1.解析xml,提取資料
使用python自帶的xml.dom中的minidom(也可以用lxml)
xml檔案如下:
![](https://img.laitimes.com/img/__Qf2AjLwojIjJCLyojI0JCLiITMyETOxgDOxAjM-cmbw5SN2ETN1kDM5ETO4EDMy8CX5ADOxAjMvwVZsNWa0JXYvw1cldWYtl2XlxWam9CX0VmbuETNipmLzVGbpZ2Lc9CX6MHc0RHaiojIsJye.png)
minidom.parse()#解析檔案,傳回DOM對象
_get_documentElement()DOM是樹形結構,獲得了樹形結構的根節點
getElementsByTagName()根據name查找根目錄下的子節點
getAttribute()擷取DOM節點的屬性的值
提取的代碼如下:
class get_xml():
#加載擷取xml的文檔對象
def __init__(self,address):
#解析address檔案,傳回DOM對象,address為檔案位址
self.doc = minidom.parse(address)
#DOM是樹形結構,_get_documentElement()獲得了樹形結構的根節點
self.root = self.doc._get_documentElement()
#.getElementsByTagName(),根據name查找根目錄下的子節點
self.httpSample_nodes = self.root.getElementsByTagName('httpSample')
def getxmldata(self):
data_list=[]
j = -1
responseData_node = self.root.getElementsByTagName("responseData")
for i in self.httpSample_nodes:
j = j+1
#getAttribute(),擷取DOM節點的屬性的值
if i.getAttribute("lb") == "發送資訊":
a = 'chatId":"(.*?)"'
elif i.getAttribute("lb") == "接收資訊":
# a = "chatId%3A%22(.*?)%22"
a = "info%3A%22(.*?)%22"
if (i.getAttribute("lb") == "發送資訊" or i.getAttribute("lb") == "接收資訊") and i.getAttribute("rc") == "200":
try:
#使用re包裡面的方法,通過正規表達式提取資料
b = re.search(a, responseData_node[j].firstChild.data)
if b is not None:
d = b.group(1)
print("d:",d)
data_list.append((d, i.getAttribute("ts"), i.getAttribute("lt"),i.getAttribute("lb")))
except:
pass
return data_list
2.存儲為Excel,導出資料到Excel
用到的包openpyxl,openpyxl.workbook下的
Workbook()
用來在記憶體裡建立檔案,最後寫進磁盤的
wb = load_workbook(filename = XXXX.xlsx):讀取Excel檔案,檔案位址為XXXX.xlsx
wb = Workbook():建立一個Workbook對象
ew = ExcelWriter(workbook = wb):建立一個excelWriter,最後用來儲存
wb.create_sheet(0, 'XXX'):建立一個sheet,位置是0,sheet名字是XXX
ws = wb.worksheets[0]:打開一個sheet,sheet位置是0,即第1個sheet
ws.cell(row=1,column=1).value = XXX:在1行1列的位置加入資料XXX
ew.save(filename = XXXX.xlsx):将資料導出到本地,本地檔案位址為XXXX.xlsx
一個導出Excel的例子如下:
import openpyxl
from openpyxl import writer,load_workbook
# Workbook用來在記憶體裡建立檔案最後寫進磁盤的
from openpyxl.workbook import workbook, Workbook
from openpyxl.writer.excel import ExcelWriter
from openpyxl.cell import get_column_letter
# if __name__ == "__main__":
def importexcel(match,dest_filename):
if(os.path.exists(dest_filename)):
wb = load_workbook(filename=dest_filename)
else:
wb = Workbook()
ew = ExcelWriter(workbook = wb)
#建立一個新sheet
wb.create_sheet(0, '聊聊發送接收請求')
# 打開已存在的第一個sheet,也可以用get_sheet_names獲得所有的sheet的名字
ws = wb.worksheets[0]
ws.title = "聊聊發送接收請求"
ws.cell('A1').value = "chartid"
ws.cell('B1').value = "接收時間戳"
ws.cell('C1').value = "發送時間戳"
ws.cell('D1').value = "時間戳差"
ws.cell('E1').value = "接收lt"
ws.cell('F1').value = "發送到接收的響應時間"
l = 2
for i in match:
ws.cell(row=l,column=1).value = i['chatId']
ws.cell(row=l,column=2).value = i['accept_timestamp']
ws.cell(row=l,column=3).value = i['send_timestamp']
ws.cell(row=l,column=4).value = i['timestamp_gap']
ws.cell(row=l,column=5).value = i['accept_lt']
ws.cell(row=l,column=6).value = i['response_time']
print(i,l)
l = l+1
ew.save(filename = dest_filename)