豆瓣即将上映电影top5条形图、柱状图

from xpinyin import Pinyin
import requests
from lxml import html
from matplotlib import pyplot as plt
#设置支持中文字体
plt.rcParams["font.sans-serif"] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
import pandas as pd
# pip install xpinyin
def spider(city):
    # splitter 是分隔使用符号,默认是 '-'
    city_pinyin = Pinyin().get_pinyin(city,splitter='')
    url = 'https://movie.douban.com/cinema/later/{}/'.format(city_pinyin)
    print('您要爬取的目标站点是', url)
    print('爬虫进行中，请稍后.........')
    # 请求头信息， 目的是伪装成浏览器进行爬虫
    headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:70.0) Gecko/20100101 Firefox/70.0'}
    # 获取网页的源代码
    response = requests.get(url, headers = headers)
    html_data = response.text
    # print(html_data)
    # 提取我们想要的内容
    selector = html.fromstring(html_data)
    div_list = selector.xpath('//div[@id="showing-soon"]/div')
    print('您好，{}市共查询到{}部即将上映的电影'.format(city, len(div_list)))
    movie_info_list = []
    for div in div_list:
        # 获取电影名字
        movie_name = div.xpath('div[1]/h3/a/text()')
        # if len(movie_name)==0:
        #     movie_name = '没有查询到数据'
        # else:
        #     movie_name = movie_name[0]
        movie_name = '没有查询到数据' if len(movie_name) == 0 else movie_name[0]
        # print(movie_name)



        # 想看人数
        want_see = div.xpath('div[1]/ul/li[4]/span/text()')[0]
        want_see = int(want_see.replace('人想看', ''))
        # print(want_see)

        movie_info_list.append({
            "movie_name":movie_name,
            "want_see":want_see,
            })


    movie_info_list.sort(key=lambda x: x['want_see'],reverse=True)
    a=[]
    b=[]
    for movie in movie_info_list:
        movie_name=movie['movie_name']
        want_see=movie['want_see']
        a.append(movie_name)
        print(a)
        b.append(want_see)
    x=[]
    y=[]
    for i in range(5):
        x.append(a[i])
        y.append(b[i])
    # plt.barh(x, y)
    # plt.ylabel('电影名称')
    # plt.xlabel('想看人数')
    # plt.show()

    # labels = ['电影：{}'.format(i) for i in range(1, 9)]
    colors = ['red', 'blue', 'green', 'yellow', 'pink']
    # 每一个元素距中心点的距离 可选值 0~1
    explode = [0, 0, 0, 0, 0.2]
    plt.pie(x=y,
            labels=x,
            colors=colors,
            shadow=True,
            startangle=90,
            explode=explode,
            autopct='%1.1f%%'
            )
    plt.axis('equal')  # 设置成标准圆形
    plt.legend(loc=2)  # 指定为2象限
    plt.title('电影')
    plt.show()


city = 'shenayng'
# 调用函数
spider(city)

电影条形图.png

电影饼状图.png

三国人物top10条形图、柱状图

import jieba
from wordcloud import WordCloud
import imageio
from matplotlib import pyplot as plt

# 设置支持中文字体
plt.rcParams["font.sans-serif"] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
#读取文件
# mask = imageio.imread('china.jpg')
with open('./threekingdom.txt','r',encoding='UTF-8') as f:
    data = f.read()

    #分词
    words_list = jieba.lcut(data)
    print(words_list)

    #构建一个集合，定义无关词
    excludes = {"将军","却说","二人","不可","荆州","不能","如此","丞相","商议",
                "如何","主公","军士","军马","左右","次日","引兵","大喜","天下","东吴","于是","今日"
        ,"不敢","魏兵","陛下","都督","人马","不知","孔明曰","玄德曰","云长","刘备"}

    #构建一个容器，存储我们要的数据
    #{"夏侯渊"：34，"害怕"：33....}
    counts = {}
    #遍历word_list 目标是筛选出人名
    for word in words_list:
        #print(word)
        if len(word)<= 1:
        #过滤无关词语即可
            continue
        else:
        #向字典counts里更新值
        #counts[word]=字典里原来该次出现的次数 + 1
        # counts[word] = counts[word] + 1
        # counts["正文"] = counts["正文"] + 1
            counts[word] = counts.get(word,0) + 1
    # print(counts)

