pip install beautifulsoup4 lxml

import requests
from bs4 import BeautifulSoup

# 獲取網頁內容
url = 'https://example.com'
response = requests.get(url)
html_content = response.content

# 創(chuàng)建 BeautifulSoup 對象
soup = BeautifulSoup(html_content, 'html.parser')

# 查找第一個 h1 元素
h1_tag = soup.find('h1')
print(h1_tag.text)

# 查找所有的鏈接
links = soup.find_all('a')
for link in links:
    print(link.get('href'))

# 使用 CSS 選擇器查找元素
items = soup.select('.item .title')
for item in items:
    print(item.text)

# 提取標簽文本
title = soup.find('h1').text

# 提取屬性
link = soup.find('a')
href = link.get('href')   # 或者 link['href']

import requests

# 目標網址
url = 'https://www.bbc.com/news'

# 發(fā)送請求
response = requests.get(url)

# 檢查請求狀態(tài)
if response.status_code == 200:
    html_content = response.content
else:
    print("Failed to retrieve the webpage")

from bs4 import BeautifulSoup

# 解析 HTML 內容
soup = BeautifulSoup(html_content, 'html.parser')

# 查找新聞標題和鏈接
news_list = []
for item in soup.select('.gs-c-promo-heading'):
    title = item.get_text()
    link = item.get('href')
    if link and not link.startswith('http'):
        link = 'https://www.bbc.com' + link  # 補全相對鏈接
    news_list.append([title, link])

import csv

# 寫入數據到 CSV 文件
with open('bbc_news.csv', 'w', newline='', encoding='utf-8') as csvfile:
    writer = csv.writer(csvfile)
    writer.writerow(['Title', 'Link'])
    writer.writerows(news_list)

print("Data saved to bbc_news.csv")

try:
    response = requests.get(url)
    response.raise_for_status()
except requests.exceptions.RequestException as e:
    print(f"Error: {e}")

import time
time.sleep(1)  # 延時 1 秒

import requests
from bs4 import BeautifulSoup
import csv
import time

def fetch_news(url):
    try:
        response = requests.get(url)
        response.raise_for_status()
        return response.content
    except requests.exceptions.RequestException as e:
        print(f"Error: {e}")
        return None

def parse_news(html_content):
    soup = BeautifulSoup(html_content, 'html.parser')
    news_list = []
    for item in soup.select('.gs-c-promo-heading'):
        title = item.get_text()
        link = item.get('href')
        if link and not link.startswith('http'):
            link = 'https://www.bbc.com' + link
        news_list.append([title, link])
    return news_list

def save_to_csv(news_list, filename='bbc_news.csv'):
    with open(filename, 'w', newline='', encoding='utf-8') as csvfile:
        writer = csv.writer(csvfile)
        writer.writerow(['Title', 'Link'])
        writer.writerows(news_list)
    print(f"Data saved to {filename}")

def main():
    url = 'https://www.bbc.com/news'
    html_content = fetch_news(url)
    if html_content:
        news_list = parse_news(html_content)
        save_to_csv(news_list)
        time.sleep(1)

if __name__ == "__main__":
    main()