first_commit .gitignore

plugins/reimu/__init__.py

@@ -0,0 +1,96 @@
+from nonebot import on_command
+from nonebot.adapters.cqhttp.permission import PRIVATE
+from .data_source import from_reimu_get_info
+from services.log import logger
+from nonebot.adapters.cqhttp import Bot, Event
+from nonebot.typing import T_State
+from util.utils import is_number, get_message_text, UserExistLimiter, scheduler
+from models.count_user import UserCount
+from configs.config import COUNT_PER_DAY_REIMU
+
+__plugin_name__ = '上车'
+__plugin_usage__ = r"""
+* 请各位使用后不要转发 *
+* 大部分解压密码是⑨ *
+/ 每人每天仅提供 5 次上车机会（只能私聊）更多次数请向管理员申请（用爱发电）限制小色批乱搜 /
+/ 并不推荐小色批使用此功能（主要是不够色，目的不够明确） /
+上车 [目的地]
+上车 5 [目的地]  该目的地第5页停车场
+ps: 请尽量提供具体的目的地名称
+""".strip()
+
+
+_ulmt = UserExistLimiter()
+
+reimu = on_command('上车', permission=PRIVATE, block=True, priority=1)
+
+
+@reimu.args_parser
+async def _(bot: Bot, event: Event, state: T_State):
+    if get_message_text(event.json()) in ['取消', '算了']:
+        await reimu.finish("已取消操作..", at_sender=True)
+    if not get_message_text(event.json()):
+        await reimu.reject('没时间等了！快说你要去哪里？', at_sender=True)
+    state['keyword'] = get_message_text(event.json())
+    state['page'] = 1
+
+
+@reimu.handle()
+async def _(bot: Bot, event: Event, state: T_State):
+    if str(event.get_message()) in ['帮助']:
+        await reimu.finish(__plugin_usage__)
+    if await UserCount.check_count(event.user_id, 'reimu', COUNT_PER_DAY_REIMU):
+        await reimu.finish('今天已经没车了，请明天再来...', at_sender=True)
+    if _ulmt.check(event.user_id):
+        await reimu.finish('您还没下车呢，请稍等...', at_sender=True)
+    _ulmt.set_True(event.user_id)
+    msg = get_message_text(event.json())
+    args = msg.split(" ")
+    if msg in ['!', '！', '?', '？', ',', '，', '.', '。']:
+        await reimu.finish(__plugin_usage__)
+    if msg:
+        if len(args) > 1 and is_number(args[0]):
+            state['keyword'] = args[1]
+            state['page'] = args[0]
+        else:
+            state['keyword'] = msg
+            state['page'] = 1
+
+
+@reimu.got('keyword', '你的目的地是哪？')
+async def _(bot: Bot, event: Event, state: T_State):
+    try:
+        keyword = state['keyword']
+        page = state['page']
+        print(keyword, page)
+        await UserCount.add_count(event.user_id, 'reimu')
+        await reimu.send('已经帮你关好车门了', at_sender=True)
+        reimu_report = await from_reimu_get_info(keyword, page)
+        if reimu_report:
+            await reimu.send(reimu_report)
+        else:
+            logger.error("Not found reimuInfo")
+            await reimu.send("没找着")
+        _ulmt.set_False(event.user_id)
+    except:
+        _ulmt.set_False(event.user_id)
+
+
+@scheduler.scheduled_job(
+    'cron',
+    # year=None,
+    # month=None,
+    # day=None,
+    # week=None,
+    # day_of_week="mon,tue,wed,thu,fri",
+    hour=0,
+    minute=1,
+    # second=None,
+    # start_date=None,
+    # end_date=None,
+    # timezone=None,
+)
+async def _():
+    await UserCount.reset_count()
+
+

