_links #SHELLSEO
	import list
	import thread
	sys.path.append('..')
	reload(sys)
	sys.setdefaultencoding("utf-8")
	
	class www_mb(threading.Thread):
	 def __init__(self):
	 threading.Thread.__init__(self)
	 self.url=""
	
	 def www_index(self,url):
	 self.url=url
	 s1,s2=self.url_http_200(url)
	 if s1==True:
	 print "OK"
	 utf_gbk, data = self.utf_8_G(s2) #解码
	 if data == "no":
	 print u"读取或转换失败"
	 return 0
	 print "1111111"
	 data=self.open_file_null(data)
	 #self.th_re(data)
	 print "2222"
	 self.TXT_file_add("index.html",u"%s"%(data))
	 else:
	 print "NO"
	
	 def www_index2(self,url):
	 LS = list.Clist() #初始化类
	 LS.list_del() #清空list列表
	 self.url=url
	 s1,data=self.url_http_200(url)
	 if s1==True:
	 print "OK"
	 p = re.compile( r'<a.+?href=.+?>.+?</a>' )
	 pname = re.compile( r'(?<=>).*?(?=</a>)' )
	 phref = re.compile( r'(?<=href\=\").*?(?=\")')
	 sarr = p.findall(data)#找出一条一条的<a></a>标签 #这添加到数组在过滤重复值减少mysql压力
	 i=0
	 for every in sarr:
	 if i>=3000:
	 break
	 else:
	 i+=1
	 sname = pname.findall( every )
	 if sname:
	 #sname = sname[0]
	 shref = phref.findall( every )
	 if shref:
	 if (self.url in str(shref[0])):
	 if (len(shref[0])-len(url))>=2:
	 LS.liet_add(str(shref[0])) #站内链接 全URL
	 #print "1111",str(shref[0])
	 else:
	 if not("http://" in str(shref[0]) or "https://" in str(shref[0])):
	 if len(shref[0])>=2:
	 LS.liet_add(url+"/"+str(shref[0])) #指向目录
	 #print "2222",str(shref[0])
	 LS.liet_lsqc() #数组列表去重复
	 random.shuffle(LS.list_2) #打算数组原有排序方式
	 data2=""
	
	 for i in range(len(LS.list_2)):
	 print LS.list_2[i]
	 s1,data=self.url_http_200(LS.list_2[i])
	 if s1==True:
	 print "OK"
	 data2=data
	 break #跳出 整个循环
	
	 utf_gbk, data = self.utf_8_G(data2) #解码
	 if data == u"no":
	 print u"读取或转换失败"
	 return 0
	 data=self.open_file_null(data)
	 self.TXT_file_add("index2.html",u"%s"%(data))
	
	
	 def th_re(self,data):
	 try: #.+?
	 try:
	 #{time} 当前时间标签 (固定)
	 p = re.compile( r'<title>[\s\S]*</title>')
	 data= p.sub('<title>{time}</title>', data)
	 #<title>【德尔顿官网】,热水器,电热水器,磁能热水器,安全健康热水器</title>
	 except :
	 pass
	
	 try:
	 #{time} 当前时间标签 (固定)
	 p = re.compile( r'<a title="[\s\S]*" href="/">')
	 data= p.sub('<a title="{time}" href="/">', data)
	 #<a title="热水器十大品牌 电热水器哪个牌子好 磁能热水器-德尔顿" href="/">
	 except :
	 pass
	
	 try:
	 #{time} 当前时间标签 (固定)
	 p = re.compile( r'<strong>[\s\S]*</strong>')
	 data= p.sub('<strong>{time}</strong>', data)
	 #<strong>磁能热水器行业德尔顿...</strong>
	 except :
	 pass
	
	 try:
	 #{tmkeyword2} 整个网站模板随机抽取1个关键字
	 p = re.compile( r'>[\s\S]*</span>')
	 data= p.sub('>{tmkeyword2}</span>', data)
	 #>劳女士</span>
	 except :
	 pass
	
