zoukankan      html  css  js  c++  java
  • 批量爬取贴吧图片 糗事百科 煎蛋网

    批量爬取贴吧图片
    from urllib import request
    import re
    # %e5%9b%be%e7%89%87
    url = "http://tieba.baidu.com/f?kw=%E6%91%84%E5%BD%B1%E5%90%A7"

    headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 Safari/537.36"
    }

    req = request.Request(url = url,headers=headers)

    response = request.urlopen(req)

    html = response.read().decode("utf-8")

    img_link = re.findall(r'<img src="(.*?)"',html)

    # print(img_link)
    # str.startswith()

    for link in img_link:
    # 判断链接是否是以http开头的
    if link.startswith("http"):
    print("开始爬取:%s"%link)
    request.urlretrieve(url = link,filename = '../images/'+link[-10:])
    else:
    pass


    糗事百科
    from urllib import request
    import re
    url = "https://www.qiushibaike.com/pic/page/%s/"
    headers = {
    "User-Agent"": ""Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 Safari/537.36"",
    }
    for i in range(1,11):
    req = request.Request(url=url%i,headers=headers)
    response = request.urlopen(req)
    html = response.read().decode("utf-8")
    img_link = re.findall(r'<img src="(.*?)"',html)
    for link in img_link:
    if link.startswith("//pic"):
    links="http:"+link
    try:
    request.urlretrieve(url=links,filename="./images/"+links[-10:])
    except:
    pass
    else:
    print(link,"图片路径不正确")


    煎蛋网
    from urllib import request
    import re
    url = "http://jandan.net/pic/page-127"
    headers = {
    "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
    "Accept-Language": "zh-CN,zh;q=0.9",
    "Cache-Control": "no-cache",
    "Connection": "keep-alive",
    "Cookie": "_ga=GA1.2.1246691030.1543560067; _gid=GA1.2.1877436102.1559200246",
    "Host": "jandan.net",
    "Pragma": "no-cache",
    "Upgrade-Insecure-Requests": "1",
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 Safari/537.36",
    }
    req = request.Request(url=url,headers=headers)
    response = request.urlopen(req)
    html = response.read().decode("utf-8")
    link = re.findall(r'<img .* org_src="(.*?)"',html)
    for var in link:
    links="http:"+var
    print("正在下载:%s"%(links))
    request.urlretrieve(links,"./image/"+links[-10:])






  • 相关阅读:
    python中if __name__ == '__main__': 的解析
    CPPUTest 单元测试框架(针对 C 单元测试的使用说明)
    哈希表详解
    使用RSS提升DPDK应用的性能(转)
    DPDK内存管理-----rte_mbuf(转)
    DPDK内存管理-----(二)rte_mempool内存管理
    DPDK内存管理(1)(转)
    Scala + IntelliJ IDEA
    什么是消息队列中间件
    微信小程序直播
  • 原文地址:https://www.cnblogs.com/wyf2019/p/10951937.html
Copyright © 2011-2022 走看看