diff --git a/py/douban.py b/py/douban.py deleted file mode 100644 index 92bc4d80..00000000 --- a/py/douban.py +++ /dev/null @@ -1,127 +0,0 @@ -#coding=utf-8 -#!/usr/bin/python -import sys -sys.path.append('..') -from base.spider import Spider -import json - -host_url = 'https://frodo.douban.com/api/v2' -apikey = "?apikey=0ac44ae016490db2204ce0a042db2916" - -class Spider(Spider): # 元类 默认的元类 type - def getName(self): - return "豆瓣" - def init(self,extend=""): - print("============{0}============".format(extend)) - pass - def isVideoFormat(self,url): - pass - def manualVideoCheck(self): - pass - def homeContent(self,filter): - result = {} - cateManual = { - "热门电影": "hot_gaia", - "热播剧集": "tv_hot", - "热播综艺": "show_hot", - "电影筛选": "movie", - "电视筛选": "tv", - "电影榜单": "rank_list_movie", - "电视榜单": "rank_list_tv" - } - 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): - url = host_url + '/subject_collection/subject_real_time_hotest/items' + apikey - rsp = self.fetch(url,headers=self.header) - jo = json.loads(rsp.text) - joList = jo.get("subject_collection_items") - lists = [] - for item in joList: - rating = item['rating']['value'] if item['rating'] else "" - lists.append({ - "vod_id": f'msearch:{item.get("type", "")}__{item.get("id", "")}', - "vod_name": item['title'], - "vod_pic": item['pic']['normal'], - "vod_remarks": rating - }) - result = { - 'list':lists - } - return result - def categoryContent(self,tid,pg,filter,extend): - result = {} - if extend: - sort = extend.pop('sort') if "sort" in extend else "T" - tags = ",".join(item for item in extend.values()) - else: - sort = "T" - tags = "" - if tid == "hot_gaia": - urlpath = f"/movie/{tid}" - getdata = "items" - sort = extend.get("sort", "recommend") - area = extend.get("area", "全部") - sort = sort + "&area=" + area - elif tid == "tv_hot" or tid == "show_hot": - urlpath = f"/subject_collection/{tid}/items" - getdata = "subject_collection_items" - elif tid.startswith("rank_list"): - id = "movie_real_time_hotest" if tid == "rank_list_movie" else "tv_real_time_hotest" - urlpath = f"/subject_collection/{id}/items" - getdata = "subject_collection_items" - else: - urlpath = f"/{tid}/recommend" - getdata = "items" - - url = host_url + urlpath + apikey + '&sort=' + sort + '&tags=' + tags + '&start=' + str((int(pg) - 1) * 30) - rsp = self.fetch(url,headers=self.header) - jo = json.loads(rsp.text) - jolist = jo[getdata] - - videos = [] - for vod in jolist: - rating = vod.get("rating", "").get("value", "") if vod.get("rating", "") else "" - pic = vod.get("pic", "").get("normal", "") if vod.get("pic", "") else "" - videos.append({ - "vod_id": f'msearch:{vod.get("type", "")}__{vod.get("id", "")}', - "vod_name": vod['title'], - "vod_pic": pic, - "vod_remarks": rating - }) - - result['list'] = videos - result['page'] = pg - result['pagecount'] = 9999 - result['limit'] = 90 - result['total'] = 999999 - return result - - def detailContent(self,array): - pass - def searchContent(self,key,quick): - pass - def playerContent(self,flag,id,vipFlags): - pass - - config = { - "player": {}, - "filter": {"hot_gaia":[{"key":"sort","name":"排序","value":[{"n":"热度","v":"recommend"},{"n":"最新","v":"time"},{"n":"评分","v":"rank"}]},{"key":"area","name":"地区","value":[{"n":"全部","v":"全部"},{"n":"华语","v":"华语"},{"n":"欧美","v":"欧美"},{"n":"韩国","v":"韩国"},{"n":"日本","v":"日本"}]}],"tv_hot":[{"key":"type","name":"分类","value":[{"n":"综合","v":"tv_hot"},{"n":"国产剧","v":"tv_domestic"},{"n":"欧美剧","v":"tv_american"},{"n":"日剧","v":"tv_japanese"},{"n":"韩剧","v":"tv_korean"},{"n":"动画","v":"tv_animation"}]}],"show_hot":[{"key":"type","name":"分类","value":[{"n":"综合","v":"show_hot"},{"n":"国内","v":"show_domestic"},{"n":"国外","v":"show_foreign"}]}],"movie":[{"key":"类型","name":"类型","value":[{"n":"全部类型","v":""},{"n":"喜剧","v":"喜剧"},{"n":"爱情","v":"爱情"},{"n":"动作","v":"动作"},{"n":"科幻","v":"科幻"},{"n":"动画","v":"动画"},{"n":"悬疑","v":"悬疑"},{"n":"犯罪","v":"犯罪"},{"n":"惊悚","v":"惊悚"},{"n":"冒险","v":"冒险"},{"n":"音乐","v":"音乐"},{"n":"历史","v":"历史"},{"n":"奇幻","v":"奇幻"},{"n":"恐怖","v":"恐怖"},{"n":"战争","v":"战争"},{"n":"传记","v":"传记"},{"n":"歌舞","v":"歌舞"},{"n":"武侠","v":"武侠"},{"n":"情色","v":"情色"},{"n":"灾难","v":"灾难"},{"n":"西部","v":"西部"},{"n":"纪录片","v":"纪录片"},{"n":"短片","v":"短片"}]},{"key":"地区","name":"地区","value":[{"n":"全部地区","v":""},{"n":"华语","v":"华语"},{"n":"欧美","v":"欧美"},{"n":"韩国","v":"韩国"},{"n":"日本","v":"日本"},{"n":"中国大陆","v":"中国大陆"},{"n":"美国","v":"美国"},{"n":"中国香港","v":"中国香港"},{"n":"中国台湾","v":"中国台湾"},{"n":"英国","v":"英国"},{"n":"法国","v":"法国"},{"n":"德国","v":"德国"},{"n":"意大利","v":"意大利"},{"n":"西班牙","v":"西班牙"},{"n":"印度","v":"印度"},{"n":"泰国","v":"泰国"},{"n":"俄罗斯","v":"俄罗斯"},{"n":"加拿大","v":"加拿大"},{"n":"澳大利亚","v":"澳大利亚"},{"n":"爱尔兰","v":"爱尔兰"},{"n":"瑞典","v":"瑞典"},{"n":"巴西","v":"巴西"},{"n":"丹麦","v":"丹麦"}]},{"key":"sort","name":"排序","value":[{"n":"近期热度","v":"T"},{"n":"首映时间","v":"R"},{"n":"高分优先","v":"S"}]},{"key":"年代","name":"年代","value":[{"n":"全部年代","v":""},{"n":"2022","v":"2022"},{"n":"2021","v":"2021"},{"n":"2020","v":"2020"},{"n":"2019","v":"2019"},{"n":"2010年代","v":"2010年代"},{"n":"2000年代","v":"2000年代"},{"n":"90年代","v":"90年代"},{"n":"80年代","v":"80年代"},{"n":"70年代","v":"70年代"},{"n":"60年代","v":"60年代"},{"n":"更早","v":"更早"}]}],"tv":[{"key":"类型","name":"类型","value":[{"n":"不限","v":""},{"n":"电视剧","v":"电视剧"},{"n":"综艺","v":"综艺"}]},{"key":"电视剧形式","name":"电视剧形式","value":[{"n":"不限","v":""},{"n":"喜剧","v":"喜剧"},{"n":"爱情","v":"爱情"},{"n":"悬疑","v":"悬疑"},{"n":"动画","v":"动画"},{"n":"武侠","v":"武侠"},{"n":"古装","v":"古装"},{"n":"家庭","v":"家庭"},{"n":"犯罪","v":"犯罪"},{"n":"科幻","v":"科幻"},{"n":"恐怖","v":"恐怖"},{"n":"历史","v":"历史"},{"n":"战争","v":"战争"},{"n":"动作","v":"动作"},{"n":"冒险","v":"冒险"},{"n":"传记","v":"传记"},{"n":"剧情","v":"剧情"},{"n":"奇幻","v":"奇幻"},{"n":"惊悚","v":"惊悚"},{"n":"灾难","v":"灾难"},{"n":"歌舞","v":"歌舞"},{"n":"音乐","v":"音乐"}]},{"key":"综艺形式","name":"综艺形式","value":[{"n":"不限","v":""},{"n":"真人秀","v":"真人秀"},{"n":"脱口秀","v":"脱口秀"},{"n":"音乐","v":"音乐"},{"n":"歌舞","v":"歌舞"}]},{"key":"地区","name":"地区","value":[{"n":"全部地区","v":""},{"n":"华语","v":"华语"},{"n":"欧美","v":"欧美"},{"n":"国外","v":"国外"},{"n":"韩国","v":"韩国"},{"n":"日本","v":"日本"},{"n":"中国大陆","v":"中国大陆"},{"n":"中国香港","v":"中国香港"},{"n":"美国","v":"美国"},{"n":"英国","v":"英国"},{"n":"泰国","v":"泰国"},{"n":"中国台湾","v":"中国台湾"},{"n":"意大利","v":"意大利"},{"n":"法国","v":"法国"},{"n":"德国","v":"德国"},{"n":"西班牙","v":"西班牙"},{"n":"俄罗斯","v":"俄罗斯"},{"n":"瑞典","v":"瑞典"},{"n":"巴西","v":"巴西"},{"n":"丹麦","v":"丹麦"},{"n":"印度","v":"印度"},{"n":"加拿大","v":"加拿大"},{"n":"爱尔兰","v":"爱尔兰"},{"n":"澳大利亚","v":"澳大利亚"}]},{"key":"sort","name":"排序","value":[{"n":"近期热度","v":"T"},{"n":"首播时间","v":"R"},{"n":"高分优先","v":"S"}]},{"key":"年代","name":"年代","value":[{"n":"全部","v":""},{"n":"2022","v":"2022"},{"n":"2021","v":"2021"},{"n":"2020","v":"2020"},{"n":"2019","v":"2019"},{"n":"2010年代","v":"2010年代"},{"n":"2000年代","v":"2000年代"},{"n":"90年代","v":"90年代"},{"n":"80年代","v":"80年代"},{"n":"70年代","v":"70年代"},{"n":"60年代","v":"60年代"},{"n":"更早","v":"更早"}]},{"key":"平台","name":"平台","value":[{"n":"全部","v":""},{"n":"腾讯视频","v":"腾讯视频"},{"n":"爱奇艺","v":"爱奇艺"},{"n":"优酷","v":"优酷"},{"n":"湖南卫视","v":"湖南卫视"},{"n":"Netflix","v":"Netflix"},{"n":"HBO","v":"HBO"},{"n":"BBC","v":"BBC"},{"n":"NHK","v":"NHK"},{"n":"CBS","v":"CBS"},{"n":"NBC","v":"NBC"},{"n":"tvN","v":"tvN"}]}],"rank_list_movie":[{"key":"榜单","name":"榜单","value":[{"n":"实时热门电影","v":"movie_real_time_hotest"},{"n":"一周口碑电影榜","v":"movie_weekly_best"},{"n":"豆瓣电影Top250","v":"movie_top250"}]}],"rank_list_tv":[{"key":"榜单","name":"榜单","value":[{"n":"实时热门电视","v":"tv_real_time_hotest"},{"n":"华语口碑剧集榜","v":"tv_chinese_best_weekly"},{"n":"全球口碑剧集榜","v":"tv_global_best_weekly"},{"n":"国内口碑综艺榜","v":"show_chinese_best_weekly"},{"n":"国外口碑综艺榜","v":"show_global_best_weekly"}]}]} - } - header = { - "Host": "frodo.douban.com", - "Connection": "Keep-Alive", - "Referer": "https://servicewechat.com/wx2f9b06c1de1ccfca/84/page-frame.html", - "User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.143 Safari/537.36 MicroMessenger/7.0.9.501 NetType/WIFI MiniProgramEnv/Windows WindowsWechat" - } - - def localProxy(self,param): - return [200, "video/MP2T", action, ""] \ No newline at end of file diff --git a/py/py_cctv.py b/py/py_cctv.py deleted file mode 100644 index 0dd9e974..00000000 --- a/py/py_cctv.py +++ /dev/null @@ -1,181 +0,0 @@ -#coding=utf-8 -#!/usr/bin/python -import sys -sys.path.append('..') -from base.spider import Spider -import time - -class Spider(Spider): # 元类 默认的元类 type - def getName(self): - return "央视大全" - def init(self,extend=""): - print("============{0}============".format(extend)) - pass - def isVideoFormat(self,url): - pass - def manualVideoCheck(self): - pass - def homeContent(self,filter): - result = {} - cateManual = { - "央视大全": "CCTV" - } - classes = [] - for k in cateManual: - classes.append({ - 'type_name':k, - 'type_id':cateManual[k] - }) - result['class'] = classes - if(filter): - import datetime - current_year = datetime.datetime.now().year - yearList = [{"n":"全部","v":""}] - for year in range(current_year, current_year - 10, -1): - yearList.append({"n":year,"v":year}) - yearDict = {"key":"year","name":"年份","value":yearList} - for classe in classes: - self.config['filter'][classe['type_id']].append(yearDict) - result['filters'] = self.config['filter'] - return result - - def homeVideoContent(self): - result = {} - return result - def categoryContent(self,tid,pg,filter,extend): - result = {} - month = "" - year = "" - if 'month' in extend.keys(): - month = extend['month'] - if 'year' in extend.keys(): - year = extend['year'] - if year == '': - month = '' - prefix = year + month - extend['p'] = pg - filterMap = { - "fl":"", - "fc":"", - "cid":"", - "p":"1" - } - suffix = "" - for key in filterMap.keys(): - if key in extend.keys(): - filterMap[key] = extend[key] - suffix = suffix + '&' + key + '=' + str(filterMap[key]) - url = 'https://api.cntv.cn/lanmu/columnSearch?