记录 BeautifulSoup 一些使用方法

from bs4 import BeautifulSoup
import requests

def paginate(url_template, page_num):
    url = url_template.format(page_num)
    response = requests.get(url)
    soup = BeautifulSoup(response.text, 'html.parser')
    # 在这里处理当前页面的内容
    divs = soup.find_all('div', class_='relative') # 限制class_='relative'
    for div in divs:
        links = div.find_all('a')
        for link in links:
            print(link.get('href'))
            # thread=threading.Thread(target=download_images, args=(link.get('href'),)).start()
            # threads.append(thread)
            # sleep(30)
            download_images(link.get('href'))
# 定义页面模板和起始页码
url_template = 'https://xxx.net/search?kw=xxx&page={}'

获取有多少页的代码 多少个翻页按钮

    #获取有多少页
    span = soup.find('span', class_='relative z-0 inline-flex flex-wrap shadow-sm rounded-md')
    if span:
        a_links = span.find_all('a')
        num = len(a_links)
        print(f"当前链接共有{num}页")

查找指定图片链接代码

       image_links = [img['src'] for img in soup.find_all('img', class_='block my-1')]
       image_names = [img['title'] for img in soup.find_all('img', class_='block my-1')]