python 實現添加標簽&打標簽的操作

odue_df=df_train_stmt.loc[(df_train_stmt.AGE3>0)|(df_train_stmt.AGE4>0)|(df_train_stmt.AGE5>0)|(df_train_stmt.AGE6>0),['XACCOUNT']].drop_duplicates()
odue_df['label']=1
cust_df=df_acct[['CUSTR_NBR','XACCOUNT']].drop_duplicates()
#做合並
df_y=pd.merge(cust_df,odue_df,how='left',on='XACCOUNT').groupby('CUSTR_NBR').agg({'label':max}).reset_index().fillna(0)

#標註標簽 Label
def label(row):
   if row['Date_received'] == 'null':
       return -1
   if row['Date'] != 'null':
       td = pd.to_datetime(row['Date'], format='%Y%m%d') - pd.to_datetime(row['Date_received'], format='%Y%m%d')
       if td <= pd.Timedelta(15, 'D'):
           return 1
   return 0
dfoff['label'] = dfoff.apply(label, axis=1)
#打標簽，判斷天數
def get_label(s):
    s = s.split(':')
    if s[0]=='null':
        return 0
    elif (date(int(s[0][0:4]),int(s[0][4:6]),int(s[0][6:8]))-date(int(s[1][0:4]),int(s[1][4:6]),int(s[1][6:8]))).days<=15:
        return 1
    else:
        return -1
dataset2.label = dataset2.label.apply(get_label)

 
import re
import json 
import requests
from bs4 import BeautifulSoup
import lxml.html
from lxml import etree
 
result = requests.get('http://example.webscraping.com/places/default/view/Algeria-4')
with open('123.html', 'wb') as f:
    f.write(result.content)
# print(parse_regex(result.text))
test_data = """
        <div>
            <ul>
                 <li class="item-0"><a href="link1.html" rel="external nofollow"  rel="external nofollow"  id="places_neighbours__row">9,596,960first item</a></li>
                 <li class="item-1"><a href="link2.html" rel="external nofollow" >second item</a></li>
                 <li class="item-inactive"><a href="link3.html" rel="external nofollow" >third item</a></li>
                 <li class="item-1"><a href="link4.html" rel="external nofollow"  id="places_neighbours__row">fourth item</a></li>
                 <li class="item-0"><a href="link5.html" rel="external nofollow"  rel="external nofollow" >fifth item</a></li>
                 <li class="good-0"><a href="link5.html" rel="external nofollow"  rel="external nofollow" >fifth item</a></li>
             </ul>
             <book>
                    <title lang="aaengbb">Harry Potter</title>
                    <price id="places_neighbours__row">29.99</price>
            </book>
            <book>
                <title lang="zh">Learning XML</title>
                <price>39.95</price>
            </book>
            <book>
                <title>Python</title>
                <price>40</price>
            </book>
         </div>
        """
# //div/ul/li/a[@id]  選取a標簽中帶有id屬性的標簽
# //div/ul/li/a　選取所有a標簽
# //div/ul/li[2]/a
"""
/ 從根標簽開始  必須具有嚴格的父子關系
// 從當前標簽  後續節點含有即可選出
* 通配符　選擇所有
//div/book[1]/title  選擇div下第一個book標簽的title標簽
//div/book[1]/tittle[@lang="zh"] 選擇div下第一個book標簽的title標簽並且內容是zh的title標簽
//div/book/title　//book/title //title 具有相同結果　隻不過選取路徑不一樣
//book/title/@* 將title所有的屬性值選出來
//book/title/text() 將title的內容選擇出來,使用內置函數
//a[@href="link1.html" rel="external nofollow"  rel="external nofollow"  and @id="places_neighbours_row"]
//div/book/[last()]/title/text() 將最後一個book元素選出
//div/book[price > 39]/title/text() 將book子標簽price數值大於３９的選擇出來
//li[starts-with(@class,'item')] 將class屬性前綴是item的選出來
//title[contains(@lang,"eng")]將title屬性lang含有eng關鍵字的標簽選出
"""
html = lxml.html.fromstring(test_data)  # 加載任意一個字符串
html_data = html.xpath('//title[contains(@lang,"eng")]')  # xpath 查找路徑
# print(dir(html_data[0]))  # 查看html_data有什麼功能
print(html_data)
for i in html_data:
    print(i.text)