cms.py 56.6 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
import json
H
hjdhnx 已提交
7 8 9 10 11 12 13 14 15

import requests
import re
import math
from utils.web import *
from utils.system import getHost
from utils.config import playerConfig
from utils.log import logger
from utils.encode import base64Encode,baseDecode,fetch,post,request,getCryptoJS,getPreJs,buildUrl,getHome
H
hjdhnx 已提交
16 17
from utils.encode import verifyCode,setDetail,join,urljoin2,parseText,requireCache
from utils.encode import md5 as mmd5
H
hjdhnx 已提交
18
from utils.safePython import safePython
H
hjdhnx 已提交
19
from utils.parser import runPy,runJScode,JsObjectWrapper,PyJsObject,PyJsString
H
hjdhnx 已提交
20
from utils.htmlParser import jsoup
H
hjdhnx 已提交
21
from urllib.parse import urljoin,quote,unquote
H
hjdhnx 已提交
22
from concurrent.futures import ThreadPoolExecutor  # 引入线程池
H
hjdhnx 已提交
23
from flask import url_for,redirect,render_template_string
H
hjdhnx 已提交
24
from easydict import EasyDict as edict
H
hjdhnx 已提交
25
from controllers.service import storage_service
H
hjdhnx 已提交
26

H
hjdhnx 已提交
27 28
def setItem(key,value):
    lsg = storage_service()
H
hjdhnx 已提交
29 30 31 32
    if isinstance(key,PyJsString):
        key = parseText(str(key))
    if isinstance(value,PyJsString):
        value = parseText(str(value))
H
hjdhnx 已提交
33 34 35 36
    return lsg.setItem(key,value)

def getItem(key,value=''):
    lsg = storage_service()
H
hjdhnx 已提交
37 38 39 40
    if isinstance(key,PyJsString):
        key = parseText(str(key))
    if isinstance(value,PyJsString):
        value = parseText(str(value))
H
hjdhnx 已提交
41 42 43 44
    return lsg.getItem(key,value)

def clearItem(key):
    lsg = storage_service()
H
hjdhnx 已提交
45 46
    if isinstance(key,PyJsString):
        key = parseText(str(key))
H
hjdhnx 已提交
47 48
    return lsg.clearItem(key)

H
hjdhnx 已提交
49 50 51
def encodeUrl(url):
    # return base64Encode(quote(url))
    # return base64Encode(url)
H
hjdhnx 已提交
52 53 54 55
    # print(type(url))
    if isinstance(url,PyJsString):
        # obj = obj.to_dict()
        url = parseText(str(url))
H
hjdhnx 已提交
56 57
    return quote(url)

H
hjdhnx 已提交
58 59 60 61 62 63
def stringify(obj):
    if isinstance(obj,PyJsObject):
        # obj = obj.to_dict()
        obj = parseText(str(obj))
    return json.dumps(obj, separators=(',', ':'), ensure_ascii=False)

H
hjdhnx 已提交
64 65 66 67 68 69 70 71 72 73
def requireObj(url):
    if isinstance(url,PyJsString):
        url = parseText(str(url))
    return requireCache(url)

def md5(text):
    if isinstance(text,PyJsString):
        text = parseText(str(text))
    return mmd5(text)

H
hjdhnx 已提交
74 75 76
py_ctx = {
'requests':requests,'print':print,'base64Encode':base64Encode,'baseDecode':baseDecode,
'log':logger.info,'fetch':fetch,'post':post,'request':request,'getCryptoJS':getCryptoJS,
H
hjdhnx 已提交
77
'buildUrl':buildUrl,'getHome':getHome,'setDetail':setDetail,'join':join,'urljoin2':urljoin2,
H
hjdhnx 已提交
78
'PC_UA':PC_UA,'MOBILE_UA':MOBILE_UA,'UC_UA':UC_UA,'UA':UA,'IOS_UA':IOS_UA,
H
hjdhnx 已提交
79 80
'setItem':setItem,'getItem':getItem,'clearItem':clearItem,'stringify':stringify,'encodeUrl':encodeUrl,
'requireObj':requireObj,'md5':md5
H
hjdhnx 已提交
81 82 83 84
}
# print(getCryptoJS())

class CMS:
H
hjdhnx 已提交
85
    def __init__(self, rule, db=None, RuleClass=None, PlayParse=None,new_conf=None,ext=''):
H
hjdhnx 已提交
86 87
        if new_conf is None:
            new_conf = {}
H
hjdhnx 已提交
88
        self.lsg = storage_service()
H
hjdhnx 已提交
89 90
        self.title = rule.get('title', '')
        self.id = rule.get('id', self.title)
H
hjdhnx 已提交
91
        self.filter_url = rule.get('filter_url', '').replace('{{fl}}','{{fl|safe}}') # python jinjia2禁用自动编码
H
hjdhnx 已提交
92
        cate_exclude  = rule.get('cate_exclude','')
H
hjdhnx 已提交
93
        tab_exclude  = rule.get('tab_exclude','')
H
hjdhnx 已提交
94
        self.lazy = rule.get('lazy', False)
H
hjdhnx 已提交
95 96
        # self.play_disable = new_conf.get('PLAY_DISABLE',False)
        self.play_disable = self.lsg.getItem('PLAY_DISABLE',False)
H
hjdhnx 已提交
97
        self.retry_count = new_conf.get('RETRY_CNT',3)
H
hjdhnx 已提交
98
        # self.lazy_mode = new_conf.get('LAZYPARSE_MODE')
H
优化  
hjdhnx 已提交
99
        self.lazy_mode = self.lsg.getItem('LAZYPARSE_MODE',2)
H
hjdhnx 已提交
100
        self.ocr_api = new_conf.get('OCR_API')
H
hjdhnx 已提交
101 102 103 104
        # self.cate_exclude = new_conf.get('CATE_EXCLUDE','')
        self.cate_exclude = self.lsg.getItem('CATE_EXCLUDE','')
        # self.tab_exclude = new_conf.get('TAB_EXCLUDE','')
        self.tab_exclude = self.lsg.getItem('TAB_EXCLUDE','')
H
hjdhnx 已提交
105 106 107 108 109
        if cate_exclude:
            if not str(cate_exclude).startswith('|') and not str(self.cate_exclude).endswith('|'):
                self.cate_exclude = self.cate_exclude+'|'+cate_exclude
            else:
                self.cate_exclude += cate_exclude
H
hjdhnx 已提交
110 111 112 113 114
        if tab_exclude:
            if not str(tab_exclude).startswith('|') and not str(self.tab_exclude).endswith('|'):
                self.tab_exclude = self.tab_exclude+'|'+tab_exclude
            else:
                self.tab_exclude += tab_exclude
H
hjdhnx 已提交
115
        # print(self.cate_exclude)
H
hjdhnx 已提交
116 117 118 119 120 121 122 123 124 125 126 127 128 129
        try:
            self.vod = redirect(url_for('vod')).headers['Location']
        except:
            self.vod = '/vod'
        # if not self.play_disable and self.lazy:
        if not self.play_disable:
            self.play_parse = rule.get('play_parse', False)
            try:
                play_url = getHost(self.lazy_mode)
            except:
                play_url = getHost(1,5705)
            # play_url = new_conf.get('PLAY_URL',getHost(2))
            if not play_url.startswith('http'):
                play_url = 'http://'+play_url
H
优化  
hjdhnx 已提交
130
            # print(play_url)
H
hjdhnx 已提交
131 132
            if self.play_parse:
                # self.play_url = play_url + self.vod + '?play_url='
H
hjdhnx 已提交
133
                self.play_url = f'{play_url}{self.vod}?rule={self.id}&ext={ext}&play_url='
H
hjdhnx 已提交
134 135 136 137 138 139
                # logger.info(f'cms重定向链接:{self.play_url}')
            else:
                self.play_url = ''
        else:
            self.play_parse = False
            self.play_url = ''
H
优化  
hjdhnx 已提交
140
        logger.info('播放免嗅地址: '+self.play_url)
H
hjdhnx 已提交
141 142 143 144 145

