.py小程式總結
阿新 • • 發佈：2020-12-21
首先pycharm裡面的程式碼格式化，也就是所說的美化快捷鍵【Ctrl+Alt+L】
1、IP地址由範圍打印出每個ip地址，業務中有太多的ip需要整理，所以批量處理一下，已做到一步完成大規模的重複步驟
# -*-coding:utf-8-*- q = open('jieguo.txt', 'w') f = open('addredd.txt') for line in f.readlines(): line = line.strip() line = line.split('-') val1 = line[0].split('.') val2 = line[1].split('.') title = '%s.%s.%s.' % (val1[0], val1[1], val1[2]) ip_start = val1[3] ip_end = val2[3] # print(title,ip_strat,ip_end) for i in range(int(ip_start), int(ip_end) + 1): # my_dict = ['%s,%s'%ip_strat,ip_end] # print("%s%s" %(title,i)) q.write('%s%s\n' % (title, i))
2、天氣網北京昌平地區的天氣情況
# 天氣網昌平地區爬蟲案例 import requests from lxml import etree class WeatherSpider: def __init__(self): # self.url = "http://www.weather.com.cn/weather/101210404.shtml" self.url = "http://www.weather.com.cn/weather/101010700.shtml" self.headers = { "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.119 Safari/537.36"} def get_url_content(self): return requests.get(self.url, headers=self.headers).content.decode() def get_weather_data(self, html): tmp_html = etree.HTML(html) tomorrow_doc = \ tmp_html.xpath("//div[contains(@class,'con') and contains(@class,'today')]//div[@class='c7d']/ul/li[2]")[0] weather_data = {} weather_data["日期"] = tomorrow_doc.xpath("./h1/text()")[0] weather_data["天氣"] = tomorrow_doc.xpath("./p[@class='wea']/@title")[0] weather_data["最高氣溫"] = tomorrow_doc.xpath("./p[@class='tem']/span/text()")[0] weather_data["最低氣溫"] = tomorrow_doc.xpath("./p[@class='tem']/i/text()")[0] weather_data["空速"] = tomorrow_doc.xpath("./p[@class='win']/i/text()")[0] return weather_data def run(self): # 獲取url請求內容 content_html = self.get_url_content() # 根據url內容獲取天氣資料 data = self.get_weather_data(content_html) # 列印爬取的天氣資料 # data_dict = [] # for i in data: # data_dict.append() # print(data_dict) print(data) if __name__ == '__main__': spider = WeatherSpider() spider.run()
3、合併多個表格到一個sheet裡面
# -*- coding: utf-8 -*- # 將多個Excel檔案合併成一個 import xlrd import xlsxwriter # 開啟一個excel檔案 def open_xls(file): fh = xlrd.open_workbook(file) return fh # 獲取excel中所有的sheet表 def getsheet(fh): return fh.sheets() # 獲取sheet表的行數 def getnrows(fh, sheet): table = fh.sheets()[sheet] return table.nrows # 讀取檔案內容並返回行內容 def getFilect(file, shnum): fh = open_xls(file) table = fh.sheets()[shnum] num = table.nrows for row in range(num): rdata = table.row_values(row) datavalue.append(rdata) return datavalue # 獲取sheet表的個數 def getshnum(fh): x = 0 sh = getsheet(fh) for sheet in sh: x += 1 return x if __name__ == '__main__': # 定義要合併的excel檔案列表 allxls = ['F:/test/excel1.xlsx', 'F:/test/excel2.xlsx'] # 儲存所有讀取的結果 datavalue = [] for fl in allxls: fh = open_xls(fl) x = getshnum(fh) for shnum in range(x): print("正在讀取檔案：" + str(fl) + "的第" + str(shnum) + "個sheet表的內容...") rvalue = getFilect(fl, shnum) # 定義最終合併後生成的新檔案 endfile = 'F:/test/excel3.xlsx' wb1 = xlsxwriter.Workbook(endfile) # 建立一個sheet工作物件 ws = wb1.add_worksheet() for a in range(len(rvalue)): for b in range(len(rvalue[a])): c = rvalue[a][b] ws.write(a, b, c) wb1.close() print("檔案合併完成")
4、對比兩個文字，查詢不同的資訊
# coding=utf-8 import re oldt = [] newt = [] f = open('new', encoding='utf-8') for a in f.readlines(): a = a.strip() newt.append(a) f.close() q = open('old', encoding='utf-8') for b in q.readlines(): b = b.strip() oldt.append(b) q.close() for i in newt: if i in oldt: pass else: print('%s' % i)
5、柱狀圖
import numpy as np import matplotlib.pyplot as plt np.random.seed(19680801) n_bins = 10 x = np.random.randn(1000, 3) fig, axes = plt.subplots(nrows=2, ncols=2) ax0, ax1, ax2, ax3 = axes.flatten() colors = ['red', 'tan', 'lime'] ax0.hist(x, n_bins, density=True, histtype='bar', color=colors, label=colors) ax0.legend(prop={'size': 10}) ax0.set_title('bars with legend') ax1.hist(x, n_bins, density=True, histtype='barstacked') ax1.set_title('stacked bar') ax2.hist(x, histtype='barstacked', rwidth=0.9) ax3.hist(x[:, 0], rwidth=0.9) ax3.set_title('different sample sizes') fig.tight_layout() plt.show()
