cms.py 29.4 KB
Newer Older
H
hjdhnx 已提交
1 2 3 4 5
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
# File  : cms.py
# Author: DaShenHan&道长-----先苦后甜,任凭晚风拂柳颜------
# Date  : 2022/8/25
H
hjdhnx 已提交
6

H
hjdhnx 已提交
7
import requests
8
import re
9
import math
H
hjdhnx 已提交
10
from utils.web import *
H
hjdhnx 已提交
11
from models import *
H
hjdhnx 已提交
12
from utils.config import config
H
hjdhnx 已提交
13
from utils.log import logger
14 15
from utils.encode import base64Encode,baseDecode,fetch,post,request,getCryptoJS,getPreJs,buildUrl,getHome
from utils.encode import verifyCode
H
hjdhnx 已提交
16
from utils.safePython import safePython
H
hjdhnx 已提交
17
from utils.parser import runPy,runJScode
H
hjdhnx 已提交
18
from utils.htmlParser import jsoup
H
hjdhnx 已提交
19
from urllib.parse import urljoin
20
from concurrent.futures import ThreadPoolExecutor  # 引入线程池
H
hjdhnx 已提交
21
from flask import url_for,redirect
22
from easydict import EasyDict as edict
H
hjdhnx 已提交
23

H
hjdhnx 已提交
24 25
py_ctx = {
'requests':requests,'print':print,'base64Encode':base64Encode,'baseDecode':baseDecode,
H
hjdhnx 已提交
26
'log':logger.info,'fetch':fetch,'post':post,'request':request,'getCryptoJS':getCryptoJS,
27
'buildUrl':buildUrl,'getHome':getHome
H
hjdhnx 已提交
28
}
29
# print(getCryptoJS())
H
hjdhnx 已提交
30

H
hjdhnx 已提交
31
class CMS:
H
hjdhnx 已提交
32
    def __init__(self, rule, db=None, RuleClass=None, PlayParse=None,new_conf=None):
H
hjdhnx 已提交
33 34
        if new_conf is None:
            new_conf = {}
H
hjdhnx 已提交
35
        self.title = rule.get('title', '')
H
hjdhnx 已提交
36
        self.id = rule.get('id', self.title)
H
hjdhnx 已提交
37
        self.lazy = rule.get('lazy', False)
38
        self.play_disable = new_conf.get('PLAY_DISABLE',False)
39
        self.retry_count = new_conf.get('RETRY_CNT',3)
40
        self.lazy_mode = new_conf.get('LAZYPARSE_MODE')
41
        self.ocr_api = new_conf.get('OCR_API')
42 43 44 45
        try:
            self.vod = redirect(url_for('vod')).headers['Location']
        except:
            self.vod = '/vod'
H
hjdhnx 已提交
46
        # if not self.play_disable and self.lazy:
47 48
        if not self.play_disable:
            self.play_parse = rule.get('play_parse', False)
49 50 51 52
            try:
                play_url = getHost(self.lazy_mode)
            except:
                play_url = getHost(1,5705)
53
            # play_url = new_conf.get('PLAY_URL',getHost(2))
54 55 56
            if not play_url.startswith('http'):
                play_url = 'http://'+play_url
            if self.play_parse:
H
hjdhnx 已提交
57
                # self.play_url = play_url + self.vod + '?play_url='
H
hjdhnx 已提交
58
                self.play_url = f'{play_url}{self.vod}?rule={self.id}&play_url='
H
hjdhnx 已提交
59
                # logger.info(f'cms重定向链接:{self.play_url}')
60 61
            else:
                self.play_url = ''
H
hjdhnx 已提交
62
        else:
63
            self.play_parse = False
H
hjdhnx 已提交
64
            self.play_url = ''
H
hjdhnx 已提交
65
        # logger.info('播放免嗅地址: '+self.play_url)
66

