class style, rename

This commit is contained in:
BennyThink
2021-01-18 22:26:02 +08:00
parent 368f6b260b
commit 0dee0fcacf
9 changed files with 672 additions and 601 deletions

4
.gitignore vendored
View File

@@ -110,6 +110,6 @@ venv.bak/
/.idea/modules.xml
/.idea/vcs.xml
.idea/
/data/cookies.dump
/yyetsbot/data/cookies.dump
/.idea/inspectionProfiles/profiles_settings.xml
data/
yyetsbot/data/

View File

@@ -1 +0,0 @@
dir to storage request id and data.

View File

@@ -1,127 +0,0 @@
# coding: utf-8
# YYeTsBot - html_request.py
# 2019/8/15 18:30
__author__ = 'Benny <benny.think@gmail.com>'
import os
import logging
import requests
import feedparser
from bs4 import BeautifulSoup
from config import SEARCH_URL, GET_USER, RSS_URL, BASE_URL, SHARE_WEB, SHARE_URL, WORKERS, SHARE_API
from utils import load_cookies, cookie_file, login
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(filename)s [%(levelname)s]: %(message)s')
s = requests.Session()
ua = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36"
s.headers.update({"User-Agent": ua})
def get_search_html(kw: str) -> str:
if not os.path.exists(cookie_file):
logging.warning("Cookie file not found")
login()
if not is_cookie_valid():
login()
cookie = load_cookies()
logging.info("Searching for %s", kw)
r = s.get(SEARCH_URL.format(kw=kw), cookies=cookie)
r.close()
return r.text
def get_detail_page(url: str) -> dict:
logging.info("Loading detail page %s", url)
share_link, api_res = analysis_share_page(url)
cnname = api_res["data"]["info"]["cnname"]
logging.info("Loading rss...")
rss_url = RSS_URL.format(id=url.split("/")[-1])
rss_result = analyse_rss(rss_url)
# get search_content from here...
if not rss_result:
rss_result = api_res
return {"all": rss_result, "share": share_link, "cnname": cnname}
def analyse_search_html(html: str) -> dict:
logging.info('Parsing html...')
soup = BeautifulSoup(html, 'lxml')
link_list = soup.find_all("div", class_="clearfix search-item")
list_result = {}
for block in link_list:
name = block.find_all('a')[-1].text
url = BASE_URL + block.find_all('a')[-1].attrs['href']
list_result[url] = name
return list_result
def analyse_rss(feed_url: str) -> dict:
# feed parser is meaningless now
return {}
# d = feedparser.parse(feed_url)
# # data['feed']['title']
# result = {}
# for item in d['entries']:
# download = {
# "title": getattr(item, "title", ""),
# "ed2k": getattr(item, "ed2k", ""),
# "magnet": getattr(item, "magnet", ""),
# "pan": getattr(item, "pan", "")}
# result[item.guid] = download
# return result
def analysis_share_page(detail_url: str) -> (str, dict):
rid = detail_url.split('/')[-1]
res = s.post(SHARE_URL, data={"rid": rid}, cookies=load_cookies()).json()
share_code = res['data'].split('/')[-1]
share_url = SHARE_WEB.format(code=share_code)
logging.info("Share url is %s", share_url)
# get api response
api_response = s.get(SHARE_API.format(code=share_code)).json()
return share_url, api_response
def is_cookie_valid() -> bool:
cookie = load_cookies()
r = s.get(GET_USER, cookies=cookie)
return r.json()['status'] == 1
def offline_search(search_content):
# from cloudflare workers
# no redis cache for now
logging.info("Loading data from cfkv...")
index = WORKERS.format(id="index")
data: dict = requests.get(index).json()
logging.info("Loading complete, searching now...")
results = {}
for name, rid in data.items():
if search_content in name:
fake_url = f"http://www.rrys2020.com/resource/{rid}"
results[fake_url] = name.replace("\n", " ")
logging.info("Search complete")
return results
def offline_link(resource_url) -> str:
rid = resource_url.split("/")[-1]
query_url = WORKERS.format(id=rid)
# TODO: too lazy to optimize cloudflare worker page.
return query_url
if __name__ == '__main__':
a = offline_search("越狱")
print(a)

10
tests/test_fansub.py Normal file
View File

@@ -0,0 +1,10 @@
import unittest
class MyTestCase(unittest.TestCase):
def test_something(self):
self.assertEqual(True, False)
if __name__ == '__main__':
unittest.main()

