增加了兔小贝儿歌

controllers/cms.py

@@ -26,7 +26,7 @@ py_ctx = {
 'requests':requests,'print':print,'base64Encode':base64Encode,'baseDecode':baseDecode,
 'log':logger.info,'fetch':fetch,'post':post,'request':request,'getCryptoJS':getCryptoJS,
 'buildUrl':buildUrl,'getHome':getHome,'setDetail':setDetail,'join':join,'urljoin2':urljoin2,
-'PC_UA':PC_UA,'MOBILE_UA':MOBILE_UA,'UC_UA':UC_UA
+'PC_UA':PC_UA,'MOBILE_UA':MOBILE_UA,'UC_UA':UC_UA,'IOS_UA':IOS_UA
 }
 # print(getCryptoJS())
 
@@ -104,6 +104,8 @@ class CMS:
                     headers[k] = PC_UA
                 elif v == 'UC_UA':
                     headers[k] = UC_UA
+                elif v == 'IOS_UA':
+                    headers[k] = IOS_UA
         lower_keys = list(map(lambda x:x.lower(),keys))
         if not 'user-agent' in lower_keys:
             headers['User-Agent'] = UA
@@ -302,6 +304,14 @@ class CMS:
         else:
             return ''
 
+    def dealJson(self,html):
+        try:
+            res = re.search('.*?{(.*)}',html,re.M|re.I).groups()[0]
+            html = '{' + res + '}'
+            return html
+        except:
+            return html
+
     def checkHtml(self,r):
         r.encoding = self.encoding
         html = r.text
@@ -474,6 +484,8 @@ class CMS:
                 return self.blank()
             jsp = jsoup(self.homeUrl)
             is_json = str(p[0]).startswith('json:')
+            if is_json:
+                html = self.dealJson(html)
             pdfh = jsp.pjfh if is_json else jsp.pdfh
             pdfa = jsp.pjfa if is_json else jsp.pdfa
             pd = jsp.pj if is_json else jsp.pd
@@ -481,12 +493,17 @@ class CMS:
             try:
                 if self.double:
                     items = pdfa(html, p[0])
+                    # print(items)
                     for item in items:
                         items2 = pdfa(item,p[1])
+                        # print(items2)
                         for item2 in items2:
                             try:
                                 title = pdfh(item2, p[2])
-                                img = pd(item2, p[3])
+                                try:
+                                    img = pd(item2, p[3])
+                                except:
+                                    img = ''
                                 desc = pdfh(item2, p[4])
                                 links = [pd(item2, p5) if not self.detailUrl else pdfh(item2, p5) for p5 in p[5].split('+')]
                                 link = '$'.join(links)
@@ -617,6 +634,7 @@ class CMS:
                 r = requests.get(url, headers=self.headers, timeout=self.timeout)
                 html = self.checkHtml(r)
                 if is_json:
+                    html = self.dealJson(html)
                     html = json.loads(html)
                 # print(html)
                 items = pdfa(html,p[0].replace('json:','',1))
@@ -659,8 +677,10 @@ class CMS:
     def detailOneVod(self,id,fyclass=''):
         detailUrl = str(id)
         vod = {}
-        if not detailUrl.startswith('http'):
+        if not detailUrl.startswith('http') and not '/' in detailUrl:
             url = self.detailUrl.replace('fyid', detailUrl).replace('fyclass',fyclass)
+        elif '/' in detailUrl:
+            url = urljoin(self.homeUrl,detailUrl)
         else:
             url = detailUrl
         print(url)
@@ -671,8 +691,8 @@ class CMS:
                 vod['vod_play_from'] = '道长在线'
                 vod['vod_remarks'] = detailUrl
                 vod['vod_actor'] = '没有二级,只有一级链接直接嗅探播放'
-                vod['vod_content'] = detailUrl
-                vod['vod_play_url'] = '嗅探播放$'+self.play_url+detailUrl
+                vod['vod_content'] = url
+                vod['vod_play_url'] = '嗅探播放$'+self.play_url+url
                 print(vod)
                 return vod
 
