python获取关键字

方法一

import requests
from bs4 import BeautifulSoup

def get_webpage_content(url):
    try:
        response = requests.get(url)
        if response.status_code == 200:
            return response.text
        else:
            print("Failed to retrieve webpage. Status code:", response.status_code)
            return None
    except Exception as e:
        print("Error:", e)
        return None

def extract_keywords(content, keywords):
    keyword_info = {}
    soup = BeautifulSoup(content, 'html.parser')
    for keyword in keywords:
        keyword_info[keyword] = []
        for tag in soup.find_all(text=lambda text: text and keyword in text):
            keyword_info[keyword].append(tag.strip())
    return keyword_info

def main():
    url = input("请输入要搜索的网址：")
    keywords = input("请输入要搜索的关键词，以空格分隔：").split()
    
    webpage_content = get_webpage_content(url)
    if webpage_content:
        keyword_info = extract_keywords(webpage_content, keywords)
        for keyword, info in keyword_info.items():
            print(f"关键词 '{keyword}' 出现的内容：")
            for item in info:
                print(item)
    else:
        print("未能获取网页内容，请检查输入的网址是否正确。")

if __name__ == "__main__":
    main()

方法二

import requests
from bs4 import BeautifulSoup

def get_webpage_content(url):
    try:
        response = requests.get(url)
        if response.status_code == 200:
            return response.text
        else:
            print("Failed to retrieve webpage. Status code:", response.status_code)
            return None
    except Exception as e:
        print("Error:", e)
        return None

def extract_custom_keywords(content, custom_keywords):
    keyword_info = {}
    soup = BeautifulSoup(content, 'html.parser')
    for keyword in custom_keywords:
        keyword_info[keyword] = []
        for tag in soup.find_all(text=lambda text: text and keyword in text):
            keyword_info[keyword].append(tag.strip())
    return keyword_info

def main():
    url = input("请输入要搜索的网址：")
    custom_keywords = input("请输入要搜索的自定义关键词，以空格分隔：").split()
    
    webpage_content = get_webpage_content(url)
    if webpage_content:
        keyword_info = extract_custom_keywords(webpage_content, custom_keywords)
        for keyword, info in keyword_info.items():
            print(f"关键词 '{keyword}' 出现的内容：")
            for item in info:
                print(item)
    else:
        print("未能获取网页内容，请检查输入的网址是否正确。")

if __name__ == "__main__":
    main()