py_央库云.py 25 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505
  1. #coding=utf-8
  2. #!/usr/bin/python
  3. import sys
  4. sys.path.append('..')
  5. from base.spider import Spider
  6. import json
  7. import time
  8. import base64
  9. import re
  10. from urllib import request, parse
  11. import urllib
  12. import urllib.request
  13. import time
  14. class Spider(Spider): # 元类 默认的元类 type
  15. def getName(self):
  16. return "中央电视台"#可搜索
  17. def init(self,extend=""):
  18. print("============{0}============".format(extend))
  19. pass
  20. def destroy(self):
  21. pass
  22. def isVideoFormat(self,url):
  23. pass
  24. def manualVideoCheck(self):
  25. pass
  26. def homeContent(self,filter):
  27. result = {}
  28. cateManual = {
  29. "央视大全":"节目大全",
  30. "电视剧": "电视剧",
  31. "动画片": "动画片",
  32. "纪录片": "纪录片",
  33. "特别节目": "特别节目"
  34. }
  35. classes = []
  36. for k in cateManual:
  37. classes.append({
  38. 'type_name':k,
  39. 'type_id':cateManual[k]
  40. })
  41. result['class'] = classes
  42. if(filter):
  43. result['filters'] = self.config['filter']
  44. return result
  45. def homeVideoContent(self):
  46. result = {
  47. 'list':[]
  48. }
  49. return result
  50. def categoryContent(self,tid,pg,filter,extend):
  51. result = {}
  52. month = ""#月
  53. year = ""#年
  54. area=''#地区
  55. channel=''#频道
  56. datafl=''#类型
  57. letter=''#字母
  58. pagecount=24
  59. if tid=='动画片':
  60. id=urllib.parse.quote(tid)
  61. if 'datadq-area' in extend.keys():
  62. area=urllib.parse.quote(extend['datadq-area'])
  63. if 'dataszm-letter' in extend.keys():
  64. letter=extend['dataszm-letter']
  65. if 'datafl-sc' in extend.keys():
  66. datafl=urllib.parse.quote(extend['datafl-sc'])
  67. 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)
  68. elif tid=='纪录片':
  69. id=urllib.parse.quote(tid)
  70. if 'datapd-channel' in extend.keys():
  71. channel=urllib.parse.quote(extend['datapd-channel'])
  72. if 'datafl-sc' in extend.keys():
  73. datafl=urllib.parse.quote(extend['datafl-sc'])
  74. if 'datanf-year' in extend.keys():
  75. year=extend['datanf-year']
  76. if 'dataszm-letter' in extend.keys():
  77. letter=extend['dataszm-letter']
  78. 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)
  79. elif tid=='电视剧':
  80. id=urllib.parse.quote(tid)
  81. if 'datafl-sc' in extend.keys():
  82. datafl=urllib.parse.quote(extend['datafl-sc'])
  83. if 'datanf-year' in extend.keys():
  84. year=extend['datanf-year']
  85. if 'dataszm-letter' in extend.keys():
  86. letter=extend['dataszm-letter']
  87. 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)
  88. elif tid=='特别节目':
  89. id=urllib.parse.quote(tid)
  90. if 'datapd-channel' in extend.keys():
  91. channel=urllib.parse.quote(extend['datapd-channel'])