	 try:
	 #{tmkeyword2} 整个网站模板随机抽取1个关键字
	 p = re.compile( r'<p[\s\S]*>[\s\S]*')
	 data= p.sub('{tmkeyword2}', data)
	 #>看看离您最近的体验店在哪
	 except :
	 pass
	
	 try:
	 #{tmkeyword} 主关键词标签 (固定)
	 p = re.compile( r'<meta content="[\s\S]*" name="keywords">')
	 data= p.sub('<meta content="{tmkeyword}" name="keywords">', data)
	 #<meta content="热水器,电热水器,即热式电热水器,磁能热水器" name="keywords">
	 except :
	 pass
	
	 try:
	 #{tmkeyword} 主关键词标签 (固定)
	 p = re.compile( r'<meta name=".*?" content="[\s\S]*" />')
	 data= p.sub('<meta name="keywords" content="{tmkeyword}" />', data)
	 except :
	 pass
	
	 try:
	 #{tmkeyword} 主关键词标签 (固定)
	 #{tmkeyword2} 整个网站模板随机抽取1个关键字
	 p = re.compile( r'<meta name=".*?" content="[\s\S]*">')
	 data= p.sub('<meta name="description" content="{tmkeyword}{tmkeyword2}">', data)
	 #<meta name="description" content="德尔顿中国健康热水器,不需防电墙、不需接地线,不生水垢,电磁热水器,磁能热水器,安全热水器,家装群体首选健康速磁生活电热水器品牌，招商代理电话：400-888-1682。">
	 except :
	 pass
	
	 try:
	 #{link} 随机链接标签(内链) (随机)
	 p = re.compile( r'<A.*?href="[\s\S]*</A>')
	 sarr = p.findall(data)
	 if len(sarr)>=1:
	 phref = re.compile( r'(?<=href\=\").*?(?=\")')
	 sarr = phref.findall(data)
	 if ("http://" in str(sarr[0]) or "https://" in str(sarr[0])):
	 if (url in str(shref[0])):
	 data= p.sub('{link}', data) #替换成内链
	 else:
	 data= p.sub('{ylinks}', data) #替换成外链
	 else:
	 if (".asp" in str(sarr[0]) or ".aspx" in str(sarr[0]) or ".php" in str(sarr[0]) or ".htm" in str(sarr[0]) or ".html" in str(sarr[0])):
	 data= p.sub('{link}', data) #替换成内链
	 else:
	 data= p.sub('{newslist}', data) #目录页目录链接 (随机)
	 #<A href="/guanyu/shipin/">企业视频</A>
	 except :
	 pass
	
	 try:
	 #{link} 随机链接标签(内链) (随机)
	 p = re.compile( r'<a.*?href="[\s\S]*</a>')
	 sarr = p.findall(data)
	 if len(sarr)>=1:
	 phref = re.compile( r'(?<=href\=\").*?(?=\")')
	 sarr = phref.findall(data)
	 if ("http://" in str(sarr[0]) or "https://" in str(sarr[0])):
	 if (url in str(shref[0])):
	 data= p.sub('{link}', data) #替换成内链
	 else:
	 data= p.sub('{ylinks}', data) #替换成外链
	 else:
	 if (".asp" in str(sarr[0]) or ".aspx" in str(sarr[0]) or ".php" in str(sarr[0]) or ".htm" in str(sarr[0]) or ".html" in str(sarr[0])):
	 data= p.sub('{link}', data) #替换成内链
	 else:
	 data= p.sub('{newslist}', data) #目录页目录链接 (随机)
	 except :
	 pass
	
