【爬虫练手】表情包爬虫

最新推荐文章于 2024-05-01 14:17:27 发布

於陵樺暉

最新推荐文章于 2024-05-01 14:17:27 发布

阅读量173

点赞数

分类专栏：爬虫

本文链接：https://blog.youkuaiyun.com/wyh33200/article/details/105720932

版权

爬虫专栏收录该内容

10 篇文章

订阅专栏

import requests,os,re
from lxml import etree
from urllib import request

def parse_page(url):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.122 Safari/537.36'
    }
    response = requests.get(url,headers=headers)
    text = response.text
    html = etree.HTML(text)
    imgs = html.xpath("//div[@class='page-content text-center']//img")
    for img in imgs:
        img_url = img.get('data-original')
        alt = img.get('alt')
        alt = re.sub(r'[\/ ：* ?？“ < > ”|]','',alt)
        suffix = os.path.splitext(img_url)[1]
        filename = alt+suffix
        request.urlretrieve(img_url,'images/'+filename)

def main():
    for x in range(1,401):
        url = 'https://www.doutula.com/photo/list/?page={}'.format(x)
        parse_page(url)


if __name__ ==  '__main__':
    main()