H
hjdhnx 已提交
67 68
        self.db = db
        self.RuleClass = RuleClass
H
hjdhnx 已提交
69
        self.PlayParse = PlayParse
70
        host = rule.get('host','').rstrip('/')
71
        timeout = rule.get('timeout',5000)
H
hjdhnx 已提交
72
        homeUrl = rule.get('homeUrl','/')
73 74 75 76
        url = rule.get('url','')
        detailUrl = rule.get('detailUrl','')
        searchUrl = rule.get('searchUrl','')
        headers = rule.get('headers',{})
77 78 79 80
        cookie = self.getCookie()
        # print(f'{self.title}cookie:{cookie}')
        if cookie:
            headers['cookie'] = cookie
81
        limit = rule.get('limit',6)
H
hjdhnx 已提交
82
        encoding = rule.get('编码', 'utf-8')
H
hjdhnx 已提交
83
        self.limit = min(limit,30)
84 85 86 87 88 89 90 91
        keys = headers.keys()
        for k in headers.keys():
            if str(k).lower() == 'user-agent':
                v = headers[k]
                if v == 'MOBILE_UA':
                    headers[k] = MOBILE_UA
                elif v == 'PC_UA':
                    headers[k] = PC_UA
H
hjdhnx 已提交
92 93
                elif v == 'UC_UA':
                    headers[k] = UC_UA
94 95 96
        lower_keys = list(map(lambda x:x.lower(),keys))
        if not 'user-agent' in lower_keys:
            headers['User-Agent'] = UA
97 98
        if not 'referer' in lower_keys:
            headers['Referer'] = host
99 100 101 102 103 104 105
        self.headers = headers
        self.host = host
        self.homeUrl = urljoin(host,homeUrl) if host and homeUrl else homeUrl
        if url.find('[') >-1 and url.find(']') > -1:
            u1 = url.split('[')[0]
            u2 = url.split('[')[1].split(']')[0]
            self.url = urljoin(host,u1)+'['+urljoin(host,u2)+']' if host and url else url
H
hjdhnx 已提交
106
        else:
107 108 109 110
            self.url = urljoin(host, url) if host and url else url

        self.detailUrl = urljoin(host,detailUrl) if host and detailUrl else detailUrl
        self.searchUrl = urljoin(host,searchUrl) if host and searchUrl else searchUrl
H
hjdhnx 已提交
111 112
        self.class_name = rule.get('class_name','')
        self.class_url = rule.get('class_url','')
113
        self.class_parse = rule.get('class_parse','')
H
hjdhnx 已提交
114 115 116
        self.filter_name = rule.get('filter_name', '')
        self.filter_url = rule.get('filter_url', '')
        self.filter_parse = rule.get('filter_parse', '')
117
        self.double = rule.get('double',False)
H
hjdhnx 已提交
118 119 120
        self.一级 = rule.get('一级','')
        self.二级 = rule.get('二级','')
        self.搜索 = rule.get('搜索','')
121
        self.推荐 = rule.get('推荐','')
H
hjdhnx 已提交
122
        self.encoding = encoding
123
        self.timeout = round(int(timeout)/1000,2)
H
hjdhnx 已提交
124 125
        self.filter = rule.get('filter',[])
        self.extend = rule.get('extend',[])
126
        self.d = self.getObject()
H
hjdhnx 已提交
127 128 129 130

    def getName(self):
        return self.title

131 132 133 134 135 136 137 138 139 140 141 142
    def getObject(self):
        o = edict({
            'jsp':jsoup(self.url),
            'getParse':self.getParse,
            'saveParse':self.saveParse,
            'headers':self.headers,
            'encoding':self.encoding,
            'name':self.title,
            'timeout':self.timeout,
        })
        return o

143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186
    def regexp(self,prule,text,pos=None):
        ret = re.search(prule,text).groups()
        if pos != None and isinstance(pos,int):
            return ret[pos]
        else:
            return ret

    def test(self,text,string):
        searchObj = re.search(rf'{text}', string, re.M | re.I)
        # print(searchObj)
        # global vflag
        if searchObj:
            # vflag = searchObj.group()
            pass
        return searchObj

    def blank(self):
        result = {
            'list': []
        }
        return result

    def blank_vod(self):
        return {
            "vod_id": "",
            "vod_name": "",
            "vod_pic": "",
            "type_name": "",
            "vod_year": "",
            "vod_area": "",
            "vod_remarks": "",
            "vod_actor": "",
            "vod_director": "",
            "vod_content": ""
        }

    def jsoup(self):
        jsp = jsoup(self.url)
        pdfh = jsp.pdfh
        pdfa = jsp.pdfa
        pd = jsp.pd
        pq = jsp.pq
        return pdfh,pdfa,pd,pq

