import re
|
import threading
|
import time
|
|
from selenium import webdriver
|
from selenium.webdriver.chrome.options import Options
|
from selenium.webdriver.chrome.service import Service
|
from selenium.webdriver.common.by import By
|
from selenium.webdriver.support.wait import WebDriverWait
|
from selenium.webdriver.support import expected_conditions as EC
|
|
|
class CommentManager:
|
|
def __init__(self):
|
self.options = Options()
|
self.options.add_argument("--disable-blink-features")
|
self.options.add_argument("--disable-blink-features=AutomationControlled")
|
|
# driver = webdriver.Chrome(options=options)
|
# 另外一种方式
|
# 谷歌浏览器位置
|
chrome_location = r'C:\Program Files (x86)\Google\Chrome\Application\chrome.exe'
|
# 谷歌浏览器驱动地址
|
chromedriver_path = r'chromedriver.exe'
|
self.options.binary_location = chrome_location # 指定chrome的路径
|
self.service = Service(chromedriver_path)
|
# 获取正则表达式
|
comment_template_str = ""
|
# 将中文替换为正则表达式支持的unicode编码
|
comment_template_str = comment_template_str.encode('unicode_escape').decode("utf-8")
|
self.comment_templates = [(x.split("#")[0], x.split("#")[1]) if x.find("#")>=0 for x in comment_template_str.split("\n")]
|
self.driver = None
|
|
def __init(self):
|
if not self.driver:
|
self.driver = webdriver.Chrome(service=self.service, options=self.options)
|
|
def start_process_comment(self):
|
"""
|
开始处理评论
|
:return:
|
"""
|
self.__init()
|
self.driver.get(
|
"https://channels.weixin.qq.com/platform/comment?isImageMode=0")
|
# 等到左侧菜单出现后才能执行后续操作
|
wait = WebDriverWait(self.driver, 100) # 最多等待10秒
|
element = wait.until(EC.visibility_of_element_located((By.ID, "side-bar")))
|
threading.Thread(target=lambda: self.click_like(self.driver), daemon=True).start()
|
|
def __process_like(self,comment_content, comment_element):
|
"""
|
处理单条评论的赞
|
:param comment_content:
|
:param comment_element:
|
:return:
|
"""
|
comment_pattern = re.compile(r'[\u4e00-\u9fa5]+')
|
comment_content = re.sub("<img.*?>", "", comment_content)
|
if not comment_pattern.search(comment_content):
|
# 符合标准的评论
|
return
|
comment_actions = comment_element.find_element(By.CLASS_NAME, "action-list").find_elements(By.CLASS_NAME,
|
"action-item")
|
classes: str = comment_actions[0].find_element(By.TAG_NAME, "svg").get_attribute("class")
|
if classes and classes.find("fill-like") >= 0:
|
# 已经点过赞了
|
return
|
like = comment_element.find_element(By.CLASS_NAME, "like-action")
|
like.click()
|
self.driver.implicitly_wait(2)
|
|
def __process_reply(self, comment_content, comment_element):
|
"""
|
处理单条评论的回复
|
:param comment_content:
|
:param comment_element:
|
:return:
|
"""
|
def get_reply_comment(nick_name, content):
|
# 内容是否符合标准
|
for t in self.comment_templates:
|
if re.match(t[0], content):
|
# 满足内容
|
retrun t[1].replace("[昵称]",nick_name)
|
|
comment_pattern = re.compile(r'[\u4e00-\u9fa5]+')
|
comment_content = re.sub("<img.*?>", "", comment_content)
|
if not comment_pattern.search(comment_content):
|
# 符合标准的评论
|
return
|
try:
|
comment_reply_list = comment_element.find_element(By.CLASS_NAME, "comment-reply-list")
|
if comment_reply_list.find_element(By.XPATH, ".//div[normalize-space()='作者']"):
|
print("已经回复。。。。")
|
return
|
except:
|
