合并百度影音的离线数据( with python 2.3)

yipeiwu_com5年前Python基础

四种格式的解析:

filelist

slicelist

download.cfg

third_party_download.cfg

还是2个文件。替换之前版本即可。

初步测试正常,但时间轴不对。

代码如下:

# -*- coding: UTF-8 -*-
import os
import io
import codecs
import string
import shutil
import moviefmt
import traceback
def coroutine(func):
 def start(*args,**kwargs):
  g = func(*args,**kwargs)
  g.next()
  return g
 return start
@coroutine
def enum_movie_file(target): 
 selectedFolder = (yield)
 for fileitem in os.listdir(selectedFolder):    
  targetFO = os.path.join(selectedFolder,fileitem)  
  if(os.path.isfile(targetFO) == True):
   continue;  
  target.send(targetFO)  
@coroutine
def read_movie_file(funcDisp,target):
 while(True):
  filmFolder = (yield)
  for fileitem in os.listdir(filmFolder):  
   targetfile = os.path.join(filmFolder,fileitem)
   if(os.path.isfile(targetfile) == False):
    continue;   
   filebasename , fext = os.path.splitext(fileitem);    
   if(filebasename[0] == "."):
    continue   
   if(funcDisp.has_key(string.lower(fext))):
    pfn = funcDisp[string.lower(fext)];
    (targetFmt,targetObjects,filmFolderEx,filebasenameEx) = pfn(targetfile)
    if(targetFmt is None):
     continue;
    outputs = filmFolder,filebasename, (targetFmt,targetObjects,filmFolderEx,filebasenameEx);
    # outputs = filmFolder,filebasename, pfn(targetfile);
    target.send(outputs)
    break
def getWindowsText(orgText): 
 try:
  return orgText.encode('gbk') 
 except Exception as exc: 
  print("%s" % exc); 
  return orgText
@coroutine
def create_report(outputfile):
 objTar = codecs.open(outputfile,"w+")  
 while(1):
  filmFolder,filebasename,(extname,piece_list,filmFolderEx,filebasenameEx) = (yield)
  if(extname == None) :
   break;
  objTar.write('cd \"%s\"\r\n' % (filmFolderEx if filmFolderEx else filmFolder))  
  objTar.write('attrib -h *.*\r\n ')  
  if(len(piece_list) >1):
   objTar.write('copy /b ')  
  else:
   objTar.write('copy ')  
  if(len(piece_list) == 1):
   objTar.write('\"%s \"' %(getWindowsText(piece_list[0])))
  else:   
   bFirst = True
   for line in piece_list:
    if(bFirst == False):     
     objTar.write('+\"%s\"' %(getWindowsText(line))) 
    else:     
     objTar.write('\"%s\"' %(getWindowsText(line)))
     bFirst = False
  relpath = os.path.dirname(filmFolder)  
  currentPath = os.path.join(getWindowsText(relpath),getWindowsText(filebasenameEx if filebasenameEx else filebasename)) 
  objTar.write(' %s.%s\r\n' % (currentPath,extname))    
  objTar.write('cd %s\r\n' %(relpath))
 objTar.close()    
if __name__ == '__main__': 
 funcDisp = dict()
 funcDisp['.bdv_0000']= moviefmt.read_bdv_file;
 funcDisp['.rmvb_0000']= moviefmt.read_rmvb_file;
 funcDisp['.mkv_0000']= moviefmt.read_mkv_file;
 funcDisp['.bdv']= moviefmt.read_bdv_index;   
 funcDisp['.mp4_0000']= moviefmt.read_mp4_file;   
 funcDisp['']= moviefmt.read_mkv_2_file; 
 funcDisp['.filelist'] = moviefmt.read_filelist_index;
 funcDisp['.slicelist'] = moviefmt.read_slicelist_index;
 funcDisp['.cfg'] = moviefmt.read_cfg_index;
 try:
  rmf = enum_movie_file(read_movie_file(funcDisp,create_report('film.bat')))
  rmf.send(os.getcwd())
