diff --git a/jtxtv09/py/AppToV5.py b/jtxtv09/py/AppToV5.py new file mode 100644 index 0000000..a0830b2 --- /dev/null +++ b/jtxtv09/py/AppToV5.py @@ -0,0 +1,187 @@ +# -*- coding: utf-8 -*- +# 本资源来源于互联网公开渠道，仅可用于个人学习及爬虫技术交流。 +# 严禁将其用于任何商业用途，下载后请于 24 小时内删除，搜索结果均来自源站，本人不承担任何责任。 +""" +{ + "key": "xxx", + "name": "xxx", + "type": 3, + "api": "./ApptoV5无加密.py", + "ext": "http://domain.com" +} +""" + +import re,sys,uuid +from base.spider import Spider +sys.path.append('..') + +class Spider(Spider): + host,config,local_uuid,parsing_config = '','','',[] + headers = { + 'User-Agent': "Dart/2.19 (dart:io)", + 'Accept-Encoding': "gzip", + 'appto-local-uuid': local_uuid + } + + def init(self, extend=''): + try: + host = extend.strip() + if not host.startswith('http'): + return {} + if not re.match(r'^https?://[a-zA-Z0-9-]+(\.[a-zA-Z0-9-]+)*(:\d+)?/?$', host): + host_=self.fetch(host).json() + self.host = host_['domain'] + else: + self.host = host + self.local_uuid = str(uuid.uuid4()) + response = self.fetch(f'{self.host}/apptov5/v1/config/get?p=android&__platform=android', headers=self.headers).json() + config = response['data'] + self.config = config + parsing_conf = config['get_parsing']['lists'] + parsing_config = {} + for i in parsing_conf: + if len(i['config']) != 0: + label = [] + for j in i['config']: + if j['type'] == 'json': + label.append(j['label']) + parsing_config.update({i['key']:label}) + self.parsing_config = parsing_config + return None + except Exception as e: + print(f'初始化异常：{e}') + return {} + + def detailContent(self, ids): + response = self.fetch(f"{self.host}/apptov5/v1/vod/getVod?id={ids[0]}",headers=self.headers).json() + data3 = response['data'] + videos = [] + vod_play_url = '' + vod_play_from = '' + for i in data3['vod_play_list']: + play_url = '' + for j in i['urls']: + play_url += f"{j['name']}${i['player_info']['from']}@{j['url']}#" + vod_play_from += i['player_info']['show'] + '$$$' + vod_play_url += play_url.rstrip('#') + '$$$' + vod_play_url = vod_play_url.rstrip('$$$') + vod_play_from = vod_play_from.rstrip('$$$') + videos.append({ + 'vod_id': data3.get('vod_id'), + 'vod_name': data3.get('vod_name'), + 'vod_content': data3.get('vod_content'), + 'vod_remarks': data3.get('vod_remarks'), + 'vod_director': data3.get('vod_director'), + 'vod_actor': data3.get('vod_actor'), + 'vod_year': data3.get('vod_year'), + 'vod_area': data3.get('vod_area'), + 'vod_play_from': vod_play_from, + 'vod_play_url': vod_play_url + }) + return {'list': videos} + + def searchContent(self, key, quick, pg='1'): + url = f"{self.host}/apptov5/v1/search/lists?wd={key}&page={pg}&type=&__platform=android" + response = self.fetch(url, headers=self.headers).json() + data = response['data']['data'] + for i in data: + if i.get('vod_pic').startswith('mac://'): + i['vod_pic'] = i['vod_pic'].replace('mac://', 'http://', 1) + return {'list': data, 'page': pg, 'total': response['data']['total']} + + def playerContent(self, flag, id, vipflags): + default_ua = 'Mozilla/5.0 (iPhone; CPU iPhone OS 13_2_3 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/13.0.3 Mobile/15E148 Safari/604.1' + parsing_config = self.parsing_config + parts = id.split('@') + if len(parts) != 2: + return {'parse': 0, 'url': id, 'header': {'User-Agent': default_ua}} + playfrom, rawurl = parts + label_list = parsing_config.get(playfrom) + if not label_list: + return {'parse': 0, 'url': rawurl, 'header': {'User-Agent': default_ua}} + result = {'parse': 1, 'url': rawurl, 'header': {'User-Agent': default_ua}} + for label in label_list: + payload = { + 'play_url': rawurl, + 'label': label, + 'key': playfrom + } + try: + response = self.post( + f"{self.host}/apptov5/v1/parsing/proxy?__platform=android", + data=payload, + headers=self.headers + ).json() + except Exception as e: + print(f"请求异常: {e}") + continue + if not isinstance(response, dict): + continue + if response.get('code') == 422: + continue + data = response.get('data') + if not isinstance(data, dict): + continue + url = data.get('url') + if not url: + continue + ua = data.get('UA') or data.get('UserAgent') or default_ua + result = { + 'parse': 0, + 'url': url, + 'header': {'User-Agent': ua} + } + break + return result + + def homeContent(self, filter): + config = self.config + if not config: + return {} + home_cate = config['get_home_cate'] + classes = [] + for i in home_cate: + if isinstance(i.get('extend', []),dict): + classes.append({'type_id': i['cate'], 'type_name': i['title']}) + return {'class': classes} + + def homeVideoContent(self): + response = self.fetch(f'{self.host}/apptov5/v1/home/data?id=1&mold=1&__platform=android',headers=self.headers).json() + data = response['data'] + vod_list = [] + for i in data['sections']: + for j in i['items']: + vod_pic = j.get('vod_pic') + if vod_pic.startswith('mac://'): + vod_pic = vod_pic.replace('mac://', 'http://', 1) + vod_list.append({ + "vod_id": j.get('vod_id'), + "vod_name": j.get('vod_name'), + "vod_pic": vod_pic, + "vod_remarks": j.get('vod_remarks') + }) + return {'list': vod_list} + + def categoryContent(self, tid, pg, filter, extend): + response = self.fetch(f"{self.host}/apptov5/v1/vod/lists?area={extend.get('area','')}&lang={extend.get('lang','')}&year={extend.get('year','')}&order={extend.get('sort','time')}&type_id={tid}&type_name=&page={pg}&pageSize=21&__platform=android", headers=self.headers).json() + data = response['data'] + data2 = data['data'] + for i in data['data']: + if i.get('vod_pic','').startswith('mac://'): + i['vod_pic'] = i['vod_pic'].replace('mac://', 'http://', 1) + return {'list': data2, 'page': pg, 'total': data['total']} + + def getName(self): + pass + + def isVideoFormat(self, url): + pass + + def manualVideoCheck(self): + pass + + def destroy(self): + pass + + def localProxy(self, param): + pass \ No newline at end of file diff --git a/jtxtv09/py/哔哩直播.py b/jtxtv09/py/哔哩直播.py new file mode 100644 index 0000000..fbf2c77 --- /dev/null +++ b/jtxtv09/py/哔哩直播.py @@ -0,0 +1,314 @@ +# coding=utf-8 +# !