筛dateType为特定值，并进行roomLiveTitle去重
作者：互联网
#筛选类型数据和标题并进行标题去重
class ShaiXuanLeiXingAndBiaoTi:
def __init__(self,file_name):
self.file_name = file_name
self.mubiao_list = []
self.sheqi_list=[]
self.read_list=self.readText(self.file_name)
self.end_num = 0
# 读取文件，以列表形式获取所有内容
def readText(self,file_name):
with open(file=file_name, mode='r',encoding="utf-8") as f:
read_list = f.readlines()
return read_list
#处理DataType所在行的数据,获取dataType的值
def getDataType(self,datatype_hang):
datatype_list = datatype_hang.split(":")
print("datatype_list:")
print(datatype_list)
ziduan_zhi_list = datatype_list[1].split(",")
print("ziduan_zhi_list:")
print(ziduan_zhi_list)
ziduan_zhi = ziduan_zhi_list[0].strip()
print("ziduan_zhi:")
print(ziduan_zhi)
print(type(ziduan_zhi))
return ziduan_zhi
#获取要从保留的内容中删除，添加到删除列表中数据
def getDeleteDataList(self):
print("处理前self.mubiao_list个数")
print(len(self.mubiao_list))
print(self.mubiao_list)
zhongjian_list = []
num = 0
while True:
num = num + 1
print("删除目标,保存数据到中间列表中，循环处理第%s次" % str(num))
#获取 self.mubiao_list 中最后一项的内容
zuihouyixiang = self.mubiao_list[-1]
zuihouyixiang_pan= zuihouyixiang.strip() #去掉前后空格
print("zuihouyixiang:")
print(zuihouyixiang)
self.mubiao_list.pop() # self.mubiao_list删除最后一项
zhongjian_list.append(zuihouyixiang)
# 判断该行内容是否是""data": {"，如果是则终止循环
if zuihouyixiang_pan == '"data": {':
print("zuihouyixiangdai{")
print(zuihouyixiang)
break
# 获取 self.mubiao_list 中最后一项的内容
zuihouyixiang = self.mubiao_list[-1]
self.mubiao_list.pop() # self.mubiao_list删除最后一项
zhongjian_list.append(zuihouyixiang)
print("处理后self.mubiao_list个数")
print(len(self.mubiao_list))
print("zhongjian_list个数")
print(len(zhongjian_list))
return zhongjian_list
#将zhongjian_list中的内容导向存储到self.sheqi_list中
def getSheQiList(self,zhongjian_list):
print("zhongjian_list:")
print(zhongjian_list)
zhongjian_list_len = len(zhongjian_list)
for i in range(0,zhongjian_list_len):
self.sheqi_list.append(zhongjian_list[-1]) #将zhongjian_list的最后一项加入到self.sheqi_list
zhongjian_list.pop() #删除zhongjian_list的最后一项
print("self.sheqi_list:")
print(self.sheqi_list)
# 向下继续查找，找到第一个”},“，则停止
def xiangxia(self):
k=0
for j in range(0,10):
k=k+1
if (self.end_num+j < self.read_list_len):
print("处理到self.read_list中第%s下表的的内容" % str(self.end_num+j))
one_hang = self.read_list[self.end_num+j]
self.sheqi_list.append(one_hang)
if "}" in one_hang.strip():
print("one_hang},")
print(one_hang)
break
print("k:")
print(k)
return k
#写入列表数据到文件中
def writeListToTxt(self,file_name,list_data):
with open(file_name,"w",encoding="utf-8") as f:
for one in list_data:
f.write(one)
#写入字符串内容到文件中
def writeStrToTxt(self,file_name,str):
with open(file_name,"w",encoding="utf-8") as f:
f.write(str)
#处理一个实体对象，即一个中括号对象