  rmf.close()
 except StopIteration:
  pass
 except Exception as exc: 
  print("%s" % exc); 
  info = traceback.format_exc()
  print(info)      
 print("done");  
# -*- coding: UTF-8 -*-
import os
import io
import sys
import string
import shutil
import codecs
import glob
import re
def read_bdv_index_V1(objFile):
 piece_list= list() 
 for line in objFile:
  if(line[0:4] != 'file'):
   continue;
  strings = string.split(line,'/')
  tarfile = strings[len(strings)-1]  
  tempText = string.strip(tarfile)
  piece_list.append(tempText)
 return "avi",piece_list,None,None
def read_bdv_index_V2(objFile):
 piece_list= list() 
 for line in objFile:  
  nPos = line.count('bdv')
  if( nPos <=0):
   continue;  
  tarfile = line[0:len(line)-2] 
  piece_list.append(tarfile) 
 return "mpeg",piece_list,None,None
def read_bdv_index_V3(objFile):
 piece_list= list()   
 oneFile= os.path.basename(objFile) 
 piece_list.append(oneFile)
 return "avi",piece_list,None,None
def read_bdv_index_V4(objFile):
 piece_list= list() 
 #skip #EXT-X-MEDIA-SEQUENCE
 objFile.readline();
 for line in objFile:
  if(line.startswith('#')==True):
   continue;  
  piece_list.append(line.replace('\r\n',''))
 return "avi",piece_list,None,None
def count_file_item(objFile,extText):
 cItem = 0;
 folderName = os.path.dirname(objFile)
 for fileitem in os.listdir(folderName): 
  filebasename , fext = os.path.splitext(fileitem); 
  if(fext == extText):
   cItem = cItem +1
 return cItem 
def read_bdv_index(filename):
 piece_list= list() 
 ext_type = None
 filmFolderEx = None
 filebasenameEx = None
 # total file count
 cItem = count_file_item(filename,".bdv")
 if(cItem == 1):
  ext_type,piece_list,filmFolderEx,filebasenameEx = read_bdv_index_V3(filename)
 else:
  objFile = codecs.open(filename,'r','utf-8') 
  topline = objFile.readline();
  bdv_ver = topline.replace("\r\n","")
  if(bdv_ver == '#EXTM3U'):
   v3Text = objFile.readline();
   if(v3Text.startswith('#EXT-X-TARGETDURATION') == False):
    ext_type,piece_list = read_bdv_index_V2(objFile)
   else:
    ext_type,piece_list = read_bdv_index_V4(objFile)
  else:
   ext_type,piece_list = read_bdv_index_V1(objFile)
  objFile.close()  
 return (ext_type ,piece_list,filmFolderEx,filebasenameEx)  
def read_bdv_file(filename):
 piece_list= list()
 piece_list.append('*.bdv_*')
 return ('avi',piece_list,None,None)
def read_rmvb_file(filename):
 piece_list= list()
 piece_list.append('*.rmvb_*')
 return ('rmvb',piece_list,None,None)
def read_mkv_file(filename):
 piece_list= list() 
 piece_list.append('*.mkv_*')
 return ('mkv',piece_list,None,None)
def read_mp4_file(filename):
 piece_list= list() 
 piece_list.append('*.mp4_*')
 return ('mp4',piece_list,None,None)
def read_mkv_2_file(filename):
 piece_list= list() 
 piece_list.append('video_*')
 return ('mkv',piece_list,None,None)
def read_filelist_index(filename):
 filmFolderEx = None
 filebasenameEx = None
 objFile = codecs.open(filename,'r','utf-8') 
 topline = objFile.readline();
 bdv_ver = topline.replace("\r\n","")
 if(bdv_ver == '#EXTM3U'):
  v3Text = objFile.readline();
  if(v3Text.startswith('#EXT-X-TARGETDURATION') == False):
