123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843844845846847848849850851852853854855856857858859860861862863864865866867868869870871872873874875876877878879880881882883884885886887888889890891892893894895896897898899900901902903904905906907908909910911912913914915916917918919920921922923924925926927928929930931932933934935936937938939940941942943944945946947948949950951952953954955956957958959960961962963964965966967968969970971972973974975976977978979980981982983984985986987988989990991992993994995996997998999100010011002100310041005100610071008100910101011101210131014101510161017101810191020102110221023102410251026102710281029103010311032103310341035103610371038103910401041104210431044104510461047104810491050105110521053105410551056105710581059106010611062 |
- # coding=utf-8
- # !/usr/bin/python
- import os.path
- import random
- import sys
- sys.path.append('..')
- try:
- from base.spider import Spider as BaseSpider
- #from base.spider import BaseSpider
- except ImportError:
- from t4.base.spider import BaseSpider
- import json
- import time
- import base64
- import datetime
- import re
- from urllib import request, parse
- from pathlib import Path
- import urllib
- import urllib.request
- """
- 配置示例:
- t4的配置里ext节点会自动变成api对应query参数extend,但t4的ext字符串不支持路径格式,比如./开头或者.json结尾
- api里会自动含有ext参数是base64编码后的选中的筛选条件
- 错误示例,ext含有json:
- {
- "key":"hipy_cntv央视",
- "name":"cntv央视(hipy_t4)",
- "type":4,
- "api":"http://192.168.31.49:5707/api/v1/vod/cntv央视?api_ext={{host}}/txt/hipy/cntv央视.json",
- "searchable":1,
- "quickSearch":1,
- "filterable":0,
- "ext":"cntv央视.json"
- }
- 正确示例。同时存在ext和api_ext会优先取ext作为extend加载init
- {
- "key":"hipy_t4_cntv央视",
- "name":"cntv央视(hipy_t4)",
- "type":4,
- "api":"http://192.168.31.49:5707/api/v1/vod/cntv央视?api_ext={{host}}/txt/hipy/cntv央视.json",
- "searchable":1,
- "quickSearch":0,
- "filterable":1,
- "ext":"{{host}}/files/hipy/cntv央视.json"
- },
- {
- "key": "hipy_t3_cntv央视",
- "name": "cntv央视(hipy_t3)",
- "type": 3,
- "api": "{{host}}/txt/hipy/cntv央视.py",
- "searchable": 1,
- "quickSearch": 0,
- "filterable": 1,
- "ext": "{{host}}/files/hipy/cntv央视.json"
- },
- """
- class Spider(BaseSpider): # 元类 默认的元类 type
- module = None
- def getDependence(self):
- return ['base_spider']
- def getName(self):
- return "中央电视台" # 可搜索
- def init_api_ext_file(self):
- ext_file = __file__.replace('.py', '.json')
- print(f'ext_file:{ext_file}')
- # 特别节目网页: https://tv.cctv.com/yxg/index.shtml?spm=C28340.PlFTqGe6Zk8M.E2PQtIunpEaz.65
- # 特别节目分类筛选获取页面: https://tv.cctv.com/yxg/tbjm/index.shtml
- # 纪录片网页: https://tv.cctv.com/yxg/index.shtml?spm=C28340.PlFTqGe6Zk8M.E2PQtIunpEaz.65
- # 纪录片分类筛选获取页面:https://tv.cctv.com/yxg/jlp/index.shtml
- # ==================== 获取特别节目的筛选条件 ======================
- r = self.fetch('https://tv.cctv.com/yxg/tbjm/index.shtml')
- html = r.text
- html = self.html(html)
- filter_tbjm = []
- lis = html.xpath('//*[@id="pindao"]/li')
- li_value = []
- for li in lis:
- li_value.append({
- 'n': ''.join(li.xpath('./span//text()')),
- 'v': ''.join(li.xpath('@datacd')),
- })
- # print(li_value)
- filter_tbjm.append({
- "key": "datapd-channel",
- "name": "频道",
- "value": li_value
- })
- lis = html.xpath('//*[@id="fenlei"]/li')
- li_value = []
- for li in lis:
- li_value.append({
- 'n': ''.join(li.xpath('./span//text()')),
- 'v': ''.join(li.xpath('@datalx')),
- })
