（python功能定制）复杂的xml文件对比，产生HTML展示区别
程序员文章站
2023-08-18 10:15:58
功能的设计初衷： 处理复杂的xml对比，屏蔽同节点先后顺序的影响 主要涉及知识点： 1、ElementTree库 xml解析： 导入ElementTree，import xml.etree.ElementTree as ET 解析Xml文件找到根节点： 直接解析XML文件并获得根节点，tree = ......
功能的设计初衷：
处理复杂的xml对比，屏蔽同节点先后顺序的影响
主要涉及知识点：
1、ElementTree库 ------- xml解析：
-
- 导入ElementTree，
import xml.etree.ElementTree as ET - 解析Xml文件找到根节点：
- 直接解析XML文件并获得根节点，
tree = ET.parse('country_data.xml') root = tree.getroot() - 解析字符串，
root = ET.fromstring(country_data_as_string) - 遍历根节点可以获得子节点，然后就可以根据需求拿到需要的字段了，如：<APP_KEY channel = 'CSDN'> hello123456789 </APP_KEY>
- 导入ElementTree，
-
-
- tag，即标签，用于标识该元素表示哪种数据，即APP_KEY
- attrib，即属性，用Dictionary形式保存，即{'channel' = 'CSDN'}
- text，文本字符串，可以用来存储一些数据，即hello123456789
- tail，尾字符串，并不是必须的，例子中没有包含。
-
2、difflib库 ------- 提供的类和方法用来进行序列的差异化比较，它能够比对文件并生成差异结果文本或者html格式的差异化比较页面
这里使用了类difflib.HtmlDiff，用来创建一个html表格展示文件差异，他既可以进行全文本展示，也可以只展示上下文不同。
其构造函数如下：
__init__(tabsize=8, wrapcolumn=None, linejunk=None, charjunk=IS_CHARACTER_JUNK)
-
-
- tabsize表示制表符代表的空格个数，默认为8
- wrapcolumn,可选参数，用来设置多少个字符时自动换行，默认None,为None时表示不自动换行（重点：可以让html显示更美观）
- linejunk 和 charjunk，可选参数，在ndiff()中使用，
-
公共方法（生成一个包含表格的html文件，其内容是用来展示差异）：
make_file(fromlines, tolines [, fromdesc][, todesc][, context][, numlines])
-
-
- fromlines 和tolines,用于比较的内容，格式为字符串组成的列表
- fromdesc 和 todesc，可选参数，对应的fromlines,tolines的差异化文件的标题，默认为空字符串
- context 和 numlines，可选参数，context 为True时，只显示差异的上下文，为false，显示全文，numlines默认为5，当context为True时，控制展示上下文的行数，当context为false时,控制不同差异的高亮之间移动时“next”的开始位置（如果设置为0，当移动懂顶端时，超链接会丢失引用地址）
-
3、platform库 -------- 获取当前系统
4、logger库 -------- 如果使用robot framework，可以看到明显区别，可以定制日志log显示
robot framework的体验还不错，大概是因为其测试报告已经可以满足正常需要，很少有人会想去修改或者增加自己想要展示的内容，比如增加一个超链接，展示更多的内容，所以这部分花了很长时间均没有在网上找到相关资料，最后只能阅读源码。
遗憾与待优化：
其中有一部分内容，原先准备采用自循环的方式处理，但是过程中的数据传输逻辑容易错乱，以后会考虑把这部分优化一下。
##############################以下是代码部分，附件文件可以拖到本地执行并查看结果##################################################
1 # coding=utf-8
2 import re
3 import xml.etree.ElementTree as ET #解析xml的库
4 import difflib #文件对比库
5 import datetime #时间库
6 import platform #获取系统的库window、linux...