/usr/bin/python + +""" + +作者 丢丢喵 🚓 内容均从互联网收集而来 仅供交流学习使用 版权归原创者所有 如侵犯了您的权益 请通知作者 将及时删除侵权内容 + ====================Diudiumiao==================== + +""" + +from Crypto.Util.Padding import unpad +from Crypto.Util.Padding import pad +from urllib.parse import unquote +from Crypto.Cipher import ARC4 +from urllib.parse import quote +from base.spider import Spider +from Crypto.Cipher import AES +from datetime import datetime +from bs4 import BeautifulSoup +from base64 import b64decode +import urllib.request +import urllib.parse +import datetime +import binascii +import requests +import base64 +import json +import time +import sys +import re +import os + +sys.path.append('..') + +xurl = "https://search.bilibili.com" + +xurl1 = "https://api.live.bilibili.com" + +headerx = { + 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/129.0.0.0 Safari/537.36 Edg/129.0.0.0' + } + +class Spider(Spider): + global xurl + global xurl1 + global headerx + + def getName(self): + return "首页" + + def init(self, extend): + pass + + def isVideoFormat(self, url): + pass + + def manualVideoCheck(self): + pass + + def extract_middle_text(self, text, start_str, end_str, pl, start_index1: str = '', end_index2: str = ''): + if pl == 3: + plx = [] + while True: + start_index = text.find(start_str) + if start_index == -1: + break + end_index = text.find(end_str, start_index + len(start_str)) + if end_index == -1: + break + middle_text = text[start_index + len(start_str):end_index] + plx.append(middle_text) + text = text.replace(start_str + middle_text + end_str, '') + if len(plx) > 0: + purl = '' + for i in range(len(plx)): + matches = re.findall(start_index1, plx[i]) + output = "" + for match in matches: + match3 = re.search(r'(?:^|[^0-9])(\d+)(?:[^0-9]|$)', match[1]) + if match3: + number = match3.group(1) + else: + number = 0 + if 'http' not in match[0]: + output += f"#{match[1]}${number}{xurl}{match[0]}" + else: + output += f"#{match[1]}${number}{match[0]}" + output = output[1:] + purl = purl + output + "$$$" + purl = purl[:-3] + return purl + else: + return "" + else: + start_index = text.find(start_str) + if start_index == -1: + return "" + end_index = text.find(end_str, start_index + len(start_str)) + if end_index == -1: + return "" + + if pl == 0: + middle_text = text[start_index + len(start_str):end_index] + return middle_text.replace("\\", "") + + if pl == 1: + middle_text = text[start_index + len(start_str):end_index] + matches = re.findall(start_index1, middle_text) + if matches: + jg = ' '.join(matches) + return jg + + if pl == 2: + middle_text = text[start_index + len(start_str):end_index] + matches = re.findall(start_index1, middle_text) + if matches: + new_list = [f'{item}' for item in matches] + jg = '$$$'.join(new_list) + return jg + + def homeContent(self, filter): + result = {} + result = {"class": [{"type_id": "舞", "type_name": "舞蹈"}, + {"type_id": "音乐", "type_name": "音乐"}, + {"type_id": "手游", "type_name": "手游"}, + {"type_id": "网游", "type_name": "网游"}, + {"type_id": "单机游戏", "type_name": "单机游戏"}, + {"type_id": "虚拟主播", "type_name": "虚拟主播"}, + {"type_id": "电台", "type_name": "电台"}, + {"type_id": "体育", "type_name": "体育"}, + {"type_id": "聊天", "type_name": "聊天"}, + {"type_id": "娱乐", "type_name": "娱乐"}, + {"type_id": "电影", "type_name": "影视"}, + {"type_id": "新闻", "type_name": "新闻"}] + } + + return result + + def homeVideoContent(self): + pass + + def categoryContent(self, cid, pg, filter, ext): + result = {} + videos = [] + + if pg: + page = int(pg) + else: + page = 1 + + url = f'{xurl}/live?keyword={cid}&page={str(page)}' + detail = requests.get(url=url, headers=headerx) + detail.encoding = "utf-8" + res = detail.text + doc = BeautifulSoup(res, "lxml") + + soups = doc.find_all('div', class_="video-list-item") + + for vod in soups: + + names = vod.find('h3', class_="bili-live-card__info--tit") + name = names.text.strip().replace('直播中', '') + + id = names.find('a')['href'] + id = self.extract_middle_text(id, 'bilibili.com/', '?', 0) + + pic = vod.find('img')['src'] + if 'http' not in pic: + pic = "https:" + pic + + remarks = vod.find('a', class_="bili-live-card__info--uname") + remark = remarks.text.strip() + + video = { + "vod_id": id, + "vod_name": name, + "vod_pic": pic, + "vod_remarks": remark + } + videos.append(video) + + result = {'list': videos} + result['page'] = pg + result['pagecount'] = 9999 + result['limit'] = 90 + result['total'] = 999999 + return result + + def detailContent(self, ids): + did = ids[0] + result = {} + videos = [] + xianlu = '' + bofang = '' + + url = f'{xurl1}/xlive/web-room/v2/index/getRoomPlayInfo?room_id={did}&platform=web&protocol=0,1&format=0,1,2&codec=0,1' + detail = requests.get(url=url, headers=headerx) + detail.encoding = "utf-8" + data = detail.json() + + content = '欢迎观看哔哩直播' + + setup = data['data']['playurl_info']['playurl']['stream'] + + nam = 0 + + for vod in setup: + + try: + host = vod['format'][nam]['codec'][0]['url_info'][1]['host'] + except (KeyError, IndexError): + continue + + base = vod['format'][nam]['codec'][0]['base_url'] + + extra = vod['format'][nam]['codec'][0]['url_info'][1]['extra'] + + id = host + base + extra + + nam = nam + 1 + + namc = f"{nam}号线路" + + bofang = bofang + namc + '$' + id + '#' + + bofang = bofang[:-1] + + xianlu = '哔哩专线' + + videos.append({ + "vod_id": did, + "vod_content": content, + "vod_play_from": xianlu, + "vod_play_url": bofang + }) + + result['list'] = videos + return result + + def playerContent(self, flag, id, vipFlags): + + result = {} + result["parse"] = 0 + result["playUrl"] = '' + result["url"] = id + result["header"] = headerx + return result + + def searchContentPage(self, key, quick, pg): + result = {} + videos = [] + + if pg: + page = int(pg) + else: + page = 1 + + url = f'{xurl}/live?keyword={key}&page={str(page)}' + detail = requests.get(url=url, headers=headerx) + detail.encoding = "utf-8" + res = detail.text + doc = BeautifulSoup(res, "lxml") + + soups = doc.find_all('div', class_="video-list-item") + + for vod in soups: + + names = vod.find('h3', class_="bili-live-card__info--tit") + name = names.text.strip().replace('直播中', '') + + id = names.find('a')['href'] + id = self.extract_middle_text(id, 'bilibili.com/', '?', 0) + + pic = vod.find('img')['src'] + if 'http' not in pic: + pic = "https:" + pic + + remarks = vod.find('a', class_="bili-live-card__info--uname") + remark = remarks.text.strip() + + video = { + "vod_id": id, + "vod_name": name, + "vod_pic": pic, + "vod_remarks": remark + } + videos.append(video) + + result['list'] = videos + result['page'] = pg + result['pagecount'] = 9999 + result['limit'] = 90 + result['total'] = 999999 + return result + + def searchContent(self, key, quick, pg="1"): + return self.searchContentPage(key, quick, '1') + + def localProxy(self, params): + if params['type'] == "m3u8": + return self.proxyM3u8(params) + elif params['type'] == "media": + return self.proxyMedia(params) + elif params['type'] == "ts": + return self.proxyTs(params) + return None + + + + + + + + diff --git a/jtxtv09/py/央库云.py b/jtxtv09/py/央库云.py new file mode 100644 index 0000000..36937c0 --- /dev/null +++ b/jtxtv09/py/央库云.py @@ -0,0 +1,476 @@ +""" +@header({ + searchable: 1, + filterable: 1, + quickSearch: 1, + title: '中央电视台', + lang: 'hipy' +}) +""" + +#coding=utf-8 +#!/usr/bin/python +import sys +sys.path.append('..') +from base.spider import Spider +import json +import time +import base64 +import re +from urllib import request, parse +import urllib +import urllib.request +import time + +class Spider(Spider): # 元类 默认的元类 type + def getName(self): + return "中央电视台"#可搜索 + def init(self,extend=""): + print("============{0}============".format(extend)) + pass + def destroy(self): + pass + def isVideoFormat(self,url): + pass + def manualVideoCheck(self): + pass + def homeContent(self,filter): + result = {} + cateManual = { + "央视大全":"节目大全", + "电视剧": "电视剧", + "动画片": "动画片", + "纪录片": "纪录片", + "特别节目": "特别节目" + + } + classes = [] + for k in cateManual: + classes.append({ + 'type_name':k, + 'type_id':cateManual[k] + }) + result['class'] = classes + if(filter): + result['filters'] = self.config['filter'] + return result + def homeVideoContent(self): + result = { + 'list':[] + } + return result + def categoryContent(self,tid,pg,filter,extend): + result = {} + month = ""#月 + year = ""#年 + area=''#地区 + channel=''#频道 + datafl=''#类型 + letter=''#字母 + pagecount=24 + if tid=='动画片': + id=urllib.parse.quote(tid) + if 'datadq-area' in extend.keys(): + area=urllib.parse.quote(extend['datadq-area']) + if 'dataszm-letter' in extend.keys(): + letter=extend['dataszm-letter'] + if 'datafl-sc' in extend.keys(): + datafl=urllib.parse.quote(extend['datafl-sc']) + url='https://api.cntv.cn/list/getVideoAlbumList?channelid=CHAL1460955899450127&area={0}&sc={4}&fc={1}&letter={2}&p={3}&n=24&serviceId=tvcctv&topv=1&t=json'.format(area,id,letter,pg,datafl) + elif tid=='纪录片': + id=urllib.parse.quote(tid) + if 'datapd-channel' in extend.keys(): + channel=urllib.parse.quote(extend['datapd-channel']) + if 'datafl-sc' in extend.keys(): + datafl=urllib.parse.quote(extend['datafl-sc']) + if 'datanf-year' in extend.keys(): + year=extend['datanf-year'] + if 'dataszm-letter' in extend.keys(): + letter=extend['dataszm-letter'] + url='https://api.cntv.cn/list/getVideoAlbumList?channelid=CHAL1460955924871139&fc={0}&channel={1}&sc={2}&year={3}&letter={4}&p={5}&n=24&serviceId=tvcctv&topv=1&t=json'.format(id,channel,datafl,year,letter,pg) + elif tid=='电视剧': + id=urllib.parse.quote(tid) + if 'datafl-sc' in extend.keys(): + datafl=urllib.parse.quote(extend['datafl-sc']) + if 'datanf-year' in extend.keys(): + year=extend['datanf-year'] + if 'dataszm-letter' in extend.keys(): + letter=extend['dataszm-letter'] + url='https://api.cntv.cn/list/getVideoAlbumList?channelid=CHAL1460955853485115&area={0}&sc={1}&fc={2}&year={3}&letter={4}&p={5}&n=24&serviceId=tvcctv&topv=1&t=json'.format(area,datafl,id,year,letter,pg) + elif tid=='特别节目': + id=urllib.parse.quote(tid) + if 'datapd-channel' in extend.keys(): + channel=urllib.parse.quote(extend['datapd-channel']) + if 'datafl-sc' in extend.keys(): + datafl=urllib.parse.quote(extend['datafl-sc']) + if 'dataszm-letter' in extend.keys(): + letter=extend['dataszm-letter'] + url='https://api.cntv.cn/list/getVideoAlbumList?channelid=CHAL1460955953877151&channel={0}&sc={1}&fc={2}&bigday=&letter={3}&p={4}&n=24&serviceId=tvcctv&topv=1&t=json'.format(channel,datafl,id,letter,pg) + elif tid=='节目大全': + cid=''#频道 + if 'cid' in extend.keys(): + cid=extend['cid'] + fc=''#分类 + if 'fc' in extend.keys(): + fc=extend['fc'] + fl=''#字母 + if 'fl' in extend.keys(): + fl=extend['fl'] + url = 'https://api.cntv.cn/lanmu/columnSearch?&fl={0}&fc={1}&cid={2}&p={3}&n=20&serviceId=tvcctv&t=json&cb=ko'.format(fl,fc,cid,pg) + pagecount=20 + else: + url = 'https://tv.cctv.com/epg/index.shtml' + + videos=[] + htmlText =self.webReadFile(urlStr=url,header=self.header) + if tid=='节目大全': + index=htmlText.rfind(');') + if index>-1: + htmlText=htmlText[3:index] + videos =self.get_list1(html=htmlText,tid=tid) + else: + videos =self.get_list(html=htmlText,tid=tid) + #print(videos) + + result['list'] = videos + result['page'] = pg + result['pagecount'] = 9999 if len(videos)>=pagecount else pg + result['limit'] = 90 + result['total'] = 999999 + return result + def detailContent(self,array): + result={} + aid = array[0].split('###') + tid = aid[0] + logo = aid[3] + lastVideo = aid[2] + title = aid[1] + id= aid[4] + + vod_year= aid[5] + actors= aid[6] + brief= aid[7] + fromId='CCTV' + if tid=="节目大全": + lastUrl = 'https://api.cntv.cn/video/videoinfoByGuid?guid={0}&serviceId=tvcctv'.format(id) + htmlTxt = self.webReadFile(urlStr=lastUrl,header=self.header) + topicId=json.loads(htmlTxt)['ctid'] + Url = "https://api.cntv.cn/NewVideo/getVideoListByColumn?id={0}&d=&p=1&n=100&sort=desc&mode=0&serviceId=tvcctv&t=json".format(topicId) + htmlTxt = self.webReadFile(urlStr=Url,header=self.header) + else: + Url='https://api.cntv.cn/NewVideo/getVideoListByAlbumIdNew?id={0}&serviceId=tvcctv&p=1&n=100&mode=0&pub=1'.format(id) + jRoot = '' + videoList = [] + try: + if tid=="搜索": + fromId='中央台' + videoList=[title+"$"+lastVideo] + else: + htmlTxt=self.webReadFile(urlStr=Url,header=self.header) + jRoot = json.loads(htmlTxt) + data=jRoot['data'] + jsonList=data['list'] + videoList=self.get_EpisodesList(jsonList=jsonList) + if len(videoList)<1: + htmlTxt=self.webReadFile(urlStr=lastVideo,header=self.header) + if tid=="电视剧" or tid=="纪录片": + patternTxt=r"'title':\s*'(?P.