feat: 增加微头条统计
This commit is contained in:
@@ -7,7 +7,7 @@ from nonebot import on_command
|
||||
from nonebot.rule import to_me
|
||||
from requests_html import HTMLSession, HTML
|
||||
|
||||
zhibo8Command = on_command("/zhibo8", rule=to_me(), aliases={'预测', '英超', 'zhibo8'}, priority=10)
|
||||
zhibo8Command = on_command("zhibo8", rule=to_me(), aliases={'预测', '英超', 'zhibo8'}, priority=10)
|
||||
|
||||
xiaobianStr = r"""
|
||||
小编们预测比分：
|
||||
|
||||
@@ -11,12 +11,25 @@ from requests_html import HTMLSession, HTML
|
||||
import json
|
||||
from selenium.webdriver import Chrome, ChromeOptions
|
||||
|
||||
tongjiCommand = on_command("统计", rule=to_me(), aliases={'微头条', 'tongji', 'tj'}, priority=10)
|
||||
|
||||
driver_path = '../../../../driver/cromedriver_win32'
|
||||
# driver_path = '../../../../driver/cromedriver_win32'
|
||||
max_behot_time = '0'
|
||||
# 初始化map对象，分别记录每个人的微头条个数
|
||||
weitoutiaoMap = {"太能喵": 0, "小小": 0, "大帝强": 0, "叶小欢": 0}
|
||||
|
||||
"""
|
||||
接收QQ消息，根据消息统计微头条结果
|
||||
"""
|
||||
@tongjiCommand.handle()
|
||||
async def handle_first_receive(bot: Bot, event: Event, state: T_State, args= CommandArg()):
|
||||
# 清空原有的weitoutiaoMap中的统计结果
|
||||
for k,v in weitoutiaoMap.items():
|
||||
weitoutiaoMap[k] = 0
|
||||
getWeiToutiaoInfo()
|
||||
# 将上周的微头条考核结果发送给用户
|
||||
await tongjiCommand.finish(str(weitoutiaoMap))
|
||||
|
||||
"""
|
||||
获取微头条数据信息
|
||||
"""
|
||||
@@ -49,7 +62,7 @@ def getWeiToutiaoInfo():
|
||||
else:
|
||||
# 获取该微头条的发布人和发布日期
|
||||
author = None
|
||||
contentSubString = content[-8]
|
||||
contentSubString = content[-8:]
|
||||
if contentSubString.find("太能喵")>0:
|
||||
weitoutiaoMap["太能喵"] = weitoutiaoMap["太能喵"]+1
|
||||
elif contentSubString.find("小小")>0:
|
||||
@@ -60,64 +73,64 @@ def getWeiToutiaoInfo():
|
||||
weitoutiaoMap["叶小欢"] = weitoutiaoMap["叶小欢"] + 1
|
||||
getWeiToutiaoInfo()
|
||||
|
||||
"""
|
||||
获取文章数据信息
|
||||
"""
|
||||
def getWenzhangInfo():
|
||||
global max_behot_time
|
||||
|
||||
# 第一步输入这个：去除开头警告
|
||||
warnings.simplefilter('ignore', ResourceWarning)
|
||||
|
||||
chrome_option = ChromeOptions()
|
||||
chrome_option.headless = True
|
||||
chrome_option.add_argument('--no-sandbox') # 解决DevToolsActivePort文件不存在的报错
|
||||
chrome_option.add_argument('--disable-gpu') # 谷歌文档提到需要加上这个属性来规避bug
|
||||
chrome_option.add_argument('--hide-scrollbars') # 隐藏滚动条, 应对一些特殊页面
|
||||
chrome_option.add_experimental_option('excludeSwitches', ['enable-automation'])
|
||||
chrome_option.add_argument('--headless')
|
||||
|
||||
browser = Chrome(executable_path=driver_path, options=chrome_option)
|
||||
|
||||
# 获取上一周的第一天和最后一天的时间戳
|
||||
lastWeekStartTime, lastWeekEndTime = getLastWeekFirstDayTimeStamp()
|
||||
session = HTMLSession()
|
||||
wenzhangGet = session.get(f"https://www.toutiao.com/api/pc/list/user/feed?category=pc_profile_article&token=MS4wLjABAAAA7lHc4sBPuZaQ85qdIrwVvWm8Ps5O1kPMpuh5lTJAwII&max_behot_time={max_behot_time}&aid=24&app_name=toutiao_web", verify=False, proxies=None)
|
||||
# print(weitoutiaoGet.text)
|
||||
# 使用Json解析返回的数据
|
||||
resultJson = json.loads(wenzhangGet.text)
|
||||
# 先获取下个max_behot_time时间戳，如果需要翻页查询需要使用该参数
|
||||
max_behot_time = resultJson['next']['max_behot_time']
|
||||
# 开始循环解析data数据，获取微头条的内容和发布人员
|
||||
dataList = resultJson['data']
|
||||
# 获取每一条消息的发布时间戳，如果发布时间出现早于上周一0点的数据，结束统计，函数返回，否则递归调用当前函数
|
||||
for data in dataList:
|
||||
# 获取本条新闻的发布时间
|
||||
publishTime = data["publish_time"]
|
||||
if int(publishTime) > int(lastWeekEndTime):
|
||||
continue
|
||||
elif int(publishTime) < int(lastWeekStartTime):
|
||||
return
|
||||
else:
|
||||
# 获取该文章的标题和对应的url，需要再通过url获取文章正文，解析作者是谁
|
||||
title = data["title"]
|
||||
url = data["url"]
|
||||
if url:
|
||||
# 请求文章正文内容
|
||||
browser.get(url)
|
||||
element = browser.find_element(by='XPATH', value="//article")
|
||||
print(element)
|
||||
# author = None
|
||||
# if data.find("太能喵")>0:
|
||||
# weitoutiaoMap["太能喵"] = weitoutiaoMap["太能喵"]+1
|
||||
# elif content.find("小小")>0:
|
||||
# weitoutiaoMap["小小"] = weitoutiaoMap["小小"]+1
|
||||
# elif content.find("大帝强") > 0:
|
||||
# weitoutiaoMap["大帝强"] = weitoutiaoMap["大帝强"] + 1
|
||||
# elif content.find("叶小欢") > 0:
|
||||
# weitoutiaoMap["叶小欢"] = weitoutiaoMap["叶小欢"] + 1
|
||||
# 如果没有被return掉，继续请求下一页内容
|
||||
getWeiToutiaoInfo()
|
||||
# """
|
||||
# 获取文章数据信息
|
||||
# """
|
||||
# def getWenzhangInfo():
|
||||
# global max_behot_time
|
||||
#
|
||||
# # 第一步输入这个：去除开头警告
|
||||
# warnings.simplefilter('ignore', ResourceWarning)
|
||||
#
|
||||
# chrome_option = ChromeOptions()
|
||||
# chrome_option.headless = True
|
||||
# chrome_option.add_argument('--no-sandbox') # 解决DevToolsActivePort文件不存在的报错
|
||||
# chrome_option.add_argument('--disable-gpu') # 谷歌文档提到需要加上这个属性来规避bug
|
||||
# chrome_option.add_argument('--hide-scrollbars') # 隐藏滚动条, 应对一些特殊页面
|
||||
# chrome_option.add_experimental_option('excludeSwitches', ['enable-automation'])
|
||||
# chrome_option.add_argument('--headless')
|
||||
#
|
||||
# browser = Chrome(executable_path=driver_path, options=chrome_option)
|
||||
#
|
||||
# # 获取上一周的第一天和最后一天的时间戳
|
||||
# lastWeekStartTime, lastWeekEndTime = getLastWeekFirstDayTimeStamp()
|
||||
# session = HTMLSession()
|
||||
# wenzhangGet = session.get(f"https://www.toutiao.com/api/pc/list/user/feed?category=pc_profile_article&token=MS4wLjABAAAA7lHc4sBPuZaQ85qdIrwVvWm8Ps5O1kPMpuh5lTJAwII&max_behot_time={max_behot_time}&aid=24&app_name=toutiao_web", verify=False, proxies=None)
|
||||
# # print(weitoutiaoGet.text)
|
||||
# # 使用Json解析返回的数据
|
||||
# resultJson = json.loads(wenzhangGet.text)
|
||||
# # 先获取下个max_behot_time时间戳，如果需要翻页查询需要使用该参数
|
||||
# max_behot_time = resultJson['next']['max_behot_time']
|
||||
# # 开始循环解析data数据，获取微头条的内容和发布人员
|
||||
# dataList = resultJson['data']
|
||||
# # 获取每一条消息的发布时间戳，如果发布时间出现早于上周一0点的数据，结束统计，函数返回，否则递归调用当前函数
|
||||
# for data in dataList:
|
||||
# # 获取本条新闻的发布时间
|
||||
# publishTime = data["publish_time"]
|
||||
# if int(publishTime) > int(lastWeekEndTime):
|
||||
# continue
|
||||
# elif int(publishTime) < int(lastWeekStartTime):
|
||||
# return
|
||||
# else:
|
||||
# # 获取该文章的标题和对应的url，需要再通过url获取文章正文，解析作者是谁
|
||||
# title = data["title"]
|
||||
# url = data["url"]
|
||||
# if url:
|
||||
# # 请求文章正文内容
|
||||
# browser.get(url)
|
||||
# element = browser.find_element(by='XPATH', value="//article")
|
||||
# print(element)
|
||||
# # author = None
|
||||
# # if data.find("太能喵")>0:
|
||||
# # weitoutiaoMap["太能喵"] = weitoutiaoMap["太能喵"]+1
|
||||
# # elif content.find("小小")>0:
|
||||
# # weitoutiaoMap["小小"] = weitoutiaoMap["小小"]+1
|
||||
# # elif content.find("大帝强") > 0:
|
||||
# # weitoutiaoMap["大帝强"] = weitoutiaoMap["大帝强"] + 1
|
||||
# # elif content.find("叶小欢") > 0:
|
||||
# # weitoutiaoMap["叶小欢"] = weitoutiaoMap["叶小欢"] + 1
|
||||
# # 如果没有被return掉，继续请求下一页内容
|
||||
# getWeiToutiaoInfo()
|
||||
|
||||
"""
|
||||
获取当前日期上一周的第一天和最后一天的时间戳
|
||||
@@ -132,5 +145,5 @@ def getLastWeekFirstDayTimeStamp():
|
||||
return last_week_start.timestamp(), last_week_end.timestamp()
|
||||
|
||||
if __name__ == '__main__':
|
||||
getWenzhangInfo()
|
||||
getWeiToutiaoInfo()
|
||||
# print(weitoutiaoMap)
|
||||
Reference in New Issue
Block a user