You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

461 lines
23 KiB

8 months ago
  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 isVideoFormat(self,url):
  21. pass
  22. def manualVideoCheck(self):
  23. pass
  24. def homeContent(self,filter):
  25. result = {}
  26. cateManual = {
  27. "电视剧": "电视剧",
  28. "动画片": "动画片",
  29. "纪录片": "纪录片",
  30. "特别节目": "特别节目",
  31. "节目大全":"节目大全"
  32. }
  33. classes = []
  34. for k in cateManual:
  35. classes.append({
  36. 'type_name':k,
  37. 'type_id':cateManual[k]
  38. })
  39. result['class'] = classes
  40. if(filter):
  41. result['filters'] = self.config['filter']
  42. return result
  43. def homeVideoContent(self):
  44. result = {
  45. 'list':[]
  46. }
  47. return result
  48. def categoryContent(self,tid,pg,filter,extend):
  49. result = {}
  50. month = ""#月
  51. year = ""#年
  52. area=''#地区
  53. channel=''#频道
  54. datafl=''#类型
  55. letter=''#字母
  56. pagecount=24
  57. if tid=='动画片':
  58. id=urllib.parse.quote(tid)
  59. if 'datadq-area' in extend.keys():
  60. area=urllib.parse.quote(extend['datadq-area'])
  61. if 'dataszm-letter' in extend.keys():
  62. letter=extend['dataszm-letter']
  63. if 'datafl-sc' in extend.keys():
  64. datafl=urllib.parse.quote(extend['datafl-sc'])
  65. 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)
  66. elif tid=='纪录片':
  67. id=urllib.parse.quote(tid)
  68. if 'datapd-channel' in extend.keys():
  69. channel=urllib.parse.quote(extend['datapd-channel'])
  70. if 'datafl-sc' in extend.keys():
  71. datafl=urllib.parse.quote(extend['datafl-sc'])
  72. if 'datanf-year' in extend.keys():
  73. year=extend['datanf-year']
  74. if 'dataszm-letter' in extend.keys():
  75. letter=extend['dataszm-letter']
  76. 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)
  77. elif tid=='电视剧':
  78. id=urllib.parse.quote(tid)
  79. if 'datafl-sc' in extend.keys():
  80. datafl=urllib.parse.quote(extend['datafl-sc'])
  81. if 'datanf-year' in extend.keys():
  82. year=extend['datanf-year']
  83. if 'dataszm-letter' in extend.keys():
  84. letter=extend['dataszm-letter']
  85. 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)
  86. elif tid=='特别节目':
  87. id=urllib.parse.quote(tid)
  88. if 'datapd-channel' in extend.keys():
  89. channel=urllib.parse.quote(extend['datapd-channel'])
  90. if 'datafl-sc' in extend.keys():
  91. datafl=urllib.parse.quote(extend['datafl-sc'])
  92. if 'dataszm-letter' in extend.keys():
  93. letter=extend['dataszm-letter']
  94. 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)
  95. elif tid=='节目大全':
  96. cid=''#频道
  97. if 'cid' in extend.keys():
  98. cid=extend['cid']
  99. fc=''#分类
  100. if 'fc' in extend.keys():
  101. fc=extend['fc']
  102. fl=''#字母
  103. if 'fl' in extend.keys():
  104. fl=extend['fl']
  105. 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)
  106. pagecount=20
  107. else:
  108. url = 'https://tv.cctv.com/epg/index.shtml'
  109. videos=[]
  110. htmlText =self.webReadFile(urlStr=url,header=self.header)
  111. if tid=='节目大全':
  112. index=htmlText.rfind(');')
  113. if index>-1:
  114. htmlText=htmlText[3:index]
  115. videos =self.get_list1(html=htmlText,tid=tid)
  116. else:
  117. videos =self.get_list(html=htmlText,tid=tid)
  118. #print(videos)
  119. result['list'] = videos
  120. result['page'] = pg
  121. result['pagecount'] = 9999 if len(videos)>=pagecount else pg
  122. result['limit'] = 90
  123. result['total'] = 999999
  124. return result
  125. def detailContent(self,array):
  126. result={}
