cms.py 33.7 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
    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
H
hjdhnx 已提交
189 190 191 192
        pjfh = jsp.pjfh
        pjfa = jsp.pjfa
        pj = jsp.pj

193 194 195
        pq = jsp.pq
        return pdfh,pdfa,pd,pq

H
hjdhnx 已提交
196 197 198 199 200 201 202 203 204 205 206
    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:
207 208
            if not all([res.class_name,res.class_url]):
                return []
H
hjdhnx 已提交
209 210 211 212
            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
213
            logger.info(f"{self.getName()}使用缓存分类:{classes}")
H
hjdhnx 已提交
214 215 216 217
            return classes
        else:
            return []

218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248
    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
249 250 251 252 253 254 255 256 257 258 259 260
    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
261
        # print(res)
H
hjdhnx 已提交
262 263 264 265
        if res:
            res.class_name = class_name
            res.class_url = class_url
            self.db.session.add(res)
H
hjdhnx 已提交
266
            msg = f'{self.getName()}修改成功:{res.id}'
H
hjdhnx 已提交
267 268 269 270
        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
271
            msg = f'{self.getName()}新增成功:{res.id}'
H
hjdhnx 已提交
272 273 274

        try:
            self.db.session.commit()
H
hjdhnx 已提交
275
            logger.info(msg)
H
hjdhnx 已提交
276 277 278
        except Exception as e:
            return f'发生了错误:{e}'

H
hjdhnx 已提交
279 280 281 282 283 284 285 286 287 288 289 290 291 292 293
    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
294
            return ''
H
hjdhnx 已提交
295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322

    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
323

324
    def homeContent(self,fypage=1):
H
hjdhnx 已提交
325 326
        # yanaifei
        # https://yanetflix.com/vodtype/dianying.html
H
hjdhnx 已提交
327
        t1 = time()
H
hjdhnx 已提交
328 329
        result = {}
        classes = []
330
        video_result = self.blank()
331 332 333 334 335 336 337 338 339 340 341

        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
342
        print(self.headers)
H
hjdhnx 已提交
343
        has_cache = False
344
        if self.homeUrl.startswith('http'):
345 346 347
            # print(self.homeUrl)
            # print(self.class_parse)
            try:
H
hjdhnx 已提交
348
                if self.class_parse:
H
hjdhnx 已提交
349
                    t2 = time()
H
hjdhnx 已提交
350
                    cache_classes = self.getClasses()
H
hjdhnx 已提交
351
                    logger.info(f'{self.getName()}读取缓存耗时:{get_interval(t2)}毫秒')
H
hjdhnx 已提交
352 353
                    if len(cache_classes) > 0:
                        classes = cache_classes
H
hjdhnx 已提交
354
                        # print(cache_classes)
H
hjdhnx 已提交
355
                        has_cache = True
H
hjdhnx 已提交
356 357 358 359 360 361 362 363
                # 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
364
                    # print(html)
H
hjdhnx 已提交
365
                    # print(self.headers)
H
hjdhnx 已提交
366 367
                    if self.class_parse and not has_cache:
                        p = self.class_parse.split(';')
368
                        # print(p)
H
hjdhnx 已提交
369 370 371 372 373
                        jsp = jsoup(self.url)
                        pdfh = jsp.pdfh
                        pdfa = jsp.pdfa
                        pd = jsp.pd
                        items = pdfa(html,p[0])
374 375
                        # print(len(items))
                        # print(items)
H
hjdhnx 已提交
376 377
                        for item in items:
                            title = pdfh(item, p[1])
H
hjdhnx 已提交
378 379 380
                            # 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
381
                            url = pd(item, p[2])
382
                            # print(url)
H
hjdhnx 已提交
383 384 385 386 387 388 389 390 391 392 393
                            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)
394
            except Exception as e:
H
hjdhnx 已提交
395
                logger.info(f'{self.getName()}主页发生错误:{e}')
396

