2019-07-31 东软实训 python第四天

Python

1. '123{}678'.format('45')
2. from lxml import html
   xpath_dom = html.fromString()
   ul_list = selector.xpath('//div[@id="search_nature_rg"]/ul/li')
3. 三目运算
   trueStatement if condition else falseStatement
4. pandas
   存储为csv文件：
   df = pd.DataFrame(book_list)
   df.to_csv('dangdang.csv')
5. iris.data[:,:2]
   切片，直接切列

import requests
from lxml import html
from wordcloud import WordCloud
from matplotlib import pyplot as plt
plt.rcParams["font.sans-serif"] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
def spider_movie(address):
    movie_list = []
    url = 'https://movie.douban.com/cinema/later/{}'.format(address)
    headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.142 Safari/537.36"}
    resp = requests.get(url, headers=headers)
    html_data = resp.text
    selector = html.fromstring(html_data)
    div_list = selector.xpath('//div[@id="showing-soon"]/div')
    print('共有{}部电影即将上映'.format(len(div_list)))

    for div in div_list:
        # 电影名
        name = div.xpath('./div[@class="intro"]/h3/a/text()')[0]
        # print(name)

        # 上映日期
        day = div.xpath('./div[@class="intro"]/ul/li/text()')[0]
        # print(day)

        # 类型
        type = div.xpath('./div[@class="intro"]/ul/li/text()')[1]
        # print(type)

        # 上映国家
        country = div.xpath('./div[@class="intro"]/ul/li/text()')[2]
        # print(country)

        # 想看人数
        div_three = div.xpath('./div[@class="intro"]/ul/li')[3]
        number = div_three.xpath('./span/text()')[0]
        number = str(number).replace('人想看', '')
        number = int(number)
        # print(number)

        # 添加电影信息
        movie_list.append({
            'name':name,
            'day':day,
            'type':type,
            'country':country,
            'number':number
        })

    # 排序
    movie_list.sort(key=lambda x:x['number'], reverse=True)

    # 遍历
    for movie in movie_list:
        print(movie)

    # 绘制即将上映电影最想看前五人数占比图
    top5_movie = [movie_list[i] for i in range(4)]
    labels = [x['name'] for x in top5_movie]
    # print(labels)
    counts = [x['number'] for x in top5_movie]
    # print(counts)
    colors = ['red', 'purple', 'yellow', 'gray', 'green']
    plt.pie(counts, labels=labels, autopct='%1.2f%%', colors=colors)
    plt.legend(loc=2)
    plt.axis('equal')
    plt.show()

     # 绘制即将上映电影国家的占比图
    total = [x['country'] for x in movie_list]
    text = ''.join(total)
    print(text)
    words_list = jieba.lcut(text)
    print(words_list)
    counts = {}
    excludes ={"大陆"}
    for word in words_list:
        if len(word) <= 1:
            continue
        else:
            counts[word] = counts.get(word, 0) + 1
    print(counts)
    for word in excludes:
        del counts[word]
    items = list(counts.items())
    print(items)
    items.sort(key=lambda x: x[1], reverse=True)
    print(items)
    numm = [] # 数量
    labels = [] # 国家
    for i in range(len(items)):
        x, y = items[i]
        numm.append(y)
        if(x == "中国"):
            x = "中国大陆"
        labels.append(x)
    plt.pie(numm, labels=labels, autopct='%1.2f%%')
    plt.legend(loc=2)
    plt.axis('equal')
    plt.show()

    # top5.png
    text = ' '.join(labels)
    WordCloud(
        font_path='MSYH.TTC',
        background_color='white',
        width=800,
        height=600,
        collocations=False
    ).generate(text).to_file('top5.png')

spider_movie('chongqing')