百度SEO快排秘籍：发包代码实操指南，快速提升网站排名！

www.tx7878.cn|绝对压力变送器
www.tx7878.cn|EJA变送器
www.tx7878.cn|静压式液位计
www.tx7878.cn|温度漂移
www.tx7878.cn|弹簧管压力表
www.tx7878.cn|压力控制
www.tx7878.cn|料位计
www.tx7878.cn|高温压力传感器
www.tx7878.cn|界位
www.tx7878.cn|磁致伸缩传感器
www.tx7878.cn|连杆浮球液位开关
www.tx7878.cn|磁浮子液位计
www.tx7878.cn|液位控制系统
www.tx7878.cn|差压传感器
www.tx7878.cn|射频导纳
www.tx7878.cn|料位仪
www.tx7878.cn|超声流量计
www.tx7878.cn|数字压力计
www.tx7878.cn|压力分布

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC

from selenium.webdriver import ActionChains
import time,random,requests,json
from selenium.webdriver.common.keys import Keys
import os, subprocess,datetime
import multiprocessing
import undetected_chromedriver as uc

# 排除关键词列表
# exclude_keywords = []
# cmd = '"C:\Program Files\Google\Chrome\Application\chrome.exe" ' \
# '--remote-debugging-port=9222 ' \
# '--user-data-dir="C:\selenium\ChromeProfile"'
# subprocess.run(cmd) 
# with open('./stealth.min.js') as f:
#     js = f.read()

#屏蔽的目标网站
ExcludetargetURL = [
    "https://www.baidu.com/"
]

class GoogleSearch:
    def __init__(self):
        options = uc.ChromeOptions()
        self.depth_deep = 15
        options.add_argument(f'--user-agent={self.random_useragent()}')
        options.add_argument("--disable-popup-blocking")
        options.add_argument('--ignore-ssl-errors=true')
        options.add_argument("--disable-extensions")
        options.add_argument("--disable-popup-blocking")
        options.add_argument("--profile-directory=Default")
        options.add_argument("--ignore-certificate-errors")
        options.add_argument("--disable-plugins-discovery")
        options.add_argument('--incognito')
        options.add_argument("--disable-infobars")
        options.add_argument("--no-default-browser-check")
        # options.add_experimental_option("useAutomationExtension", False)
        options.add_argument('--load-images=no')
        options.add_argument('--no-first-run')
        options.add_argument('--no-service-autorun')
        options.add_argument('--no-default-browser-check')
        options.add_argument('--password-store=basic')
        options.add_argument('--no-sandbox')
        options.add_argument('--proxy-type=http')
        options.add_argument('--ssl-protocol=TLSv1')
        # options.add_experimental_option("debuggerAddress", "127.0.0.1:9222")
        # 去除顶部浏览器提示
        # options.add_experimental_option('excludeSwitches', ['enable-automation'])
        # 修改webdriver浏览器特征
        # options.add_experimental_option('useAutomationExtension', False)
        # options.add_argument('headless')
        self.driver = uc.Chrome(headless=True,use_subprocess=False,executable_path='./chromedriver.exe',options=options)
        # self.driver = webdriver.Chrome(executable_path='./chromedriver.exe', options=options)
        self.driver.implicitly_wait(30)
        self.driver.delete_all_cookies()
    
    #随机浏览器UA
    def random_useragent(self):
        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 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36',
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36"
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/121.0.0.0 Safari/537.36"
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.0.0 Safari/537.36"
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/97.0.0.0 Safari/537.36"
	    ]
        return random.choice(UaList)
    
    #随机滑动500-1000的距离
    def random_scroll(self):
        for i in range(random.randint(1,3)):
            self.driver.execute_script(f'window.scrollTo(0, {random.randint(500, 20000)})')
            time.sleep(0.4)
        return True


    # 随机浏览器屏幕分辨率
    def random_screen(self):
        screen_list = [
            (1920, 1080),
            (1600, 900),
            (1440, 900),
            (1366, 768),
            (1280, 1024),
            (1280, 800),
            (1024, 768)
        ]
        return random.choice(screen_list)
    