        self.db = db
        self.RuleClass = RuleClass
        self.PlayParse = PlayParse
        host = rule.get('host','').rstrip('/')
H
hjdhnx 已提交
146
        host = unquote(host)
H
hjdhnx 已提交
147 148 149 150 151 152 153 154 155 156 157
        timeout = rule.get('timeout',5000)
        homeUrl = rule.get('homeUrl','/')
        url = rule.get('url','')
        detailUrl = rule.get('detailUrl','')
        searchUrl = rule.get('searchUrl','')
        default_headers = getHeaders(host)
        self_headers = rule.get('headers',{})
        default_headers.update(self_headers)
        headers = default_headers
        cookie = self.getCookie()
        # print(f'{self.title}cookie:{cookie}')
H
hjdhnx 已提交
158
        self.oheaders = self_headers
H
hjdhnx 已提交
159 160
        if cookie:
            headers['cookie'] = cookie
H
hjdhnx 已提交
161
            self.oheaders['cookie'] = cookie
H
hjdhnx 已提交
162 163 164 165 166 167 168 169 170 171 172 173 174
        limit = rule.get('limit',6)
        encoding = rule.get('编码', 'utf-8')
        self.limit = min(limit,30)
        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
                elif v == 'UC_UA':
                    headers[k] = UC_UA
H
hjdhnx 已提交
175 176
                elif v == 'IOS_UA':
                    headers[k] = IOS_UA
H
hjdhnx 已提交
177 178 179 180 181 182
        lower_keys = list(map(lambda x:x.lower(),keys))
        if not 'user-agent' in lower_keys:
            headers['User-Agent'] = UA
        if not 'referer' in lower_keys:
            headers['Referer'] = host
        self.headers = headers
H
hjdhnx 已提交
183
        # print(headers)
H
hjdhnx 已提交
184
        self.host = host
H
hjdhnx 已提交
185
        self.homeUrl = urljoin(host,homeUrl) if host and homeUrl else homeUrl or host
H
hjdhnx 已提交
186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219
        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
        else:
            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
        self.class_name = rule.get('class_name','')
        self.class_url = rule.get('class_url','')
        self.class_parse = rule.get('class_parse','')
        self.filter_name = rule.get('filter_name', '')
        self.filter_url = rule.get('filter_url', '')
        self.filter_parse = rule.get('filter_parse', '')
        self.double = rule.get('double',False)
        self.一级 = rule.get('一级','')
        self.二级 = rule.get('二级','')
        self.搜索 = rule.get('搜索','')
        self.推荐 = rule.get('推荐','')
        self.encoding = encoding
        self.timeout = round(int(timeout)/1000,2)
        self.filter = rule.get('filter',[])
        self.extend = rule.get('extend',[])
        self.d = self.getObject()

    def getName(self):
        return self.title

    def getObject(self):
        o = edict({
            'jsp':jsoup(self.url),
            'getParse':self.getParse,
            'saveParse':self.saveParse,
H
hjdhnx 已提交
220
            'oheaders':self.oheaders,
221
            'headers':self.headers, # 通用免嗅需要
H
hjdhnx 已提交
222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251
            'encoding':self.encoding,
            'name':self.title,
            'timeout':self.timeout,
        })
        return o

    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 {
252 253 254 255 256 257 258 259 260 261
            "vod_id": "id",
            "vod_name": "片名",
            "vod_pic": "",# 图片
            "type_name": "剧情",
            "vod_year": "年份",
            "vod_area": "地区",
            "vod_remarks": "更新信息",
            "vod_actor": "主演",
            "vod_director": "导演",
            "vod_content": "简介"
H
hjdhnx 已提交
262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375
        }

    def jsoup(self):
        jsp = jsoup(self.url)
        pdfh = jsp.pdfh
        pdfa = jsp.pdfa
        pd = jsp.pd
        pjfh = jsp.pjfh
        pjfa = jsp.pjfa
        pj = jsp.pj

        pq = jsp.pq
        return pdfh,pdfa,pd,pq

    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:
            if not all([res.class_name,res.class_url]):
                return []
            cls = res.class_name.split('&')
            cls2 = res.class_url.split('&')
            classes = [{'type_name':cls[i],'type_id':cls2[i]} for i in range(len(cls))]
            # _logger.info(classes)
            logger.info(f"{self.getName()}使用缓存分类:{classes}")
            return classes
        else:
            return []

    def getCookie(self):
        name = self.getName()
        if not self.db:
            msg = f'{name}未提供数据库连接'
            print(msg)
            return False
        res = self.db.session.query(self.RuleClass).filter(self.RuleClass.name == name).first()
        if res:
            return res.cookie or None
        else:
            return None

    def saveCookie(self,cookie):
        name = self.getName()
        if not self.db:
            msg = f'{name}未提供数据库连接'
            print(msg)
            return False
        res = self.db.session.query(self.RuleClass).filter(self.RuleClass.name == name).first()
        if res:
            res.cookie = cookie
            self.db.session.add(res)
        else:
            res = self.RuleClass(name=name, cookie=cookie)
            self.db.session.add(res)
        try:
            self.db.session.commit()
            logger.info(f'{name}已保存cookie:{cookie}')
        except Exception as e:
            return f'保存cookie发生了错误:{e}'

    def saveClass(self, classes):
        if not self.db:
            msg = '未提供数据库连接'
            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()
        # print(res)
        if res:
            res.class_name = class_name
            res.class_url = class_url
            self.db.session.add(res)
            msg = f'{self.getName()}修改成功:{res.id}'
        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()
            msg = f'{self.getName()}新增成功:{res.id}'

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

    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:
            return ''

H
hjdhnx 已提交
376 377
    def dealJson(self,html):
        try:
H
hjdhnx 已提交
378 379
            # res = re.search('.*?\{(.*)\}',html,re.M|re.I).groups()[0]
            res = re.search('.*?\{(.*)\}',html,re.M|re.S).groups()[0]
H
hjdhnx 已提交
380 381 382 383 384
            html = '{' + res + '}'
            return html
        except:
            return html

