Python 爬蟲練習項目——異步加載爬取

項目代碼

from bs4 import BeautifulSoup
import requests
url_prefix = 'https://knewone.com/discover?page='
infos = []

# 獲取單個頁面數據
def getAPage(url,data = None):
    web_data = requests.get(url)
    soup = BeautifulSoup(web_data.text,'lxml')
    # print(soup)

    images = soup.select('header > a > img')
    titles = soup.select('section > h4 > a')
    links = soup.select('a.cover-inner')
    likes = soup.select('span.fanciers_count')

    if data == None:
        for image,title,link,like in zip(images,titles,links,likes):
            data = {
                'image':image.get('src'),
                'title':title.get_text(),
                'link':'https://knewone.com' + link.get('href'),
                'like':int(like.get_text())
            }
            print(data)

            infos.append(data)
# 獲取多個加載的數據
def getMorePages(start,end):
    for url_suffix in range(start,end):
        getAPage(url_prefix + str(url_suffix))
        print('---------------已經獲取{}條數據---------------'.format(len(infos)), sep='\n')
# 獲取點贊排名前幾的數據
def getInfosByLikes(order,infos =infos):
    infos = sorted(infos,key= lambda info:info['like'],reverse = True)
    for info in infos[:order]:
        print(info['like'],info['title'],info['image'],info['link'])

getMorePages(1,4)


getInfosByLikes(5)

項目特點：

【轉載】同步加載、異步加載、延遲加載

爬取的網站鏈接

KnewOne

需要下載代碼的可以到我的GitHub上下載 https://github.com/FightingBob/-Web-Crawler-training  如果覺得可以，請給我顆star鼓勵一下，謝謝！