Python高级应用程序设计任务

import matplotlib.pyplot as plt

plt.rcParams[‘font.sans-serif‘]=[‘SimHei‘] #用来正常显示中文标签
plt.rcParams[‘axes.unicode_minus‘]=False #用来正常显示负号

Type = [‘108~138‘, ‘59.9~119.5‘, ‘2470~7500‘,‘119‘, ‘108~158‘,‘61~183‘,‘2720~7320‘,‘100~2550‘,‘518~618‘]
Data = [130, 75, 60, 12,3,69,13,45,2]
#cols = [‘r‘,‘g‘,‘y‘,‘coral‘]
#绘制饼图
plt.pie(Data ,labels=Type, autopct=‘%1.1f%%‘)
#设置显示图像为圆形
plt.axis(‘equal‘)
plt.title(‘各个价格段的销售比重‘)
plt.show()

import matplotlib.pyplot as plt
plt.rcParams[‘font.family‘] = [‘sans-serif‘]
plt.rcParams[‘font.sans-serif‘] = [‘SimHei‘]

plt.figure(figsize=(10,6))
# 价格
prices = [‘108~138‘, ‘59.9~119.5‘, ‘2470~7500‘,‘119‘, ‘108~158‘,‘61~183‘,‘2720~7320‘,‘100~2550‘,‘518~618‘]
# 月售，选择，评分
undergraduate_enrollment = [130, 75, 60, 12,3,69,13,45,2]
secondary_vocational_enrollment = [310, 26,373,764,270,66,62,36,72]
high_school_enrollment = [4.9,4.7,5.0,4.9,5.0,4.7,5.0,4.5,4.0]
x = list(range(len(undergraduate_enrollment)))

#设置间距
total_width, n = 0.8, 3
width = total_width / n
#在偏移间距位置绘制柱状图1
for i in range(len(x)):
    x[i] -= width
plt.bar(x, undergraduate_enrollment, width=width, label=‘月售‘, fc=‘teal‘)
# 设置数字标签
for a, b in zip(x, undergraduate_enrollment):
    plt.text(a, b, b, ha=‘center‘, va=‘bottom‘, fontsize=10)
             
#在偏移间距位置绘制柱状图2
for i in range(len(x)):
    x[i] += width
plt.bar(x, secondary_vocational_enrollment, width=width, label=‘选择‘, tick_label=prices, fc=‘darkorange‘)
# 设置数字标签
for a, b in zip(x, secondary_vocational_enrollment):
    plt.text(a, b, b, ha=‘center‘, va=‘bottom‘, fontsize=10)
    
#在偏移间距位置绘制柱状图3
for i in range(len(x)):
    x[i] += width
plt.bar(x, high_school_enrollment, width=width, label=‘评分‘, fc=‘lightcoral‘)
# 设置数字标签
for a, b in zip(x, high_school_enrollment):
    plt.text(a, b, b, ha=‘center‘, va=‘bottom‘, fontsize=10)
    
plt.title("不同价位的月售、选择及各自的评分情况统计")
plt.ylabel("数量")
plt.legend(loc=‘lower right‘)

plt.show()

# 导入bs4,requests,pandas模块
import requests
from bs4 import BeautifulSoup
import pandas as pd

def resourceHtml(url):
    # 判断爬取 是否出错
    try:
        # 使用get方式爬取页面,添加头部伪装浏览器
        r = requests.get(url, headers={‘user-agent‘: ‘Mozilla/5.0‘})

        r.raise_for_status()
        # 设置编码格式
        r.encoding = r.apparent_encoding
        # 返回源码
        return r.text
    except:
        return "源码获取失败"


def hemlparser(item, resourcetext,urls):

    soup = BeautifulSoup(resourcetext, "html.parser")

    ul = soup.select("div.exe-packg02>ul>li")
    for li in ul:
        
        h3 = li.find("h3")  # h3标签
        
        h3text = h3.text.strip()  # 标题
        
        href = h3.find_all("a", "_j_search_link")[0].attrs["href"]  # 地址
        
        p = li.find_all("p", "seg-desc")[0].text.strip() #内容

        solenum = li.find_all("li")[0].text.strip() # 已售数量

        price = li.select("li>a._j_search_link")[0].text.strip() # 价格

        item.append([h3text, href, p, solenum, price]) 

        urls.append(href) # 链接集合

    # 数据持久化
    S = pd.ExcelWriter("JingDianList.xlsx")

    pf = pd.DataFrame( item, columns=["h3text", "href", "p", "solenum", "price"])

    pf.to_excel(S)
    S.save()


def hemlparser2(text):
    soup = BeautifulSoup(text, "html.parser")
   
    ID = soup.select("span.sales-id")[0].text.strip()  # id号码
    
    h1 = soup.find("h1").text.strip()
    
    prices = soup.select("strong")[0].text.strip()  # 消费价格区间
   
    sold = soup.select("li.item-sold")[0].text.strip()  # 月销售数量
    
    Collection = soup.select("div.clearfix>a>span")[0].text.strip()  # 收藏数量
    if soup.select("span.ssi"):
        ssi = soup.select("span.ssi")[0].text.strip()
    else:
        ssi =‘‘
    return [ID, h1, prices, sold, Collection, ssi]



if __name__ == "__main__":
    item = []
    urls = []
    List = []
    # 泉州地区链接
    url = "http://www.mafengwo.cn/search/q.php?t=sales&q=%E6%B3%89%E5%B7%9E"
    resourcetext = resourceHtml(url)
    # print(resourcetext)

    hemlparser(item, resourcetext, urls) # 保存列表数据
    # print(item)
    # print(urls)
    
    for url in urls:
        text = resourceHtml(url)
        List.append(hemlparser2(text))

    # 数据持久化
    S = pd.ExcelWriter("JingDian.xlsx")
    pf = pd.DataFrame(List, columns=[
                      "ID", "h1", "prices", "sold", "Collection", "ssi"])
    pf.to_excel(S)     # 保存详细数据
    S.save()