python爬取网站图片保存到本地文件夹

爬取的网站

https://wallpaperscraft.com/catalog/anime

爬取代码

# 导包
import os
import requests
import parsel
from parsel import Selector  

def download_onepagephoto(website_url,count):  # 下载一页图片
    # 用i暂存传输过来的count值
    i=count
    # 发送请求
    response = requests.get(website_url)
    response.encoding = response.apparent_encoding
    # 很关键的一步,构建Selector对象
    sel = Selector(response.text)
    # 获取到网页中样式为wallpapers__item类下a标签的href的值
    index = sel.css('.wallpapers__item a::attr(href)').getall()
    # 遍历进入每个图片
    for line in index:
        # 模拟进入另一个页面,如法炮制上述操作
        response = requests.get("https://wallpaperscraft.com"+line)
        response.encoding = response.apparent_encoding
        sel = Selector(response.text)
        index2 = sel.css('.wallpaper__placeholder a::attr(href)').getall()
        if len(index2)!=0:
            nameurl=index2[0]
            # 获取到图片链接,将其保存到同级目录本地photo文件夹
            photo=requests.get(nameurl).content
            with open("photo/"+str(i)+".jpg","wb") as fp:
                fp.write(photo)
            print(str(i)+" already success")
            i=i+1
    return i

count=1
#爬取第一页
count=download_onepagephoto("https://wallpaperscraft.com/catalog/anime/1920x1080",count)
#爬取第二页及以后
for temp in range(2,174):
    count=download_onepagephoto("https://wallpaperscraft.com/catalog/anime/1920x1080/page"+str(temp),count)
    print("第"+str(temp)+"页图片爬取完成")



【创作不易,望点赞收藏,若有疑问,请评论,谢谢】

posted @ 2022-04-29 08:55  东血  阅读(693)  评论(0编辑  收藏  举报

载入天数...载入时分秒...