Python爬虫——数据可视化
导入需要的第三方库
import matplotlib.pyplot as plt
import seaborn as sns
import pandas as pd
import requests
import urllib3
import matplotlib as mpl
设置可以显示中文和改变字体
mpl.rcParams['font.sans-serif'] = ['KaiTi']
mpl.rcParams['font.serif'] = ['KaiTi']
mpl.rcParams['axes.unicode_minus'] = False
sns.set_style("darkgrid", {"font.sans-serif": ['KaiTi', 'Arial']})
爬取数据:此方法只适用于表格
urllib3.disable_warnings()
url = "http://www.stats.gov.cn/ztjc/zdtjgz/zgrkpc/dqcrkpc/ggl/202105/t20210519_1817699.html"
response = requests.get(url, verify=False)
response.encoding = response.apparent_encoding
html = response.text
data = pd.read_html(html, header=0)[1]
print(data)
提取数据中的某一列
city = list(data["地区"])#提取数据中名为“地区”的