优化pdfh

controllers/cms.py

@@ -1048,7 +1048,7 @@ class CMS:
                 if is_json:
                     html = self.dealJson(html)
                     html = json.loads(html)
-                # print(html)
+                print(html)
                 if not is_json and html.find('输入验证码') > -1:
                     cookie = verifyCode(url,self.headers,self.timeout,self.retry_count,self.ocr_api)
                     # cookie = ''
@@ -1063,14 +1063,15 @@ class CMS:
                     html = r.text
 
                 items = pdfa(html,p[0].replace('json:','',1))
-                # print(items)
+                print(len(items),items)
                 videos = []
                 for item in items:
                     # print(item)
                     try:
                         # title = pdfh(item, p[1])
-                        title =''.join([pdfh(item, i) for i in p[1].split('||')])
-
+                        print(p[1].split('||'))
+                        title = ''.join([pdfh(item, i) for i in p[1].split('||')])
+                        print(title)
                         try:
                             img = pd(item, p[2])
                         except:
@@ -1095,7 +1096,8 @@ class CMS:
                             "vod_remarks": desc,
                             "vod_content": content, # 无用参数
                         })
-                    except:
+                    except Exception as e:
+                        print(e)
                         pass
                 # print(videos)
             except Exception as e:

js/追剧喵.js

@@ -2,4 +2,5 @@
 var rule = Object.assign(muban.海螺2,{
     title:'追剧喵',
     host:'https://zjmiao.com',
+    搜索:'.search-list;a&&Text;.lazy&&data-original;.deployment&&Text;a&&href',
 });
\ No newline at end of file

utils/htmlParser.py

@@ -22,6 +22,7 @@ class jsoup:
     def pdfh(self,html,parse:str,add_url=False):
         if not parse:
             return ''
+
         doc = pq(html)
         option = None
         if parse.find('&&') > -1:
@@ -32,8 +33,9 @@ class jsoup:
             else:
                 parse = parse[0] if self.test(':eq|:lt|:gt|#',parse[0]) else f'{parse[0]}:eq(0)'
         # FIXME 暂时不支持jsonpath那样的|| 分割取或属性
+
         if option:
-            # print(f'parse:{parse}=>(option:{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
@@ -42,8 +44,8 @@ class jsoup:
             elif option == 'Html':
                 ret = ret.html()
             else:
-                ret = ret.attr(option)
-                if add_url and option in ['url','src','href','data-original','data-src']:
+                ret = ret.attr(option) or ''
+                if ret and add_url and option in ['url','src','href','data-original','data-src']:
                     if 'http' in ret:
                         ret = ret[ret.find('http'):]
                     else: