tvbox/PyramidStore/plugin/adult/Phb.py

# -*- coding: utf-8 -*-
# by @嗷呜
import json
import re
import sys
from base64 import b64decode, b64encode
from urllib.parse import urlparse

import requests
from pyquery import PyQuery as pq
from requests import Session
sys.path.append('..')
from base.spider import Spider

class Spider(Spider):

    def init(self, extend=""):
        '''
        内置代理配置：真心jar为例
        {
            "key": "Phb",
            "name": "Phb",
            "type": 3,
            "searchable": 1,
            "quickSearch": 1,
            "filterable": 1,
            "api": "./py/Phb.py",
            "ext": {
                "http": "http://127.0.0.1:1072",
                "https": "http://127.0.0.1:1072"
            }
        },
        注：http(s)代理都是http
        '''
        try:self.proxies = json.loads(extend)
        except:self.proxies = {}
        self.headers = {
            'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.5410.0 Safari/537.36',
            'pragma': 'no-cache',
            'cache-control': 'no-cache',
            'sec-ch-ua-platform': '"Windows"',
            'sec-ch-ua': '"Not(A:Brand";v="99", "Google Chrome";v="133", "Chromium";v="133"',
            'dnt': '1',
            'sec-ch-ua-mobile': '?0',
            'sec-fetch-site': 'cross-site',
            'sec-fetch-mode': 'cors',
            'sec-fetch-dest': 'empty',
            'accept-language': 'zh-CN,zh;q=0.9,en;q=0.8',
            'priority': 'u=1, i',
        }
        self.host = self.gethost()
        self.headers.update({'referer': f'{self.host}/', 'origin': self.host})
        self.session = Session()
        self.session.proxies.update(self.proxies)
        self.session.headers.update(self.headers)

        # ====== 在这里处理并传入指定的 Cookie ======
        # 你提供的 Cookie 字符串
        cookie_string = "KEY=2800769*3022907:116762244:2236104702:1; platform=mobile; ss=830813246555776814; sessid=300353306947678113; comp_detect-cookies=13166.100000; fg_afaf12e4c5419a855dd0bf120670f=41719.100000; fg_757a7e3b2b97e62caeae14647b10ab8a=62682.100000; fg_63bebf99a35b4f802b2ee7589fece7c6=48941.100000; fg_7d466c3b3b825a5e5f974868b9d87c01=43396.100000; fg_7d31324eedb583147b6dcbea0051c868=81750.100000; __s=683BD997-42FE722901BB234E92-52ADB4D; __l=683BD997-42FE722901BB234E92-52ADB4D; _ga=GA1.1.865788991.1748752797; accessAgeDisclaimerPH=1; googtrans=/auto/zh-CN; googtrans=/auto/zh-CN; ua=5088e51afb755e3294a3359f17dd8eee; il=v11msoKzX_h0h258sWpnEAzxOpywRHt3No__oI88GHuIUxNzY0Njk2NzIzOVY2Q1c2d2l2eGp4T19pOW5CVV9JSU1FQ0NGWW01YWlLNnZ5Y251LQ..; cookieConsent=2; bs=e1649232670c3a49db241055d6ccf891; bsdd=e1649232670c3a49db241055d6ccf891; htjf-mobile=3; tj_UUID=ChBNOIxil6REvZRCDWP3pmmCEgwIjYi1vgYQmfiBowEYASIgZTE2NDkyMzI2NzBjM2E0OWRiMjQxMDU1ZDZjY2Y4OTE=; tj_UUID_v2=ChBNOIxil6REvZRCDWP3pmmCEgwIjYi1vgYQmfiBowEYASIgZTE2NDkyMzI2NzBjM2E0OWRiMjQxMDU1ZDZjY2Y4OTE=; _ga_B39RFFWGYY=GS2.1.s1748884900$o2$g1$t1748885526$j58$l0$h0"

        # 将 Cookie 字符串解析为字典
        parsed_cookies = {}
        for part in cookie_string.split('; '):
            if '=' in part:
                key, value = part.split('=', 1) # 只在第一个等号处分割，因为值可能包含等号
                parsed_cookies[key.strip()] = value.strip() # strip() 用于去除可能存在的空格

        self.session.cookies.update(parsed_cookies)
        # ==================================

        pass

    def getName(self):
        pass

    def isVideoFormat(self, url):
        pass

    def manualVideoCheck(self):
        pass

    def destroy(self):
        pass

    def homeContent(self, filter):
        result = {}
        cateManual = {
            "推荐": "/recommended",
            "视频": "/video",
            "片单": "/playlists",
            "频道": "/channels",
            "分类": "/categories",
            "明星": "/pornstars"
        }
        classes = []
        filters = {}
        for k in cateManual:
            classes.append({
                'type_name': k,
                'type_id': cateManual[k]
            })
        result['class'] = classes
        result['filters'] = filters
        return result

    def homeVideoContent(self):
        # data = self.getpq('/recommended')
        # vhtml = data("#recommendedListings .pcVideoListItem .phimage")
        # return {'list': self.getlist(vhtml)}
        pass

    def categoryContent(self, tid, pg, filter, extend):
        vdata = []
        result = {}
        result['page'] = pg
        result['pagecount'] = 9999
        result['limit'] = 90
        result['total'] = 999999
        if tid == '/video' or '_this_video' in tid:
            pagestr = f'&' if '?' in tid else f'?'
            tid = tid.split('_this_video')[0]
            data = self.getpq(f'{tid}{pagestr}page={pg}')
            vdata = self.getlist(data('#videoCategory .pcVideoListItem'))
        elif tid == '/recommended':
            data = self.getpq(f'{tid}?page={pg}')    
            vdata = self.getlist(data('#recommendedListings .pcVideoListItem .phimage'))
        elif tid == '/playlists':
            data = self.getpq(f'{tid}?page={pg}')
            vhtml = data('#playListSection li')
            vdata = []
            for i in vhtml.items():
                vdata.append({
                    'vod_id': 'playlists_click_' + i('.thumbnail-info-wrapper .display-block a').attr('href'),
                    'vod_name': i('.thumbnail-info-wrapper .display-block a').attr('title'),
                    'vod_pic': self.proxy(i('.largeThumb').attr('src')),
                    'vod_tag': 'folder',
                    'vod_remarks': i('.playlist-videos .number').text(),
                    'style': {"type": "rect", "ratio": 1.33}
                })
        elif tid == '/channels':
            data = self.getpq(f'{tid}?o=rk&page={pg}')
            vhtml = data('#filterChannelsSection li .description')
            vdata = []
            for i in vhtml.items():
                vdata.append({
                    'vod_id': 'director_click_' + i('.avatar a').attr('href'),
                    'vod_name': i('.avatar img').attr('alt'),
                    'vod_pic': self.proxy(i('.avatar img').attr('src')),
                    'vod_tag': 'folder',
                    'vod_remarks': i('.descriptionContainer ul li').eq(-1).text(),
                    'style': {"type": "rect", "ratio": 1.33}
                })
        elif tid == '/categories' and pg == '1':
            result['pagecount'] = 1
            data = self.getpq(f'{tid}')
            vhtml = data('.categoriesListSection li .relativeWrapper')
            vdata = []
            for i in vhtml.items():
                vdata.append({
                    'vod_id': i('a').attr('href') + '_this_video',
                    'vod_name': i('a').attr('alt'),
                    'vod_pic': self.proxy(i('a img').attr('src')),
                    'vod_tag': 'folder',
                    'style': {"type": "rect", "ratio": 1.33}
                })
        elif tid == '/pornstars':
            data = self.getpq(f'{tid}?o=t&page={pg}')
            vhtml = data('#popularPornstars .performerCard .wrap')
            vdata = []
            for i in vhtml.items():
                vdata.append({
                    'vod_id': 'pornstars_click_' + i('a').attr('href'),
                    'vod_name': i('.performerCardName').text(),
                    'vod_pic': self.proxy(i('a img').attr('src')),
                    'vod_tag': 'folder',
                    'vod_year': i('.performerVideosViewsCount span').eq(0).text(),
                    'vod_remarks': i('.performerVideosViewsCount span').eq(-1).text(),
                    'style': {"type": "rect", "ratio": 1.33}
                })
        elif 'playlists_click' in tid:
            tid = tid.split('click_')[-1]
            if pg == '1':
                hdata = self.getpq(tid)
                self.token = hdata('#searchInput').attr('data-token')
                vdata = self.getlist(hdata('#videoPlaylist .pcVideoListItem .phimage'))
            else:
                tid = tid.split('playlist/')[-1]
                data = self.getpq(f'/playlist/viewChunked?id={tid}&token={self.token}&page={pg}')
                vdata = self.getlist(data('.pcVideoListItem .phimage'))
        elif 'director_click' in tid:
            tid = tid.split('click_')[-1]
            data = self.getpq(f'{tid}/videos?page={pg}')
            vdata = self.getlist(data('#showAllChanelVideos .pcVideoListItem .phimage'))
        elif 'pornstars_click' in tid:
            tid = tid.split('click_')[-1]
            data = self.getpq(f'{tid}/videos?page={pg}')
            vdata = self.getlist(data('#mostRecentVideosSection .pcVideoListItem .phimage'))
        result['list'] = vdata
        return result

