python 使用ElementTree解析xml檔案
阿新 • • 發佈:2018-11-21
以country.xml為例,內容如下:
<?xml version="1.0"?> <data> <country name="Liechtenstein"> <rank updated="yes">2</rank> <year>2008</year> <gdppc>141100</gdppc> <neighbor name="Austria" direction="E"/> <neighbor name="Switzerland" direction="W"/> </country> <country name="Singapore"> <rank updated="yes">5</rank> <year>2011</year> <gdppc>59900</gdppc> <neighbor name="Malaysia" direction="N"/> </country> <country name="Panama"> <rank updated="yes">69</rank> <year>2011</year> <gdppc>13600</gdppc> <neighbor name="Costa Rica" direction="W"/> <neighbor name="Colombia" direction="E"/> </country> </data>
1.解析
1)呼叫parse()方法,返回解析樹
python3.3之後ElementTree模組會自動尋找可用的C庫來加快速度
try: import xml.etree.cElementTree as ET except ImportError: import xml.etree.ElementTree as ET tree = ET.parse("country.xml") # <class 'xml.etree.ElementTree.ElementTree'> root = tree.getroot() # 獲取根節點 <Element 'data' at 0x02BF6A80>
2)呼叫from_string(),返回解析樹的根元素
import xml.etree.ElementTree as ET
data = open("country.xml").read()
root = ET.fromstring(data) # <Element 'data' at 0x036168A0>
3)呼叫ElementTree類ElementTree(self, element=None, file=None) # 這裡的element作為根節點
import xml.etree.ElementTree as ET tree = ET.ElementTree(file="country.xml") # <xml.etree.ElementTree.ElementTree object at 0x03031390> root = tree.getroot() # <Element 'data' at 0x030EA600>
2.遍歷
1)簡單遍歷
import xml.etree.ElementTree as ET
tree = ET.parse("country.xml")
root = tree.getroot()
print(root.tag, ":", root.attrib) # 列印根元素的tag和屬性
# 遍歷xml文件的第二層
for child in root:
# 第二層節點的標籤名稱和屬性
print(child.tag,":", child.attrib)
# 遍歷xml文件的第三層
for children in child:
# 第三層節點的標籤名稱和屬性
print(children.tag, ":", children.attrib)
可以通過下標的方式直接訪問節點
# 訪問根節點下第一個country的第二個節點year,獲取對應的文字
year = root[0][1].text # 2008
2)ElementTree提供的方法
find
(match) # 查詢第一個匹配的子元素, match可以時tag或是xpaht路徑findall
(match) # 返回所有匹配的子元素列表findtext
(match, default=None) #iter
(tag=None) # 以當前元素為根節點 建立樹迭代器,如果tag不為None,則以tag進行過濾iterfind
(match) #
例子:
# 過濾出所有neighbor標籤
for neighbor in root.iter("neighbor"):
print(neighbor.tag, ":", neighbor.attrib)
# 遍歷所有的counry標籤
for country in root.findall("country"):
# 查詢country標籤下的第一個rank標籤
rank = country.find("rank").text
# 獲取country標籤的name屬性
name = country.get("name")
print(name, rank)
3.修改xml結構
1) 屬性相關
# 將所有的rank值加1,並新增屬性updated為yes
for rank in root.iter("rank"):
new_rank = int(rank.text) + 1
rank.text = str(new_rank) # 必須將int轉為str
rank.set("updated", "yes") # 新增屬性
# 再終端顯示整個xml
ET.dump(root)
# 注意 修改的內容存在記憶體中 尚未儲存到檔案中
# 儲存修改後的內容
tree.write("output.xml")
import xml.etree.ElementTree as ET
tree = ET.parse("output.xml")
root = tree.getroot()
for rank in root.iter("rank"):
# attrib為屬性字典
# 刪除對應的屬性updated
del rank.attrib['updated']
ET.dump(root)
小結: 關於class xml.etree.ElementTree.
Element 屬性相關
- attrib 為包含元素屬性的字典
keys() 返回元素屬性名稱列表
- items() 返回(name,value)列表
get
(key, default=None) 獲取屬性set
(key, value) # 跟新/新增 屬性- del xxx.attrib[key] # 刪除對應的屬性
2) 節點/元素 相關
刪除子元素remove()
import xml.etree.ElementTree as ET
tree = ET.parse("country.xml")
root = tree.getroot()
# 刪除rank大於50的國家
for country in root.iter("country"):
rank = int(country.find("rank").text)
if rank > 50:
# remove()方法 刪除子元素
root.remove(country)
ET.dump(root)
新增子元素
程式碼:
import xml.etree.ElementTree as ET
tree = ET.parse("country.xml")
root = tree.getroot()
country = root[0]
last_ele = country[len(list(country))-1]
last_ele.tail = '\n\t\t'
# 建立新的元素, tag為test_append
elem1 = ET.Element("test_append")
elem1.text = "elem 1"
# elem.tail = '\n\t'
country.append(elem1)
# SubElement() 其實內部呼叫的時append()
elem2 = ET.SubElement(country, "test_subelement")
elem2.text = "elem 2"
# extend()
elem3 = ET.Element("test_extend")
elem3.text = "elem 3"
elem4 = ET.Element("test_extend")
elem4.text = "elem 4"
country.extend([elem3, elem4])
# insert()
elem5 = ET.Element("test_insert")
elem5.text = "elem 5"
country.insert(5, elem5)
ET.dump(country)
效果:
新增子元素方法總結:
append
(subelement)extend
(subelements)insert
(index, element)
4.建立xml文件
想建立root Element,然後建立SubElement,最後將root element傳入ElementTree(element),建立tree,呼叫tree.write()方法寫入檔案
對於建立元素的3個方法: 使用ET.Element、Element物件的makeelement()方法以及ET.SubElement
import xml.etree.ElementTree as ET
def subElement(root, tag, text):
ele = ET.SubElement(root, tag)
ele.text = text
ele.tail = '\n'
root = ET.Element("note")
to = root.makeelement("to", {})
to.text = "peter"
to.tail = '\n'
root.append(to)
subElement(root, "from", "marry")
subElement(root, "heading", "Reminder")
subElement(root, "body", "Don't forget the meeting!")
tree = ET.ElementTree(root)
tree.write("note.xml", encoding="utf-8", xml_declaration=True)
效果:
由於原生儲存的XML時預設無縮排,如果想要設定縮排的話, 需要修改儲存方式
程式碼:
import xml.etree.ElementTree as ET
from xml.dom import minidom
def subElement(root, tag, text):
ele = ET.SubElement(root, tag)
ele.text = text
def saveXML(root, filename, indent="\t", newl="\n", encoding="utf-8"):
rawText = ET.tostring(root)
dom = minidom.parseString(rawText)
with open(filename, 'w') as f:
dom.writexml(f, "", indent, newl, encoding)
root = ET.Element("note")
to = root.makeelement("to", {})
to.text = "peter"
root.append(to)
subElement(root, "from", "marry")
subElement(root, "heading", "Reminder")
subElement(root, "body", "Don't forget the meeting!")
# 儲存xml檔案
saveXML(root, "note.xml")