文章
文章用户商铺文档快讯圈子网址导航供求信息
推广

度崩资源网 | Telegram群 | 广告位招租

[Python] 分享百度快排发包python源码核心文件

最近都在研究怎么做快排，分享下成果，可以一起学习交流！

  附上代码：

# -*- coding: utf-8 -*-from selenium import webdriver
import time
import requests
import random
import os
from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
import traceback
import urllib.request
import pymysql
import socket
#import win32api #pip install pypiwin32
 
#from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
#DesiredCapabilities.INTERNETEXPLORER['ignoreProtectedModeSettings'] = True
 
 
 
#rasdial 宽带连接 19ab68----643534
def connect():
    cmd_str = "rasdial %s %s %s" % (g_adsl_account['name'], g_adsl_account['username'], g_adsl_account['password'])
    os.system(cmd_str)
    time.sleep(5)
 
 
#"rasdial 断开宽带连接 /disconnect"
def disconnect():
    cmd_str = "rasdial %s /disconnect" % g_adsl_account['name']
    os.system(cmd_str)
    time.sleep(5)
     
#获取ip地址 
def get_ip():
    #return ['ip','address']
    fp = urllib.request.urlopen("http://ip.chinaz.com/getip.aspx")
    mybytes = fp.read()
    # note that Python3 does not read the html code as string
    # but as html code bytearray, convert to string with
    mystr = mybytes.decode("utf8")
    fp.close()
    ip = mystr.find("ip")
    add = mystr.find("address")
    ip = mystr[ip+4:add-2]
    address = mystr[add+9:-2]
    return [ip,address]
 
#将ip地址插入数据库
def insert_db(ipdate):
    #try:
        #获取一个数据库连接，注意如果是UTF-8类型的，需要制定数据库
        conn=pymysql.connect(host='localhost',user='root',passwd='',port=3306,charset='utf8')
        cur=conn.cursor()                              #获取一个游标对象
        #cur.execute("CREATE DATABASE zongzong")          #执行对应的SQL语句
        #exit()
        cur.execute("USE zongzong")
        #exit()
        #cur.execute("CREATE TABLE `ip_log` (`id` int(11) NOT NULL AUTO_INCREMENT,`ip` varchar(32) DEFAULT NULL,`address` varchar(64) DEFAULT NULL,`keyword` varchar(64) DEFAULT '',`url` varchar(256) DEFAULT '',`error` varchar(64) DEFAULT '',`created_at` timestamp NULL DEFAULT NULL ON UPDATE CURRENT_TIMESTAMP,PRIMARY KEY (`id`)) ENGINE=InnoDB AUTO_INCREMENT=21 DEFAULT CHARSET=utf8;")
         
        #插入数据
        ISOTIMEFORMAT='%Y-%m-%d %X'
        ipdate.append( time.strftime( ISOTIMEFORMAT, time.localtime() ))
        cur.execute("INSERT INTO ip_log(ip,address,keyword,url,error,page,rank,created_at) VALUES(%s, %s, %s, %s, %s, %s, %s, %s)",ipdate)
         
        #cur.execute("SELECT * FROM ip_log")
        #data=cur.fetchall()
        #print(data)
             
        cur.close()#关闭游标
        conn.commit()#向数据库中提交任何未解决的事务，对不支持事务的数据库不进行任何操作
        conn.close()#关闭到数据库的连接，释放数据库资源
    #except:
    #   print("发生异常")   
 
 
#获取搜素出来的url
def get_search_url(driver):
    urls = []
    real = []
    real_url = []
    click_link = []
    content = driver.find_element_by_css_selector("div[id=\"content_left\"]")
    links = content.find_elements_by_tag_name("a")
    for link in links:
        if link.get_attribute('class') == "c-showurl":
            real.append(link.text)
            url = link.get_attribute('href')
            urls.append(url)
             