- # print(li_value)
- filter_tbjm.append({
- "key": "datafl-sc",
- "name": "类型",
- "value": li_value
- })
- lis = html.xpath('//*[@id="zimu"]/li')
- li_value = []
- for li in lis:
- li_value.append({
- 'n': ''.join(li.xpath('./span//text()')),
- 'v': ''.join(li.xpath('@datazm')),
- })
- # print(li_value)
- filter_tbjm.append({
- "key": "dataszm-letter",
- "name": "首字母",
- "value": li_value
- })
- print(filter_tbjm)
- # ==================== 纪录片筛选获取 ======================
- r = self.fetch('https://tv.cctv.com/yxg/jlp/index.shtml')
- html = r.text
- html = self.html(html)
- filter_jlp = []
- lis = html.xpath('//*[@id="pindao"]/li')
- li_value = []
- for li in lis:
- li_value.append({
- 'n': ''.join(li.xpath('./span//text()')),
- 'v': ''.join(li.xpath('@datacd')),
- })
- # print(li_value)
- filter_jlp.append({
- "key": "datapd-channel",
- "name": "频道",
- "value": li_value
- })
- lis = html.xpath('//*[@id="fenlei"]/li')
- li_value = []
- for li in lis:
- li_value.append({
- 'n': ''.join(li.xpath('./span//text()')),
- 'v': ''.join(li.xpath('@datalx')),
- })
- # print(li_value)
- filter_jlp.append({
- "key": "datafl-sc",
- "name": "类型",
- "value": li_value
- })
- lis = html.xpath('//*[@id="nianfen"]/li')
- li_value = []
- for li in lis:
- li_value.append({
- 'n': ''.join(li.xpath('./span//text()')),
- 'v': ''.join(li.xpath('@datanf')),
- })
- # print(li_value)
- filter_jlp.append({
- "key": "datanf-year",
- "name": "年份",
- "value": li_value
- })
- lis = html.xpath('//*[@id="zimu"]/li')
- li_value = []
- for li in lis:
- li_value.append({
- 'n': ''.join(li.xpath('./span//text()')),
- 'v': ''.join(li.xpath('@datazm')),
- })
- # print(li_value)
- filter_jlp.append({
- "key": "dataszm-letter",
- "name": "首字母",
- "value": li_value
- })
- print(filter_jlp)
- ext_file_dict = {
- "特别节目": filter_tbjm,
- "纪录片": filter_jlp,
- }
- # print(json.dumps(ext_file_dict,ensure_ascii=False,indent=4))
- with open(ext_file, mode='w+', encoding='utf-8') as f:
- # f.write(json.dumps(ext_file_dict,ensure_ascii=False,indent=4))
- f.write(json.dumps(ext_file_dict, ensure_ascii=False))
- def init(self, extend=""):
- def init_file(ext_file):
- ext_file = Path(ext_file).as_posix()
- # print(f'ext_file:{ext_file}')
- if os.path.exists(ext_file):
- # print('存在扩展文件')
- with open(ext_file, mode='r', encoding='utf-8') as f:
- try:
- ext_dict = json.loads(f.read())
- # print(ext_dict)
- self.config['filter'].update(ext_dict)
- except Exception as e:
- print(f'更新扩展筛选条件发生错误:{e}')
- print("============依赖列表:{0}============".format(extend))
- ext = self.extend
- print("============ext:{0}============".format(ext))
- if isinstance(ext, str) and ext:
- if ext.startswith('./'):
- ext_file = os.path.join(os.path.dirname(__file__), ext)
- init_file(ext_file)
- elif ext.startswith('http'):
- try:
- r = self.fetch(ext)
- self.config['filter'].update(r.json())
- except Exception as e:
- print(f'更新扩展筛选条件发生错误:{e}')
- elif not ext.startswith('./') and not ext.startswith('http'):
- ext_file = os.path.join(os.path.dirname(__file__), './' + ext + '.json')
- init_file(ext_file)
- # ==================== 栏目大全加载年月筛选 ======================
- lanmu_list = self.config['filter']['栏目大全']
- lanmu_keys_list = [lanmu['key'] for lanmu in lanmu_list]
- if 'year' not in lanmu_keys_list:
- currentYear = datetime.date.today().year
- yearList = [{"n": "全部", "v": ""}]
