offline mode

bot.py

@@ -19,10 +19,11 @@
 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
-from utils import (save_error_dump, save_to_cache, get_from_cache, get_error_dump,
-                   reset_request, today_request, show_usage)
-from config import PROXY, TOKEN, SEARCH_URL, MAINTAINER, REPORT
+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
+                   )
+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:
@@ -119,23 +120,29 @@ def send_search(message):
         today_request("answer")
         send_my_response(message)
         return
-    bot.send_chat_action(message.chat.id, 'record_video')
 
+    bot.send_chat_action(message.chat.id, 'record_video')
     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
 
-    logging.info('Receiving message about %s from user %s(%s)', name, message.chat.username, message.chat.id)
-    html = get_search_html(name)
-    result = analyse_search_html(html)
+    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 = ""
+        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['name'], callback_data="choose%s" % url)
+        btn = types.InlineKeyboardButton(detail, callback_data="choose%s" % url)
         markup.add(btn)
 
     if result:
@@ -151,7 +158,7 @@ def send_search(message):
         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 ", disable_web_page_preview=True)
+                                          "⚠️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)
@@ -174,13 +181,20 @@ 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()
 
-    link = get_from_cache(resource_url)
+    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)
 
-    markup = types.InlineKeyboardMarkup()
     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)
@@ -194,7 +208,7 @@ def choose_link(call):
 def share_page(call):
     bot.send_chat_action(call.message.chat.id, 'typing')
     resource_url = re.findall(r"share(\S*)", call.data)[0]
-    result = get_from_cache(resource_url)
+    result = yyets_get_from_cache(resource_url)
     bot.send_message(call.message.chat.id, result['share'])
 
 
@@ -203,7 +217,7 @@ 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 = get_from_cache(resource_url)
+    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')

config.py

@@ -11,18 +11,20 @@
 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}"
-RESOURCE_SCORE = "http://www.rrys2020.com/resource/getScore"  # post rid=38000
 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

html_request.py

@@ -10,7 +10,7 @@
 import feedparser
 from bs4 import BeautifulSoup
 
-from config import SEARCH_URL, GET_USER, RSS_URL, BASE_URL, SHARE_WEB, SHARE_URL, RESOURCE_SCORE, SHARE_API
+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')
@@ -43,7 +43,7 @@ def get_detail_page(url: str) -> dict:
     rss_url = RSS_URL.format(id=url.split("/")[-1])
     rss_result = analyse_rss(rss_url)
 
-    # get name from here...
+    # get search_content from here...
     if not rss_result:
         rss_result = api_res
 
@@ -58,7 +58,7 @@ def analyse_search_html(html: str) -> dict:
     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": name, "score": get_score(url.split('/')[-1])}
+        list_result[url] = name
 
     return list_result
 
@@ -92,21 +92,36 @@ def analysis_share_page(detail_url: str) -> (str, dict):
     return share_url, api_response
 
 
-def get_score(rid: str) -> float:
-    # there is actually no meaning in getting score for now
-    return 10.0
-    # return s.post(RESOURCE_SCORE, data={"rid": rid}).json()['score']
-
-
 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__':
-    __search = get_search_html('轮到你了')
-    __search_result = analyse_search_html(__search)
-    __chose = "http://www.rrys2020.com/resource/38000"
-    __link = get_detail_page(__chose)
-    print(__link)
+    a = offline_search("越狱")
+    print(a)

utils.py

@@ -24,7 +24,7 @@ def save_to_cache(url: str, value: dict) -> None:
     r.set(url, data, ex=3600 * 12)
 
 
-def get_from_cache(url: str) -> dict:
+def yyets_get_from_cache(url: str) -> dict:
     logging.info("Reading data from cache %s", url)
     from html_request import get_detail_page
 
@@ -35,7 +35,7 @@ def get_from_cache(url: str) -> dict:
     else:
         logging.info("Cache miss")
         save_to_cache(url, get_detail_page(url))
-        return get_from_cache(url)
+        return yyets_get_from_cache(url)
 
 
 def save_error_dump(uid, err: str):