H
hjdhnx 已提交
385 386 387 388 389 390 391 392 393 394
    def checkHtml(self,r):
        r.encoding = self.encoding
        html = r.text
        if html.find('?btwaf=') > -1:
            btwaf = re.search('btwaf(.*?)"',html,re.M|re.I).groups()[0]
            url = r.url.split('#')[0]+'?btwaf'+btwaf
            # print(f'需要过宝塔验证:{url}')
            cookies_dict = requests.utils.dict_from_cookiejar(r.cookies)
            cookie_str = ';'.join([f'{k}={cookies_dict[k]}' for k in cookies_dict])
            self.headers['cookie'] = cookie_str
H
hjdhnx 已提交
395
            r = requests.get(url, headers=self.headers, timeout=self.timeout,verify=False)
H
hjdhnx 已提交
396 397 398 399 400 401 402 403
            r.encoding = self.encoding
            html = r.text
            if html.find('?btwaf=') < 0:
                self.saveCookie(cookie_str)

        # print(html)
        return html

H
hjdhnx 已提交
404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451
    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}'


    def homeContent(self,fypage=1):
        # yanaifei
        # https://yanetflix.com/vodtype/dianying.html
        t1 = time()
        result = {}
        classes = []
        video_result = self.blank()

        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)
        print(self.headers)
        has_cache = False
H
hjdhnx 已提交
452
        # print(self.homeUrl)
H
hjdhnx 已提交
453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468
        if self.homeUrl.startswith('http'):
            # print(self.class_parse)
            try:
                if self.class_parse:
                    t2 = time()
                    cache_classes = self.getClasses()
                    logger.info(f'{self.getName()}读取缓存耗时:{get_interval(t2)}毫秒')
                    if len(cache_classes) > 0:
                        classes = cache_classes
                        # print(cache_classes)
                        has_cache = True
                # logger.info(f'是否有缓存分类:{has_cache}')
                if has_cache and not self.推荐:
                    pass
                else:
                    new_classes = []
H
hjdhnx 已提交
469
                    r = requests.get(self.homeUrl, headers=self.headers, timeout=self.timeout,verify=False)
H
hjdhnx 已提交
470
                    html = self.checkHtml(r)
H
hjdhnx 已提交
471 472 473 474
                    # print(html)
                    # print(self.headers)
                    if self.class_parse and not has_cache:
                        p = self.class_parse.split(';')
H
hjdhnx 已提交
475 476
                        # print(p[0])
                        # print(html)
H
hjdhnx 已提交
477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492
                        jsp = jsoup(self.url)
                        pdfh = jsp.pdfh
                        pdfa = jsp.pdfa
                        pd = jsp.pd
                        items = pdfa(html,p[0])
                        # print(len(items))
                        # print(items)
                        for item in items:
                            title = pdfh(item, p[1])
                            # 过滤排除掉标题名称
                            if self.cate_exclude and jsp.test(self.cate_exclude, title):
                                continue
                            url = pd(item, p[2])
                            # print(url)
                            tag = url
                            if len(p) > 3 and p[3].strip():
H
hjdhnx 已提交
493 494 495 496 497
                                try:
                                    tag = self.regexp(p[3].strip(),url,0)
                                except:
                                    logger.info(f'分类匹配错误:{title}对应的链接{url}无法匹配{p[3]}')
                                    continue
H
hjdhnx 已提交
498 499 500 501 502 503 504 505 506 507
                            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)
            except Exception as e:
                logger.info(f'{self.getName()}主页发生错误:{e}')
508
        classes = list(filter(lambda x:not self.cate_exclude or not jsoup(self.url).test(self.cate_exclude, x['type_name']),classes))
H
hjdhnx 已提交
509 510
        result['class'] = classes
        if self.filter:
H
hjdhnx 已提交
511 512 513 514
            if isinstance(self.filter,dict):
                result['filters'] = self.filter
            else:
                result['filters'] = playerConfig['filter']
H
hjdhnx 已提交
515 516 517 518 519 520
        result.update(video_result)
        # print(result)
        logger.info(f'{self.getName()}获取首页总耗时(包含读取缓存):{get_interval(t1)}毫秒')
        return result

    def homeVideoContent(self,html,fypage=1):
H
hjdhnx 已提交
521 522
        p = self.推荐
        if not p:
H
hjdhnx 已提交
523 524
            return self.blank()

H
hjdhnx 已提交
525
        jsp = jsoup(self.homeUrl)
H
hjdhnx 已提交
526 527
        result = {}
        videos = []
H
hjdhnx 已提交
528 529 530 531 532 533 534
        is_js = isinstance(p, str) and str(p).strip().startswith('js:')  # 是js
        if is_js:
            headers['Referer'] = getHome(self.host)
            py_ctx.update({
                'input': self.homeUrl,
                'HOST': self.host,
                'TYPE': 'home',  # 海阔js环境标志
H
hjdhnx 已提交
535
                'oheaders':self.d.oheaders,
H
hjdhnx 已提交
536
                'fetch_params': {'headers': self.headers, 'timeout': self.d.timeout, 'encoding': self.d.encoding},
H
hjdhnx 已提交
537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554
                'd': self.d,
                'getParse': self.d.getParse,
                'saveParse': self.d.saveParse,
                'jsp': jsp, 'setDetail': setDetail,
            })
            ctx = py_ctx
            jscode = getPreJs() + p.strip().replace('js:', '', 1)
            # print(jscode)
            try:
                loader, _ = runJScode(jscode, ctx=ctx)
                # print(loader.toString())
                vods = loader.eval('VODS')
                # print(vods)
                if isinstance(vods, JsObjectWrapper):
                    videos = vods.to_list()
            except Exception as e:
                logger.info(f'首页推荐执行js获取列表出错:{e}')
        else:
H
hjdhnx 已提交
555 556 557 558
            if p == '*' and self.一级:
                p = self.一级
                self.double = False
                logger.info(f'首页推荐继承一级: {p}')
H
hjdhnx 已提交
559 560 561 562 563 564
            p = p.strip().split(';')  # 解析
            if not self.double and len(p) < 5:
                return self.blank()
            if self.double and len(p) < 6:
                return self.blank()
            jsp = jsoup(self.homeUrl)
H
hjdhnx 已提交
565 566 567 568 569 570
            pp = self.一级.split(';')
            def getPP(p,pn,pp,ppn):
                ps = pp[ppn] if p[pn] == '*' and len(pp) > ppn else p[pn]
                return ps
            p0 = getPP(p,0,pp,0)
            is_json = str(p0).startswith('json:')
H
hjdhnx 已提交
571 572
            if is_json:
                html = self.dealJson(html)
H
hjdhnx 已提交
573 574 575
            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
576 577 578



