0
点赞
收藏
分享

微信扫一扫

python爬虫模板

英乐 2022-05-02 阅读 41
import re,requests
from lxml import etree
from concurrent.futures import ThreadPoolExecutor,ProcessPoolExecutor
def urls(url):
    res=requests.get(url)
    # html=etree.HTML(res.text)
    # image_urls=html.xpath('/html/body/div[5]/ul/li/a/div[1]/img/@src') #图片是js解析出来的,xpath无效,数据在js变量里面
    html=re.compile('lazysrc="(?P<img_urls>.*?)"',re.S)
    image_urls=html.finditer(res.text)

    for url in image_urls:
        res2=requests.get(url.group('img_urls'))
        s=url.group('img_urls')
        i = s.split('.')[2].split('/')[-1]
        with open(f'tupian2/{i}.jpg', mode='wb') as f:  # 写入图片
            f.write(res2.content)

if __name__ == '__main__':
    with ThreadPoolExecutor(20) as t:
        for i in range(1,10):
            t.submit(urls,f'https://www.3gbizhi.com/meinv/index_{i}.html')
    print('下载完成')

举报

相关推荐

0 条评论