    #设置电脑屏幕分辨率
    def set_screen(self):
        self.driver.set_window_size(1920, 1080)


    # 随机延迟0.2-3秒
    def random_delay(self):
        time.sleep(random.uniform(1, 3))
        return True
    
    # 随机点击页面
    def random_click(self,elements):
        if len(elements) > 0:
        # 随机选择一个元素
            click_index = random.randint(0, len(elements) - 1)
            try:
                # 尝试获取链接并触发点击
                link = elements[click_index].find_element(By.TAG_NAME, 'a')
                self.driver.execute_script("arguments[0].click();", link)
                self.random_delay()

                # 检查是否有新窗口打开
                windows = self.driver.window_handles
                if len(windows) > 1:
                    new_window = windows[-1]
                    self.driver.switch_to.window(new_window)
                    # 等待新页面加载（根据需要调整等待时间）
                    self.random_delay()
                    # 在新窗口中关闭
                    self.driver.close()
                    # 切换回原始窗口
                    self.driver.switch_to.window(windows[0])
                    self.random_delay()
            except Exception as e:
                print(f"An error occurred: {e}")
    def elementCLick(self,element,keyword,index):
        # 通常新打开的窗口或标签页是列表中的最后一个
        # self.driver.execute_script("arguments[0].click();", element)
        self.random_delay()
        try:
            self.random_scroll()
            try:
                element.click()
            except:
                href = element.find_element(By.TAG_NAME, 'a').get_attribute('href')
                cmd = f"window.open('{href}');"
                self.driver.execute_script(cmd)
            with open("result.txt", "a+",encoding="utf-8") as f:
                #获取当前时间
                datetime = time.strftime("%Y-%m-%d %H:%M:%S",time.localtime())
                f.write(f"时间:{datetime},ip:{self.get_public_ip()} 关键词:{keyword} ,排名:{index}  \n")
                print("写入成功")
          
            while True:
                windows = self.driver.window_handles
                if len(windows)>1:
                    new_window = windows[-1]
                    self.driver.switch_to.window(new_window)
                    # 等待新页面加载（根据需要调整等待时间）
                    # self.random_delay()
                    # 在新窗口中关闭
                    self.driver.close()
                    # 切换回原始窗口
                    # self.random_delay()
                else:
                    break
            self.driver.switch_to.window(windows[0])
        except Exception as e:
            print(f"An error occurred: {e}")
            pass
       
        
    def get_search_results(self, keyword):
        results = []
        try:
            window_size = self.random_screen()
            self.driver.set_window_size(window_size[0], window_size[1])
            self.random_delay()
            input_keyword = self.driver.find_element(By.ID, "kw")
            input_keyword.clear()
            input_keyword.send_keys(keyword)
            self.random_delay()
            action = random.randint(0, 1)
            if action == 0:
                # 点击搜索按钮
                self.driver.find_element(By.ID, "su").click()
                self.random_delay()
                print("鼠标点击按钮")
            else:
                input_keyword.send_keys(Keys.ENTER)
                print("按下了Enter")
            self.random_delay()
            print('打开百度成功',self.driver.title)
            self.random_scroll()
            elements_hrefs = self.driver.find_elements(By.XPATH, '//h3[@class="c-title t t tts-title"]')
            # self.random_click(elements_hrefs)
            return elements_hrefs
        except Exception as e:
            print("打开百度失败",e)
            results = []
        return results

    #获取真实的url
    def get_real_url(self, url):
        try:
            url = requests.get(url, headers={'User-Agent': self.random_useragent()},allow_redirects=False)
            real_url = url.headers['location']
            return real_url
        except Exception as e:
                print("获取真实URL失败",e)
                return ''

    def get_public_ip(self):
        response = requests.get("http://httpbin.org/ip")
        data = response.json()
        ip = data['origin']
        return ip

