python+selenium模拟百度关键词排名点击

声明：代码为转载内容，仅限于参考学习python。

1. # -*- coding: utf-8 -*-from selenium import webdriver
2. import time
3. import requests
4. import random
5. import os
6. from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
7. import traceback
8. import urllib.request
9. import pymysql
10. import socket
11. #import win32api #pip install pypiwin32
13. #from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
14. #DesiredCapabilities.INTERNETEXPLORER[‘ignoreProtectedModeSettings’] = True
18. #rasdial 宽带连接 19ab68—-643534
19. def connect():
20.     cmd_str = “rasdial %s %s %s” % (g_adsl_account[‘name’], g_adsl_account[‘username’], g_adsl_account[‘password’])
21.     os.system(cmd_str)
22.     time.sleep(5)
25. #”rasdial 断开宽带连接 /disconnect”
26. def disconnect():
27.     cmd_str = “rasdial %s /disconnect” % g_adsl_account[‘name’]
28.     os.system(cmd_str)
29.     time.sleep(5)
31. #获取ip地址
32. def get_ip():
33.     #return [‘ip’,’address’]
34.     fp = urllib.request.urlopen(“http://ip.chinaz.com/getip.aspx”)
35.     mybytes = fp.read()
36.     # note that Python3 does not read the html code as string
37.     # but as html code bytearray, convert to string with
38.     mystr = mybytes.decode(“utf8”)
39.     fp.close()
40.     ip = mystr.find(“ip”)
41.     add = mystr.find(“address”)
42.     ip = mystr[ip+4:add-2]
43.     address = mystr[add+9:-2]
44.     return [ip,address]
46. #将ip地址插入数据库
47. def insert_db(ipdate):
48.     #try:
49.         #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
50.         conn=pymysql.connect(host=’localhost’,user=’root’,passwd=”,port=3306,charset=’utf8′)
51.         cur=conn.cursor()                              #获取一个游标对象
52.         #cur.execute(“CREATE DATABASE zongzong”)          #执行对应的SQL语句
53.         #exit()
54.         cur.execute(“USE zongzong”)
55.         #exit()
56.         #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;”)
58.         #插入数据
59.         ISOTIMEFORMAT=’%Y-%m-%d %X’
60.         ipdate.append( time.strftime( ISOTIMEFORMAT, time.localtime() ))
61.         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)
63.         #cur.execute(“SELECT * FROM ip_log”)
64.         #data=cur.fetchall()
65.         #print(data)
67.         cur.close()#关闭游标
68.         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
69.         conn.close()#关闭到数据库的连接，释放数据库资源
70.     #except:
71.     #   print(“发生异常”)
74. #获取搜素出来的url
75. def get_search_url(driver):
76.     urls = []
77.     real = []
78.     real_url = []
79.     click_link = []
80.     content = driver.find_element_by_css_selector(“div[id=\”content_left\”]”)
81.     links = content.find_elements_by_tag_name(“a”)
82.     for link in links:
83.         if link.get_attribute(‘class’) == “c-showurl”:
84.             real.append(link.text)
85.             url = link.get_attribute(‘href’)
86.             urls.append(url)
88.             #解密url
89.             header = requests.head(url).headers
90.             is_append = True
91.             for out_url in out_urls:
92.                 if out_url in header[‘location’]:
93.                     is_append = False
94.                     break
96.             if is_append == True:
97.                 real_url.append(header[‘location’])
98.                 #a标签对象
99.                 click_link.append(link)
101.     #print(real)
102.     #print(urls)
103.     #return urls
104.     return [real_url,click_link]
107. #function：解析加密url，剔除竞争对手的url
108. # def get_real_url(urls):
109.     # real_url = []
110.     # for url in urls:
111.         # header = requests.head(url).headers
112.         # is_append = True
113.         # for out_url in out_urls:
114.             # if out_url in header[‘location’]:
115.                 # is_append = False
116.                 # break
118.         # if is_append == True:
119.             # real_url.append(header[‘location’])
120.     # return real_url
122. #function 目标地址是否在某个list中
123. def get_urlIndex(tagurl,urls):
124.     i = 0
125.     has = -1
126.     for url in urls:
127.         if tagurl in url:
128.             has = True
129.             return i
130.         i = i+1
131.     return has
134. #点击百度搜索内容下面的下一页
135. def click_nextBtn(driver):
136.     div = driver.find_element_by_css_selector(“div[id=\”page\”]”)
137.     a = div.find_elements_by_tag_name(“a”)
138.     for item in a:
139.         print(item.text)
140.         if item.text == “下一页>”:
141.             item.click()
143.     return driver
148. #随机点击
149. def click_search_url(driver,items):
150.     urls = []
151.     real = []
152.     content = driver.find_element_by_css_selector(“div[id=\”content_left\”]”)
153.     links = content.find_elements_by_tag_name(“a”)
154.     i=0
155.     ”’获取当前窗口”’
156.     nowhandle = driver.current_window_handle
157.     #allhandles=driver.window_handles
158.     #for handle in allhandles:
159.     #   print(‘….当前窗口….’,handle.title)
160.     #exit()
162.     for link in links:
163.         if link.get_attribute(‘class’) == “c-showurl”:
164.             if i in items:
165.                 print(“随机点击item:”,i)
166.                 print(link.get_attribute(‘href’),link.text)
167.                 #exit()
168.                 link.click()
169.                 #停留在点击页面
170.                 time.sleep(random.randint(5,10))
172.                 ”’获取所有窗口”’
173.                 allhandles=driver.window_handles
174.                 #for handle in allhandles:
175.                 #   print(‘….当前窗口….’,handle.title)
176.                 #exit()
178.                 ”’循环判断窗口是否为当前窗口”’
179.                 for handle in allhandles:
180.                     if handle != nowhandle:
181.                         print(“切换到当前窗口”)
182.                         driver.switch_to_window(handle)
183.                         print(“title:”,driver.title)
184.                         ”’关闭当前窗口”’
185.                         driver.close()
186.                         ”’回到原先的窗口”’
187.                         print(“切换到原来的窗口”)
188.                         driver.switch_to_window(nowhandle)
189.                         print(“title:”,driver.title)
190.                 print(“本次随机点击完毕！”)
192.             i=i+1
195. #获取随机点击的搜索页random.randint(0
196. def get_random_index(index,len):
197.     if index >= 8:
198.         random_index = [
199.             random.randint(0,4),random.randint(5,8)
200.         ]
201.     elif index>=4:
202.         random_index = [
203.             random.randint(0,3),random.randint(3,index)
204.         ]
205.     elif index>=0:
206.         random_index = [
207.             index
208.         ]
209.     elif index == -1:
210.         if len <=5:
211.             random_index = [
212.                 random.randint(0,5)
213.             ]
214.         else:
215.             random_index = [
216.                 #random.randint(0,4),random.randint(5,len)
217.                 random.randint(5,len)
218.             ]
219.     return random_index
223. def getUA():
224.     uaList = [
225.         #360
226.         “Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36”,
227.         #chrome
228.         “Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.94 Safari/537.36”,
229.         #”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″,
230.         “Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36”,
232.         #firefox
233.         #”Mozilla/5.0 (Windows NT 6.1; WOW64; rv:46.0) Gecko/20100101 Firefox/46.0″,
234.         “Mozilla/5.0 (Windows NT 6.3; WOW64; rv:36.0) Gecko/20100101 Firefox/36.0”,
236.         #ie11
237.         #”Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; rv:11.0) like Gecko”,
238.         #ie8
239.         #”Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0; 4399Box.1357; 4399Box.1253; 4399Box.1357)”,
241.         #2345王牌
242.         #”Chrome/39.0.2171.99 Safari/537.36 2345Explorer/6.5.0.11018″,
244.         #搜狗
245.         #”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″,
246.         #opera
247.         “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”
249.     ]
250.     headers = random.choice(uaList)
251.     return headers
253. #屏幕浏览器窗口大小
254. def getWindowSize():
255.     wind_size = [
256.         [1920,1080],
257.         [1600,900],
258.         [1280,720]
259.     ]
260.     headers = random.choice(wind_size)
261.     return headers
264. #屏幕分辨率设置
265. def setDisplay():
266.     display_size = [
267.         [1920,1080],
268.         [1680,1050],
269.         [1600,900],
270.         [1440,900],
271.         [1400,1050]
272.     ]
273.     d_size = random.choice(display_size)
275.     dm = win32api.EnumDisplaySettings(None, 0)
276.     dm.PelsWidth = d_size[0]
277.     dm.PelsHeight = d_size[1]
278.     dm.BitsPerPel = 32