View File

@@ -1,329 +1,325 @@
# coding: utf-8
# YYeTsBot - bot.py
# 2019/8/15 18:27
__author__ = 'Benny <benny.think@gmail.com>'
import io
import time
import re
import os
import logging
import json
import tempfile
from urllib.parse import quote_plus
import telebot
from telebot import types, apihelper
from tgbot_ping import get_runtime
from apscheduler.schedulers.background import BackgroundScheduler
from html_request import get_search_html, analyse_search_html, get_detail_page, offline_search, offline_link
from utils import (save_error_dump, save_to_cache, yyets_get_from_cache, get_error_dump,
reset_request, today_request, show_usage,
redis_announcement
)
from config import PROXY, TOKEN, SEARCH_URL, MAINTAINER, REPORT, WORKERS, OFFLINE
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(filename)s [%(levelname)s]: %(message)s')
if PROXY:
apihelper.proxy = {'https': PROXY}
bot = telebot.TeleBot(os.environ.get('TOKEN') or TOKEN)
angry_count = 0
@bot.message_handler(commands=['start'])
def send_welcome(message):
bot.send_chat_action(message.chat.id, 'typing')
bot.send_message(message.chat.id, '欢迎使用,直接发送想要的剧集标题给我就可以了,不需要其他关键字,我会帮你搜索。\n\n'
'人人影视专注于欧美日韩剧集,请不要反馈“我搜不到喜羊羊与灰太狼/流浪地球”这种问题,'
'我会生气的😠😡🤬😒\n\n'
'建议使用<a href="http://www.zmz2019.com/">人人影视</a> 标准译名',
parse_mode='html', disable_web_page_preview=True)
@bot.message_handler(commands=['help'])
def send_help(message):
bot.send_chat_action(message.chat.id, 'typing')
bot.send_message(message.chat.id, '''机器人无法使用或者报错?从 /ping 里可以看到运行状态以及最新信息。
同时你可以使用如下方式寻求使用帮助和报告错误\n
1. @BennyThink
2. <a href='https://github.com/BennyThink/YYeTsBot/issues'>Github issues</a>
3. <a href='https://t.me/mikuri520'>Telegram Channel</a>''', parse_mode='html', disable_web_page_preview=True)
@bot.message_handler(commands=['ping'])
def send_ping(message):
logging.info("Pong!")
bot.send_chat_action(message.chat.id, 'typing')
info = get_runtime("botsrunner_yyets_1")
redis = get_runtime("botsrunner_redis_1", "Redis")
usage = ""
if str(message.chat.id) == MAINTAINER:
usage = show_usage()
announcement = redis_announcement() or ""
if announcement:
announcement = f"\n\n*公告:{announcement}*\n\n"
bot.send_message(message.chat.id, f"{info}\n{redis}\n\n{usage}\n{announcement}",
parse_mode='markdown')
@bot.message_handler(commands=['settings'])
def settings(message):
is_admin = str(message.chat.id) == MAINTAINER
# 普通用户只可以查看,不可以设置
# 管理员可以查看可以设置
if message.text != "/settings" and not is_admin:
bot.send_message(message.chat.id, "此功能只允许管理员使用。请使用 /ping 和 /settings 查看相关信息")
return
# 删除公告,设置新公告
if message.text != "/settings":
date = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
text = message.text.replace("/settings", f"{date}\t")
logging.info("New announcement %s", text)
redis_announcement(text, "set")
setattr(message, "text", "/settings")
settings(message)
return
announcement = redis_announcement()
markup = types.InlineKeyboardMarkup()
btn1 = types.InlineKeyboardButton("删除公告", callback_data="announcement")
if is_admin and announcement:
markup.add(btn1)
bot.send_message(message.chat.id, f"目前公告:\n\n {announcement or '暂无公告'}", reply_markup=markup)
@bot.callback_query_handler(func=lambda call: re.findall(r"announcement(\S*)", call.data))
def delete_announcement(call):
bot.send_chat_action(call.message.chat.id, 'typing')
redis_announcement(op="del")
bot.edit_message_text(f"目前公告:\n\n {redis_announcement() or '暂无公告'}",
call.message.chat.id,
call.message.message_id)
@bot.message_handler(commands=['credits'])
def send_credits(message):
bot.send_chat_action(message.chat.id, 'typing')
bot.send_message(message.chat.id, '''感谢字幕组的无私奉献!本机器人资源来源:\n
<a href="http://www.zmz2019.com/">人人影视</a>
<a href="http://cili001.com/">磁力下载站</a>
<a href="http://www.zhuixinfan.com/main.php">追新番</a>
''', parse_mode='html', disable_web_page_preview=True)
def download_to_io(photo):
logging.info("Initializing bytes io...")
mem = io.BytesIO()
file_id = photo[-1].file_id
logging.info("Downloading photos...")
file_info = bot.get_file(file_id)
content = bot.download_file(file_info.file_path)
mem.write(content)
logging.info("Downloading complete.")
return mem
def send_my_response(message):
bot.send_chat_action(message.chat.id, 'record_video_note')
# I may also send picture
photo = message.photo
uid = message.reply_to_message.caption
text = f"主人说:{message.text or message.caption or '啥也没说😯'}"
if photo:
bot.send_chat_action(message.chat.id, 'typing')
logging.info("Photo received from maintainer")
mem = download_to_io(photo)
mem.name = f'{uid}.jpg'
r = bot.send_photo(uid, mem.getvalue(), caption=text)
else:
r = bot.send_message(uid, text)
logging.info("Reply has been sent to %s with message id %s", uid, r.message_id)
bot.reply_to(message, "回复已经发送给这位用户")
fw = bot.forward_message(message.chat.id, uid, r.message_id)
time.sleep(3)
bot.delete_message(message.chat.id, fw.message_id)
logging.info("Forward has been deleted.")
@bot.message_handler(content_types=["photo", "text"])
def send_search(message):
bot.send_chat_action(message.chat.id, 'typing')
today_request("total")
if message.reply_to_message and message.reply_to_message.document and \
message.reply_to_message.document.file_name.startswith("error") and str(message.chat.id) == MAINTAINER:
today_request("answer")
send_my_response(message)
return
name = message.text
logging.info('Receiving message: %s from user %s(%s)', name, message.chat.username, message.chat.id)
if name is None:
today_request("invalid")
