From 509fe358453d86b3d737f21ad5136fccb7eac4af Mon Sep 17 00:00:00 2001
From: hjdhnx <hjd124579>
Date: Fri, 16 Sep 2022 18:05:16 +0800
Subject: [PATCH] =?UTF-8?q?=E4=BC=98=E5=8C=96pdfh?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 base/rules.db                                | Bin 40960 -> 40960 bytes
 controllers/cms.py                           |  12 +++++++-----
 "js/\350\277\275\345\211\247\345\226\265.js" |   1 +
 utils/htmlParser.py                          |   8 +++++---
 4 files changed, 13 insertions(+), 8 deletions(-)

diff --git a/base/rules.db b/base/rules.db
index 8a503d3657320f471a0335c39c461d2716c4b710..8579e1d50696c9b01a66654ccb3e03aef629c1f2 100644
GIT binary patch
delta 90
zcmZoTz|?SnX@WH4>xnYXjITE)<O(~cStOdJ7@C_I8<-j=npz|on<iN#o0=pWrWl!}
u8Yh|C8W<Z{8mC&CrW#mUrX(gCq?)7}TPCMin586|SeT?(ZsrsD)C~X;3LCxv

delta 90
zcmZoTz|?SnX@WH4i-|JMj4w7O<O(~Qq$Z}N8K)+tnI@+irx=?Wq?no-7?_!xnj0r4
ur5GmKrly*kCnqNwq#9VHSQwd@r<tZ2rI;9*C8s5so2FW%ZsrsD)C~Yo6dd{h

diff --git a/controllers/cms.py b/controllers/cms.py
index fa6fb41..b09996c 100644
--- a/controllers/cms.py
+++ b/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:
diff --git "a/js/\350\277\275\345\211\247\345\226\265.js" "b/js/\350\277\275\345\211\247\345\226\265.js"
index 18f314d..9a6f989 100644
--- "a/js/\350\277\275\345\211\247\345\226\265.js"
+++ "b/js/\350\277\275\345\211\247\345\226\265.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
diff --git a/utils/htmlParser.py b/utils/htmlParser.py
index f2fadaf..f94dfad 100644
--- a/utils/htmlParser.py
+++ b/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:
-- 
GitLab