爬虫糗事百科图片代码

Posted 2020-10-31 lili414

#在平常写代码的文件夹下新建一个image_spider的文件夹作为工程文件，并在此文件夹目录下新建一个image文件夹作为保存图片的文件

#抓取百科的图片
#访问url必须有http开头
import  requests
import  re

def crawl_image(image_url, image_local_path):
    image_url = "http:"+image_url
    r = requests.get(image_url,stream=True)
    with open(image_local_path,"wb") as f:
        f.write(r.content)

def crawl(page):
    url = "https://www.qiushibaike.com/imgrank/page/" + str(page)
    res = requests.get(url)
    content_list = re.findall("<div class=\"thumb\">(.*?)</div>",res.content.decode("utf-8"),re.S)
    for content in content_list:
        image_list = re.findall("<img src=\"(.*?)\"",content)
       # print(image_list)
        for image_url in image_list:
            crawl_image(image_url,"D:/Program Files/python/image_spider/image/" + image_url.strip().split(‘/‘)[-1])
            #print("./image/" + image_url.strip().split(‘/‘)[-1])

if __name__ == ‘__main__‘:
    crawl(1)