# -*- coding:utf-8 -*- import requests, time, datetime,re,os from bs4 import BeautifulSoup as bs headers = { "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9", "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/106.0.0.0 Safari/537.36", } # 获取频道节目列表 def get_epgs_tvmao2(channel,channel_id,dt,func_arg): epgs = [] desc = '' msg = '' success = 1 ban = 0 #标识是否被BAN掉了,此接口不确定是否有反爬机制 now_date = datetime.datetime.now() need_date = dt delta = need_date - now_date now_weekday = now_date.weekday() need_weekday = now_weekday + delta.days + 1 id_split = channel_id.split('-') if len(id_split) == 2: id = id_split[1] elif len(id_split) ==3: id = '-'.join(id_split[1:3]) else: id = channel_id url = "https://lighttv.tvmao.com/qa/qachannelschedule?epgCode=%s&op=getProgramByChnid&epgName=&isNew=on&day=%s"%(id,need_weekday) # print(url) try: res = requests.get(url,headers = headers) res_j = res.json() datas = res_j[2]['pro'] # {'name': '星空放映厅', 'typeid': 0, 'pid': 'FpK3GaM', 'time': '00:15', 'status': -1}, # print(type(datas)) for data in datas: epgs.append(data) # {'name': '星空放映厅', 'typeid': 0, 'pid': 'FpK3GaM', 'time': '00:15', 'status': -1} # print(epgs) return { 'success': success, 'epgs': epgs, 'msg': msg, 'last_program_date': dt, 'ban': ban, 'source':'tvmao' } except Exception as e: success = 0 msg = 'spider-tvmao-%s'%e ret = { 'success': success, 'epgs': epgs, 'msg': msg, 'last_program_date': dt, 'ban': 0, 'source':'tvmao' } return ret # 获取频道列表 def get_channels_tvmao(sorts={'央视': 'cctv', '卫视': 'satellite','辽宁': 'LNTV','沈阳': 'LNSY'}): channels = [] # url_sort = 'https://www.tvmao.com/program/playing/' # res = requests.get(url_sort,headers = headers,timeout = 5) # res.encoding = 'utf-8' # soup = bs(res.text,'html.parser') # provinces = {} # big_sorts = {} # provinces_more = soup.select('div.province > ul.province-list > li') # big_sorts_more = soup.select('dl.chntypetab > dd') # for province_more in provinces_more: # province = province_more.text.strip().replace('黑龙','黑龙江') # province_id = province_more.a['href'].replace('/program/playing/','').replace('/','') # province = { # province:province_id, # } # provinces.update(province) # for big_sort_more in big_sorts_more: # sort_name = big_sort_more.text.strip() # url = big_sort_more.a['href'] # sort_id = url.replace('/program/playing/','').replace('/','') # # print(sort_name,sort_id) # if sort_name in provinces or sort_name == '收藏' or sort_name == '数字付费': # continue # big_sorts.update({sort_name:sort_id}) # provinces.update(big_sorts) # sorts = provinces n = 0 for sort_name in sorts: url = 'https://www.tvmao.com/program/playing/%s'%sorts[sort_name] res = requests.get(url,headers = headers,timeout = 5) res.encoding = 'utf-8' soup = bs(res.text,'html.parser') channel_trs = soup.select('table.timetable > tr') n += 1 for tr in channel_trs: xmls = [] tr1 = tr.td.a name = tr1['title'] # 如果name中包含有“频道”则替换为空 name = name.replace('频道','') href = tr1['href'] id = href.replace('/program/','').replace('/','-').replace('.html','').replace('-program_','') id = re.sub('-w\d$','',id) res1 = tr1['res'] channel = { 'name': name, 'id': [id], 'url': 'https://m.tvmao.com/program/%s.html' % id, 'source': 'tvmao', 'logo': '', 'desc': '', 'sort': sort_name, 'res': res1, } channels.append(channel) xmls.append('%s' % (name, name)) print('%s' % (name, name)) dt = datetime.datetime.now() program = get_epgs_tvmao2(channel,id,dt,{}) programs = program['epgs'] # {'name': '星空放映厅', 'typeid': 0, 'pid': 'FpK3GaM', 'time': '00:15', 'status': -1} # 2024秘境之眼-峭壁精灵黑叶猴(4K) for program in programs: id = channel['id'] start = program['time'] # '00:15' dt_srr = re.sub(r'[:：]', '', start) start = f'{datetime.datetime.now().strftime('%Y%m%d')}{dt_srr }00 +0800' # 结束时间等于下一条的开始时间 try: end = programs[programs.index(program)+1]['time'] end = re.sub(r'[:：]', '', end) end = f'{datetime.datetime.now().strftime('%Y%m%d')}{end}00 +0800' except: end = f'{datetime.datetime.now().strftime('%Y%m%d')}235900 +0800' title = program['name'] xmls.append('%s' % (start, end, name, title)) print('%s' % (start, end, name, title)) # 获取当前日期 dtx = datetime.datetime.now().strftime('%Y%m%d') path = os.path.join(os.path.dirname(os.path.abspath(__file__)), f'channel/tvmao_{dtx}.xml') # 读取原文件内容，避免使用'a'模式 with open(path, 'r', encoding='utf-8') as f1: lines = f1.readlines() # 删除原有最后一行 if lines and lines[-1].strip() == '': lines = lines[:-1] # 写入新的内容 with open(path, 'w', encoding='utf-8') as f: f.writelines(lines) f.write('\n'.join(xmls) + '\n') f.write('') time.sleep(10) # 防止被封 return channels def main(): # 保存到当前路径下的channel文件夹中，文件名为tvsou_20240807.xml dt = datetime.datetime.now().strftime('%Y%m%d') path = os.path.dirname(os.path.abspath(__file__))+f'/channel/tvmao_{dt}.xml' # 保存xml格式 with open(path, 'w', encoding='utf-8') as f: heade_str=''' \n''' heade_str = heade_str +'' f.write(heade_str) f.close() get_channels_tvmao() if __name__ == '__main__': sorts = { '央视': 'cctv', '卫视': 'satellite', '辽宁': '210000', '吉林': '220000', '北京': '110000', '黑龙江': '230000', '上海': '310000', '天津': '120000', '江苏': '320000', '江西': '360000', '广东': '440000', '贵州': '520000', '宁夏': '640000', '河北': '130000', '浙江': '330000', '山东': '370000', '河南': '410000', '广西': '450000', '云南': '530000', '陕西': '610000', '内蒙古': '150000', '新疆': '650000', '山西': '140000', '安徽': '340000', '湖北': '420000', '海南': '460000', '重庆': '500000', '西藏': '540000', '甘肃': '620000', '内蒙': '150000', '福建': '350000', '湖南': '430000', '四川': '510000', '青海': '630000'} # get_channels_tvmao() main()