            #解密url
            header = requests.head(url).headers
            is_append = True
            for out_url in out_urls:
                if out_url in header['location']:
                    is_append = False
                    break
                     
            if is_append == True:
                real_url.append(header['location'])
                #a标签对象
                click_link.append(link)
                     
    #print(real)
    #print(urls)
    #return urls
    return [real_url,click_link]
     
     
#function：解析加密url，剔除竞争对手的url
# def get_real_url(urls):
    # real_url = []
    # for url in urls:
        # header = requests.head(url).headers
        # is_append = True
        # for out_url in out_urls:
            # if out_url in header['location']:
                # is_append = False
                # break
             
        # if is_append == True:
            # real_url.append(header['location'])
    # return real_url
 
#function 目标地址是否在某个list中
def get_urlIndex(tagurl,urls):
    i = 0
    has = -1
    for url in urls:
        if tagurl in url:
            has = True
            return i
        i = i+1
    return has 
 
     
#点击百度搜索内容下面的下一页
def click_nextBtn(driver):
    div = driver.find_element_by_css_selector("div[id=\"page\"]")
    a = div.find_elements_by_tag_name("a")
    for item in a:
        print(item.text)
        if item.text == "下一页>":
            item.click()
     
    return driver
 
             
 
 
#随机点击
def click_search_url(driver,items):
    urls = []
    real = []
    content = driver.find_element_by_css_selector("div[id=\"content_left\"]")
    links = content.find_elements_by_tag_name("a")
    i=0
    '''获取当前窗口'''
    nowhandle = driver.current_window_handle
    #allhandles=driver.window_handles
    #for handle in allhandles:
    #   print('....当前窗口....',handle.title)
    #exit()
     
    for link in links:
        if link.get_attribute('class') == "c-showurl":
            if i in items:
                print("随机点击item:",i)
                print(link.get_attribute('href'),link.text)
                #exit()
                link.click()
                #停留在点击页面
                time.sleep(random.randint(5,10))
             
                '''获取所有窗口'''
                allhandles=driver.window_handles
                #for handle in allhandles:
                #   print('....当前窗口....',handle.title)
                #exit()
                 
                '''循环判断窗口是否为当前窗口'''
                for handle in allhandles:
                    if handle != nowhandle:
                        print("切换到当前窗口")
                        driver.switch_to_window(handle)
                        print("title:",driver.title)
                        '''关闭当前窗口'''
                        driver.close()
                        '''回到原先的窗口'''
                        print("切换到原来的窗口")
                        driver.switch_to_window(nowhandle)
                        print("title:",driver.title)
                print("本次随机点击完毕！")
                         
            i=i+1
 
             
#获取随机点击的搜索页random.randint(0
def get_random_index(index,len):
    if index >= 8:
        random_index = [
            random.randint(0,4),random.randint(5,8)
        ]
    elif index>=4:
        random_index = [
            random.randint(0,3),random.randint(3,index)
        ]
    elif index>=0:
        random_index = [
            index
        ]
    elif index == -1:
        if len <=5:
            random_index = [
                random.randint(0,5)
            ]
        else:
            random_index = [
                #random.randint(0,4),random.randint(5,len)
                random.randint(5,len)
            ]
    return random_index
 
 
 
def getUA():
    uaList = [
        #360
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36",
        #chrome
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.94 Safari/537.36",
        #"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.94 Safari/537.36",
        "Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36",
         
        #firefox
        #"Mozilla/5.0 (Windows NT 6.1; WOW64; rv:46.0) Gecko/20100101 Firefox/46.0",
        "Mozilla/5.0 (Windows NT 6.3; WOW64; rv:36.0) Gecko/20100101 Firefox/36.0",
         
        #ie11
        #"Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; rv:11.0) like Gecko",
        #ie8 
        #"Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0; 4399Box.1357; 4399Box.1253; 4399Box.1357)",
         
        #2345王牌
        #"Chrome/39.0.2171.99 Safari/537.36 2345Explorer/6.5.0.11018",
         
        #搜狗
        #"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/38.0.2125.122 Safari/537.36 SE 2.X MetaSr 1.0",
        #opera
        "Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36 OPR/26.0.1656.60"
         