H
hjdhnx 已提交
579 580 581
            # print(html)
            try:
                if self.double:
H
hjdhnx 已提交
582
                    items = pdfa(html, p0.replace('json:',''))
H
hjdhnx 已提交
583
                    # print(p[0])
H
hjdhnx 已提交
584
                    # print(items)
H
hjdhnx 已提交
585
                    # print(len(items))
H
hjdhnx 已提交
586 587
                    for item in items:
                        items2 = pdfa(item,p[1])
H
hjdhnx 已提交
588
                        # print(len(items2))
H
hjdhnx 已提交
589 590
                        for item2 in items2:
                            try:
H
hjdhnx 已提交
591 592 593
                                p2 = getPP(p,2,pp,1)
                                title = pdfh(item2, p2)
                                # print(title)
H
hjdhnx 已提交
594
                                try:
H
hjdhnx 已提交
595 596
                                    p3 = getPP(p,3,pp,2)
                                    img = pd(item2, p3)
H
hjdhnx 已提交
597 598
                                except:
                                    img = ''
H
hjdhnx 已提交
599 600 601 602 603 604 605
                                try:
                                    p4 = getPP(p,4,pp,3)
                                    desc = pdfh(item2, p4)
                                except:
                                    desc = ''
                                p5 = getPP(p,5,pp,4)
                                links = [pd(item2, _p5) if not self.detailUrl else pdfh(item2, _p5) for _p5 in p5.split('+')]
H
hjdhnx 已提交
606
                                link = '$'.join(links)
H
hjdhnx 已提交
607 608 609 610 611
                                if len(p) > 6 and p[6]:
                                    p6 = getPP(p,6,pp,5)
                                    content = pdfh(item2, p6)
                                else:
                                    content = ''
H
hjdhnx 已提交
612 613 614 615 616 617 618 619 620 621 622 623 624 625
                                videos.append({
                                    "vod_id": link,
                                    "vod_name": title,
                                    "vod_pic": img,
                                    "vod_remarks": desc,
                                    "no_use":{
                                        "vod_content": content,
                                        "type_id": 1,
                                        "type_name": "首页推荐",
                                    },
                                })
                            except:
                                pass
                else:
H
hjdhnx 已提交
626
                    items = pdfa(html, p0.replace('json:',''))
H
hjdhnx 已提交
627 628
                    # print(items)
                    for item in items:
H
hjdhnx 已提交
629
                        try:
H
hjdhnx 已提交
630 631 632 633 634 635 636 637 638 639 640 641 642
                            p1 = getPP(p,1,pp,1)
                            title = pdfh(item, p1)
                            try:
                                p2 = getPP(p,2,pp,2)
                                img = pd(item, p2)
                            except:
                                img = ''
                            try:
                                p3 = getPP(p,3,pp,3)
                                desc = pdfh(item, p3)
                            except:
                                desc = ''
                            p4 = getPP(p,4,pp,4)
H
hjdhnx 已提交
643
                            # link = pd(item, p[4])
H
hjdhnx 已提交
644
                            links = [pd(item, _p5) if not self.detailUrl else pdfh(item, _p5) for _p5 in p4.split('+')]
H
hjdhnx 已提交
645
                            link = '$'.join(links)
H
hjdhnx 已提交
646 647 648 649 650
                            if len(p) > 5 and p[5]:
                                p5 = getPP(p,5,pp,5)
                                content = pdfh(item, p5)
                            else:
                                content = ''
H
hjdhnx 已提交
651 652 653 654 655
                            videos.append({
                                "vod_id": link,
                                "vod_name": title,
                                "vod_pic": img,
                                "vod_remarks": desc,
H
hjdhnx 已提交
656
                                "no_use": {
657 658 659 660
                                    "vod_content": content,
                                    "type_id": 1,
                                    "type_name": "首页推荐",
                                },
H
hjdhnx 已提交
661 662 663
                            })
                        except:
                            pass
H
hjdhnx 已提交
664

H
hjdhnx 已提交
665
            # result['list'] = videos[min((fypage-1)*self.limit,len(videos)-1):min(fypage*self.limit,len(videos))]
H
hjdhnx 已提交
666 667 668 669 670
            except Exception as e:
                logger.info(f'首页内容获取失败:{e}')
                return self.blank()

        result['list'] = videos
H
hjdhnx 已提交
671
        # print(videos)
H
hjdhnx 已提交
672 673 674 675 676 677 678 679 680 681 682
        result['no_use'] = {
            'code': 1,
            'msg': '数据列表',
            'page': fypage,
            'pagecount': math.ceil(len(videos) / self.limit),
            'limit': self.limit,
            'total': len(videos),
            'now_count': len(result['list']),
        }
        # print(result)
        return result
H
hjdhnx 已提交
683

H
hjdhnx 已提交
684
    def categoryContent(self, fyclass, fypage, fl=None):
H
hjdhnx 已提交
685 686 687 688
        """
        一级带分类的数据返回
        :param fyclass: 分类标识
        :param fypage: 页码
H
hjdhnx 已提交
689
        :param fl: 筛选
H
hjdhnx 已提交
690 691
        :return: cms一级数据
        """
H
hjdhnx 已提交
692 693 694

        if fl is None:
            fl = {}
H
hjdhnx 已提交
695 696 697 698 699 700 701 702 703 704 705 706
        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)
        # url = self.url + '/{0}.html'.format
        t1 = time()
        pg = str(fypage)
H
hjdhnx 已提交
707
        url = self.url.replace('fyclass',fyclass)
H
hjdhnx 已提交
708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723
        if self.filter_url:
            if not 'fyfilter' in url: # 第一种情况,默认不写fyfilter关键字,视为直接拼接在链接后面当参数
                if not url.endswith('&') and not self.filter_url.startswith('&'):
                    url += '&'
                url += self.filter_url
            else: # 第二种情况直接替换关键字为待拼接的结果后面渲染,适用于 ----fypage.html的情况
                url = url.replace('fyfilter', self.filter_url)
            url = render_template_string(url,fl=fl)

