使用python对https://www.mohfw.gov.in/的html表进行Web抓取

pip install requests
pip install beautifulsoup4

import requests
from bs4 import BeautifulSoup

# 发送HTTP GET请求获取网页内容
url = "https://www.mohfw.gov.in/"
response = requests.get(url)
html_content = response.text

# 使用BeautifulSoup解析网页内容
soup = BeautifulSoup(html_content, "html.parser")

# 根据HTML结构提取所需的数据
table = soup.find("table", class_="table-responsive")
rows = table.find_all("tr")

for row in rows:
    columns = row.find_all("td")
    if len(columns) >= 5:
        state = columns[1].text.strip()
        confirmed_cases = columns[2].text.strip()
        cured_cases = columns[3].text.strip()
        deaths = columns[4].text.strip()
        print("State:", state)
        print("Confirmed Cases:", confirmed_cases)
        print("Cured Cases:", cured_cases)
        print("Deaths:", deaths)
        print("--------------------")