H
hjdhnx 已提交
397 398
        result['class'] = classes
        if self.filter:
H
hjdhnx 已提交
399
            result['filters'] = playerConfig['filter']
400
        result.update(video_result)
H
hjdhnx 已提交
401
        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
402 403
        return result

404 405 406 407 408 409 410 411 412 413 414 415
    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)
H
hjdhnx 已提交
416 417 418 419
        is_json = str(p[0]).startswith('json:')
        pdfh = jsp.pjfh if is_json else jsp.pdfh
        pdfa = jsp.pjfa if is_json else jsp.pdfa
        pd = jsp.pj if is_json else jsp.pd
H
hjdhnx 已提交
420
        # print(html)
421 422 423 424 425 426
        try:
            if self.double:
                items = pdfa(html, p[0])
                for item in items:
                    items2 = pdfa(item,p[1])
                    for item2 in items2:
427 428 429 430
                        try:
                            title = pdfh(item2, p[2])
                            img = pd(item2, p[3])
                            desc = pdfh(item2, p[4])
H
hjdhnx 已提交
431 432
                            links = [pd(item, p5) if not self.detailUrl else pdfh(item, p5) for p5 in p[5].split('+')]
                            link = '$'.join(links)
433 434 435 436 437 438 439 440 441 442 443 444 445
                            content = '' if len(p) < 7 else pdfh(item2, p[6])
                            videos.append({
                                "vod_id": link,
                                "vod_name": title,
                                "vod_pic": img,
                                "vod_remarks": desc,
                                "vod_content": content,
                                "type_id": 1,
                                "type_name": "首页推荐",
                            })
                        except:
                            pass
            else:
H
hjdhnx 已提交
446 447
                items = pdfa(html, p[0].replace('json:',''))
                # print(items)
448 449 450 451 452
                for item in items:
                    try:
                        title = pdfh(item, p[1])
                        img = pd(item, p[2])
                        desc = pdfh(item, p[3])
H
hjdhnx 已提交
453 454 455
                        # link = pd(item, p[4])
                        links = [pd(item, p5) if not self.detailUrl else pdfh(item, p5) for p5 in p[4].split('+')]
                        link = '$'.join(links)
456
                        content = '' if len(p) < 6 else pdfh(item, p[5])
457 458 459 460 461 462 463 464 465
                        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",
                        })
466 467
                    except:
                        pass
468 469 470 471 472 473 474 475 476
            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
477
            logger.info(f'首页内容获取失败:{e}')
478
            return self.blank()
H
hjdhnx 已提交
479 480 481 482 483 484 485 486

    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
487
        
H
hjdhnx 已提交
488 489 490 491 492 493 494 495 496
        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
497 498
        # url = self.url + '/{0}.html'.format
        t1 = time()
H
hjdhnx 已提交
499 500
        pg = str(fypage)
        url = self.url.replace('fyclass',fyclass).replace('fypage',pg)
501 502
        if fypage == 1 and self.test('[\[\]]',url):
            url = url.split('[')[1].split(']')[0]
H
hjdhnx 已提交
503
        p = self.一级.split(';')  # 解析
504 505 506
        if len(p) < 5:
            return self.blank()

H
hjdhnx 已提交
507
        jsp = jsoup(self.url)
H
hjdhnx 已提交
508 509 510 511
        is_json = str(p[0]).startswith('json:')
        pdfh = jsp.pjfh if is_json else jsp.pdfh
        pdfa = jsp.pjfa if is_json else jsp.pdfa
        pd = jsp.pj if is_json else jsp.pd
H
hjdhnx 已提交
512 513 514
        # 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'))
515