            # fl_url = render_template_string(self.filter_url,fl=fl)
            # if not 'fyfilter' in url: # 第一种情况,默认不写fyfilter关键字,视为直接拼接在链接后面当参数
            #     if not url.endswith('&') and not fl_url.startswith('&'):
            #         url += '&'
            #     url += fl_url
            # else: # 第二种情况直接替换关键字为渲染后的结果,适用于 ----fypage.html的情况
            #     url = url.replace('fyfilter',fl_url)
H
hjdhnx 已提交
724 725 726 727 728 729 730 731 732 733 734 735 736
        if url.find('fypage') > -1:
            if '(' in url and ')' in url:
                # url_rep = url[url.find('('):url.find(')')+1]
                # cnt_page = url.split('(')[1].split(')')[0].replace('fypage',pg)
                # print(url_rep)
                url_rep = re.search('.*?\((.*)\)',url,re.M|re.S).groups()[0]
                cnt_page = url_rep.replace('fypage', pg)
                # print(url_rep)
                # print(cnt_page)
                cnt_ctx = {}
                exec(f'cnt_pg={cnt_page}', cnt_ctx)
                cnt_pg = str(cnt_ctx['cnt_pg']) # 计算表达式的结果
                url = url.replace(url_rep,str(cnt_pg)).replace('(','').replace(')','')
H
hjdhnx 已提交
737
                # print(url)
H
hjdhnx 已提交
738 739
            else:
                url = url.replace('fypage',pg)
H
hjdhnx 已提交
740 741
        if fypage == 1 and self.test('[\[\]]',url):
            url = url.split('[')[1].split(']')[0]
H
hjdhnx 已提交
742 743
        elif fypage > 1 and self.test('[\[\]]',url):
            url = url.split('[')[0]
H
hjdhnx 已提交
744
        # print(url)
H
hjdhnx 已提交
745
        logger.info(url)
H
hjdhnx 已提交
746
        p = self.一级
H
hjdhnx 已提交
747 748
        jsp = jsoup(self.url)
        videos = []
H
hjdhnx 已提交
749 750 751 752 753
        is_js = isinstance(p, str) and str(p).startswith('js:')  # 是js
        if is_js:
            headers['Referer'] = getHome(url)
            py_ctx.update({
                'input': url,
H
hjdhnx 已提交
754
                'TYPE': 'cate',  # 海阔js环境标志
H
hjdhnx 已提交
755
                'oheaders': self.d.oheaders,
H
hjdhnx 已提交
756
                'fetch_params': {'headers': self.headers, 'timeout': self.d.timeout, 'encoding': self.d.encoding},
H
hjdhnx 已提交
757
                'd': self.d,
H
hjdhnx 已提交
758 759 760
                'MY_CATE':fyclass, # 分类id
                'MY_FL':fl, # 筛选
                'MY_PAGE':fypage,  # 页数
H
hjdhnx 已提交
761 762 763 764 765 766 767 768 769 770 771 772
                'detailUrl':self.detailUrl or '', # 详情页链接
                'getParse': self.d.getParse,
                'saveParse': self.d.saveParse,
                'jsp': jsp, 'setDetail': setDetail,
            })
            ctx = py_ctx
            # print(ctx)
            jscode = getPreJs() + p.replace('js:', '', 1)
            # print(jscode)
            loader, _ = runJScode(jscode, ctx=ctx)
            # print(loader.toString())
            vods = loader.eval('VODS')
H
hjdhnx 已提交
773
            # print('vods:',vods)
H
hjdhnx 已提交
774 775 776 777 778
            if isinstance(vods, JsObjectWrapper):
                videos = vods.to_list()

        else:
            p = p.split(';')  # 解析
H
hjdhnx 已提交
779
            # print(len(p))
H
hjdhnx 已提交
780 781 782 783 784 785 786 787 788 789 790 791
            if len(p) < 5:
                return self.blank()

            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
            # 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'))

            items = []
H
hjdhnx 已提交
792
            try:
H
hjdhnx 已提交
793
                r = requests.get(url, headers=self.headers, timeout=self.timeout,verify=False)
H
hjdhnx 已提交
794
                html = self.checkHtml(r)
H
hjdhnx 已提交
795
                print(self.headers)
H
hjdhnx 已提交
796
                # print(html)
H
hjdhnx 已提交
797
                if is_json:
H
hjdhnx 已提交
798
                    html = self.dealJson(html)
H
hjdhnx 已提交
799
                    html = json.loads(html)
H
hjdhnx 已提交
800
                # print(html)
H
hjdhnx 已提交
801 802
                # with open('1.html',mode='w+',encoding='utf-8') as f:
                #     f.write(html)
H
hjdhnx 已提交
803 804
                items = pdfa(html,p[0].replace('json:','',1))
            except:
H
hjdhnx 已提交
805
                pass
H
hjdhnx 已提交
806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829
            # print(items)
            for item in items:
                # print(item)
                try:
                    title = pdfh(item, p[1])
                    img = pd(item, p[2])
                    desc = pdfh(item, p[3])
                    links = [pd(item, p4) if not self.detailUrl else pdfh(item, p4) for p4 in p[4].split('+')]
                    link = '$'.join(links)
                    content = '' if len(p) < 6 else pdfh(item, p[5])
                    # sid = self.regStr(sid, "/video/(\\S+).html")
                    videos.append({
                        "vod_id": f'{fyclass}${link}' if self.detailUrl else link,# 分类,播放链接
                        "vod_name": title,
                        "vod_pic": img,
                        "vod_remarks": desc,
                        "vod_content": content,
                    })
                except Exception as e:
                    print(f'发生了错误:{e}')
                    pass
        # print(videos)
        limit = 40
        cnt = 9999 if len(videos) > 0 else 0
H
hjdhnx 已提交
830 831
        result['list'] = videos
        result['page'] = fypage
H
hjdhnx 已提交
832 833 834 835
        result['pagecount'] = max(cnt,fypage)
        result['limit'] = limit
        result['total'] = cnt
        # print(result)
H
hjdhnx 已提交
836
        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
837

H
hjdhnx 已提交
838 839
        return result

840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869
    def 二级渲染(self,parse_str:'str|dict',**kwargs):
        # *args是不定长参数 列表
        # ** args是不定长参数字典
        p = parse_str  # 二级传递解析表达式 js的obj json对象
        detailUrl = kwargs.get('detailUrl','') # 不定长字典传递的二级详情页vod_id原始数据
        url = kwargs.get('url','')  # 不定长字典传递的二级详情页链接智能拼接数据
        vod = kwargs.get('vod',self.blank_vod()) # 最终要返回的二级详情页数据 默认空
        html = kwargs.get('html','')  # 不定长字典传递的源码(如果不传才会在下面程序中去获取)
        show_name = kwargs.get('show_name','') # 是否显示来源(用于drpy区分)
        jsp = kwargs.get('jsp','')  # jsp = jsoup(self.url) 传递的jsp解析
        fyclass = kwargs.get('fyclass','') # 二级传递的分类名称,可以得知进去的类别
        if p == '*':  # 解析表达式为*默认一级直接变播放
            vod['vod_play_from'] = '道长在线'
            vod['vod_remarks'] = detailUrl
            vod['vod_actor'] = '没有二级,只有一级链接直接嗅探播放'
            # vod['vod_content'] = url if not show_name else f'({self.id}) {url}'
            vod['vod_content'] = url
            vod['vod_play_url'] = '嗅探播放$' + self.play_url + url

        elif not p or (not isinstance(p, dict) and not isinstance(p, str)) or (isinstance(p, str) and not str(p).startswith('js:')):
            pass
        else:
            is_json = p.get('is_json', False) if isinstance(p, dict) else 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
            pq = jsp.pq
            obj = {}
            vod_name = ''
            if not html: # 没传递html参数接下来智能获取
H
hjdhnx 已提交
870
                r = requests.get(url, headers=self.headers, timeout=self.timeout,verify=False)
871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920
                html = self.checkHtml(r)
                if is_json:
                    html = self.dealJson(html)
                    html = json.loads(html)
            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])
                title = '\n'.join([','.join([pdfh(html, pp1).strip() for pp1 in i.split('+')]) for i in p1])
                # print(title)
                obj['title'] = title
            if p.get('desc'):
                try:
                    p1 = p['desc'].split(';')
                    desc = '\n'.join([pdfh(html, i).replace('\n', ' ') for i in p1])
                    obj['desc'] = desc
                except:
                    pass

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

            if p.get('img'):
                p1 = p['img']
                try:
                    img = pd(html, p1)
                    obj['img'] = img
                except Exception as e:
                    logger.info(f'二级图片定位失败,但不影响使用{e}')

