diff --git a/疫情数据爬取demo.py b/疫情数据爬取demo.py new file mode 100644 index 0000000..adcb379 --- /dev/null +++ b/疫情数据爬取demo.py @@ -0,0 +1,45 @@ +import requests +import csv +from lxml import etree +import pandas as pd +import matplotlib.pyplot as plt + +url = "https://www.bitpush.news/covid19/" +headers = { + "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.82 Safari/537.36", +} # 头部,伪装浏览器访问,防反爬虫。 +response = requests.get(url=url, headers=headers) # request.get请求网址 +html = response.text # 网址源代码 +parse = etree.HTMLParser(encoding='utf-8') # 创建HTML解析,格式为"utf-8" +doc = etree.HTML(html) + +# xpath解析网站格式 +country = doc.xpath('/html/body/div/div/div[2]/div[2]/div/div/div/div/div[1]/table/tbody/tr/td/span/text()') +person = doc.xpath('/html/body/div/div/div[2]/div[2]/div/div/div/div/div[1]/table/tbody/tr/td[2]/text()') +person = [x.replace(",", "") for x in person] # 由于确诊人数中有逗号,我们使用列表推导式删除 +death = doc.xpath('/html/body/div/div/div[2]/div[2]/div/div/div/div/div[1]/table/tbody/tr/td[3]/text()') +death = [x.replace(",", "") for x in death] # 同上 + +message = list(zip(country, person, death)) # 打包数据之后将其转换成列表 +# csv文件保存 +with open("content.csv", "w", encoding="utf-8", newline="") as f: # newline=""防止空行 + w = csv.writer(f) + w.writerows(message) +df = pd.read_csv("content.csv", names=["country", "person", "death"]) +df1 = df.head(15) # df的前15项 + +# 绘制条形图 +# 设置中文显示 +plt.rcParams['font.sans-serif'] = ['SimHei'] +plt.rcParams['figure.figsize'] = (10, 5) # 设置figure_size尺寸 +# x轴坐标 +x = df1["country"].values +# y轴坐标 +y = df1["person"].values +# 绘制柱状图 +plt.bar(x, y) +# 设置x轴名称 +plt.xlabel("城市", fontsize=14) +# 设置x轴名称 +plt.ylabel("确诊人数", fontsize=14) +plt.show() # 显示条形图