H
hjdhnx 已提交
187 188 189 190 191 192 193 194 195 196 197
    def getClasses(self):
        if not self.db:
            msg = '未提供数据库连接'
            print(msg)
            return []
        name = self.getName()
        # self.db.metadata.clear()
        # RuleClass = rule_classes.init(self.db)
        res = self.db.session.query(self.RuleClass).filter(self.RuleClass.name == name).first()
        # _logger.info('xxxxxx')
        if res:
198 199
            if not all([res.class_name,res.class_url]):
                return []
H
hjdhnx 已提交
200 201 202 203
            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))]
            # _logger.info(classes)
H
hjdhnx 已提交
204
            logger.info(f"{self.getName()}使用缓存分类:{classes}")
H
hjdhnx 已提交
205 206 207 208
            return classes
        else:
            return []

209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239
    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}'

H
hjdhnx 已提交
240 241 242 243 244 245 246 247 248 249 250 251
    def saveClass(self, classes):
        if not self.db:
            msg = '未提供数据库连接'
            print(msg)
            return msg
        name = self.getName()
        class_name = '&'.join([cl['type_name'] for cl in classes])
        class_url = '&'.join([cl['type_id'] for cl in classes])
        # data = RuleClass.query.filter(RuleClass.name == '555影视').all()
        # self.db.metadata.clear()
        # RuleClass = rule_classes.init(self.db)
        res = self.db.session.query(self.RuleClass).filter(self.RuleClass.name == name).first()
H
hjdhnx 已提交
252
        # print(res)
H
hjdhnx 已提交
253 254 255 256
        if res:
            res.class_name = class_name
            res.class_url = class_url
            self.db.session.add(res)
H
hjdhnx 已提交
257
            msg = f'{self.getName()}修改成功:{res.id}'
H
hjdhnx 已提交
258 259 260 261
        else:
            res = self.RuleClass(name=name, class_name=class_name, class_url=class_url)
            self.db.session.add(res)
            res = self.db.session.query(self.RuleClass).filter(self.RuleClass.name == name).first()
H
hjdhnx 已提交
262
            msg = f'{self.getName()}新增成功:{res.id}'
H
hjdhnx 已提交
263 264 265

        try:
            self.db.session.commit()
H
hjdhnx 已提交
266
            logger.info(msg)
H
hjdhnx 已提交
267 268 269
        except Exception as e:
            return f'发生了错误:{e}'

H
hjdhnx 已提交
270 271 272 273 274 275 276 277 278 279 280 281 282 283 284
    def getParse(self,play_url):
        if not self.db:
            msg = '未提供数据库连接'
            print(msg)
            return ''
        name = self.getName()
        # self.db.metadata.clear()
        # RuleClass = rule_classes.init(self.db)
        res = self.db.session.query(self.PlayParse).filter(self.PlayParse.play_url == play_url).first()
        # _logger.info('xxxxxx')
        if res:
            real_url = res.real_url
            logger.info(f"{name}使用缓存播放地址:{real_url}")
            return real_url
        else:
H
hjdhnx 已提交
285
            return ''
H
hjdhnx 已提交
286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313

    def saveParse(self, play_url,real_url):
        if not self.db:
            msg = '未提供数据库连接'
            print(msg)
            return msg
        name = self.getName()
        # data = RuleClass.query.filter(RuleClass.name == '555影视').all()
        # self.db.metadata.clear()
        # RuleClass = rule_classes.init(self.db)
        res = self.db.session.query(self.PlayParse).filter(self.PlayParse.play_url == play_url).first()
        # print(res)
        if res:
            res.real_url = real_url
            self.db.session.add(res)
            msg = f'{name}服务端免嗅修改成功:{res.id}'
        else:
            res = self.PlayParse(play_url=play_url, real_url=real_url)
            self.db.session.add(res)
            res = self.db.session.query(self.PlayParse).filter(self.PlayParse.play_url == play_url).first()
            msg = f'{name}服务端免嗅新增成功:{res.id}'

        try:
            self.db.session.commit()
            logger.info(msg)
        except Exception as e:
            return f'{name}发生了错误:{e}'