- for year in range(currentYear, currentYear - 10, -1):
- yearList.append({"n": year, "v": year})
- yearDict = {"key": "year", "name": "年份", "value": yearList}
- lanmu_list.append(yearDict)
- if 'month' not in lanmu_keys_list:
- monthList = [{"n": "全部", "v": ""}]
- for month in range(1, 13):
- text = str(month).rjust(2, '0')
- monthList.append({"n": text, "v": text})
- monthDict = {"key": "month", "name": "月份", "value": monthList}
- lanmu_list.append(monthDict)
- # 装载模块,这里只要一个就够了
- if isinstance(extend, list):
- for lib in extend:
- if '.Spider' in str(type(lib)):
- self.module = lib
- break
- def isVideoFormat(self, url):
- pass
- def manualVideoCheck(self):
- pass
- def homeContent(self, filter):
- result = {}
- cateManual = {
- "4K专区": "4K专区",
- "栏目大全": "栏目大全",
- "特别节目": "特别节目",
- "纪录片": "纪录片",
- "电视剧": "电视剧",
- "动画片": "动画片",
-
- }
- 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': []
- }
- if self.module:
- result = self.module.homeVideoContent()
- 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
- year_prefix = '' # 栏目大全的年月筛选过滤
- 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 == '栏目大全':
- 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']
- year = extend.get('year') or ''
- month = extend.get('month') or ''
- if year:
- year_prefix = year + month
- 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
- elif tid == '4K专区':
- cid = 'CHAL1558416868484111'
- url = 'https://api.cntv.cn/NewVideo/getLastVideoList4K?serviceId=cctv4k&cid={0}&p={1}&n={2}&t=json&cb=ko'.format(
- cid, pg, pagecount
- )
- elif tid == '频道直播':
- url = 'https://tv.cctv.com/epg/index.shtml'
- else:
- url = 'https://tv.cctv.com/epg/index.shtml'
- videos = []
- htmlText = self.fetch(url).text
- if tid == '栏目大全':
- index = htmlText.rfind(');')
- if index > -1:
- htmlText = htmlText[3:index]
- videos = self.get_list1(html=htmlText, tid=tid, year_prefix=year_prefix)
- elif tid == '4K专区':
- index = htmlText.rfind(');')
- if index > -1:
- htmlText = htmlText[3:index]
- videos = self.get_list_4k(html=htmlText, tid=tid)
- elif tid == '频道直播':
- html = self.html(htmlText)
- lis = html.xpath('//*[@id="jiemudan01"]//div[contains(@class,"channel_con")]//ul/li')
- for li in lis:
- vid = ''.join(li.xpath('./img/@title'))
- pic = ''.join(li.xpath('./img/@src'))
- pic = self.urljoin('https://tv.cctv.com/epg/index.shtml', pic)
- videos.append({
- 'vod_id': '||'.join([tid, vid, f'https://tv.cctv.com/live/{vid}/', pic]),
- 'vod_name': vid,
- 'vod_pic': pic,
- 'vod_mark': '',
- })
- 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 = {}
- year_prefix = ''
- did = array[0]
- if '$$$' in did:
- year_prefix = did.split('$$$')[0]
- did = did.split('$$$')[1]
- aid = did.split('||')
- tid = aid[0]
- title = aid[1]
- lastVideo = aid[2]
- logo = aid[3]
- if tid == '频道直播':
- vod = {
- "vod_id": did,
- "vod_name": title.replace(' ', ''),
- "vod_pic": logo,
- "vod_content": f'频道{title}正在直播中',
- "vod_play_from": '道长在线直播',
- "vod_play_url": f'在线观看${title}||{lastVideo}',
- }
- result = {'list': [vod]}
- return result
- id = aid[4]
- vod_year = aid[5]
- actors = aid[6] if len(aid) > 6 else ''
- brief = aid[7] if len(aid) > 7 else '' # get请求最长255,这个描述会有可能直接被干没了。
- fromId = 'CCTV'
- if tid == "栏目大全":
- lastUrl = 'https://api.cntv.cn/video/videoinfoByGuid?guid={0}&serviceId=tvcctv'.format(id)
- # htmlTxt = self.webReadFile(urlStr=lastUrl, header=self.header)