  127. aid = array[0].split('###')
  128. tid = aid[0]
  129. logo = aid[3]
  130. lastVideo = aid[2]
  131. title = aid[1]
  132. id= aid[4]
  133. vod_year= aid[5]
  134. actors= aid[6]
  135. brief= aid[7]
  136. fromId='CCTV'
  137. if tid=="节目大全":
  138. lastUrl = 'https://api.cntv.cn/video/videoinfoByGuid?guid={0}&serviceId=tvcctv'.format(id)
  139. htmlTxt = self.webReadFile(urlStr=lastUrl,header=self.header)
  140. topicId=json.loads(htmlTxt)['ctid']
  141. Url = "https://api.cntv.cn/NewVideo/getVideoListByColumn?id={0}&d=&p=1&n=100&sort=desc&mode=0&serviceId=tvcctv&t=json".format(topicId)
  142. htmlTxt = self.webReadFile(urlStr=Url,header=self.header)
  143. else:
  144. Url='https://api.cntv.cn/NewVideo/getVideoListByAlbumIdNew?id={0}&serviceId=tvcctv&p=1&n=100&mode=0&pub=1'.format(id)
  145. jRoot = ''
  146. videoList = []
  147. try:
  148. if tid=="搜索":
  149. fromId='中央台'
  150. videoList=[title+"$"+lastVideo]
  151. else:
  152. htmlTxt=self.webReadFile(urlStr=Url,header=self.header)
  153. jRoot = json.loads(htmlTxt)
  154. data=jRoot['data']
  155. jsonList=data['list']
  156. videoList=self.get_EpisodesList(jsonList=jsonList)
  157. if len(videoList)<1:
  158. htmlTxt=self.webReadFile(urlStr=lastVideo,header=self.header)
  159. if tid=="电视剧" or tid=="纪录片":
  160. 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>.+?)'"
  161. elif tid=="特别节目":
  162. patternTxt=r'class="tp1"><a\s*href="(?P<url>https://.+?)"\s*target="_blank"\s*title="(?P<title>.+?)"></a></div>'
  163. elif tid=="动画片":
  164. 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>.+?)'"
  165. elif tid=="节目大全":
  166. patternTxt=r'href="(?P<url>.+?)" target="_blank" alt="(?P<title>.+?)" title=".+?">'
  167. videoList=self.get_EpisodesList_re(htmlTxt=htmlTxt,patternTxt=patternTxt)
  168. fromId='央视'
  169. except:
  170. pass
  171. if len(videoList) == 0:
  172. return {}
  173. vod = {
  174. "vod_id":array[0],
  175. "vod_name":title,
  176. "vod_pic":logo,
  177. "type_name":tid,
  178. "vod_year":vod_year,
  179. "vod_area":"",
  180. "vod_remarks":'',
  181. "vod_actor":actors,
  182. "vod_director":'',
  183. "vod_content":brief
  184. }
  185. vod['vod_play_from'] = fromId
  186. vod['vod_play_url'] = "#".join(videoList)
  187. result = {
  188. 'list':[
  189. vod
  190. ]
  191. }
  192. return result
  193. def get_lineList(self,Txt,mark,after):
  194. circuit=[]
  195. origin=Txt.find(mark)
  196. while origin>8:
  197. end=Txt.find(after,origin)
  198. circuit.append(Txt[origin:end])
  199. origin=Txt.find(mark,end)
  200. return circuit
  201. def get_RegexGetTextLine(self,Text,RegexText,Index):
  202. returnTxt=[]
  203. pattern = re.compile(RegexText, re.M|re.S)
  204. ListRe=pattern.findall(Text)
  205. if len(ListRe)<1:
  206. return returnTxt
  207. for value in ListRe:
  208. returnTxt.append(value)
  209. return returnTxt
  210. def searchContent(self,key,quick):
  211. key=urllib.parse.quote(key)
  212. 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)
  213. htmlTxt=self.webReadFile(urlStr=Url,header=self.header)
  214. videos=self.get_list_search(html=htmlTxt,tid='搜索')
  215. result = {
  216. 'list':videos
  217. }
  218. return result
  219. def playerContent(self,flag,id,vipFlags):
  220. result = {}
  221. url=''
  222. parse=0
  223. headers = {
  224. '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'
  225. }
  226. if flag=='CCTV':
  227. url=self.get_m3u8(urlTxt=id)
  228. else:
  229. try:
  230. html=self.webReadFile(urlStr=id,header=self.header)