H
hjdhnx 已提交
314

315
    def homeContent(self,fypage=1):
H
hjdhnx 已提交
316 317
        # yanaifei
        # https://yanetflix.com/vodtype/dianying.html
H
hjdhnx 已提交
318
        t1 = time()
H
hjdhnx 已提交
319 320
        result = {}
        classes = []
321
        video_result = self.blank()
322 323 324 325 326 327 328 329 330 331 332

        if self.class_url and self.class_name:
            class_names = self.class_name.split('&')
            class_urls = self.class_url.split('&')
            cnt = min(len(class_urls), len(class_names))
            for i in range(cnt):
                classes.append({
                    'type_name': class_names[i],
                    'type_id': class_urls[i]
                })
        # print(self.url)
H
hjdhnx 已提交
333
        has_cache = False
334
        if self.homeUrl.startswith('http'):
335 336 337
            # print(self.homeUrl)
            # print(self.class_parse)
            try:
H
hjdhnx 已提交
338
                if self.class_parse:
H
hjdhnx 已提交
339
                    t2 = time()
H
hjdhnx 已提交
340
                    cache_classes = self.getClasses()
H
hjdhnx 已提交
341
                    logger.info(f'{self.getName()}读取缓存耗时:{get_interval(t2)}毫秒')
H
hjdhnx 已提交
342 343
                    if len(cache_classes) > 0:
                        classes = cache_classes
H
hjdhnx 已提交
344
                        # print(cache_classes)
H
hjdhnx 已提交
345
                        has_cache = True
H
hjdhnx 已提交
346 347 348 349 350 351 352 353
                # logger.info(f'是否有缓存分类:{has_cache}')
                if has_cache and not self.推荐:
                    pass
                else:
                    new_classes = []
                    r = requests.get(self.homeUrl, headers=self.headers, timeout=self.timeout)
                    r.encoding = self.encoding
                    html = r.text
H
hjdhnx 已提交
354
                    # print(html)
H
hjdhnx 已提交
355 356
                    if self.class_parse and not has_cache:
                        p = self.class_parse.split(';')
357
                        # print(p)
H
hjdhnx 已提交
358 359 360 361 362
                        jsp = jsoup(self.url)
                        pdfh = jsp.pdfh
                        pdfa = jsp.pdfa
                        pd = jsp.pd
                        items = pdfa(html,p[0])
363 364
                        # print(len(items))
                        # print(items)
H
hjdhnx 已提交
365 366 367
                        for item in items:
                            title = pdfh(item, p[1])
                            url = pd(item, p[2])
368
                            # print(url)
H
hjdhnx 已提交
369 370 371 372 373 374 375 376 377 378 379
                            tag = url
                            if len(p) > 3 and p[3].strip():
                                tag = self.regexp(p[3].strip(),url,0)
                            new_classes.append({
                                'type_name': title,
                                'type_id': tag
                            })
                        if len(new_classes) > 0:
                            classes.extend(new_classes)
                            self.saveClass(classes)
                    video_result = self.homeVideoContent(html,fypage)
380
            except Exception as e:
H
hjdhnx 已提交
381
                logger.info(f'{self.getName()}主页发生错误:{e}')
382

H
hjdhnx 已提交
383 384 385
        result['class'] = classes
        if self.filter:
            result['filters'] = config['filter']
386
        result.update(video_result)
H
hjdhnx 已提交
387
        logger.info(f'{self.getName()}获取首页总耗时(包含读取缓存):{get_interval(t1)}毫秒')
H
hjdhnx 已提交
388 389
        return result

