python06模块2

configparser

configparser用于处理特定格式的文件，其本质上是利用open来操作文件。

1 # 注释1
2 ;  注释2
3  
4 [section1] # 节点
5 k1 = v1    # 值
6 k2:v2       # 值
7  
8 [section2] # 节点
9 k1 = v1    # 值
View Code

1、获取所有节点

1 import configparser
2  
3 config = configparser.ConfigParser()
4 config.read('xxxooo', encoding='utf-8')
5 ret = config.sections()
6 print(ret)
View Code

2、获取指定节点下所有的键值对

1 import configparser
2  
3 config = configparser.ConfigParser()
4 config.read('xxxooo', encoding='utf-8')
5 ret = config.items('section1')
6 print(ret)
View Code

3、获取指定节点下所有的建

1 import configparser
2  
3 config = configparser.ConfigParser()
4 config.read('xxxooo', encoding='utf-8')
5 ret = config.options('section1')
6 print(ret)
View Code

4、获取指定节点下指定key的值

 1 import configparser
 2  
 3 config = configparser.ConfigParser()
 4 config.read('xxxooo', encoding='utf-8')
 5  
 6  
 7 v = config.get('section1', 'k1')
 8 # v = config.getint('section1', 'k1')
 9 # v = config.getfloat('section1', 'k1')
10 # v = config.getboolean('section1', 'k1')
11  
12 print(v)
View Code

5、检查、删除、添加节点

 1 import configparser
 2  
 3 config = configparser.ConfigParser()
 4 config.read('xxxooo', encoding='utf-8')
 5  
 6  
 7 # 检查
 8 has_sec = config.has_section('section1')
 9 print(has_sec)
10  
11 # 添加节点
12 config.add_section("SEC_1")
13 config.write(open('xxxooo', 'w'))
14  
15 # 删除节点
16 config.remove_section("SEC_1")
17 config.write(open('xxxooo', 'w'))
View Code

6、检查、删除、设置指定组内的键值对

 1 import configparser
 2  
 3 config = configparser.ConfigParser()
 4 config.read('xxxooo', encoding='utf-8')
 5  
 6 # 检查
 7 has_opt = config.has_option('section1', 'k1')
 8 print(has_opt)
 9  
10 # 删除
11 config.remove_option('section1', 'k1')
12 config.write(open('xxxooo', 'w'))
13  
14 # 设置
15 config.set('section1', 'k10', "123")
16 config.write(open('xxxooo', 'w'))
View Code

XML

XML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：

 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>
View Code

1、解析XML

利用ElementTree.XML将字符串解析成xml对象
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 # 获取xml文件的根节点
7 root = tree.getroot()
利用ElementTree.parse将文件直接解析成xml对象

2、操作XML

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：

  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
节点功能一览表

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），so   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

 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)
View Code

b、遍历XML中指定的节点

 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)
View Code

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 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')
解析字符串方式，修改，保存
 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')
解析文件方式，修改，保存

d、删除节点

 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')
解析字符串方式打开，删除，保存
 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')
解析文件方式打开，删除，保存

3、创建XML文档

 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)
创建方式（一）
 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)
创建方式（二）
 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)
创建方式（三）

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：

 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()
View Code

4、命名空间

详细介绍，猛击这里

 1 from xml.etree import ElementTree as ET
 2 
 3 ET.register_namespace('com',"http://www.company.com") #some name
 4 
 5 # build a tree structure
 6 root = ET.Element("{http://www.company.com}STUFF")
 7 body = ET.SubElement(root, "{http://www.company.com}MORE_STUFF", attrib={"{http://www.company.com}hhh": "123"})
 8 body.text = "STUFF EVERYWHERE!"
 9 
10 # wrap it in an ElementTree instance, and save as XML
11 tree = ET.ElementTree(root)
12 
13 tree.write("page.xml",
14            xml_declaration=True,
15            encoding='utf-8',
16            method="xml")
命名空间

requests

Python标准库中提供了：urllib等模块以供Http请求，但是，它的 API 太渣了。它是为另一个时代、另一个互联网所创建的。它需要巨量的工作，甚至包括各种方法覆盖，来完成最简单的任务。

1 import urllib.request
2 
3 
4 f = urllib.request.urlopen('http://www.webxml.com.cn//webservices/qqOnlineWebService.asmx/qqCheckOnline?qqCode=424662508')
5 result = f.read().decode('utf-8')
发送GET请求
1 import urllib.request
2 
3 req = urllib.request.Request('http://www.example.com/')
4 req.add_header('Referer', 'http://www.python.org/')
5 r = urllib.request.urlopen(req)
6 
7 result = f.read().decode('utf-8')
发送携带请求头的GET请求