    ]
    headers = random.choice(uaList)
    return headers
 
#屏幕浏览器窗口大小
def getWindowSize():
    wind_size = [
        [1920,1080],
        [1600,900],
        [1280,720]
    ]
    headers = random.choice(wind_size)
    return headers
     
     
#屏幕分辨率设置
def setDisplay():
    display_size = [
        [1920,1080],
        [1680,1050],
        [1600,900],
        [1440,900],
        [1400,1050]
    ]
    d_size = random.choice(display_size)
     
    dm = win32api.EnumDisplaySettings(None, 0)
    dm.PelsWidth = d_size[0]
    dm.PelsHeight = d_size[1]
    dm.BitsPerPel = 32
    dm.DisplayFixedOutput = 0
    win32api.ChangeDisplaySettings(dm, 0)
 
     
#拨号 19ab68----643534        
g_adsl_account = {
    "name":"宽带连接",
    "username":"19ab68",
    "password":"643534"
}
 
 
#屏蔽点击的地址（竞争对手）
out_urls = [
    'zhimo.yuanzhumuban.cc',
    'bbs.yuanzhumuban.cc',
        'http://money.163.com/15/0416/11/ANANRECC00253B0H.html'
]
 
 
##内页词
targetURL = [
     
        ['http://www.hkuws.com','注册离岸公司'],
    ['zs.efu.com.cn/mornfeeit/','梦菲雪'],
    ['zs.efu.com.cn/chengshijiaren/','城市佳人'],
    ['www.kidsnet.cn/exposition','童装展会'],
    #['top.kidsnet.cn/','童装加盟排行榜'],
    #['www.nynet.com.cn/','内衣网'],
    #['www.nzw.cn/','女装网'],
    ['zs.efu.com.cn/ks/','卡索'],
    ['zs.efu.com.cn/distin-kidny/','迪斯廷凯'],
    ['zs.efu.com.cn/fuzhuang/luyidigao/','路易迪高童装代{过}{滤}理'],
    ['brand.efu.com.cn/brandshow-1221090.html','凯帝龙驰'],
    ['zs.efu.com.cn/rabbitjero/','兔子杰罗'],
    ['zs.efu.com.cn/wmprince/','西瓜王子'],
        ['zs.efu.com.cn/betu','百图'],
        ['zs.efu.com.cn/pepco/','小猪班纳'],
 
 
    #['http://news.ifeng.com/a/20160518/48795120_0.shtml','华夏信财'],
    ['http://weibo.com/huaxiafinance','华夏信财'],
    ['http://p2p.hexun.com/2016-04-26/183531215.html','华夏信财'],
    #['http://news.xinhuanet.com/fortune/2016-04/26/c_128932834.htm','华夏信财'],
    ['http://www.xcf.cn/gdyw/201605/t20160526_772682.htm','华夏信财'],
    ['http://www.huaxiaoxia.com/','华夏信财'],
        #['https://lc.huaxiafinance.com/','华夏信财'],
 
 
 
        ['so.tedu.cn','网络营销培训机构'],
        ['www.cosatto.net.cn','个性安全座椅'],
        ['www.kaihuata.com/','开化旅游'],
        #['www.kaihuata.com/','开化'],
 
]
 
 
for targetInfo in targetURL:
    try:
        #更换ip
        disconnect()
        connect()
         
        while(1):
                    try:
                        socket.gethostbyname("baidu.com")
                        break;
                    except:
                        disconnect()
                        connect()
        #更换分辨率
        #setDisplay()
         
         
        #启动浏览器
        #driver = webdriver.Ie()
        #driver = webdriver.Chrome()
        #driver = webdriver.Firefox()
         
