urllibrequest爬虫，爬取彼岸图片

• import urllib.request
  from bs4 import BeautifulSoup
  
  def index(page):
      if page == 1:
          url = 'https://pic.netbian.com/index.html'
      else:
          url = "https://pic.netbian.com/index_{}.html".format(page)
      # url = 'https://pic.netbian.com/index.html'
      headers = {
          'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) '
                        'Chrome/93.0.4577.82 Safari/537.36 '
      }
      w1 = urllib.request.Request(url=url, headers=headers)
      w2 = urllib.request.urlopen(w1).read()
      data = BeautifulSoup(w2, "html.parser")
      ul = data.find("div", class_="slist").find_all("li")
      # print(ul)
      for i in ul:
          n = i.find_all("img")
          for j in n:
              #图片地址
              src = j['src']
              #图片标题
              title = j["alt"].replace(" ", "")
              print(title)
              #拼接
              src1 = "https://pic.netbian.com/" + src
              #print(src1)
              #下载图片
              urllib.request.urlretrieve(url=src1, filename="./image/"+title+".jpg")
  
  #爬取前20页
  for j in range(1, 20):
      index(j)

这是爬取的网页链接最新4K壁纸_最新4K桌面壁纸_彼岸图网

 

图片下载成功