python 实现添加标签&打标签的操作

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()
#做合并
df_y=pd.merge(cust_df,odue_df,how='left',on='XACCOUNT').groupby('CUSTR_NBR').agg({'label':max}).reset_index().fillna(0)

#标注标签 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)
#打标签，判断天数
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]  选取a标签中带有id属性的标签
# //div/ul/li/a　选取所有a标签
# //div/ul/li[2]/a
"""
/ 从根标签开始  必须具有严格的父子关系
// 从当前标签  后续节点含有即可选出
* 通配符　选择所有
//div/book[1]/title  选择div下第一个book标签的title标签
//div/book[1]/tittle[@lang="zh"] 选择div下第一个book标签的title标签并且内容是zh的title标签
//div/book/title　//book/title //title 具有相同结果　只不过选取路径不一样
//book/title/@* 将title所有的属性值选出来
//book/title/text() 将title的内容选择出来,使用内置函数
//a[@href="link1.html" rel="external nofollow"  rel="external nofollow"  and @id="places_neighbours_row"]
//div/book/[last()]/title/text() 将最后一个book元素选出
//div/book[price > 39]/title/text() 将book子标签price数值大于３９的选择出来
//li[starts-with(@class,'item')] 将class属性前缀是item的选出来
//title[contains(@lang,"eng")]将title属性lang含有eng关键字的标签选出
"""
html = lxml.html.fromstring(test_data)  # 加载任意一个字符串
html_data = html.xpath('//title[contains(@lang,"eng")]')  # xpath 查找路径
# print(dir(html_data[0]))  # 查看html_data有什么功能
print(html_data)
for i in html_data:
 print(i.text)