plugins/reimu/data_source.py

@@ -0,0 +1,116 @@
+from lxml import etree
+import time
+import aiohttp
+from services.log import logger
+from configs.config import MAXINFO_REIMU
+from util.user_agent import get_user_agent
+from util.utils import get_local_proxy
+from asyncio.exceptions import TimeoutError
+
+
+async def from_reimu_get_info(key_word: str, page: int) -> str:
+    if "miku" in key_word.lower():
+        logger.warning("Taboo words are being triggered")
+        return None
+    repass = ""
+    url = 'https://blog.reimu.net/search/' + key_word + '/page/' + str(page)
+    url_s = 'https://blog.reimu.net/'
+    try:
+        if key_word == "最近的存档":
+            logger.debug("Now starting get the {}".format(url_s))
+            repass = await get_repass(url_s)
+        else:
+            logger.debug("Now starting get the {}".format(url))
+            repass = await get_repass(url)
+    except TimeoutError as e:
+        logger.error("Timeout! {}".format(e))
+
+    return repass
+
+
+async def get_repass(url: str) -> str:
+    repass = ""
+    info = "[Note]注意大部分资源解压密码为⑨\n"
+    fund = None
+    print(url)
+    async with aiohttp.ClientSession(headers=get_user_agent()) as session:
+        async with session.get(url, proxy=get_local_proxy(), timeout=15) as response:
+            html = etree.HTML(await response.text())
+
+            fund_l = html.xpath('//h1[@class="page-title"]/text()')
+            if fund_l:
+                fund = fund_l[0]
+                if fund == "未找到":
+                    return "老司机也找不到路了……"
+            else:
+                pass
+
+            headers = html.xpath('//article/header/h2/a/text()')
+            urls = html.xpath('//article/header/h2/a/@href')
+            logger.debug("Now get {} post from search page".format(len(headers)))
+
+            headers_d = []
+            urls_d = []
+            for i, header in enumerate(headers):
+                if check_need_list(header):
+                    headers_d.append(headers[i])
+                    urls_d.append(urls[i])
+                else:
+                    logger.debug("This title {} does not meet the requirements".format(header))
+
+            header_len = len(headers_d)
+            logger.debug("Get {} post after processing".format(header_len))
+            if header_len > MAXINFO_REIMU:
+                headers_d = headers_d[:MAXINFO_REIMU]
+                urls_d = urls_d[:MAXINFO_REIMU]
+
+            for h_s, url_s in zip(headers_d, urls_d):
+                if h_s != "审核结果存档":
+                    time.sleep(1.5)
+                    putline = await get_son_html_info(h_s, url_s)
+                    if putline:
+                        if repass:
+                            repass = "\n\n- - - - - - - - \n".join([repass, putline])
+                        else:
+                            repass = putline
+                else:
+                    logger.info("审核归档页面已跳过")
+
+            if repass:
+                repass = info + repass
+            return repass
+
+
+async def get_son_html_info(h_s, url_s) -> str:
+    repass = ""
+    logger.debug("Now starting get the {}".format(url_s))
+    async with aiohttp.ClientSession(headers=get_user_agent()) as session:
+        async with session.get(url_s, proxy=get_local_proxy(), timeout=15) as response:
+            html = etree.HTML(await response.text())
+            pres = html.xpath('//div[@class="entry-content"]/pre/text()')
+            a_texts = html.xpath('//div[@class="entry-content"]/pre//a/text()')
+            a_hrefs = html.xpath('//div[@class="entry-content"]/pre//a/@href')
+
+            if pres and a_texts and a_hrefs:
+                while "" in pres:
+                    pres.remove("")
+
+                repass = "【资源名称】 {}\n\n{}".format(h_s, pres[0].strip())
+                for i, (a_t_s, a_h_s) in enumerate(zip(a_texts, a_hrefs)):
+                    a = "\n {}  {}  {} ".format(a_t_s, a_h_s, pres[i + 1].strip())
+                    repass += a
+            else:
+                logger.warning("Not get putline from {}".format(url_s))
+
+            return repass
+
+
+def check_need_list(header: str) -> bool:
+    not_need = ['音乐', '御所动态']
+    for nd in not_need:
+        if nd in header:
+            return False
+    return True
+
+
+# print(asyncio.get_event_loop().run_until_complete(from_reimu_get_info('萝莉')))