下面是爬取书的价格和书名的简单示例：

import requests
from bs4 import BeautifulSoup
content = requests.get("http://books.toscrape.com/").text # 拿到网页源码
soup = BeautifulSoup(content, "html.parser")
all_prices = soup.find_all("p", attrs={"class": "price_color"}) # 获取所有类名为“price_color”的 p 标签
for price in all_prices:
    print(price.string) #拿到每个标签里的文字内容
all_titles = soup.find_all("h3")
for title in all_titles:
    all_links = title.find_all("a")
    for link in all_links:
        print(link.string)

如果h3里只有一个a标签，可以用find()代替find_all()，里面也不需要循环了，如下：

for title in all_titles:
    link = title.find("a")
    print(link.string)

再来一个爬虫经典案例，爬豆瓣电影TOP250的影片名，完整代码如下:

import requests
from bs4 import BeautifulSoup

headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/123.0.0.0 Safari/537.36"
}
for i in range(0, 250, 25):
    response = requests.get(f'https://movie.douban.com/top250?start={i}', headers=headers)
    html = response.text
    soup = BeautifulSoup(html, 'html.parser')
    all_titles = soup.find_all('span', attrs={'class': 'title'})
    for title in all_titles:
        title_string = title.string
        if '/' not in title_string:
            print(title_string)

下面来进阶一点，我们来爬一下图片

为了安全就不做过多解释了

import requests
from bs4 import BeautifulSoup
from urllib.parse import urljoin

headers = {
    'Referer': 'https://www.pixiv.net/',
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/123.0.0.0 Safari/537.36 Edg/123.0.0.0'
}
url = 'https://www.toopic.cn/'
path = 'F://spiderImages'
response = requests.get(url, headers=headers)
html = response.text
soup = BeautifulSoup(html, 'html.parser')
image_links = []
for img in soup.find_all('img', attrs={'class': 'lazy'}):
    img_url = img['data-original']
    # 如果图片链接是相对路径，则将其转换为绝对路径
    if not img_url.startswith(('http://', 'https://')):
        img_url = urljoin(url, img_url)
    image_links.append(img_url)
for i, image_link in enumerate(image_links):
    response = requests.get(image_link, headers=headers)
    with open(f'{path}/img{i + 1}.jpg', 'wb') as file:
        file.write(response.content)