279.     dm.DisplayFixedOutput = 0
280.     win32api.ChangeDisplaySettings(dm, 0)
283. #拨号 19ab68—-643534
284. g_adsl_account = {
285.     “name”:”宽带连接”,
286.     “username”:”19ab68″,
287.     “password”:”643534″
288. }
291. #屏蔽点击的地址（竞争对手）
292. out_urls = [
293.     ‘zhimo.yuanzhumuban.cc’,
294.     ‘bbs.yuanzhumuban.cc’,
295.         ‘http://money.163.com/15/0416/11/ANANRECC00253B0H.html’
296. ]
299. ##内页词
300. targetURL = [
302.         [‘http://www.hkuws.com’,’注册离岸公司’],
303.     [‘zs.efu.com.cn/mornfeeit/’,’梦菲雪’],
304.     [‘zs.efu.com.cn/chengshijiaren/’,’城市佳人’],
305.     [‘www.kidsnet.cn/exposition’,’童装展会’],
306.     #[‘top.kidsnet.cn/’,’童装加盟排行榜’],
307.     #[‘www.nynet.com.cn/’,’内衣网’],
308.     #[‘www.nzw.cn/’,’女装网’],
309.     [‘zs.efu.com.cn/ks/’,’卡索’],
310.     [‘zs.efu.com.cn/distin-kidny/’,’迪斯廷凯’],
311.     [‘zs.efu.com.cn/fuzhuang/luyidigao/’,’路易迪高童装代{过}{滤}理’],
312.     [‘brand.efu.com.cn/brandshow-1221090.html’,’凯帝龙驰’],
313.     [‘zs.efu.com.cn/rabbitjero/’,’兔子杰罗’],
314.     [‘zs.efu.com.cn/wmprince/’,’西瓜王子’],
315.         [‘zs.efu.com.cn/betu’,’百图’],
316.         [‘zs.efu.com.cn/pepco/’,’小猪班纳’],
319.     #[‘http://news.ifeng.com/a/20160518/48795120_0.shtml’,’华夏信财’],
320.     [‘http://weibo.com/huaxiafinance’,’华夏信财’],
321.     [‘http://p2p.hexun.com/2016-04-26/183531215.html’,’华夏信财’],
322.     #[‘http://news.xinhuanet.com/fortune/2016-04/26/c_128932834.htm’,’华夏信财’],
323.     [‘http://www.xcf.cn/gdyw/201605/t20160526_772682.htm’,’华夏信财’],
324.     [‘http://www.huaxiaoxia.com/’,’华夏信财’],
325.         #[‘https://lc.huaxiafinance.com/’,’华夏信财’],
329.         [‘so.tedu.cn’,’网络营销培训机构’],
330.         [‘www.cosatto.net.cn’,’个性安全座椅’],
331.         [‘www.kaihuata.com/’,’开化旅游’],
332.         #[‘www.kaihuata.com/’,’开化’],
334. ]
337. for targetInfo in targetURL:
338.     try:
339.         #更换ip
340.         disconnect()
341.         connect()
343.         while(1):
344.                     try:
345.                         socket.gethostbyname(“baidu.com”)
346.                         break;
347.                     except:
348.                         disconnect()
349.                         connect()
350.         #更换分辨率
351.         #setDisplay()
354.         #启动浏览器
355.         #driver = webdriver.Ie()
356.         #driver = webdriver.Chrome()
357.         #driver = webdriver.Firefox()
359.         #设置PhantomJS的user_agent
360.         dcap = dict(DesiredCapabilities.PHANTOMJS)
361.         user_agent = getUA()
362.         print(user_agent)
363.         dcap[“phantomjs.page.settings.userAgent”] = (
364.                 user_agent
365.         )
366.         #dcap[“phantomjs.page.settings.resourceTimeout”] = (15000)
367.         dcap[“phantomjs.page.settings.loadImages”] = (False)
368.         driver = webdriver.PhantomJS(desired_capabilities=dcap,service_args=[‘–load-images=no’])
371.         # UA = getUA()
372.         # print(UA)
373.         # webdriver.DesiredCapabilities.PHANTOMJS[‘phantomjs.page.customHeaders.User-Agent’] = UA
374.         # driver = webdriver.PhantomJS()
376.         driver.implicitly_wait(30)
378.         #清cookie
379.         driver.delete_all_cookies()
381.         #driver.maximize_window() # 浏览器全屏显示
383.         #打开百度
384.         driver.get(“http://www.baidu.com/”)
385.         #driver.get(“http://mch.weiba01.com/2.php”)
387.         #设置浏览器窗口大小
388.         window_size = getWindowSize()
389.         driver.set_window_size(window_size[0], window_size[1])
392.         #搜索某个关键词
393.         print(‘打开百度成功’,driver.title)
394.         target = targetInfo[0]
395.         keyword = targetInfo[1]
396.         if len(targetInfo)>2:
397.                 error_keyword = targetInfo[random.randint(2,len(targetInfo)-1)]
398.         print(“>>>>>>>>>>>>>>>点击的关键词：”,keyword,”—>目标地址：”,target,”>>>>>>>>>>>>>>>>>>>>”)
401.         if len(targetInfo)>2:
402.             #模拟错误关键词
403.             print(“点击错误关键词：”,error_keyword);
404.             driver.find_element_by_id(“kw”).send_keys(error_keyword)
405.             time.sleep(2)
406.             driver.find_element_by_id(“su”).click()
407.             time.sleep(5)
408.             driver.find_element_by_id(“kw”).clear()
409.             time.sleep(2)
410.             print(“错误关键词点击完毕”)
412.         driver.find_element_by_id(“kw”).send_keys(keyword)
413.         #time.sleep(2)
415.         #点击搜索按钮
416.         print(“…开始点击搜索按钮..”)
