XML模块
XML
XML:
- 客户端向服务器发送请求,服务器返回的都是字符串。
- 字符串可以是html模式,可以是字典形式(json模式),也可以是xml模式。
- xml模块专门处理xml模式的字符串。
- xml本质是实现不同语言或程序之间进行数据交换的协议。
XML文件格式如下:
![](https://images.cnblogs.com/OutliningIndicators/ContractedBlock.gif)
1 <data> 2 <country name="Liechtenstein"> 3 <rank updated="yes">2</rank> 4 <year>2023</year> 5 <gdppc>141100</gdppc> 6 <neighbor direction="E" name="Austria" /> 7 <neighbor direction="W" name="Switzerland" /> 8 </country> 9 <country name="Singapore"> 10 <rank updated="yes">5</rank> 11 <year>2026</year> 12 <gdppc>59900</gdppc> 13 <neighbor direction="N" name="Malaysia" /> 14 </country> 15 <country name="Panama"> 16 <rank updated="yes">69</rank> 17 <year>2026</year> 18 <gdppc>13600</gdppc> 19 <neighbor direction="W" name="Costa Rica" /> 20 <neighbor direction="E" name="Colombia" /> 21 </country> 22 </data> 23 24 xml格式代码
1、解析XML
![](https://images.cnblogs.com/OutliningIndicators/ContractedBlock.gif)
1 from xml.etree import ElementTree as ET
2
3
4 # 打开文件,读取XML内容
5 str_xml = open('xo.xml', 'r').read()
6
7 # 将字符串解析成xml特殊对象,root代指xml文件的根节点
8 root = ET.XML(str_xml)
![](https://images.cnblogs.com/OutliningIndicators/ContractedBlock.gif)
1 from xml.etree import ElementTree as ET 2 3 # 直接解析xml文件 4 tree = ET.parse("xo.xml") 5 ''' 6 一切对象 7 对象都是由类创建,对象所有的功能都在与其相关的类中 8 1.本质是ElementTree类创建的,等价于 tree = ET.ElementTree() 9 2.getroot() 获取xml根节点 10 3.write() 内存中的xml写进文件 11 ''' 12 13 # 获取xml文件的根节点 14 root = tree.getroot() 15 16 利用ElementTree.parse将文件直接解析成xml对象
![](https://images.cnblogs.com/OutliningIndicators/ContractedBlock.gif)
1 from xml.etree import ElementTree as ET 2 3 #从字符串中解析xml得到一个Element对象 4 str_xml = open('first.xml', 'r').read() 5 root = ET.XML(str_xml) 6 7 #从Element对象转换成ElementTree对象,参数提供root 8 #一个root代表一个树 9 tree = Element(root) 10 11 从第一种解析方式转换到第二种
2、2、操作XML(Element类的功能)
XML格式类型是节点嵌套节点,对于每一个节点均有以下功能,以便对当前节点进行操作:
![](https://images.cnblogs.com/OutliningIndicators/ContractedBlock.gif)
1 class Element: 2 """An XML element. 3 4 This class is the reference implementation of the Element interface. 5 6 An element's length is its number of subelements. That means if you 7 want to check if an element is truly empty, you should check BOTH 8 its length AND its text attribute. 9 10 The element tag, attribute names, and attribute values can be either 11 bytes or strings. 12 13 *tag* is the element name. *attrib* is an optional dictionary containing 14 element attributes. *extra* are additional element attributes given as 15 keyword arguments. 16 17 Example form: 18 <tag attrib>text<child/>...</tag>tail 19 20 """ 21 22 当前节点的标签名 23 tag = None 24 """The element's name.""" 25 26 当前节点的属性 27 28 attrib = None 29 """Dictionary of the element's attributes.""" 30 31 当前节点的内容 32 text = None 33 """ 34 Text before first subelement. This is either a string or the value None. 35 Note that if there is no text, this attribute may be either 36 None or the empty string, depending on the parser. 37 38 """ 39 40 tail = None 41 """ 42 Text after this element's end tag, but before the next sibling element's 43 start tag. This is either a string or the value None. Note that if there 44 was no text, this attribute may be either None or an empty string, 45 depending on the parser. 