print("还没回复。。。。")
|
|
comment_actions = comment_element.find_element(By.CLASS_NAME, "action-list").find_elements(By.CLASS_NAME,
|
"action-item")
|
# 点击评论
|
comment_actions[1].click()
|
wait = WebDriverWait(self.driver, 5) # 最多等待10秒
|
element = wait.until(EC.visibility_of_element_located((By.CLASS_NAME, "comment-create-content")))
|
|
replay_content = get_reply_comment(, comment_element)
|
if not replay_content:
|
# 不需要评论
|
return
|
|
self.driver.find_element(By.CLASS_NAME,
|
"comment-create-content").find_element(By.TAG_NAME,
|
"textarea").send_keys(replay_content)
|
self.driver.implicitly_wait(1)
|
self.driver.find_element(By.CLASS_NAME,
|
"comment-create-content").find_element(By.XPATH, "div[3]/div[2]").click()
|
time.sleep(2)
|
|
|
def __click_like_all(self, driver, start_index=0):
|
scroll_list = driver.find_element(By.CLASS_NAME, "feed-comment__wrp")
|
|
loadmore = scroll_list.find_element(By.CLASS_NAME, "loadmore__dot")
|
# 获取父控件
|
loadmore = loadmore.find_element(By.XPATH, "./..")
|
has_more = loadmore.value_of_css_property("display") == "none"
|
comments = scroll_list.find_elements(By.XPATH, "div[2]/div/div/div[contains(@class,'comment-item')]")
|
print("评论条数", len(comments))
|
|
for index in range(start_index, len(comments)):
|
comment = comments[index]
|
# 评论内容
|
comment_content = comment.find_element(By.CLASS_NAME, "comment-content").get_attribute("innerHTML")
|
if not comment_content:
|
continue
|
print("=======评论内容：", comment_content)
|
self.__process_reply(comment_content, comment)
|
self.__process_like(comment_content, comment)
|
# 往下滑动
|
if has_more:
|
driver.execute_script(
|
"var __comment_scroll = document.getElementsByClassName('feed-comment__wrp')[0]; __comment_scroll.scrollTop = __comment_scroll.scrollHeight;")
|
print("往下滚动")
|
time.sleep(3)
|
self.__click_like_all(driver, start_index=len(comments))
|
else:
|
print("没有更多了")
|
|
def click_like(self, driver: webdriver.Chrome):
|
wait = WebDriverWait(driver, 100) # 最多等待10秒
|
element = wait.until(EC.visibility_of_element_located((By.CLASS_NAME, "feeds-container")))
|
time.sleep(1)
|
# 查找视频列表
|
videos_root = driver.find_element(By.CLASS_NAME, "feeds-container")
|
videos = videos_root.find_elements(By.CLASS_NAME, "comment-feed-wrap")
|
for video in videos:
|
# 选择视频
|
video.click()
|
driver.implicitly_wait(2)
|
self.__click_like_all(driver)
|
|
def close(self):
|
if self.driver:
|
try:
|
self.driver.close()
|
except:
|
pass
|
|
|
if __name__ == "__main__":
|
# CommentManager().start_process_comment()
|
s ="你好"
|
print(s.encode('unicode_escape').decode("utf-8"))
|
|
# if __name__ == "__main__":
|
# data = """
|
# 213<img src="https://res.wx.qq.com/mpres/zh_CN/htmledition/comm_htmledition/images/pic/common/pic_blank.gif" alt="[呲牙]" class="we-emoji we-emoji__Grin"><img src="https://res.wx.qq.com/mpres/zh_CN/htmledition/comm_htmledition/images/pic/common/pic_blank.gif" alt="[呲牙]" class="we-emoji we-emoji__Grin"><img src="https://res.wx.qq.com/mpres/zh_CN/htmledition/comm_htmledition/images/pic/common/pic_blank.gif" alt="[呲牙]" class="we-emoji we-emoji__Grin">
|
# """
|
#
|
# result = re.compile(r'[\u4e00-\u9fa5]+').search(re.sub("<img.*?>", "", data))
|
# print(result)
|