6、餅圖
# -*- coding:utf-8 -*- import matplotlib.pyplot as plt labels = 'Frogs', 'Hogs', 'Dogs', 'Logs' sizes = [15, 30, 45, 10] explode = (0, 0.1, 0, 0) # only "explode" the 2nd slice (i.e. 'Hogs') fig1, (ax1, ax2) = plt.subplots(2) ax1.pie(sizes, labels=labels, autopct='%1.1f%%', shadow=True) ax1.axis('equal') ax2.pie(sizes, autopct='%1.2f%%', shadow=True, startangle=90, explode=explode, pctdistance=1.12) ax2.axis('equal') ax2.legend(labels=labels, loc='upper right') plt.show()
7、柱狀圖
# -*- coding:utf-8 -*- import numpy as np import matplotlib.pyplot as plt plt.subplot(1, 1, 1) x = np.array([1, 2, 3, 4]) y1 = np.array([8566, 6482, 5335, 7310]) y2 = np.array([4283, 2667, 3655, 3241]) plt.bar(x, y1, width=0.3, label="任務量") plt.bar(x + 0.3, y2, width=0.3, label="完成量") # x+0.3相當於完成量的每個柱子右移0.3 plt.title("全國各分割槽任務量", loc="center") # 新增資料標籤 for a, b in zip(x, y1): plt.text(a, b, b, ha='center', va="bottom", fontsize=12, color="blue") for a, b in zip(x, y2): plt.text(a, b, b, ha='left', va="baseline", fontsize=12, color="r") plt.xlabel('區域') plt.ylabel('任務情況') # 設定x軸刻度值 plt.xticks(x + 0.15, ["東區", "西區", "南區", "北區"]) plt.rcParams['font.sans-serif']=['SimHei'] #顯示中文標籤 plt.rcParams['axes.unicode_minus']=False #這兩行需要手動設定 plt.grid(False) plt.legend() # 顯示圖例 plt.show()
8、折線圖
import numpy as np import random import xlrd import xlwt import matplotlib.pyplot as plt from mpl_toolkits.mplot3d import Axes3D x=[1,2,3,4,5,6,7,8,9,10] y=[3,4,5,6,7,8,9,10,11,12] plt.grid(True,linestyle = "-.") plt.plot(x,y,marker='*',color='green') # 設定數字標籤 for a, b in zip(x, y): plt.text(a, b+2, b, ha='center', va='bottom', fontsize=10) plt.ylim(0,30) plt.xlabel('the value of k') plt.ylabel('number') plt.title('red vs green') plt.show()
9、資料生成Excel
# -*- coding:utf-8 -*- import xlsxwriter # 建立一個excel workbook = xlsxwriter.Workbook("../z周聯絡/chart_line.xlsx") # 建立一個sheet worksheet = workbook.add_worksheet() # worksheet = workbook.add_worksheet("bug_analysis") # 自定義樣式，加粗 bold = workbook.add_format({'bold': 1}) # --------1、準備資料並寫入excel--------------- # 向excel中寫入資料，建立圖示時要用到 headings = ['Number', 'testA', 'testB'] data = [ ['2017-9-1', '2017-9-2', '2017-9-3', '2017-9-4', '2017-9-5', '2017-9-6'], [10, 40, 50, 20, 10, 50], [30, 60, 70, 50, 40, 30], ] # 寫入表頭 worksheet.write_row('A1', headings, bold) # 寫入資料 worksheet.write_column('A2', data[0]) worksheet.write_column('B2', data[1]) worksheet.write_column('C2', data[2]) # --------2、生成圖表並插入到excel--------------- # 建立一個柱狀圖(line chart) chart_col = workbook.add_chart({'type': 'line'}) # 配置第一個系列資料 chart_col.add_series({ # 這裡的sheet1是預設的值，因為我們在新建sheet時沒有指定sheet名 # 如果我們新建sheet時設定了sheet名，這裡就要設定成相應的值 'name': '=Sheet1!$B$1', 'categories': '=Sheet1!$A$2:$A$7', 'values': '=Sheet1!$B$2:$B$7', 'line': {'color': 'red'}, }) # 配置第二個系列資料 chart_col.add_series({ 'name': '=Sheet1!$C$1', 'categories': '=Sheet1!$A$2:$A$7', 'values': '=Sheet1!$C$2:$C$7', 'line': {'color': 'yellow'}, }) # 配置第二個系列資料(用了另一種語法) # chart_col.add_series({ # 'name': ['Sheet1', 0, 2], # 'categories': ['Sheet1', 1, 0, 6, 0], # 'values': ['Sheet1', 1, 2, 6, 2], # 'line': {'color': 'yellow'}, # }) # 設定圖表的title 和 x，y軸資訊 chart_col.set_title({'name': 'The xxx site Bug Analysis'}) chart_col.set_x_axis({'name': 'Test number'}) chart_col.set_y_axis({'name': 'Sample length (mm)'}) # 設定圖表的風格 chart_col.set_style(1) # 把圖表插入到worksheet並設定偏移 worksheet.insert_chart('A10', chart_col, {'x_offset': 25, 'y_offset': 10}) workbook.close()