练习2_小图片下载源码

练习2_小图片下载源码

import urllib.request
from urllib import request
from bs4 import BeautifulSoup

n=1
#1.获取网页源代码
url = 'https://www.duitang.com/search/?kw=%E6%98%93%E7%83%8A%E5%8D%83%E7%8E%BA&type=feed'

def crawl(url):
    #避免反爬 伪装 浏览器信息
    headers = {
        'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.138 Safari/537.36'
    }
    req = request.Request(url,headers=headers)#创建伪装成功
    page = urllib.request.urlopen(req,timeout=20)#设置超时，防止url不可访问
    contens = page.read() # 获取源代码
    #print(contens)

#2.解析出图链接 re pyquery selenium
    soup = BeautifulSoup(contens,'html.parser')#自带的解析方式，另一种是lxml
    #im = soup.find_all('img')
    # for i in im:
    #     link = i.get('src')
    #     print(link)
    im = soup.findAll('img',attrs={"alt":"易烊千玺"})
    for i in im:
        link = i.get('src')
        #print(link)
#3.写入文件（下载自行开放）
        # global n
        # urllib.request.urlretrieve(link,'images\%s.jpg'%n)
        # n+=1
        # print("正在下载第%s张"%n)