  92. if 'datafl-sc' in extend.keys():
  93. datafl=urllib.parse.quote(extend['datafl-sc'])
  94. if 'dataszm-letter' in extend.keys():
  95. letter=extend['dataszm-letter']
  96. 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)
  97. elif tid=='节目大全':
  98. cid=''#频道
  99. if 'cid' in extend.keys():
  100. cid=extend['cid']
  101. fc=''#分类
  102. if 'fc' in extend.keys():
  103. fc=extend['fc']
  104. fl=''#字母
  105. if 'fl' in extend.keys():
  106. fl=extend['fl']
  107. 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)
  108. pagecount=20
  109. else:
  110. url = 'https://tv.cctv.com/epg/index.shtml'
  111. videos=[]
  112. htmlText =self.webReadFile(urlStr=url,header=self.header)
  113. if tid=='节目大全':
  114. index=htmlText.rfind(');')
  115. if index>-1:
  116. htmlText=htmlText[3:index]
  117. videos =self.get_list1(html=htmlText,tid=tid)
  118. else:
  119. videos =self.get_list(html=htmlText,tid=tid)
  120. #print(videos)
  121. result['list'] = videos
  122. result['page'] = pg
  123. result['pagecount'] = 9999 if len(videos)>=pagecount else pg
  124. result['limit'] = 90
  125. result['total'] = 999999
  126. return result
  127. def detailContent(self,array):
  128. result={}
  129. aid = array[0].split('###')
  130. tid = aid[0]
  131. logo = aid[3]
  132. lastVideo = aid[2]
  133. title = aid[1]
  134. id= aid[4]
  135. vod_year= aid[5]
  136. actors= aid[6]
  137. brief= aid[7]
  138. fromId='CCTV'
  139. if tid=="节目大全":
  140. lastUrl = 'https://api.cntv.cn/video/videoinfoByGuid?guid={0}&serviceId=tvcctv'.format(id)
  141. htmlTxt = self.webReadFile(urlStr=lastUrl,header=self.header)
  142. topicId=json.loads(htmlTxt)['ctid']
  143. Url = "https://api.cntv.cn/NewVideo/getVideoListByColumn?id={0}&d=&p=1&n=100&sort=desc&mode=0&serviceId=tvcctv&t=json".format(topicId)
  144. htmlTxt = self.webReadFile(urlStr=Url,header=self.header)
  145. else:
  146. Url='https://api.cntv.cn/NewVideo/getVideoListByAlbumIdNew?id={0}&serviceId=tvcctv&p=1&n=100&mode=0&pub=1'.format(id)
  147. jRoot = ''
  148. videoList = []
  149. try:
  150. if tid=="搜索":
  151. fromId='中央台'
  152. videoList=[title+"$"+lastVideo]
  153. else:
  154. htmlTxt=self.webReadFile(urlStr=Url,header=self.header)
  155. jRoot = json.loads(htmlTxt)
  156. data=jRoot['data']
  157. jsonList=data['list']
  158. videoList=self.get_EpisodesList(jsonList=jsonList)
  159. if len(videoList)<1:
  160. htmlTxt=self.webReadFile(urlStr=lastVideo,header=self.header)
  161. if tid=="电视剧" or tid=="纪录片":
  162. 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>.+?)'"
  163. elif tid=="特别节目":
  164. patternTxt=r'class="tp1"><a\s*href="(?P<url>https://.+?)"\s*target="_blank"\s*title="(?P<title>.+?)"></a></div>'
  165. elif tid=="动画片":
  166. 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>.+?)'"