{0}&n=20&serviceId=tvcctv&t=json'.format(suffix) - jo = self.fetch(url,headers=self.header).json() - vodList = jo['response']['docs'] - videos = [] - for vod in vodList: - lastVideo = vod['lastVIDE']['videoSharedCode'] - if len(lastVideo) == 0: - lastVideo = '_' - guid = prefix+'###'+vod['column_name']+'###'+lastVideo+'###'+vod['column_logo'] - # guid = prefix+'###'+vod['column_website']+'###'+vod['column_logo'] - title = vod['column_name'] - img = vod['column_logo'] - videos.append({ - "vod_id":guid, - "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] - logo = aid[3] - lastVideo = aid[2] - title = aid[1] - date = aid[0] - if lastVideo == '_': - return {} - - lastUrl = 'https://api.cntv.cn/video/videoinfoByGuid?guid={0}&serviceId=tvcctv'.format(lastVideo) - lastJo = self.fetch(lastUrl,headers=self.header).json() - topicId = lastJo['ctid'] - url = "https://api.cntv.cn/NewVideo/getVideoListByColumn?id={0}&d={1}&p=1&n=100&sort=desc&mode=0&serviceId=tvcctv&t=json".format(topicId,date) - jo = self.fetch(url,headers=self.header).json() - vodList = jo['data']['list'] - videoList = [] - for video in vodList: - videoList.append(video['title']+"$"+video['guid']) - if len(videoList) == 0: - return {} - if len(date) == 0: - date = time.strftime("%Y", time.localtime(time.time())) - vod = { - "vod_id":array[0], - "vod_name":date +" "+title, - "vod_pic":logo, - "type_name":lastJo['channel'], - "vod_year":date, - "vod_area":"", - "vod_remarks":date, - "vod_actor":"", - "vod_director":topicId, - "vod_content":"当前页面默认只展示最新100期的内容，可在分类页面选择年份和月份进行往期节目查看。年份和月份仅影响当前页面内容，不参与分类过滤。视频默认播放可以获取到的最高帧率。" - } - - vod['vod_play_from'] = 'CCTV' - vod['vod_play_url'] = "#".join(videoList) - result = { - 'list':[ - vod - ] - } - return result - - def searchContent(self,key,quick): - result = { - 'list':[] - } - return result - def playerContent(self,flag,id,vipFlags): - result = {} - url = "https://vdn.apps.cntv.cn/api/getHttpVideoInfo.do?pid={0}".format(id) - jo = self.fetch(url,headers=self.header).json() - link = jo['hls_url'].strip() - rsp = self.fetch(link,headers=self.header) - content = rsp.text.strip() - arr = content.split('\n') - urlPrefix = self.regStr(link,'(http[s]?://[a-zA-z0-9.]+)/') - - subUrl = arr[-1].split('/') - subUrl[3] = '1200' - subUrl[-1] = '1200.m3u8' - hdUrl = urlPrefix + '/'.join(subUrl) - - url = urlPrefix + arr[-1] - - hdRsp = self.fetch(hdUrl,headers=self.header) - if hdRsp.status_code == 200: - url = hdUrl - - result["parse"] = 0 - result["playUrl"] = '' - result["url"] = url - result["header"] = '' - return result - - config = { - "player": {}, - "filter": {"CCTV":[{"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":"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", - "Origin": "https://tv.cctv.com", - "Referer": "https://tv.cctv.com/" - } - - def localProxy(self,param): - return [200, "video/MP2T", action, ""] diff --git a/py/py_cctv_new.py b/py/py_cctv_new.py deleted file mode 100644 index c79ac3e8..00000000 --- a/py/py_cctv_new.py +++ /dev/null @@ -1,461 +0,0 @@ -#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 isVideoFormat(self,url): - pass - def manualVideoCheck(self): - pass - def homeContent(self,filter): - result = {} - cateManual = { - "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", - "节目大全":"节目大全" - } - 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): - 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":"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", action, ""] - #-----------------------------------------------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/py/py_xmly.py b/py/py_xmly.py deleted file mode 100644 index bf50ea6f..00000000 --- a/py/py_xmly.py +++ /dev/null @@ -1,222 +0,0 @@ -#coding=utf-8 -#!/usr/bin/python -import sys -sys.path.append('..') -from base.spider import Spider -import math -import json -from requests import session, utils - -class Spider(Spider): - def getName(self): - return "喜马拉雅" - def init(self,extend=""): - pass - def isVideoFormat(self,url): - pass - def manualVideoCheck(self): - pass - def homeContent(self,filter): - result = {} - cateManual = { - "小说": "7", - "儿童": "11", - "评书": "10", - "娱乐": "13", - "悬疑": "14", - "人文": "17", - "国学": "18", - "头条": "24", - "音乐": "19", - "历史": "16", - "情感": "20", - "健康": "22", - "生活": "21", - "影视": "15", - "英语": "29", - "科技": "28", - "体育": "25", - "汽车": "23", - "广播剧": "8", - "小语种": "30", - "教育考试": "32", - "少儿素养": "12", - "商业管理": "27", - "个人提升": "31", - "投资理财": "26", - "相声小品": "9", - } - 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 = {} - return result - - def categoryContent(self,tid,pg,filter,extend): - result = {} - header = { - "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/108.0.0.0 Safari/537.36 Edg/108.0.1462.54", - "Referer": "https://www.ximalaya.com/channel/{}/".format(tid) - } - url = 'https://www.ximalaya.com/revision/metadata/v2/channel/albums?pageNum={0}&pageSize=50&sort=1&metadata=&groupId={1}'.format(pg, tid) - rsp = self.fetch(url,headers=header) - jo = json.loads(rsp.text) - videos = [] - numvL = len(jo['data']['albums']) - pgc = math.ceil(numvL/15) - for a in jo['data']['albums']: - aid = a['albumId'] - img = 'http://imagev2.xmcdn.com/{0}'.format(a['albumCoverPath']) - name = a['albumTitle'] - if a['vipType'] == 1: - remark = 'VIP' - else: - remark = '' - videos.append({ - "vod_id": aid, - "vod_name": name, - "vod_pic": img, - "vod_remarks": remark - }) - result['list'] = videos - result['page'] = pg - result['pagecount'] = pgc - result['limit'] = numvL - result['total'] = numvL - return result - - def detailContent(self,array): - aid = array[0] - header = { - "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/108.0.0.0 Safari/537.36 Edg/108.0.1462.54", - "Referer": "https://www.ximalaya.com/album/{}/".format(aid) - } - pg = 1 - url = 'https://www.ximalaya.com/revision/album/v1/getTracksList?albumId={}&pageNum={}&pageSize=30'.format(aid, pg) - rsp = self.fetch(url, headers=header) - jo = json.loads(rsp.text) - items = jo['data']['tracks'] - numjo = jo['data']['trackTotalCount'] - while len(items) < numjo: - pg = pg + 1 - url = 'https://www.ximalaya.com/revision/album/v1/getTracksList?albumId={}&pageNum={}&pageSize=30'.format(aid, pg) - rsp = self.fetch(url, headers=header) - jo = json.loads(rsp.text) - items.extend(jo['data']['tracks']) - playUrl = '' - for item in items: - dir = item['anchorName'].strip() - act = item['anchorName'].strip() - title = item['albumTitle'] - pic = 'http://imagev2.xmcdn.com/{0}'.format(item['albumCoverPath']) - year = item['createDateFormat'].split('-')[0] - cont = item['albumTitle'] - name = item['title'].strip() - purl = item['trackId'] - playUrl = playUrl + '{0}${1}#'.format(name, purl) - vod = { - "vod_id": aid, - "vod_name": title, - "vod_pic": pic, - "type_name": '', - "vod_year": year, - "vod_area": '', - "vod_remarks": '', - "vod_actor": act, - "vod_director": dir, - "vod_content": cont - } - - vod['vod_play_from'] = '喜马拉雅' - vod['vod_play_url'] = playUrl - - result = { - 'list': [ - vod - ] - } - return result - - - def searchContent(self,key,quick): - header = { - "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/108.0.0.0 Safari/537.36 Edg/108.0.1462.54", - "Referer": "https://www.ximalaya.com/" - } - url = 'https://www.ximalaya.com/revision/search/main?core=all&kw={}&spellchecker=true&device=iPhone&live=true'.format(key) - rsp = self.fetch(url, headers=header) - jo = json.loads(rsp.text) - items = jo['data']['album']['docs'] - pg = 1 - while pg < jo['data']['album']['totalPage']: - pg = pg + 1 - url = 'https://www.ximalaya.com/revision/search/main?core=album&kw={0}&page={1}&spellchecker=true&rows=20&condition=relation&device=iPhone&fq=&paidFilter=false'.format(key, pg) - rsp = self.fetch(url, headers=header) - jo = json.loads(rsp.text) - items.extend(jo['data']['album']['docs']) - videos = [] - for item in items: - name = item['title'] - pic = item['coverPath'] - if item['vipType'] == 1: - mark = 'VIP' - else: - mark = '' - sid = item['albumId'] - videos.append({ - "vod_id":sid, - "vod_name":name, - "vod_pic":pic, - "vod_remarks":mark - }) - result = { - 'list': videos - } - return result - - def playerContent(self,flag,id,vipFlags): - result = {} - header = { - "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/108.0.0.0 Safari/537.36 Edg/108.0.1462.54", - "Referer": 'https://www.ximalaya.com/sound/{0}/'.format(id) - } - #这里是游客cookie，有vip的填入自己的会员cookie - cookies_str = '_xmLog=h5&48be63f9-2a8a-48e1-b923-d29486aac356&process.env.sdkVersion; xm-page-viewid=ximalaya-web; x_xmly_traffic=utm_source%253A%2526utm_medium%253A%2526utm_campaign%253A%2526utm_content%253A%2526utm_term%253A%2526utm_from%253A' - cookies_dic = dict([co.strip().split('=') for co in cookies_str.split(';')]) - rsp = session() - cookies_jar = utils.cookiejar_from_dict(cookies_dic) - rsp.cookie = cookies_jar - url = 'https://www.ximalaya.com/revision/play/v1/audio?id={0}&ptype=1'.format(id) - rsp = self.fetch(url, cookies=rsp.cookie, headers=header) - jo = json.loads(rsp.text) - purl = jo['data']['src'] - result["parse"] = 0 - result["playUrl"] = '' - result["url"] = purl - result["header"] = '' - return result - - config = { - "player": {}, - "filter": {} - } - header = {} - - def localProxy(self,param): - action = { - 'url':'', - 'header':'', - 'param':'', - 'type':'string', - 'after':'' - } - return [200, "video/MP2T", action, ""] \ No newline at end of file