+?)',\n{0,1}\s*'brief':\s*'(.+?)',\n{0,1}\s*'img':\s*'(.+?)',\n{0,1}\s*'url':\s*'(?P<url>.+?)'" + elif tid=="特别节目": + patternTxt=r'class="tp1"><a\s*href="(?P<url>https://.+?)"\s*target="_blank"\s*title="(?P<title>.+?)"></a></div>' + elif tid=="动画片": + patternTxt=r"'title':\s*'(?P<title>.+?)',\n{0,1}\s*'img':\s*'(.+?)',\n{0,1}\s*'brief':\s*'(.+?)',\n{0,1}\s*'url':\s*'(?P<url>.+?)'" + elif tid=="节目大全": + patternTxt=r'href="(?P<url>.+?)" target="_blank" alt="(?P<title>.+?)" title=".+?">' + videoList=self.get_EpisodesList_re(htmlTxt=htmlTxt,patternTxt=patternTxt) + fromId='央视' + except: + pass + if len(videoList) == 0: + return {} + vod = { + "vod_id":array[0], + "vod_name":title, + "vod_pic":logo, + "type_name":tid, + "vod_year":vod_year, + "vod_area":"", + "vod_remarks":'', + "vod_actor":actors, + "vod_director":'', + "vod_content":brief + } + vod['vod_play_from'] = fromId + vod['vod_play_url'] = "#".join(videoList) + result = { + 'list':[ + vod + ] + } + return result + def get_lineList(self,Txt,mark,after): + circuit=[] + origin=Txt.find(mark) + while origin>8: + end=Txt.find(after,origin) + circuit.append(Txt[origin:end]) + origin=Txt.find(mark,end) + return circuit + def get_RegexGetTextLine(self,Text,RegexText,Index): + returnTxt=[] + pattern = re.compile(RegexText, re.M|re.S) + ListRe=pattern.findall(Text) + if len(ListRe)<1: + return returnTxt + for value in ListRe: + returnTxt.append(value) + return returnTxt + def searchContent(self,key,quick): + return self.searchContentPage(key, quick, '1') + def searchContentPage(self, key, quick, page): + key=urllib.parse.quote(key) + Url='https://search.cctv.com/ifsearch.php?page=1&qtext={0}&sort=relevance&pageSize=20&type=video&vtime=-1&datepid=1&channel=&pageflag=0&qtext_str={0}'.format(key) + htmlTxt=self.webReadFile(urlStr=Url,header=self.header) + videos=self.get_list_search(html=htmlTxt,tid='搜索') + result = { + 'list':videos + } + return result + def playerContent(self,flag,id,vipFlags): + result = {} + url='' + parse=0 + headers = { + 'User-Agent':'Mozilla/5.0 (iPhone; CPU iPhone OS 9_1 like Mac OS X) AppleWebKit/601.1.46 (KHTML, like Gecko) Version/9.0 Mobile/13B143 Safari/601.1' + } + if flag=='CCTV': + url=self.get_m3u8(urlTxt=id) + else: + try: + html=self.webReadFile(urlStr=id,header=self.header) + guid=self.get_RegexGetText(Text=html,RegexText=r'var\sguid\s*=\s*"(.+?)";',Index=1) + url=self.get_m3u8(urlTxt=guid) + except : + url=id + parse=1 + if url.find('https:')<0: + url=id + parse=1 + result["parse"] = parse#1=嗅探,0=播放 + result["playUrl"] = '' + result["url"] = url + result["header"] =headers + return result + config = { + "player": {}, + "filter": { + "电视剧":[ + {"key":"datafl-sc","name":"类型","value":[{"n":"全部","v":""},{"n":"谍战","v":"谍战"},{"n":"悬疑","v":"悬疑"},{"n":"刑侦","v":"刑侦"},{"n":"历史","v":"历史"},{"n":"古装","v":"古装"},{"n":"武侠","v":"武侠"},{"n":"军旅","v":"军旅"},{"n":"战争","v":"战争"},{"n":"喜剧","v":"喜剧"},{"n":"青春","v":"青春"},{"n":"言情","v":"言情"},{"n":"偶像","v":"偶像"},{"n":"家庭","v":"家庭"},{"n":"年代","v":"年代"},{"n":"革命","v":"革命"},{"n":"农村","v":"农村"},{"n":"都市","v":"都市"},{"n":"其他","v":"其他"}]}, + {"key":"datadq-area","name":"地区","value":[{"n":"全部","v":""},{"n":"中国大陆","v":"中国大陆"},{"n":"中国香港","v":"香港"},{"n":"美国","v":"美国"},{"n":"欧洲","v":"欧洲"},{"n":"泰国","v":"泰国"}]}, + {"key":"datanf-year","name":"年份","value":[{"n":"全部","v":""},{"n":"2023","v":"2023"},{"n":"2022","v":"2022"},{"n":"2021","v":"2021"},{"n":"2020","v":"2020"},{"n":"2019","v":"2019"},{"n":"2018","v":"2018"},{"n":"2017","v":"2017"},{"n":"2016","v":"2016"},{"n":"2015","v":"2015"},{"n":"2014","v":"2014"},{"n":"2013","v":"2013"},{"n":"2012","v":"2012"},{"n":"2011","v":"2011"},{"n":"2010","v":"2010"},{"n":"2009","v":"2009"},{"n":"2008","v":"2008"},{"n":"2007","v":"2007"},{"n":"2006","v":"2006"},{"n":"2005","v":"2005"},{"n":"2004","v":"2004"},{"n":"2003","v":"2003"},{"n":"2002","v":"2002"},{"n":"2001","v":"2001"},{"n":"2000","v":"2000"},{"n":"1999","v":"1999"},{"n":"1998","v":"1998"},{"n":"1997","v":"1997"}]}, + {"key":"dataszm-letter","name":"字母","value":[{"n":"全部","v":""},{"n":"A","v":"A"},{"n":"C","v":"C"},{"n":"E","v":"E"},{"n":"F","v":"F"},{"n":"G","v":"G"},{"n":"H","v":"H"},{"n":"I","v":"I"},{"n":"J","v":"J"},{"n":"K","v":"K"},{"n":"L","v":"L"},{"n":"M","v":"M"},{"n":"N","v":"N"},{"n":"O","v":"O"},{"n":"P","v":"P"},{"n":"Q","v":"Q"},{"n":"R","v":"R"},{"n":"S","v":"S"},{"n":"T","v":"T"},{"n":"U","v":"U"},{"n":"V","v":"V"},{"n":"W","v":"W"},{"n":"X","v":"X"},{"n":"Y","v":"Y"},{"n":"Z","v":"Z"},{"n":"0-9","v":"0-9"}]} + ], + "动画片":[ + {"key":"datafl-sc","name":"类型","value":[{"n":"全部","v":""},{"n":"亲子","v":"亲子"},{"n":"搞笑","v":"搞笑"},{"n":"冒险","v":"冒险"},{"n":"动作","v":"动作"},{"n":"宠物","v":"宠物"},{"n":"体育","v":"体育"},{"n":"益智","v":"益智"},{"n":"历史","v":"历史"},{"n":"教育","v":"教育"},{"n":"校园","v":"校园"},{"n":"言情","v":"言情"},{"n":"武侠","v":"武侠"},{"n":"经典","v":"经典"},{"n":"未来","v":"未来"},{"n":"古代","v":"古代"},{"n":"神话","v":"神话"},{"n":"真人","v":"真人"},{"n":"励志","v":"励志"},{"n":"热血","v":"热血"},{"n":"奇幻","v":"奇幻"},{"n":"童话","v":"童话"},{"n":"剧情","v":"剧情"},{"n":"夺宝","v":"夺宝"},{"n":"其他","v":"其他"}]}, + {"key":"datadq-area","name":"地区","value":[{"n":"全部","v":""},{"n":"中国大陆","v":"中国大陆"},{"n":"美国","v":"美国"},{"n":"欧洲","v":"欧洲"}]}, + {"key":"dataszm-letter","name":"字母","value":[{"n":"全部","v":""},{"n":"A","v":"A"},{"n":"C","v":"C"},{"n":"E","v":"E"},{"n":"F","v":"F"},{"n":"G","v":"G"},{"n":"H","v":"H"},{"n":"I","v":"I"},{"n":"J","v":"J"},{"n":"K","v":"K"},{"n":"L","v":"L"},{"n":"M","v":"M"},{"n":"N","v":"N"},{"n":"O","v":"O"},{"n":"P","v":"P"},{"n":"Q","v":"Q"},{"n":"R","v":"R"},{"n":"S","v":"S"},{"n":"T","v":"T"},{"n":"U","v":"U"},{"n":"V","v":"V"},{"n":"W","v":"W"},{"n":"X","v":"X"},{"n":"Y","v":"Y"},{"n":"Z","v":"Z"},{"n":"0-9","v":"0-9"}]} + ], + "纪录片":[ + {"key":"datapd-channel","name":"频道","value":[{"n":"全部","v":""},{"n":"CCTV{1 综合","v":"CCTV{1 综合"},{"n":"CCTV{2 财经","v":"CCTV{2 财经"},{"n":"CCTV{3 综艺","v":"CCTV{3 综艺"},{"n":"CCTV{4 中文国际","v":"CCTV{4 中文国际"},{"n":"CCTV{5 体育","v":"CCTV{5 体育"},{"n":"CCTV{6 电影","v":"CCTV{6 电影"},{"n":"CCTV{7 国防军事","v":"CCTV{7 国防军事"},{"n":"CCTV{8 电视剧","v":"CCTV{8 电视剧"},{"n":"CCTV{9 纪录","v":"CCTV{9 纪录"},{"n":"CCTV{10 科教","v":"CCTV{10 科教"},{"n":"CCTV{11 戏曲","v":"CCTV{11 戏曲"},{"n":"CCTV{12 社会与法","v":"CCTV{12 社会与法"},{"n":"CCTV{13 新闻","v":"CCTV{13 新闻"},{"n":"CCTV{14 少儿","v":"CCTV{14 少儿"},{"n":"CCTV{15 音乐","v":"CCTV{15 音乐"},{"n":"CCTV{17 农业农村","v":"CCTV{17 农业农村"}]}, + {"key":"datafl-sc","name":"类型","value":[{"n":"全部","v":""},{"n":"人文历史","v":"人文历史"},{"n":"人物","v":"人物"},{"n":"军事","v":"军事"},{"n":"探索","v":"探索"},{"n":"社会","v":"社会"},{"n":"时政","v":"时政"},{"n":"经济","v":"经济"},{"n":"科技","v":"科技"}]}, + {"key":"datanf-year","name":"年份","value":[{"n":"全部","v":""},{"n":"2023","v":"2023"},{"n":"2022","v":"2022"},{"n":"2021","v":"2021"},{"n":"2020","v":"2020"},{"n":"2019","v":"2019"},{"n":"2018","v":"2018"},{"n":"2017","v":"2017"},{"n":"2016","v":"2016"},{"n":"2015","v":"2015"},{"n":"2014","v":"2014"},{"n":"2013","v":"2013"},{"n":"2012","v":"2012"},{"n":"2011","v":"2011"},{"n":"2010","v":"2010"},{"n":"2009","v":"2009"},{"n":"2008","v":"2008"}]}, + {"key":"dataszm-letter","name":"字母","value":[{"n":"全部","v":""},{"n":"A","v":"A"},{"n":"C","v":"C"},{"n":"E","v":"E"},{"n":"F","v":"F"},{"n":"G","v":"G"},{"n":"H","v":"H"},{"n":"I","v":"I"},{"n":"J","v":"J"},{"n":"K","v":"K"},{"n":"L","v":"L"},{"n":"M","v":"M"},{"n":"N","v":"N"},{"n":"O","v":"O"},{"n":"P","v":"P"},{"n":"Q","v":"Q"},{"n":"R","v":"R"},{"n":"S","v":"S"},{"n":"T","v":"T"},{"n":"U","v":"U"},{"n":"V","v":"V"},{"n":"W","v":"W"},{"n":"X","v":"X"},{"n":"Y","v":"Y"},{"n":"Z","v":"Z"},{"n":"0-9","v":"0-9"}]} + ], + "特别节目":[ + {"key":"datapd-channel","name":"频道","value":[{"n":"全部","v":""},{"n":"CCTV{1 综合","v":"CCTV{1 综合"},{"n":"CCTV{2 财经","v":"CCTV{2 财经"},{"n":"CCTV{3 综艺","v":"CCTV{3 综艺"},{"n":"CCTV{4 中文国际","v":"CCTV{4 中文国际"},{"n":"CCTV{5 体育","v":"CCTV{5 体育"},{"n":"CCTV{6 电影","v":"CCTV{6 电影"},{"n":"CCTV{7 国防军事","v":"CCTV{7 国防军事"},{"n":"CCTV{8 电视剧","v":"CCTV{8 电视剧"},{"n":"CCTV{9 纪录","v":"CCTV{9 纪录"},{"n":"CCTV{10 科教","v":"CCTV{10 科教"},{"n":"CCTV{11 戏曲","v":"CCTV{11 戏曲"},{"n":"CCTV{12 社会与法","v":"CCTV{12 社会与法"},{"n":"CCTV{13 新闻","v":"CCTV{13 新闻"},{"n":"CCTV{14 少儿","v":"CCTV{14 少儿"},{"n":"CCTV{15 音乐","v":"CCTV{15 音乐"},{"n":"CCTV{17 农业农村","v":"CCTV{17 农业农村"}]}, + {"key":"datafl-sc","name":"类型","value":[{"n":"全部","v":""},{"n":"全部","v":"全部"},{"n":"新闻","v":"新闻"},{"n":"经济","v":"经济"},{"n":"综艺","v":"综艺"},{"n":"体育","v":"体育"},{"n":"军事","v":"军事"},{"n":"影视","v":"影视"},{"n":"科教","v":"科教"},{"n":"戏曲","v":"戏曲"},{"n":"青少","v":"青少"},{"n":"音乐","v":"音乐"},{"n":"社会","v":"社会"},{"n":"公益","v":"公益"},{"n":"其他","v":"其他"}]}, + {"key":"dataszm-letter","name":"字母","value":[{"n":"全部","v":""},{"n":"A","v":"A"},{"n":"C","v":"C"},{"n":"E","v":"E"},{"n":"F","v":"F"},{"n":"G","v":"G"},{"n":"H","v":"H"},{"n":"I","v":"I"},{"n":"J","v":"J"},{"n":"K","v":"K"},{"n":"L","v":"L"},{"n":"M","v":"M"},{"n":"N","v":"N"},{"n":"O","v":"O"},{"n":"P","v":"P"},{"n":"Q","v":"Q"},{"n":"R","v":"R"},{"n":"S","v":"S"},{"n":"T","v":"T"},{"n":"U","v":"U"},{"n":"V","v":"V"},{"n":"W","v":"W"},{"n":"X","v":"X"},{"n":"Y","v":"Y"},{"n":"Z","v":"Z"},{"n":"0-9","v":"0-9"}]} + ], + "节目大全":[{"key":"cid","name":"频道","value":[{"n":"全部","v":""},{"n":"CCTV-1综合","v":"EPGC1386744804340101"},{"n":"CCTV-2财经","v":"EPGC1386744804340102"},{"n":"CCTV-3综艺","v":"EPGC1386744804340103"},{"n":"CCTV-4中文国际","v":"EPGC1386744804340104"},{"n":"CCTV-5体育","v":"EPGC1386744804340107"},{"n":"CCTV-6电影","v":"EPGC1386744804340108"},{"n":"CCTV-7国防军事","v":"EPGC1386744804340109"},{"n":"CCTV-8电视剧","v":"EPGC1386744804340110"},{"n":"CCTV-9纪录","v":"EPGC1386744804340112"},{"n":"CCTV-10科教","v":"EPGC1386744804340113"},{"n":"CCTV-11戏曲","v":"EPGC1386744804340114"},{"n":"CCTV-12社会与法","v":"EPGC1386744804340115"},{"n":"CCTV-13新闻","v":"EPGC1386744804340116"},{"n":"CCTV-14少儿","v":"EPGC1386744804340117"},{"n":"CCTV-15音乐","v":"EPGC1386744804340118"},{"n":"CCTV-16奥林匹克","v":"EPGC1634630207058998"},{"n":"CCTV-17农业农村","v":"EPGC1563932742616872"},{"n":"CCTV-5+体育赛事","v":"EPGC1468294755566101"}]},{"key":"fc","name":"分类","value":[{"n":"全部","v":""},{"n":"新闻","v":"新闻"},{"n":"体育","v":"体育"},{"n":"综艺","v":"综艺"},{"n":"健康","v":"健康"},{"n":"生活","v":"生活"},{"n":"科教","v":"科教"},{"n":"经济","v":"经济"},{"n":"农业","v":"农业"},{"n":"法治","v":"法治"},{"n":"军事","v":"军事"},{"n":"少儿","v":"少儿"},{"n":"动画","v":"动画"},{"n":"纪实","v":"纪实"},{"n":"戏曲","v":"戏曲"},{"n":"音乐","v":"音乐"},{"n":"影视","v":"影视"}]},{"key":"fl","name":"字母","value":[{"n":"全部","v":""},{"n":"A","v":"A"},{"n":"B","v":"B"},{"n":"C","v":"C"},{"n":"D","v":"D"},{"n":"E","v":"E"},{"n":"F","v":"F"},{"n":"G","v":"G"},{"n":"H","v":"H"},{"n":"I","v":"I"},{"n":"J","v":"J"},{"n":"K","v":"K"},{"n":"L","v":"L"},{"n":"M","v":"M"},{"n":"N","v":"N"},{"n":"O","v":"O"},{"n":"P","v":"P"},{"n":"Q","v":"Q"},{"n":"R","v":"R"},{"n":"S","v":"S"},{"n":"T","v":"T"},{"n":"U","v":"U"},{"n":"V","v":"V"},{"n":"W","v":"W"},{"n":"X","v":"X"},{"n":"Y","v":"Y"},{"n":"Z","v":"Z"}]},{"key":"year","name":"年份","value":[{"n":"全部","v":""},{"n":"2023","v":"2023"},{"n":"2022","v":"2022"},{"n":"2021","v":"2021"},{"n":"2020","v":"2020"},{"n":"2019","v":"2019"},{"n":"2018","v":"2018"},{"n":"2017","v":"2017"},{"n":"2016","v":"2016"},{"n":"2015","v":"2015"},{"n":"2014","v":"2014"},{"n":"2013","v":"2013"},{"n":"2012","v":"2012"},{"n":"2011","v":"2011"},{"n":"2010","v":"2010"},{"n":"2009","v":"2009"},{"n":"2008","v":"2008"},{"n":"2007","v":"2007"},{"n":"2006","v":"2006"},{"n":"2005","v":"2005"},{"n":"2004","v":"2004"},{"n":"2003","v":"2003"},{"n":"2002","v":"2002"},{"n":"2001","v":"2001"},{"n":"2000","v":"2000"}]},{"key":"month","name":"月份","value":[{"n":"全部","v":""},{"n":"12","v":"12"},{"n":"11","v":"11"},{"n":"10","v":"10"},{"n":"09","v":"09"},{"n":"08","v":"08"},{"n":"07","v":"07"},{"n":"06","v":"06"},{"n":"05","v":"05"},{"n":"04","v":"04"},{"n":"03","v":"03"},{"n":"02","v":"02"},{"n":"01","v":"01"}]}] + } + } + header = { + "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.54 Safari/537.36", + "Host": "tv.cctv.com", + "Referer": "https://tv.cctv.com/" + } + + def localProxy(self,param): + return [200, "video/MP2T", ""] + #-----------------------------------------------自定义函数----------------------------------------------- + #访问网页 + def webReadFile(self,urlStr,header): + html='' + req=urllib.request.Request(url=urlStr)#,headers=header + with urllib.request.urlopen(req) as response: + html = response.read().decode('utf-8') + return html + #判断网络地址是否存在 + def TestWebPage(self,urlStr,header): + html='' + req=urllib.request.Request(url=urlStr,method='HEAD')#,headers=header + with urllib.request.urlopen(req) as response: + html = response.getcode () + return html + #正则取文本 + def get_RegexGetText(self,Text,RegexText,Index): + returnTxt="" + Regex=re.search(RegexText, Text, re.M|re.S) + if Regex is None: + returnTxt="" + else: + returnTxt=Regex.group(Index) + return returnTxt + #取集数 + def get_EpisodesList(self,jsonList): + videos=[] + for vod in jsonList: + url = vod['guid'] + title =vod['title'] + if len(url) == 0: + continue + videos.append(title+"$"+url) + return videos + #取集数 + def get_EpisodesList_re(self,htmlTxt,patternTxt): + ListRe=re.finditer(patternTxt, htmlTxt, re.M|re.S) + videos=[] + for vod in ListRe: + url = vod.group('url') + title =vod.group('title') + if len(url) == 0: + continue + videos.append(title+"$"+url) + return videos + #取剧集区 + def get_lineList(self,Txt,mark,after): + circuit=[] + origin=Txt.find(mark) + while origin>8: + end=Txt.find(after,origin) + circuit.append(Txt[origin:end]) + origin=Txt.find(mark,end) + return circuit + #正则取文本,返回数组 + def get_RegexGetTextLine(self,Text,RegexText,Index): + returnTxt=[] + pattern = re.compile(RegexText, re.M|re.S) + ListRe=pattern.findall(Text) + if len(ListRe)<1: + return returnTxt + for value in ListRe: + returnTxt.append(value) + return returnTxt + #删除html标签 + def removeHtml(self,txt): + soup = re.compile(r'<[^>]+>',re.S) + txt =soup.sub('', txt) + return txt.replace(" "," ") + #取m3u8 + def get_m3u8(self,urlTxt): + url = "https://vdn.apps.cntv.cn/api/getHttpVideoInfo.do?pid={0}".format(urlTxt) + html=self.webReadFile(urlStr=url,header=self.header) + jo =json.loads(html) + link = jo['hls_url'].strip() + html = self.webReadFile(urlStr=link,header=self.header) + content = html.strip() + arr = content.split('\n') + urlPrefix = self.get_RegexGetText(Text=link,RegexText='(http[s]?://[a-zA-z0-9.]+)/',Index=1) + subUrl = arr[-1].split('/') + subUrl[3] = '1200' + subUrl[-1] = '1200.m3u8' + hdUrl = urlPrefix + '/'.join(subUrl) + + url = urlPrefix + arr[-1] + + hdRsp = self.TestWebPage(urlStr=hdUrl,header=self.header) + if hdRsp == 200: + url = hdUrl + else: + url='' + return url + #搜索 + def get_list_search(self,html,tid): + jRoot = json.loads(html) + jsonList=jRoot['list'] + videos=[] + for vod in jsonList: + url = vod['urllink'] + title =self.removeHtml(txt=vod['title']) + img=vod['imglink'] + id=vod['id'] + brief=vod['channel'] + year=vod['uploadtime'] + if len(url) == 0: + continue + guid="{0}###{1}###{2}###{3}###{4}###{5}###{6}###{7}".format(tid,title,url,img,id,year,'',brief) + videos.append({ + "vod_id":guid, + "vod_name":title, + "vod_pic":img, + "vod_remarks":year + }) + return videos + return videos + def get_list1(self,html,tid): + jRoot = json.loads(html) + videos = [] + data=jRoot['response'] + if data is None: + return [] + jsonList=data['docs'] + for vod in jsonList: + id = vod['lastVIDE']['videoSharedCode'] + title =vod['column_name'] + url=vod['column_website'] + img=vod['column_logo'] + year=vod['column_playdate'] + brief=vod['column_brief'] + actors='' + if len(url) == 0: + continue + guid="{0}###{1}###{2}###{3}###{4}###{5}###{6}###{7}".format(tid,title,url,img,id,year,actors,brief) + #print(vod_id) + videos.append({ + "vod_id":guid, + "vod_name":title, + "vod_pic":img, + "vod_remarks":'' + }) + #print(videos) + return videos + #分类取结果 + def get_list(self,html,tid): + jRoot = json.loads(html) + videos = [] + data=jRoot['data'] + if data is None: + return [] + jsonList=data['list'] + for vod in jsonList: + url = vod['url'] + title =vod['title'] + img=vod['image'] + id=vod['id'] + try: + brief=vod['brief'] + except: + brief='' + try: + year=vod['year'] + except: + year='' + try: + actors=vod['actors'] + except: + actors='' + if len(url) == 0: + continue + guid="{0}###{1}###{2}###{3}###{4}###{5}###{6}###{7}".format(tid,title,url,img,id,year,actors,brief) + #print(vod_id) + videos.append({ + "vod_id":guid, + "vod_name":title, + "vod_pic":img, + "vod_remarks":'' + }) + return videos diff --git a/jtxtv09/py/央视影视.py b/jtxtv09/py/央视影视.py new file mode 100644 index 0000000..20f8581 --- /dev/null +++ b/jtxtv09/py/央视影视.py @@ -0,0 +1,242 @@ +#coding=utf-8 +#!/usr/bin/python +import sys +sys.path.append('..') +from base.spider import Spider +import json +import time +import base64 +import requests + +class Spider(Spider): + def getName(self): + return "央视综艺" + + def init(self, extend=""): + print("============{0}============".format(extend)) + pass + + def isVideoFormat(self, url): + pass + + def manualVideoCheck(self): + pass + + def homeContent(self, filter): + result = {} + cateManual = { + "中华情": "TOPC1451541564922207", + "回声嘹亮": "TOPC1451535575561597", + "你好生活第三季": "TOPC1627961377879898", + "我的艺术清单": "TOPC1582272259917160", + "黄金100秒": "TOPC1451468496522494", + "非常6+1": "TOPC1451467940101208", + "向幸福出发": "TOPC1451984638791216", + "幸福账单": "TOPC1451984801613379", + "中国文艺报道": "TOPC1601348042760302", + "舞蹈世界": "TOPC1451547605511387", + "艺览天下": "TOPC1451984851125433", + "天天把歌唱": "TOPC1451535663610626", + "金牌喜剧班": "TOPC1611826337610628", + "环球综艺秀": "TOPC1571300682556971", + "挑战不可能第五季": "TOPC1579169060379297", + "我们有一套": "TOPC1451527089955940", + "为了你": "TOPC1451527001597710", + "朗读者第一季": "TOPC1487120479377477", + "挑战不可能第二季": "TOPC1474277421637816", + "精彩一刻": "TOPC1451464786232149", + "挑战不可能之加油中国": "TOPC1547519813971570", + "挑战不可能第一季": "TOPC1452063816677656", + "机智过人第三季": "TOPC1564019920570762", + "经典咏流传第二季": "TOPC1547521714115947", + "挑战不可能第三季": "TOPC1509500865106312", + "经典咏流传第一季": "TOPC1513676755770201", + "欢乐中国人第二季": "TOPC1516784350726581", + "故事里的中国第一季": "TOPC1569729252342702", + "你好生活第二季": "TOPC1604397385056621", + "喜上加喜": "TOPC1590026042145705", + "走在回家的路上": "TOPC1577697653272281", + "综艺盛典": "TOPC1451985071887935", + "艺术人生": "TOPC1451984891490556", + "全家好拍档": "TOPC1474275463547690", + "大魔术师": "TOPC1451984047073332", + "欢乐一家亲": "TOPC1451984214170587", + "开心辞典": "TOPC1451984378754815", + "综艺星天地": "TOPC1451985188986150", + "激情广场": "TOPC1451984341218765", + "笑星大联盟": "TOPC1451984731428297", + "天天乐": "TOPC1451984447718918", + "欢乐英雄": "TOPC1451984242834620", + "欢乐中国行": "TOPC1451984301286720", + "我爱满堂彩": "TOPC1451538709371329", + "综艺头条": "TOPC1569226855085860", + "中华情": "TOPC1451541564922207", + "魔法奇迹": "TOPC1451542029126607" + } + classes = [] + for k in cateManual: + classes.append({ + 'type_name': k, + 'type_id': cateManual[k] + }) + result['class'] = classes + if filter: + result['filters'] = self.config['filter'] + return result + + def homeVideoContent(self): + result = { + 'list': [] + } + return result + + def categoryContent(self, tid, pg, filter, extend): + result = {} + extend['id'] = tid + extend['p'] = pg + filterParams = ["id", "p", "d"] + params = ["", "", ""] + for idx in range(len(filterParams)): + fp = filterParams[idx] + if fp in extend.keys(): + params[idx] = '{0}={1}'.format(filterParams[idx], extend[fp]) + suffix = '&'.join(params) + url = 'https://api.cntv.cn/NewVideo/getVideoListByColumn?{0}&n=20&sort=desc&mode=0&serviceId=tvcctv&t=json'.format(suffix) + if not tid.startswith('TOPC'): + url = 'https://api.cntv.cn/NewVideo/getVideoListByAlbumIdNew?{0}&n=20&sort=desc&mode=0&serviceId=tvcctv&t=json'.format(suffix) + rsp = self.fetch(url, headers=self.header) + jo = json.loads(rsp.text) + vodList = jo['data']['list'] + videos = [] + for vod in vodList: + guid = vod['guid'] + title = vod['title'] + img = vod['image'] + brief = vod['brief'] + videos.append({ + "vod_id": guid + "###" + img, + "vod_name": title, + "vod_pic": img, + "vod_remarks": '' + }) + result['list'] = videos + result['page'] = pg + result['pagecount'] = 9999 + result['limit'] = 90 + result['total'] = 999999 + return result + + def detailContent(self, array): + aid = array[0].split('###') + tid = aid[0] + url = "https://vdn.apps.cntv.cn/api/getHttpVideoInfo.do?pid={0}".format(tid) + + rsp = self.fetch(url, headers=self.header) + jo = json.loads(rsp.text) + title = jo['title'].strip() + link = jo['hls_url'].strip() + vod = { + "vod_id": tid, + "vod_name": title, + "vod_pic": aid[1], + "type_name": '', + "vod_year": "", + "vod_area": "", + "vod_remarks": "", + "vod_actor": "", + "vod_director": "", + "vod_content": "" + } + vod['vod_play_from'] = 'CCTV' + vod['vod_play_url'] = title + "$" + link + + result = { + 'list': [vod] + } + return result + + def searchContent(self, key, quick): + result = { + 'list': [] + } + return result + + def playerContent(self, flag, id, vipFlags): + result = {} + # 先尝试获取原始m3u8文件 + rsp = self.fetch(id, headers=self.header) + content = rsp.text.strip() + + if not content: + # 如果获取失败，直接返回原始链接 + result["parse"] = 0 + result["playUrl"] = '' + result["url"] = id + result["header"] = self.header + return result + + arr = content.split('\n') + urlPrefix = self.regStr(id, '(http[s]?://[a-zA-z0-9.]+)/') + + # 尝试获取高清链接 + resolutions = ['2000', '1200', '800'] # 从高到低尝试 + final_url = id # 默认使用原始链接 + + for res in resolutions: + try: + subUrl = arr[-1].split('/') + subUrl[3] = res + subUrl[-1] = f'{res}.m3u8' + hdUrl = urlPrefix + '/'.join(subUrl) + + # 检查高清链接是否有效 + hdRsp = requests.head(hdUrl, headers=self.header, timeout=5) + if hdRsp.status_code == 200: + final_url = hdUrl + break + except: + continue + + result["parse"] = 0 + result["playUrl"] = '' + result["url"] = final_url + result["header"] = self.header + return result + + config = { + "player": {}, + "filter": { + "TOPC1451557970755294": [ + { + "key": "d", + "name": "年份", + "value": [ + {"n": "全部", "v": ""}, + {"n": "2023", "v": "2023"}, + {"n": "2022", "v": "2022"}, + {"n": "2021", "v": "2021"}, + {"n": "2020", "v": "2020"}, + {"n": "2019", "v": "2019"}, + {"n": "2018", "v": "2018"}, + {"n": "2017", "v": "2017"}, + {"n": "2016", "v": "2016"}, + {"n": "2015", "v": "2015"}, + {"n": "2014", "v": "2014"}, + {"n": "2013", "v": "2013"}, + {"n": "2012", "v": "2012"}, + {"n": "2011", "v": "2011"}, + {"n": "2010", "v": "2010"}, + {"n": "2009", "v": "2009"} + ] + } + ] + } + } + header = { + "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.54 Safari/537.36", + "Referer": "https://www.cctv.com/", + "Origin": "https://www.cctv.com" + } + + def localProxy(self, param): + return [200, "video/MP2T", None, ""] \ No newline at end of file diff --git a/jtxtv09/py/文才影视.py b/jtxtv09/py/文才影视.py new file mode 100644 index 0000000..700c2b0 --- /dev/null +++ b/jtxtv09/py/文才影视.py @@ -0,0 +1,225 @@ +# -*- coding: utf-8 -*- +# by @嗷呜 +import json +import sys +import threading +import uuid +import requests +sys.path.append('..') +from base.spider import Spider +import time +from Crypto.Hash import MD5, SHA1 + +class Spider(Spider): + ''' + 配置示例： + { + "key": "xxxx", + "name": "xxxx", + "type": 3, + "api": ".