H
hjdhnx 已提交
516
        videos = []
517 518 519 520 521
        items = []
        try:
            r = requests.get(url, headers=self.headers, timeout=self.timeout)
            r.encoding = self.encoding
            print(r.url)
H
hjdhnx 已提交
522 523
            # html = r.text
            html = r.json() if is_json else r.text
H
hjdhnx 已提交
524
            # print(html)
H
hjdhnx 已提交
525
            items = pdfa(html,p[0].replace('json:','',1))
526 527
        except:
            pass
H
hjdhnx 已提交
528
        # print(items)
H
hjdhnx 已提交
529 530
        for item in items:
            # print(item)
531 532 533 534
            try:
                title = pdfh(item, p[1])
                img = pd(item, p[2])
                desc = pdfh(item, p[3])
H
hjdhnx 已提交
535 536
                links = [pd(item, p4) if not self.detailUrl else pdfh(item, p4) for p4 in p[4].split('+')]
                link = '$'.join(links)
537 538 539
                content = '' if len(p) < 6 else pdfh(item, p[5])
                # sid = self.regStr(sid, "/video/(\\S+).html")
                videos.append({
H
hjdhnx 已提交
540
                    "vod_id": f'{fyclass}${link}' if self.detailUrl else link,# 分类,播放链接
541 542 543 544 545
                    "vod_name": title,
                    "vod_pic": img,
                    "vod_remarks": desc,
                    "vod_content": content,
                })
H
hjdhnx 已提交
546 547
            except Exception as e:
                print(f'发生了错误:{e}')
548
                pass
H
hjdhnx 已提交
549
        result['list'] = videos
H
hjdhnx 已提交
550
        result['page'] = fypage
H
hjdhnx 已提交
551
        result['pagecount'] = 9999
552
        result['limit'] = 9999
H
hjdhnx 已提交
553
        result['total'] = 999999
H
hjdhnx 已提交
554
        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
555
        
H
hjdhnx 已提交
556 557
        return result

H
hjdhnx 已提交
558
    def detailOneVod(self,id,fyclass=''):
559 560
        detailUrl = str(id)
        vod = {}
561
        if not detailUrl.startswith('http'):
H
hjdhnx 已提交
562
            url = self.detailUrl.replace('fyid', detailUrl).replace('fyclass',fyclass)
H
hjdhnx 已提交
563
        else:
564
            url = detailUrl
565
        # print(url)
H
hjdhnx 已提交
566 567 568 569 570 571 572 573 574 575 576 577 578 579 580
        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)
H
hjdhnx 已提交
581 582 583 584 585

            is_json = p.get('is_json',False) # 二级里加is_json参数
            pdfh = jsp.pjfh if is_json else jsp.pdfh
            pdfa = jsp.pjfa if is_json else jsp.pdfa
            pd = jsp.pj if is_json else jsp.pd
H
hjdhnx 已提交
586 587 588
            pq = jsp.pq
            obj = {}
            vod_name = ''
589 590
            r = requests.get(url, headers=self.headers, timeout=self.timeout)
            r.encoding = self.encoding
H
hjdhnx 已提交
591 592
            # html = r.text
            html = r.json() if is_json else r.text
593
            # print(html)
H
hjdhnx 已提交
594 595 596
            if p.get('title'):
                p1 = p['title'].split(';')
                vod_name = pdfh(html,p1[0]).replace('\n',' ')
H
hjdhnx 已提交
597 598
                # title = '\n'.join([pdfh(html,i).replace('\n',' ') for i in p1])
                title = '\n'.join([','.join([pdfh(html, pp1).strip() for pp1 in i.split('+')]) for i in p1])
H
hjdhnx 已提交
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
                # 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'):
H
hjdhnx 已提交
632
                vodHeader = pdfa(html,p['tabs'].split(';')[0])
H
hjdhnx 已提交
633 634
                # print(f'线路列表数:{len((vodHeader))}')
                # print(vodHeader)
H
hjdhnx 已提交
635 636
                if not is_json:
                    vodHeader = [pq(v).text() for v in vodHeader]
H
hjdhnx 已提交
637 638 639 640 641 642 643 644 645 646 647
            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)):
H
hjdhnx 已提交
648 649 650 651
                   tab_name = str(vodHeader[i])
                   tab_ext = p['tabs'].split(';')[1] if len(p['tabs'].split(';')) > 1 else ''
                   p1 = p['lists'].replace('#idv',tab_name).replace('#id',str(i))
                   tab_ext = tab_ext.replace('#idv',tab_name).replace('#id',str(i))
H
hjdhnx 已提交
652
                   vodList = pdfa(html,p1) # 1条线路的选集列表
H
hjdhnx 已提交
653
                   # print(vodList)
H
hjdhnx 已提交
654
                   # vodList = [pq(i).text()+'$'+pd(i,'a&&href') for i in vodList]  # 拼接成 名称$链接
H
hjdhnx 已提交
655 656 657 658 659 660 661
                   if self.play_parse: # 自动base64编码
                       vodList = [(pdfh(html,tab_ext) if tab_ext else tab_name)+'$'+self.play_url+base64Encode(i) for i in vodList] if is_json else\
                           [pq(i).text()+'$'+self.play_url+base64Encode(pd(i,'a&&href')) for i in vodList]  # 拼接成 名称$链接
                   else:
                       vodList = [(pdfh(html, tab_ext) if tab_ext else tab_name) + '$' + self.play_url + i for i in
                                  vodList] if is_json else \
                           [pq(i).text() + '$' + self.play_url + pd(i, 'a&&href') for i in vodList]  # 拼接成 名称$链接
H
hjdhnx 已提交
662 663 664 665 666 667 668
                   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:
669
            logger.info(f'{self.getName()}获取单个详情页{detailUrl}出错{e}')
H
hjdhnx 已提交
670
        # print(vod)
671 672 673 674 675 676 677 678
        return vod

