cms.py 30.4 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 playerConfig
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
17
from utils.parser import runPy,runJScode,JsObjectWrapper
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')
H
hjdhnx 已提交
42
        self.cate_exclude = new_conf.get('CATE_EXCLUDE','')
43 44 45 46
        try:
            self.vod = redirect(url_for('vod')).headers['Location']
        except:
            self.vod = '/vod'
H
hjdhnx 已提交
47
        # if not self.play_disable and self.lazy:
48 49
        if not self.play_disable:
            self.play_parse = rule.get('play_parse', False)
50 51 52 53
            try:
                play_url = getHost(self.lazy_mode)
            except:
                play_url = getHost(1,5705)
54
            # play_url = new_conf.get('PLAY_URL',getHost(2))
55 56 57
            if not play_url.startswith('http'):
                play_url = 'http://'+play_url
            if self.play_parse:
H
hjdhnx 已提交
58
                # self.play_url = play_url + self.vod + '?play_url='
H
hjdhnx 已提交
59
                self.play_url = f'{play_url}{self.vod}?rule={self.id}&play_url='
H
hjdhnx 已提交
60
                # logger.info(f'cms重定向链接:{self.play_url}')
61 62
            else:
                self.play_url = ''
H
hjdhnx 已提交
63
        else:
64
            self.play_parse = False
H
hjdhnx 已提交
65
            self.play_url = ''
H
hjdhnx 已提交
66
        # logger.info('播放免嗅地址: '+self.play_url)
67

H
hjdhnx 已提交
68 69
        self.db = db
        self.RuleClass = RuleClass
H
hjdhnx 已提交
70
        self.PlayParse = PlayParse
71
        host = rule.get('host','').rstrip('/')
72
        timeout = rule.get('timeout',5000)
H
hjdhnx 已提交
73
        homeUrl = rule.get('homeUrl','/')
74 75 76
        url = rule.get('url','')
        detailUrl = rule.get('detailUrl','')
        searchUrl = rule.get('searchUrl','')
H
hjdhnx 已提交
77 78 79 80
        default_headers = getHeaders(host)
        self_headers = rule.get('headers',{})
        default_headers.update(self_headers)
        headers = default_headers
81 82 83 84
        cookie = self.getCookie()
        # print(f'{self.title}cookie:{cookie}')
        if cookie:
            headers['cookie'] = cookie
85
        limit = rule.get('limit',6)
H
hjdhnx 已提交
86
        encoding = rule.get('编码', 'utf-8')
H
hjdhnx 已提交
87
        self.limit = min(limit,30)
88 89 90 91 92 93 94 95
        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
96 97
                elif v == 'UC_UA':
                    headers[k] = UC_UA
98 99 100
        lower_keys = list(map(lambda x:x.lower(),keys))
        if not 'user-agent' in lower_keys:
            headers['User-Agent'] = UA
101 102
        if not 'referer' in lower_keys:
            headers['Referer'] = host
H
hjdhnx 已提交
103
        # print(headers)
104 105 106 107 108 109 110
        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
111
        else:
112 113 114 115
            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
116 117
        self.class_name = rule.get('class_name','')
        self.class_url = rule.get('class_url','')
118
        self.class_parse = rule.get('class_parse','')
H
hjdhnx 已提交
119 120 121
        self.filter_name = rule.get('filter_name', '')
        self.filter_url = rule.get('filter_url', '')
        self.filter_parse = rule.get('filter_parse', '')
122
        self.double = rule.get('double',False)
H
hjdhnx 已提交
123 124 125
        self.一级 = rule.get('一级','')
        self.二级 = rule.get('二级','')
        self.搜索 = rule.get('搜索','')
126
        self.推荐 = rule.get('推荐','')
H
hjdhnx 已提交
127
        self.encoding = encoding
128
        self.timeout = round(int(timeout)/1000,2)
H
hjdhnx 已提交
129 130
        self.filter = rule.get('filter',[])
        self.extend = rule.get('extend',[])
131
        self.d = self.getObject()
H
hjdhnx 已提交
132 133 134 135

    def getName(self):
        return self.title

136 137 138 139 140 141 142 143 144 145 146 147
    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

148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191
    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
192 193 194 195 196 197 198 199 200 201 202
    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:
203 204
            if not all([res.class_name,res.class_url]):
                return []
H
hjdhnx 已提交
205 206 207 208
            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
209
            logger.info(f"{self.getName()}使用缓存分类:{classes}")
H
hjdhnx 已提交
210 211 212 213
            return classes
        else:
            return []

214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244
    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
245 246 247 248 249 250 251 252 253 254 255 256
    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
257
        # print(res)
H
hjdhnx 已提交
258 259 260 261
        if res:
            res.class_name = class_name
            res.class_url = class_url
            self.db.session.add(res)
H
hjdhnx 已提交
262
            msg = f'{self.getName()}修改成功:{res.id}'
H
hjdhnx 已提交
263 264 265 266
        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
267
            msg = f'{self.getName()}新增成功:{res.id}'
H
hjdhnx 已提交
268 269 270

        try:
            self.db.session.commit()
H
hjdhnx 已提交
271
            logger.info(msg)
H
hjdhnx 已提交
272 273 274
        except Exception as e:
            return f'发生了错误:{e}'

H
hjdhnx 已提交
275 276 277 278 279 280 281 282 283 284 285 286 287 288 289
    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
290
            return ''
H
hjdhnx 已提交
291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318

    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
319

320
    def homeContent(self,fypage=1):
H
hjdhnx 已提交
321 322
        # yanaifei
        # https://yanetflix.com/vodtype/dianying.html
H
hjdhnx 已提交
323
        t1 = time()
H
hjdhnx 已提交
324 325
        result = {}
        classes = []
326
        video_result = self.blank()
327 328 329 330 331 332 333 334 335 336 337

        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
338
        print(self.headers)
H
hjdhnx 已提交
339
        has_cache = False
340
        if self.homeUrl.startswith('http'):
341 342 343
            # print(self.homeUrl)
            # print(self.class_parse)
            try:
H
hjdhnx 已提交
344
                if self.class_parse:
H
hjdhnx 已提交
345
                    t2 = time()
H
hjdhnx 已提交
346
                    cache_classes = self.getClasses()
H
hjdhnx 已提交
347
                    logger.info(f'{self.getName()}读取缓存耗时:{get_interval(t2)}毫秒')
H
hjdhnx 已提交
348 349
                    if len(cache_classes) > 0:
                        classes = cache_classes
H
hjdhnx 已提交
350
                        # print(cache_classes)
H
hjdhnx 已提交
351
                        has_cache = True
H
hjdhnx 已提交
352 353 354 355 356 357 358 359
                # 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
360
                    # print(html)
H
hjdhnx 已提交
361
                    # print(self.headers)
H
hjdhnx 已提交
362 363
                    if self.class_parse and not has_cache:
                        p = self.class_parse.split(';')
364
                        # print(p)
H
hjdhnx 已提交
365 366 367 368 369
                        jsp = jsoup(self.url)
                        pdfh = jsp.pdfh
                        pdfa = jsp.pdfa
                        pd = jsp.pd
                        items = pdfa(html,p[0])
370 371
                        # print(len(items))
                        # print(items)
H
hjdhnx 已提交
372 373
                        for item in items:
                            title = pdfh(item, p[1])
H
hjdhnx 已提交
374 375 376
                            # 过滤排除掉标题名称
                            if self.cate_exclude and jsp.test(self.cate_exclude, title):
                                continue
H
hjdhnx 已提交
377
                            url = pd(item, p[2])
378
                            # print(url)
H
hjdhnx 已提交
379 380 381 382 383 384 385 386 387 388 389
                            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)
390
            except Exception as e:
H
hjdhnx 已提交
391
                logger.info(f'{self.getName()}主页发生错误:{e}')
392

H
hjdhnx 已提交
393 394
        result['class'] = classes
        if self.filter:
H
hjdhnx 已提交
395
            result['filters'] = playerConfig['filter']
396
        result.update(video_result)
H
hjdhnx 已提交
397
        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
398 399
        return result

400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420
    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:
421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446
                        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])
447 448 449 450 451 452 453 454 455
                        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",
                        })
456 457
                    except:
                        pass
458 459 460 461 462 463 464 465 466
            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
467
            logger.info(f'首页内容获取失败:{e}')
468
            return self.blank()
H
hjdhnx 已提交
469 470 471 472 473 474 475 476

    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
477
        
H
hjdhnx 已提交
478 479 480 481 482 483 484 485 486
        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
487 488
        # url = self.url + '/{0}.html'.format
        t1 = time()
H
hjdhnx 已提交
489 490
        pg = str(fypage)
        url = self.url.replace('fyclass',fyclass).replace('fypage',pg)
491 492
        if fypage == 1 and self.test('[\[\]]',url):
            url = url.split('[')[1].split(']')[0]
H
hjdhnx 已提交
493
        p = self.一级.split(';')  # 解析
494 495 496
        if len(p) < 5:
            return self.blank()

H
hjdhnx 已提交
497 498 499 500
        jsp = jsoup(self.url)
        pdfh = jsp.pdfh
        pdfa = jsp.pdfa
        pd = jsp.pd
H
hjdhnx 已提交
501 502 503
        # 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'))
504

H
hjdhnx 已提交
505
        videos = []
506 507 508 509 510 511
        items = []
        try:
            r = requests.get(url, headers=self.headers, timeout=self.timeout)
            r.encoding = self.encoding
            print(r.url)
            html = r.text
H
hjdhnx 已提交
512
            # print(html)
513 514 515
            items = pdfa(html, p[0])
        except:
            pass
H
hjdhnx 已提交
516 517
        for item in items:
            # print(item)
518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533
            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
534
        result['list'] = videos
H
hjdhnx 已提交
535
        result['page'] = fypage
H
hjdhnx 已提交
536
        result['pagecount'] = 9999
537
        result['limit'] = 9999
H
hjdhnx 已提交
538
        result['total'] = 999999
H
hjdhnx 已提交
539
        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
540
        
H
hjdhnx 已提交
541 542
        return result

543 544 545
    def detailOneVod(self,id):
        detailUrl = str(id)
        vod = {}
546 547
        if not detailUrl.startswith('http'):
            url = self.detailUrl.replace('fyid', detailUrl)
H
hjdhnx 已提交
548
        else:
549
            url = detailUrl
550
        # print(url)
H
hjdhnx 已提交
551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571
        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 = ''
572 573 574 575
            r = requests.get(url, headers=self.headers, timeout=self.timeout)
            r.encoding = self.encoding
            html = r.text
            # print(html)
H
hjdhnx 已提交
576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638
            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:
639
            logger.info(f'{self.getName()}获取单个详情页{detailUrl}出错{e}')
H
hjdhnx 已提交
640
        # print(vod)
641 642 643 644 645 646 647 648
        return vod

    def detailContent(self, fypage, array):
        """
        cms二级数据
        :param array:
        :return:
        """
H
hjdhnx 已提交
649
        t1 = time()
650 651 652
        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
653 654 655 656 657 658 659 660 661 662 663 664 665 666 667
        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
668
        # print(result)
H
hjdhnx 已提交
669 670
        return result