390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410
    def homeVideoContent(self,html,fypage=1):
        if not self.推荐:
            return self.blank()

        p = self.推荐.split(';')  # 解析
        if not self.double and len(p) < 5:
            return self.blank()
        if self.double and len(p) < 6:
            return self.blank()
        result = {}
        videos = []
        jsp = jsoup(self.homeUrl)
        pdfh = jsp.pdfh
        pdfa = jsp.pdfa
        pd = jsp.pd
        try:
            if self.double:
                items = pdfa(html, p[0])
                for item in items:
                    items2 = pdfa(item,p[1])
                    for item2 in items2:
411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436
                        try:
                            title = pdfh(item2, p[2])
                            img = pd(item2, p[3])
                            desc = pdfh(item2, p[4])
                            link = pd(item2, p[5])
                            content = '' if len(p) < 7 else pdfh(item2, p[6])
                            videos.append({
                                "vod_id": link,
                                "vod_name": title,
                                "vod_pic": img,
                                "vod_remarks": desc,
                                "vod_content": content,
                                "type_id": 1,
                                "type_name": "首页推荐",
                            })
                        except:
                            pass
            else:
                items = pdfa(html, p[0])
                for item in items:
                    try:
                        title = pdfh(item, p[1])
                        img = pd(item, p[2])
                        desc = pdfh(item, p[3])
                        link = pd(item, p[4])
                        content = '' if len(p) < 6 else pdfh(item, p[5])
437 438 439 440 441 442 443 444 445
                        videos.append({
                            "vod_id": link,
                            "vod_name": title,
                            "vod_pic": img,
                            "vod_remarks": desc,
                            "vod_content": content,
                            "type_id": 1,
                            "type_name": "首页推荐",
                        })
446 447
                    except:
                        pass
448 449 450 451 452 453 454 455 456
            result['list'] = videos
            result['code'] = 1
            result['msg'] = '数据列表'
            result['page'] = fypage
            result['pagecount'] = math.ceil(len(videos)/self.limit)
            result['limit'] = self.limit
            result['total'] = len(videos)
            return result
        except Exception as e:
H
hjdhnx 已提交
457
            logger.info(f'首页内容获取失败:{e}')
458
            return self.blank()
H
hjdhnx 已提交
459 460 461 462 463 464 465 466

    def categoryContent(self, fyclass, fypage):
        """
        一级带分类的数据返回
        :param fyclass: 分类标识
        :param fypage: 页码
        :return: cms一级数据
        """
H
hjdhnx 已提交
467
        
H
hjdhnx 已提交
468 469 470 471 472 473 474 475 476
        result = {}
        # urlParams = ["", "", "", "", "", "", "", "", "", "", "", ""]
        # urlParams = [""] * 12
        # urlParams[0] = tid
        # urlParams[8] = str(pg)
        # for key in self.extend:
        #     urlParams[int(key)] = self.extend[key]
        # params = '-'.join(urlParams)
        # print(params)
H
hjdhnx 已提交
477 478
        # url = self.url + '/{0}.html'.format
        t1 = time()
H
hjdhnx 已提交
479 480
        pg = str(fypage)
        url = self.url.replace('fyclass',fyclass).replace('fypage',pg)
481 482
        if fypage == 1 and self.test('[\[\]]',url):
            url = url.split('[')[1].split(']')[0]
H
hjdhnx 已提交
483
        p = self.一级.split(';')  # 解析
484 485 486
        if len(p) < 5:
            return self.blank()

H
hjdhnx 已提交
487 488 489 490
        jsp = jsoup(self.url)
        pdfh = jsp.pdfh
        pdfa = jsp.pdfa
        pd = jsp.pd
H
hjdhnx 已提交
491 492 493
        # print(pdfh(r.text,'body a.module-poster-item.module-item:eq(1)&&Text'))
        # print(pdfh(r.text,'body a.module-poster-item.module-item:eq(0)'))
        # print(pdfh(r.text,'body a.module-poster-item.module-item:first'))
494