所在路径/金牌.py", + "searchable": 1, + "quickSearch": 1, + "filterable": 1, + "changeable": 1, + "ext": { + "site": "https://www.jiabaide.cn,域名2,域名3" + } + }, + ''' + def init(self, extend=""): + if extend: + hosts=json.loads(extend)['site'] + self.host = self.host_late(hosts) + pass + + def getName(self): + pass + + def isVideoFormat(self, url): + pass + + def manualVideoCheck(self): + pass + + def destroy(self): + pass + + def homeContent(self, filter): + cdata = self.fetch(f"{self.host}/api/mw-movie/anonymous/get/filer/type", headers=self.getheaders()).json() + fdata = self.fetch(f"{self.host}/api/mw-movie/anonymous/v1/get/filer/list", headers=self.getheaders()).json() + result = {} + classes = [] + filters={} + for k in cdata['data']: + classes.append({ + 'type_name': k['typeName'], + 'type_id': str(k['typeId']), + }) + sort_values = [{"n": "最近更新", "v": "2"},{"n": "人气高低", "v": "3"}, {"n": "评分高低", "v": "4"}] + for tid, d in fdata['data'].items(): + current_sort_values = sort_values.copy() + if tid == '1': + del current_sort_values[0] + filters[tid] = [ + {"key": "type", "name": "类型", + "value": [{"n": i["itemText"], "v": i["itemValue"]} for i in d["typeList"]]}, + + *([] if not d["plotList"] else [{"key": "v_class", "name": "剧情", + "value": [{"n": i["itemText"], "v": i["itemText"]} + for i in d["plotList"]]}]), + + {"key": "area", "name": "地区", + "value": [{"n": i["itemText"], "v": i["itemText"]} for i in d["districtList"]]}, + + {"key": "year", "name": "年份", + "value": [{"n": i["itemText"], "v": i["itemText"]} for i in d["yearList"]]}, + + {"key": "lang", "name": "语言", + "value": [{"n": i["itemText"], "v": i["itemText"]} for i in d["languageList"]]}, + + {"key": "sort", "name": "排序", "value": current_sort_values} + ] + result['class'] = classes + result['filters'] = filters + return result + + def homeVideoContent(self): + data1 = self.fetch(f"{self.host}/api/mw-movie/anonymous/v1/home/all/list", headers=self.getheaders()).json() + data2=self.fetch(f"{self.host}/api/mw-movie/anonymous/home/hotSearch",headers=self.getheaders()).json() + data=[] + for i in data1['data'].values(): + data.extend(i['list']) + data.extend(data2['data']) + vods=self.getvod(data) + return {'list':vods} + + def categoryContent(self, tid, pg, filter, extend): + + params = { + "area": extend.get('area', ''), + "filterStatus": "1", + "lang": extend.get('lang', ''), + "pageNum": pg, + "pageSize": "30", + "sort": extend.get('sort', '1'), + "sortBy": "1", + "type": extend.get('type', ''), + "type1": tid, + "v_class": extend.get('v_class', ''), + "year": extend.get('year', '') + } + data = self.fetch(f"{self.host}/api/mw-movie/anonymous/video/list?{self.js(params)}", headers=self.getheaders(params)).json() + result = {} + result['list'] = self.getvod(data['data']['list']) + result['page'] = pg + result['pagecount'] = 9999 + result['limit'] = 90 + result['total'] = 999999 + return result + + def detailContent(self, ids): + data=self.fetch(f"{self.host}/api/mw-movie/anonymous/video/detail?id={ids[0]}",headers=self.getheaders({'id':ids[0]})).json() + vod=self.getvod([data['data']])[0] + vod['vod_play_from']='文才' + vod['vod_play_url'] = '#'.join( + f"{i['name'] if len(vod['episodelist']) > 1 else vod['vod_name']}${ids[0]}@@{i['nid']}" for i in + vod['episodelist']) + vod.pop('episodelist', None) + return {'list':[vod]} + + def searchContent(self, key, quick, pg="1"): + params = { + "keyword": key, + "pageNum": pg, + "pageSize": "8", + "sourceCode": "1" + } + data=self.fetch(f"{self.host}/api/mw-movie/anonymous/video/searchByWord?{self.js(params)}",headers=self.getheaders(params)).json() + vods=self.getvod(data['data']['result']['list']) + return {'list':vods,'page':pg} + + def playerContent(self, flag, id, vipFlags): + self.header = { + 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; ) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.6478.61 Chrome/126.0.6478.61 Not/A)Brand/8 Safari/537.36', + 'sec-ch-ua-platform': '"Windows"', + 'DNT': '1', + 'sec-ch-ua': '"Not/A)Brand";v="8", "Chromium";v="126", "Google Chrome";v="126"', + 'sec-ch-ua-mobile': '?0', + 'Origin': self.host, + 'Referer': f'{self.host}/' + } + ids=id.split('@@') + pdata = self.fetch(f"{self.host}/api/mw-movie/anonymous/v2/video/episode/url?clientType=1&id={ids[0]}&nid={ids[1]}",headers=self.getheaders({'clientType':'1','id': ids[0], 'nid': ids[1]})).json() + vlist=[] + for i in pdata['data']['list']:vlist.extend([i['resolutionName'],i['url']]) + return {'parse':0,'url':vlist,'header':self.header} + + def localProxy(self, param): + pass + + def host_late(self, url_list): + if isinstance(url_list, str): + urls = [u.strip() for u in url_list.split(',')] + else: + urls = url_list + if len(urls) <= 1: + return urls[0] if urls else '' + + results = {} + threads = [] + + def test_host(url): + try: + start_time = time.time() + response = requests.head(url, timeout=1.0, allow_redirects=False) + delay = (time.time() - start_time) * 1000 + results[url] = delay + except Exception as e: + results[url] = float('inf') + for url in urls: + t = threading.Thread(target=test_host, args=(url,)) + threads.append(t) + t.start() + for t in threads: + t.join() + return min(results.items(), key=lambda x: x[1])[0] + + def md5(self, sign_key): + md5_hash = MD5.new() + md5_hash.update(sign_key.encode('utf-8')) + md5_result = md5_hash.hexdigest() + return md5_result + + def js(self, param): + return '&'.join(f"{k}={v}" for k, v in param.items()) + + def getheaders(self, param=None): + if param is None:param = {} + t=str(int(time.time()*1000)) + param['key']='cb808529bae6b6be45ecfab29a4889bc' + param['t']=t + sha1_hash = SHA1.new() + sha1_hash.update(self.md5(self.js(param)).encode('utf-8')) + sign = sha1_hash.hexdigest() + deviceid = str(uuid.uuid4()) + headers = { + 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; ) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.6478.61 Chrome/126.0.6478.61 Not/A)Brand/8 Safari/537.36', + 'Accept': 'application/json, text/plain, */*', + 'sign': sign, + 't': t, + 'deviceid':deviceid + } + return headers + + def convert_field_name(self, field): + field = field.lower() + if field.startswith('vod') and len(field) > 3: + field = field.replace('vod', 'vod_') + if field.startswith('type') and len(field) > 4: + field = field.replace('type', 'type_') + return field + + def getvod(self, array): + return [{self.convert_field_name(k): v for k, v in item.items()} for item in array] +