	 try:
	 #{link} 随机链接标签(内链) (随机)
	 p = re.compile( r'<a.*?href="[\s\S]*</A>')
	 sarr = p.findall(data)
	 if len(sarr)>=1:
	 phref = re.compile( r'(?<=href\=\").*?(?=\")')
	 sarr = phref.findall(data)
	 if ("http://" in str(sarr[0]) or "https://" in str(sarr[0])):
	 if (url in str(shref[0])):
	 data= p.sub('{link}', data) #替换成内链
	 else:
	 data= p.sub('{ylinks}', data) #替换成外链
	 else:
	 if (".asp" in str(sarr[0]) or ".aspx" in str(sarr[0]) or ".php" in str(sarr[0]) or ".htm" in str(sarr[0]) or ".html" in str(sarr[0])):
	 data= p.sub('{link}', data) #替换成内链
	 else:
	 data= p.sub('{newslist}', data) #目录页目录链接 (随机)
	 except :
	 pass
	
	 try:
	 #正文
	 p = re.compile( r'>*.+?[\s\S]*')
	 sarr = p.findall(data)
	 if len(sarr)>=1:
	 #print u"%s"%(sarr)
	 if len(sarr[0])>=150:
	 data= p.sub('>{skeyword}{content}{content}。{skeyword}{content}{content}。{skeyword}{content}{content}。{skeyword}{content}{content}。', data)
	 #print sarr[0],"=====",data
	 if len(sarr[0])>=100:
	 data= p.sub('>{skeyword}{content}{content}。{skeyword}{content}{content}。', data)
	 if len(sarr[0])>=50:
	 data= p.sub('>{skeyword}{content}{content}。', data)
	 except :
	 pass
	
	 return data
	 except Exception,e:
	 return data
	
	
	# sarr = p.findall(data)
	# for line in res:
	# print line
	# print len(sarr)
	# res = p.split(data)
	# for line in res:
	# print line
	
	
	 def open_file_null(self,file_data): #清除空行
	 data=""
	 try:
	 p = re.compile( r'.+?\n')
	 sarr = p.findall(file_data)
	 for every in sarr:
	 if ("//" in str(every) or "!" in str(every)):
	 data+=str(every)
	 else:
	 #print self.th_re(str(every))
	 data+=self.th_re(str(every))
	 #if every.split():
	 #data+=every
	 # if len(every)>1:
	 # data+=every
	 #data+=every.lstrip().rstrip().strip().rstrip('\n')
	 return data
	 except Exception,e:
	 print u"zzzzzzzzzzzzz",e
	 return data
	
	 def TXT_file_add(self,file_nem,data): #写入文本
	 try:
	 #file_nem=time.strftime('%Y.%m.%d') #file_nem+".txt"
	 file_object = open(file_nem,'w')
	 #file_object.write(list_passwed[E])
	 file_object.writelines(data)
	 #file_object.writelines("\n")
	 file_object.close()
	 except Exception,e:
	 print u"写入TXT失败",file_nem,data,e
	 return 0
	
	 def utf_8_G(self,data): #解码
	 try:
	 try:
	 return "gbk",data.decode('gbk')
	 except Exception,e:
	 #print e
	 pass
	 try:
	 return "utf-8",data.decode('utf-8')
	 except Exception,e:
	 #print e
	 pass
	 try:
	 return "gb2312",data.decode('gb2312')
	 except Exception,e:
	 #print e
	 pass
	 except Exception,e:
	 print "utf_8_G",e
	 return "utf_8_G","no"
	 pass
	
	 def url_http_200(self,url):
	 try:
	 req = urllib2.Request(url)
	 req.add_header('User-Agent',"Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)")
	 s = urllib2.urlopen(req,timeout=10) # 超时10秒 #s = urllib2.urlopen(r"http://www.163.com")
	 int_url_read = s.read()
	 if len(int_url_read)>=5000:
	 return True,int_url_read
	 else:
	 return False,""
	 except BaseException, e:
	 #print "xxxxxxxxxxxx",(str(e))
	 return False,""
	
	
	if __name__=='__main__':
	 m=www_mb() #http://www.deerdun.com
	 m.www_index("http://www.deerdun.com") #http://www.ybfhcl.com
	 m.www_index2("http://www.deerdun.com")
	
	
	
	# p = re.compile('(one|two|three)')
	# print p.sub('num', 'one word two words three words apple', 2)
试试其它关键字
　主站模板　
同语言下
可能有用的
cqwck贡献的其它代码(2)