46 47 """ 48 49 def __init__(self, tag, attrib={}, **extra): 50 if not isinstance(attrib, dict): 51 raise TypeError("attrib must be dict, not %s" % ( 52 attrib.__class__.__name__,)) 53 attrib = attrib.copy() 54 attrib.update(extra) 55 self.tag = tag 56 self.attrib = attrib 57 self._children = [] 58 59 def __repr__(self): 60 return "<%s %r at %#x>" % (self.__class__.__name__, self.tag, id(self)) 61 62 def makeelement(self, tag, attrib): 63 创建一个新节点 64 """Create a new element with the same type. 65 66 *tag* is a string containing the element name. 67 *attrib* is a dictionary containing the element attributes. 68 69 Do not call this method, use the SubElement factory function instead. 70 71 """ 72 return self.__class__(tag, attrib) 73 74 def copy(self): 75 """Return copy of current element. 76 77 This creates a shallow copy. Subelements will be shared with the 78 original tree. 79 80 """ 81 elem = self.makeelement(self.tag, self.attrib) 82 elem.text = self.text 83 elem.tail = self.tail 84 elem[:] = self 85 return elem 86 87 def __len__(self): 88 return len(self._children) 89 90 def __bool__(self): 91 warnings.warn( 92 "The behavior of this method will change in future versions. " 93 "Use specific 'len(elem)' or 'elem is not None' test instead.", 94 FutureWarning, stacklevel=2 95 ) 96 return len(self._children) != 0 # emulate old behaviour, for now 97 98 def __getitem__(self, index): 99 return self._children[index] 100 101 def __setitem__(self, index, element): 102 # if isinstance(index, slice): 103 # for elt in element: 104 # assert iselement(elt) 105 # else: 106 # assert iselement(element) 107 self._children[index] = element 108 109 def __delitem__(self, index): 110 del self._children[index] 111 112 def append(self, subelement): 113 为当前节点追加一个子节点 114 """Add *subelement* to the end of this element. 115 116 The new element will appear in document order after the last existing 117 subelement (or directly after the text, if it's the first subelement), 118 but before the end tag for this element. 119 120 """ 121 self._assert_is_element(subelement) 122 self._children.append(subelement) 123 124 def extend(self, elements): 125 为当前节点扩展 n 个子节点 126 """Append subelements from a sequence. 127 128 *elements* is a sequence with zero or more elements. 129 130 """ 131 for element in elements: 132 self._assert_is_element(element) 133 self._children.extend(elements) 134 135 def insert(self, index, subelement): 136 在当前节点的子节点中插入某个节点,即:为当前节点创建子节点,然后插入指定位置 137 """Insert *subelement* at position *index*.""" 138 self._assert_is_element(subelement) 139 self._children.insert(index, subelement) 140 141 def _assert_is_element(self, e): 142 # Need to refer to the actual Python implementation, not the 143 # shadowing C implementation. 144 if not isinstance(e, _Element_Py): 145 raise TypeError('expected an Element, not %s' % type(e).__name__) 146 147 def remove(self, subelement): 148 在当前节点在子节点中删除某个节点 149 """Remove matching subelement. 150 151 Unlike the find methods, this method compares elements based on 152 identity, NOT ON tag value or contents. To remove subelements by 153 other means, the easiest way is to use a list comprehension to 154 select what elements to keep, and then use slice assignment to update 155 the parent element. 156 157 ValueError is raised if a matching element could not be found. 158 159 """ 160 # assert iselement(element) 161 self._children.remove(subelement) 162 163 def getchildren(self): 164 获取所有的子节点(废弃) 165 """(Deprecated) Return all subelements. 166 167 Elements are returned in document order. 168 169 """ 170 warnings.warn( 171 "This method will be removed in future versions. " 172 "Use 'list(elem)' or iteration over elem instead.", 173 DeprecationWarning, stacklevel=2 174 ) 175 return self._children 176 177 def find(self, path, namespaces=None): 178 获取第一个寻找到的子节点 179 """Find first matching element by tag name or path. 180 181 *path* is a string having either an element tag or an XPath, 182 *namespaces* is an optional mapping from namespace prefix to full name. 183 184 Return the first matching element, or None if no element was found. 185 186 """ 187 return ElementPath.find(self, path, namespaces) 188 189 def findtext(self, path, default=None, namespaces=None): 190 获取第一个寻找到的子节点的内容 191 """Find text for first matching element by tag name or path. 192 193 *path* is a string having either an element tag or an XPath, 194 *default* is the value to return if the element was not found, 195 *namespaces* is an optional mapping from namespace prefix to full name. 196 197 Return text content of first matching element, or default value if 198 none was found. Note that if an element is found having no text 199 content, the empty string is returned. 200 201 """ 202 return ElementPath.findtext(self, path, default, namespaces) 203 204 def findall(self, path, namespaces=None): 205 获取所有的子节点 206 """Find all matching subelements by tag name or path. 207 208 *path* is a string having either an element tag or an XPath, 209 *namespaces* is an optional mapping from namespace prefix to full name. 210 211 Returns list containing all matching elements in document order. 212 213 """ 214 return ElementPath.findall(self, path, namespaces) 215 216 def iterfind(self, path, namespaces=None): 217 获取所有指定的节点,并创建一个迭代器(可以被for循环) 218 """Find all matching subelements by tag name or path. 219 220 *path* is a string having either an element tag or an XPath, 221 *namespaces* is an optional mapping from namespace prefix to full name. 222 223 Return an iterable yielding all matching elements in document order. 224 225 """ 226 return ElementPath.iterfind(self, path, namespaces) 227 228 def clear(self): 229 清空节点 230 """Reset element. 231 232 This function removes all subelements, clears all attributes, and sets 233 the text and tail attributes to None. 234 235 """ 236 self.attrib.clear() 237 self._children = [] 238 self.text = self.tail = None 239 240 def get(self, key, default=None): 241 获取当前节点的属性值 242 """Get element attribute. 243 244 Equivalent to attrib.get, but some implementations may handle this a 245 bit more efficiently. *key* is what attribute to look for, and 246 *default* is what to return if the attribute was not found. 247 248 Returns a string containing the attribute value, or the default if 249 attribute was not found. 250 251 """ 252 return self.attrib.get(key, default) 253 254 def set(self, key, value): 255 为当前节点设置属性值 256 """Set element attribute. 