        #设置PhantomJS的user_agent
        dcap = dict(DesiredCapabilities.PHANTOMJS)
        user_agent = getUA()
        print(user_agent)
        dcap["phantomjs.page.settings.userAgent"] = (
                user_agent
        )
        #dcap["phantomjs.page.settings.resourceTimeout"] = (15000)
        dcap["phantomjs.page.settings.loadImages"] = (False)
        driver = webdriver.PhantomJS(desired_capabilities=dcap,service_args=['--load-images=no'])
         
         
        # UA = getUA()
        # print(UA)
        # webdriver.DesiredCapabilities.PHANTOMJS['phantomjs.page.customHeaders.User-Agent'] = UA
        # driver = webdriver.PhantomJS()
         
        driver.implicitly_wait(30)
         
        #清cookie
        driver.delete_all_cookies()
 
        #driver.maximize_window() # 浏览器全屏显示
 
        #打开百度
        driver.get("http://www.baidu.com/")
        #driver.get("http://mch.weiba01.com/2.php")
         
        #设置浏览器窗口大小
        window_size = getWindowSize()
        driver.set_window_size(window_size[0], window_size[1])
                 
                 
        #搜索某个关键词
        print('打开百度成功',driver.title)
        target = targetInfo[0]
        keyword = targetInfo[1]
        if len(targetInfo)>2:
                error_keyword = targetInfo[random.randint(2,len(targetInfo)-1)]       
        print(">>>>>>>>>>>>>>>点击的关键词：",keyword,"--->目标地址：",target,">>>>>>>>>>>>>>>>>>>>")
         
         
        if len(targetInfo)>2:
            #模拟错误关键词
            print("点击错误关键词：",error_keyword);
            driver.find_element_by_id("kw").send_keys(error_keyword)
            time.sleep(2)
            driver.find_element_by_id("su").click()
            time.sleep(5)
            driver.find_element_by_id("kw").clear()
            time.sleep(2)
            print("错误关键词点击完毕")
             
        driver.find_element_by_id("kw").send_keys(keyword)
        #time.sleep(2)
 
        #点击搜索按钮
        print("...开始点击搜索按钮..")
        driver.find_element_by_id("su").click()
        #exit()
        print("...点击完毕..")
        time.sleep(2)
 
         
        #获取搜索结果页 0:着陆页  1：对应的链接对象
        urls_res = get_search_url(driver)
        real_urls = urls_res[0]
        #get_search_url(driver)[1][2].click()
         
         
        #real_urls = get_real_url(urls)
        print("搜索出来的可点击着陆页个数：",len(real_urls))
        print(real_urls)
        index = get_urlIndex(target,real_urls)
        print("目标index:",index)
 
        page = 1
        while index == -1 and page <= 4:
            if page == 1:
                #点击前面的几个着陆页,模拟用户真实行为
                items = get_random_index(index,len(real_urls))
                #items = [4]
                print(items)
                click_search_url(driver,items)
             
            #下一页
            driver = click_nextBtn(driver)
            time.sleep(3)
            urls_res = get_search_url(driver)
            real_urls = urls_res[0]
            #real_urls = get_real_url(urls)
            print(real_urls)
            index = get_urlIndex(target,real_urls)
             
            page = page+1
 
             
             
        if index > 4 and page == 1:
            #第一页，随机点击两个或一个
            int = random.randint(1,2)
            if int == 2:
                items = get_random_index(index,len(real_urls))
            else:
                items = [1]
            print(items)
            click_search_url(driver,items)
             
        if page >=5:
            print("没有找到目标地址，放弃搜索...")
            print("关闭浏览器")
            driver.quit()
             
            time.sleep(5)
            data = get_ip()
            data.append(keyword)
            data.append(target)
            data.append("no_find")
            data.append(-1)
            data.append(-1)
            insert_db(data)
            continue
         
        print("目标在page",page,"当前排名：",index,real_urls[index])
        print("反问最后的目标页...")
        #driver.get(real_urls[index])
        urls_res[1][index].click()
        time.sleep(5)
         
        nowhandle = driver.current_window_handle
        allhandles = driver.window_handles
        #目标页和搜索栏目页切换下
        for handle in allhandles:
            if handle != nowhandle:
                print("切换到当前窗口")
                driver.switch_to_window(handle)
                stime = random.randint(15,25)
                #stime = 5;
                print("目标页title:",driver.title,"停留-->",stime)
                time.sleep(stime)
                '''关闭当前窗口'''
                driver.close()
                 