    def search_google(self, item, depth=1):
        try:
            # 去除唯一值,防止重复搜索
            url_ip,keyword = item
            self.driver.get(f'https://www.baidu.com')
            print(">>>>>>>>>>点击的关键词：",keyword,"--->目标地址：",url_ip,">>>>>>>>>>>>>>>>")
            elements_hrefs = self.get_search_results(keyword)
            # 模拟用户真实行为,滑动屏幕
            for index, element in enumerate(elements_hrefs):
                url = element.find_element(By.XPATH,'.//a').get_attribute('href')
                real_url = self.get_real_url(url)
                if real_url != '':
                    if url_ip in real_url:
                        print("存在真实url",real_url)
                        self.elementCLick(element,keyword,index)
                        return True
            
            connt = 1
            for pn in range(self.depth_deep):
                print(f"============={connt}==============")
                while True:
                    windows = self.driver.window_handles
                    if len(windows)>1:
                        new_window = windows[-1]
                        self.driver.switch_to.window(new_window)
                        # 等待新页面加载（根据需要调整等待时间）
                        # self.random_delay()
                        # 在新窗口中关闭
                        self.driver.close()
                        # 切换回原始窗口
                        # self.random_delay()
                    else:
                        self.driver.switch_to.window(windows[0])
                        break
                try:
                    elems = self.driver.find_elements(By.CLASS_NAME,'n')
                    elems[-1].click()
                except:
                    self.driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")
                    elems = self.driver.find_elements(By.CLASS_NAME,'n')
                    elems[-1].click()
                self.random_delay()
                elements_hrefs = self.driver.find_elements(By.XPATH, '//h3[@class="c-title t t tts-title"]')
                self.random_click(elements_hrefs)
                for index, element in enumerate(elements_hrefs):
                    url = element.find_element(By.XPATH,'.//a').get_attribute('href')
                    real_url = self.get_real_url(url)
                    if real_url != '':
                        # print(real_url)
                        if url_ip in real_url:
                            print("存在真实url",real_url)
                            depth = 20
                            # self.elementCLick(element,keyword,index)
                            self.elementCLick(element,keyword,connt*len(elements_hrefs)+index)
                            return True
                connt +=1
        except Exception as e:
            print("搜索失败",e)
        return False
            

    def read_from_file(self):
        with open('keyword.txt', 'r', encoding='utf-8') as file:
            for line in file.readlines():
                self.search_google(line.strip().split("|"))
        self.driver.quit()
        print("搜索完成")
    # 包含关键词列表
    def write_to_file(self, title):
        with open("result.txt", "a+", encoding="utf-8") as file:
            file.write(title + "\n")

# 随机切换ip
def random_ip():
    import os
    try:
        os.system("rasdial 宽带连接  /disconnect") 
        time.sleep(5)
        os.system("rasdial 宽带连接  21261637 147258") 
        time.sleep(10)
    except Exception as e:
        print("切换ip失败",e)
    # ip = requests.get("http://httpbin.org/ip")
    # data = ip.json()
    # ip_list = data['origin'].split(", ")
    # # 随机切换ip
    # random.shuffle(ip_list)
    # return ip_list[0]
if __name__ == "__main__":
    multiprocessing.freeze_support()
    for cou in range(1,16):
        # random_ip()
        google_search = GoogleSearch()
        google_search.read_from_file()
        time.sleep(10)

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC

from selenium.webdriver import ActionChains
import time,random,requests,json
from selenium.webdriver.common.keys import Keys
import os, subprocess,datetime
import multiprocessing
import undetected_chromedriver as uc

# 排除关键词列表
# exclude_keywords = []
# cmd = '"C:\Program Files\Google\Chrome\Application\chrome.exe" ' \
# '--remote-debugging-port=9222 ' \
# '--user-data-dir="C:\selenium\ChromeProfile"'
# subprocess.run(cmd) 
# with open('./stealth.min.js') as f:
#     js = f.read()

#屏蔽的目标网站
ExcludetargetURL = [
    "https://openinstall.io/"
]

class GoogleSearch:
    def __init__(self):
        options = webdriver.ChromeOptions()
        self.depth_deep = 15
        options.add_argument(f'--user-agent={self.random_useragent()}')
        options.add_argument("--disable-popup-blocking")
        options.add_argument('--ignore-ssl-errors=true')
        options.add_argument("--disable-extensions")
        options.add_argument("--disable-popup-blocking")
        options.add_argument("--profile-directory=Default")
        options.add_argument("--ignore-certificate-errors")
        options.add_argument("--disable-plugins-discovery")
        options.add_argument('--incognito')
        options.add_argument("--disable-infobars")
        options.add_argument("--no-default-browser-check")
        # options.add_experimental_option("useAutomationExtension", False)
        options.add_argument('--load-images=no')
        options.add_argument('--no-first-run')
        options.add_argument('--no-service-autorun')
        options.add_argument('--no-default-browser-check')
        options.add_argument('--password-store=basic')
        options.add_argument('--no-sandbox')
        options.add_argument('--proxy-type=http')
        options.add_argument('--ssl-protocol=TLSv1')
        options.add_experimental_option("debuggerAddress", "127.0.0.1:9222")
        # 去除顶部浏览器提示
        # options.add_experimental_option('excludeSwitches', ['enable-automation'])
        # 修改webdriver浏览器特征
        # options.add_experimental_option('useAutomationExtension', False)
        # options.add_argument('headless')
        # self.driver = uc.Chrome(headless=True,use_subprocess=False,executable_path='./chromedriver.exe',options=options)
        self.driver = webdriver.Chrome(executable_path='./chromedriver.exe', options=options)
        self.driver.implicitly_wait(30)
        # self.driver.delete_all_cookies()
    
    #随机浏览器UA
    def random_useragent(self):
        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 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36',
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36"
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/121.0.0.0 Safari/537.36"
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.0.0 Safari/537.36"
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/97.0.0.0 Safari/537.36"
	    ]
        return random.choice(UaList)
    
    #随机滑动500-1000的距离
    def random_scroll(self):
        for i in range(random.randint(1,3)):
            self.driver.execute_script(f'window.scrollTo(0, {random.randint(500, 20000)})')
            time.sleep(0.4)
        return True


    # 随机浏览器屏幕分辨率
    def random_screen(self):
        screen_list = [
            (1920, 1080),
            (1600, 900),
            (1440, 900),
            (1366, 768),
            (1280, 1024),
            (1280, 800),
            (1024, 768)
        ]
        return random.choice(screen_list)
    
    #设置电脑屏幕分辨率
    def set_screen(self):
        self.driver.set_window_size(1920, 1080)


    # 随机延迟0.2-3秒
    def random_delay(self):
        time.sleep(random.uniform(2, 5))
        return True
    
    # 随机点击页面
    def random_click(self,elements):
        if len(elements) > 0:
        # 随机选择一个元素
            click_index = random.randint(0, len(elements) - 1)
            try:
                # 尝试获取链接并触发点击
                link = elements[click_index].find_element(By.TAG_NAME, 'a')
                self.driver.execute_script("arguments[0].click();", link)
                self.random_delay()

                # 检查是否有新窗口打开
                windows = self.driver.window_handles
                if len(windows) > 1:
                    new_window = windows[-1]
                    self.driver.switch_to.window(new_window)
                    # 等待新页面加载（根据需要调整等待时间）
                    self.random_delay()
                    # 在新窗口中关闭
                    self.driver.close()
                    # 切换回原始窗口
                    self.driver.switch_to.window(windows[0])
                    self.random_delay()
            except Exception as e:
                print(f"An error occurred: {e}")
    def elementCLick(self,element,keyword,index):
        # 通常新打开的窗口或标签页是列表中的最后一个
        # self.driver.execute_script("arguments[0].click();", element)
        self.random_delay()
        try:
            self.random_scroll()
            try:
                element.click()
            except:
                href = element.find_element(By.TAG_NAME, 'a').get_attribute('href')
                cmd = f"window.open('{href}');"
                self.driver.execute_script(cmd)
            with open("result.txt", "a+",encoding="utf-8") as f:
                #获取当前时间
                datetime = time.strftime("%Y-%m-%d %H:%M:%S",time.localtime())
                f.write(f"时间:{datetime},ip:{self.get_public_ip()} 关键词:{keyword} ,排名:{index}  \n")
                print("写入成功")
            # windows = self.driver.window_handles
            # new_window = windows[-1]
            # self.driver.switch_to.window(new_window)
            # links = WebDriverWait(self.driver, 10).until(EC.presence_of_all_elements_located((By.TAG_NAME, 'a')))
            # if links:
                