H
hjdhnx 已提交
495
        videos = []
496 497 498 499 500 501 502 503 504
        items = []
        try:
            r = requests.get(url, headers=self.headers, timeout=self.timeout)
            r.encoding = self.encoding
            print(r.url)
            html = r.text
            items = pdfa(html, p[0])
        except:
            pass
H
hjdhnx 已提交
505 506
        for item in items:
            # print(item)
507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522
            try:
                title = pdfh(item, p[1])
                img = pd(item, p[2])
                desc = pdfh(item, p[3])
                link = pd(item, p[4])
                content = '' if len(p) < 6 else pdfh(item, p[5])
                # sid = self.regStr(sid, "/video/(\\S+).html")
                videos.append({
                    "vod_id": link,
                    "vod_name": title,
                    "vod_pic": img,
                    "vod_remarks": desc,
                    "vod_content": content,
                })
            except:
                pass
H
hjdhnx 已提交
523
        result['list'] = videos
H
hjdhnx 已提交
524
        result['page'] = fypage
H
hjdhnx 已提交
525
        result['pagecount'] = 9999
526
        result['limit'] = 9999
H
hjdhnx 已提交
527
        result['total'] = 999999
H
hjdhnx 已提交
528
        logger.info(f'{self.getName()}获取分类{fyclass}{fypage}页耗时:{get_interval(t1)}毫秒,共计{round(len(str(result)) / 1000, 2)} kb')
H
hjdhnx 已提交
529
        
H
hjdhnx 已提交
530 531
        return result

532 533 534
    def detailOneVod(self,id):
        detailUrl = str(id)
        vod = {}
535 536
        if not detailUrl.startswith('http'):
            url = self.detailUrl.replace('fyid', detailUrl)
H
hjdhnx 已提交
537
        else:
538
            url = detailUrl
539
        # print(url)
H
hjdhnx 已提交
540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560
        try:
            p = self.二级  # 解析
            if p == '*':
                vod = self.blank_vod()
                vod['vod_play_from'] = '道长在线'
                vod['desc'] = self.play_url+detailUrl
                vod['vod_actor'] = '没有二级,只有一级链接直接嗅探播放'
                vod['content'] = detailUrl
                vod['vod_play_url'] = '嗅探播放$'+detailUrl
                return vod

            if not isinstance(p,dict):
                return vod

            jsp = jsoup(self.url)
            pdfh = jsp.pdfh
            pdfa = jsp.pdfa
            pd = jsp.pd
            pq = jsp.pq
            obj = {}
            vod_name = ''
561 562 563 564
            r = requests.get(url, headers=self.headers, timeout=self.timeout)
            r.encoding = self.encoding
            html = r.text
            # print(html)
H
hjdhnx 已提交
565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627
            if p.get('title'):
                p1 = p['title'].split(';')
                vod_name = pdfh(html,p1[0]).replace('\n',' ')
                title = '\n'.join([pdfh(html,i).replace('\n',' ') for i in p1])
                # print(title)
                obj['title'] = title
            if p.get('desc'):
                p1 = p['desc'].split(';')
                desc = '\n'.join([pdfh(html,i).replace('\n',' ') for i in p1])
                obj['desc'] = desc

            if p.get('content'):
                p1 = p['content'].split(';')
                content = '\n'.join([pdfh(html,i).replace('\n',' ') for i in p1])
                obj['content'] = content

            if p.get('img'):
                p1 = p['img'].split(';')
                img = '\n'.join([pdfh(html,i).replace('\n',' ') for i in p1])
                obj['img'] = img

            vod = {
                "vod_id": detailUrl,
                "vod_name": vod_name,
                "vod_pic": obj.get('img',''),
                "type_name": obj.get('title',''),
                "vod_year": "",
                "vod_area": "",
                "vod_remarks": obj.get('desc',''),
                "vod_actor": "",
                "vod_director": "",
                "vod_content": obj.get('content','')
            }

            vod_play_from = '$$$'
            playFrom = []
            if p.get('tabs'):
                vodHeader = pdfa(html,p['tabs'])
                # print(f'线路列表数:{len((vodHeader))}')
                # print(vodHeader)
                vodHeader = [pq(v).text() for v in vodHeader]
            else:
                vodHeader = ['道长在线']