注：更多见Python官方文档：https://docs.python.org/3.5/library/urllib.request.html#module-urllib.request

Requests 是使用 Apache2 Licensed 许可证的 基于Python开发的HTTP 库，其在Python内置模块的基础上进行了高度的封装，从而使得Pythoner进行网络请求时，变得美好了许多，使用Requests可以轻而易举的完成浏览器可有的任何操作。

1、安装模块 (pip3 install requests) 2或者源码安装（解压缩，进入终端，进入cdsetup.py的目录夹，python setup.py install )

2、使用模块

 1 1、无参数实例
 2  
 3 import requests
 4  
 5 ret = requests.get('https://github.com/timeline.json')
 6  
 7 print(ret.url)
 8 print(ret.text)
 9  
10  
11  
12 # 2、有参数实例
13  
14 import requests
15  
16 payload = {'key1': 'value1', 'key2': 'value2'}
17 ret = requests.get("http://httpbin.org/get", params=payload)
18  
19 print(ret.url)
20 print(ret.text)
GET请求
 1 1、基本POST实例
 2  
 3 import requests
 4  
 5 payload = {'key1': 'value1', 'key2': 'value2'}
 6 ret = requests.post("http://httpbin.org/post", data=payload)
 7  
 8 print(ret.text)
 9  
10  
11 # 2、发送请求头和数据实例
12  
13 import requests
14 import json
15  
16 url = 'https://api.github.com/some/endpoint'
17 payload = {'some': 'data'}
18 headers = {'content-type': 'application/json'}
19  
20 ret = requests.post(url, data=json.dumps(payload), headers=headers)
21  
22 print(ret.text)
23 print(ret.cookies)
POST请求
 1 requests.get(url, params=None, **kwargs)
 2 requests.post(url, data=None, json=None, **kwargs)
 3 requests.put(url, data=None, **kwargs)
 4 requests.head(url, **kwargs)
 5 requests.delete(url, **kwargs)
 6 requests.patch(url, data=None, **kwargs)
 7 requests.options(url, **kwargs)
 8  
 9 # 以上方法均是在此方法的基础上构建
10 requests.request(method, url, **kwargs)
其他要求

更多requests模块相关的文档见：http://cn.python-requests.org/zh_CN/latest/

3、Http请求和XML实例

实例：检测QQ账号是否在线

 1 import urllib
 2 import requests
 3 from xml.etree import ElementTree as ET
 4 
 5 # 使用内置模块urllib发送HTTP请求，或者XML格式内容
 6 """
 7 f = urllib.request.urlopen('http://www.webxml.com.cn//webservices/qqOnlineWebService.asmx/qqCheckOnline?qqCode=424662508')
 8 result = f.read().decode('utf-8')
 9 """
10 
11 
12 # 使用第三方模块requests发送HTTP请求，或者XML格式内容
13 r = requests.get('http://www.webxml.com.cn//webservices/qqOnlineWebService.asmx/qqCheckOnline?qqCode=424662508')
14 result = r.text
15 
16 # 解析XML格式内容
17 node = ET.XML(result)
18 
19 # 获取内容
20 if node.text == "Y":
21     print("在线")
22 else:
23     print("离线")
View Code

实例：查看火车停靠信息

 1 import urllib
 2 import requests
 3 from xml.etree import ElementTree as ET
 4 
 5 # 使用内置模块urllib发送HTTP请求，或者XML格式内容
 6 """
 7 f = urllib.request.urlopen('http://www.webxml.com.cn/WebServices/TrainTimeWebService.asmx/getDetailInfoByTrainCode?TrainCode=G666&UserID=')
 8 result = f.read().decode('utf-8')
 9 """
10 
11 # 使用第三方模块requests发送HTTP请求，或者XML格式内容
12 r = requests.get('http://www.webxml.com.cn/WebServices/TrainTimeWebService.asmx/getDetailInfoByTrainCode?TrainCode=G666&UserID=')
13 result = r.text
14 
15 # 解析XML格式内容
16 root = ET.XML(result)
17 for node in root.iter('TrainDetailInfo'):
18     print(node.find('TrainStation').text,node.find('StartTime').text,node.tag,node.attrib)
View Code