            #     random_link = random.choice(links)
            #     random_link.click()
            #     self.random_scroll()
            #     print(f"Clicked on random link: {random_link.get_attribute('href')}")
            # else:
            #     print("No links found on the page.")
            
            while True:
                windows = self.driver.window_handles
                if len(windows)>1:
                    new_window = windows[-1]
                    self.driver.switch_to.window(new_window)
                    # 等待新页面加载（根据需要调整等待时间）
                    # self.random_delay()
                    # 在新窗口中关闭
                    self.driver.close()
                    # 切换回原始窗口
                    # self.random_delay()
                else:
                    break
            self.driver.switch_to.window(windows[0])
        except Exception as e:
            print(f"An error occurred: {e}")
            pass
       
        
    def get_search_results(self, keyword):
        results = []
        try:
            window_size = self.random_screen()
            self.driver.set_window_size(window_size[0], window_size[1])
            self.random_delay()
            input_keyword = self.driver.find_element(By.ID, "kw")
            input_keyword.clear()
            input_keyword.send_keys(keyword)
            self.random_delay()
            action = random.randint(0, 1)
            if action == 0:
                # 点击搜索按钮
                self.driver.find_element(By.ID, "su").click()
                self.random_delay()
                # print("鼠标点击按钮")
            else:
                input_keyword.send_keys(Keys.ENTER)
                # print("按下了Enter")
            self.random_delay()
            # print('打开百度成功',self.driver.title)
            # self.random_scroll()
            elements_hrefs = self.driver.find_elements(By.XPATH, '//h3[@class="c-title t t tts-title"]')
            # self.random_click(elements_hrefs)
            return elements_hrefs
        except Exception as e:
            print("打开百度失败",e)
            results = []
        return results

    #获取真实的url
    def get_real_url(self, url):
        try:
            url = requests.get(url, headers={'User-Agent': self.random_useragent()},allow_redirects=False)
            real_url = url.headers['location']
            return real_url
        except Exception as e:
                print("获取真实URL失败",e)
                return ''

    def get_public_ip(self):
        response = requests.get("http://httpbin.org/ip")
        data = response.json()
        ip = data['origin']
        return ip

    def search_google(self, item, depth=1):
        try:
            # 去除唯一值,防止重复搜索
            url_ip,keyword = item
            self.driver.get(f'https://www.baidu.com')
            print(">>>>>>>>>>点击的关键词：",keyword,"--->目标地址：",url_ip,">>>>>>>>>>>>>>>>")
            elements_hrefs = self.get_search_results(keyword)
            # 模拟用户真实行为,滑动屏幕
            for index, element in enumerate(elements_hrefs):
                url = element.find_element(By.XPATH,'.//a').get_attribute('href')
                real_url = self.get_real_url(url)
                if real_url != '':
                    if url_ip in real_url:
                        print("存在真实url",real_url)
                        self.elementCLick(element,keyword,index)
                        return True
            
            connt = 1
            for pn in range(self.depth_deep):
                print(f"暂时无数据包，正在加载第{pn+1}页")
                while True:
                    windows = self.driver.window_handles
                    if len(windows)>1:
                        new_window = windows[-1]
                        self.driver.switch_to.window(new_window)
                        # 等待新页面加载（根据需要调整等待时间）
                        # self.random_delay()
                        # 在新窗口中关闭
                        self.driver.close()
                        # 切换回原始窗口
                        # self.random_delay()
                    else:
                        self.driver.switch_to.window(windows[0])
                        break
                try:
                    elems = self.driver.find_elements(By.CLASS_NAME,'n')
                    elems[-1].click()
                except:
                    self.driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")
                    elems = self.driver.find_elements(By.CLASS_NAME,'n')
                    elems[-1].click()
                self.random_delay()
                elements_hrefs = self.driver.find_elements(By.XPATH, '//h3[@class="c-title t t tts-title"]')
                # self.random_click(elements_hrefs)
                for index, element in enumerate(elements_hrefs):
                    url = element.find_element(By.XPATH,'.//a').get_attribute('href')
                    real_url = self.get_real_url(url)
                    if real_url != '':
                        # print(real_url)
                        if url_ip in real_url:
                            print("存在真实url",real_url)
                            depth = 20
                            # self.elementCLick(element,keyword,index)
                            self.elementCLick(element,keyword,connt*len(elements_hrefs)+index)
                            return True
                connt +=1
        except Exception as e:
            print("搜索失败",e)
        return False
            