7 import os
8 from robot.api import logger #不需要的话可以注释掉：robot framework框架脚本运行时会产生日志，可以利用这个库定制log
9
10 # listafter：将解析后的xml，转换成按序排列的list：（tag，attrib，（tag，attrib，text））
11 # 此方法是被下面一个方法xmltolist()调用的，想知道具体结果，可以使用下面的方法打印解析后的结果
12 def listafter(listcom1):
13 listcomarr1 = []
14 text1 = []
15 listcomarr1.append(listcom1.tag)
16 listcomarr1.append(listcom1.attrib)
17 if len(listcom1) > 0:
18 for listcom2 in listcom1:
19 listcomarr2 = []
20 text2 = []
21 listcomarr2.append(listcom2.tag)
22 listcomarr2.append(listcom2.attrib)
23 if len(listcom2) > 0:
24 for listcom3 in listcom2:
25 listcomarr3 = []
26 text3 = []
27 listcomarr3.append(listcom3.tag)
28 listcomarr3.append(listcom3.attrib)
29 if len(listcom3) > 0:
30 for listcom4 in listcom3:
31 listcomarr4 = []
32 text4 = []
33 listcomarr4.append(listcom4.tag)
34 listcomarr4.append(listcom4.attrib)
35 if len(listcom4) > 0:
36 for listcom5 in listcom4:
37 listcomarr5 = []
38 text5 = []
39 listcomarr5.append(listcom5.tag)
40 listcomarr5.append(listcom5.attrib)
41 if len(listcom5) > 0:
42 for listcom6 in listcom5:
43 listcomarr6 = []
44 text6 = []
45 listcomarr6.append(listcom6.tag)
46 listcomarr6.append(listcom6.attrib)
47 if len(listcom6) > 0:
48 for listcom7 in listcom6:
49 listcomarr7 = []
50 text7 = []
51 listcomarr7.append(listcom7.tag)
52 listcomarr7.append(listcom7.attrib)
53 if len(listcom7) > 0:
54 for listcom8 in listcom7:
55 listcomarr8 = []
56 text8 = []
57 listcomarr8.append(listcom8.tag)
58 listcomarr8.append(listcom8.attrib)
59 if len(listcom8) > 0:
60 for listcom9 in listcom8:
61 listcomarr9 = []
62 text9 = []
63 listcomarr9.append(listcom9.tag)
64 listcomarr9.append(listcom9.attrib)
65 # Start：判断是否需要继续递归
66 if len(listcom9) > 0:
67 for listcom10 in listcom9:
68 listcomarr10 = []
69 text10 = []
70 listcomarr10.append(listcom10.tag)
71 listcomarr10.append(listcom10.attrib)
72 listcomarr10.append([listcom10.text])
73 text9.append(listcomarr10)
74 else:
75 text9.append(listcom9.text)
76 # End：判断是否需要继续递归
77 # list二维数组排序
78 text9 = sorted(text9)
79 listcomarr9.append(text9)
80 text8.append(listcomarr9)
81 else:
82 text8.append(listcom8.text)
83 text8 = sorted(text8)
84 listcomarr8.append(text8)
85 text7.append(listcomarr8)
86 else:
87 text7.append(listcom7.text)
88 text7 = sorted(text7)
89 listcomarr7.append(text7)
90 text6.append(listcomarr7)
91 else:
92 text6.append(listcom6.text)
93 text6 = sorted(text6)
94 listcomarr6.append(text6)
95 text5.append(listcomarr6)
96 else:
97 text5.append(listcom5.text)
98 text5 = sorted(text5)
99 listcomarr5.append(text5)
100 text4.append(listcomarr5)
101 else:
102 text4.append(listcom4.text)
103 text4 = sorted(text4)
104 listcomarr4.append(text4)
105 text3.append(listcomarr4)
106 else:
107 text3.append(listcom3.text)
108 text3 = sorted(text3)
109 listcomarr3.append(text3)
110 text2.append(listcomarr3)
111 else:
112 text2.append(listcom2.text)
113 text2 = sorted(text2)
114 listcomarr2.append(text2)
115 text1.append(listcomarr2)
116 else:
117 text1.append(listcom1.text)
118 text1 = sorted(text1)
119 listcomarr1.append(text1)
120 return listcomarr1
121
122 # 将xml内容转换成按序排列的list，返回值有3个:处理后的spmlxmllist、不需要处理的头部spmlstart、不需要处理的尾部spmlend
123 # spmlstart、spmlend是为了控制不需要处理的头部和尾部，提高处理效率
124 def xmltolist(spml):