with open('assets/warning.webp', 'rb') as sti:
bot.send_message(message.chat.id, "不要调戏我!我会报警的")
bot.send_sticker(message.chat.id, sti)
return
if OFFLINE:
logging.warning("☢️ Going offline mode!!!")
bot.send_message(message.chat.id, "人人影视官网不可用,目前在使用离线模式,可能没有最新的剧集。")
html = ""
bot.send_chat_action(message.chat.id, 'upload_document')
result = offline_search(name)
else:
html = get_search_html(name)
result = analyse_search_html(html)
markup = types.InlineKeyboardMarkup()
for url, detail in result.items():
btn = types.InlineKeyboardButton(detail, callback_data="choose%s" % url)
markup.add(btn)
if result:
logging.info("🎉 Resource match.")
today_request("success")
bot.send_message(message.chat.id, "呐,💐🌷🌹选一个呀!", reply_markup=markup)
else:
logging.warning("⚠️️ Resource not found")
today_request("fail")
bot.send_chat_action(message.chat.id, 'typing')
encoded = quote_plus(name)
bot.send_message(message.chat.id, f"没有找到你想要的信息,是不是你打了错别字,或者搜索了一些国产影视剧。🤪\n"
f"还是你想调戏我哦🙅‍️\n\n"
f"可以看看这个链接,看看有没有结果。 {SEARCH_URL.format(kw=encoded)} \n\n"
"⚠️如果确定要我背锅,那么请使用 /help 来提交错误", disable_web_page_preview=True)
if REPORT:
btn = types.InlineKeyboardButton("快来修复啦", callback_data="fix")
markup.add(btn)
bot.send_chat_action(message.chat.id, 'upload_document')
bot.send_message(message.chat.id, f"{name}》😭\n大部分情况下机器人是好用的,不要怀疑我的代码质量.\n"
f"如果你真的确定是机器人出问题了,那么点下面的按钮叫 @BennyThink 来修!\n"
f"⚠️报错前请三思,不要乱点,确保这锅应该甩给我。否则我会很生气的😡小心被拉黑哦",
reply_markup=markup)
content = f""" 报告者:{message.chat.first_name}{message.chat.last_name or ""}@{message.chat.username or ""}({message.chat.id})
问题发生时间{time.strftime("%Y-%m-%data %H:%M:%S", time.localtime(message.date))}
请求内容{name}
请求URL{SEARCH_URL.format(kw=encoded)}\n\n
返回内容{html}
"""
save_error_dump(message.chat.id, content)
@bot.callback_query_handler(func=lambda call: re.findall(r"choose(\S*)", call.data))
def choose_link(call):
bot.send_chat_action(call.message.chat.id, 'typing')
# call.data is url, http://www.rrys2020.com/resource/36588
resource_url = re.findall(r"choose(\S*)", call.data)[0]
markup = types.InlineKeyboardMarkup()
if OFFLINE:
worker_page = offline_link(resource_url)
btn1 = types.InlineKeyboardButton("打开网页", url=worker_page)
markup.add(btn1)
bot.send_message(call.message.chat.id, "离线模式,点击按钮打开网页获取结果", reply_markup=markup)
return
link = yyets_get_from_cache(resource_url)
if not link:
link = get_detail_page(resource_url)
save_to_cache(resource_url, link)
btn1 = types.InlineKeyboardButton("分享页面", callback_data="share%s" % resource_url)
btn2 = types.InlineKeyboardButton("我全都要", callback_data="all%s" % resource_url)
markup.add(btn1, btn2)
text = "想要分享页面,还是我全都要?\n\n" \
"名词解释:“分享页面”会返回给你一个网站,从那里可以看到全部的下载链接。\n" \
"“我全都要”会给你发送一个txt文件文件里包含全部下载连接\n"
bot.send_message(call.message.chat.id, text, reply_markup=markup)
@bot.callback_query_handler(func=lambda call: re.findall(r"share(\S*)", call.data))
def share_page(call):
bot.send_chat_action(call.message.chat.id, 'typing')
resource_url = re.findall(r"share(\S*)", call.data)[0]
result = yyets_get_from_cache(resource_url)
bot.send_message(call.message.chat.id, result['share'])
@bot.callback_query_handler(func=lambda call: re.findall(r"all(\S*)", call.data))
def all_episode(call):
# just send a file
bot.send_chat_action(call.message.chat.id, 'typing')
resource_url = re.findall(r"all(\S*)", call.data)[0]
result = yyets_get_from_cache(resource_url)
with tempfile.NamedTemporaryFile(mode='wb+', prefix=result["cnname"], suffix=".txt") as tmp:
bytes_data = json.dumps(result["all"], ensure_ascii=False, indent=4).encode('u8')
tmp.write(bytes_data)
tmp.flush()
with open(tmp.name, "rb") as f:
bot.send_chat_action(call.message.chat.id, 'upload_document')
bot.send_document(call.message.chat.id, f)
@bot.callback_query_handler(func=lambda call: re.findall(r"unwelcome(\d*)", call.data))
def send_unwelcome(call):
# this will come from me only
logging.warning("I'm so unhappy!")
message = call.message
bot.send_chat_action(message.chat.id, 'typing')
# angry_count = angry_count + 1
global angry_count
angry_count += 1
uid = re.findall(r"unwelcome(\d*)", call.data)[0]
if uid:
text = "人人影视主要提供欧美日韩等海外资源,你的这个真没有🤷‍。\n" \
"<b>麻烦你先从自己身上找原因</b>,我又不是你的专属客服。\n" \
"不要再报告这种错误了🙄️,面倒な。😡"
bot.send_message(uid, text, parse_mode="html")
bot.reply_to(message, f"有生之日 生气次数:{angry_count}")
@bot.callback_query_handler(func=lambda call: call.data == 'fix')
def report_error(call):
logging.error("Reporting error to maintainer.")
bot.send_chat_action(call.message.chat.id, 'typing')
error_content = get_error_dump(call.message.chat.id)
if error_content == "":
bot.answer_callback_query(call.id, '多次汇报重复的问题并不会加快处理速度。', show_alert=True)
return
text = f'人人影视机器人似乎出现了一些问题🤔🤔🤔……{error_content[0:300]}'
markup = types.InlineKeyboardMarkup()
btn = types.InlineKeyboardButton("unwelcome", callback_data=f"unwelcome{call.message.chat.id}")
markup.add(btn)
bot.send_message(MAINTAINER, text, disable_web_page_preview=True, reply_markup=markup)
with tempfile.NamedTemporaryFile(mode='wb+', prefix=f"error_{call.message.chat.id}_", suffix=".txt") as tmp:
tmp.write(error_content.encode('u8'))
tmp.flush()
with open(tmp.name, "rb") as f:
bot.send_chat_action(call.message.chat.id, 'upload_document')
bot.send_document(MAINTAINER, f, caption=str(call.message.chat.id))
bot.answer_callback_query(call.id, 'Debug信息已经发送给维护者请耐心等待回复~', show_alert=True)
if __name__ == '__main__':
logging.info('YYeTs bot is running...')
scheduler = BackgroundScheduler()
