fi = open("D:\python_learning\data\data\Axew.txt","r",encoding="utf-8")
wflag =False                #寫(xiě)標(biāo)記
newline = []                #創(chuàng)建一個(gè)新的列表


for line in fi :            #按行讀入文件，此時(shí)line的type是str
    if "=" in line:        #重置寫(xiě)標(biāo)記
        wflag =False
    if "原型剖析" in line:     #檢驗(yàn)是否到了要寫(xiě)入的內(nèi)容
        wflag = True
        continue
    if wflag == True:
        K = list(line)
        if len(K)>1:           #去除文本中的空行
            for i in K :       #寫(xiě)入需要內(nèi)容
                newline.append(i)

strlist = "".join(newline)      #合并列表元素
newlines = str(strlist)         #list轉(zhuǎn)化成str
print(newlines)
"""
for D in range(1,100):                       #刪掉句中（）
    newlines = newlines.replace("（{}）".format(D),"")

for P in range(0,9):                               #刪掉前面數(shù)值標(biāo)題
    for O in  range(0,9):
        for U in range(0, 9):
           newlines = newlines.replace("{}.{}{}".format(P,O,U), "")
fo.write(newlines)

fo.close()
fi.close()

"""

path='D:\\python_learning\\data\\data\\'+df.iloc[0,3]+'.txt'
#為循環(huán)做準(zhǔn)備
import re

f1=list(open(path,"r",encoding="utf-8"))#列表格式
f2="".join(f1)#合并列表元素
#print(type(f3))

pattern= re.compile(r'===棲息地===\n(.*?)\n==', flags=re.DOTALL)#在所有行里找以‘===棲息地===\n'開(kāi)頭，‘\n=='結(jié)尾的所有文本

if len(pattern.findall(f2))==0:#有可能找不到，以防報(bào)錯(cuò)
    result='none'
else:
        result=pattern.findall(f2)[0]

print(result)

#數(shù)據(jù)框增加列的參考
import pandas as pd
df = pd.DataFrame(columns = list('abcd'),data = [[6,7,8,9],[10,11,12,13]])
#在b列前面增加一個(gè)m列
col_name = list(df.columns)
col_name.insert(1,'m')
df.reindex(columns = col_name,fill_value = 12)
#在b列前一次性增加三列h,n,g
col_name = col_name[0:2]+list('hng')+col_name[2:]
df.reindex(columns = col_name,fill_value = 10)
import pandas as pd

df = pd.DataFrame(columns =word,data = [['Bulbasaur',7,8,9],[10,11,12,13]])
print(df)
col_name = list(df.columns)#列名
print(col_name )
#在b列前面增加一個(gè)m列

col_name.insert(1,'m')
print(col_name)
df=df.reindex(columns =['name','概述', '外貌', '棲息地', '原型剖析'],fill_value = 12)
print(df)

import pandas as pd
data_name = pd.read_csv(r'D:\python_learning\data\basedata.csv')
#print(data_name)
word=['概述','外貌','棲息地','原型剖析']
col_name = list(data_name.columns)#列名
col_name = col_name +word#添加新的列名
#print(col_name )
df=data_name.reindex(columns = col_name,fill_value =' ')#在數(shù)據(jù)框中增加四列，填充空格
print(df)
#print(df.iloc[2,2])

# #  引入包

# In[ ]:

import re
import pandas as pd

# # 引入基礎(chǔ)數(shù)據(jù)

# In[135]:

data_name = pd.read_csv(r'D:\python_learning\data\basedata.csv')
#print(data_name)
word=['概述','外貌','棲息地','原型剖析']

col_name = list(data_name.columns)#列名
col_name = col_name +word#添加新的列名

#print(col_name )
df=data_name.reindex(columns = col_name,fill_value =' ')#在數(shù)據(jù)框中增加四列，填充空格
#print(df)
#print(df.iloc[2,2])

# # 引入函數(shù)

# In[ ]:

#去除空行函數(shù)
def deletespace(path1,path2):
    with open(path1,'r',encoding = 'utf-8') as fr,open(path2,'w',encoding = 'utf-8') as fd:
            for text in fr.readlines():
                    if text.split():
                            fd.write(text)
            print('輸出成功....')
    fr.close()
    fd.close()

# In[143]:

#正則找文本
def find(path,conversion):
    f1=list(open(path,"r",encoding="utf-8"))#列表格式
    f2="".join(f1)#合并列表元素
    #print(type(f3))

    pattern= re.compile(conversion, flags=re.DOTALL)#在所有行里找以‘===棲息地===\n'開(kāi)頭，‘\n=='結(jié)尾的所有文本

    if len(pattern.findall(f2))==0:#有可能找不到，以防報(bào)錯(cuò)
        result='none'
    else:
            result=pattern.findall(f2)[0]
    return result

# # 起始準(zhǔn)備 把所有空行消除，不需要運(yùn)行第二遍

# In[ ]:

data_name = pd.read_csv(r'D:\python_learning\data\basedata.csv')
for word in df.iloc[:,3]:
    path1='D:\\python_learning\\data\\data\\'+word+'.txt'#爬蟲(chóng)獲取的數(shù)據(jù)
    path2='D:\\python_learning\\data\\description\\'+word+'.txt'
    deletespace(path1,path2)

# # 開(kāi)始循環(huán)

# In[ ]:

word=['概述','外貌','棲息地','原型剖析']#根據(jù)文本中情況進(jìn)行正則
conversion=['==概述==\n(.*?)==','===外貌===\n(.*?)==','===棲息地===\n(.*?)==','==原型剖析==\n(.*?)==']#正則文本

word1=col_name[7]
print(word1)
newlines=seek(path,word1)
print(newlines)

# In[145]:

print(len(df))
print(len(list(df.columns)))

# In[150]:

for i in range(len(df)):
    for j in range(6,len(list(df.columns))):
        path='D:\\python_learning\\data\\description\\'+df.iloc[i,3]+'.txt'
        k=j-6
        cword=conversion[k]
        result=find(path,cword)
        df.iloc[i,j]=result
# In[152]:

df.to_csv('df.csv',encoding ='utf_8_sig')#輸出中文必須用這個(gè)utf_8_sig  編碼才是中文
print("已輸出文檔")
#出現(xiàn)問(wèn)題，很多匹配不到，發(fā)現(xiàn)是原始文本的原因