把相同的模板都进行了继承写法

新增了影视工厂和在线之家
修复了cookemv和莫扎兔等要搜索验证的网站

app.py

@@ -7,6 +7,7 @@ import random
 from utils.encode import base64Encode
 import js2py
 from flask_sqlalchemy import SQLAlchemy
+from flask_migrate import Migrate
 import config
 # import settings
 import warnings
@@ -32,7 +33,7 @@ print('自定义播放解析地址:',app.config.get('PLAY_URL'))
 print('当前操作系统',sys.platform)
 app.logger.name="drLogger"
 db = SQLAlchemy(app)
-
+migrate = Migrate(app, db)
 rule_list = getRuleLists()
 logger.info(rule_list)
 logger.info(f'局域网: {getHost(1, 5705)}/index\n本地: {getHost(0, 5705)}/index')
@@ -104,6 +105,7 @@ def vod():
     # rule = ctx.eval('rule')
     ruleDict = ctx.rule.to_dict()
     ruleDict['id'] = rule  # 把路由请求的id装到字典里,后面播放嗅探才能用
+    # print(ruleDict)
     # print(rule)
     # print(type(rule))
     # print(ruleDict)

classes/cms.py

@@ -11,7 +11,7 @@ from utils.web import *
 from models import *
 from utils.config import config
 from utils.log import logger
-from utils.encode import base64Encode,baseDecode,fetch,post,request,getCryptoJS,getPreJs,buildUrl
+from utils.encode import base64Encode,baseDecode,fetch,post,request,getCryptoJS,getPreJs,buildUrl,getHome,verifyCode
 from utils.safePython import safePython
 from utils.parser import runPy,runJScode
 from utils.htmlParser import jsoup
@@ -23,7 +23,7 @@ from easydict import EasyDict as edict
 py_ctx = {
 'requests':requests,'print':print,'base64Encode':base64Encode,'baseDecode':baseDecode,
 'log':logger.info,'fetch':fetch,'post':post,'request':request,'getCryptoJS':getCryptoJS,
-'buildUrl':buildUrl
+'buildUrl':buildUrl,'getHome':getHome,'verifyCode':verifyCode
 }
 # print(getCryptoJS())
 
@@ -35,12 +35,19 @@ class CMS:
         self.id = rule.get('id', self.title)
         self.lazy = rule.get('lazy', False)
         self.play_disable = new_conf.get('PLAY_DISABLE',False)
+        self.retry_count = new_conf.get('RETRY_CNT',3)
         self.lazy_mode = new_conf.get('LAZYPARSE_MODE')
-        self.vod = redirect(url_for('vod')).headers['Location']
+        try:
+            self.vod = redirect(url_for('vod')).headers['Location']
+        except:
+            self.vod = '/vod'
         # if not self.play_disable and self.lazy:
         if not self.play_disable:
             self.play_parse = rule.get('play_parse', False)
-            play_url = getHost(self.lazy_mode)
+            try:
+                play_url = getHost(self.lazy_mode)
+            except:
+                play_url = getHost(1,5705)
             # play_url = new_conf.get('PLAY_URL',getHost(2))
             if not play_url.startswith('http'):
                 play_url = 'http://'+play_url
@@ -65,6 +72,10 @@ class CMS:
         detailUrl = rule.get('detailUrl','')
         searchUrl = rule.get('searchUrl','')
         headers = rule.get('headers',{})
+        cookie = self.getCookie()
+        # print(f'{self.title}cookie:{cookie}')
+        if cookie:
+            headers['cookie'] = cookie
         limit = rule.get('limit',6)
         encoding = rule.get('编码', 'utf-8')
         self.limit = min(limit,30)
@@ -81,6 +92,8 @@ class CMS:
         lower_keys = list(map(lambda x:x.lower(),keys))
         if not 'user-agent' in lower_keys:
             headers['User-Agent'] = UA
+        if not 'referer' in lower_keys:
+            headers['Referer'] = host
         self.headers = headers
         self.host = host
         self.homeUrl = urljoin(host,homeUrl) if host and homeUrl else homeUrl
@@ -180,6 +193,8 @@ class CMS:
         res = self.db.session.query(self.RuleClass).filter(self.RuleClass.name == name).first()
         # _logger.info('xxxxxx')
         if res:
+            if not all([res.class_name,res.class_url]):
+                return []
             cls = res.class_name.split('&')
             cls2 = res.class_url.split('&')
             classes = [{'type_name':cls[i],'type_id':cls2[i]} for i in range(len(cls))]
@@ -189,6 +204,37 @@ class CMS:
         else:
             return []
 