    def read_from_file(self):
        with open('keyword.txt', 'r', encoding='utf-8') as file:
            for line in file.readlines():
                self.search_google(line.strip().split("|"))
        self.driver.quit()
        print("搜索完成")
    # 包含关键词列表
    def write_to_file(self, title):
        with open("result.txt", "a+", encoding="utf-8") as file:
            file.write(title + "\n")

# 随机切换ip
def random_ip():
    import os
    try:
        os.system("rasdial 宽带连接  /disconnect") 
        time.sleep(5)
        os.system("rasdial 宽带连接  21261637 147258") 
        time.sleep(10)
    except Exception as e:
        print("切换ip失败",e)
    # ip = requests.get("http://httpbin.org/ip")
    # data = ip.json()
    # ip_list = data['origin'].split(", ")
    # # 随机切换ip
    # random.shuffle(ip_list)
    # return ip_list[0]
if __name__ == "__main__":
    multiprocessing.freeze_support()
    for cou in range(1,16):
        # random_ip()
        google_search = GoogleSearch()
        google_search.read_from_file()
        time.sleep(10)

from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver import ActionChains
import time,random,requests,json5
from selenium.webdriver.common.keys import Keys
import os, subprocess,datetime
import multiprocessing,re,platform

# 根据平台选择WebDriver
if platform.system() == "Windows":
    from undetected_chromedriver import ChromeOptions, Chrome as WebDriver
else:
    from selenium import webdriver
    WebDriver = webdriver.Chrome
    ChromeOptions = webdriver.ChromeOptions


class GoogleSearch:
    SEARCH_ENGINE_URL = 'https://www.sogou.com/?'
    NEXT_PAGE_ID = 'sogou_next'
    RESULT_CLASS_NAME = 'vrwrap'
    def __init__(self):
        self.depth_deep = 10
        options = ChromeOptions()
        options.add_argument(f'--user-agent={self.random_useragent()}')
        options.add_argument("--disable-popup-blocking")
        options.add_argument('--ignore-ssl-errors=true')
        options.add_argument("--disable-extensions")
        options.add_argument("--profile-directory=Default")
        options.add_argument("--ignore-certificate-errors")
        options.add_argument("--disable-plugins-discovery")
        options.add_argument('--incognito')
        options.add_argument("--disable-infobars")
        options.add_argument("--no-default-browser-check")
        options.add_argument('--load-images=no')
        options.add_argument('--no-first-run')
        options.add_argument('--no-service-autorun')
        options.add_argument('--password-store=basic')
        options.add_argument('--no-sandbox')
        # options.add_argument('--proxy-type=http')
        # options.add_argument('--ssl-protocol=TLSv1')
        
        # 初始化WebDriver
        if platform.system() == "Windows":
            self.driver = WebDriver(options=options,headless=True,use_subprocess=False)
        else:
            self.driver = WebDriver(executable_path='./chromedriver.exe', options=options)
        
        self.driver.implicitly_wait(30)
        self.driver.delete_all_cookies()
    

        # options.add_experimental_option("debuggerAddress", "127.0.0.1:9222")
        # 去除顶部浏览器提示
        # options.add_experimental_option('excludeSwitches', ['enable-automation'])
        # 修改webdriver浏览器特征
        # options.add_experimental_option('useAutomationExtension', False)
        # options.add_argument('headless')
    
    #随机浏览器UA
    def random_useragent(self):
        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 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36',
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36"
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/121.0.0.0 Safari/537.36"
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.0.0 Safari/537.36"
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/97.0.0.0 Safari/537.36"
	    ]
        return random.choice(UaList)
    
    #随机滑动500-1000的距离
    def random_scroll(self):
        for i in range(random.randint(1,3)):
            self.driver.execute_script(f'window.scrollTo(0, {random.randint(500, 20000)})')
            time.sleep(0.4)
        return True


    # 随机浏览器屏幕分辨率
    def random_screen(self):
        screen_list = [
            (1920, 1080),
            (1600, 900),
            (1440, 900),
            (1366, 768),
            (1280, 1024),
            (1280, 800),
            (1024, 768)
        ]
        return random.choice(screen_list)
    
    #设置电脑屏幕分辨率
    def set_screen(self):
        self.driver.set_window_size(1920, 1080)


    # 随机延迟0.2-3秒
    def random_delay(self):
        time.sleep(random.uniform(1, 3))
        return True
    
    # 随机点击页面
    def random_click(self,elements):
        if len(elements) > 0:
        # 随机选择一个元素
            click_index = random.randint(0, len(elements) - 1)
            try:
                # 尝试获取链接并触发点击
                link = elements[click_index].find_element(By.TAG_NAME, 'a')
                self.driver.execute_script("arguments[0].click();", link)
                self.random_delay()

                # 检查是否有新窗口打开
                windows = self.driver.window_handles
                if len(windows) > 1:
                    new_window = windows[-1]
                    self.driver.switch_to.window(new_window)
                    # 等待新页面加载（根据需要调整等待时间）
                    self.random_delay()
                    # 在新窗口中关闭
                    self.driver.close()
                    # 切换回原始窗口
                    self.driver.switch_to.window(windows[0])
                    self.random_delay()
            except Exception as e:
                print(f"An error occurred: {e}")

    def elementCLick(self,element,keyword,index):
        # 通常新打开的窗口或标签页是列表中的最后一个
        # self.driver.execute_script("arguments[0].click();", element)
        self.random_delay()
        try:
            self.random_scroll()
            try:
                element.find_element(By.TAG_NAME, 'a').click()
            except:
                href = element.find_element(By.TAG_NAME, 'a').get_attribute('href')
                cmd = f"window.open('{href}');"
                self.driver.execute_script(cmd)
                times = random.randint(10,24)
                print(f"停留{times}秒")
            time.sleep(random.randint(10,24))
            self.random_scroll()
            with open("result.txt", "a+",encoding="utf-8") as f:
                #获取当前时间
                datetime = time.strftime("%Y-%m-%d %H:%M:%S",time.localtime())
                f.write(f"时间:{datetime},ip:{self.get_public_ip()} 关键词:{keyword} ,排名:{index}  \n")
                print("写入成功")
            # windows = self.driver.window_handles
            # new_window = windows[-1]
            # self.driver.switch_to.window(new_window)
            # links = WebDriverWait(self.driver, 10).until(EC.presence_of_all_elements_located((By.TAG_NAME, 'a')))
            # if links:
                
            #     random_link = random.choice(links)
            #     random_link.click()
            #     self.random_scroll()
            #     print(f"Clicked on random link: {random_link.get_attribute('href')}")
            # else:
            #     print("No links found on the page.")
            
            while True:
                windows = self.driver.window_handles
                if len(windows)>1:
                    new_window = windows[-1]
                    self.driver.switch_to.window(new_window)
                    # 等待新页面加载（根据需要调整等待时间）
                    # self.random_delay()
                    # 在新窗口中关闭
                    self.driver.close()
                    # 切换回原始窗口
                    # self.random_delay()
                else:
                    break
            self.driver.switch_to.window(windows[0])
        except Exception as e:
            print(f"An error occurred: {e}")
            pass
       
        
    def get_search_results(self, url_ip,keyword):
        results = []
        try:
            window_size = self.random_screen()
            self.driver.set_window_size(window_size[0], window_size[1])
            self.random_delay()
            input_keyword = self.driver.find_element(By.ID, "query")
            input_keyword.clear()
            # input_keyword.send_keys(f"site {url_ip} {keyword}" )
            input_keyword.send_keys(keyword )
            self.random_delay()
            action = random.randint(0, 1)
            if action == 0:
                # 点击搜索按钮
                self.driver.find_element(By.ID, "stb").click()
                self.random_delay()
                print("鼠标点击按钮")
            else:
                input_keyword.send_keys(Keys.ENTER)
                print("按下了Enter")
            self.random_delay()
            print('打开搜狗成功',self.driver.title)
            self.random_scroll()
            elements_hrefs = self.driver.find_elements(By.CLASS_NAME, 'vrwrap')
            # self.random_click(elements_hrefs)
            return elements_hrefs
        except Exception as e:
            print("打开搜狗失败",e)
            results = []
        return results