scheduler.add_job(reset_request, 'cron', hour=0, minute=0)
scheduler.start()
bot.polling(none_stop=True)
# coding: utf-8
# YYeTsBot - bot.py
# 2019/8/15 18:27
__author__ = 'Benny <benny.think@gmail.com>'
import io
import time
import re
import os
import logging
import json
import tempfile
from urllib.parse import quote_plus
import telebot
from telebot import types, apihelper
from tgbot_ping import get_runtime
from apscheduler.schedulers.background import BackgroundScheduler
from fansub import YYeTs
from utils import (save_error_dump, get_error_dump, reset_request, today_request,
show_usage, redis_announcement
)
from config import PROXY, TOKEN, SEARCH_URL, MAINTAINER, REPORT, OFFLINE
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(filename)s [%(levelname)s]: %(message)s')
if PROXY:
apihelper.proxy = {'https': PROXY}
bot = telebot.TeleBot(os.environ.get('TOKEN') or TOKEN)
angry_count = 0
@bot.message_handler(commands=['start'])
def send_welcome(message):
bot.send_chat_action(message.chat.id, 'typing')
bot.send_message(message.chat.id, '欢迎使用,直接发送想要的剧集标题给我就可以了,不需要其他关键字,我会帮你搜索。\n\n'
'人人影视专注于欧美日韩剧集,请不要反馈“我搜不到喜羊羊与灰太狼/流浪地球”这种问题,'
'我会生气的😠😡🤬😒\n\n'
'建议使用<a href="http://www.zmz2019.com/">人人影视</a> 标准译名',
parse_mode='html', disable_web_page_preview=True)
@bot.message_handler(commands=['help'])
def send_help(message):
bot.send_chat_action(message.chat.id, 'typing')
bot.send_message(message.chat.id, '''机器人无法使用或者报错?从 /ping 里可以看到运行状态以及最新信息。
同时你可以使用如下方式寻求使用帮助和报告错误\n
1. @BennyThink
2. <a href='https://github.com/BennyThink/YYeTsBot/issues'>Github issues</a>
3. <a href='https://t.me/mikuri520'>Telegram Channel</a>''', parse_mode='html', disable_web_page_preview=True)
@bot.message_handler(commands=['ping'])
def send_ping(message):
logging.info("Pong!")
bot.send_chat_action(message.chat.id, 'typing')
info = get_runtime("botsrunner_yyets_1")
redis = get_runtime("botsrunner_redis_1", "Redis")
usage = ""
if str(message.chat.id) == MAINTAINER:
usage = show_usage()
announcement = redis_announcement() or ""
if announcement:
announcement = f"\n\n*公告:{announcement}*\n\n"
bot.send_message(message.chat.id, f"{info}\n{redis}\n\n{usage}\n{announcement}",
parse_mode='markdown')
@bot.message_handler(commands=['settings'])
def settings(message):
is_admin = str(message.chat.id) == MAINTAINER
# 普通用户只可以查看,不可以设置。
# 管理员可以查看可以设置
if message.text != "/settings" and not is_admin:
bot.send_message(message.chat.id, "此功能只允许管理员使用。请使用 /ping 和 /settings 查看相关信息")
return
# 删除公告,设置新公告
if message.text != "/settings":
date = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
text = message.text.replace("/settings", f"{date}\t")
logging.info("New announcement %s", text)
redis_announcement(text, "set")
setattr(message, "text", "/settings")
settings(message)
return
announcement = redis_announcement()
markup = types.InlineKeyboardMarkup()
btn1 = types.InlineKeyboardButton("删除公告", callback_data="announcement")
if is_admin and announcement:
markup.add(btn1)
bot.send_message(message.chat.id, f"目前公告:\n\n {announcement or '暂无公告'}", reply_markup=markup)
@bot.callback_query_handler(func=lambda call: re.findall(r"announcement(\S*)", call.data))
def delete_announcement(call):
bot.send_chat_action(call.message.chat.id, 'typing')
redis_announcement(op="del")
bot.edit_message_text(f"目前公告:\n\n {redis_announcement() or '暂无公告'}",
call.message.chat.id,
call.message.message_id)
@bot.message_handler(commands=['credits'])
def send_credits(message):
bot.send_chat_action(message.chat.id, 'typing')
bot.send_message(message.chat.id, '''感谢字幕组的无私奉献!本机器人资源来源:\n
<a href="http://www.zmz2019.com/">人人影视</a>
<a href="http://cili001.com/">磁力下载站</a>
<a href="http://www.zhuixinfan.com/main.php">追新番</a>
''', parse_mode='html', disable_web_page_preview=True)
def download_to_io(photo):
logging.info("Initializing bytes io...")
mem = io.BytesIO()
file_id = photo[-1].file_id
logging.info("Downloading photos...")
file_info = bot.get_file(file_id)
content = bot.download_file(file_info.file_path)
mem.write(content)
logging.info("Downloading complete.")
return mem
def send_my_response(message):
bot.send_chat_action(message.chat.id, 'record_video_note')
# I may also send picture
photo = message.photo
uid = message.reply_to_message.caption
text = f"主人说:{message.text or message.caption or '啥也没说😯'}"
if photo:
bot.send_chat_action(message.chat.id, 'typing')
logging.info("Photo received from maintainer")
mem = download_to_io(photo)
mem.name = f'{uid}.jpg'
r = bot.send_photo(uid, mem.getvalue(), caption=text)
else:
r = bot.send_message(uid, text)
logging.info("Reply has been sent to %s with message id %s", uid, r.message_id)
bot.reply_to(message, "回复已经发送给这位用户")
fw = bot.forward_message(message.chat.id, uid, r.message_id)
time.sleep(3)
bot.delete_message(message.chat.id, fw.message_id)
logging.info("Forward has been deleted.")
@bot.message_handler(content_types=["photo", "text"])
def send_search(message):
yyets = YYeTs()
bot.send_chat_action(message.chat.id, 'typing')
today_request("total")
if message.reply_to_message and message.reply_to_message.document and \
message.reply_to_message.document.file_name.startswith("error") and str(message.chat.id) == MAINTAINER:
today_request("answer")
send_my_response(message)
return
name = message.text
logging.info('Receiving message: %s from user %s(%s)', name, message.chat.username, message.chat.id)
if name is None:
today_request("invalid")