+    def getCookie(self):
+        name = self.getName()
+        if not self.db:
+            msg = f'{name}未提供数据库连接'
+            print(msg)
+            return False
+        res = self.db.session.query(self.RuleClass).filter(self.RuleClass.name == name).first()
+        if res:
+            return res.cookie or None
+        else:
+            return None
+
+    def saveCookie(self,cookie):
+        name = self.getName()
+        if not self.db:
+            msg = f'{name}未提供数据库连接'
+            print(msg)
+            return False
+        res = self.db.session.query(self.RuleClass).filter(self.RuleClass.name == name).first()
+        if res:
+            res.cookie = cookie
+            self.db.session.add(res)
+        else:
+            res = self.RuleClass(name=name, cookie=cookie)
+            self.db.session.add(res)
+        try:
+            self.db.session.commit()
+            logger.info(f'{name}已保存cookie:{cookie}')
+        except Exception as e:
+            return f'保存cookie发生了错误:{e}'
+
     def saveClass(self, classes):
         if not self.db:
             msg = '未提供数据库连接'
@@ -305,18 +351,18 @@ class CMS:
                     html = r.text
                     if self.class_parse and not has_cache:
                         p = self.class_parse.split(';')
-                        print(p)
+                        # print(p)
                         jsp = jsoup(self.url)
                         pdfh = jsp.pdfh
                         pdfa = jsp.pdfa
                         pd = jsp.pd
                         items = pdfa(html,p[0])
-                        print(len(items))
-                        print(items)
+                        # print(len(items))
+                        # print(items)
                         for item in items:
                             title = pdfh(item, p[1])
                             url = pd(item, p[2])
-                            print(url)
+                            # print(url)
                             tag = url
                             if len(p) > 3 and p[3].strip():
                                 tag = self.regexp(p[3].strip(),url,0)
@@ -626,9 +672,22 @@ class CMS:
         pq = jsp.pq
         videos = []
         try:
-            r = requests.get(url, headers=self.headers)
+            r = requests.get(url, headers=self.headers,timeout=self.timeout)
             r.encoding = self.encoding
             html = r.text
+            # print(html)
+            if html.find('输入验证码') > -1:
+                cookie = verifyCode(url,self.headers,self.timeout,self.retry_count)
+                if not cookie:
+                    return {
+                        'list': videos
+                    }
+                self.saveCookie(cookie)
+                self.headers['cookie'] = cookie
+                r = requests.get(url, headers=self.headers, timeout=self.timeout)
+                r.encoding = self.encoding
+                html = r.text
+
             items = pdfa(html, p[0])
             # print(items)
             videos = []
@@ -709,10 +768,14 @@ if __name__ == '__main__':
     from utils import parser
     # js_path = f'js/玩偶姐姐.js'
     # js_path = f'js/555影视.js'
+    with open('../js/模板.js', encoding='utf-8') as f:
+        before = f.read()
     js_path = f'js/cokemv.js'
-    ctx, js_code = parser.runJs(js_path)
-    rule = ctx.eval('rule')
-    cms = CMS(rule)
+    ctx, js_code = parser.runJs(js_path,before=before)
+    ruleDict = ctx.rule.to_dict()
+    # ruleDict['id'] = rule  # 把路由请求的id装到字典里,后面播放嗅探才能用
+
+    cms = CMS(ruleDict)
     print(cms.title)
     print(cms.homeContent())
     # print(cms.categoryContent('5',1))
@@ -721,4 +784,4 @@ if __name__ == '__main__':
     # print(cms.detailContent(1,['https://cokemv.me/voddetail/40573.html']))
     # cms.categoryContent('dianying',1)
     # print(cms.detailContent(['67391']))
-    # print(cms.searchContent('斗罗大陆'))
+    print(cms.searchContent('斗罗大陆'))
\ No newline at end of file

commands.txt

+flask db init
+flask db migrate
+flask db upgrade
+
+
+废弃操作仅限 flask-migrate==2.7.0:
+# # 导入数据迁移核心类
+# from flask_migrate import Migrate
+# from flask_script import Manager
+# manager = Manager(app)
+# 初始化数据迁移
+# migrate = Migrate(app, db)
+# manager.add_command('sql', MigrateCommand)
+# python app.py sql migrate -m “init”
+# python app.py sql upgrade
\ No newline at end of file

