您的位置: 网站首页> SEO工具> 当前文章
selenium贴吧回复(多账号多吧)
老董-我爱我家房产SEO2020-11-13176围观,115赞
一批帖子需要回复,一堆账号等着去完成回复。手动登录回帖非常人所能忍受,脚本祝人一臂之力。selenium百度贴吧多贴多账号回复脚本如下:
注意:
1、回帖按钮用的js提交,如果发布过程出现输入验证码,会提示回复成功但实际上未发布上去。
2、回帖比较比较特别,元素加载完毕,下拉到底部必须等待一段时间,否则回复不上去;而发帖则不需等待,只要加载完直接发即可!
功能:多账号多贴子回复,默认60-70秒回复1次,每个账号依次回复多个帖子。
1、准备cookie_zh.txt,一行一个cookie
2、准备tie_urls.txt,一行一个帖子网址()
3、准备content.txt ,一行一个回复的句子,每次随机1个回复。
# -*- coding: utf-8 -*-
"""
注意:
用的js提交,如果发布过程出现输入验证码,会提示回复成功但实际上未发布上去)
下拉到底部必须等待,否则回复不上去
功能:多账号多贴子回复,每个账号回复多条贴子
默认60-70秒回复1次
准备cookie_zh.txt一行一个cookie
准备tie_urls.txt,一行一个帖子网址
准备content.txt 一行一个回复的句子,随机1个回复
"""
from pyquery import PyQuery as pq
import threading
import queue
import time
from urllib.parse import urlparse
from openpyxl import load_workbook
from openpyxl import Workbook
import time
import gc
import json
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.chrome.options import Options
import random
from selenium.webdriver.common.action_chains import ActionChains
from pykeyboard import PyKeyboard
def get_driver(chromedriver_path,chrome_path,ua):
ua = ua
option = Options()
option.binary_location = chrome_path
option.add_argument("user-agent=" + ua)
option.add_argument("--no-sandbox")
option.add_argument("--disable-dev-shm-usage")
option.add_argument("--disable-gpu")
option.add_argument("--disable-features=NetworkService")
option.add_argument("--disable-features=VizDisplayCompositor")
# option.add_argument('headless')
option.add_argument('log-level=3') # 屏蔽日志
option.add_argument('--ignore-certificate-errors-spki-list') # 屏蔽ssl error
option.add_argument('-ignore -ssl-errors') # 屏蔽ssl error
option.add_experimental_option("excludeSwitches", ["enable-automation"])
option.add_experimental_option('useAutomationExtension', False)
No_Image_loading = {"profile.managed_default_content_settings.images": 1}
option.add_experimental_option("prefs", No_Image_loading)
# 屏蔽webdriver特征
option.add_argument("--disable-blink-features")
option.add_argument("--disable-blink-features=AutomationControlled")
driver = webdriver.Chrome(options=option, chrome_options=option,executable_path=chromedriver_path)
return driver
# 获得所有账号cookie
def get_cookie(filepath):
cookie_list = []
cookie_list = [line.strip() for line in open(filepath,'r',encoding='utf-8')]
return cookie_list
# 字符串cookie转为字典
def to_dict(cookie_str):
cookie = {}
lists = cookie_str.split(';')
for i in lists:
j = i.strip()
j = j.split('=')
cookie[j[0]] = j[1]
return cookie
# 自动登录
def auto_login(cookie_dict):
num = user_name = 0
teiba_index = 'https://tieba.baidu.com/'
driver.get(teiba_index)
driver.delete_all_cookies()
for k, v in cookie_dict.items():
driver.add_cookie({'name': k, 'value': v})
try:
driver.get(teiba_index) # 带cookie访问
# 右侧导航加载
navs = WebDriverWait(driver, 30).until(
EC.visibility_of_element_located((By.ID, "com_userbar"))
)
li_list = driver.find_elements_by_css_selector('#com_userbar > ul >li')
li_classnames = [li.get_attribute('class') for li in li_list]
if 'u_username' in li_classnames:
num = 1
user = WebDriverWait(driver, 30).until(
EC.visibility_of_element_located(
(By.CSS_SELECTOR, "#j_u_username > div.u_menu_item.u_menu_username > a > span"))