    #获取真实的url
    def get_real_url(self, url):
        try:
            url = requests.get(url, headers={'User-Agent': self.random_useragent()},allow_redirects=False)
            real_url = url.text
            real_url = re.findall(r'window.location.replace\("(.*?)"\)', real_url)[0]
            print(f"解析真实Url:{real_url}")
            return real_url
        except Exception as e:
            print("获取真实URL失败",e)
            return ''

    def get_public_ip(self):
        response = requests.get("http://httpbin.org/ip")
        data = response.json()
        ip = data['origin']
        return ip

    def search_google(self, item, depth=1):
        try:
            # 去除唯一值,防止重复搜索
            url_ip,keyword = item
            self.driver.get(self.SEARCH_ENGINE_URL)
            print(">>>>>>>>>>点击的关键词：",keyword,"--->目标地址：",url_ip,">>>>>>>>>>>>>>>>")
            results = self.get_search_results(url_ip,keyword)
            # 模拟用户真实行为,滑动屏幕
            for index, element in enumerate(results):
                url = element.find_element(By.XPATH,'.//a').get_attribute('href')
                real_url = self.get_real_url(url)
                if real_url != '':
                    if url_ip in real_url:
                        print("存在真实url",real_url)
                        self.elementCLick(element,keyword,index+1)
                        return True
            
            connt = 1
            for pn in range(self.depth_deep):
                print(f"============={connt}==============")
                while True:
                    windows = self.driver.window_handles
                    if len(windows)>1:
                        new_window = windows[-1]
                        self.driver.switch_to.window(new_window)
                        # 等待新页面加载（根据需要调整等待时间）
                        # self.random_delay()
                        # 在新窗口中关闭
                        self.driver.close()
                        # 切换回原始窗口
                        # self.random_delay()
                    else:
                        self.driver.switch_to.window(windows[0])
                        break
                try:
                    elems = self.driver.find_elements(By.ID,'sogou_next')
                    elems[-1].click()
                except:
                    self.driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")
                    elems = self.driver.find_elements(By.CLASS_NAME,'n')
                    elems[-1].click()
                self.random_delay()
                elements_hrefs = self.driver.find_elements(By.CLASS_NAME, 'vrwrap')
                # self.random_click(elements_hrefs)
                for index, element in enumerate(elements_hrefs):
                    url = element.find_element(By.XPATH,'.//a').get_attribute('href')
                    real_url = self.get_real_url(url)
                    if real_url != '':
                        # print(real_url)
                        if url_ip in real_url:
                            print("存在真实url",real_url)
                            self.depth = 20
                            # self.elementCLick(element,keyword,index)
                            self.elementCLick(element,keyword,connt*len(elements_hrefs)+index)
                            return True
                connt +=1
        except Exception as e:
            print("搜索失败",e)
        return False
            

    def read_from_file(self):
        with open('keyword.txt', 'r', encoding='utf-8') as file:
            for line in file.readlines():
                self.search_google(line.strip().split("|"))
        self.driver.quit()
        print("搜索完成")
    # 包含关键词列表
    def write_to_file(self, title):
        with open("result.txt", "a+", encoding="utf-8") as file:
            file.write(title + "\n")

# 随机切换ip
def random_ip():
    import os
    try:
        os.system("rasdial 宽带连接  /disconnect") 
        time.sleep(5)
        os.system("rasdial 宽带连接  21261637 147258") 
        time.sleep(10)
    except Exception as e:
        print("切换ip失败",e)

if __name__ == "__main__":
    multiprocessing.freeze_support()
    for cou in range(1,16):
        google_search = GoogleSearch()
        google_search.read_from_file()
        time.sleep(10)