125 if spml.find("<spml:") != -1:
126 startnum = re.search(r'<spml:[^>]*>', spml).span()[1]
127 endnum = spml.rfind("</spml:")
128 spmlstart = spml[:startnum].strip()
129 spmlend = spml[endnum:].strip()
130 spmlxml = '''<spml:modifyRequest xmlns:spml='{spml}' xmlns:subscriber="{subscriber}" xmlns:xsi="{xsi}">\n%s</spml:modifyRequest>''' % (
131 spml[startnum:endnum].strip())
132 elif spml.find("<PlexViewRequest") != -1:
133 startnum = re.search(r'<PlexViewRequest[^>]*>', spml).span()[1]
134 endnum = spml.rfind("</PlexViewRequest>")
135 spmlstart = spml[:startnum].strip()
136 spmlend = spml[endnum:].strip()
137 spmlxml = '''<PlexViewRequest>\n%s</PlexViewRequest>''' % (spml[startnum:endnum].strip())
138 else:
139 spmlstart = ""
140 spmlend = ""
141 spmlxml = spml
142 # print spmlstart
143 # print endspml
144 # print spmlxml
145 tree = ET.fromstring(spmlxml)
146 spmlxmllist = listafter(tree)
147 return spmlxmllist, spmlstart, spmlend
148
149 # 将xmltolist处理形成的spmlxmllist再回头变成xml（xml中，同节点的内容已被按需排列）
150 def listtoxml(spmllist1):
151 kong = " "
152 spmltag1 = spmllist1[0]
153 spmlattrib1 = ""
154 bodyxml1 = ""
155 if spmllist1[1] != {}:
156 for key, value in spmllist1[1].items():
157 spmlattrib1 += " %s='%s'" % (key, value)
158 startxml1 = "<%s%s>" % (spmltag1, spmlattrib1)
159 endxml1 = "</%s>" % (spmltag1)
160 spmlxml1 = ""
161 if isinstance(spmllist1[2][0], list):
162 spmlxml2 = ""
163 for spmllist2 in spmllist1[2]:
164 spmltag2 = spmllist2[0]
165 spmlattrib2 = ""
166 bodyxml2 = ""
167 if spmllist2[1] != {}:
168 for key, value in spmllist2[1].items():
169 spmlattrib2 += " %s='%s'" % (key, value)
170 startxml2 = "<%s%s>" % (spmltag2, spmlattrib2)
171 endxml2 = "</%s>" % (spmltag2)
172 if isinstance(spmllist2[2][0], list):
173 spmlxml3 = ""
174 for spmllist3 in spmllist2[2]:
175 spmltag3 = spmllist3[0]
176 spmlattrib3 = ""
177 bodyxml3 = ""
178 if spmllist3[1] != {}:
179 for key, value in spmllist3[1].items():
180 spmlattrib3 += " %s='%s'" % (key, value)
181 startxml3 = "<%s%s>" % (spmltag3, spmlattrib3)
182 endxml3 = "</%s>" % (spmltag3)
183 if isinstance(spmllist3[2][0], list):
184 spmlxml4 = ""
185 for spmllist4 in spmllist3[2]:
186 spmltag4 = spmllist4[0]
187 spmlattrib4 = ""
188 bodyxml4 = ""
189 if spmllist4[1] != {}:
190 for key, value in spmllist4[1].items():
191 spmlattrib4 += " %s='%s'" % (key, value)
192 startxml4 = "<%s%s>" % (spmltag4, spmlattrib4)
193 endxml4 = "</%s>" % (spmltag4)
194 if isinstance(spmllist4[2][0], list):
195 spmlxml5 = ""
196 for spmllist5 in spmllist4[2]:
197 spmltag5 = spmllist5[0]
198 spmlattrib5 = ""
199 bodyxml5 = ""
200 if spmllist5[1] != {}:
201 for key, value in spmllist5[1].items():
202 spmlattrib5 += " %s='%s'" % (key, value)
203 startxml5 = "<%s%s>" % (spmltag5, spmlattrib5)
204 endxml5 = "</%s>" % (spmltag5)
205 if isinstance(spmllist5[2][0], list):
206 spmlxml6 = ""
207 for spmllist6 in spmllist5[2]:
208 spmltag6 = spmllist6[0]
209 spmlattrib6 = ""
210 bodyxml6 = ""
211 if spmllist6[1] != {}:
212 for key, value in spmllist6[1].items():
213 spmlattrib6 += " %s='%s'" % (key, value)
214 startxml6 = "<%s%s>" % (spmltag6, spmlattrib6)
215 endxml6 = "</%s>" % (spmltag6)
216 if isinstance(spmllist6[2][0], list):
217 spmlxml7 = ""