# {
# "data": {
# "tagList": [
# "测试"
# ],
# "roomLiveTitle": "直播间标题-大会直播",
# "coverOne": "\/tojoy\/tojoyClould\/backstageSystem\/image\/1633680869417.jpg",
# "screenShot": "\/tojoy\/tojoyClould\/serverUpload\/202207\/14\/image\/1657783758511.jpg",
# "roomLiveId": 4003879,
# "coverTwo": "\/tojoy\/tojoyClould\/backstageSystem\/image\/1633680876038.jpg",
# "status": 4,
# "videoPlayUrl": "http:\/\/1259323955.vod2.myqcloud.com\/685cdfeevodcq1259323955\/b520d1e2387702293080090030\/f0.mp4?oss-cn-beijing.aliyuncs.com"
# },
# "dataIndex": 1,
# "dataType": 4,
# "dataSource": 3
# },
def handleOneShiTi(self):
# 遍历每一行
#第一次开始处理
for i in range(0,self.read_list_len):
print("处理到第%s行的内容" % str(i))
#读取一行内容
one_hang = self.read_list[i]
#如果 dataType 不在该行中
if ziduan.lower() not in one_hang.lower():
# 将一行内容添加到self.mubiao_list，即要保留的内容
self.mubiao_list.append(one_hang)
self.end_num = self.end_num + 1
else: # 如果判断 dataType 在该行中，则判断dataType的值
print("遇到第一个%s值不是%s的%s行的内容" % (ziduan, ziduanzhi,i))
print(one_hang)
data_type_zhi = self.getDataType(datatype_hang=one_hang)
print(data_type_zhi)
#如果字段值不是4
if data_type_zhi != ziduanzhi:
break # 终止循环
else:
# 将一行内容添加到self.mubiao_list，即要保留的内容
self.mubiao_list.append(one_hang)
self.end_num = self.end_num + 1
print("处理到self.mubiao_list第%s个下标" % str(self.end_num))
print("从断点下标%s开始处理" % str(self.end_num))
zhongjian_list = self.getDeleteDataList()
print("self.mubiao_list_hou:")
print(self.mubiao_list)
print(len(self.mubiao_list))
# 将zhongjian_list的内容倒向保存到self.sheqi_list中
self.getSheQiList(zhongjian_list)
#向下继续查找，找到第一个”}“，则停止
k = self.xiangxia()
self.end_num = self.end_num+k
print("接着从断点 %s行开始处理" % str(self.end_num))
#循环处理后续内容
while self.end_num <self.read_list_len:
# 第二次开始处理
# 接着从self.end_num开始读取，此时需要再进行判断
for i in range(self.end_num, self.read_list_len):
print("处理到第%s行的内容" % str(i))
# 读取一行内容
one_hang = self.read_list[i]
# 如果 dataType 不在该行中
if ziduan.lower() not in one_hang.lower():
# 将一行内容添加到self.mubiao_list，即要保留的内容
self.mubiao_list.append(one_hang)
self.end_num = self.end_num + 1
else: # 如果判断 dataType 在该行中，则判断dataType的值
print("遇到一个%s值不是%s的%s行的内容" % (ziduan, ziduanzhi, i))
print(one_hang)
data_type_zhi = self.getDataType(datatype_hang=one_hang)
print(data_type_zhi)
# 如果字段值不是4（预期值）
if data_type_zhi != ziduanzhi:
break # 终止循环
else:
# 将一行内容添加到self.mubiao_list，即要保留的内容
self.mubiao_list.append(one_hang)
self.end_num = self.end_num + 1
print("处理到self.mubiao_list第%s个下标" % str(self.end_num))
print("从断点下标%s开始处理" % str(self.end_num))
#如果起始值大于等于数列长度
if self.end_num>=self.read_list_len:
print("从断点下标%s超过超过数列%s长度，终止循环" % (str(self.end_num),str(self.read_list_len)))
break #就终止while循环
zhongjian_list = self.getDeleteDataList()
print("self.mubiao_list_hou:")
print(self.mubiao_list)
print(len(self.mubiao_list))
# 将zhongjian_list的内容倒向保存到self.sheqi_list中
self.getSheQiList(zhongjian_list)
