123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346 |
- # coding=utf-8
- # !/usr/bin/python
- import sys
- sys.path.append('..')
- from base.spider import Spider
- import json
- import re
- import urllib
- class Spider(Spider): # 元类 默认的元类 type
- def getName(self):
- return "Alist"
- def init(self, extend=""):
- print("============{0}============".format(extend))
- pass
- def isVideoFormat(self, url):
- pass
- def manualVideoCheck(self):
- pass
- def homeContent(self, filter):
- result = {}
- cateManual = {
- "小雅": "http://43.139.29.179:5244",
- "七米蓝": "https://al.chirmyram.com",
- "梅花盘": "https://pan.142856.xyz/OneDrive",
- "触光云盘": "https://pan.ichuguang.com",
- "小孟资源": "https://8023.haohanba.cn/小孟丨资源大合集/无损音乐",
- "资源小站": "https://960303.xyz/ali",
- "轻弹浅唱": "https://g.xiang.lol",
- "小兵组网盘视频": "https://6vv.app"
- }
- classes = []
- for k in cateManual:
- classes.append({
- 'type_name': k,
- "type_flag": "1",
- 'type_id': cateManual[k]
- })
- result['class'] = classes
- if (filter):
- result['filters'] = self.config['filter']
- return result
- def homeVideoContent(self):
- result = {
- 'list': []
- }
- return result
- ver = ''
- baseurl = ''
- def getVersion(self, gtid):
- param = {
- "path": '/'
- }
- if gtid.count('/') == 2:
- gtid = gtid + '/'
- baseurl = re.findall(r"http.*://.*?/", gtid)[0]
- ver = self.fetch(baseurl + 'api/public/settings', param)
- vjo = json.loads(ver.text)['data']
- if type(vjo) is dict:
- ver = 3
- else:
- ver = 2
- self.ver = ver
- self.baseurl = baseurl
- def categoryContent(self, tid, pg, filter, extend):
- result = {}
- if tid.count('/') == 2:
- tid = tid + '/'
- nurl = re.findall(r"http.*://.*?/", tid)[0]
- if self.ver == '' or self.baseurl != nurl:
- self.getVersion(tid)
- ver = self.ver
- baseurl = self.baseurl
- if tid.count('/') == 2:
- tid = tid + '/'
- pat = tid.replace(baseurl,"")
- param = {
- "path": '/' + pat
- }
- if ver == 2:
- rsp = self.postJson(baseurl + 'api/public/path', param)
- jo = json.loads(rsp.text)
- vodList = jo['data']['files']
- elif ver == 3:
- rsp = self.postJson(baseurl + 'api/fs/list', param)
- jo = json.loads(rsp.text)
- vodList = jo['data']['content']
- videos = []
- cid = ''
- purl = ''
- svodList = str(vodList)
- lenvodList = len(vodList)
- substr = str(re.findall(r"\'name\': \'(.*?)\'", svodList))
- foldernum = svodList.count('\'type\': 1')
- filenum = lenvodList - foldernum
- for vod in vodList:
- if ver == 2:
- img = vod['thumbnail']
- elif ver == 3:
- img = vod['thumb']
- if len(img) == 0:
- if vod['type'] == 1:
- img = "http://img1.3png.com/281e284a670865a71d91515866552b5f172b.png"
- if pat != '':
- aid = pat + '/'
- else:
- aid = pat
- if vod['type'] == 1:
- tag = "folder"
- remark = "文件夹"
- cid = baseurl + aid + vod['name']
- #计算文件大小
- else:
- size = vod['size']
- if size > 1024 * 1024 * 1024 * 1024.0:
- fs = "TB"
- sz = round(size / (1024 * 1024 * 1024 * 1024.0), 2)
- elif size > 1024 * 1024 * 1024.0:
- fs = "GB"
- sz = round(size / (1024 * 1024 * 1024.0), 2)
- elif size > 1024 * 1024.0:
- fs = "MB"
- sz = round(size / (1024 * 1024.0), 2)
- elif size > 1024.0:
- fs = "KB"
- sz = round(size / (1024.0), 2)
- else:
- fs = "KB"
- sz = round(size / (1024.0), 2)
- tag = "file"
- remark = str(sz) + fs
- cid = baseurl + aid + vod['name']
- # 开始爬视频与字幕
- if filenum < 150:
- if 'mp4' in vod['name'] or 'mkv' in vod['name'] or 'TS' in vod['name'] or 'flv' in vod['name'] or 'rmvb' in vod['name'] or 'mp3' in vod['name'] or 'flac' in vod['name'] or 'wav' in vod['name'] or 'wma' in vod['name'] or 'dff' in vod['name']:
- vodurl = vod['name']
- # 开始爬字幕
- cid = '###'
- subname = re.findall(r"(.*)\.", vod['name'])[0]
- if filenum == 2:
- if '.ass' in substr:
- sub = re.findall(r"'(.*).ass", substr)[0]
- subt = '@@@' + sub + '.ass'
- if ',' in sub:
- sub = re.findall(r"', '(.*).ass", substr)[0]
- subt = '@@@' + sub + '.ass'
- if '.srt' in substr:
- sub = re.findall(r"'(.*).srt", substr)[0]
- subt = '@@@' + sub + '.srt'
- if ',' in sub:
- sub = re.findall(r"', '(.*).srt", substr)[0]
- subt = '@@@' + sub + '.srt'
- else:
- if subname + '.ass' in substr:
- subt = '@@@' + subname + '.ass'
- elif subname + '.srt' in substr:
- subt = '@@@' + subname + '.srt'
- # 合并链接
- if 'subt' in locals().keys():
- purl = purl + '{0}{1}#'.format(vodurl, subt)
- else:
- purl = purl + '{0}#'.format(vodurl)
- else:
- subname = re.findall(r"(.*)\.", vod['name'])[0]
- if subname + '.ass' in substr:
- subt = '@@@' + subname + '.ass'
- cid = cid + subt
- elif subname + '.srt' in substr:
- subt = '@@@' + subname + '.srt'
- cid = cid + subt
- videos.append({
- "vod_id": cid,
- "vod_name": vod['name'],
- "vod_pic": img,
- "vod_tag": tag,
- "vod_remarks": remark
- })
- if 'purl' in locals().keys():
- purl = baseurl + aid + '+++' + purl
- for i in range(foldernum, lenvodList):
- if videos[i]['vod_id'] == '###':
- videos[i]['vod_id'] = purl
- result['list'] = videos
- result['page'] = 1
- result['pagecount'] = 1
- result['limit'] = 999
- result['total'] = 999999
- return result
- def detailContent(self, array):
- id = array[0]
- if '+++' in id:
- ids = id.split('+++')
- durl = ids[0]
- vsList = ids[1].strip('#').split('#')
- vsurl = ''
- for vs in vsList:
- if '@@@' in vs:
- dvs = vs.split('@@@')
- vname = dvs[0]
- vurl = durl + dvs[0]
- surl = durl + dvs[1]
- vsurl = vsurl + '{0}${1}@@@{2}#'.format(vname, vurl, surl)
- else:
- vurl = durl + vs
- vsurl = vsurl + '{0}${1}#'.format(vs, vurl)
- url = vsurl
- else:
- durl = id
- if self.ver == '' or self.baseurl == '':
- self.getVersion(durl)
- baseurl = self.baseurl
- if '+++' in id:
- vid = durl.replace(baseurl, "").strip('/')
- else:
- vid = durl.replace(re.findall(r".*/", durl)[0], "")
- url = vid + '$' + id
- vod = {
- "vod_id": vid,
- "vod_name": vid,
- "vod_pic": '',
- "vod_tag": '',
- "vod_play_from": "播放",
- "vod_play_url": url
- }
- result = {
- 'list': [
- vod
- ]
- }
- return result
- def searchContent(self, key, quick):
- result = {
- 'list': []
- }
- return result
- def playerContent(self, flag, id, vipFlags):
- result = {}
- url = ''
- subturl = ''
- ifsub = '@@@' in id
- if ifsub is True:
- ids = id.split('@@@')
- if self.ver == '' or self.baseurl == '':
- self.getVersion(ids[1])
- ver = self.ver
- baseurl = self.baseurl
- fileName = ids[1].replace(baseurl, "")
- vfileName = ids[0].replace(baseurl, "")
- param = {
- "path": '/' + fileName,
- "password": "",
- "page_num": 1,
- "page_size": 100
- }
- vparam = {
- "path": '/' + vfileName,
- "password": "",
- "page_num": 1,
- "page_size": 100
- }
- if ver == 2:
- rsp = self.postJson(baseurl + 'api/public/path', param)
- jo = json.loads(rsp.text)
- vodList = jo['data']['files'][0]
- subturl = vodList['url']
- vrsp = self.postJson(baseurl + 'api/public/path', vparam)
- vjo = json.loads(vrsp.text)
- vList = vjo['data']['files'][0]
- url = vList['url']
- elif ver == 3:
- rsp = self.postJson(baseurl + 'api/fs/get', param)
- jo = json.loads(rsp.text)
- vodList = jo['data']
- subturl = vodList['raw_url']
- vrsp = self.postJson(baseurl + 'api/fs/get', vparam)
- vjo = json.loads(vrsp.text)
- vList = vjo['data']
- url = vList['raw_url']
- if subturl.startswith('http') is False:
- head = re.findall(r"h.*?:", baseurl)[0]
- subturl = head + subturl
- if url.startswith('http') is False:
- head = re.findall(r"h.*?:", baseurl)[0]
- url = head + url
- urlfileName = urllib.parse.quote(fileName)
- subturl = subturl.replace(fileName, urlfileName)
- urlvfileName = urllib.parse.quote(vfileName)
- url = url.replace(vfileName, urlvfileName)
- result['subt'] = subturl
- else:
- if self.ver == '' or self.baseurl == '':
- self.getVersion(id)
- ver = self.ver
- baseurl = self.baseurl
- vfileName = id.replace(baseurl, "")
- vparam = {
- "path": '/' + vfileName,
- "password": "",
- "page_num": 1,
- "page_size": 100
- }
- if ver == 2:
- vrsp = self.postJson(baseurl + 'api/public/path', vparam)
- vjo = json.loads(vrsp.text)
- vList = vjo['data']['files'][0]
- driver = vList['driver']
- url = vList['url']
- elif ver == 3:
- vrsp = self.postJson(baseurl + 'api/fs/get', vparam)
- vjo = json.loads(vrsp.text)
- vList = vjo['data']
- url = vList['raw_url']
- driver = vList['provider']
- if url.startswith('http') is False:
- head = re.findall(r"h.*?:", baseurl)[0]
- url = head + url
- urlvfileName = urllib.parse.quote(vfileName)
- url = url.replace(vfileName, urlvfileName)
- if driver == 'Baidu.Disk':
- result["header"] = {"User-Agent": "pan.baidu.com"}
- result["parse"] = 0
- result["playUrl"] = ''
- result["url"] = url
- return result
- config = {
- "player": {},
- "filter": {}
- }
- header = {}
- def localProxy(self, param):
- return [200, "video/MP2T", action, ""]
|