  231. guid=self.get_RegexGetText(Text=html,RegexText=r'var\sguid\s*=\s*"(.+?)";',Index=1)
  232. url=self.get_m3u8(urlTxt=guid)
  233. except :
  234. url=id
  235. parse=1
  236. if url.find('https:')<0:
  237. url=id
  238. parse=1
  239. result["parse"] = parse#1=嗅探,0=播放
  240. result["playUrl"] = ''
  241. result["url"] = url
  242. result["header"] =headers
  243. return result
  244. config = {
  245. "player": {},
  246. "filter": {
  247. "电视剧":[
  248. {"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"}]},
  249. {"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"}]},
  250. {"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"}]},
  251. {"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"}]}
  252. ],
  253. "动画片":[
  254. {"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"}]},
  255. {"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"}]},
  256. {"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"}]}
  257. ],
  258. "纪录片":[
  259. {"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"}]},
  260. {"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"}]},
  261. {"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"}]},
  262. {"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"}]}
  263. ],
  264. "特别节目":[
  265. {"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"}]},
  266. {"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"}]},
  267. {"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"}]}
  268. ],
  269. "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":"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"}]}]
  270. }
  271. }
  272. header = {
  273. "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",
  274. "Host": "tv.cctv.com",
  275. "Referer": "https://tv.cctv.com/"
  276. }
  277. def localProxy(self,param):
  278. return [200, "video/MP2T", action, ""]
  279. #-----------------------------------------------自定义函数-----------------------------------------------
  280. #访问网页
  281. def webReadFile(self,urlStr,header):
  282. html=''
  283. req=urllib.request.Request(url=urlStr)#,headers=header
  284. with urllib.request.urlopen(req) as response:
  285. html = response.read().decode('utf-8')
  286. return html
  287. #判断网络地址是否存在
  288. def TestWebPage(self,urlStr,header):
  289. html=''
  290. req=urllib.request.Request(url=urlStr,method='HEAD')#,headers=header
  291. with urllib.request.urlopen(req) as response:
  292. html = response.getcode ()
  293. return html
  294. #正则取文本
  295. def get_RegexGetText(self,Text,RegexText,Index):
  296. returnTxt=""
  297. Regex=re.search(RegexText, Text, re.M|re.S)
  298. if Regex is None:
  299. returnTxt=""
  300. else:
  301. returnTxt=Regex.group(Index)
  302. return returnTxt
  303. #取集数
  304. def get_EpisodesList(self,jsonList):
  305. videos=[]
  306. for vod in jsonList:
  307. url = vod['guid']
  308. title =vod['title']
  309. if len(url) == 0:
  310. continue
  311. videos.append(title+"$"+url)
  312. return videos
  313. #取集数
  314. def get_EpisodesList_re(self,htmlTxt,patternTxt):
  315. ListRe=re.finditer(patternTxt, htmlTxt, re.M|re.S)
  316. videos=[]
  317. for vod in ListRe:
  318. url = vod.group('url')
  319. title =vod.group('title')
  320. if len(url) == 0:
  321. continue
  322. videos.append(title+"$"+url)
  323. return videos
  324. #取剧集区
  325. def get_lineList(self,Txt,mark,after):
  326. circuit=[]
  327. origin=Txt.find(mark)
  328. while origin>8:
  329. end=Txt.find(after,origin)
  330. circuit.append(Txt[origin:end])
  331. origin=Txt.find(mark,end)
  332. return circuit