218 for spmllist7 in spmllist6[2]:
219 spmltag7 = spmllist7[0]
220 spmlattrib7 = ""
221 bodyxml7 = ""
222 if spmllist7[1] != {}:
223 for key, value in spmllist7[1].items():
224 spmlattrib7 += " %s='%s'" % (key, value)
225 startxml7 = "<%s%s>" % (spmltag7, spmlattrib7)
226 endxml7 = "</%s>" % (spmltag7)
227 if isinstance(spmllist7[2][0], list):
228 spmlxml8 = ""
229 for spmllist8 in spmllist7[2]:
230 spmltag8 = spmllist8[0]
231 spmlattrib8 = ""
232 bodyxml8 = ""
233 if spmllist8[1] != {}:
234 for key, value in spmllist8[1].items():
235 spmlattrib8 += " %s='%s'" % (key, value)
236 startxml8 = "<%s%s>" % (spmltag8, spmlattrib8)
237 endxml8 = "</%s>" % (spmltag8)
238 if isinstance(spmllist8[2][0], list):
239 spmlxml9 = ""
240 for spmllist9 in spmllist8[2]:
241 spmltag9 = spmllist9[0]
242 spmlattrib9 = ""
243 bodyxml9 = ""
244 if spmllist9[1] != {}:
245 for key, value in spmllist9[1].items():
246 spmlattrib9 += " %s='%s'" % (key, value)
247 startxml9 = "<%s%s>" % (spmltag9, spmlattrib9)
248 endxml9 = "</%s>" % (spmltag9)
249 if isinstance(spmllist9[2][0], list):
250 spmlxml10 = ""
251 for spmllist10 in spmllist9[2]:
252 spmltag10 = spmllist10[0]
253 spmlattrib10 = ""
254 bodyxml10 = ""
255 if spmllist10[1] != {}:
256 for key, value in spmllist10[1].items():
257 spmlattrib10 += " %s='%s'" % (
258 key, value)
259 startxml10 = "<%s%s>" % (
260 spmltag10, spmlattrib10)
261 endxml10 = "</%s>" % (spmltag10)
262 bodyxml10 = spmllist10[2][0]
263 spmlxml10 += "\n%s%s%s%s" % (
264 kong * 9, startxml10, bodyxml10,
265 endxml10)
266 spmlxml9 += "\n%s%s%s\n%s%s" % (
267 kong * 8, startxml9, spmlxml10, kong * 8,
268 endxml9)
269 else:
270 bodyxml9 = spmllist9[2][0]
271 spmlxml9 += "\n%s%s%s%s" % (
272 kong * 8, startxml9, bodyxml9, endxml9)
273 spmlxml8 += "\n%s%s%s\n%s%s" % (
274 kong * 7, startxml8, spmlxml9, kong * 7, endxml8)
275 else:
276 bodyxml8 = spmllist8[2][0]
277 spmlxml8 += "\n%s%s%s%s" % (
278 kong * 7, startxml8, bodyxml8, endxml8)
279 spmlxml7 += "\n%s%s%s\n%s%s" % (
280 kong * 6, startxml7, spmlxml8, kong * 6, endxml7)
281 else:
282 bodyxml7 = spmllist7[2][0]
283 spmlxml7 += "\n%s%s%s%s" % (
284 kong * 6, startxml7, bodyxml7, endxml7)
285 spmlxml6 += "\n%s%s%s\n%s%s" % (
286 kong * 5, startxml6, spmlxml7, kong * 5, endxml6)
287 else:
288 bodyxml6 = spmllist6[2][0]
289 spmlxml6 += "\n%s%s%s%s" % (kong * 5, startxml6, bodyxml6, endxml6)
290 spmlxml5 += "\n%s%s%s\n%s%s" % (
291 kong * 4, startxml5, spmlxml6, kong * 4, endxml5)
292 else:
293 bodyxml5 = spmllist5[2][0]
294 spmlxml5 += "\n%s%s%s%s" % (kong * 4, startxml5, bodyxml5, endxml5)
295 spmlxml4 += "\n%s%s%s\n%s%s" % (kong * 3, startxml4, spmlxml5, kong * 3, endxml4)
296 else:
297 bodyxml4 = spmllist4[2][0]
298 spmlxml4 += "\n%s%s%s%s" % (kong * 3, startxml4, bodyxml4, endxml4)
299 spmlxml3 += "\n%s%s%s\n%s%s" % (kong * 2, startxml3, spmlxml4, kong * 2, endxml3)
300 else:
301 bodyxml3 = spmllist3[2][0]
302 spmlxml3 += "\n%s%s%s%s" % (kong * 2, startxml3, bodyxml3, endxml3)
303 spmlxml2 += "\n%s%s%s\n%s%s" % (kong * 1, startxml2, spmlxml3, kong * 1, endxml2)
304 else:
305 bodyxml2 = spmllist2[2][0]
306 spmlxml2 += "\n%s%s%s%s" % (kong * 1, startxml2, bodyxml2, endxml2)
307 spmlxml1 += "\n%s%s\n%s" % (startxml1, spmlxml2, endxml1)