- htmlTxt = self.fetch(lastUrl).text
- topicId = json.loads(htmlTxt)['ctid']
- url = 'https://api.cntv.cn/NewVideo/getVideoListByColumn'
- # params = {
- # 'p': '1',
- # 'n': '100',
- # 't': 'json',
- # 'mode': '0',
- # 'sort': 'desc',
- # 'serviceId': 'tvcctv',
- # 'd': year_prefix,
- # 'id': topicId
- # }
- # htmlTxt = self.fetch(url,data=params).text
- Url = "{0}?id={1}&d=&p=1&n=100&sort=desc&mode=0&serviceId=tvcctv&t=json&d={2}".format(
- url, topicId, year_prefix)
- elif tid == "4K专区":
- Url = 'https://api.cntv.cn/NewVideo/getVideoListByAlbumIdNew?id={0}&serviceId=cctv4k&p=1&n=100&mode=0&pub=1'.format(
- id)
- print(Url)
- 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)
- htmlTxt = self.fetch(Url).text
- 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)
- htmlTxt = self.fetch(lastVideo).text
- if tid == "电视剧" or tid == "纪录片" or tid == "4K专区":
- patternTxt = r"'title':\s*'(?P<title>.+?)',\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 == "栏目大全":
- 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": did,
- "vod_name": title.replace(' ', ''),
- "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, pg=1):
- 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)
- htmlTxt = self.fetch(Url).text
- 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)
- elif flag == '道长在线直播':
- # _url = id
- title = id.split('||')[0] # 获取标题
- _url = f'https://vdn.live.cntv.cn/api2/liveHtml5.do?channel=pc://cctv_p2p_hd{title}&channel_id={title}'
- htmlTxt = self.fetch(_url).text
- # print(htmlTxt)
- vdata = self.regStr(htmlTxt, "var .*?=.*?'(.*?)';")
- vdata = self.str2json(vdata)
- print(vdata)
- url = vdata['hls_url']['hls1']
- print(url)
- url = self.fixm3u8_url(url)
- else:
- try:
- # htmlTxt = self.webReadFile(urlStr=id, header=self.header)
- htmlTxt = self.fetch(id).text
- guid = self.get_RegexGetText(Text=htmlTxt, 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
- # 分类抓取地址:
- # 栏目大全:https://tv.cctv.com/lm/index.shtml?spm=C28340.Pu9TN9YUsfNZ.E2PQtIunpEaz.24
- # 电视剧:https://tv.cctv.com/yxg/index.shtml?spm=C28340.PlFTqGe6Zk8M.E2PQtIunpEaz.65#datacid=dsj&datafl=&datadq=&fc=%E7%94%B5%E8%A7%86%E5%89%A7&datanf=&dataszm=
- # 动画片:https://tv.cctv.com/yxg/index.shtml?spm=C28340.PlFTqGe6Zk8M.E2PQtIunpEaz.65#datacid=dhp&datafl=&datadq=&fc=%E5%8A%A8%E7%94%BB%E7%89%87&dataszm=
- # 记录片:https://tv.cctv.com/yxg/index.shtml?spm=C28340.PlFTqGe6Zk8M.E2PQtIunpEaz.65#datacid=jlp&datapd=&datafl=&fc=%E7%BA%AA%E5%BD%95%E7%89%87&datanf=&dataszm=
- # 特别节目:https://tv.cctv.com/yxg/index.shtml?spm=C28340.PlFTqGe6Zk8M.E2PQtIunpEaz.65#datacid=tbjm&datapd=&datafl=&fc=%E7%89%B9%E5%88%AB%E8%8A%82%E7%9B%AE&datajr=&dataszm=
- 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": "2024", "v": "2024"}, {"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": "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": "2024", "v": "2024"}, {"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": "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"}]}
- ],
- "栏目大全": [{"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"}]},
- ]
- }
- }
- 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, params):
- 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(" ", " ")
- def hookM3u8(self, url):
- """
- https://www.52pojie.cn/thread-1932358-1-1.html