with open('warning.webp', 'rb') as sti:
bot.send_message(message.chat.id, "不要调戏我!我会报警的")
bot.send_sticker(message.chat.id, sti)
return
if OFFLINE:
logging.warning("☢️ Going offline mode!!!")
bot.send_message(message.chat.id, "人人影视官网不可用,目前在使用离线模式,可能没有最新的剧集。")
bot.send_chat_action(message.chat.id, 'upload_document')
result = yyets.offline_search_preview(name)
else:
result = yyets.online_search_preview(name)
markup = types.InlineKeyboardMarkup()
for url, detail in result.items():
btn = types.InlineKeyboardButton(detail, callback_data="choose%s" % url)
markup.add(btn)
if result:
logging.info("🎉 Resource match.")
today_request("success")
bot.send_message(message.chat.id, "呐,💐🌷🌹选一个呀!", reply_markup=markup)
else:
logging.warning("⚠️️ Resource not found")
today_request("fail")
bot.send_chat_action(message.chat.id, 'typing')
encoded = quote_plus(name)
bot.send_message(message.chat.id, f"没有找到你想要的信息,是不是你打了错别字,或者搜索了一些国产影视剧。🤪\n"
f"还是你想调戏我哦🙅‍️\n\n"
f"可以看看这个链接,看看有没有结果。 {SEARCH_URL.format(kw=encoded)} \n\n"
"⚠️如果确定要我背锅,那么请使用 /help 来提交错误", disable_web_page_preview=True)
if REPORT:
btn = types.InlineKeyboardButton("快来修复啦", callback_data="fix")
markup.add(btn)
bot.send_chat_action(message.chat.id, 'upload_document')
bot.send_message(message.chat.id, f"{name}》😭\n大部分情况下机器人是好用的,不要怀疑我的代码质量.\n"
f"如果你真的确定是机器人出问题了,那么点下面的按钮叫 @BennyThink 来修!\n"
f"⚠️报错前请三思,不要乱点,确保这锅应该甩给我。否则我会很生气的😡小心被拉黑哦",
reply_markup=markup)
content = f""" 报告者:{message.chat.first_name}{message.chat.last_name or ""}@{message.chat.username or ""}({message.chat.id})
问题发生时间{time.strftime("%Y-%m-%data %H:%M:%S", time.localtime(message.date))}
请求内容{name}
请求URL{SEARCH_URL.format(kw=encoded)}\n\n
"""
save_error_dump(message.chat.id, content)
@bot.callback_query_handler(func=lambda call: re.findall(r"choose(\S*)", call.data))
def choose_link(call):
yyets = YYeTs()
bot.send_chat_action(call.message.chat.id, 'typing')
# call.data is url, http://www.rrys2020.com/resource/36588
resource_url = re.findall(r"choose(\S*)", call.data)[0]
markup = types.InlineKeyboardMarkup()
if OFFLINE:
worker_page = yyets.offline_search_result(resource_url)
btn1 = types.InlineKeyboardButton("打开网页", url=worker_page)
markup.add(btn1)
bot.send_message(call.message.chat.id, "离线模式,点击按钮打开网页获取结果", reply_markup=markup)
return
btn1 = types.InlineKeyboardButton("分享页面", callback_data="share%s" % resource_url)
btn2 = types.InlineKeyboardButton("我全都要", callback_data="all%s" % resource_url)
markup.add(btn1, btn2)
text = "想要分享页面,还是我全都要?\n\n" \
"名词解释:“分享页面”会返回给你一个网站,从那里可以看到全部的下载链接。\n" \
"“我全都要”会给你发送一个txt文件文件里包含全部下载连接\n"
bot.send_message(call.message.chat.id, text, reply_markup=markup)
@bot.callback_query_handler(func=lambda call: re.findall(r"share(\S*)", call.data))
def share_page(call):
yyets = YYeTs()
bot.send_chat_action(call.message.chat.id, 'typing')
resource_url = re.findall(r"share(\S*)", call.data)[0]
result = yyets.online_search_result(resource_url)
bot.send_message(call.message.chat.id, result['share'])
@bot.callback_query_handler(func=lambda call: re.findall(r"all(\S*)", call.data))
def all_episode(call):
# just send a file
yyets = YYeTs()
bot.send_chat_action(call.message.chat.id, 'typing')
resource_url = re.findall(r"all(\S*)", call.data)[0]
result = yyets.online_search_result(resource_url)
with tempfile.NamedTemporaryFile(mode='wb+', prefix=result["cnname"], suffix=".txt") as tmp:
bytes_data = json.dumps(result["all"], ensure_ascii=False, indent=4).encode('u8')
tmp.write(bytes_data)
tmp.flush()
with open(tmp.name, "rb") as f:
bot.send_chat_action(call.message.chat.id, 'upload_document')
bot.send_document(call.message.chat.id, f)
@bot.callback_query_handler(func=lambda call: re.findall(r"unwelcome(\d*)", call.data))
def send_unwelcome(call):
# this will come from me only
logging.warning("I'm so unhappy!")
message = call.message
bot.send_chat_action(message.chat.id, 'typing')
# angry_count = angry_count + 1
global angry_count
angry_count += 1
uid = re.findall(r"unwelcome(\d*)", call.data)[0]
if uid:
text = "人人影视主要提供欧美日韩等海外资源,你的这个真没有🤷‍。\n" \
"<b>麻烦你先从自己身上找原因</b>,我又不是你的专属客服。\n" \
"不要再报告这种错误了🙄️,面倒な。😡"
bot.send_message(uid, text, parse_mode="html")
bot.reply_to(message, f"有生之日 生气次数:{angry_count}")
@bot.callback_query_handler(func=lambda call: call.data == 'fix')
def report_error(call):
logging.error("Reporting error to maintainer.")
bot.send_chat_action(call.message.chat.id, 'typing')
error_content = get_error_dump(call.message.chat.id)
if error_content == "":
bot.answer_callback_query(call.id, '多次汇报重复的问题并不会加快处理速度。', show_alert=True)
return
text = f'人人影视机器人似乎出现了一些问题🤔🤔🤔……{error_content[0:300]}'
markup = types.InlineKeyboardMarkup()
btn = types.InlineKeyboardButton("unwelcome", callback_data=f"unwelcome{call.message.chat.id}")
markup.add(btn)
bot.send_message(MAINTAINER, text, disable_web_page_preview=True, reply_markup=markup)
with tempfile.NamedTemporaryFile(mode='wb+', prefix=f"error_{call.message.chat.id}_", suffix=".txt") as tmp:
tmp.write(error_content.encode('u8'))
tmp.flush()
with open(tmp.name, "rb") as f:
bot.send_chat_action(call.message.chat.id, 'upload_document')
bot.send_document(MAINTAINER, f, caption=str(call.message.chat.id))
bot.answer_callback_query(call.id, 'Debug信息已经发送给维护者请耐心等待回复~', show_alert=True)
if __name__ == '__main__':
logging.info('YYeTs bot is running...')
scheduler = BackgroundScheduler()
scheduler.add_job(reset_request, 'cron', hour=0, minute=0)
scheduler.start()
bot.polling(none_stop=True)

