学习Python的第五天

豆瓣TOP250爬虫

import requests
from lxml import etree
from matplotlib import pyplot as plt
plt.rcParams["font.sans-serif"] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
def spider_douban_top250():
    movie_list_info = []
    header = {"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"}

    for i in range(0, 250, 25):
        url = 'https://movie.douban.com/top250?start={}&filter='.format(i)
        # 获取bytes类型响应
        data = requests.get(url, headers=header).content
        html = etree.HTML(data)
        ol_list = html.xpath('//div[@id="content"]//div[@class="article"]/ol/li')
        for movie in ol_list:

            # 影片序号
            # serial_number
            serial_number = movie.xpath('./div[@class="item"]/div[@class="pic"]/em/text()')[0]
            # print('电影序号：', serial_number)
            # 电影的名字
            # movie_name
            movie_name = movie.xpath('./div[@class="item"]/div[@class="info"]//a/span[1]/text()')[0]
            # print('电影名字：', movie_name)
            # 电影的介绍
            # movie_introduce
            movie_introduce = movie.xpath('./div[@class="item"]/div[@class="info"]/div[@class="bd"]/p[1]/text()')[0].strip()
            movie_introduce = str(movie_introduce.replace('\xa0', ' '))
            # print('电影介绍：', movie_introduce)

            # 电影的星级
            # movie_star
            movie_star = movie.xpath('./div[@class="item"]/div[@class="info"]/div[@class="bd"]/div/span[2]/text()')[0]
            # print('电影的星级：', movie_star)

            # 电影的评价
            # movie_evaluate
            movie_evaluate = movie.xpath('./div[@class="item"]/div[@class="info"]/div[@class="bd"]/div/span[4]/text()')
            movie_evaluate = movie_evaluate[0].replace('人评价', '')
            # print('电影的评价：', movie_evaluate)

            # 电影的描述
            # movie_describe
            movie_describe = movie.xpath('./div[@class="item"]/div[@class="info"]/div[@class="bd"]/p[2]/span[1]/text()')
            # print('电影的描述：', movie_describe)

            # 电影的图片
            # movie_image

            # 电影封面的地址
            # movie_image_url
            movie_image_url = movie.xpath('./div[@class="item"]/div[@class="pic"]/a/img/@src')[0]
            # print('电影封面的地址：', movie_image_url)

            movie_list_info.append({
                'serial_number': serial_number,
                'movie_name': movie_name,
                'movie_introduce': movie_introduce,
                'star': movie_star,
                'evaluate': movie_evaluate,
                'describe': movie_describe,
                'movie_image_url': movie_image_url
            })
       for movie in movie_list_info:
        print(movie)

       # 下载图片
    for movie in movie_list_info:
        url = movie['movie_image_url']
        resp = requests.get(url)
        if resp.status_code == 200:
            img_name = '0000000{}.jpg'.format(movie['serial_number'])
            with open('./img/{}'.format(img_name), 'wb') as f:
                f.write(resp.content)
spider_douban_top250()

绘制影片导演top10

 intro_list = []
    counts = {}
    for ductor in movie_list_info:
        ductor = ductor['movie_introduce'].split(' ')
        counts[ductor[1]] = counts.get(ductor[1], 0) + 1
    print(ductor)
    print(counts)
    # 排序 [(), ()]
    ductor_items = list(counts.items())
    ductor_items.sort(key=lambda x: x[1], reverse=True)
    print(ductor_items)
    nations = []
    cishu = []
    for i in range(10):
        # 序列解包
        ductors, count = ductor_items[i]
        # print(role, count)
        nations.append(ductors)
        cishu.append(count)

    explode = [0.1, 0, 0, 0, 0, 0, 0, 0, 0, 0]
    colors = ['red', 'purple', 'blue', 'yellow']
    plt.pie(cishu, explode=explode, colors=colors, shadow=True, labels=nations, autopct='%1.1f%%')
    plt.legend(loc=2)  # 图例位置
    plt.axis('equal')
    plt.show()

图片的下载

# 图片的下载
import requests
url = 'http://g.hiphotos.baidu.com/image/pic/item/5366d0160924ab18014cefd83bfae6cd7a890b82.jpg'
response = requests.get(url)
# 获取bytes类型的相应
data = response.content
with open('风景.png', 'wb') as f:
    f.write(data)