            for v in vodHeader:
                playFrom.append(v)
            vod_play_from = vod_play_from.join(playFrom)

            vod_play_url = '$$$'
            vod_tab_list = []
            if p.get('lists'):
                for i in range(len(vodHeader)):
                   p1 = p['lists'].replace('#id',str(i))
                   vodList = pdfa(html,p1) # 1条线路的选集列表
                   # vodList = [pq(i).text()+'$'+pd(i,'a&&href') for i in vodList]  # 拼接成 名称$链接
                   vodList = [pq(i).text()+'$'+self.play_url+pd(i,'a&&href') for i in vodList]  # 拼接成 名称$链接
                   vlist = '#'.join(vodList) # 拼多个选集
                   vod_tab_list.append(vlist)
                vod_play_url = vod_play_url.join(vod_tab_list)
            # print(vod_play_url)
            vod['vod_play_from'] = vod_play_from
            vod['vod_play_url'] = vod_play_url
        except Exception as e:
628
            logger.info(f'{self.getName()}获取单个详情页{detailUrl}出错{e}')
H
hjdhnx 已提交
629
        # print(vod)
630 631 632 633 634 635 636 637
        return vod

    def detailContent(self, fypage, array):
        """
        cms二级数据
        :param array:
        :return:
        """
H
hjdhnx 已提交
638
        t1 = time()
639 640 641
        array = array[(fypage-1)*self.limit:min(self.limit*fypage,len(array))]
        thread_pool = ThreadPoolExecutor(min(self.limit,len(array)))  # 定义线程池来启动多线程执行此任务
        obj_list = []
H
hjdhnx 已提交
642 643 644 645 646 647 648 649 650 651 652 653 654 655 656
        try:
            for vod_url in array:
                obj = thread_pool.submit(self.detailOneVod, vod_url)
                obj_list.append(obj)
            thread_pool.shutdown(wait=True)  # 等待所有子线程并行完毕
            vod_list = [obj.result() for obj in obj_list]
            result = {
                'list': vod_list
            }
            logger.info(f'{self.getName()}获取详情页耗时:{get_interval(t1)}毫秒,共计{round(len(str(result)) / 1000, 2)} kb')
        except Exception as e:
            result = {
                'list': []
            }
            logger.info(f'{self.getName()}获取详情页耗时:{get_interval(t1)}毫秒,发生错误:{e}')
H
hjdhnx 已提交
657
        # print(result)
H
hjdhnx 已提交
658 659
        return result

H
hjdhnx 已提交
660
    def searchContent(self, key, fypage=1):
H
hjdhnx 已提交
661
        pg = str(fypage)
662 663
        if not self.searchUrl:
            return self.blank()
H
hjdhnx 已提交
664
        url = self.searchUrl.replace('**', key).replace('fypage',pg)
H
hjdhnx 已提交
665
        logger.info(f'{self.getName()}搜索链接:{url}')
666 667 668 669 670
        if not self.搜索:
            return self.blank()
        p = self.一级.split(';') if self.搜索 == '*' and self.一级 else self.搜索.split(';')  # 解析
        if len(p) < 5:
            return self.blank()
H
hjdhnx 已提交
671 672 673 674 675 676
        jsp = jsoup(self.url)
        pdfh = jsp.pdfh
        pdfa = jsp.pdfa
        pd = jsp.pd
        pq = jsp.pq
        videos = []
H
hjdhnx 已提交
677
        try:
678
            r = requests.get(url, headers=self.headers,timeout=self.timeout)
H
hjdhnx 已提交
679 680
            r.encoding = self.encoding
            html = r.text
681 682
            # print(html)
            if html.find('输入验证码') > -1:
683
                cookie = verifyCode(url,self.headers,self.timeout,self.retry_count,self.ocr_api)
684
                # cookie = ''
685 686 687 688 689 690 691 692 693 694
                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