   ext_type,piece_list,filmFolderEx,filebasenameEx = read_bdv_index_V2(objFile)
  else:
   ext_type,piece_list,filmFolderEx,filebasenameEx = read_bdv_index_V4(objFile)   
 else:
  ext_type,piece_list,filmFolderEx,filebasenameEx = read_bdv_index_V1(objFile)
 objFile.close()  
 return ("mp4" ,piece_list,filmFolderEx,filebasenameEx)    
def read_slicelist_index(filename):
 piece_list= list() 
 objFile = codecs.open(filename,'r','utf-8') 
 topline = objFile.readline();
 bdv_ver = topline.replace("\r\n","")
 if(bdv_ver == '#BD-SECTION'): 
  while(True):
   currentLine = objFile.readline();
   if(currentLine is None or len(currentLine) ==0):
    break
   piece_list.append(currentLine.replace("\r\n",""))
 objFile.close()  
 return ('mp4',piece_list,None,None)
def read_cfg_index(filename):
 piece_list= list() 
 simpleFileName = os.path.basename(filename)
 if(simpleFileName == 'download.cfg'):
  simpleFolderName = os.path.dirname(filename)
  chkLst =glob.glob(os.path.join(simpleFolderName, '*.filelist'));
  if(chkLst is not None and len(chkLst) >0):
   return (None,None,None,None)
  chkLst =glob.glob(os.path.join(simpleFolderName, '*.bdv'));
  piece_list.append(chkLst[0]);
  return ('avi',piece_list)
 if(simpleFileName != 'third_party_download.cfg'):
  raise Exception('unknown format file : %s' %(filename))
 reObj = re.compile('(?P<var_key>\S+):(?P<var_value>\S+)',re.IGNORECASE)
 lineDict = dict()
# [orgLines.append(orgLine.replace("\r\n","") ) for orgLine in codecs.open(filename,'r','utf-8')]
 for orgLine in codecs.open(filename,'r','utf-8'):
  orgLine = orgLine.replace("\r\n","")  
  results = reObj.findall(orgLine)
  if(len(results) > 0):
   lineDict[results[0][0]] =results[0][1]
 resID = lineDict["resource"] 
 vid = lineDict[ '%s_vid'%(resID)]
 targetName = lineDict["video_name"]
 simpleFolderName = os.path.dirname(filename)
 upLevelFolderName = os.path.dirname(simpleFolderName)
 targetFolder = os.path.join(upLevelFolderName,vid)
 targetFolder = os.path.join(targetFolder,vid)
 chkLst =glob.glob(os.path.join(targetFolder, '*.%s*' %(resID)));
 targetFile = chkLst[0] 
  #skip #EXT-X-MEDIA-SEQUENCE 
 for line in codecs.open(targetFile,'r','utf-8'):
  if(line.startswith('#')==True):
   continue;  
  line = os.path.basename(line.replace('\r\n',''))
  line = os.path.basename(line.replace('\r',''))
  line = os.path.basename(line.replace('\n',''))
  piece_list.append(line )
 return ('avi',piece_list,targetFolder,targetName)

以上就是本文的全部内容,希望大家喜欢。

相关文章

pandas DataFrame行或列的删除方法的实现示例

pandas DataFrame行或列的删除方法的实现示例

此文我们继续围绕DataFrame介绍相关操作。 平时在用DataFrame时候,删除操作用的不太多,基本是从源DataFrame中筛选数据,组成一个新的DataFrame再继续操作。...

关于django 数据库迁移(migrate)应该知道的一些事

命令 首先数据库迁移的两大命令: python manage.py makemigrations & python manage.py migrate 前者是将model层转为...

详解python中的文件与目录操作

详解python中的文件与目录操作 一 获得当前路径 1、代码1 >>>import os >>>print('Current directo...

matplotlib 输出保存指定尺寸的图片方法

其实这个问题来源于笔者的横坐标太多了,然后生成的那个figure框框太小,导致坐标重叠,而输出的图片是需要批量保存的,总不能每次都拉长截图吧 所以在plot绘图之前加上了一句 plt...

Windows下安装python2.7及科学计算套装

Windows下安装python2.7及科学计算套装

安装环境及说明 操作系统:64位win7 以下所有安装包已经被我打包至网盘,请移步到 http://www.colafile.com/file/4591550进行下载 因为在64位win...