config.py

@@ -24,4 +24,5 @@ LAZYPARSE_MODE = 1  # 播放解析模式(0 本地 1 局域网 2远程 仅在全
 WALL_PAPER_ENABLE = True  # 启用自定义壁纸
 WALL_PAPER = "https://picsum.photos/1280/720/?blur=10"  # 自定义壁纸,可注释
 SUP_PORT = 9001  # supervisord 服务端口
+RETRY_CNT = 3 # 验证码重试次数
 # {% if config.WALL_PAPER %}"wallpaper":"{{ config.WALL_PAPER }}",{% endif %}
\ No newline at end of file

js/555影视.js

 var rule = Object.assign(muban.mxpro,{
 title:'555影视',
 host:'https://www.5dy6.cc',
+headers:{//网站的请求头,完整支持所有的,常带ua和cookies
+    'User-Agent':'MOBILE_UA',
+    "Cookie": "searchneed=ok"
+},
 searchable:1,
 quickSearch:1,
 });
\ No newline at end of file

js/cokemv.js

@@ -2,4 +2,6 @@ var rule = Object.assign(muban.mxpro,{
 title:'cokemv',
 host:'https://cokemv.me',
 class_parse:'.navbar-items li:gt(1):lt(7);a&&Text;a&&href;/(\\d+).html',
+searchable:1,
+quickSearch:1,
 });
\ No newline at end of file

js/在线之家.js

+var rule = Object.assign(muban.首图2,{
+title:'在线之家',
+host:'https://zxzj.vip',
+});
\ No newline at end of file

js/夜空.js

@@ -3,7 +3,7 @@ title:'夜空',
 host:'https://www.yekong.cc',
 url:'/pianku-fyclass--------fypage---/',
 searchUrl:'/search-**----------fypage---/',
-searchable:0,
+searchable:1,
 quickSearch:0,
 class_parse:'.navbar-items li:gt(1):lt(7);a&&Text;a&&href;.*v/(.*?)/',
 });
\ No newline at end of file

js/影视工厂.js

+var rule = Object.assign(muban.首图,{
+title:'影视工厂',
+host:'https://www.ysgc.cc',
+searchable:1,
+quickSearch:1,
+});
\ No newline at end of file

js/模板.js

@@ -21,7 +21,7 @@ var muban = {
     quickSearch:0,//是否启用快速搜索,
     headers:{//网站的请求头,完整支持所有的,常带ua和cookies
         'User-Agent':'MOBILE_UA',
-        "Cookie": "searchneed=ok"
+        // "Cookie": "searchneed=ok"
     },
     class_parse:'.navbar-items li:gt(2):lt(8);a&&Text;a&&href;/(\\d+).html',
     play_parse:true,
@@ -32,6 +32,48 @@ var muban = {
     一级:'body a.module-poster-item.module-item;a&&title;.lazyload&&data-original;.module-item-note&&Text;a&&href',
     二级:{"title":"h1&&Text;.module-info-tag&&Text","img":".lazyload&&data-original","desc":".module-info-item:eq(1)&&Text;.module-info-item:eq(2)&&Text;.module-info-item:eq(3)&&Text","content":".module-info-introduction&&Text","tabs":".module-tab-item","lists":".module-play-list:eq(#id) a"},
     搜索:'body .module-item;.module-card-item-title&&Text;.lazyload&&data-original;.module-item-note&&Text;a&&href;.module-info-item-content&&Text',
+},
+首图:{
+    title:'',
+    host:'',
+    url:'/vodshow/fyclass--------fypage---/',
+    searchUrl:'/vodsearch/**----------fypage---.html',
+    searchable:0,//是否启用全局搜索,
+    quickSearch:0,//是否启用快速搜索,
+    headers:{//网站的请求头,完整支持所有的,常带ua和cookies
+        'User-Agent':'MOBILE_UA',
+        // "Cookie": "searchneed=ok"
+    },
+    class_parse:'.myui-header__menu li.hidden-sm:gt(0):lt(5);a&&Text;a&&href;/(\\d+).html',
+    play_parse:true,
+    lazy:'',
+    limit:10,
+    推荐:'ul.myui-vodlist.clearfix;li;a&&title;a&&data-original;.pic-text&&Text;a&&href',
+    double:true, // 推荐内容是否双层定位
+    一级:'.myui-vodlist li;a&&title;a&&data-original;.pic-text&&Text;a&&href',
+    二级:{"title":".myui-content__detail .title&&Text;.myui-content__detail p:eq(-2)&&Text","img":".myui-content__thumb .lazyload&&data-original","desc":".myui-content__detail p:eq(0)&&Text;.myui-content__detail p:eq(1)&&Text;.myui-content__detail p:eq(2)&&Text","content":".content&&Text","tabs":".nav-tabs:eq(0) li","lists":".myui-content__list:eq(#id) li"},
+    搜索:'#searchList li;a&&title;.lazyload&&data-original;.text-muted&&Text;a&&href;.text-muted:eq(-1)&&Text',
+},
+首图2:{
+    title:'',
+    host:'',
+    url:'/list/fyclass-fypage.html',
+    searchUrl:'/vodsearch/**----------fypage---.html',
+    searchable:0,
+    quickSearch:0,
+    headers:{
+        'User-Agent':'MOBILE_UA',
+        // "Cookie": ""
+    },
+    class_parse:'.stui-header__menu li:gt(0):lt(7);a&&Text;a&&href;/(\\d+).html',
+    play_parse:true,
+    lazy:'',
+    limit:10,
+    推荐:'ul.stui-vodlist.clearfix;li;a&&title;.lazyload&&data-original;.pic-text&&Text;a&&href',
+    double:true, // 推荐内容是否双层定位
+    一级:'.stui-vodlist li;a&&title;a&&data-original;.pic-text&&Text;a&&href',
+    二级:{"title":".stui-content__detail .title&&Text;.stui-content__detail p:eq(-2)&&Text","img":".stui-content__thumb .lazyload&&data-original","desc":".stui-content__detail p:eq(0)&&Text;.stui-content__detail p:eq(1)&&Text;.stui-content__detail p:eq(2)&&Text","content":".detail&&Text","tabs":".stui-vodlist__head","lists":".stui-content__playlist:eq(#id) li"},
+    搜索:'#searchList li;a&&title;.lazyload&&data-original;.text-muted&&Text;a&&href;.text-muted:eq(-1)&&Text',
 }
 