417.         driver.find_element_by_id(“su”).click()
418.         #exit()
419.         print(“…点击完毕..”)
420.         time.sleep(2)
423.         #获取搜索结果页 0:着陆页  1：对应的链接对象
424.         urls_res = get_search_url(driver)
425.         real_urls = urls_res[0]
426.         #get_search_url(driver)[1][2].click()
429.         #real_urls = get_real_url(urls)
430.         print(“搜索出来的可点击着陆页个数：”,len(real_urls))
431.         print(real_urls)
432.         index = get_urlIndex(target,real_urls)
433.         print(“目标index:”,index)
435.         page = 1
436.         while index == -1 and page <= 4:
437.             if page == 1:
438.                 #点击前面的几个着陆页,模拟用户真实行为
439.                 items = get_random_index(index,len(real_urls))
440.                 #items = [4]
441.                 print(items)
442.                 click_search_url(driver,items)
444.             #下一页
445.             driver = click_nextBtn(driver)
446.             time.sleep(3)
447.             urls_res = get_search_url(driver)
448.             real_urls = urls_res[0]
449.             #real_urls = get_real_url(urls)
450.             print(real_urls)
451.             index = get_urlIndex(target,real_urls)
453.             page = page+1
457.         if index > 4 and page == 1:
458.             #第一页，随机点击两个或一个
459.             int = random.randint(1,2)
460.             if int == 2:
461.                 items = get_random_index(index,len(real_urls))
462.             else:
463.                 items = [1]
464.             print(items)
465.             click_search_url(driver,items)
467.         if page >=5:
468.             print(“没有找到目标地址，放弃搜索…”)
469.             print(“关闭浏览器”)
470.             driver.quit()
472.             time.sleep(5)
473.             data = get_ip()
474.             data.append(keyword)
475.             data.append(target)
476.             data.append(“no_find”)
477.             data.append(-1)
478.             data.append(-1)
479.             insert_db(data)
480.             continue
482.         print(“目标在page”,page,”当前排名：”,index,real_urls[index])
483.         print(“反问最后的目标页…”)
484.         #driver.get(real_urls[index])
485.         urls_res[1][index].click()
486.         time.sleep(5)
488.         nowhandle = driver.current_window_handle
489.         allhandles = driver.window_handles
490.         #目标页和搜索栏目页切换下
491.         for handle in allhandles:
492.             if handle != nowhandle:
493.                 print(“切换到当前窗口”)
494.                 driver.switch_to_window(handle)
495.                 stime = random.randint(15,25)
496.                 #stime = 5;
497.                 print(“目标页title:”,driver.title,”停留–>”,stime)
498.                 time.sleep(stime)
499.                 ”’关闭当前窗口”’
500.                 driver.close()
502.                 ”’回到原先的窗口”’
503.                 print(“切换到原来的窗口”)
504.                 driver.switch_to_window(nowhandle)
505.                 print(“title:”,driver.title)
508.         #time.sleep(random.randint(40,60))
509.         #time.sleep(5)
511.         #清除所有cookie
512.         print(“打印cookie”)
513.         cookie= driver.get_cookies()
514.         print(cookie)
515.         print(“清除cookie”)
516.         driver.delete_all_cookies()
517.         print(“打印cookie:”)
518.         cookie= driver.get_cookies()
519.         print(cookie)
521.         #关闭浏览器
522.         print(“关闭浏览器”)
523.         time.sleep(5)
524.         #driver.close()
525.         driver.quit()
526.         #time.sleep(5)
528.         #数据库记录运行信息
529.         data = get_ip()
530.         data.append(keyword)
531.         data.append(target)
532.         data.append(“success”)
533.         data.append(page)
534.         data.append(index)
535.         insert_db(data)
537.     except:
538.         data = get_ip()
539.         data.append(keyword)
540.         data.append(target)
541.         data.append(“faild”)
542.         data.append(-1)
543.         data.append(-1)
544.         insert_db(data)