注：更多接口猛击这里

logging

用于便捷记录日志且线程安全的模块

1、单文件日志

 1 import logging
 2   
 3   
 4 logging.basicConfig(filename='log.log',
 5                     format='%(asctime)s - %(name)s - %(levelname)s -%(module)s:  %(message)s',
 6                     datefmt='%Y-%m-%d %H:%M:%S %p',
 7                     level=10)
 8   
 9 logging.debug('debug')
10 logging.info('info')
11 logging.warning('warning')
12 logging.error('error')
13 logging.critical('critical')
14 logging.log(10,'log')
View Code

日志等级：

1 CRITICAL = 50
2 FATAL = CRITICAL
3 ERROR = 40
4 WARNING = 30
5 WARN = WARNING
6 INFO = 20
7 DEBUG = 10
8 NOTSET = 0
View Code

注：只有【当前写等级】大于【日志等级】时，日志文件才被记录。

日志记录格式：

2、多文件日志

对于上述记录日志的功能，只能将日志记录在单文件中，如果想要设置多个日志文件，logging.basicConfig将无法完成，需要自定义文件和日志操作对象。

 1 定义文件
 2 file_1_1 = logging.FileHandler('l1_1.log', 'a')
 3 fmt = logging.Formatter(fmt="%(asctime)s - %(name)s - %(levelname)s -%(module)s:  %(message)s")
 4 file_1_1.setFormatter(fmt)
 5 
 6 file_1_2 = logging.FileHandler('l1_2.log', 'a')
 7 fmt = logging.Formatter()
 8 file_1_2.setFormatter(fmt)
 9 
10 # 定义日志
11 logger1 = logging.Logger('s1', level=logging.ERROR)
12 logger1.addHandler(file_1_1)
13 logger1.addHandler(file_1_2)
14 
15 
16 # 写日志
17 logger1.critical('1111')
日志一
1 定义文件
2 file_2_1 = logging.FileHandler('l2_1.log', 'a')
3 fmt = logging.Formatter()
4 file_2_1.setFormatter(fmt)
5 
6 # 定义日志
7 logger2 = logging.Logger('s2', level=logging.INFO)
8 logger2.addHandler(file_2_1)
日志2

如上述创建的两个日志对象

  • 当使用【logger1】写日志时，会将相应的内容写入 l1_1.log 和 l1_2.log 文件中
  • 当使用【logger2】写日志时，会将相应的内容写入 l2_1.log 文件中

系统命令

可以执行shell命令的相关模块和函数有：

  • os.system
  • os.spawn*
  • os.popen*          --废弃
  • popen2.*           --废弃
  • commands.*      --废弃，3.x中被移除
1 import commands
2 
3 result = commands.getoutput('cmd')
4 result = commands.getstatus('cmd')
5 result = commands.getstatusoutput('cmd')
commands

以上执行shell命令的相关的模块和函数的功能均在 subprocess 模块中实现，并提供了更丰富的功能。

call 

执行命令，返回状态码

ret = subprocess.call(["ls", "-l"], shell=False)
ret = subprocess.call("ls -l", shell=True)

check_call

执行命令，如果执行状态码是 0 ，则返回0，否则抛异常

1 subprocess.check_call(["ls", "-l"])
2 subprocess.check_call("exit 1", shell=True)

check_output

执行命令，如果状态码是 0 ，则返回执行结果，否则抛异常

1 subprocess.check_output(["echo", "Hello World!"])
2 subprocess.check_output("exit 1", shell=True)

subprocess.Popen(...)

用于执行复杂的系统命令

参数：

    • args：shell命令，可以是字符串或者序列类型（如：list，元组）
    • bufsize：指定缓冲。0 无缓冲,1 行缓冲,其他 缓冲区大小,负值 系统缓冲
    • stdin, stdout, stderr：分别表示程序的标准输入、输出、错误句柄
    • preexec_fn：只在Unix平台下有效，用于指定一个可执行对象（callable object），它将在子进程运行之前被调用
    • close_sfs：在windows平台下，如果close_fds被设置为True，则新创建的子进程将不会继承父进程的输入、输出、错误管道。
      所以不能将close_fds设置为True同时重定向子进程的标准输入、输出与错误(stdin, stdout, stderr)。
    • shell：同上
    • cwd：用于设置子进程的当前目录
    • env：用于指定子进程的环境变量。如果env = None，子进程的环境变量将从父进程中继承。
    • universal_newlines：不同系统的换行符不同，True -> 同意使用 \n
    • startupinfo与createionflags只在windows下有效
      将被传递给底层的CreateProcess()函数，用于设置子进程的一些属性，如：主窗口的外观，进程的优先级等等 
1 1 import subprocess
2 2 ret1 = subprocess.Popen(["mkdir","t1"])
3 3 ret2 = subprocess.Popen("mkdir t2", shell=True)
View Code