    def detailContent(self, ids):
        url = f"{self.host}{ids[0]}"
        data = self.getpq(ids[0])
        vn = data('meta[property="og:title"]').attr('content')
        dtext = data('.userInfo .usernameWrap a')
        pdtitle = '[a=cr:' + json.dumps(
            {'id': 'director_click_' + dtext.attr('href'), 'name': dtext.text()}) + '/]' + dtext.text() + '[/a]'
        vod = {
            'vod_name': vn,
            'vod_director': pdtitle,
            'vod_remarks': (data('.userInfo').text() + ' / ' + data('.ratingInfo').text()).replace('\n', ' / '),
            'vod_play_from': 'Pornhub',
            'vod_play_url': ''
        }
        js_content = data("#player script").eq(0).text()
        plist = [f"{vn}${self.e64(f'{1}@@@@{url}')}"]
        try:
            pattern = r'"mediaDefinitions":\s*(\[.*?\]),\s*"isVertical"'
            match = re.search(pattern, js_content, re.DOTALL)
            if match:
                json_str = match.group(1)
                udata = json.loads(json_str)
                plist = [
                    f"{media['height']}${self.e64(f'{0}@@@@{url}')}"
                    for media in udata[:-1]
                    if (url := media.get('videoUrl'))
                ]
        except Exception as e:
            print(f"提取mediaDefinitions失败: {str(e)}")
        vod['vod_play_url'] = '#'.join(plist)
        return {'list': [vod]}

    def searchContent(self, key, quick, pg="1"):
        data = self.getpq(f'/video/search?search={key}&page={pg}')
        return {'list': self.getlist(data('#videoSearchResult .pcVideoListItem .phimage'))}

    def playerContent(self, flag, id, vipFlags):
        ids = self.d64(id).split('@@@@')
        if '.m3u8' in ids[1]: ids[1] = self.proxy(ids[1], 'm3u8')
        return {'parse': int(ids[0]), 'url': ids[1], 'header': self.headers}

    def localProxy(self, param):
        url = self.d64(param.get('url'))
        if param.get('type') == 'm3u8':
            return self.m3Proxy(url)
        else:
            return self.tsProxy(url)

    def m3Proxy(self, url):
        ydata = requests.get(url, headers=self.headers, proxies=self.proxies, allow_redirects=False)
        data = ydata.content.decode('utf-8')
        if ydata.headers.get('Location'):
            url = ydata.headers['Location']
            data = requests.get(url, headers=self.headers, proxies=self.proxies).content.decode('utf-8')
        lines = data.strip().split('\n')
        last_r = url[:url.rfind('/')]
        parsed_url = urlparse(url)
        durl = parsed_url.scheme + "://" + parsed_url.netloc
        for index, string in enumerate(lines):
            if '#EXT' not in string:
                if 'http' not in string:
                    domain = last_r if string.count('/') < 2 else durl
                    string = domain + ('' if string.startswith('/') else '/') + string
                lines[index] = self.proxy(string, string.split('.')[-1].split('?')[0])
        data = '\n'.join(lines)
        return [200, "application/vnd.apple.mpegur", data]

    def tsProxy(self, url):
        data = requests.get(url, headers=self.headers, proxies=self.proxies, stream=True)
        return [200, data.headers['Content-Type'], data.content]

    def gethost(self):
        try:
            response = requests.get('https://www.pornhub.com', headers=self.headers, proxies=self.proxies,
                                    allow_redirects=False)
            return response.headers['Location'][:-1]
        except Exception as e:
            print(f"获取主页失败: {str(e)}")
            return "https://www.pornhub.com"

    def e64(self, text):
        try:
            text_bytes = text.encode('utf-8')
            encoded_bytes = b64encode(text_bytes)
            return encoded_bytes.decode('utf-8')
        except Exception as e:
            print(f"Base64编码错误: {str(e)}")
            return ""

    def d64(self, encoded_text):
        try:
            encoded_bytes = encoded_text.encode('utf-8')
            decoded_bytes = b64decode(encoded_bytes)
            return decoded_bytes.decode('utf-8')
        except Exception as e:
            print(f"Base64解码错误: {str(e)}")
            return ""

    def getlist(self, data):
        vlist = []
        for i in data.items():
            vlist.append({
                'vod_id': i('a').attr('href'),
                'vod_name': i('a').attr('title'),
                'vod_pic': self.proxy(i('img').attr('src')),
                'vod_remarks': i('.bgShadeEffect').text() or i('.duration').text(),
                'style': {'ratio': 1.33, 'type': 'rect'}
            })
        return vlist

    def getpq(self, path):
        try:
            response = self.session.get(f'{self.host}{path}').text
            return pq(response.encode('utf-8'))
        except Exception as e:
            print(f"请求失败: , {str(e)}")
            return None

    def proxy(self, data, type='img'):
        if data and len(self.proxies):return f"{self.getProxyUrl()}&url={self.e64(data)}&type={type}"
        else:return data