Python 3.2 数据处理实战：文件读写与规则过滤详解

def showtxt(path,outpathname,detailpath): 
 
  greenpath=r"C:\\Users\\qindongliang\\Desktop\\tnstxt\\green.txt"; 
  redpath=r"C:\\Users\\qindongliang\\Desktop\\tnstxt\\red.txt"; 
  redset=listtxt(redpath) 
  greenset=listtxt(greenpath) 
  print("红色词数量: ",len(redset)) 
  print("绿色词数量: ",len(greenset)) 
  #符合1条件的内容写入 
  f1=open(r"C:\Users\qindongliang\Desktop\tnstxt\result\\"+detailpath+"\\1.txt",encoding="UTF-8",mode="a+") 
  #符合2条件的内容写入 
  f2=open(r"C:\Users\qindongliang\Desktop\tnstxt\result\\"+detailpath+"\\2.txt",encoding="UTF-8",mode="a+") 
  #符合3条件的内容写入 
  f3=open(r"C:\Users\qindongliang\Desktop\tnstxt\result\\"+detailpath+"\\3.txt",encoding="UTF-8",mode="a+") 
  #符合4条件的内容写入 
  f4=open(r"C:\Users\qindongliang\Desktop\tnstxt\result\\"+detailpath+"\\4.txt",encoding="UTF-8",mode="a+") 
 
 
 
  delcount=1; 
  f=open(path,encoding="UTF-8",mode="r+") 
  fnew=open(outpathname,encoding="UTF-8",mode="a+") 
  flog=open(outpathname+".log",encoding="UTF-8",mode="a+") 
  #count=1; 
  for line in f: 
    list=line.strip().split("\t") 
    line=line.strip() 
    catalogid=list[0] 
    score=list[1] 
    keyword=clear(list[4].strip()) 
    if keyword in redset: 
      if catalogid.startswith("018022") or catalogid.startswith("018035") or catalogid.startswith("014023003") : 
        f1.write(line+"\n")#符合1条件写入 
        fnew.write(line+"\n")#符合1条件写入 
      else: 
        flog.write(line+"  不符合条件1 "+"\n") 
        delcount=delcount+1 
 
    if keyword in greenset: 
      if not (catalogid.startswith("018022") or catalogid.startswith("018035") or catalogid.startswith("014023003")) : 
        fnew.write(line+"\n") 
      else: 
        f2.write(line+"\n") 
        flog.write(line+"  不符合条件2"+"\n") 
        delcount=delcount+1 
 
 
    flist=formatStrList(keyword) 
    if "sexy" in flist or "sex" in flist: 
      if catalogid.startswith("018022") or catalogid.startswith("018035") or catalogid.startswith("014023003") : 
        f3.write(line+"\n") 
        fnew.write(line+"\n") 
      else: 
        flog.write(line+" 不符合条件3"+"\n") 
        delcount=delcount+1 
 
    #if (keyword.find("underwear")!=-1) & keyword.find("sexy")==-1 & keyword.find("sex")==-1: 
    if "underwear" in flist and "sexy" not in flist and "sex" not in flist: 
      if catalogid.startswith("014032") : 
        f4.write(line+"\n") 
        fnew.write(line+"\n") 
      else: 
        flog.write(line+" 不符合条件4"+"\n") 
        delcount=delcount+1 
 
    #print(list[0]," ",list[1]," ",list[4]) 
    #print() 
 
 
 
  flog.write("删除总数目： "+str(delcount)) 
  f.close() 
  f1.close() 
  f2.close() 
  f3.close() 
  f4.close() 
  fnew.close() 
  flog.close() 
 
import re 
def clear(str): 
  str=re.sub("[\"\"\'\'+]","",str) 
  return str 
 
 
def formatStrList(keyword): 
  list=keyword.split(" ") 
  for item in list: 
    item.strip(); 
  return list 
 
 
 
 
def listtxt(path): 
   f=open(path,encoding="UTF-8") 
   s=set() 
   for line in f: 
     s.add(line.strip()) 
   f.close() 
   return s 
 
path1=r"C:\\Users\\qindongliang\\Desktop\\tnstxt\\highfrequency.txt" 
pathout1=r"C:\\Users\\qindongliang\\Desktop\\tnstxt\\detail\\a_highfrequency.txt" 
detail1path="highfrequency" 
path2=r"C:\\Users\\qindongliang\\Desktop\\tnstxt\\highfrequency_d1.txt" 
pathout2=r"C:\\Users\\qindongliang\\Desktop\\tnstxt\\detail\\b_highfrequency_d1.txt" 
detail2path="highfrequency_d1" 
 
#showtxt(path1,pathout1,detail1path) 
 
showtxt(path2,pathout2,detail2path)