# 向下继续查找，找到第一个”},“，则停止
k = self.xiangxia()
self.end_num = self.end_num + k
print("接着从断点 %s行开始处理" % str(self.end_num))
def handleFile(self,ziduan="dataType",ziduanzhi="4"):
print("self.read_list:")
print(self.read_list)
#获取数列的长度
self.read_list_len = len(self.read_list)
print("self.read_list_len:")
print(self.read_list_len)
self.handleOneShiTi()
# #将最后一行的内容写入到mubiao_list中
# self.mubiao_list.append(self.read_list[-1])
print(self.read_list_len)
print(len(self.mubiao_list))
print(len(self.sheqi_list))
self.writeListToTxt(file_name="mubiao_%s_%s.txt"%(ziduan,ziduanzhi), list_data=self.mubiao_list)
self.writeListToTxt(file_name="sheqi_not_%s_%s.txt"%(ziduan,ziduanzhi), list_data=self.sheqi_list)
return "mubiao_%s_%s.txt"%(ziduan,ziduanzhi)
#统计某个字段在列表中出现的次数
#将一个列表倒序写入另一个列表
def firstListDaoXuTOSecondList(self,first_list,second_list):
first_list_len = len(first_list)
#循环写入
for i in range(0,first_list_len):
zuihouyixiang = first_list[-1]
second_list.append(zuihouyixiang)
first_list.pop() #删除最后一项
return second_list
#将一个列表正序写入另一个列表
def firstListZhengXuTOSecondList(self,first_list,second_list):
first_list_len = len(first_list)
#循环写入
for i in range(0,first_list_len):
second_list.append(first_list[i])
return second_list
#根据一条重复的内容筛选出对应的整个对象
def getOneShiTiByOneZiduan(self,one_list,quanji_list):
#获取一个对象的内容
one_duixiang_list= []
quanji_list_len = len(quanji_list) #获取总长度
xiabiao = int(one_list[0])
#存储一个实体对象的前半部分
one_duixiang_qian_list = []
#从下标开始，往上读取，读到第一个 ""data": {"，如果是则终止循环
while True:
one_duixiang_qian_list.append(quanji_list[xiabiao])
if '"data": {'.lower() in str(quanji_list[xiabiao]).lower():
break
else:
xiabiao = xiabiao-1
one_duixiang_qian_list.append(quanji_list[xiabiao-1])
#打印实体前半部分
print(one_duixiang_qian_list)
xiabiao = int(one_list[0]) #重新获取下标
#存储一个实体对象的后半部分
one_duixiang_hou_list = []
#从下标开始，往下读取，读到第一个 “dataType”，然后dataType下第一个“}”终止
biaozhi = False #是否找到“dataType”的标识，默认为False,找到后置为True
while True:
xiabiao = xiabiao + 1
one_duixiang_hou_list.append(quanji_list[xiabiao]) #保存内容
if "dataType".lower() in str(quanji_list[xiabiao]).lower():
print("已经找到第一个节点dataType,再往下找到}就终止")
biaozhi = True
if biaozhi:
if "}".lower() in str(quanji_list[xiabiao]).lower():
break #终止循环
# 打印实体后半部分
print(one_duixiang_hou_list)
one_duixiang_list = self.firstListDaoXuTOSecondList(first_list=one_duixiang_qian_list,
second_list=one_duixiang_list)
one_duixiang_list = self.firstListZhengXuTOSecondList(first_list=one_duixiang_hou_list,
second_list=one_duixiang_list)
print("one_duixiang_list:")
print(one_duixiang_list)
return one_duixiang_list
#获取文件的名字
#获取文件的后缀
#根据筛选类型后输出的文件,从中再次筛选标题内容
def getRoomLiveTitle(self,ziduan="dataType",ziduanzhi="4",quchongziduan="roomLiveTitle"):
mubiao_file = self.handleFile(ziduan=ziduan,ziduanzhi=ziduanzhi)
#读取目标文件中的所有roomLiveTitle的值