257 258 Equivalent to attrib[key] = value, but some implementations may handle 259 this a bit more efficiently. *key* is what attribute to set, and 260 *value* is the attribute value to set it to. 261 262 """ 263 self.attrib[key] = value 264 265 def keys(self): 266 获取当前节点的所有属性的 key 267 268 """Get list of attribute names. 269 270 Names are returned in an arbitrary order, just like an ordinary 271 Python dict. Equivalent to attrib.keys() 272 273 """ 274 return self.attrib.keys() 275 276 def items(self): 277 获取当前节点的所有属性值,每个属性都是一个键值对 278 """Get element attributes as a sequence. 279 280 The attributes are returned in arbitrary order. Equivalent to 281 attrib.items(). 282 283 Return a list of (name, value) tuples. 284 285 """ 286 return self.attrib.items() 287 288 def iter(self, tag=None): 289 在当前节点的子孙中根据节点名称寻找所有指定的节点,并返回一个迭代器(可以被for循环)。 290 """Create tree iterator. 291 292 The iterator loops over the element and all subelements in document 293 order, returning all elements with a matching tag. 294 295 If the tree structure is modified during iteration, new or removed 296 elements may or may not be included. To get a stable set, use the 297 list() function on the iterator, and loop over the resulting list. 298 299 *tag* is what tags to look for (default is to return all elements) 300 301 Return an iterator containing all the matching elements. 302 303 """ 304 if tag == "*": 305 tag = None 306 if tag is None or self.tag == tag: 307 yield self 308 for e in self._children: 309 yield from e.iter(tag) 310 311 # compatibility 312 def getiterator(self, tag=None): 313 # Change for a DeprecationWarning in 1.4 314 warnings.warn( 315 "This method will be removed in future versions. " 316 "Use 'elem.iter()' or 'list(elem.iter())' instead.", 317 PendingDeprecationWarning, stacklevel=2 318 ) 319 return list(self.iter(tag)) 320 321 def itertext(self): 322 在当前节点的子孙中根据节点名称寻找所有指定的节点的内容,并返回一个迭代器(可以被for循环)。 323 """Create text iterator. 324 325 The iterator loops over the element and all subelements in document 326 order, returning all inner text. 327 328 """ 329 tag = self.tag 330 if not isinstance(tag, str) and tag is not None: 331 return 332 if self.text: 333 yield self.text 334 for e in self: 335 yield from e.itertext() 336 if e.tail: 337 yield e.tail 338 339 Element类
由于 每个节点 都具有以上的方法,并且在上一步骤中解析时均得到了root(xml文件的根节点),可以利用以上方法进行操作xml文件。
a、遍历XML文档的所有内容
![](https://images.cnblogs.com/OutliningIndicators/ContractedBlock.gif)
1 from xml.etree import ElementTree as ET 2 3 ############ 解析方式一 ############ 4 """ 5 # 打开文件,读取XML内容 6 str_xml = open('xo.xml', 'r').read() 7 8 # 将字符串解析成xml特殊对象,root代指xml文件的根节点 9 root = ET.XML(str_xml) 10 """ 11 ############ 解析方式二 ############ 12 13 # 直接解析xml文件 14 tree = ET.parse("xo.xml") 15 16 # 获取xml文件的根节点 17 root = tree.getroot() 18 19 20 ### 操作 21 22 # 顶层标签 23 print(root.tag) 24 25 26 # 遍历XML文档的第二层 27 for child in root: 28 # 第二层节点的标签名称和标签属性 29 print(child.tag, child.attrib) 30 # 遍历XML文档的第三层 31 for i in child: 32 # 第二层节点的标签名称和内容 33 print(i.tag,i.text) 34 35 遍历xml所有内容
b、遍历XML中指定的节点
![](https://images.cnblogs.com/OutliningIndicators/ContractedBlock.gif)
