爬取表情包

[发表情网](https://www.fabiaoqing.com/biaoqing/lists/page/1.html)


import requests,os
from lxml import etree
from fake_useragent import UserAgent

def crawl(url):
    headers={
    
        "User-Agent":UserAgent().chrome
    }
    #获取页面响应信息
    page_text=requests.get(url,headers).text
    #解析表情包的详情页url
    tree=etree.HTML(page_text)
    list_data=tree.xpath('//div[@class="ui segment imghover"]/div/a')
    if not os.path.exists('表情包'):
        os.mkdir('表情包')
    for i in list_data:
        detail_url='https://www.fabiaoqing.com'+i.xpath('./@href')[0]
        # print(detail_url)
        #对详情页面url发起请求，获取响应
        detail_page_text=requests.get(detail_url,headers).text
        tree=etree.HTML(detail_page_text)
        #得到搞笑图片的地址，发起请求进行持久化存储
        detail_list_data=tree.xpath('//div[@class="swiper-wrapper"]/div/img/@src')[0]
        fp=detail_list_data.split('/')[-1]
        with open('表情包/'+fp, 'wb') as fp:
            fp.write(requests.get(detail_list_data).content)
            print(fp,'下载完了！！！')
#调用
crawl('https://www.fabiaoqing.com/biaoqing/lists/page/1.html')