利用python爬取图片并下载到本地

离·i殇

已于 2022-06-05 22:14:09 修改

阅读量3.1k

点赞数 1

分类专栏：学习笔记文章标签： python

于 2022-06-05 21:36:58 首次发布

本文链接：https://blog.csdn.net/m0_64609927/article/details/125137058

版权

学习笔记专栏收录该内容

11 篇文章 1 订阅

订阅专栏

#coding:gbk
import os
from statistics import quantiles
import requests
import re                                    #正则表达式，进行文字匹配
import urllib.request,urllib.error           #制定URL，获取网页数据              
from bs4 import BeautifulSoup                #网页解析，获取数据
 
 
 
#创建正则表达式对象，表示规则
findlink = re.compile(r'<link href="(.*?)" itemprop=')                               

def main():
    baseurl =  "https://www.hippopx.com/zh"
    Datelist,quantity = getDate(baseurl)
    while(quantity):
        Download(Datelist[quantity-1][0])                              #下载图片
        quantity-=1
 
 
def getDate(baseurl):
    a=0
    datelist = []
    html = askURL(baseurl)  
    Soup = BeautifulSoup(html,"html.parser") 
    for item in Soup.select("li"):                                      #查找符合要求的字符串,形成列表
            date = []                                                        #保存一张图片的数据
            item = str(item)
            link = findlink.findall(item)                                 #获取图片链接
            if len(link):
                date.append(link[0])      
                a+=1
            if(len(date)):
                datelist.append(date)
    return datelist,a
 
 
 
#得到指定URL的网页内容
def askURL(url):
    head = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.140 Safari/537.36 Edge/18.17763"}
    #模拟浏览器头部信息，向服务器发送消息
    request = urllib.request.Request(url,headers=head)
    html = ""
    try:
        response = urllib.request.urlopen(request)
        html = response.read().decode("utf-8")
        
    except urllib.error.URLError as e:
        if hasattr(e,"code"):
            print(e.code)
        if hasattr(e,"reason"):
            print(e.reason)
    return html
 
 
def Download(Url):
    url=Url
    d='D:\\B\\'
    path=d+url.split('/')[-1]
    try:
        if not os.path.exists(d):
            os.mkdir(d)
        if not os.path.exists(path):
            r=requests.get(url)
            r.raise_for_status()
            with open(path,'wb') as f:
                f.write(r.content)
                f.close()
                print("图片保存成功")
        else:
            print("图片已存在")
    except:
        print("图片获取失败")
 
 
if __name__ == "__main__":
    main()