H
hjdhnx 已提交
671
    def searchContent(self, key, fypage=1):
H
hjdhnx 已提交
672
        pg = str(fypage)
673 674
        if not self.searchUrl:
            return self.blank()
H
hjdhnx 已提交
675
        url = self.searchUrl.replace('**', key).replace('fypage',pg)
H
hjdhnx 已提交
676
        logger.info(f'{self.getName()}搜索链接:{url}')
677 678 679 680 681
        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
682 683 684 685 686 687
        jsp = jsoup(self.url)
        pdfh = jsp.pdfh
        pdfa = jsp.pdfa
        pd = jsp.pd
        pq = jsp.pq
        videos = []
H
hjdhnx 已提交
688
        try:
689
            r = requests.get(url, headers=self.headers,timeout=self.timeout)
H
hjdhnx 已提交
690 691
            r.encoding = self.encoding
            html = r.text
692 693
            # print(html)
            if html.find('输入验证码') > -1:
694
                cookie = verifyCode(url,self.headers,self.timeout,self.retry_count,self.ocr_api)
695
                # cookie = ''
696 697 698 699 700 701 702 703 704 705
                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
706
            items = pdfa(html, p[0])
707
            # print(items)
H
hjdhnx 已提交
708 709 710
            videos = []
            for item in items:
                # print(item)
711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727
                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
728 729
        except Exception as e:
            logger.info(f'搜索{self.getName()}发生错误:{e}')
H
hjdhnx 已提交
730 731 732 733 734
        result = {
            'list': videos
        }
        return result

H
hjdhnx 已提交
735
    def playContent(self, play_url,jxs=None):
H
hjdhnx 已提交
736
        # logger.info('播放免嗅地址: ' + self.play_url)
H
hjdhnx 已提交
737 738
        if not jxs:
            jxs = []
H
hjdhnx 已提交
739
        if self.lazy:
740
            print(f'{play_url}->开始执行免嗅代码{type(self.lazy)}->{self.lazy}')
H
hjdhnx 已提交
741 742
            t1 = time()
            try:
743 744 745 746
                if type(self.lazy) == JsObjectWrapper:
                    logger.info(f'lazy非纯文本免嗅失败耗时:{get_interval(t1)}毫秒,播放地址:{play_url}')

                elif not str(self.lazy).startswith('js:'):
H
hjdhnx 已提交
747 748 749 750 751 752 753 754 755 756 757 758 759 760 761
                    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)
762
                    headers['Referer'] = getHome(play_url)
H
hjdhnx 已提交
763 764
                    py_ctx.update({
                        'input': play_url,
765
                        'fetch_params':{'headers':headers,'timeout':self.d.timeout,'encoding':self.d.encoding},
H
hjdhnx 已提交
766 767
                        'd': self.d,
                        'jxs':jxs,
768 769
                        'getParse':self.d.getParse,
                        'saveParse':self.d.saveParse,
H
hjdhnx 已提交
770 771 772 773 774 775 776 777 778 779 780 781 782
                        'pdfh': self.d.jsp.pdfh,
                        'pdfa': self.d.jsp.pdfa, 'pd': self.d.jsp.pd,
                    })
                    ctx = py_ctx
                    # print(ctx)
                    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
783 784 785 786 787
            return play_url
        else:
            logger.info(f'播放重定向到:{play_url}')
            return play_url

H
hjdhnx 已提交
788 789
if __name__ == '__main__':
    from utils import parser
H
hjdhnx 已提交
790
    # js_path = f'js/玩偶姐姐.js'
H
hjdhnx 已提交
791
    # js_path = f'js/555影视.js'
792 793
    with open('../js/模板.js', encoding='utf-8') as f:
        before = f.read()
H
hjdhnx 已提交
794
    js_path = f'js/vip影院.js'
795 796
    ctx, js_code = parser.runJs(js_path,before=before)
    ruleDict = ctx.rule.to_dict()
797 798
    # lazy = ctx.eval('lazy')
    # print(lazy)
799 800 801
    # 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
802
    print(cms.title)
H
hjdhnx 已提交
803
    print(cms.homeContent())
H
hjdhnx 已提交
804
    # print(cms.categoryContent('5',1))
805
    # print(cms.categoryContent('latest',1))
H
hjdhnx 已提交
806
    # print(cms.detailContent(['https://www.2345ka.com/v/45499.html']))
H
hjdhnx 已提交
807
    # print(cms.detailContent(1,['https://cokemv.me/voddetail/40573.html']))
H
hjdhnx 已提交
808
    # cms.categoryContent('dianying',1)
H
hjdhnx 已提交
809
    # print(cms.detailContent(['67391']))
810
    print(cms.searchContent('斗罗大陆'))