    def detailContent(self, fypage, array):
        """
        cms二级数据
        :param array:
        :return:
        """
H
hjdhnx 已提交
679
        t1 = time()
680 681 682
        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
683 684
        try:
            for vod_url in array:
H
hjdhnx 已提交
685 686 687 688 689 690
                vod_class = ''
                if vod_url.find('$') > -1:
                    tmp = vod_url.split('$')
                    vod_class = tmp[0]
                    vod_url = tmp[1]
                obj = thread_pool.submit(self.detailOneVod, vod_url,vod_class)
H
hjdhnx 已提交
691 692 693 694 695 696 697 698 699 700 701 702
                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
703
        # print(result)
H
hjdhnx 已提交
704 705
        return result

H
hjdhnx 已提交
706
    def searchContent(self, key, fypage=1):
H
hjdhnx 已提交
707
        pg = str(fypage)
708 709
        if not self.searchUrl:
            return self.blank()
H
hjdhnx 已提交
710
        url = self.searchUrl.replace('**', key).replace('fypage',pg)
H
hjdhnx 已提交
711
        logger.info(f'{self.getName()}搜索链接:{url}')
712 713 714 715 716
        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
717
        jsp = jsoup(self.url)
H
hjdhnx 已提交
718 719 720 721
        is_json = str(p[0]).startswith('json:')
        pdfh = jsp.pjfh if is_json else jsp.pdfh
        pdfa = jsp.pjfa if is_json else jsp.pdfa
        pd = jsp.pj if is_json else jsp.pd
H
hjdhnx 已提交
722 723
        pq = jsp.pq
        videos = []
H
hjdhnx 已提交
724
        try:
725
            r = requests.get(url, headers=self.headers,timeout=self.timeout)
H
hjdhnx 已提交
726
            r.encoding = self.encoding
H
hjdhnx 已提交
727 728
            # html = r.text
            html = r.json() if is_json else r.text
729
            # print(html)
H
hjdhnx 已提交
730
            if not is_json and html.find('输入验证码') > -1:
731
                cookie = verifyCode(url,self.headers,self.timeout,self.retry_count,self.ocr_api)
732
                # cookie = ''
733 734 735 736 737 738 739 740 741 742
                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
743
            items = pdfa(html,p[0].replace('json:','',1))
744
            # print(items)
H
hjdhnx 已提交
745 746 747
            videos = []
            for item in items:
                # print(item)
748 749 750 751
                try:
                    title = pdfh(item, p[1])
                    img = pd(item, p[2])
                    desc = pdfh(item, p[3])
H
hjdhnx 已提交
752 753 754
                    # link = '$'.join([pd(item, p4) for p4 in p[4].split('+')])
                    links = [pd(item, p4) if not self.detailUrl else pdfh(item, p4) for p4 in p[4].split('+')]
                    link = '$'.join(links)
755 756 757 758 759 760 761 762 763 764 765 766
                    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
767 768
        except Exception as e:
            logger.info(f'搜索{self.getName()}发生错误:{e}')
H
hjdhnx 已提交
769 770 771 772 773
        result = {
            'list': videos
        }
        return result

