Python通过DOM和SAX方式解析XML的应用实例分享
XML.DOM
需求
有一个表，里面数据量比较大，每天一更新，其字段可以通过xml配置文件进行配置，即，可能每次建表的字段不一样。
上游跑时会根据配置从源文件中提取，到入库这一步需要根据配置进行建表。
解决
写了一个简单的xml，配置需要字段及类型
上游读取到对应的数据
入库这一步，先把原表删除，根据配置建新表
XML文件
<?xml version="1.0" encoding="UTF-8"?> <!-- 表名 ,数据库名 可灵活配置插入哪个库哪个表 --> <table name="top_query" db_name="evaluting_sys"> <!-- 非业务主键，自增长,可配名，其他 INTEGER UNSIGNED AUTO_INCREMENT --> <primary_key> <name>id</name> </primary_key> <!-- 字段开始 --> <field> <name>query</name> <type>varchar(200)</type> <is_index>false</is_index> <description>query</description> </field> <field> <name>pv</name> <type>integer</type> <is_index>false</is_index> <description>pv</description> </field> <field> <name>avg_money</name> <type>integer</type> <is_index>false</is_index> <description></description> </field> <!-- 字段配置结束 --> </table>
处理脚本
#!/usr/bin/python
# -*- coding:utf-8 -*-
#author: wklken
#desc: use to read db xml config.
#-----------------------
#2012-02-18 created
#----------------------
import sys,os
from xml.dom import minidom, Node
def read_dbconfig_xml(xml_file_path):
content = {}
root = minidom.parse(xml_file_path)
table = root.getElementsByTagName("table")[0]
#read dbname and table name.
table_name = table.getAttribute("name")
db_name = table.getAttribute("db_name")
if len(table_name) > 0 and len(db_name) > 0:
db_sql = "create database if not exists `" + db_name +"`; use " + db_name + ";"
table_drop_sql = "drop " + table_name + " if exists " + table_name + ";"
content.update({"db_sql" : db_sql})
content.update({"table_sql" : table_drop_sql })
else:
print "Error:attribute is not define well! db_name=" + db_name + " ;table_name=" + table_name
sys.exit(1)
#print table_name, db_name
table_create_sql = "create table " + table_name +"("
#read primary cell
primary_key = table.getElementsByTagName("primary_key")[0]
primary_key_name = primary_key.getElementsByTagName("name")[0].childNodes[0].nodeValue
table_create_sql += primary_key_name + " INTEGER NOT NULL AUTO_INCREMENT PRIMARY KEY,"
#print primary_key.toxml()
#read ordernary field
fields = table.getElementsByTagName("field")
f_index = 0
for field in fields:
f_index += 1
name = field.getElementsByTagName("name")[0].childNodes[0].nodeValue
type = field.getElementsByTagName("type")[0].childNodes[0].nodeValue
table_create_sql += name + " " + type
if f_index != len(fields):
table_create_sql += ","
is_index = field.getElementsByTagName("is_index")[0].childNodes[0].nodeValue
table_create_sql += ");"
content.update({"table_create_sql" : table_create_sql})
#character set latin1 collate latin1_danish_ci;
print content
if __name__ == "__main__":
read_dbconfig_xml(sys.argv[1])
涉及方法
root = minidom.parse(xml_file_path) 获取dom对象
root.getElementsByTagName("table") 根据tag获取节点列表
table.getAttribute("name") 获取属性
primary_key.getElementsByTagName("name")[0].childNodes[0].nodeValue 获取子节点的值（id 得到id）
SAX
需求
读取xml数据文件，文件较大，需要实时处理插入到数据库
xml文档
<PERSONS> <person> <id>100000</id> <sex>男</sex> <address>北京，海淀区</address> <fansNum>437</fansNum> <summary>1989</summary> <wbNum>333</wbNum> <gzNum>242</gzNum> <blog>null</blog> <edu>大学</edu> <work></work> <renZh>1</renZh> <brithday>2月14日</brithday> </person> </PERSONS>
处理
sax处理时并不会像dom一样可以以类似节点的维度进行读取,它只有 开始标签 内容 结束标签 之分
处理思想是：通过一个handler，对开始标签，内容，结束标签各有一个处理函数
代码及注解
person 处理类
from xml.sax import handler,parseString
class PersonHandler(handler.ContentHandler):
def __init__(self, db_ops):
#db op obj
self.db_ops = db_ops
#存储一个person的map
self.person = {}
#当前的tag
self.current_tag = ""
#是否是tag之间的内容 ，目的拿到tag间内容，不受空白的干扰
self.in_quote = 0
#开始，清空map
def startElement(self, name, attr):
#以person，清空map
if name == "person":
self.person = {}
#记录 状态
self.current_tag = name
self.in_quote = 1
#结束，插入数据库
def endElement(self, name):
#以person结尾 代表读取一个person的信息结束
if name == "person":
#do something
in_fields = tuple([ ('"' + self.person.get(i,"") + '"') for i in fields ])
print in_sql % in_fields
db_ops.insert( in_sql%(in_fields))
#处理
self.in_quote = 0
def characters(self, content):
#若是在tag之间的内容，更新到map中
if self.in_quote:
self.person.update({self.current_tag: content})
加上入库的完整代码
#!/usr/bin/python
# -*- coding:utf-8 -*-
#parse_person.py
#version : 0.1
#author : wukunliang@163.com
#desc : parse person.xml and out sql
import sys,os
import MySQLdb
reload(sys)
sys.setdefaultencoding('utf-8')
in_sql = "insert into person(id,sex,address,fansNum,summary,wbNum,gzNum,blog,edu,work,renZh,brithday) values(%s, %s, %s, %s, %s, %s,
%s, %s, %s, %s, %s, %s)"
fields = ("id","sex","address","fansNum","summary","wbNum","gzNum","blog","edu","work","renZh","brithday")
#数据库方法
class Db_Connect:
def __init__(self, db_host, user, pwd, db_name, charset="utf8", use_unicode = True):
print "init begin"
print db_host, user, pwd, db_name, charset , use_unicode
self.conn = MySQLdb.Connection(db_host, user, pwd, db_name, charset=charset , use_unicode=use_unicode)
print "init end"
def insert(self, sql):
try:
n = self.conn.cursor().execute(sql)
return n
except MySQLdb.Warning, e:
print "Error: execute sql '",sql,"' failed"
def close(self):
self.conn.close()
#person 处理类
from xml.sax import handler,parseString
class PersonHandler(handler.ContentHandler):
def __init__(self, db_ops):
#db op obj
self.db_ops = db_ops
#存储一个person的map