with open(file=mubiao_file, mode='r',encoding="utf-8") as f:
mubiaofile_list = f.readlines()
#存储所有带有"roomLiveTitle"的行
all_roomLiveTitle_list = []
#存储没有重复的RoomLiveTitle的值
roomLiveTitle_wuchongfu_list = []
#存储没有重复的RoomLiveTitle的值带下标
roomLiveTitle_wuchongfu_with_xiaobiao_list = []
#存储重复的RoomLiveTitle的值
roomLiveTitle_chongfu_list = []
#存储重复的RoomLiveTitle的值
roomLiveTitle_chongfu_with_xiaobiao_list = []
for i in range(0,len(mubiaofile_list)):
if quchongziduan.lower() in str(mubiaofile_list[i]).lower():
#存储mubiaofile_list到
all_roomLiveTitle_list.append([i,mubiaofile_list[i]])
#获取all_roomLiveTitle_list的长度
all_roomLiveTitle_list_len = len(all_roomLiveTitle_list)
#遍历all_roomLiveTitle_list
for i in range(0,all_roomLiveTitle_list_len):
one_list = all_roomLiveTitle_list[i]
if one_list[1] not in roomLiveTitle_wuchongfu_list:
roomLiveTitle_wuchongfu_list.append(one_list[1])
else:
roomLiveTitle_chongfu_with_xiaobiao_list.append(one_list)
#打印重复的标题数列
print("roomLiveTitle_chongfu_with_xiaobiao_list:")
print(roomLiveTitle_chongfu_with_xiaobiao_list)
if len(roomLiveTitle_chongfu_with_xiaobiao_list)<1:
print("无重复【%s】"%quchongziduan)
else:
print("获取重复的内容：")
#存储所有重复的内容
all_chongfu_shiti_list = []
#存储所有重复的实体({})内容的字符串
all_one_shiti_list_str_list = []
for i in range(0,len(roomLiveTitle_chongfu_with_xiaobiao_list)):
print("循环获取内容")
one_shiti_list = self.getOneShiTiByOneZiduan(one_list=roomLiveTitle_chongfu_with_xiaobiao_list[i],
quanji_list=mubiaofile_list)
# 获取去重后的内容中一个实体内容的字符串
one_chongfu_shiti_list_str = "".join(one_shiti_list)
#添加one_chongfu_shiti_list_str到all_one_shiti_list_str_list中
all_one_shiti_list_str_list.append(one_chongfu_shiti_list_str)
all_chongfu_shiti_list = self.firstListZhengXuTOSecondList(first_list=one_shiti_list,
second_list=all_chongfu_shiti_list)
print("all_chongfu_shiti_list:")
print(all_chongfu_shiti_list)
chongfu_file_name = str(mubiao_file).strip(".txt")+"_chongfu"+".txt"
self.writeListToTxt(file_name=chongfu_file_name,
list_data=all_chongfu_shiti_list)
#获取所有内容组成一个字符串
mubiaofile_list_str = "".join(mubiaofile_list)
#遍历替换重复的内容为空
for one in all_one_shiti_list_str_list:
mubiaofile_list_str = mubiaofile_list_str.replace(one,"") #替换重复的内容为空
#将替换后的内容赋值给quchonghou
quchonghou = mubiaofile_list_str
#将去重后的内容保存到文件中
quchong_file_name = str(mubiao_file).strip(".txt") + "_quchong" + ".txt"
self.writeStrToTxt(file_name=quchong_file_name,
str=quchonghou)
if __name__ == '__main__':
#获取某个dataType的数据
file_name = "new 2.txt"
ziduan = "dataType"
ziduanzhi = "4"
quchongziduan = "roomLiveTitle"
sx = ShaiXuanLeiXingAndBiaoTi(file_name)
sx.getRoomLiveTitle(ziduan=ziduan,ziduanzhi=ziduanzhi,quchongziduan=quchongziduan)
标签：roomLiveTitle,mubiao,self,list,len,特定,print,dateType 来源： https://www.cnblogs.com/jingzaixin/p/16584750.html