- JavaScript:$.ajaxSettings.async = false; var s = ""; let a = $.get(vodh5player.playerList[0].ads.contentSrc); for (var m = 0; m < a.responseText.match(/asp.*?m3u8/g).length; m++) { s = s + "https://hls.cntv.myalicdn.com//asp" + a.responseText.match(/asp.*?m3u8/g)[m].slice(7) + "\n\n" }; var blob = new Blob([s], { type: "text/plain" }); var url = URL.createObjectURL(blob); window.open(url);
- @param url:
- @return:
- """
- url = url or ''
- hook1 = lambda x: x.replace('asp/', 'asp//', 1)
- hook2 = lambda x: x.replace('hls/', 'hls//', 1)
- hook3 = lambda x: x.replace('https://hls.cntv.myhwcdn.cn', 'https://dh5.cntv.myhwcdn.cn/', 1)
- hook4 = lambda x: x.replace('https://hls.cntv.myalicdn.com', 'https://dh5.cntv.myhwcdn.cn/', 1)
- hook5 = lambda x: x.replace('https://hls.cntv.lxdns.com', 'https://dh5.cntv.myhwcdn.cn/', 1)
- hook6 = lambda x: x.replace('http://hls.cntv.kcdnvip.com', 'https://dh5.cntv.myhwcdn.cn/', 1)
- hook7 = lambda x: x.replace('https://newcntv.qcloudcdn.com', 'https://dh5.cntv.myhwcdn.cn/', 1)
- hook8 = lambda x: x.replace('https://dh5aliwx01.v.cntv.cn', 'https://dh5.cntv.myhwcdn.cn/', 1)
- hooks = [hook1, hook2, hook3, hook4, hook5, hook6, hook7, hook8]
- hook = random.choice(hooks)
- return hook(url)
- # 取m3u8
- def get_m3u8(self, urlTxt):
- """
- https://blog.csdn.net/panwang666/article/details/135347859
- JavaScript:jQuery.getJSON("https://vdn.apps.cntv.cn/api/getHttpVideoInfo.do?pid="+guid,function(result){document.writeln(result.hls_url.link(result.hls_url));});
- https://newcntv.qcloudcdn.com/asp/hls/main/0303000a/3/default/3628bb15af644f588dc91ec68425b9ac/main.m3u8?maxbr=2048
- @param urlTxt:
- @return:
- """
- url = "https://vdn.apps.cntv.cn/api/getHttpVideoInfo.do?pid={0}".format(urlTxt)
- # htmlTxt = self.webReadFile(urlStr=url, header=self.header)
- htmlTxt = self.fetch(url).text
- jo = json.loads(htmlTxt)
- link = jo['hls_url'].strip()
- # print('hls_url:',link)
- # 获取域名前缀
- urlPrefix = self.get_RegexGetText(Text=link, RegexText='(http[s]?://[a-zA-z0-9.]+)/', Index=1)
- # 域名前缀指定替换,然后可以获取到更高质量的视频列表
- # /asp/h5e/hls/2000/0303000a/3/default/3628bb15af644f588dc91ec68425b9ac/2000.m3u8
- new_link = link.replace(f'{urlPrefix}/asp/hls/', 'https://dh5.cntv.myhwcdn.cn/asp/h5e/hls/').split('?')[0]
- # print('new_link:',new_link)
- html = self.webReadFile(urlStr=new_link, header=self.header)
- content = html.strip()
- arr = content.split('\n')
- subUrl = arr[-1].split('/')
- # hdUrl = urlPrefix + arr[-1]
- # subUrl[3] = '2000'
- # subUrl[-1] = '2000.m3u8'
- # hdUrl = urlPrefix + '/'.join(subUrl)
- maxVideo = subUrl[-1].replace('.m3u8', '')
- hdUrl = link.replace('main', maxVideo)
- hdUrl = hdUrl.replace(urlPrefix, 'https://dh5.cntv.myhwcdn.cn/')
- hdRsp = self.TestWebPage(urlStr=hdUrl, header=self.header)
- if hdRsp == 200:
- url = hdUrl.split('?')[0]
- url = self.hookM3u8(url)
- self.log(f'视频链接: {url}')
- else:
- url = ''
- return url
- def fixm3u8_url(self, url):
- # 获取域名前缀
- urlPrefix = self.get_RegexGetText(Text=url, RegexText='(http[s]?://[a-zA-z0-9.]+)/', Index=1)
- # 域名前缀指定替换,然后可以获取到更高质量的视频列表
- new_link = url.split('?')[0]
- # print(new_link)
- html = self.webReadFile(urlStr=new_link, header=self.header)
- content = html.strip()
- # print(content)
- arr = content.split('\n')
- subUrl = arr[3] if 'EXT-X-VERSION' in content else arr[2]
- hdUrl = self.urljoin(new_link, subUrl).split('?')[0]