    #将指向同一个人的词进行合并
    counts['孔明'] = counts['孔明'] + counts['孔明曰']
    counts['玄德'] = counts['玄德'] + counts['玄德曰'] + counts['刘备']
    counts['关公'] = counts['关公'] + counts['云长']
    #删无关词
    for word in excludes:
        del counts[word]

    #排序筛选
    #吧字典转化成列表[(),()] [{},{}]
    items = list(counts.items())
    #按照词频次数进行排序
    items.sort(key=lambda x:x[1],reverse=True)

    #显示出现词语前10的词
    #role_list = []
    # role_list = ["孔明","孔明"，。。。]
    role_list = []
    x = []
    y = []
    for i in range(10):
        #将返回的数据拆开，拆包
        #print(items[i])
        role,count = items[i]
        print(role,count)
    #     #i临时文件如果不需要的话可以写成_
    #     #优点是让读代码的人能够清晰的知道此处不需要使用i
    #     for _ in range(count):
    #         role_list.append(role)
    # print(role_list)

        x.append(role)
        y.append(count)
    # plt.bar(x,y)
    # plt.grid()#格子
    # plt.xlabel('人物')
    # plt.ylabel('次数')
    # plt.show()

    colors = ['red', 'blue', 'green', 'yellow', 'pink', 'purple', 'gray', 'orange']
    # 每一个元素距中心点的距离 可选值 0~1
    explode = [0, 0, 0, 0, 0.2,0,0,0,0,0]
    plt.pie(x=y,
            labels=x,
            colors=colors,
            shadow=True,
            startangle=90,
            explode=explode,
            autopct='%1.1f%%'
            )
    plt.axis('equal')  # 设置成标准圆形
    plt.legend(loc=2)  # 指定为2象限
    plt.title('三国人物')
    plt.show()
#课上老师版三国人物

三国人物条形图.png

三国人物饼状图.png

import jieba
from wordcloud import WordCloud
import imageio
from matplotlib import pyplot as plt
plt.rcParams["font.sans-serif"] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
# 读取文件
# mask = imageio.imread('china.jpg')
with open('./threekingdom.txt', 'r', encoding='UTF-8') as f:
    data = f.read()

    # 分词
    words_list = jieba.lcut(data)
    print(words_list)

    #  构建一个集合，定义无关词
    excludes = {"将军","却说","二人","不可","荆州","不能","如此","丞相",
                "商议","如何","主公","军士","军马","左右","次日","引兵",
                "大喜","天下","东吴","于是","今日","不敢","魏兵","陛下",
                "都督","人马","不知","孔明曰","玄德曰","玄德","云长"}
                #,"","","","","","","","","","",

    # 构建一个容器，存储我们要的数据
    # {"夏侯渊":34,"害怕":33......}\
    counts = {}
    # 遍历wordlist 目标是筛选出人名
    for word in words_list:
        # print(word)
        if len(word) <= 1:
            # 过滤无关词语即可
            continue
        else:
            # 向字典counts里更新值
            # counts[word] = 字典中原来该词出现的次数 + 1

            # counts[word] = counts[word] + 1
            # counts["正文"] = counts["正文"] +1
            counts[word] = counts.get(word, 0) + 1
    # print(counts)

    # 指向同一个词的人进行合并
    counts['孔明'] = counts['孔明'] + counts['孔明曰']
    counts['刘备'] = counts['玄德'] + counts['玄德曰'] + counts['刘备']
    counts['关公'] = counts['关公'] + counts['云长']

    # 删除无关的词语
    for word in excludes:
        del counts[word]
    # 排序筛选
    # 吧字典转化成列表 [(),()]   [{},{}]
    items = list(counts.items())
    # 按照词频次数进行排序
    items.sort(key=lambda x:x[1],reverse=True)