1 from xml.etree import ElementTree as ET 2 3 ############ 解析方式一 ############ 4 """ 5 # 打开文件,读取XML内容 6 str_xml = open('xo.xml', 'r').read() 7 8 # 将字符串解析成xml特殊对象,root代指xml文件的根节点 9 root = ET.XML(str_xml) 10 """ 11 ############ 解析方式二 ############ 12 13 # 直接解析xml文件 14 tree = ET.parse("xo.xml") 15 16 # 获取xml文件的根节点 17 root = tree.getroot() 18 19 20 ### 操作 21 22 # 顶层标签 23 print(root.tag) 24 25 26 # 遍历XML中所有的year节点 27 for node in root.iter('year'): 28 # 节点的标签名称和内容 29 print(node.tag, node.text) 30 31 遍历xml指定节点
c、修改节点内容
由于修改的节点时,均是在内存中进行,其不会影响文件中的内容。所以,如果想要修改,则需要重新将内存中的内容写到文件。
1.解析字符串方式,修改,保存
![](https://images.cnblogs.com/OutliningIndicators/ContractedBlock.gif)
1 from xml.etree import ElementTree as ET 2 3 ############ 解析方式一 ############ 4 5 # 打开文件,读取XML内容 6 str_xml = open('xo.xml', 'r').read() 7 8 # 将字符串解析成xml特殊对象,root代指xml文件的根节点 9 root = ET.XML(str_xml) 10 11 ############ 操作 ############ 12 13 # 顶层标签 14 print(root.tag) 15 16 # 循环所有的year节点 17 for node in root.iter('year'): 18 # 将year节点中的内容自增一 19 new_year = int(node.text) + 1 20 node.text = str(new_year) 21 22 # 设置属性 23 node.set('name', 'alex') 24 node.set('age', '18') 25 # 删除属性 26 del node.attrib['name'] 27 28 29 ############ 保存文件 ############ 30 tree = ET.ElementTree(root) 31 tree.write("newnew.xml", encoding='utf-8') 32 33 法1
2.解析文件方式,修改,保存
![](https://images.cnblogs.com/OutliningIndicators/ContractedBlock.gif)
1 from xml.etree import ElementTree as ET 2 3 ############ 解析方式二 ############ 4 5 # 直接解析xml文件 6 tree = ET.parse("xo.xml") 7 8 # 获取xml文件的根节点 9 root = tree.getroot() 10 11 ############ 操作 ############ 12 13 # 顶层标签 14 print(root.tag) 15 16 # 循环所有的year节点 17 for node in root.iter('year'): 18 # 将year节点中的内容自增一 19 new_year = int(node.text) + 1 20 node.text = str(new_year) 21 22 # 设置属性 23 node.set('name', 'alex') 24 node.set('age', '18') 25 # 删除属性 26 del node.attrib['name'] 27 28 29 ############ 保存文件 ############ 30 tree.write("newnew.xml", encoding='utf-8') 31 32 法2
d、删除节点
1.解析字符串方式打开,删除,保存
![](https://images.cnblogs.com/OutliningIndicators/ContractedBlock.gif)
1 from xml.etree import ElementTree as ET 2 3 ############ 解析字符串方式打开 ############ 4 5 # 打开文件,读取XML内容 6 str_xml = open('xo.xml', 'r').read() 7 8 # 将字符串解析成xml特殊对象,root代指xml文件的根节点 9 root = ET.XML(str_xml) 10 11 ############ 操作 ############ 12 13 # 顶层标签 14 print(root.tag) 15 16 # 遍历data下的所有country节点 17 for country in root.findall('country'): 18 # 获取每一个country节点下rank节点的内容 19 rank = int(country.find('rank').text) 20 21 if rank > 50: 22 # 删除指定country节点 23 root.remove(country) 24 25 ############ 保存文件 ############ 26 tree = ET.ElementTree(root) 27 tree.write("newnew.xml", encoding='utf-8') 28 29 法1
2.解析文件方式打开,删除,保存
![](https://images.cnblogs.com/OutliningIndicators/ContractedBlock.gif)
1 from xml.etree import ElementTree as ET 2 3 ############ 解析文件方式 ############ 4 5 # 直接解析xml文件 6 tree = ET.parse("xo.xml") 7 8 # 获取xml文件的根节点 9 root = tree.getroot() 10 11 ############ 操作 ############ 12 13 # 顶层标签 14 print(root.tag) 15 16 # 遍历data下的所有country节点 17 for country in root.findall('country'): 18 # 获取每一个country节点下rank节点的内容 19 rank = int(country.find('rank').text) 20 21 if rank > 50: 22 # 删除指定country节点 23 root.remove(country) 24 25 ############ 保存文件 ############ 26 tree.write("newnew.xml", encoding='utf-8') 27 28 法2
3、创建XML文档
1.创建方式(一)
![](https://images.cnblogs.com/OutliningIndicators/ContractedBlock.gif)
