手把手教你如何玩转一些python小玩意

根据关键字，进行百度搜索爬虫（比如图片）

#!/usr/bin/env python
# -*- coding:utf-8 -*-
# function:爬取百度链接的图片（只需要传入要爬取的关键字即可）
import os
import re
import urllib
import json
import socket
import urllib.request
import urllib.parse
import urllib.error
# 设置超时
import time

timeout = 5
socket.setdefaulttimeout(timeout)


class Crawler:
    # 睡眠时长
    __time_sleep = 0.1
    __amount = 0
    __start_amount = 0
    __counter = 0
    headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:23.0) Gecko/20100101 Firefox/23.0'}

    # 获取图片url内容等
    # t 下载图片时间间隔
    def __init__(self, t=0.1):
        self.time_sleep = t

    # 获取后缀名
    def get_suffix(self, name):
        m = re.search(r'\.[^\.]*$', name)
        if m.group(0) and len(m.group(0)) <= 5:
            return m.group(0)
        else:
            return '.jpeg'

    # 获取referrer，用于生成referrer
    def get_referrer(self, url):
        par = urllib.parse.urlparse(url)
        if par.scheme:
            return par.scheme + '://' + par.netloc
        else:
            return par.netloc

        # 保存图片(路径为当前项目路径下)
    def save_image(self, rsp_data, word):
        if not os.path.exists("./" + word):
            os.mkdir("./" + word)
        # 判断名字是否重复，获取图片长度 (默认的话，我从2000开始计算，因为之前已经有2000张图片了)
        self.__counter = len(os.listdir('./' + word)) + 1 + 3579
        for image_info in rsp_data['imgs']:

            try:
                time.sleep(self.time_sleep)
                suffix = self.get_suffix(image_info['objURL'])
                # 指定UA和referrer，减少403
                refer = self.get_referrer(image_info['objURL'])
                opener = urllib.request.build_opener()
                opener.addheaders = [
                    ('User-agent', 'Mozilla/5.0 (Windows NT 10.0; WOW64; rv:55.0) Gecko/20100101 Firefox/55.0'),
                    ('Referer', refer)
                ]
                urllib.request.install_opener(opener)
                # 保存图片
                urllib.request.urlretrieve(image_info['objURL'], './' + word + '/' + str(self.__counter) + str(suffix))
            except urllib.error.HTTPError as urllib_err:
                print(urllib_err)
                continue
            except Exception as err:
                time.sleep(1)
                print(err)
                print("产生未知错误，放弃保存")
                continue
            else:
                print("图+1,已有" + str(self.__counter) + "张图")
                self.__counter += 1
        return

    # 开始获取
    def get_images(self, word='风景'):
        search = urllib.parse.quote(word)
        # pn int 图片数
        pn = self.__start_amount
        while pn < self.__amount:

            url = 'http://image.baidu.com/search/avatarjson?tn=resultjsonavatarnew&ie=utf-8&word=' + search + '&cg=girl&pn=' + str(
                pn) + '&rn=60&itg=0&z=0&fr=&width=&height=&lm=-1&ic=0&s=0&st=-1&gsm=1e0000001e'
            # 设置header防ban
            try:
                time.sleep(self.time_sleep)
                req = urllib.request.Request(url=url, headers=self.headers)
                page = urllib.request.urlopen(req)
                rsp = page.read().decode('unicode_escape')
            except UnicodeDecodeError as e:
                print(e)
                print('-----UnicodeDecodeErrorurl:', url)
            except urllib.error.URLError as e:
                print(e)
                print("-----urlErrorurl:", url)
            except socket.timeout as e:
                print(e)
                print("-----socket timout:", url)
            else:
                # 解析json
                rsp_data = json.loads(rsp)
                self.save_image(rsp_data, word)
                # 读取下一页
                print("下载下一页")
                pn += 60
            finally:
                page.close()
        print("下载任务结束")
        return

    def start(self, word, spider_page_num=1, start_page=1):
        """
        爬虫入口
        :param word: 抓取的关键词
        :param spider_page_num: 需要抓取数据页数 总抓取图片数量为 页数x60
        :param start_page:起始页数
        :return:
        """
        self.__start_amount = (start_page - 1) * 60
        self.__amount = spider_page_num * 60 + self.__start_amount
        self.get_images(word)


if __name__ == '__main__':
    crawler = Crawler(0.05)  # 抓取延迟为 0.05
    #  抓取关键词为 “美女”，总数为 1 页（即总共 1*60=60 张），开始页码为 2
    # crawler.start('风景', 10, 2)
    # 抓取关键词为 “二次元 美女”，总数为 10 页（即总共 10*60=600 张），起始抓取的页码为 1
    crawler.start('风景图片大全', 100, 1)
    # 抓取关键词为 “帅哥”，总数为 5 页（即总共 5*60=300 张）
    # crawler.start('帅哥', 5)

python绘制折线图

# 绘制折线图
'''
import numpy as np
import matplotlib.pyplot as plt
#X轴，Y轴数据
x = [0,1,2,3,4,5,6]
y = [0.3,0.4,2,5,3,4.5,4]
plt.figure(figsize=(8,4)) # 创建绘图对象
plt.plot(x,y,"b--",linewidth=1)  # 在当前绘图对象绘图（X轴，Y轴，蓝色虚线，线宽度）
plt.xlabel("Time(s)") #X 轴标签
plt.ylabel("Volt") # Y轴标签
plt.title("Line plot") # 图标题
plt.show() #显示图
plt.savefig("line.jpg") # 保存图
'''
import matplotlib.pyplot as plt
# 支持中文
from pylab import *
mpl.rcParams['font.sans-serif'] = ['SimHei']

names = ['BR', 'CLR', 'ML-LOC', 'RAKEL', 'V-GLLCBN']
x = range(len(names))
y = [0.1326, 0.1531, 0.1627, 0.1564, 0.2062]
y1 = [3.8942/9, 4.2231/9, 4.2483/9, 4.2411/9, 4.7556/9]
y2 = [0.2513, 0.2801, 0.2832, 0.2792, 0.2905]
y3 = [0.6412, 0.6321, 0.6243, 0.6288, 0.6172]
y4 = [0.4681, 0.604, 0.6910, 0.6332, 0.9704]
# plt.plot(x, y, 'ro-')
# plt.plot(x, y1, 'bo-')
# pl.xlim(-1, 11)  # 限定横轴的范围
# pl.ylim(-1, 110)  # 限定纵轴的范围
plt.plot(x, y, marker='o', mec='r', mfc='w', label=u'汉明损失曲线图')
plt.plot(x, y1, marker='o', ms=10, label=u'覆盖率曲线图')
plt.plot(x, y2, marker='o', ms=10, label=u'排名损失曲线图')
plt.plot(x, y3, marker='o', ms=10, label=u'平均精度曲线图')
plt.plot(x, y4, marker='o', ms=10, label=u'平均预测时间曲线图')
# 让图例生效
plt.legend()
plt.xticks(x, names, rotation=0)
plt.margins(0.2)
plt.subplots_adjust(bottom=0.15)
# X轴标签
plt.xlabel(u"对比算法")
# Y轴标签
plt.ylabel("数值")
# 标题
plt.title("随机标记30%数据集作为训练集的不同算法性能比较")
# 显示图片
plt.show()