python爬虫 - 图片下载示例代码

import requests
import os
from bs4 import BeautifulSoup
import urllib.request



class Crawl_Channel_Japan_Proxy():

    headers = {
        "Connection": "keep-alive",
        "Cache-Control": "max-age=0",
        "Upgrade-Insecure-Requests": "1",
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.149 Safari/537.36",
        "Sec-Fetch-Dest": "document",
        "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9",
        "Sec-Fetch-Site": "same-origin",
        "Sec-Fetch-Mode": "navigate",
        "Sec-Fetch-User": "?1",
        "Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8"
    }

    def fetchUrl(self, url):
        response = requests.get(url, headers=self.headers)
        return response

    def insert_brand(self):
        response = self.fetchUrl("https://www.countryflags.io")
        if response.status_code == 200:
            dir=os.path.abspath('.')
            work_path=os.path.join(dir,'country_flag')

            soup = BeautifulSoup(response.text, 'html.parser')
            item = soup.find("section", id="countries")
            div_list = item.find_all("div", class_="item_country")

            # 图片下载
            opener=urllib.request.build_opener()
            opener.addheaders=[('User-Agent','Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.75 Safari/537.36')]
            urllib.request.install_opener(opener)
            for div in div_list:
                imgurl = div.find('img').get('src')
                find = div.find('p', class_="mb0 bold")
                country = find.string
                country_all = find.nextSibling.nextSibling.string
                country_all = country_all if country_all is not None else ''
                print(find.nextSibling.nextSibling)
                print(imgurl + '    ' + country + '    ' + country_all)
                io_imgurl = 'https://www.countryflags.io' + imgurl
                dest = os.path.join(work_path, country + '_' + country_all + '.png')
                urllib.request.urlretrieve(io_imgurl, dest)

if __name__ == "__main__":
    crawl = Crawl_Channel_Japan_Proxy()
    crawl.insert_brand()

 

  • 0
    点赞
  • 1
    收藏
    觉得还不错? 一键收藏
  • 打赏
    打赏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

戴国进

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付:¥1
获取中
扫码支付

您的余额不足,请更换扫码支付或充值

打赏作者

实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值