Python selenium 加載并保存QQ群成員,去除其群主、管理員信息的示例代碼
一位伙計自己開了個游戲室，想在群里拉點人，就用所學知識幫幫忙，于是就有了這篇文章，今天小編特此通過實例代碼給大家介紹下Python selenium 加載并保存QQ群成員去除其群主、管理員信息的示例代碼
模擬登陸頁面
頁面分析
思路：
點擊登陸按鈕選擇要登陸的賬號
代碼實現
# Author:smart_num_1# Blog:https://blog.csdn.net/smart_num_1# WeChat:Be_a_lucky_dogfrom selenium import webdriverfrom selenium.webdriver.common.by import Byfrom selenium.webdriver.support import expected_conditions as ECfrom selenium.webdriver.support.ui import WebDriverWaitdef login(driver = None): already_dic = {} # 創建一個字典，保存電腦登陸的QQ login_button = WebDriverWait(driver = driver,timeout = 100).until(EC.presence_of_element_located((By.XPATH,’//p[@class='user-info']/a’))) login_button.click() # 點擊登錄，獲取電腦登陸的QQ already_login_number = WebDriverWait(driver = driver,timeout = 100).until(EC.presence_of_element_located((By.XPATH,’//div[@id='loginWin']/iframe’))) driver.get(url = already_login_number.get_attribute(’src’)) # 此步驟目的，是因為登錄框是一個子頁面，在上一級頁面中獲得到的這個子頁面 already_login_numbers = WebDriverWait(driver = driver,timeout = 100).until(EC.presence_of_all_elements_located((By.XPATH,’//span[contains(@class,'nick')]’))) # 獲取電腦登陸的QQ print(’在以下賬號中選擇所需賬號’) for already_login_number in already_login_numbers: already_dic[already_login_number.get_attribute(’innerText’)] = already_login_number print(already_login_number.get_attribute(’innerText’)) QQ_NeedToLogin = input(’需要登陸: ’) # 通過獲取鍵名，在 already_dic 獲得相應的鍵值 already_dic[QQ_NeedToLogin].click() # 模擬點擊要登陸的QQ，達到登陸的效果 time.sleep(1)if __name__ == ’__main__’:start_url = ’https://qun.qq.com/index.html#click’ # 群首頁，用來登陸賬號driver = webdriver.Chrome(executable_path = ’./chromedriver.exe’)# 因為selenium 需要用到瀏覽器、瀏覽器驅動，但是還要配置環境變量，很麻煩，如果這樣指定 webdriver 路徑的話，就可以省去那一步driver.get(url=start_url) login(driver=driver)
選擇所需加載群
頁面分析
打開群管理界面，會看到這樣的信息，我們的目的是爬取已加入群的成員信息
代碼實現
# Author:smart_num_1# Blog:https://blog.csdn.net/smart_num_1# WeChat:Be_a_lucky_dogdef get_group_number(driver = None): group_number_dic = {} # 同樣的，利用字典儲存信息 my_group_list = WebDriverWait(driver = driver,timeout = 100).until(EC.presence_of_all_elements_located((By.XPATH,’//ul[@class='my-group-list']/li’))) # 獲取每個已加入群的節點信息 print(’在以下群中選擇：’) i = 1 for my_group in my_group_list: try: group_number_dic[str(i)] = my_group print(’第 %s 個--- ’%str(i) + my_group.get_attribute(’title’) + ’ ’ + my_group.get_attribute(’data-id’)) i += 1 except: continue # 打印出獲得的群信息，獲取所有的目標群 group = input(’獲取群編號 : ’) # 通過鍵名獲取鍵值，得到要點擊的目標 group_number_dic[group].click() return driverif __name__ == ’__main__’:member_url_test = ’https://qun.qq.com/member.html’driver.get(url = member_url_test) driver = get_group_number(driver=driver)
保存所需信息
頁面分析
可以看到，是個動態加載的頁面，因為用的是selenium，所以就沒必要分析到底是通過請求那個url得到的信息，直接模擬滾動獲取就可以了
代碼實現
# Author:smart_num_1# Blog:https://blog.csdn.net/smart_num_1# WeChat:Be_a_lucky_dogdef get_group_member(driver = None): driver.refresh() # 刷新一下界面，防止上一步點擊過后，頁面不更新的情況 elem_end = WebDriverWait(driver = driver,timeout = 100).until(EC.presence_of_element_located((By.XPATH,’//td[@class='td-user-nick']/img’))) # 添加了等待，這個定位可以隨便的選擇，確保頁面加載完畢的 for i in range(10): time.sleep(0.5) driver.execute_script('var action=document.documentElement.scrollTop=10000') print(’加載中······’) # 這個滾動范圍可以任選，因為每次會加載21個信息，我看過我加的群，在10次過后的成員基本屬于潛水的人了，要不要的就無所謂了 group_members = driver.find_elements_by_xpath(’//tr[contains(@class,'mb')]’) for group_member in group_members: try: data = group_member.text.split(’n’)[2].split(’ ’)[0] # 這一步，得到一個列表，從第一位開始分別是成員、群昵稱、QQ號、性別、Q齡、入群時間、等級(積分)、最后發言，在這里我是只需要QQ號碼 #對于其他信息，根據自己需要，添加代碼即可 if data.isdigit() == True: with open(’./record.txt’,’a’,encoding = ’utf-8’) as record: record.write(data + ’@qq.com’) record.write(’n’) except: continue print(’Loaded’)
完整代碼
