python爬虫（五）多页码

2023年6月3日 233次阅读 来源: luogan129 
from bs4 import BeautifulSoup
import requests
import time

url = 'https://knewone.com/discover?page='

def get_page(url,data=None):

    wb_data = requests.get(url)
    soup = BeautifulSoup(wb_data.text,'lxml')
    imgs = soup.select('a.cover-inner > img')
    titles = soup.select('section.content > h4 > a')
    links = soup.select('section.content > h4 > a')

    if data==None:
            for img, title, link in zip(imgs, titles, links):
                data = {
            'img': img.get('src'),
            'title': title.get('title'),
            'link': link.get('href')
        }
                print(data)

def get_more_pages(start,end):
    for one in  range(start,end):
        get_page(url+str(one))
        time.sleep(2)

get_more_pages(1,10)
    原文作者：luogan129
    原文地址: https://blog.csdn.net/luogan129/article/details/71302486
    本文转自网络文章，转载此文章仅为分享知识，如有侵权，请联系博主进行删除。
点赞