yongge/tvbox
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

update XYQ

Browse Source
This commit is contained in:
chuqiuyu
2023-07-11 22:46:12 +08:00
parent 08d7266a5d
commit 88d7ddd2fa
50 changed files with 1724 additions and 671 deletions
Download Patch File Download Diff File Expand all files Collapse all files
py/py_cctv_new.py
+461
View File
@@ -0,0 +1,461 @@
#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<title>.+?)',\n{0,1}\s*'brief':\s*'(.+?)',\n{0,1}\s*'img':\s*'(.+?)',\n{0,1}\s*'url':\s*'(?P<url>.+?)'"
elif tid=="特别节目":
patternTxt=r'class="tp1"><a\s*href="(?P<url>https://.+?)"\s*target="_blank"\s*title="(?P<title>.+?)"></a></div>'
elif tid=="动画片":
patternTxt=r"'title':\s*'(?P<title>.+?)',\n{0,1}\s*'img':\s*'(.+?)',\n{0,1}\s*'brief':\s*'(.+?)',\n{0,1}\s*'url':\s*'(?P<url>.+?)'"
elif tid=="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("&nbsp;"," ")
#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
py/xigua.py
-411
View File
@@ -1,411 +0,0 @@
#coding=utf-8
#!/usr/bin/python
import sys
sys.path.append('..')
from base.spider import Spider
import base64
import math
import json
import requests
import urllib
from urllib import request, parse
import urllib.request
import re
class Spider(Spider):
def getName(self):
return "西瓜视频(个人中心)"
def init(self,extend=""):
self.userid=self.get_userid()
def isVideoFormat(self,url):
pass
def manualVideoCheck(self):
pass
def homeContent(self,filter):
result = {}
cateManual = {
"电视剧":"dianshiju",
"电影":"dianying",
"动漫":"dongman",
"纪录片":"jilupian",
"少儿":"shaoer",
"综艺":"zongyi",
"关注":"follow"
}
if self.userid=='':
del cateManual['关注']
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
userid=''
def categoryContent(self,tid,pg,filter,extend):
result = {}
idTxt='电视剧'
maximum=17
url = 'https://www.ixigua.com/api/cinema/filterv2/albums'
if tid=='dianying':
idTxt='电影'
elif tid=='zongyi':
idTxt='综艺'
elif tid=='dianshiju':
idTxt='电视剧'
elif tid=='dongman':
idTxt='动漫'
elif tid=='jilupian':
idTxt='纪录片'
elif tid=='shaoer':
idTxt='少儿'
elif tid=='follow':
offset=0 if int(pg)<2 else 20*int(pg)
url='https://www.ixigua.com/api/userv2/follow/list?authorId={0}&sortType=desc&sortType=desc&cursor={1}'.format(self.userid,offset)
maximum=12
videos=[]
if tid!='follow':
offset=0 if int(pg)<2 else 18*int(pg)
self.header['Referer']='https://www.ixigua.com/cinema/filter/'.format(tid)
data=r'{"pinyin":"'+tid+'","filters":{"type":"'+idTxt+'","area":"全部地区","tag":"全部类型","sort":"综合排序","paid":"全部资费"},"offset":'+str(offset)+',"limit":18}'
req = request.Request(url=url, data=bytes(data, encoding='utf8'),headers=self.header, method='POST')
response = request.urlopen(req)
urlTxt=response.read().decode('utf-8')
videos= self.get_list_videoGroup_json(jsonTxt=urlTxt)
else:
rsp=self.fetch(url,headers=self.header)
urlTxt=rsp.text
videos= self.get_list_videoGroup_follow_json(jsonTxt=urlTxt)
numvL = len(videos)
result['list'] = videos
result['page'] = pg
result['pagecount'] = pg if int(numvL)<maximum else int(pg)+1
result['limit'] = numvL
result['total'] = numvL
return result
def get_userid(self):
Url='https://www.ixigua.com/'
rsp=self.fetch(Url,headers=self.header)
htmlTxt = rsp.text
userid= self.get_RegexGetText(Text=htmlTxt,RegexText=r'"identity":{"id":"(\d+?)",',Index=1)
return userid
def detailContent(self,array):
result = {}
aid = array[0].split('###')
key = aid[1]
title = aid[0]
act=aid[2]
logo = aid[3]
Url='https://www.ixigua.com/api/albumv2/details?albumId={0}'.format(key)
if len(aid)==5:
Url='https://www.ixigua.com/api/videov2/author/new_video_list?to_user_id={0}'.format(key)
rsp = self.fetch(Url,headers=self.header)
htmlTxt = rsp.text
typeName=''
area=''
dir=''
cont=''
vip='true'
videoList=[]
if len(aid)==5:
jRoot = json.loads(htmlTxt)
if jRoot['code']!=200:
return result
jo = jRoot['data']
jsonList=jo['videoList']
for value in jsonList:
id="{0}${1}_false".format(value['title'],value.get('group_id'))
videoList.append(id)
dir=title
elif htmlTxt.find('playlist')>2:
jRoot = json.loads(htmlTxt)
if jRoot['code']!=200:
return result
jo = jRoot['data']
jsonList=jo['playlist']
if jsonList is not None:
for value in jsonList:
id="{0}${1}?id={2}_{3}".format(value['title'],value['albumId'],value['episodeId'],vip)
videoList.append(id)
playFrom=[v for v in jo['albumInfo']['tagList']]
typeName='/'.join(playFrom)
playFrom=[v for v in jo['albumInfo']['areaList']]
area='/'.join(playFrom)
playFrom=[v['name'] for v in jo['albumInfo']['directorList']]
dir='/'.join(playFrom)
cont=jo['albumInfo']['intro']
if len(videoList)<1:
return result
vod = {
"vod_id":array[0],
"vod_name":title,
"vod_pic":logo,
"type_name":typeName,
"vod_year":'',
"vod_area":area,
"vod_remarks":"",
"vod_actor":'',
"vod_director":dir,
"vod_content":cont
}
vod['vod_play_from'] = '西瓜'
vod['vod_play_url'] = "#".join(videoList)
result = {
'list':[
vod
]
}
return result
def verifyCode(self):
pass
def searchContent(self,key,quick):
Url='https://www.ixigua.com/api/searchv2/lvideo/{0}/0'.format(urllib.parse.quote(key))
rsp = self.fetch(Url,headers=self.header)
htmlTxt = rsp.text
videos=self.get_list(html=htmlTxt)
'''
Url='https://www.ixigua.com/api/searchv2/user/{0}/10'.format(urllib.parse.quote(key))
rsp = self.fetch(Url,headers=self.header)
htmlTxt1 = rsp.text
videos=self.get_list_user(html=htmlTxt1)
'''
result = {
'list': videos
}
return result
def playerContent(self,flag,id,vipFlags):
result={}
UrlId=id.split('_')
Url='https://www.ixigua.com/{0}'.format(UrlId[0])
headers = {
'User-Agent':'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3947.100 Mobile Safari/537.36'
}
jx=1 if UrlId[1]=='true' else 0
result["parse"] = 1#0=直接播放,1=解析
result["playUrl"] = ''
result["url"] = Url
result['jx'] = jx#VIP解析
result["header"] =headers
return result
def get_RegexGetText(self,Text,RegexText,Index):
returnTxt=""
Regex=re.search(RegexText, Text, re.M|re.I)
if Regex is None:
returnTxt=""
else:
returnTxt=Regex.group(Index)
return returnTxt
def get_RegexGetTextLine(self,Text,RegexText,Index):
returnTxt=[]
pattern = re.compile(RegexText)
ListRe=pattern.findall(Text)
if len(ListRe)<1:
return returnTxt
for value in ListRe:
returnTxt.append(value)
return returnTxt
def get_playlist(self,Text,headStr,endStr):