H
hjdhnx 已提交
695
            items = pdfa(html, p[0])
696
            # print(items)
H
hjdhnx 已提交
697 698 699
            videos = []
            for item in items:
                # print(item)
700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716
                try:
                    title = pdfh(item, p[1])
                    img = pd(item, p[2])
                    desc = pdfh(item, p[3])
                    link = pd(item, p[4])
                    content = '' if len(p) < 6 else pdfh(item, p[5])
                    # sid = self.regStr(sid, "/video/(\\S+).html")
                    videos.append({
                        "vod_id": link,
                        "vod_name": title,
                        "vod_pic": img,
                        "vod_remarks": desc,
                        "vod_content": content,
                    })
                except:
                    pass
            # print(videos)
H
hjdhnx 已提交
717 718
        except Exception as e:
            logger.info(f'搜索{self.getName()}发生错误:{e}')
H
hjdhnx 已提交
719 720 721 722 723
        result = {
            'list': videos
        }
        return result

H
hjdhnx 已提交
724
    def playContent(self, play_url,jxs=None):
H
hjdhnx 已提交
725
        # logger.info('播放免嗅地址: ' + self.play_url)
H
hjdhnx 已提交
726 727
        if not jxs:
            jxs = []
H
hjdhnx 已提交
728 729
        if self.lazy:
            print(f'{play_url}->开始执行免嗅代码->{self.lazy}')
H
hjdhnx 已提交
730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765
            t1 = time()
            try:
                if not str(self.lazy).startswith('js:'):
                    pycode = runPy(self.lazy)
                    if pycode:
                        # print(pycode)
                        pos = pycode.find('def lazyParse')
                        if pos < 0:
                            return play_url
                        pyenv = safePython(self.lazy,pycode[pos:])
                        lazy_url = pyenv.action_task_exec('lazyParse',[play_url,self.d])
                        logger.info(f'py免嗅耗时:{get_interval(t1)}毫秒,播放地址:{lazy_url}')
                        if isinstance(lazy_url,str) and lazy_url.startswith('http'):
                            play_url = lazy_url
                else:
                    jscode = str(self.lazy).split('js:')[1]
                    # jscode = f'var input={play_url};{jscode}'
                    # print(jscode)
                    py_ctx.update({
                        'input': play_url,
                        'd': self.d,
                        'jxs':jxs,
                        'pdfh': self.d.jsp.pdfh,
                        'pdfa': self.d.jsp.pdfa, 'pd': self.d.jsp.pd,
                    })
                    ctx = py_ctx
                    # print(ctx)
                    t1 = time()
                    jscode = getPreJs() + jscode
                    # print(jscode)
                    loader,_ = runJScode(jscode,ctx=ctx)
                    # print(loader.toString())
                    play_url = loader.eval('input')
                    logger.info(f'js免嗅耗时:{get_interval(t1)}毫秒,播放地址:{play_url}')
            except Exception as e:
                logger.info(f'免嗅耗时:{get_interval(t1)}毫秒,并发生错误:{e}')
H
hjdhnx 已提交
766 767 768 769 770
            return play_url
        else:
            logger.info(f'播放重定向到:{play_url}')
            return play_url

H
hjdhnx 已提交
771 772
if __name__ == '__main__':
    from utils import parser
H
hjdhnx 已提交
773
    # js_path = f'js/玩偶姐姐.js'
H
hjdhnx 已提交
774
    # js_path = f'js/555影视.js'
775 776
    with open('../js/模板.js', encoding='utf-8') as f:
        before = f.read()
H
hjdhnx 已提交
777
    js_path = f'js/cokemv.js'
778 779 780 781 782
    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)
H
hjdhnx 已提交
783
    print(cms.title)
H
hjdhnx 已提交
784
    print(cms.homeContent())
H
hjdhnx 已提交
785
    # print(cms.categoryContent('5',1))
786
    # print(cms.categoryContent('latest',1))
H
hjdhnx 已提交
787
    # print(cms.detailContent(['https://www.2345ka.com/v/45499.html']))
H
hjdhnx 已提交
788
    # print(cms.detailContent(1,['https://cokemv.me/voddetail/40573.html']))
H
hjdhnx 已提交
789
    # cms.categoryContent('dianying',1)
H
hjdhnx 已提交
790
    # print(cms.detailContent(['67391']))
791
    print(cms.searchContent('斗罗大陆'))