308 else:
309 bodyxml1 = spmllist1[2][0]
310 spmlxml1 += "\n%s%s%s" % (startxml1, bodyxml1, endxml1)
311 return spmlxml1
312
313 # 将startspml, xmlspml, endspml组合起来，其中有一部分内容需要根据实际情况处理
314 def regroupspml(startspml, xmlspml, endspml):
315 xmlspml = str(xmlspml).replace("{{", "").replace("}}", ":").strip().splitlines()
316 if endspml != "":
317 startspml = str(startspml.strip()).replace("\"", "\'")
318 startspml = re.sub(" +>", ">", startspml)
319 startspml = startspml.splitlines()
323 endspml = str(endspml.strip()).splitlines()
324 spmlxmlcom = startspml + xmlspml[1:-1] + endspml
325 else:
326 spmlxmlcom = xmlspml
327 return spmlxmlcom
328
329 # 对按序排列的xml进行内容比对，生成html文件，可以很直接的看出内容区别
330 def diffspml(spmlxml1, spmlxml2):
331 spmlxmllist1, spmlstart1, spmlend1 = xmltolist(spmlxml1)
332 spmlxmllist2, spmlstart2, spmlend2 = xmltolist(spmlxml2)
333 spmlxmlcom1 = listtoxml(spmlxmllist1)
334 spmlxmlcom2 = listtoxml(spmlxmllist2)
335 spmlxmlcom1 = regroupspml(spmlstart1, spmlxmlcom1, spmlend1)
336 spmlxmlcom2 = regroupspml(spmlstart2, spmlxmlcom2, spmlend2)
337 # print spmlstart1
338 # print spmlend1
339 if spmlxmlcom1 == spmlxmlcom2:
340 return 0
341 else:
342 global diffspmNum
343 global outputhtml_dir
344 try:
345 diffspmNum += 1
346 except:
347 diffspmNum = 1
348 system = platform.system()
349 if ('Windows' in system):
350 outputhtml_dir = "c:/RobotLog"
351 else:
352 outputhtml_dir = "/tmp/RobotLog"
353 outputhtml_dir = "%s/%s" % (outputhtml_dir, datetime.datetime.now().strftime('%Y%m%d_%H%M%S'))
354 os.makedirs(outputhtml_dir)
355 Loghtmldir = "%s/%s.html" % (outputhtml_dir, diffspmNum)
356 # logger.write("<a href=\"%s\">%s</a>" % (Loghtmldir, Loghtmldir), "HTML")
357 hd = difflib.HtmlDiff(8,65)
358 with open(Loghtmldir, 'w') as fo:
359 fo.write(hd.make_file(spmlxmlcom1, spmlxmlcom2))
360 fo.close()
361 return Loghtmldir
#############################################以上是代码部分#################################################################
1 spmlxml1='''
2 <PlexViewRequest SessionId="${sessionid}" ProvisioningGroup="volte" Command="ed-ngfs-subscriber-v2"><SubParty><PrimaryPUID>+86${ISDN}@${domain}</PrimaryPUID><PartyId>+86${ISDN}</PartyId></SubParty><SeqRinging><RingingList>null^null^true^true^10^false`+86${msisdn1}^STANDARD^true^true^10^false</RingingList><DefaultAnswerTimeout>10</DefaultAnswerTimeout><Send181Mode>TAS_181_NONE</Send181Mode><Activated>true</Activated><PublicUID>+86${ISDN}@${domain}</PublicUID><Assigned>true</Assigned></SeqRinging></PlexViewRequest>
3 '''
4 spmlxml2='''
5 <PlexViewRequest SessionId="${sessionid}" ProvisioningGroup="volte" Command="ed-ngfs-subscriber-v2">
6 <SubParty>
7 <PrimaryPUID>+86${ISDN}@${domain}</PrimaryPUID>
8 <PartyId>+86${ISDN}</PartyId>
9 </SubParty>
10 <SeqRinging>
11 <RingingList>null^null^true^true^10^false`+86${msisdn1}^STANDARD^true^true^10^false</RingingList>
12 <DefaultAnswerTimeout>10</DefaultAnswerTimeout>
13 <Send181Mode>TAS_180_NONE</Send181Mode>
14 <Activated>true</Activated>
15 <PublicUID>+86${ISDN}@${domain}</PublicUID>
16 </SeqRinging>
17 </PlexViewRequest>
18 '''
19 print diffspml(spmlxml1, spmlxml2)
#####################################以上列出来了本公司使用的xml格式（还可以更复杂），方法中有部分内容是根据本身需要，特别处理的####################################