)
user_name = user.text
except Exception as e:
print('登陆过程异常',e)
else:
pass
finally:
return num,user_name
def huifu(tie_url,content):
try:
driver.get(tie_url)
# 人为滚动一下
driver.execute_script(js)
# 加载关注按钮
guanzhu = WebDriverWait(driver, 30).until(
EC.visibility_of_element_located((By.ID, "j_head_focus_btn"))
)
# 鼠标移动到关注按钮
ActionChains(driver).move_to_element(guanzhu).perform()
# 输入框加载
input_content = WebDriverWait(driver, 30).until(EC.element_to_be_clickable((By.ID, "ueditor_replace")))
# 提交按钮加载
button = WebDriverWait(driver, 30).until(EC.element_to_be_clickable((By.ID, "ueditor_replace")))
huifu_first = WebDriverWait(driver, 30).until(EC.element_to_be_clickable((By.CLASS_NAME, "p_reply_first")))
# 鼠标移动
ActionChains(driver).move_to_element(guanzhu).move_to_element(huifu_first).perform()
huifu_first.click()
# 判断到了页面底部
while True:
js_to_bottom = 'var height = document.documentElement.scrollHeight-document.documentElement.scrollTop-document.documentElement.clientHeight;return(height)'
to_bottom = driver.execute_script(js_to_bottom)
# print(to_bottom)
if int(to_bottom) == 0:
break
print('页面到达底部,需额外等10s')
# 鼠标点击进贴吧内容框
js_content_position = "document.getElementById('ueditor_replace').click();"
driver.execute_script(js_content_position)
js_content = """document.getElementById('ueditor_replace').innerText='{0}'""".format(content)
driver.execute_script(js_content)
time.sleep(10)
# button.click()
# 用js方式提交 出现弹窗不会影响提交
button_js = 'document.querySelector("#tb_rich_poster > div.poster_body.editor_wrapper > div.poster_component.editor_bottom_panel.clearfix > div > a").click()'
driver.execute_script(button_js)
except Exception as e:
print(e,'回复异常')
else:
return 1
def main(tie_urls,contents,cookie_list,time1,time2):
for cookie in cookie_list:
try:
cookie_dict = to_dict(cookie)
num_auto,user_name = auto_login(cookie_dict) # 自动登录
if num_auto == 1:
print(user_name,'自动登录成功')
else:
print('自动登录失败')
continue
except Exception as e:
print(e, '未顺利登录')
else:
for tie in tie_urls:
content = random.choice(contents)
num = huifu(tie,content)
if num == 1:
print(tie,'--回复成功')
else:
print(tie,'--回复失败')
time.sleep(random.randint(time1,time2))
finally:
time.sleep(random.randint(time1,time2))
driver.delete_all_cookies()
if __name__ == "__main__":
f = open('tieba_huifu_fail.txt','a',encoding='utf-8')
js = 'window.scrollBy(0,{0})'.format('document.body.scrollHeight')
chromedriver_path = 'D:/python3/install/chromedriver.exe'
chrome_path = 'C:/Program Files (x86)/Google/Chrome/Application/chrome.exe'
ua = 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.125 Safari/537.36'
# 全局变量
driver = get_driver(chromedriver_path,chrome_path,ua)
# cookie账号路径
cookie_path = './cookie_zh.txt'
cookie_list = get_cookie(cookie_path)
# 回复内容
contents = [i.strip() for i in open('./content.txt','r',encoding='utf-8')]
# 要回复的贴
tie_urls = [i.strip() for i in open('./tie_urls.txt', 'r', encoding='utf-8')]
# 登陆间隔时间最小and最大
sleep_min, sleep_max = 60, 70
main(tie_urls,contents,cookie_list,sleep_min,sleep_max)
driver.quit()
很赞哦!
python编程网提示:转载请注明来源www.python66.com。
有宝贵意见可添加站长微信(底部),获取技术资料请到公众号(底部)。同行交流请加群
相关文章
文章评论
-
selenium贴吧回复(多账号多吧)文章写得不错,值得赞赏


