【学习笔记】python3 爬虫-百度图片

import requests
import re,time,random,os
from urllib import parse
from fake_useragent import UserAgent

class BaiduImgSpider(object):
    def __init__(self):
        self.baseurl = 'https://image.baidu.com/search/index?tn=baiduimage&word={}'
        self.count = 1;
        self.ua = UserAgent()
        self.savepath = '/home/user/work/spider/day03/'
        self.re_str = r'{"thumbURL":"(.*?)","replaceUrl":'

    def get_html(self,name,orgname):
        header = {'User-Agent':self.ua.random}
        url = self.baseurl.format(name)
        html = requests.get(url=url,headers = header).text
        pattent = re.compile(self.re_str,re.S)
        img_list = pattent.findall(html)
        path = self.savepath+orgname
        if not os.path.exists(path):
            os.mkdir(path)
        for img_link in img_list:
            print(img_link)
            self.save_img(img_link,path)
            time.sleep(random.randint(1,2))

    def save_img(self,url,path):
        header = {'User-Agent': self.ua.random}
        html = requests.get(url=url,headers=header).content
        filename = path+"/"+str(self.count)+'.jpg'
        with open(filename,'wb') as f:
            f.write(html)
            print('下载成功',filename)
        self.count += 1

    def run(self):
        search_name = input('输入要获取的名字>');
        word = parse.quote(search_name)
        self.get_html(word,search_name)


if __name__ == '__main__':
    spider = BaiduImgSpider()
    spider.run();

直接上代码了，非常简单的