            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 = []
H
hjdhnx 已提交
921 922
            init_flag = {'ctx':False}
            def js_pre():
923 924 925 926 927
                headers['Referer'] = getHome(url)
                py_ctx.update({
                    'input': url,
                    'html': html,
                    'TYPE': 'detail',  # 海阔js环境标志
H
hjdhnx 已提交
928
                    'MY_CATE': fyclass,  # 分类id
929 930 931 932 933
                    'oheaders': self.d.oheaders,
                    'fetch_params': {'headers': self.headers, 'timeout': self.d.timeout, 'encoding': self.d.encoding},
                    'd': self.d,
                    'getParse': self.d.getParse,
                    'saveParse': self.d.saveParse,
H
hjdhnx 已提交
934
                    'jsp': jsp, 'setDetail': setDetail,'play_url':self.play_url
935
                })
H
hjdhnx 已提交
936 937 938 939
                init_flag['ctx'] = True
            if p.get('重定向') and str(p['重定向']).startswith('js:'):
                if not init_flag['ctx']:
                    js_pre()
940 941 942 943 944 945 946 947 948 949 950 951 952 953
                ctx = py_ctx
                # print(ctx)
                rcode = p['重定向'].replace('js:', '', 1)
                jscode = getPreJs() + rcode
                # print(jscode)
                loader, _ = runJScode(jscode, ctx=ctx)
                # print(loader.toString())
                logger.info(f'开始执行二级重定向代码:{rcode}')
                html = loader.eval('html')
                if isinstance(vod, JsObjectWrapper):
                    html = str(html)

            if p.get('tabs'):
                vodHeader = []
H
hjdhnx 已提交
954 955 956 957 958 959 960 961 962 963 964 965 966
                if str(p['tabs']).startswith('js:'):
                    if not init_flag['ctx']:
                        js_pre()
                    ctx = py_ctx
                    rcode = p['tabs'].replace('js:', '', 1)
                    jscode = getPreJs() + rcode
                    # print(jscode)
                    loader, _ = runJScode(jscode, ctx=ctx)
                    # print(loader.toString())
                    logger.info(f'开始执行tabs代码:{rcode}')
                    vHeader = loader.eval('TABS')
                    if isinstance(vod, JsObjectWrapper):
                        vHeader = vHeader.to_list()
967
                    vodHeader = vHeader
H
hjdhnx 已提交
968 969 970 971 972 973 974 975 976 977 978 979 980 981
                else:
                    # print(p['tabs'].split(';')[0])
                    vHeader = pdfa(html, p['tabs'].split(';')[0])
                    # print(f'线路列表数:{len((vodHeader))}')
                    # print(vodHeader)
                    if not is_json:
                        for v in vHeader:
                            # 过滤排除掉线路标题
                            v_title = pq(v).text()
                            if self.tab_exclude and jsp.test(self.tab_exclude, v_title):
                                continue
                            vodHeader.append(v_title)
                    else:
                        vodHeader = vHeader
982 983 984 985 986 987 988 989 990 991 992 993
            else:
                vodHeader = ['道长在线']

            # print(vodHeader)

            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'):
H
hjdhnx 已提交
994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030
                if str(p['lists']).startswith('js:'):
                    if not init_flag['ctx']:
                        js_pre()
                    ctx = py_ctx
                    ctx['TABS'] = vodHeader # 把选集列表传过去
                    rcode = p['lists'].replace('js:', '', 1)
                    jscode = getPreJs() + rcode
                    # print(jscode)
                    loader, _ = runJScode(jscode, ctx=ctx)
                    # print(loader.toString())
                    logger.info(f'开始执行lists代码:{rcode}')
                    vlists = loader.eval('LISTS')
                    if isinstance(vod, JsObjectWrapper):
                        vlists = vlists.to_list() # [['第1集$http://1.mp4','第2集$http://2.mp4'],['第3集$http://1.mp4','第4集$http://2.mp4']]

                    vod_play_url = vod_play_url.join(list(map(lambda x:'#'.join(x),vlists)))
                else:
                    for i in range(len(vodHeader)):
                        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))
                        vodList = pdfa(html, p1)  # 1条线路的选集列表
                        # print(vodList)
                        # vodList = [pq(i).text()+'$'+pd(i,'a&&href') for i in vodList]  # 拼接成 名称$链接
                        if self.play_parse:  # 自动base64编码
                            vodList = [(pdfh(html, tab_ext) if tab_ext else tab_name) + '$' + self.play_url + encodeUrl(i) for i
                                       in vodList] if is_json else \
                                [pq(i).text() + '$' + self.play_url + encodeUrl(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
                        vlist = '#'.join(vodList)  # 拼多个选集
                        vod_tab_list.append(vlist)
                    vod_play_url = vod_play_url.join(vod_tab_list)

H
hjdhnx 已提交
1031
            print(vod_play_url)
1032 1033 1034 1035 1036 1037 1038 1039
            vod['vod_play_from'] = vod_play_from
            # print(vod_play_from)
            vod['vod_play_url'] = vod_play_url

        if show_name:
            vod['vod_content'] = f'({self.id}){vod.get("vod_content", "")}'
        return vod

H
hjdhnx 已提交
1040
    def detailOneVod(self,id,fyclass='',show_name=False):
1041
        vod = self.blank_vod()
H
hjdhnx 已提交
1042
        detailUrl = str(id)
H
hjdhnx 已提交
1043
        # print(detailUrl)
H
hjdhnx 已提交
1044
        if not detailUrl.startswith('http') and not '/' in detailUrl:
H
hjdhnx 已提交
1045
            url = self.detailUrl.replace('fyid', detailUrl).replace('fyclass',fyclass)
H
hjdhnx 已提交
1046
            # print(url)
H
hjdhnx 已提交
1047 1048
        elif '/' in detailUrl:
            url = urljoin(self.homeUrl,detailUrl)
H
hjdhnx 已提交
1049 1050
        else:
            url = detailUrl
H
hjdhnx 已提交
1051
        logger.info(f'进入详情页: {url}')
H
hjdhnx 已提交
1052 1053 1054 1055 1056 1057 1058 1059
        try:
            p = self.二级  # 解析
            jsp = jsoup(self.url)
            is_js = isinstance(p,str) and str(p).startswith('js:') # 是js
            if is_js:
                headers['Referer'] = getHome(url)
                py_ctx.update({
                    'input': url,
H
hjdhnx 已提交
1060
                    'TYPE': 'detail',  # 海阔js环境标志
H
hjdhnx 已提交
1061
                    # 'VID': id,  # 传递的vod_id
1062
                    '二级': self.二级渲染,  # 二级解析函数,可以解析dict
H
hjdhnx 已提交
1063
                    'MY_CATE': fyclass,  # 分类id
H
hjdhnx 已提交
1064
                    'oheaders': self.d.oheaders,
H
hjdhnx 已提交
1065
                    'fetch_params': {'headers': self.headers, 'timeout': self.d.timeout, 'encoding': self.d.encoding},
H
hjdhnx 已提交
1066 1067 1068
                    'd': self.d,
                    'getParse': self.d.getParse,
                    'saveParse': self.d.saveParse,
H
优化  
hjdhnx 已提交
1069
                    'jsp':jsp,'setDetail':setDetail,'play_url':self.play_url
H
hjdhnx 已提交
1070 1071 1072 1073 1074 1075 1076
                })
                ctx = py_ctx
                # print(ctx)
                jscode = getPreJs() + p.replace('js:','',1)
                # print(jscode)
                loader, _ = runJScode(jscode, ctx=ctx)
                # print(loader.toString())
1077
                vod = loader.eval('VOD')
H
hjdhnx 已提交
1078 1079
                if isinstance(vod,JsObjectWrapper):
                    vod = vod.to_dict()
1080 1081
                    if show_name:
                        vod['vod_content'] = f'({self.id}){vod.get("vod_content", "")}'
H
hjdhnx 已提交
1082
                else:
1083
                    vod = self.blank_vod()
H
hjdhnx 已提交
1084
            else:
1085
                vod = self.二级渲染(p,detailUrl=detailUrl,url=url,vod=vod,show_name=show_name,jsp=jsp,fyclass=fyclass)
H
hjdhnx 已提交
1086 1087
        except Exception as e:
            logger.info(f'{self.getName()}获取单个详情页{detailUrl}出错{e}')
1088

