ADD file via upload

crawlbug(patrick).py

@@ -0,0 +1,54 @@
+
+import requests
+from lxml import etree
+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/95.0.4638.69 Safari/537.36"
+}
+response = requests.get(url, headers=headers)
+html = response.text
+#print(html)
+parse = etree.HTMLParser(encoding='utf-8') 
+doc = etree.HTML(html)
+# states
+zhou = doc.xpath('//div[@class="table_container"]//tbody/tr/td/span/text()')
+print(zhou)
+ren = doc.xpath('//div[@class="table_container"]//tbody/tr/td[2]/text()')
+print(ren)
+ren = [m.replace(",", "") for m in ren]
+print(ren)
+siwang = doc.xpath('//div[@class="table_container"]//tbody/tr/td[3]/text()')
+print(ren)
+siwang = [m.replace(",", "") for m in siwang]
+message = list(zip(zhou, ren, siwang))
+import csv
+with open("content.csv", "w") as f:
+    w = csv.writer(f)
+    w.writerows(message)
+import pandas as pd
+
+#读取数据
+df = pd.read_csv("content.csv", names=["zhou", "ren", "siwang"])
+df.head()
+print(df)
+for i in range(101):
+    df.drop([i],inplace=True)
+print(df)
+df.sort_values(by=['ren'],ascending=False,ignore_index=True)
+print(df)
+df=df.iloc[0:15]
+print(df)
+#作图
+import matplotlib.pyplot as plt
+# 设置中文显示
+plt.rcParams['font.sans-serif'] = ['SimHei']
+plt.rcParams['figure.figsize'] = (10, 5)  
+m = df["zhou"].values
+n = df['siwang'].values
+plt.bar(m, n)
+plt.xlabel("zhou")
+plt.ylabel("siwang")
+plt.show()
+
+
+