View File

@@ -1,30 +1,31 @@
# coding: utf-8
# YYeTsBot - config.py
# 2019/8/15 18:42
__author__ = 'Benny <benny.think@gmail.com>'
import os
BASE_URL = "http://www.rrys2020.com"
LOGIN_URL = "http://www.rrys2020.com/user/login"
GET_USER = "http://www.rrys2020.com/user/login/getCurUserTopInfo"
# rss is unavailable as of 2021.01.10
RSS_URL = "http://rss.rrys.tv/rss/feed/{id}"
SEARCH_URL = "http://www.rrys2020.com/search?keyword={kw}&type=resource"
AJAX_LOGIN = "http://www.rrys2020.com/User/Login/ajaxLogin"
SHARE_URL = "http://www.rrys2020.com/resource/ushare"
SHARE_WEB = "http://got002.com/resource.html?code={code}"
# http://got002.com/api/v1/static/resource/detail?code=9YxN91
SHARE_API = "http://got002.com/api/v1/static/resource/detail?code={code}"
WORKERS = "https://yyets.yyetsdb.workers.dev/?id={id}"
TOKEN = os.environ.get("TOKEN") or "TOKEN"
USERNAME = os.environ.get("USERNAME") or "USERNAME"
PASSWORD = os.environ.get("PASSWORD") or "password"
PROXY = os.environ.get("PROXY")
MAINTAINER = os.environ.get("MAINTAINER")
REDIS = os.environ.get("REDIS") or "redis"
REPORT = os.environ.get("REPORT") or False
OFFLINE = os.environ.get("OFFLINE") or False
# coding: utf-8
# YYeTsBot - config.py
# 2019/8/15 18:42
__author__ = 'Benny <benny.think@gmail.com>'
import os
BASE_URL = "http://www.rrys2020.com"
LOGIN_URL = "http://www.rrys2020.com/user/login"
GET_USER = "http://www.rrys2020.com/user/login/getCurUserTopInfo"
SEARCH_URL = "http://www.rrys2020.com/search?keyword={kw}&type=resource"
AJAX_LOGIN = "http://www.rrys2020.com/User/Login/ajaxLogin"
SHARE_URL = "http://www.rrys2020.com/resource/ushare"
SHARE_WEB = "http://got002.com/resource.html?code={code}"
# http://got002.com/api/v1/static/resource/detail?code=9YxN91
SHARE_API = "http://got002.com/api/v1/static/resource/detail?code={code}"
WORKERS = "https://yyets.yyetsdb.workers.dev/?id={id}"
TOKEN = os.environ.get("TOKEN") or "TOKEN"
USERNAME = os.environ.get("USERNAME") or "USERNAME"
PASSWORD = os.environ.get("PASSWORD") or "password"
PROXY = os.environ.get("PROXY")
MAINTAINER = os.environ.get("MAINTAINER")
REDIS = os.environ.get("REDIS") or "redis"
REPORT = os.environ.get("REPORT") or False
OFFLINE = os.environ.get("OFFLINE") or False
FIX_RESOURCE = "https://www.zimuxia.cn/portfolio/{name}"
FIX_SEARCH = "https://www.zimuxia.cn/?s={name}"

233
yyetsbot/fansub.py Normal file
View File

@@ -0,0 +1,233 @@
# coding: utf-8
# YYeTsBot - fansub.py
# 2019/8/15 18:30
__author__ = 'Benny <benny.think@gmail.com>'
import os
import logging
import requests
import pickle
import sys
import json
from bs4 import BeautifulSoup
from config import (SEARCH_URL, GET_USER, BASE_URL, SHARE_WEB,
SHARE_URL, WORKERS, SHARE_API, USERNAME, PASSWORD,
AJAX_LOGIN, REDIS)
import redis
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(filename)s [%(levelname)s]: %(message)s')
session = requests.Session()
ua = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36"
session.headers.update({"User-Agent": ua})
class BaseFansub:
"""
all the subclass should implement three kinds of methods:
1. online search, contains preview for bot and complete result
2. offline search (set pass if not applicable)
3. login and check (set pass if not applicable)
4. search_result this is critical for bot to draw markup
"""
label = None
cookie_file = None
def __init__(self):
self.data = None
self.url = None
self.redis = redis.StrictRedis(host=REDIS, decode_responses=True)
@property
def id(self):
# implement how to get the unique id for this resource
return None
def __get_search_html__(self, kw: str) -> str:
# return html text of search page
pass
def online_search_preview(self, search_text: str) -> dict:
# try to retrieve critical information from html
# this result must return to bot for manual selection
# {"url1": "name1", "url2": "name2"}
pass
def online_search_result(self, resource_url: str) -> dict:
"""
This will happen when user click one of the button, only by then we can know the resource link
From the information above, try to get a detail dict structure.
This method should check cache first if applicable
This method should set self.link and self.data
This method should call __execute_online_search
:param resource_url:
:return: {"all": rss_result, "share": share_link, "cnname": cnname}
"""
pass
def __execute_online_search_result(self) -> dict:
"""
Do the real search job, without any cache mechanism
:return: {"all": rss_result, "share": share_link, "cnname": cnname}
"""
pass
def offline_search_preview(self, search_text: str) -> dict:
# this result must return to bot for manual selection
# the same as online
pass
def offline_search_result(self, resource_url) -> dict:
"""
Same as online_search_result
:param resource_url:
:return:
"""
pass
def __execute_offline_search_result(self) -> dict:
"""
Do the search job, without any cache mechanism
:return: {"all": rss_result, "share": share_link, "cnname": cnname}
"""
pass
def __login_check(self):
pass
def __manual_login(self):
pass
def __save_cookies(self, requests_cookiejar):
with open(self.cookie_file, 'wb') as f:
pickle.dump(requests_cookiejar, f)
def __load_cookies(self):
with open(self.cookie_file, 'rb') as f:
return pickle.load(f)
def __get_from_cache(self, url: str, method_name: str) -> dict:
logging.info("Reading %s data from cache %s", self.label, url)
data = self.redis.get(url)
if data:
logging.info("Cache hit")
return json.loads(data)
else:
logging.info("Cache miss")
result_method = getattr(self, method_name)
self.__save_to_cache(url, result_method(url))
return self.__get_from_cache(url, method_name)
def __save_to_cache(self, url: str, value: dict, ex=3600 * 12) -> None:
data = json.dumps(value, ensure_ascii=False)
self.redis.set(url, data, ex=ex)
class YYeTs(BaseFansub):
label = "yyets"
cookie_file = os.path.join("data", "cookies.dump")
@property
def id(self):
# implement how to get the unique id for this resource
rid = self.url.split('/')[-1]
return rid
def __get_search_html__(self, kw: str) -> str:
self.__login_check()
cookie = self.__load_cookies()
logging.info("Searching for %s", kw)
r = session.get(SEARCH_URL.format(kw=kw), cookies=cookie)
r.close()
return r.text
def online_search_preview(self, search_text: str) -> dict:
html_text = self.__get_search_html__(search_text)
logging.info('Parsing html...')
soup = BeautifulSoup(html_text, 'lxml')
link_list = soup.find_all("div", class_="clearfix search-item")
dict_result = {}
for block in link_list:
name = block.find_all('a')[-1].text
url = BASE_URL + block.find_all('a')[-1].attrs['href']
dict_result[url] = name
return dict_result
def online_search_result(self, resource_url: str) -> dict:
self.url = resource_url
self.data = self.__get_from_cache(self.url, self.__execute_online_search_result.__name__)
return self.data
def __execute_online_search_result(self) -> dict:
logging.info("Loading detail page %s", self.url)
share_link, api_res = self.__get_share_page()
cnname = api_res["data"]["info"]["cnname"]
self.data = {"all": api_res, "share": share_link, "cnname": cnname}
return self.data
def offline_search_preview(self, search_text: str) -> dict:
# from cloudflare workers
# no redis cache for now
logging.info("Loading data from cfkv...")
index = WORKERS.format(id="index")
data: dict = requests.get(index).json()
logging.info("Loading complete, searching now...")
results = {}
for name, rid in data.items():
if search_text in name:
fake_url = f"http://www.rrys2020.com/resource/{rid}"
results[fake_url] = name.replace("\n", " ")
logging.info("Search complete")
return results
def offline_search_result(self, resource_url) -> dict:
self.url = resource_url
query_url = WORKERS.format(id=self.id)
self.data = {"all": None, "share": query_url, "cnname": None}
return self.data
def __login_check(self):
if not os.path.exists(self.cookie_file):
logging.warning("Cookie file not found")
self.__manual_login()
cookie = self.__load_cookies()
r = session.get(GET_USER, cookies=cookie)
if not r.json()['status'] == 1:
self.__manual_login()
def __manual_login(self):
data = {"account": USERNAME, "password": PASSWORD, "remember": 1}
logging.info("Login in as %s", data)
r = requests.post(AJAX_LOGIN, data=data)
resp = r.json()
if resp.get('status') == 1:
logging.info("Login success! %s", r.cookies)
self.__save_cookies(r.cookies)
else:
logging.error("Login failed! %s", resp)
sys.exit(1)
r.close()
def __get_share_page(self):
rid = self.id
res = session.post(SHARE_URL, data={"rid": rid}, cookies=self.__load_cookies()).json()
share_code = res['data'].split('/')[-1]
share_url = SHARE_WEB.format(code=share_code)
logging.info("Share url is %s", share_url)
# get api response
api_response = session.get(SHARE_API.format(code=share_code)).json()
return share_url, api_response
if __name__ == '__main__':
y = YYeTs()

