豆瓣TOP250

####绘制饼图

from random import randint
from matplotlib import pyplot as plt
plt.rcParams["font.sans-serif"] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
# x是饼图中各个元素的值
x = [randint(3000, 15000) for _ in range(8)]
# 每个元素的标签
labels = ['员工{}'.format(i) for i in range(1, 9)]
colors = ['red', 'blue', 'green', 'yellow','pink','purple','gray','orange']
# 每一个元素距离中心点的距离 可选值 0~1
explode = [0, 0, 0, 0, 0, 0, 0, 0.2]
plt.pie(x=x,
        labels=labels,
        colors=colors,
        shadow=True,
        startangle=90,#开始的角度
        explode=explode,
        autopct='%1.1f%%' # 显示百分比
        )
plt.axis('equal') # 设置成标准圆形
plt.legend(loc=3)# 指定为 2象限
plt.title('某大型公司员工工资占比')
plt.show()

运行结果：

切片：

l1 = [{'name':'张三','grade':56},
      {'name':'李四','grade':90},
      {'name':'王五','grade':6},
      {'name': '赵六', 'grade': 33},
      {'name': '田七', 'grade': 67},
      {'name': '老八', 'grade': 12}
      ]
print(l1[:3])

####豆瓣Top250:

import requests
from lxml import html
import pandas as pd
url ='https://movie.douban.com/top250'
headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:70.0) Gecko/20100101 Firefox/70.0'}
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)
ol_list = selector.xpath('//div[@class="article"]/ol/li')
print('您好，共查询到{}部电影'.format( len(ol_list)))
for li in ol_list:
    # 爬取序号
    movie_number = li.xpath('div[@class="item"]/div[@class="pic"]/em[@class=""]/text()')
    movie_number = '没有查询到数据' if len(movie_number) == 0 else movie_number[0]
    # 爬取电影名
    movie_name = li.xpath('div/div[2]/div[@class="hd"]/a/span/text()')
    movie_name = '没有查询到数据' if len(movie_name) == 0 else movie_name[0]
    # 爬取详细链接
    movie_link = li.xpath('div/div[2]/div[@class="hd"]/a/@href')
    movie_link = '没有查询到数据' if len(movie_link) == 0 else movie_link[0]
    # 爬取详细信息
    movie_conmunicate = li.xpath('div[@class="item"]/div[@class="info"]/div[@class="bd"]/p[@class=""]/text()')
    movie_conmunicate = '没有查询到数据' if len(movie_conmunicate) == 0 else movie_conmunicate[0]
    # 爬取评级
    movie_level = li.xpath('div[@class="item"]/div[@class="info"]/div[@class="bd"]/div[@class="star"]/span[@class="rating_num"]/text()')
    movie_level = '没有查询到数据' if len(movie_level) == 0 else movie_level[0]
    # 爬取评价人数
    movie_num = li.xpath('div[@class="item"]/div[@class="info"]/div[@class="bd"]/div[@class="star"]/span[4]/text()')
    movie_num = '没有查询到数据' if len(movie_num) == 0 else movie_num[0]
    # 爬取看点
    movie_watch = li.xpath('div[@class="item"]/div[@class="info"]/div[@class="bd"]/p[@class="quote"]/span/text()')
    movie_watch = '没有查询到数据' if len(movie_watch) == 0 else movie_watch[0]

    movie_info_list = []
    movie_info_list.append({
        "movie_number":movie_number,
        "movie_name":movie_name,
        "movie_link":movie_link,
        "movie_conmunicate":movie_conmunicate,
        "movie_level":movie_level,
        "movie_num":movie_num,
        "movie_watch":movie_watch,})
for movie in movie_info_list:
    print(movie)
    with open('./top_img/{}.jpg'.format(movie['doubai_img']), 'wb') as f:
         f.write(requests.get(movie['movie_img'], headers=headers).content)
pd.DataFrame(movie_info_list).to_csv()