|
|
|
|
|
#####请在以下代码块填写爬虫代码
|
|
|
|
|
|
import requests
|
|
|
|
|
|
url = "https://www.bitpush.news/covid19/"# 请求的url
|
|
|
|
|
|
headers = {"user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari/537.36"}# 设置请求头信息
|
|
|
|
|
|
response = requests.get(url, headers=headers)# 使用reqeusts模快发起 GET 请求
|
|
|
|
|
|
html = response.text# 获取请求的返回结果
|
|
|
|
|
|
from lxml import etree# 导入 lxml
|
|
|
|
|
|
doc = etree.HTML(html)
|
|
|
|
|
|
#XPath 使用路径表达式来选取 XML 文档中的节点或节点集。节点是通过沿着路径 (path) 或者步 (steps) 来选取的。
|
|
|
|
|
|
country = doc.xpath('//div[@class="table_container"]//tbody/tr/td/span/text()')
|
|
|
|
|
|
person = doc.xpath('//div[@class="table_container"]//tbody/tr/td[2]/text()')
|
|
|
|
|
|
person = [x.replace(",", "") for x in person]
|
|
|
|
|
|
death = doc.xpath('//div[@class="table_container"]//tbody/tr/td[3]/text()')
|
|
|
|
|
|
death = [x.replace(",", "") for x in death]
|
|
|
|
|
|
message = list(zip(country, person, death))# 打包数据之后将其转换成列表
|
|
|
|
|
|
import csv# 导入python中的内置模块csv，将列表写入文件
|
|
|
|
|
|
with open("content.csv", "w") as f:
|
|
|
|
|
|
w = csv.writer(f)
|
|
|
|
|
|
w.writerows(message)
|
|
|
|
|
|
import pandas as pd#导入pandas库，读取数据
|
|
|
|
|
|
df = pd.read_csv("content.csv", names=["country", "person", "death"],encoding='gbk')
|
|
|
|
|
|
df1 = df.drop(0).head(10)# 由于第一行是全球的数据总和，我们先将其删除，我们显示10个国家在图上
|
|
|
|
|
|
import matplotlib.pyplot as plt#导入plt库，作图
|
|
|
|
|
|
plt.rcParams['font.sans-serif'] = ['SimHei']# 设置中文显示
|
|
|
|
|
|
plt.rcParams['figure.figsize'] = (10, 5) # 设置figure_size尺寸
|
|
|
|
|
|
x = df1["country"].values
|
|
|
|
|
|
y = df1["death"].values
|
|
|
|
|
|
plt.bar(x, y)
|
|
|
|
|
|
plt.xlabel("国家",fontsize=14)
|
|
|
|
|
|
plt.ylabel("死亡人数",fontsize=14)
|
|
|
|
|
|
plt.show()
|