- # hdUrl = hdUrl.replace(urlPrefix, 'https://dh5.cntv.myhwcdn.cn/')
- hdRsp = self.TestWebPage(urlStr=hdUrl, header=self.header)
- if hdRsp == 200:
- url = hdUrl
- self.log(f'视频链接: {url}')
- 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
- guids = [tid, title, url, img, id, year, '', brief]
- guid = "||".join(guids)
- videos.append({
- "vod_id": guid,
- "vod_name": title,
- "vod_pic": img,
- "vod_remarks": year
- })
- return videos
- def get_list1(self, html, tid, year_prefix=None):
- jRoot = json.loads(html)
- videos = []
- data = jRoot['response']
- if data is None:
- return []
- jsonList = data['docs']
- for vod in jsonList:
- id = vod['lastVIDE']['videoSharedCode']
- desc = vod['lastVIDE']['videoTitle']
- 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
- guids = [tid, title, url, img, id, year, actors, brief]
- guid = "||".join(guids)
- # print(vod_id)
- videos.append({
- "vod_id": year_prefix + '$$$' + guid if year_prefix else guid,
- "vod_name": title,
- "vod_pic": img,
- "vod_remarks": desc.split('》')[1].strip() if '》' in desc else desc.strip()
- })
- # 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
- guids = [tid, title, url, img, id, year, actors, brief]
- guid = "||".join(guids)
- # print(vod_id)
- videos.append({
- "vod_id": guid,
- "vod_name": title,
- "vod_pic": img,
- "vod_remarks": ''
- })
- return videos
- # 4k分类取结果
- def get_list_4k(self, html, tid):
- jRoot = json.loads(html)
- videos = []
- data = jRoot['data']
- if data is None:
- return []
- jsonList = data['list']
- for vod in jsonList:
- vod_remarks = vod['title']
- id = vod['id']
- vod = vod['last_video']
- img = vod['image']
- url = vod['url']
- title = vod['title']
- brief = vod.get('brief') or ''
- year = vod.get('year') or ''
- actors = vod.get('actors') or ''
- if len(url) == 0:
- continue
- guids = [tid, title, url, img, id, year, actors, brief]
- guid = "||".join(guids)
- # print(vod_id)
- videos.append({
- "vod_id": guid,
- "vod_name": title,
- "vod_pic": img,
- "vod_remarks": vod_remarks
- })
- return videos
- if __name__ == '__main__':
- from t4.core.loader import t4_spider_init
- spider = Spider()
- t4_spider_init(spider)
- # print(spider.homeContent(True))
- # print(spider.homeVideoContent())
- # spider.init_api_ext_file()
- # url = 'https://api.cntv.cn/lanmu/columnSearch?&fl=&fc=%E6%96%B0%E9%97%BB&cid=&p=1&n=20&serviceId=tvcctv&t=jsonp&cb=Callback'
- # url = 'https://api.cntv.cn/lanmu/columnSearch?&fl=&fc=&cid=&p=1&n=20&serviceId=tvcctv&t=json&cb=ko'
- # r = spider.fetch(url)
- # print(r.text)
- # home_content = spider.homeContent(None)
- # print(home_content)
- cate_content = spider.categoryContent('栏目大全', 1, {'cid': 'n'}, {})
- # cate_content = spider.categoryContent('频道直播', 1, None, None)
- print(cate_content)
- vid = cate_content['list'][0]['vod_id']
- print(vid)
- detail_content = spider.detailContent([vid])
- print(detail_content)
- # #
- vod_play_from = detail_content['list'][0]['vod_play_from']
- vod_play_url = detail_content['list'][0]['vod_play_url']
- print(vod_play_from, vod_play_url)
- _url = vod_play_url.split('#')[0].split('$')[1]
- print(_url)
- print('vod_play_from:', vod_play_from, ' vod_play_url:', _url)
- play = spider.playerContent(vod_play_from, _url, None)
- print(play)
- # play = spider.playerContent('道长在线直播', 'cctv1||https://tv.cctv.com/live/cctv1/', None)
- # print(play)
|