@@ -718,6 +738,7 @@ class CMS:
                 r = requests.get(url, headers=self.headers, timeout=self.timeout)
                 html = self.checkHtml(r)
                 if is_json:
+                    html = self.dealJson(html)
                     html = json.loads(html)
                 if p.get('title'):
                     p1 = p['title'].split(';')
@@ -867,7 +888,7 @@ class CMS:
                 'list': []
             }
             logger.info(f'{self.getName()}获取详情页耗时:{get_interval(t1)}毫秒,发生错误:{e}')
-        print(result)
+        # print(result)
         return result
 
     def searchContent(self, key, fypage=1):
@@ -919,6 +940,7 @@ class CMS:
                 r = requests.get(url, headers=self.headers,timeout=self.timeout)
                 html = self.checkHtml(r)
                 if is_json:
+                    html = self.dealJson(html)
                     html = json.loads(html)
                 # print(html)
                 if not is_json and html.find('输入验证码') > -1:
@@ -1008,6 +1030,7 @@ class CMS:
                             play_url = lazy_url
                 else:
                     jscode = str(self.lazy).split('js:')[1]
+                    jsp = jsoup(self.url)
                     # jscode = f'var input={play_url};{jscode}'
                     # print(jscode)
                     headers['Referer'] = getHome(play_url)
@@ -1018,6 +1041,7 @@ class CMS:
                         'jxs':jxs,
                         'getParse':self.d.getParse,
                         'saveParse':self.d.saveParse,
+                        'jsp': jsp,
                         'pdfh': self.d.jsp.pdfh,
                         'pdfa': self.d.jsp.pdfa, 'pd': self.d.jsp.pd,
                     })

js/LIBVIO.js

 var rule = Object.assign(muban.首图2,{
 title:'LIBVIO',
-host:'https://www.libvio.me',
+// host:'https://www.libvio.me',
+host:'https://www.libvio.fun',
 url:'/type/fyclass-fypage.html',
 class_parse:'.stui-header__menu li:gt(0):lt(7);a&&Text;a&&href;/(\\d+).html',
 searchUrl:'/search/**----------fypage---.html',

js/version.txt

-3.4.4
\ No newline at end of file
+3.4.5
\ No newline at end of file

js/兔小贝.js

+var rule = {
+    title:'兔小贝',
+    host:'https://www.tuxiaobei.com',
+    homeUrl:'',
+    url:'/list/mip-data?typeId=fyclass&page=fypage&callback=',
+    detailUrl:'/play/fyid',
+    searchUrl:'/search/index?key=**',
+    headers:{
+        'User-Agent':'MOBILE_UA'
+    },
+    timeout:5000,
+    class_url:'2&3&4&25',
+    class_name:'儿歌&故事&国学&启蒙',
+    //class_name:'#page-viewport&&ul&&li;.text&&Text;a&&href;/(.*)',
+    cate_exclude:'应用',
+    推荐:'.pic-list.list-box;.items;.text&&Text;mip-img&&src;.all&&Text;a&&href',
+    double:true,
+    limit:5,
+    play_parse:true,
+    lazy:'js:fetch_params.headers["user-agent"] = IOS_UA;let html=fetch(input,fetch_params);let src = jsp.pdfh(html,"body&&#videoWrap&&video-src");input=src;',
+    // 一级:'json:data.items;name;image;collect_num;category_id+video_id',
+    一级:'json:data.items;name;image;duration_string;video_id',
+    二级:'*',
+    搜索:'.list-con&&.items;.text&&Text;mip-img&&src;.time&&Text;a&&href',
+    searchable:1,
+    quickSearch:0,
+}
\ No newline at end of file