  167. elif tid=="节目大全":
  168. patternTxt=r'href="(?P<url>.+?)" target="_blank" alt="(?P<title>.+?)" title=".+?">'
  169. videoList=self.get_EpisodesList_re(htmlTxt=htmlTxt,patternTxt=patternTxt)
  170. fromId='央视'
  171. except:
  172. pass
  173. if len(videoList) == 0:
  174. return {}
  175. vod = {
  176. "vod_id":array[0],
  177. "vod_name":title,
  178. "vod_pic":logo,
  179. "type_name":tid,
  180. "vod_year":vod_year,
  181. "vod_area":"",
  182. "vod_remarks":'',
  183. "vod_actor":actors,
  184. "vod_director":'',
  185. "vod_content":brief
  186. }
  187. vod['vod_play_from'] = fromId
  188. vod['vod_play_url'] = "#".join(videoList)
  189. result = {
  190. 'list':[
  191. vod
  192. ]
  193. }
  194. return result
  195. def get_lineList(self,Txt,mark,after):
  196. circuit=[]
  197. origin=Txt.find(mark)
  198. while origin>8:
  199. end=Txt.find(after,origin)
  200. circuit.append(Txt[origin:end])
  201. origin=Txt.find(mark,end)
  202. return circuit
  203. def get_RegexGetTextLine(self,Text,RegexText,Index):
  204. returnTxt=[]
  205. pattern = re.compile(RegexText, re.M|re.S)
  206. ListRe=pattern.findall(Text)
  207. if len(ListRe)<1:
  208. return returnTxt
  209. for value in ListRe:
  210. returnTxt.append(value)
  211. return returnTxt
  212. def searchContent(self,key,quick):
  213. return self.searchContentPage(key, quick, '1')
  214. def searchContentPage(self, key, quick, page):
  215. key=urllib.parse.quote(key)
  216. 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)
  217. htmlTxt=self.webReadFile(urlStr=Url,header=self.header)
  218. videos=self.get_list_search(html=htmlTxt,tid='搜索')
  219. result = {
  220. 'list':videos
  221. }
  222. return result
  223. def playerContent(self, flag, id, vipFlags):
  224. result = {}
  225. url = ''
  226. parse = 0
  227. headers = {
  228. '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'
  229. }
  230. if flag == 'CCTV':
  231. url = self.get_m3u8(urlTxt=id)
  232. elif flag == '道长在线直播':
  233. title = id.split('||')[0] # 获取标题
  234. _url = f'https://vdn.live.cntv.cn/api2/liveHtml5.do?channel=pc://cctv_p2p_hd{title}&channel_id={title}'
  235. htmlTxt = self.fetch(_url).text
  236. vdata = self.regStr(htmlTxt, "var .*?=.*?'(.*?)';")
  237. vdata = self.str2json(vdata)
  238. print(vdata)
  239. url = vdata['hls_url']['hls1']
  240. print(url)
  241. url = self.fixm3u8_url(url)
  242. else:
  243. try:
  244. htmlTxt = self.fetch(id).text
  245. guid = self.get_RegexGetText(Text=htmlTxt, RegexText=r'var\sguid\s*=\s*"(.+?)";', Index=1)
  246. url = self.get_m3u8(urlTxt=guid)
  247. except:
  248. url = id
  249. parse = 1
  250. if url.find('https:') < 0:
  251. url = id
  252. parse = 1
  253. result["parse"] = parse # 1=嗅探,0=播放
  254. result["playUrl"] = ''
  255. result["url"] = url
  256. result["header"] = headers
  257. return result
  258. config = {
  259. "player": {},
  260. "filter": {
  261. "电视剧":[
  262. {"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"}]},
  263. {"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"}]},
  264. {"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"}]},
  265. {"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"}]}
  266. ],
  267. "动画片":[
  268. {"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"}]},
  269. {"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"}]},
  270. {"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"}]}
  271. ],
  272. "纪录片":[
  273. {"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"}]},
  274. {"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"}]},