 

js/看视界.js

@@ -2,7 +2,7 @@ var rule = Object.assign(muban.mxpro,{
 title:'看视界',
 host:'https://www.1080kan.cc',
 url:'/show/fyclass--------fypage---.html',
-searchUrl:'/search/**-------------.html',
+searchUrl:'/search/**----------fypage---.html',
 searchable:0,
 quickSearch:0,
 class_parse:'.navbar-items li:gt(1):lt(6);a&&Text;a&&href;.*/(.*?).html',

js/莫扎兔.js

@@ -2,5 +2,8 @@ var rule = Object.assign(muban.mxpro,{
 title:'莫扎兔',
 host:'https://www.mozhatu.com',
 url:'/index.php/vod/show/id/fyclass/page/fypage.html',
+searchUrl:'/index.php/vod/search/page/fypage/wd/**.html',
 class_parse:'.navbar-items li:gt(2):lt(8);a&&Text;a&&href;.*/(.*?).html',
+searchable:1,
+quickSearch:1,
 });
\ No newline at end of file

models/rule_classes.py

@@ -15,10 +15,11 @@ def init(db):
         name = db.Column(db.String(20),unique=True)
         class_name = db.Column(db.String(255))
         class_url = db.Column(db.String(255))
+        cookie = db.Column(db.String(255))
 
         def __repr__(self):
-            return "<RuleClass(name='%s', class_name='%s', class_url='%s')>" % (
-                self.name, self.class_name, self.class_url)
+            return "<RuleClass(name='%s', class_name='%s', class_url='%s',cookie='%s')>" % (
+                self.name, self.class_name, self.class_url,self.cookie)
 