readme.md

@@ -48,6 +48,7 @@
 [获取本地设备信息](https://m.jb51.net/article/140716.htm)   
 ###### 2022/09/10
 - [X] 1.升级至3.4.4.增加小强迷源,增加二级重定向属性(提供重定向后的源码,让代码重新取重定向过后的线路和播放列表)
+- [X] 1.升级至3.4.5.增加兔小贝儿歌源,优化json:细节处理以及详情页拼接细节
 ###### 2022/09/09
 - [X] 1.增加西瓜源,修复一级不支持lazy的bug
 - [X] 2.兄弟们dockerhub没法push镜像不知道咋回事,3.4.1的镜像自己用docker目录下的文件build吧

utils/encode.py

@@ -174,7 +174,7 @@ def base_request(url,obj):
         method = 'get'
         obj['method'] = 'method'
     # print(obj)
-    print(f'{method}:{url}')
+    print(f"{method}:{url}:{obj['headers']}")
     try:
         # r = requests.get(url, headers=headers, params=body, timeout=timeout)
         if method.lower() == 'get':
@@ -194,7 +194,7 @@ def base_request(url,obj):
 def fetch(url,obj):
     obj = dealObj(obj)
     if not obj.get('headers') or not obj['headers'].get('User-Agent'):
-        obj['headers']['User-Agent'] = PC_UA
+        obj['headers']['User-Agent'] = obj['headers'].get('user-agent',PC_UA)
     return base_request(url,obj)
 
 def post(url,obj):
@@ -206,7 +206,7 @@ def request(url,obj):
     obj = dealObj(obj)
     # print(f'{method}:{url}')
     if not obj.get('headers') or not obj['headers'].get('User-Agent'):
-        obj['headers']['User-Agent'] = UC_UA
+        obj['headers']['User-Agent'] = obj['headers'].get('user-agent',UC_UA)
 
     return base_request(url, obj)
 

utils/htmlParser.py

@@ -28,13 +28,13 @@ class jsoup:
             option = parse.split('&&')[-1]
             parse = parse.split('&&')[:-1]  # 如果只有一个&& 取的就直接是0
             if len(parse) > 1:  # 如果不大于1可能就是option操作,不需要拼eq
-                parse = ' '.join([i if self.test(':eq|:lt|:gt',i) else f'{i}:eq(0)' for i in parse])
+                parse = ' '.join([i if self.test(':eq|:lt|:gt|#',i) else f'{i}:eq(0)' for i in parse])
             else:
-                parse = parse[0] if self.test(':eq|:lt|:gt',parse[0]) else f'{parse[0]}:eq(0)'
-
+                parse = parse[0] if self.test(':eq|:lt|:gt|#',parse[0]) else f'{parse[0]}:eq(0)'
         if option:
             # print(f'parse:{parse}=>(option:{option})')
             ret = doc(parse)
+            # print(html)
             # FIXME 解析出来有多个的情况应该自动取第一个
             if option == 'Text':
                 ret = ret.text()

utils/update.py

@@ -96,6 +96,7 @@ def copy_to_update():
         # print(f'升级失败,找不到目录{dr_path}')
         logger.info(f'升级失败,找不到目录{dr_path}')
         return False
+    # 千万不能覆盖super，base
     paths = ['js','models','controllers','libs','static','templates','utils','txt']
     for path in paths:
         force_copy_files(os.path.join(dr_path, path),os.path.join(base_path, path))

utils/web.py

@@ -14,6 +14,7 @@ MOBILE_UA = 'Mozilla/5.0 (Linux; Android 11; M2007J3SC Build/RKQ1.200826.002; wv
 PC_UA = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.54 Safari/537.36'
 UA = 'Mozilla/5.0'
 UC_UA = 'Mozilla/5.0 (Linux; U; Android 9; zh-CN; MI 9 Build/PKQ1.181121.001) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/57.0.2987.108 UCBrowser/12.5.5.1035 Mobile Safari/537.36'
+IOS_UA = 'Mozilla/5.0 (iPhone; CPU iPhone OS 13_2_3 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/13.0.3 Mobile/15E148 Safari/604.1'
 headers = {
         'Referer': 'https://www.baidu.com',
         'user-agent': UA,