    # 显示出现词语前10的词

    # role_list = ["孔明","孔明","孔明","","","",]
    role_list = []
    role_l = [] # x
    role_c = [] # y
    for i in range(10):
        # 将返回的数据拆开 ,拆包
        # print(items[i])
        role, count = items[i]
        print(role, count)
        role_l.append(role)
        role_c.append(count)



        # i 临时变量如果不需要的话可以写成 _
        # 优点是让读代码的人能够清晰的知道此处不需要使用 i
        for _ in range(count):
            role_list.append(role)
    print(role_l,role_c)

    plt.bar(role_l, role_c)
    plt.show()

    plt.pie(role_c,labels=role_l,autopct='%1.1f%%')
    plt.show()
    # print(role_list)
    # # 将列表变成字符串
    # # text = "孔明 孔明 孔明 孔明......刘备 刘备 刘备 曹操 曹操 曹操"
    # text = " ".join(role_list)
    # print(text)
    # 展示

    # WordCloud(
    #     background_color='white',
    #     mask=mask,
    #     font_path='msyh.ttc',
    #     # 是否包含两个词的搭配  设置为false即可
    #     collocations=False
    #
    # ).generate(text).to_file('三国人物前十展示.png')

老师版电影

from xpinyin import Pinyin
import requests
from lxml import html
from matplotlib import pyplot as plt
#设置支持中文字体
plt.rcParams["font.sans-serif"] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
import pandas as pd
# pip install xpinyin
def spider(city):
    # splitter 是分隔使用符号,默认是 '-'
    city_pinyin = Pinyin().get_pinyin(city,splitter='')
    url = 'https://movie.douban.com/cinema/later/{}/'.format(city_pinyin)
    print('您要爬取的目标站点是', url)
    print('爬虫进行中，请稍后.........')
    # 请求头信息， 目的是伪装成浏览器进行爬虫
    headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:70.0) Gecko/20100101 Firefox/70.0'}
    # 获取网页的源代码
    response = requests.get(url, headers = headers)
    html_data = response.text
    # print(html_data)
    # 提取我们想要的内容
    selector = html.fromstring(html_data)
    div_list = selector.xpath('//div[@id="showing-soon"]/div')
    print('您好，{}市共查询到{}部即将上映的电影'.format(city, len(div_list)))
    movie_info_list = []
    for div in div_list:
        # 获取电影名字
        movie_name = div.xpath('div[1]/h3/a/text()')
        # if len(movie_name)==0:
        #     movie_name = '没有查询到数据'
        # else:
        #     movie_name = movie_name[0]
        movie_name = '没有查询到数据' if len(movie_name) == 0 else movie_name[0]
        # print(movie_name)
        country = div.xpath('div[1]/ul/li[3]/text()')[0]

        # 想看人数
        want_see = div.xpath('div[1]/ul/li[4]/span/text()')[0]
        want_see = int(want_see.replace('人想看', ''))
        # print(want_see)

        movie_info_list.append({
            "movie_name":movie_name,
            "want_see":want_see,
            "country": country,
            })


    movie_info_list.sort(key=lambda x: x['want_see'],reverse=True)
    #绘图
    movie_name_top5=[movie['movie_name'] for movie in movie_info_list[:5]]
    want_see_top5=[movie['want_see'] for movie in movie_info_list[:5]]
    plt.barh(movie_name_top5,want_see_top5)
    plt.ylabel('电影名称')
    plt.xlabel('想看人数')
    plt.show()

    #国家占比
    country_list = [movie['country'] for movie in movie_info_list]
    counts ={}
    for x in country_list:
        counts[x] = counts.get(x,0) + 1
    country_x=list(counts.values())
    labels=list(counts.keys())
    colors = ['red', 'blue', 'green', 'yellow', 'pink']

    plt.pie(x=country_x,
            labels=labels,
            colors=colors,
            shadow=True,
            startangle=90,
            autopct='%1.1f%%'
            )
    plt.axis('equal')  # 设置成标准圆形
    plt.legend(loc=2)  # 指定为2象限
    plt.title('电影')
    plt.show()
city = 'shenayng'
# 调用函数
spider(city)