1 from xml.etree import ElementTree as ET 2 3 4 # 创建根节点 5 root = ET.Element("famliy") 6 7 8 # 创建节点大儿子 9 son1 = ET.Element('son', {'name': '儿1'}) 10 # 创建小儿子 11 son2 = ET.Element('son', {"name": '儿2'}) 12 13 # 在大儿子中创建两个孙子 14 grandson1 = ET.Element('grandson', {'name': '儿11'}) 15 grandson2 = ET.Element('grandson', {'name': '儿12'}) 16 son1.append(grandson1) 17 son1.append(grandson2) 18 19 20 # 把儿子添加到根节点中 21 root.append(son1) 22 root.append(son1) 23 24 tree = ET.ElementTree(root) 25 tree.write('oooo.xml',encoding='utf-8', short_empty_elements=False) 26 27 手动创建:ET.Element
2.创建方式(二)
![](https://images.cnblogs.com/OutliningIndicators/ContractedBlock.gif)
1 from xml.etree import ElementTree as ET 2 3 # 创建根节点 4 root = ET.Element("famliy") 5 6 7 # 创建大儿子 8 # son1 = ET.Element('son', {'name': '儿1'}) 9 son1 = root.makeelement('son', {'name': '儿1'}) 10 # 创建小儿子 11 # son2 = ET.Element('son', {"name": '儿2'}) 12 son2 = root.makeelement('son', {"name": '儿2'}) 13 14 # 在大儿子中创建两个孙子 15 # grandson1 = ET.Element('grandson', {'name': '儿11'}) 16 grandson1 = son1.makeelement('grandson', {'name': '儿11'}) 17 # grandson2 = ET.Element('grandson', {'name': '儿12'}) 18 grandson2 = son1.makeelement('grandson', {'name': '儿12'}) 19 20 son1.append(grandson1) 21 son1.append(grandson2) 22 23 24 # 把儿子添加到根节点中 25 root.append(son1) 26 root.append(son1) 27 28 tree = ET.ElementTree(root) 29 tree.write('oooo.xml',encoding='utf-8', short_empty_elements=False) 30 31 用someNode.makeelement创建
3.创建方式(三)
![](https://images.cnblogs.com/OutliningIndicators/ContractedBlock.gif)
1 from xml.etree import ElementTree as ET 2 3 4 # 创建根节点 5 root = ET.Element("famliy") 6 7 8 # 创建节点大儿子 9 son1 = ET.SubElement(root, "son", attrib={'name': '儿1'}) 10 # 创建小儿子 11 son2 = ET.SubElement(root, "son", attrib={"name": "儿2"}) 12 13 # 在大儿子中创建一个孙子 14 grandson1 = ET.SubElement(son1, "age", attrib={'name': '儿11'}) 15 grandson1.text = '孙子' 16 17 18 et = ET.ElementTree(root) #生成文档对象 19 et.write("test.xml", encoding="utf-8", xml_declaration=True, short_empty_elements=False) 20 21 ET.subElement创建并append
4.由于原生保存的XML时默认无缩进,如果想要设置缩进的话, 需要修改保存方式:
![](https://images.cnblogs.com/OutliningIndicators/ContractedBlock.gif)
1 from xml.etree import ElementTree as ET 2 from xml.dom import minidom 3 4 5 def prettify(elem): 6 """将节点转换成字符串,并添加缩进。 7 """ 8 rough_string = ET.tostring(elem, 'utf-8') 9 reparsed = minidom.parseString(rough_string) 10 return reparsed.toprettyxml(indent="\t") 11 12 # 创建根节点 13 root = ET.Element("famliy") 14 15 16 # 创建大儿子 17 # son1 = ET.Element('son', {'name': '儿1'}) 18 son1 = root.makeelement('son', {'name': '儿1'}) 19 # 创建小儿子 20 # son2 = ET.Element('son', {"name": '儿2'}) 21 son2 = root.makeelement('son', {"name": '儿2'}) 22 23 # 在大儿子中创建两个孙子 24 # grandson1 = ET.Element('grandson', {'name': '儿11'}) 25 grandson1 = son1.makeelement('grandson', {'name': '儿11'}) 26 # grandson2 = ET.Element('grandson', {'name': '儿12'}) 27 grandson2 = son1.makeelement('grandson', {'name': '儿12'}) 28 29 son1.append(grandson1) 30 son1.append(grandson2) 31 32 33 # 把儿子添加到根节点中 34 root.append(son1) 35 root.append(son1) 36 37 38 raw_str = prettify(root) 39 40 f = open("xxxoo.xml",'w',encoding='utf-8') 41 f.write(raw_str) 42 f.close() 43 44 法4