circuit=""
origin=Text.find(headStr)
if origin>8:
end=Text.find(endStr,origin)
circuit=Text[origin:end]
return circuit
def removeHtml(self,txt):
soup = re.compile(r'<[^>]+>',re.S)
txt =soup.sub('', txt)
return txt.replace("&nbsp;"," ")
def get_webReadFile(self,urlStr):
headers = {
'Referer':urlStr,
'User-Agent': 'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.112 Safari/537.36',
'Host': 'www.ikmjw.com'
}
req = urllib.request.Request(url=urlStr, headers=headers)
html = urllib.request.urlopen(req).read().decode('utf-8')
return html
def get_list(self,html):
result={}
jRoot = json.loads(html)
if jRoot['code']!=0:
return result
jo = jRoot['data']
if len(jo)<1:
return result
vodList = jo['data']
if len(vodList)<1:
return result
videos=[]
img='_'
artist='_'
for vod in vodList:
if vod['type']!='lvideo':
continue
data=vod['data']
display=data['display']
title =display['name']
if len(title)==0:
continue
episode_link=display.get('episode_link')
asc_link=episode_link.get('asc_link')
KeyName='album_id'
if asc_link is None:
asc_link=episode_link.get('desc_link')
KeyName='album_id'
id=asc_link[0].get('album_id')
sslocal=asc_link[0]['scheme_url']
if sslocal!=None and sslocal.find('sslocal:')<0:
continue
video_cover_info=display.get('video_cover_info')
img=video_cover_info['url'] if video_cover_info is not None else '_'
try:
artist=display['actor']
except Exception:
artist=''
remarks=display['rating']
vod_id="{0}###{1}###{2}###{3}".format(title,id,artist,img)
videos.append({
"vod_id":vod_id,
"vod_name":title,
"vod_pic":img,
"vod_remarks":remarks
})
return videos
def get_list_user(self,html):
result={}
jRoot = json.loads(html)
if jRoot['code']!=0:
return result
jo = jRoot['data']
if len(jo)<1:
return result
vodList = jo['data']
if len(vodList)<1:
return result
videos=[]
img='_'
artist='_'
for vod in vodList:
if vod['type']!='user':
continue
data=vod['data']
img=data['avatar']
title =data['name']
log_pb=json.loads(data.get('log_pb'))
user_auth_info=json.loads(data.get('user_auth_info'))
remarks=user_auth_info['auth_info']
id=log_pb.get('search_result_id')
vod_id="{0}###{1}###{2}###{3}###{4}".format(title,id,artist,img,'user')
videos.append({
"vod_id":vod_id,
"vod_name":title,
"vod_pic":img,
"vod_remarks":remarks
})
return videos
def get_list_videoGroup_json(self,jsonTxt):
result={}
jRoot = json.loads(jsonTxt)
if jRoot['code']!=200:
return result
jo = jRoot['data']
vodList = jo['albumList']
if len(vodList)<1:
return result
videos=[]
img='_'
artist='_'
for vod in vodList:
url =vod['albumId']
title =vod['title']
imgList =vod.get('coverList')
if len(imgList)>0:
img=imgList[0]['url']
remarks=vod['subTitle']
artistList=vod.get('actorList')
if artistList is not None:
artistList=artistList if len(artistList)<5 else artistList[0:4]
artist='/'.join(artistList)
if len(title)==0:
continue
#标题###地址###演员###封面
vod_id="{0}###{1}###{2}###{3}".format(title,url,artist,img)
videos.append({
"vod_id":vod_id,
"vod_name":title,
"vod_pic":img,
"vod_remarks":remarks
})
return videos
def get_list_videoGroup_follow_json(self,jsonTxt):
videos=[]