终端输入的命令分为两种：

  • 输入即可得到输出，如：ifconfig
  • 输入进行某环境，依赖再输入，如：python
1 import subprocess
2 
3 obj = subprocess.Popen("mkdir t3", shell=True, cwd='/home/dev',)
View Code
 1 import subprocess
 2 
 3 obj = subprocess.Popen(["python"], stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE, universal_newlines=True)
 4 obj.stdin.write("print(1)\n")
 5 obj.stdin.write("print(2)")
 6 obj.stdin.close()
 7 
 8 cmd_out = obj.stdout.read()
 9 obj.stdout.close()
10 cmd_error = obj.stderr.read()
11 obj.stderr.close()
12 
13 print(cmd_out)
14 print(cmd_error)
View Code
1 import subprocess
2 
3 obj = subprocess.Popen(["python"], stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE, universal_newlines=True)
4 obj.stdin.write("print(1)\n")
5 obj.stdin.write("print(2)")
6 
7 out_error_list = obj.communicate()
8 print(out_error_list)
View Code
1 import subprocess
2 
3 obj = subprocess.Popen(["python"], stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE, universal_newlines=True)
4 out_error_list = obj.communicate('print("hello")')
5 print(out_error_list)
View Code

paramiko

paramiko是一个用于做远程控制的模块，使用该模块可以对远程服务器进行命令或文件操作，值得一说的是，fabric和ansible内部的远程管理就是使用的paramiko来现实。

1、下载安装

1 pycrypto，由于 paramiko 模块内部依赖pycrypto，所以先下载安装pycrypto
2 pip3 install pycrypto
3 pip3 install paramiko

2、模块使用

 1 #!/usr/bin/env python
 2 #coding:utf-8
 3 
 4 import paramiko
 5 
 6 ssh = paramiko.SSHClient()
 7 ssh.set_missing_host_key_policy(paramiko.AutoAddPolicy())
 8 ssh.connect('192.168.1.108', 22, 'alex', '123')
 9 stdin, stdout, stderr = ssh.exec_command('df')
10 print stdout.read()
11 ssh.close();
执行命令 - 用户名+密码
 1 import paramiko
 2 
 3 private_key_path = '/home/auto/.ssh/id_rsa'
 4 key = paramiko.RSAKey.from_private_key_file(private_key_path)
 5 
 6 ssh = paramiko.SSHClient()
 7 ssh.set_missing_host_key_policy(paramiko.AutoAddPolicy())
 8 ssh.connect('主机名 ', 端口, '用户名', key)
 9 
10 stdin, stdout, stderr = ssh.exec_command('df')
11 print stdout.read()
12 ssh.close()
执行命令 - 密钥
 1 import os,sys
 2 import paramiko
 3 
 4 t = paramiko.Transport(('182.92.219.86',22))
 5 t.connect(username='wupeiqi',password='123')
 6 sftp = paramiko.SFTPClient.from_transport(t)
 7 sftp.put('/tmp/test.py','/tmp/test.py') 
 8 t.close()
 9 
10 
11 import os,sys
12 import paramiko
13 
14 t = paramiko.Transport(('182.92.219.86',22))
15 t.connect(username='wupeiqi',password='123')
16 sftp = paramiko.SFTPClient.from_transport(t)
17 sftp.get('/tmp/test.py','/tmp/test2.py')
18 t.close()
上传或下载文件 - 用户名+密码
 1 import paramiko
 2 
 3 pravie_key_path = '/home/auto/.ssh/id_rsa'
 4 key = paramiko.RSAKey.from_private_key_file(pravie_key_path)
 5 
 6 t = paramiko.Transport(('182.92.219.86',22))
 7 t.connect(username='wupeiqi',pkey=key)
 8 
 9 sftp = paramiko.SFTPClient.from_transport(t)
10 sftp.put('/tmp/test3.py','/tmp/test3.py') 
11 
12 t.close()
13 
14 import paramiko
15 
16 pravie_key_path = '/home/auto/.ssh/id_rsa'
17 key = paramiko.RSAKey.from_private_key_file(pravie_key_path)
18 
19 t = paramiko.Transport(('182.92.219.86',22))
20 t.connect(username='wupeiqi',pkey=key)
21 
22 sftp = paramiko.SFTPClient.from_transport(t)
23 sftp.get('/tmp/test3.py','/tmp/test4.py') 
24 
25 t.close()
上传或下载文件 - 密钥
【推广】 免费学中医，健康全家人
原文地址：https://www.cnblogs.com/237325670qqcom/p/5575366.html