                '''回到原先的窗口'''
                print("切换到原来的窗口")
                driver.switch_to_window(nowhandle)
                print("title:",driver.title)
         
         
        #time.sleep(random.randint(40,60))
        #time.sleep(5)
 
        #清除所有cookie
        print("打印cookie")
        cookie= driver.get_cookies()
        print(cookie)
        print("清除cookie")
        driver.delete_all_cookies()
        print("打印cookie:")
        cookie= driver.get_cookies()
        print(cookie)
 
        #关闭浏览器
        print("关闭浏览器")
        time.sleep(5)
        #driver.close()
        driver.quit()
        #time.sleep(5)
         
        #数据库记录运行信息
        data = get_ip()
        data.append(keyword)
        data.append(target)
        data.append("success")
        data.append(page)
        data.append(index)
        insert_db(data)
     
    except:
        data = get_ip()
        data.append(keyword)
        data.append(target)
        data.append("faild")
        data.append(-1)
        data.append(-1)
        insert_db(data)
    

转载自吾爱破解

相关推荐:

  1. 宝塔Windows面板 6.4免费版下载，基于Python重构的全新Windows面板
  2. [Windows] TeamViewer14.6.4835.0无限改ID单文件版
  3. [Windows] （限时收藏）会声会影2019旗舰版+素材包+基础及进阶教程
  4. 【前端开发，JS图表】Amcharts v4.7.4 – JS图表
  5. 【windows】[吾爱破解原创工具] 某宝生意参谋【实时访客】入店来源词统计
  6. DPlayer播放器指南-such a lovely HTML5 danmaku video player
  7. Pornhub_PH站视频Chrome一键下载插件[Windows]
  8. 教你写页游自动化Python脚本 1.界面篇（模仿某键精灵）[Python3]

给TA打赏
共{{data.count}}人
人已打赏
Python吾爱破解百度快排
编程语言

Wordpress二次开发快速入门之函数钩子（Hook）大全(2)

2019-9-6 16:33:37

编程语言

【前端开发，JS图表】Amcharts v4.7.4 - JS图表

2019-10-28 13:17:47

猜你喜欢
本站所发布的一切源码、模板、应用等文章仅限用于学习和研究目的；不得将上述内容用于商业或者非法用途，否则，一切后果请用户自负。本站信息来自网络，版权争议与本站无关。您必须在下载后的24个小时之内，从您的电脑中彻底删除上述内容。如果您喜欢该程序，请支持正版，购买注册，得到更好的正版服务。如有侵权。本站内容适用于DMCA政策。若您的权利被侵害，请与我们联系处理，站长 QQ: 84087680 或 点击右侧 私信：盾给网 反馈，我们将尽快处理。
⚠️
本站所发布的一切源码、模板、应用等文章仅限用于学习和研究目的；不得将上述内容用于商业或者非法用途，否则，一切后果请用户自负。本站信息来自网络，版权争议与本站无关。您必须在下载后的24个小时之内，从您的电脑中彻底删除上述内容。如果您喜欢该程序，请支持正版，购买注册，得到更好的正版服务。如有侵权。本站内容适用于DMCA政策。
若您的权利被侵害，请与我们联系处理，站长 QQ: 84087680 或 点击右侧 私信：盾给网 反馈，我们将尽快处理。
0 条回复 A文章作者 M管理员
    暂无讨论，说说你的看法吧
❯
个人中心
购物车
优惠劵
今日签到
有新私信 私信列表
搜索

  • 扫码打开当前页

  • 官方QQ群

  • 微信公众号

  • 站长微信

返回顶部