H
hjdhnx 已提交
1089 1090
        return vod

H
hjdhnx 已提交
1091
    def detailContent(self, fypage, array,show_name=False):
H
hjdhnx 已提交
1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108
        """
        cms二级数据
        :param array:
        :return:
        """
        t1 = time()
        array = array if len(array) <= self.limit else 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 = []
        try:
            for vod_url in array:
                # print(vod_url)
                vod_class = ''
                if vod_url.find('$') > -1:
                    tmp = vod_url.split('$')
                    vod_class = tmp[0]
                    vod_url = tmp[1]
H
hjdhnx 已提交
1109
                obj = thread_pool.submit(self.detailOneVod, vod_url,vod_class,show_name)
H
hjdhnx 已提交
1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121
                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
1122
        # print(result)
H
hjdhnx 已提交
1123 1124
        return result

H
hjdhnx 已提交
1125
    def searchContent(self, key, fypage=1,show_name=False):
H
hjdhnx 已提交
1126 1127 1128 1129 1130 1131 1132
        pg = str(fypage)
        if not self.searchUrl:
            return self.blank()
        url = self.searchUrl.replace('**', key).replace('fypage',pg)
        logger.info(f'{self.getName()}搜索链接:{url}')
        if not self.搜索:
            return self.blank()
H
hjdhnx 已提交
1133 1134
        # p = self.一级.split(';') if self.搜索 == '*' and self.一级 else self.搜索.split(';')  # 解析
        p = self.一级 if self.搜索 == '*' and self.一级 else self.搜索
H
hjdhnx 已提交
1135
        pp = self.一级.split(';')
H
hjdhnx 已提交
1136 1137
        jsp = jsoup(self.url)
        videos = []
H
hjdhnx 已提交
1138
        is_js = isinstance(p, str) and str(p).startswith('js:')  # 是js
H
hjdhnx 已提交
1139 1140 1141 1142

        def getPP(p, pn, pp, ppn):
            ps = pp[ppn] if p[pn] == '*' and len(pp) > ppn else p[pn]
            return ps
H
hjdhnx 已提交
1143 1144 1145 1146
        if is_js:
            headers['Referer'] = getHome(url)
            py_ctx.update({
                'input': url,
H
hjdhnx 已提交
1147
                'oheaders': self.d.oheaders,
H
hjdhnx 已提交
1148
                'fetch_params': {'headers': self.headers, 'timeout': self.d.timeout, 'encoding': self.d.encoding},
H
hjdhnx 已提交
1149
                'd': self.d,
H
hjdhnx 已提交
1150
                'MY_PAGE': fypage,
H
hjdhnx 已提交
1151
                'KEY': key,  # 搜索关键字
H
hjdhnx 已提交
1152
                'TYPE': 'search',  # 海阔js环境标志
H
hjdhnx 已提交
1153 1154
                'detailUrl': self.detailUrl or '',
                # 详情页链接
H
hjdhnx 已提交
1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165
                'getParse': self.d.getParse,
                'saveParse': self.d.saveParse,
                'jsp': jsp, 'setDetail': setDetail,
            })
            ctx = py_ctx
            # print(ctx)
            jscode = getPreJs() + p.replace('js:', '', 1)
            # print(jscode)
            loader, _ = runJScode(jscode, ctx=ctx)
            # print(loader.toString())
            vods = loader.eval('VODS')
H
hjdhnx 已提交
1166
            # print(len(vods),type(vods))
H
hjdhnx 已提交
1167 1168
            if isinstance(vods, JsObjectWrapper):
                videos = vods.to_list()
H
hjdhnx 已提交
1169
            # print(videos)
H
hjdhnx 已提交
1170 1171 1172 1173 1174 1175 1176 1177 1178 1179
        else:
            p = p.split(';')
            if len(p) < 5:
                return self.blank()
            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
            pq = jsp.pq
            try:
H
hjdhnx 已提交
1180
                r = requests.get(url, headers=self.headers,timeout=self.timeout,verify=False)
H
hjdhnx 已提交
1181 1182
                html = self.checkHtml(r)
                if is_json:
H
hjdhnx 已提交
1183
                    html = self.dealJson(html)
H
hjdhnx 已提交
1184
                    html = json.loads(html)
H
hjdhnx 已提交
1185

H
hjdhnx 已提交
1186 1187
                # if not is_json and html.find('输入验证码') > -1:
                if not is_json and re.search('系统安全验证|输入验证码',html,re.M|re.S):
H
hjdhnx 已提交
1188 1189 1190 1191 1192 1193 1194 1195
                    cookie = verifyCode(url,self.headers,self.timeout,self.retry_count,self.ocr_api)
                    # cookie = ''
                    if not cookie:
                        return {
                            'list': videos
                        }
                    self.saveCookie(cookie)
                    self.headers['cookie'] = cookie
H
hjdhnx 已提交
1196
                    r = requests.get(url, headers=self.headers, timeout=self.timeout,verify=False)
H
hjdhnx 已提交
1197 1198
                    r.encoding = self.encoding
                    html = r.text
H
hjdhnx 已提交
1199
                if not show_name and not str(html).find(key) > -1:
H
hjdhnx 已提交
1200 1201
                    logger.info('搜索结果源码未包含关键字,疑似搜索失败,正为您打印结果源码')
                    print(html)
H
hjdhnx 已提交
1202