H
hjdhnx 已提交
774
    def playContent(self, play_url,jxs=None,flag=None):
H
hjdhnx 已提交
775
        # logger.info('播放免嗅地址: ' + self.play_url)
H
hjdhnx 已提交
776 777
        if not jxs:
            jxs = []
H
hjdhnx 已提交
778 779 780 781
        try:
            play_url = baseDecode(play_url) # 自动base64解码
        except:
            pass
H
hjdhnx 已提交
782
        if self.lazy:
783
            print(f'{play_url}->开始执行免嗅代码{type(self.lazy)}->{self.lazy}')
H
hjdhnx 已提交
784 785
            t1 = time()
            try:
786 787 788 789
                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
790 791 792 793 794 795 796 797 798 799 800 801 802 803 804
                    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)
805
                    headers['Referer'] = getHome(play_url)
H
hjdhnx 已提交
806 807
                    py_ctx.update({
                        'input': play_url,
808
                        'fetch_params':{'headers':headers,'timeout':self.d.timeout,'encoding':self.d.encoding},
H
hjdhnx 已提交
809 810
                        'd': self.d,
                        'jxs':jxs,
811 812
                        'getParse':self.d.getParse,
                        'saveParse':self.d.saveParse,
H
hjdhnx 已提交
813 814 815 816 817 818 819 820 821 822
                        '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')
H
hjdhnx 已提交
823 824 825 826
                    if isinstance(play_url,JsObjectWrapper):
                        play_url = play_url.to_dict()
                    # print(type(play_url))
                    # print(play_url)
H
hjdhnx 已提交
827 828 829
                    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
830 831 832 833 834
            return play_url
        else:
            logger.info(f'播放重定向到:{play_url}')
            return play_url

H
hjdhnx 已提交
835
if __name__ == '__main__':
H
hjdhnx 已提交
836 837 838
    print(urljoin('https://api.web.360kan.com/v1/f',
                  '//0img.hitv.com/preview/sp_images/2022/01/28/202201281528074643023.jpg'))
    # exit()
H
hjdhnx 已提交
839
    from utils import parser
H
hjdhnx 已提交
840
    # js_path = f'js/玩偶姐姐.js'
H
hjdhnx 已提交
841
    # js_path = f'js/555影视.js'
842 843
    with open('../js/模板.js', encoding='utf-8') as f:
        before = f.read()
H
hjdhnx 已提交
844
    js_path = f'js/360影视.js'
845 846
    ctx, js_code = parser.runJs(js_path,before=before)
    ruleDict = ctx.rule.to_dict()
847 848
    # lazy = ctx.eval('lazy')
    # print(lazy)
849 850 851
    # 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
852
    print(cms.title)
H
hjdhnx 已提交
853
    print(cms.homeContent())
H
hjdhnx 已提交
854
    # print(cms.categoryContent('5',1))
855
    # print(cms.categoryContent('latest',1))
H
hjdhnx 已提交
856
    # print(cms.detailContent(['https://www.2345ka.com/v/45499.html']))
H
hjdhnx 已提交
857
    # print(cms.detailContent(1,['https://cokemv.me/voddetail/40573.html']))
H
hjdhnx 已提交
858
    # cms.categoryContent('dianying',1)
H
hjdhnx 已提交
859
    # print(cms.detailContent(['67391']))
H
hjdhnx 已提交
860 861
    # print(cms.searchContent('斗罗大陆'))
    print(cms.searchContent('独行月球'))