jRoot = json.loads(jsonTxt)
if jRoot['code']!=0:
return videos
jo = jRoot['data']
vodList=jo['data']
if len(vodList)<1:
return videos
img='_'
artist=''
for vod in vodList:
url =vod.get('user_id')
title =vod['name']
img =vod.get('avatar_url')
remarks=vod['description']
artistList=vod.get('actorList')
artist=title
if len(title)==0:
continue
#标题###地址###演员###封面
vod_id="{0}###{1}###{2}###{3}###{4}".format(title,url,artist,img,'user')
videos.append({
"vod_id":vod_id,
"vod_name":title,
"vod_pic":img,
"vod_remarks":remarks
})
return videos
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_EpisodesList(self,jsonList):
vodItems=[]
for value in jsonList:
vodItems.append(value['title']+"$"+'https://www.ixigua.com/{0}?logTag=55abe18cfb733871bb04'.format(value['episodeId']))
return vodItems
config = {
"player": {},
"filter": {}
}
header = {
"Cookie":"s_v_web_id=verify_lev3h43l_rrTPrFDG_ztWQ_4ugg_8WBA_yGVYsXlVyoBh; passport_csrf_token=80e0efe90bc8bd6681a896dd90cd08cc; passport_csrf_token_default=80e0efe90bc8bd6681a896dd90cd08cc; __ac_nonce=0643361890096533c765; __ac_signature=_02B4Z6wo00f01JPVVrAAAIDBcisHPfWA66CT91IAAEDK9840CE-PheNOCgA4VtrFG0-K.KkLmAR5KsI-Xx-6dBXxz.ABWU2OpEd22kF7biwGaVmGR7an4S1heLEU9xpv0ObRSHFHDslR7uL8fb; support_webp=true; support_avif=false; MONITOR_WEB_ID=45c3b6ab-7ad4-4805-b971-5962d1d6909a; ttwid=1%7CCueNR-HU9tGVF30WaiFCjXDxh0FUXoXsZr-cIb9Dogg%7C1681089268%7Cf0eeaa2016a602a277055494954f083e9f7fa8121c5dd1162db9195932fa167b; odin_tt=386a42a5740f9859d4670373fc8c70cf320ea5b227aed04bcc53fde26c233e8c952a8b0ba5f80fd3d46f9663fa595d8c; sid_guard=842b56710f55021912487890e7d5bef3%7C1681089337%7C3024001%7CMon%2C+15-May-2023+01%3A15%3A38+GMT; uid_tt=b7eb5b73cd72bed6d3c2e1e1e8aaa9f3; uid_tt_ss=b7eb5b73cd72bed6d3c2e1e1e8aaa9f3; sid_tt=842b56710f55021912487890e7d5bef3; sessionid=842b56710f55021912487890e7d5bef3; sessionid_ss=842b56710f55021912487890e7d5bef3; sid_ucp_v1=1.0.0-KGQ2YzBlMDFiMzIyMjY0YTIwMDg2MjZmZGQzMTE5MmFlYTYzY2EwMTMKFQjL2cnx9AIQucbNoQYYGCAMOAhABRoCaGwiIDg0MmI1NjcxMGY1NTAyMTkxMjQ4Nzg5MGU3ZDViZWYz; ssid_ucp_v1=1.0.0-KGQ2YzBlMDFiMzIyMjY0YTIwMDg2MjZmZGQzMTE5MmFlYTYzY2EwMTMKFQjL2cnx9AIQucbNoQYYGCAMOAhABRoCaGwiIDg0MmI1NjcxMGY1NTAyMTkxMjQ4Nzg5MGU3ZDViZWYz; csrf_session_id=c58adecac1d20d91d8c61e72ce0c6fdb; ixigua-a-s=3; msToken=St3ptsHkwBjPgGvRWhZfVdhHO_K16vTizxxna17draCvt4ekz6DQXO6c2Ctrp6gOnn9_Abm83-a9URQp5rKb-JIPs4mQPn2fpKlQRY6jLDBWUdLYTePIAACU6cY2fk40; tt_scid=nN3WPItw72gnB5PDiGcHveirXDZ8oDl5n.ihKN583mmZhoe.uLhFpy3JOL8wrsQO0ed1",
"Referer": 'https://www.ixigua.com/cinema/filter/dianshiju/',
'User-Agent':'User-Agent: Mozilla%2F5.0+(Windows+NT+10.0%3B+WOW64)+AppleWebKit%2F537.36+(KHTML%2C+like+Gecko)+Chrome%2F63.0.3239.132+Safari%2F537.36',
'Host': 'www.ixigua.com',
'Accept': 'application/json, text/plain, */*',
'x-secsdk-csrf-token': '0001000000017b593ba6251b18bd7bce2753042917bb36e534867b9606317584c00b0ae836c61754314b7365128e',
'tt-anti-token': 'oDr7A3PDDFq4pWzk-707faf92a9e3040f5c6ed4284d53b05b7091221852c0e9d32bca9fcfe5035225',
'content-type': 'application/json'
}
def localProxy(self,param):
return [200, "video/MP2T", action, ""]