View File

@@ -1,112 +1,71 @@
# coding: utf-8
# YYeTsBot - utils.py
# 2019/8/15 20:27
__author__ = 'Benny <benny.think@gmail.com>'
import os
import sys
import pickle
import json
import logging
import requests
import redis
from config import AJAX_LOGIN, USERNAME, PASSWORD, REDIS
r = redis.StrictRedis(host=REDIS, decode_responses=True)
cookie_file = os.path.join(os.path.dirname(__file__), 'data', 'cookies.dump')
def save_to_cache(url: str, value: dict) -> None:
data = json.dumps(value, ensure_ascii=False)
r.set(url, data, ex=3600 * 12)
def yyets_get_from_cache(url: str) -> dict:
logging.info("Reading data from cache %s", url)
from html_request import get_detail_page
data = r.get(url)
if data:
logging.info("Cache hit")
return json.loads(data)
else:
logging.info("Cache miss")
save_to_cache(url, get_detail_page(url))
return yyets_get_from_cache(url)
def save_error_dump(uid, err: str):
r.set(uid, err)
def get_error_dump(uid) -> str:
err = r.get(uid)
r.delete(uid)
if not err:
err = ""
return err
def redis_announcement(content="", op="get"):
if op == "get":
return r.get("announcement")
elif op == "set":
r.set("announcement", content)
elif op == "del":
r.delete("announcement")
def save_cookies(requests_cookiejar):
with open(cookie_file, 'wb') as f:
pickle.dump(requests_cookiejar, f)
def load_cookies():
with open(cookie_file, 'rb') as f:
return pickle.load(f)
def login():
data = {"account": USERNAME, "password": PASSWORD, "remember": 1}
logging.info("Login in as %s", data)
r = requests.post(AJAX_LOGIN, data=data)
resp = r.json()
if resp.get('status') == 1:
logging.info("Login success! %s", r.cookies)
save_cookies(r.cookies)
else:
logging.error("Login failed! %s", resp)
sys.exit(1)
r.close()
def today_request(request_type: str):
if r.exists("usage"):
data: str = r.get("usage")
dict_data: dict = json.loads(data)
dict_data[request_type] += 1
saved_data: str = json.dumps(dict_data)
else:
data_format: dict = dict(total=0, invalid=0, answer=0, success=0, fail=0)
data_format[request_type] += 1
saved_data: str = json.dumps(data_format)
r.set("usage", saved_data)
def reset_request():
r.delete("usage")
def show_usage():
m = "今天我已经服务了{total}次🤓,无效请求{invalid}😆,主人回复{answer}次🤨,成功请求{success}次😝,失败请求{fail}次🤣"
data: str = r.get("usage")
if r.exists("usage"):
dict_data: dict = json.loads(data)
else:
dict_data: dict = dict(total=0, invalid=0, answer=0, success=0, fail=0)
return m.format(**dict_data)
# coding: utf-8
# YYeTsBot - utils.py
# 2019/8/15 20:27
__author__ = 'Benny <benny.think@gmail.com>'
import os
import sys
import pickle
import json
import logging
import requests
import redis
from config import AJAX_LOGIN, USERNAME, PASSWORD, REDIS
r = redis.StrictRedis(host=REDIS, decode_responses=True)
cookie_file = os.path.join(os.path.dirname(__file__), 'data', 'cookies.dump')
def save_error_dump(uid, err: str):
r.set(uid, err)
def get_error_dump(uid) -> str:
err = r.get(uid)
r.delete(uid)
if not err:
err = ""
return err
def redis_announcement(content="", op="get"):
if op == "get":
return r.get("announcement")
elif op == "set":
r.set("announcement", content)
elif op == "del":
r.delete("announcement")
def today_request(request_type: str):
if r.exists("usage"):
data: str = r.get("usage")
dict_data: dict = json.loads(data)
dict_data[request_type] += 1
saved_data: str = json.dumps(dict_data)
else:
data_format: dict = dict(total=0, invalid=0, answer=0, success=0, fail=0)
data_format[request_type] += 1
saved_data: str = json.dumps(data_format)
r.set("usage", saved_data)
def reset_request():
r.delete("usage")
def show_usage():
m = "今天我已经服务了{total}次🤓,无效请求{invalid}😆,主人回复{answer}次🤨,成功请求{success}次😝,失败请求{fail}次🤣"
data: str = r.get("usage")
if r.exists("usage"):
dict_data: dict = json.loads(data)
else:
dict_data: dict = dict(total=0, invalid=0, answer=0, success=0, fail=0)
return m.format(**dict_data)

View File

Before

Width:  |  Height:  |  Size: 19 KiB

After

Width:  |  Height:  |  Size: 19 KiB