  275. {"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"}]},
  276. {"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"}]}
  277. ],
  278. "特别节目":[
  279. {"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"}]},
  280. {"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"}]},
  281. {"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"}]}
  282. ],
  283. "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"}]}]
  284. }
  285. }
  286. header = {
  287. "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",
  288. "Host": "tv.cctv.com",
  289. "Referer": "https://tv.cctv.com/"
  290. }
  291. def localProxy(self,param):
  292. return [200, "video/MP2T", ""]
  293. #-----------------------------------------------自定义函数-----------------------------------------------
  294. #访问网页
  295. def webReadFile(self,urlStr,header):
  296. html=''
  297. req=urllib.request.Request(url=urlStr)#,headers=header
  298. with urllib.request.urlopen(req) as response:
  299. html = response.read().decode('utf-8')
  300. return html
  301. #判断网络地址是否存在
  302. def TestWebPage(self,urlStr,header):
  303. html=''
  304. req=urllib.request.Request(url=urlStr,method='HEAD')#,headers=header
  305. with urllib.request.urlopen(req) as response:
  306. html = response.getcode ()
  307. return html
  308. #正则取文本
  309. def get_RegexGetText(self,Text,RegexText,Index):
  310. returnTxt=""
  311. Regex=re.search(RegexText, Text, re.M|re.S)
  312. if Regex is None:
  313. returnTxt=""
  314. else:
  315. returnTxt=Regex.group(Index)
  316. return returnTxt
  317. #取集数
  318. def get_EpisodesList(self,jsonList):
  319. videos=[]
  320. for vod in jsonList:
  321. url = vod['guid']
  322. title =vod['title']
  323. if len(url) == 0:
  324. continue
  325. videos.append(title+"$"+url)
  326. return videos
  327. #取集数
  328. def get_EpisodesList_re(self,htmlTxt,patternTxt):
  329. ListRe=re.finditer(patternTxt, htmlTxt, re.M|re.S)
  330. videos=[]
  331. for vod in ListRe:
  332. url = vod.group('url')
  333. title =vod.group('title')
  334. if len(url) == 0:
  335. continue
  336. videos.append(title+"$"+url)
  337. return videos
  338. #取剧集区
  339. def get_lineList(self,Txt,mark,after):
  340. circuit=[]
  341. origin=Txt.find(mark)
  342. while origin>8:
  343. end=Txt.find(after,origin)
  344. circuit.append(Txt[origin:end])
  345. origin=Txt.find(mark,end)
  346. return circuit
  347. #正则取文本,返回数组
  348. def get_RegexGetTextLine(self,Text,RegexText,Index):
  349. returnTxt=[]
  350. pattern = re.compile(RegexText, re.M|re.S)
  351. ListRe=pattern.findall(Text)
  352. if len(ListRe)<1:
  353. return returnTxt
  354. for value in ListRe:
  355. returnTxt.append(value)
  356. return returnTxt
  357. #删除html标签
  358. def removeHtml(self,txt):
  359. soup = re.compile(r'<[^>]+>',re.S)
  360. txt =soup.sub('', txt)
  361. return txt.replace("&nbsp;"," ")
  362. #hookM3U8
  363. def hookM3u8(self, url):
  364. url = url or ''
  365. hook1 = lambda x: x.replace('asp/', 'asp//', 1)
  366. hook2 = lambda x: x.replace('hls/', 'hls//', 1)
  367. hook3 = lambda x: x.replace('https://newcntv.qcloudcdn.com', 'https://hls.cntv.myalicdn.com/', 1)
  368. hooks = [hook1, hook2, hook3]
  369. hook = random.choice(hooks)
  370. return hook(url)
  371. # 取m3u8
  372. def get_m3u8(self, urlTxt):
  373. url = "https://vdn.apps.cntv.cn/api/getHttpVideoInfo.do?pid={0}".format(urlTxt)
  374. htmlTxt = self.fetch(url).text
  375. jo = json.loads(htmlTxt)
  376. link = jo['hls_url'].strip()
  377. urlPrefix = self.get_RegexGetText(Text=link, RegexText='(http[s]?://[a-zA-z0-9.]+)/', Index=1)