# Author:smart_num_1# Blog:https://blog.csdn.net/smart_num_1# WeChat:Be_a_lucky_dogfrom selenium import webdriverfrom selenium.webdriver.common.by import Byfrom selenium.webdriver.support import expected_conditions as ECfrom selenium.webdriver.support.ui import WebDriverWaitfrom selenium.webdriver.chrome.options import Optionsimport timeimport randomimport osdef get_group_member(driver = None): driver.refresh() elem_end = WebDriverWait(driver = driver,timeout = 100).until(EC.presence_of_element_located((By.XPATH,’//td[@class='td-user-nick']/img’))) for i in range(10): time.sleep(0.5) driver.execute_script('var action=document.documentElement.scrollTop=10000') print(’加載中······’) group_members = driver.find_elements_by_xpath(’//tr[contains(@class,'mb')]’) for group_member in group_members: try: data = group_member.text.split(’n’)[2].split(’ ’)[0] if data.isdigit() == True: with open(’./record.txt’,’a’,encoding = ’utf-8’) as record: record.write(data + ’@qq.com’) record.write(’n’) except: continue print(’Loaded’)def get_group_number(driver = None): group_number_dic = {} my_group_list = WebDriverWait(driver = driver,timeout = 100).until(EC.presence_of_all_elements_located((By.XPATH,’//ul[@class='my-group-list']/li’))) print(’在以下群中選擇：’) i = 1 for my_group in my_group_list: try: group_number_dic[str(i)] = my_group print(’第 %s 個--- ’%str(i) + my_group.get_attribute(’title’) + ’ ’ + my_group.get_attribute(’data-id’)) i += 1 except: continue group = input(’獲取群編號 : ’) group_number_dic[group].click() return driverdef login(driver = None): already_dic = {} login_button = WebDriverWait(driver = driver,timeout = 100).until(EC.presence_of_element_located((By.XPATH,’//p[@class='user-info']/a’))) login_button.click() already_login_number = WebDriverWait(driver = driver,timeout = 100).until(EC.presence_of_element_located((By.XPATH,’//div[@id='loginWin']/iframe’))) driver.get(url = already_login_number.get_attribute(’src’)) already_login_numbers = WebDriverWait(driver = driver,timeout = 100).until(EC.presence_of_all_elements_located((By.XPATH,’//span[contains(@class,'nick')]’))) print(’在以下賬號中選擇所需賬號’) for already_login_number in already_login_numbers: already_dic[already_login_number.get_attribute(’innerText’)] = already_login_number print(already_login_number.get_attribute(’innerText’)) QQ_NeedToLogin = input(’需要登陸: ’) already_dic[QQ_NeedToLogin].click() time.sleep(1)def start(driver = None,url = None): print(’Please wait for loadingn’) driver.get(url = url) driver = get_group_number(driver=driver) print(’Please wait for loadingn’) get_group_member(driver=driver)if __name__ == ’__main__’: print(’Please wait for loading’) chrome_options=Options() chrome_options.add_argument(’--headless’) try: random.seed(time.time()) QQ_number = ’738334209’ start_url = ’https://qun.qq.com/index.html#click’ member_url = ’https://qun.qq.com/member.html#gid=%s’%QQ_number member_url_test = ’https://qun.qq.com/member.html’ driver = webdriver.Chrome(executable_path = ’./chromedriver.exe’,chrome_options=chrome_options) try: driver.get(url=start_url) login(driver=driver) while True: start(driver = driver,url = member_url_test) flag = input(’是否繼續爬取？ yes or no : ’) if flag == ’no’: break os.system(’cls’) driver.quit() except: print(’Something wrong’) driver.quit() except: print(’Something wrong!!!!!!’) os.system(’pause’)
轉載請標明出處：https://blog.csdn.net/smart_num_1/article/details/106326488
總結
到此這篇關于Python selenium 加載并保存QQ群成員 去除其群主、管理員信息的示例代碼的文章就介紹到這了,更多相關Python selenium 加載并保存QQ群成員內容請搜索好吧啦網以前的文章或繼續瀏覽下面的相關文章希望大家以后多多支持好吧啦網！
網公網安備