H
hjdhnx 已提交
1203 1204
                p0 = getPP(p,0,pp,0)
                items = pdfa(html,p0.replace('json:','',1))
H
hjdhnx 已提交
1205
                # print(len(items),items)
H
hjdhnx 已提交
1206 1207 1208
                videos = []
                for item in items:
                    # print(item)
H
hjdhnx 已提交
1209
                    try:
H
hjdhnx 已提交
1210
                        # title = pdfh(item, p[1])
H
hjdhnx 已提交
1211 1212
                        p1 = getPP(p, 1, pp, 1)
                        title = ''.join([pdfh(item, i) for i in p1.split('||')])
H
hjdhnx 已提交
1213
                        try:
H
hjdhnx 已提交
1214 1215
                            p2 = getPP(p, 2, pp, 2)
                            img = pd(item, p2)
H
hjdhnx 已提交
1216 1217 1218
                        except:
                            img = ''
                        try:
H
hjdhnx 已提交
1219 1220
                            p3 = getPP(p, 3, pp, 3)
                            desc = pdfh(item, p3)
H
hjdhnx 已提交
1221 1222
                        except:
                            desc = ''
H
hjdhnx 已提交
1223 1224 1225 1226
                        if len(p) > 5 and p[5]:
                            p5 = getPP(p, 5, pp, 5)
                            content = pdfh(item, p5)
                        else:
H
hjdhnx 已提交
1227 1228
                            content = ''
                        # link = '$'.join([pd(item, p4) for p4 in p[4].split('+')])
H
hjdhnx 已提交
1229 1230
                        p4 = getPP(p, 4, pp, 4)
                        links = [pd(item, _p4) if not self.detailUrl else pdfh(item, _p4) for _p4 in p4.split('+')]
H
hjdhnx 已提交
1231 1232 1233 1234 1235 1236 1237 1238 1239 1240
                        link = '$'.join(links)
                        # print(content)
                        # sid = self.regStr(sid, "/video/(\\S+).html")
                        videos.append({
                            "vod_id": link,
                            "vod_name": title,
                            "vod_pic": img,
                            "vod_remarks": desc,
                            "vod_content": content, # 无用参数
                        })
H
hjdhnx 已提交
1241
                    except Exception as e:
H
hjdhnx 已提交
1242
                        print(f'搜索列表解析发生错误:{e}')
H
hjdhnx 已提交
1243 1244 1245 1246
                        pass
                # print(videos)
            except Exception as e:
                logger.info(f'搜索{self.getName()}发生错误:{e}')
H
hjdhnx 已提交
1247 1248 1249 1250 1251
        if show_name and len(videos) > 0:
            for video in videos:
                video['vod_name'] = self.id + ' '+video['vod_name']
                video['vod_rule'] = self.id
                video['vod_id'] = video['vod_id'] +'#' + self.id
H
hjdhnx 已提交
1252 1253 1254 1255 1256 1257
        result = {
            'list': videos
        }
        return result

    def playContent(self, play_url,jxs=None,flag=None):
1258
        # flag参数只有类型为4的时候才有,可以忽略
H
hjdhnx 已提交
1259
        # logger.info('播放免嗅地址: ' + self.play_url)
1260
        # 注意:全局flags里的视频没法执行免嗅代码,因为会自动拦截去调用解析: url=yoursite:5705/vod?play_url=xxxx
H
hjdhnx 已提交
1261 1262
        if not jxs:
            jxs = []
H
hjdhnx 已提交
1263

H
hjdhnx 已提交
1264 1265 1266 1267 1268 1269
        # print(play_url)
        if play_url.find('http') == -1: # 字符串看起来被编码的
            try:
                play_url = baseDecode(play_url) # 自动base64解码
            except:
                pass
H
hjdhnx 已提交
1270 1271
        # print(unquote(play_url))
        play_url = unquote(play_url)
H
hjdhnx 已提交
1272 1273
        origin_play_url = play_url
        print(origin_play_url)
H
hjdhnx 已提交
1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294
        if self.lazy:
            print(f'{play_url}->开始执行免嗅代码{type(self.lazy)}->{self.lazy}')
            t1 = time()
            try:
                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:'):
                    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]
H
hjdhnx 已提交
1295
                    jsp = jsoup(self.url)
H
hjdhnx 已提交
1296 1297 1298 1299 1300
                    # jscode = f'var input={play_url};{jscode}'
                    # print(jscode)
                    headers['Referer'] = getHome(play_url)
                    py_ctx.update({
                        'input': play_url,
H
hjdhnx 已提交
1301
                        'oheaders': self.d.oheaders,
H
hjdhnx 已提交
1302
                        'fetch_params':{'headers':self.headers,'timeout':self.d.timeout,'encoding':self.d.encoding},
H
hjdhnx 已提交
1303 1304 1305 1306
                        'd': self.d,
                        'jxs':jxs,
                        'getParse':self.d.getParse,
                        'saveParse':self.d.saveParse,
H
hjdhnx 已提交
1307
                        'jsp': jsp,
H
hjdhnx 已提交
1308
                        'pdfh': self.d.jsp.pdfh,
H
优化  
hjdhnx 已提交
1309
                        'pdfa': self.d.jsp.pdfa, 'pd': self.d.jsp.pd,'play_url':self.play_url
H
hjdhnx 已提交
1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322
                    })
                    ctx = py_ctx
                    # print(ctx)
                    jscode = getPreJs() + jscode
                    # print(jscode)
                    loader,_ = runJScode(jscode,ctx=ctx)
                    # print(loader.toString())
                    play_url = loader.eval('input')
                    if isinstance(play_url,JsObjectWrapper):
                        play_url = play_url.to_dict()
                    # print(type(play_url))
                    # print(play_url)
                    logger.info(f'js免嗅耗时:{get_interval(t1)}毫秒,播放地址:{play_url}')
H
hjdhnx 已提交
1323 1324 1325 1326
                    if not play_url and play_url!='' and play_url!={}:
                        play_url = origin_play_url
                    # if play_url == {}:
                    #     play_url = None
H
hjdhnx 已提交
1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341
            except Exception as e:
                logger.info(f'免嗅耗时:{get_interval(t1)}毫秒,并发生错误:{e}')
            return play_url
        else:
            logger.info(f'播放重定向到:{play_url}')
            return play_url

if __name__ == '__main__':
    print(urljoin('https://api.web.360kan.com/v1/f',
                  '//0img.hitv.com/preview/sp_images/2022/01/28/202201281528074643023.jpg'))
    # exit()
    from utils import parser
    # js_path = f'js/玩偶姐姐.js'
    # js_path = f'js/555影视.js'
    with open('../js/模板.js', encoding='utf-8') as f:
H
hjdhnx 已提交
1342
        before = f.read().split('export')[0]
H
hjdhnx 已提交
1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360
    js_path = f'js/360影视.js'
    ctx, js_code = parser.runJs(js_path,before=before)
    ruleDict = ctx.rule.to_dict()
    # lazy = ctx.eval('lazy')
    # print(lazy)
    # ruleDict['id'] = rule  # 把路由请求的id装到字典里,后面播放嗅探才能用

    cms = CMS(ruleDict)
    print(cms.title)
    print(cms.homeContent())
    # print(cms.categoryContent('5',1))
    # print(cms.categoryContent('latest',1))
    # print(cms.detailContent(['https://www.2345ka.com/v/45499.html']))
    # print(cms.detailContent(1,['https://cokemv.me/voddetail/40573.html']))
    # cms.categoryContent('dianying',1)
    # print(cms.detailContent(['67391']))
    # print(cms.searchContent('斗罗大陆'))
    print(cms.searchContent('独行月球'))