  333. #正则取文本,返回数组
  334. def get_RegexGetTextLine(self,Text,RegexText,Index):
  335. returnTxt=[]
  336. pattern = re.compile(RegexText, re.M|re.S)
  337. ListRe=pattern.findall(Text)
  338. if len(ListRe)<1:
  339. return returnTxt
  340. for value in ListRe:
  341. returnTxt.append(value)
  342. return returnTxt
  343. #删除html标签
  344. def removeHtml(self,txt):
  345. soup = re.compile(r'<[^>]+>',re.S)
  346. txt =soup.sub('', txt)
  347. return txt.replace("&nbsp;"," ")
  348. #取m3u8
  349. def get_m3u8(self,urlTxt):
  350. url = "https://vdn.apps.cntv.cn/api/getHttpVideoInfo.do?pid={0}".format(urlTxt)
  351. html=self.webReadFile(urlStr=url,header=self.header)
  352. jo =json.loads(html)
  353. link = jo['hls_url'].strip()
  354. html = self.webReadFile(urlStr=link,header=self.header)
  355. content = html.strip()
  356. arr = content.split('\n')
  357. urlPrefix = self.get_RegexGetText(Text=link,RegexText='(http[s]?://[a-zA-z0-9.]+)/',Index=1)
  358. subUrl = arr[-1].split('/')
  359. subUrl[3] = '1200'
  360. subUrl[-1] = '1200.m3u8'
  361. hdUrl = urlPrefix + '/'.join(subUrl)
  362. url = urlPrefix + arr[-1]
  363. hdRsp = self.TestWebPage(urlStr=hdUrl,header=self.header)
  364. if hdRsp == 200:
  365. url = hdUrl
  366. else:
  367. url=''
  368. return url
  369. #搜索
  370. def get_list_search(self,html,tid):
  371. jRoot = json.loads(html)
  372. jsonList=jRoot['list']
  373. videos=[]
  374. for vod in jsonList:
  375. url = vod['urllink']
  376. title =self.removeHtml(txt=vod['title'])
  377. img=vod['imglink']
  378. id=vod['id']
  379. brief=vod['channel']
  380. year=vod['uploadtime']
  381. if len(url) == 0:
  382. continue
  383. guid="{0}###{1}###{2}###{3}###{4}###{5}###{6}###{7}".format(tid,title,url,img,id,year,'',brief)
  384. videos.append({
  385. "vod_id":guid,
  386. "vod_name":title,
  387. "vod_pic":img,
  388. "vod_remarks":year
  389. })
  390. return videos
  391. return videos
  392. def get_list1(self,html,tid):
  393. jRoot = json.loads(html)
  394. videos = []
  395. data=jRoot['response']
  396. if data is None:
  397. return []
  398. jsonList=data['docs']
  399. for vod in jsonList:
  400. id = vod['lastVIDE']['videoSharedCode']
  401. title =vod['column_name']
  402. url=vod['column_website']
  403. img=vod['column_logo']
  404. year=vod['column_playdate']
  405. brief=vod['column_brief']
  406. actors=''
  407. if len(url) == 0:
  408. continue
  409. guid="{0}###{1}###{2}###{3}###{4}###{5}###{6}###{7}".format(tid,title,url,img,id,year,actors,brief)
  410. #print(vod_id)
  411. videos.append({
  412. "vod_id":guid,
  413. "vod_name":title,
  414. "vod_pic":img,
  415. "vod_remarks":''
  416. })
  417. #print(videos)
  418. return videos
  419. #分类取结果
  420. def get_list(self,html,tid):
  421. jRoot = json.loads(html)
  422. videos = []
  423. data=jRoot['data']
  424. if data is None:
  425. return []
  426. jsonList=data['list']
  427. for vod in jsonList:
  428. url = vod['url']
  429. title =vod['title']
  430. img=vod['image']
  431. id=vod['id']
  432. try:
  433. brief=vod['brief']
  434. except:
  435. brief=''
  436. try:
  437. year=vod['year']
  438. except:
  439. year=''
  440. try:
  441. actors=vod['actors']
  442. except:
  443. actors=''
  444. if len(url) == 0:
  445. continue
  446. guid="{0}###{1}###{2}###{3}###{4}###{5}###{6}###{7}".format(tid,title,url,img,id,year,actors,brief)
  447. #print(vod_id)
  448. videos.append({
  449. "vod_id":guid,
  450. "vod_name":title,
  451. "vod_pic":img,
  452. "vod_remarks":''
  453. })
  454. return videos