self.person = {}
#当前的tag
self.current_tag = ""
#是否是tag之间的内容
self.in_quote = 0
#开始，清空map
def startElement(self, name, attr):
#以person，清空map
if name == "person":
self.person = {}
#记录 状态
self.current_tag = name
self.in_quote = 1
#结束，插入数据库
def endElement(self, name):
#以person结尾 代表读取一个person的信息结束
if name == "person":
#do something
in_fields = tuple([ ('"' + self.person.get(i,"") + '"') for i in fields ])
print in_sql % in_fields
db_ops.insert( in_sql%(in_fields))
#处理
self.in_quote = 0
def characters(self, content):
#若是在tag之间的内容，更新到map中
if self.in_quote:
self.person.update({self.current_tag: content})
if __name__ == "__main__":
f = open("./person.xml")
#如果源文件gbk 转码 若是utf-8，去掉decode.encode
db_ops = Db_Connect("127.0.0.1", "root", "root", "test")
parseString(f.read().decode("gbk").encode("utf-8"), PersonHandler(db_ops))
f.close()
db_ops.close()
平时拿python来分析数据，工具脚本还有hadoop streamming，但是用的面和深度实在欠缺 只能说道行还浅，需要多多实践
Hot AI Tools
Undresser.AI Undress
AI-powered app for creating realistic nude photos
AI Clothes Remover
Online AI tool for removing clothes from photos.
Undress AI Tool
Undress images for free
Clothoff.io
AI clothes remover
Video Face Swap
Swap faces in any video effortlessly with our completely free AI face swap tool!
Hot Article
Hot Tools
Notepad++7.3.1
Easy-to-use and free code editor
SublimeText3 Chinese version
Chinese version, very easy to use
Zend Studio 13.0.1
Powerful PHP integrated development environment
Dreamweaver CS6
Visual web development tools
SublimeText3 Mac version
God-level code editing software (SublimeText3)
Hot Topics
1387
52
Is the vscode extension malicious?
Apr 15, 2025 pm 07:57 PM
VS Code extensions pose malicious risks, such as hiding malicious code, exploiting vulnerabilities, and masturbating as legitimate extensions. Methods to identify malicious extensions include: checking publishers, reading comments, checking code, and installing with caution. Security measures also include: security awareness, good habits, regular updates and antivirus software.
Can vs code run in Windows 8
Apr 15, 2025 pm 07:24 PM
VS Code can run on Windows 8, but the experience may not be great. First make sure the system has been updated to the latest patch, then download the VS Code installation package that matches the system architecture and install it as prompted. After installation, be aware that some extensions may be incompatible with Windows 8 and need to look for alternative extensions or use newer Windows systems in a virtual machine. Install the necessary extensions to check whether they work properly. Although VS Code is feasible on Windows 8, it is recommended to upgrade to a newer Windows system for a better development experience and security.
Can visual studio code be used in python
Apr 15, 2025 pm 08:18 PM
VS Code can be used to write Python and provides many features that make it an ideal tool for developing Python applications. It allows users to: install Python extensions to get functions such as code completion, syntax highlighting, and debugging. Use the debugger to track code step by step, find and fix errors. Integrate Git for version control. Use code formatting tools to maintain code consistency. Use the Linting tool to spot potential problems ahead of time.
Choosing Between PHP and Python: A Guide
Apr 18, 2025 am 12:24 AM
PHP is suitable for web development and rapid prototyping, and Python is suitable for data science and machine learning. 1.PHP is used for dynamic web development, with simple syntax and suitable for rapid development. 2. Python has concise syntax, is suitable for multiple fields, and has a strong library ecosystem.
Can vscode be used for mac
Apr 15, 2025 pm 07:36 PM
VS Code is available on Mac. It has powerful extensions, Git integration, terminal and debugger, and also offers a wealth of setup options. However, for particularly large projects or highly professional development, VS Code may have performance or functional limitations.
Can vscode run ipynb
Apr 15, 2025 pm 07:30 PM
The key to running Jupyter Notebook in VS Code is to ensure that the Python environment is properly configured, understand that the code execution order is consistent with the cell order, and be aware of large files or external libraries that may affect performance. The code completion and debugging functions provided by VS Code can greatly improve coding efficiency and reduce errors.
Golang vs. Python: Concurrency and Multithreading
Apr 17, 2025 am 12:20 AM
Golang is more suitable for high concurrency tasks, while Python has more advantages in flexibility. 1.Golang efficiently handles concurrency through goroutine and channel. 2. Python relies on threading and asyncio, which is affected by GIL, but provides multiple concurrency methods. The choice should be based on specific needs.
PHP and Python: Different Paradigms Explained
Apr 18, 2025 am 12:26 AM
PHP is mainly procedural programming, but also supports object-oriented programming (OOP); Python supports a variety of paradigms, including OOP, functional and procedural programming. PHP is suitable for web development, and Python is suitable for a variety of applications such as data analysis and machine learning.
