增加了蓝莓影视筛选示例

controllers/cms.py

@@ -621,6 +621,22 @@ class CMS:
         t1 = time()
         pg = str(fypage)
         url = self.url.replace('fyclass',fyclass)
+        if self.filter_url:
+            if not 'fyfilter' in url: # 第一种情况,默认不写fyfilter关键字,视为直接拼接在链接后面当参数
+                if not url.endswith('&') and not self.filter_url.startswith('&'):
+                    url += '&'
+                url += self.filter_url
+            else: # 第二种情况直接替换关键字为待拼接的结果后面渲染,适用于 ----fypage.html的情况
+                url = url.replace('fyfilter', self.filter_url)
+            url = render_template_string(url,fl=fl)
+
+            # fl_url = render_template_string(self.filter_url,fl=fl)
+            # if not 'fyfilter' in url: # 第一种情况,默认不写fyfilter关键字,视为直接拼接在链接后面当参数
+            #     if not url.endswith('&') and not fl_url.startswith('&'):
+            #         url += '&'
+            #     url += fl_url
+            # else: # 第二种情况直接替换关键字为渲染后的结果,适用于 ----fypage.html的情况
+            #     url = url.replace('fyfilter',fl_url)
         if url.find('fypage') > -1:
             if '(' in url and ')' in url:
                 # url_rep = url[url.find('('):url.find(')')+1]
@@ -639,15 +655,7 @@ class CMS:
                 url = url.replace('fypage',pg)
         if fypage == 1 and self.test('[\[\]]',url):
             url = url.split('[')[1].split(']')[0]
-        if self.filter_url:
-            fl_url = render_template_string(self.filter_url,fl=fl)
-            if not 'fyfilter' in url: # 第一种情况,默认不写fyfilter关键字,视为直接拼接在链接后面当参数
-                if not url.endswith('&') and not fl_url.startswith('&'):
-                    url += '&'
-                url += fl_url
-            else: # 第二种情况直接替换关键字为渲染后的结果,适用于 ----fypage.html的情况
-                url = url.replace('fyfilter',fl_url)
-        print(url)
+        # print(url)
         p = self.一级
         jsp = jsoup(self.url)
         videos = []

py/mxpro筛选.py

+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+# File  : mxpro筛选.py
+# Author: DaShenHan&道长-----先苦后甜，任凭晚风拂柳颜------
+# Date  : 2022/9/13
+import re
+
+import requests
+from utils.htmlParser import jsoup
+
+headers = {'user-agent':'Mozilla/5.0 (Linux; Android 11; M2007J3SC Build/RKQ1.200826.002; wv) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/77.0.3865.120 MQQBrowser/6.2 TBS/045714 Mobile Safari/537.36'}
+
+
+def getFilters(url):
+    cate_id = str(re.search('.*/(\d+)', url).groups()[0])
+    print(cate_id)
+    jsp = jsoup(url)
+    pdfh = jsp.pdfh
+    pdfa = jsp.pdfa
+    print(jsp)
+    r = requests.get(url,headers=headers)
+    r.encoding = r.apparent_encoding
+    html = r.text
+    cls_list = pdfa(html,'.module-class&&.module-class-items')
+    print(len(cls_list))
+    ft_dict = {cate_id:[]}
+    for cls in cls_list:
+        tt = pdfh(cls,'.module-item-title&&Text')
+        values = pdfa(cls,'.module-item-box&&a')
+        # vl = [{"n":pdfh(i,'a&&Text'),"v":pdfh(i,'a&&href')} for i in values]
+        vl = [{"n":pdfh(i,'a&&Text'),"v":re.search('(.*?)-(.*)',pdfh(i,'a&&href'),re.M|re.I|re.S).groups()[1].replace('.html','').replace('-','')} for i in values]
+        ft_dict[cate_id].append({
+            'key': tt,
+            'name': tt,
+            'value': vl
+        })
+    print(ft_dict)
+    return ft_dict
+
+if __name__ == '__main__':
+    new_dict = {}
+    for i in '20&1&2&3&4&23'.split('&'):
+        ft_dict = getFilters(f'https://lanmeiguojiang.com/show/{i}-----------.html')
+        new_dict.update(ft_dict)
+    print(new_dict)
+
+