3.Python爬虫入门_正则表达式(简单例子)

#2019-11-23
import requests
import time
import re #Python正则表达式库

if __name__=='__main__':
    #海量爬取图片数据
    #进入网站(一般商业图片素材公司网站版权保护做得比较好,不容易爬取)
    #https://www.pexels.com/(该网站图片免费,易于爬取)
    #搜索关键词<man>,Chrome按下F12查看源码,发现图片链接
    url_picture='https://www.pexels.com/search/man/'
    response=requests.get(url=url_picture)
    with open('./pexels/man.html',mode='w',encoding='utf-8') as fp:
        fp.write(response.text)
        print('网页保存成功!')  #保存的html文件中含有多张图片的url地址
    
    #所有的数据
    #<img srcset="https://images.pexels.com/photos/220453/pexels-photo-220453.jpeg?auto=compress&amp;cs=tinysrgb&amp;dpr=1&amp;w=500 1x, 
    #https://images.pexels.com/photos/220453/pexels-photo-220453.jpeg?auto=compress&amp;cs=tinysrgb&amp;dpr=2&amp;w=500 2x" 
    #class="photo-item__img" alt="Man Smiling Behind Wall" data-image-width="3476" data-image-height="5214" 
    #data-big-src="https://images.pexels.com/photos/220453/pexels-photo-220453.jpeg?auto=compress&amp;cs=tinysrgb&amp;h=750&amp;w=1260" 
    #data-large-src="https://images.pexels.com/photos/220453/pexels-photo-220453.jpeg?auto=compress&amp;cs=tinysrgb&amp;h=650&amp;w=940" 
    #data-tiny-src="https://images.pexels.com/photos/220453/pexels-photo-220453.jpeg?auto=compress&amp;cs=tinysrgb&amp;dpr=1&amp;w=500" 
    #data-tiny-srcset="https://images.pexels.com/photos/220453/pexels-photo-220453.jpeg?auto=compress&amp;cs=tinysrgb&amp;dpr=1&amp;w=500 1x, 
    #https://images.pexels.com/photos/220453/pexels-photo-220453.jpeg?auto=compress&amp;cs=tinysrgb&amp;dpr=2&amp;w=500 2x" 
    #src="https://images.pexels.com/photos/220453/pexels-photo-220453.jpeg?auto=compress&amp;cs=tinysrgb&amp;dpr=1&amp;w=500" >
    
    #该正则获取小括号内内容 (.*?)  .表示任意字符,*表示匹配多个,?表示遇到"就停下来(非贪婪模式)
    num_name=1
    html=response.text
    pattern_url=r'<img srcset="(.*?)".*?>'  # r'':非转义的原始字符串
    pattern_img_name=r'pexels-photo-(.*?).jpeg'
    img_urls=re.findall(pattern_url,html) #得到的是一个list,里面是str元素,这些元素是匹配到的图片url
    print(img_urls)
    for img_url in img_urls:
        response=requests.get(img_url)
        content=response.content
        #img_name=re.findall(pattern_img_name,img_url) #该网站srcset内有两条可用的url,所以匹配后会有两条相同的name
        with open('./Pexels/'+str(num_name)+'.jpg','wb') as fp:
            fp.write(content)
            print(str(num_name)+'号图片下载成功!')
            num_name+=1
        time.sleep(0.1) #设置时间延迟 1s
        
    #Python 文件读写 
    #open(文件地址,读写方式,编码方式),
    #读写方式: 
    #文本'w' 
    #图片'wb'