     # db.create_all()
     db.create_all()

py/测试过验证.py

+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+# File  : 测试过验证.py
+# Author: DaShenHan&道长-----先苦后甜，任凭晚风拂柳颜------
+# Date  : 2022/8/30
+
+import requests
+import ddddocr
+from time import sleep,time
+from urllib.parse import urljoin,quote,unquote
+import requests.utils
+
+url = 'https://cokemv.me/vodsearch/斗罗大陆----------1---.html'
+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'
+
+headers = {'user-agent':PC_UA}
+
+def getHome(url):
+    # http://www.baidu.com:9000/323
+    urls = url.split('//')
+    homeUrl = urls[0] + '//' + urls[1].split('/')[0]
+    return homeUrl
+
+def verifyCode(url,total_cnt=3):
+    headers['Referer'] = getHome(url)
+    cnt = 0
+    ocr = ddddocr.DdddOcr()
+    while cnt < total_cnt:
+        s = requests.session()
+        try:
+            img = s.get(url="https://cokemv.me/index.php/verify/index.html?t="+str(time()), headers=headers,timeout=5).content
+            code = ocr.classification(img)
+            print('验证结果:',code)
+            res = s.post(
+                url=f"https://cokemv.me/index.php/ajax/verify_check?type=search&verify={code}",
+                headers=headers
+            ).json()
+            if res["msg"] == "ok":
+                cookies_dict = requests.utils.dict_from_cookiejar(s.cookies)
+                cookie_str = ';'.join([f'{k}={cookies_dict[k]}' for k in cookies_dict])
+                # return cookies_dict
+                return cookie_str
+        except:
+            pass
+        cnt += 1
+        sleep(1)
+    return ''
+
+r = requests.get(url,headers=headers)
+html = r.text
+print(html)
+if html.find('输入验证码') > -1:
+    s = verifyCode(url)
+    print(s)
\ No newline at end of file

readme.md

@@ -11,6 +11,7 @@
 - [X] 8.增加外网免嗅(自定义config.py里面改)
 - [X] 9.增加错误处理和首页单个详情获取
 - [X] 10.增加本地直播地址自定义
+- [X] 11.增加数据库迁移,[新版教程](https://www.cjavapy.com/article/1977/)  [旧版教程](https://www.cnblogs.com/LoveMoney-MrLi/articles/15765985.html)
 ###### 2022/08/29
 - [X] 1.更换js引擎,速度更快性能更好
 - [X] 2.新版js支持与python互动,后期可能支持js免嗅(lazy:'js:xxx')

requirements.txt

 js2py
 pyquery
 flask
-requests
+flask_migrate
 flask-sqlalchemy
+requests
 netifaces
 gevent ; python_version < '3.9'
 supervisor ; sys_platform != 'win32' and python_version < '3.9'
 func_timeout
-easydict
+easydict
\ No newline at end of file
+ddddocr
\ No newline at end of file

utils/encode.py

@@ -6,8 +6,11 @@
 
 import base64
 import requests
+import requests.utils
+from time import sleep
 import os
 from utils.web import UC_UA,PC_UA
+import ddddocr
 
 def getPreJs():
     base_path = os.path.dirname(os.path.abspath(os.path.dirname(__file__)))  # 上级目
@@ -27,6 +30,41 @@ def getCryptoJS():
         code = f.read()
     return code
 
+def getHome(url):
+    # http://www.baidu.com:9000/323
+    urls = url.split('//')
+    homeUrl = urls[0] + '//' + urls[1].split('/')[0]
+    return homeUrl
+
+def verifyCode(url,headers,timeout=5,total_cnt=3):
+    lower_keys = list(map(lambda x: x.lower(), headers.keys()))
+    host = getHome(url)
+    if not 'referer' in lower_keys:
+        headers['Referer'] = host
+    print(f'开始自动过验证,请求头:{headers}')
+    cnt = 0
+    ocr = ddddocr.DdddOcr()
+    while cnt < total_cnt:
+        s = requests.session()
+        try:
+            img = s.get(url=f"{host}/index.php/verify/index.html", headers=headers,timeout=timeout).content
+            code = ocr.classification(img)
+            print(f'第{cnt+1}次验证码识别结果:{code}')
+            res = s.post(
+                url=f"{host}/index.php/ajax/verify_check?type=search&verify={code}",
+                headers=headers).json()
+            if res["msg"] == "ok":
+                cookies_dict = requests.utils.dict_from_cookiejar(s.cookies)
+                cookie_str = ';'.join([f'{k}={cookies_dict[k]}' for k in cookies_dict])
+                # return cookies_dict
+                return cookie_str
+        except:
+            print(f'第{cnt+1}次验证码提交失败')
+            pass
+        cnt += 1
+        sleep(1)
+    return ''
+
 def base64Encode(text):
     return base64.b64encode(text.encode("utf8")).decode("utf-8") #base64编码
 

utils/parser.py

@@ -51,10 +51,12 @@ def runJs(jsPath, before='', after='', ctx=None):
                 js_code = fp.read()
     else:
         js_path = os.path.join(base_path, jsPath)
+        # print(js_path)
         with open(js_path, 'r', encoding='UTF-8') as fp:
             js_code = fp.read()
     # print(js_code)
     jscode_to_run = js_code
+    # print(jscode_to_run)
     if before:
         jscode_to_run = before + jscode_to_run
     if after: