python 爬虫（爬取网页的img并下载）

时间：2021-11-04 15:24:55
from urllib.request import urlopen # 引用第三方库

import requests #引用requests/用于访问网站（没安装需要安装）

from pyquery import PyQuery as pq #引用PyQuery用于 解析

# def get_url():

# #     url = 'https://s2.app1108017098.qqopenapp.com/?from=singlemessage&isappinstalled=0'

#     url = 'https://hm.baidu.com/hm.gif?cc=0&ck=1&cl=24-bit&ds=1920x1080&vl=328&ep=%7B%22netAll%22%3A168%2C%22netDns%22%3A23%2C%22netTcp%22%3A137%2C%22srv%22%3A49%2C%22dom%22%3A497%2C%22loadEvent%22%3A910%7D&et=87&ja=0&ln=zh-cn&lo=0&lt=1545373503&rnd=931647730&si=85ae31d909724b3fa587d26d1a21ab94&v=1.2.35&lv=2'

#     def get():

#         ret = urlopen(url).read()# 获取网页的源码

#         print(ret)

#         f = open('te.txt', 'wb')  # 若是'wb'就表示写二进制文件

#         f.write(ret)

#         f.close()

#     return get#返回函数

#

# get_func = get_url()#函数接收

# get_func()#输出 调用

# import requests

# from pyquery import PyQuery as pq

#爬取网页

html = requests.get('http://www.4399.com/flash/gamehw.htm').content.decode("gb2312")

#解析

doc = pq(html)

# f = open('te.txt', 'w',encoding='utf-8')  # 若是'wb'就表示写二进制文件

# f.write(html)

# f.close()

# 选择器 筛选语法

adc = doc('.tm_list > li > a').items()

for adv in adc:

    # url = adv.find('img')

    #找到html下的img 和 src

    url_q = adv.find('img').attr('lz_src')

    if url_q == None:

        url_q = adv.find('img').attr('src')

        #访问地址

    url_a = requests.get(url =url_q).content

    #拿到HTML下的名称

    name = adv.find('b').text()

    print("下载的图像：%s,地址为 %s" %(name,url_q))

    #打开文件目录

    with open("./1/"+name+".jpg",'wb') as file:

        #保存图片

        file.write(url_a)

print("图片下载完毕")

相关文章