  378. new_link = link.replace(f'{urlPrefix}/asp/hls/', 'https://dh5.cntv.qcloudcdn.com/asp/h5e/hls/').split('?')[0]
  379. html = self.webReadFile(urlStr=new_link, header=self.header)
  380. content = html.strip()
  381. arr = content.split('\n')
  382. subUrl = arr[-1].split('/')
  383. maxVideo = subUrl[-1].replace('.m3u8', '')
  384. hdUrl = link.replace('main', maxVideo)
  385. hdUrl = hdUrl.replace(urlPrefix, 'https://newcntv.qcloudcdn.com')
  386. hdRsp = self.TestWebPage(urlStr=hdUrl, header=self.header)
  387. if hdRsp == 200:
  388. url = hdUrl.split('?')[0]
  389. url = self.hookM3u8(url)
  390. self.log(f'视频链接: {url}')
  391. else:
  392. url = ''
  393. return url
  394. def fixm3u8_url(self, url):
  395. urlPrefix = self.get_RegexGetText(Text=url, RegexText='(http[s]?://[a-zA-z0-9.]+)/', Index=1)
  396. new_link = url.split('?')[0]
  397. html = self.webReadFile(urlStr=new_link, header=self.header)
  398. content = html.strip()
  399. arr = content.split('\n')
  400. subUrl = arr[3] if 'EXT-X-VERSION' in content else arr[2]
  401. hdUrl = self.urljoin(new_link, subUrl).split('?')[0]
  402. hdRsp = self.TestWebPage(urlStr=hdUrl, header=self.header)
  403. if hdRsp == 200:
  404. url = hdUrl
  405. self.log(f'视频链接: {url}')
  406. else:
  407. url = ''
  408. return url
  409. #搜索
  410. def get_list_search(self,html,tid):
  411. jRoot = json.loads(html)
  412. jsonList=jRoot['list']
  413. videos=[]
  414. for vod in jsonList:
  415. url = vod['urllink']
  416. title =self.removeHtml(txt=vod['title'])
  417. img=vod['imglink']
  418. id=vod['id']
  419. brief=vod['channel']
  420. year=vod['uploadtime']
  421. if len(url) == 0:
  422. continue
  423. guid="{0}###{1}###{2}###{3}###{4}###{5}###{6}###{7}".format(tid,title,url,img,id,year,'',brief)
  424. videos.append({
  425. "vod_id":guid,
  426. "vod_name":title,
  427. "vod_pic":img,
  428. "vod_remarks":year
  429. })
  430. return videos
  431. return videos
  432. def get_list1(self,html,tid):
  433. jRoot = json.loads(html)
  434. videos = []
  435. data=jRoot['response']
  436. if data is None:
  437. return []
  438. jsonList=data['docs']
  439. for vod in jsonList:
  440. id = vod['lastVIDE']['videoSharedCode']
  441. title =vod['column_name']
  442. url=vod['column_website']
  443. img=vod['column_logo']
  444. year=vod['column_playdate']
  445. brief=vod['column_brief']
  446. actors=''
  447. if len(url) == 0:
  448. continue
  449. guid="{0}###{1}###{2}###{3}###{4}###{5}###{6}###{7}".format(tid,title,url,img,id,year,actors,brief)
  450. #print(vod_id)
  451. videos.append({
  452. "vod_id":guid,
  453. "vod_name":title,
  454. "vod_pic":img,
  455. "vod_remarks":''
  456. })
  457. #print(videos)
  458. return videos
  459. #分类取结果
  460. def get_list(self,html,tid):
  461. jRoot = json.loads(html)
  462. videos = []
  463. data=jRoot['data']
  464. if data is None:
  465. return []
  466. jsonList=data['list']
  467. for vod in jsonList:
  468. url = vod['url']
  469. title =vod['title']
  470. img=vod['image']
  471. id=vod['id']
  472. try:
  473. brief=vod['brief']
  474. except:
  475. brief=''
  476. try:
  477. year=vod['year']
  478. except:
  479. year=''
  480. try:
  481. actors=vod['actors']
  482. except:
  483. actors=''
  484. if len(url) == 0:
  485. continue
  486. guid="{0}###{1}###{2}###{3}###{4}###{5}###{6}###{7}".format(tid,title,url,img,id,year,actors,brief)
  487. #print(vod_id)
  488. videos.append({
  489. "vod_id":guid,
  490. "vod_name":title,
  491. "vod_pic":img,
  492. "vod_remarks":''
  493. })
  494. return videos