python爬虫爬取彼岸和wallhaven壁纸

最近在设置pycharm背景板的时候，想找一些好看的壁纸，记录一下吧

彼岸壁纸代码（彼岸是每天只能下载一张的，我曾在嫉妒愤怒的情况下。。。）

import requests from lxml import etree

header = { 'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36', 'cookie':'__cfduid=d87f516a21ea92ec0ae00ab0138eb602f1601093627; Hm_lvt_2c6cc9163dcd6f496c48a6b8ac043309=1601093627,1601093653; Hm_lpvt_2c6cc9163dcd6f496c48a6b8ac043309=1601093668', } for k in range(2,10): res = requests.get('http://www.4kbizhi.com/meinv/index_'+str(k)+'.html',headers=header) res.encoding=res.apparent_encoding

    html = etree.HTML(res.text) img = html.xpath('/html/body/div[2]/div[1]/ul/li/a/img/@src') title=html.xpath('/html/body/div[2]/div[1]/ul/li/a/p/text()') for i in range(len(img)): url='http://www.4kbizhi.com'+img[i] with open("data/彼岸/"+title[i]+".jpg", "wb") as f: f.write(requests.get(url).content) 

wallhaven壁纸代码（这是个外国网站）

import requests from fake_useragent import UserAgent import re from lxml import etree
header={"User-Agent":(str(UserAgent().random))} number=0 for j in range(1,10): url = 'https://wallhaven.cc/search?q=id%3A5&sorting=random&ref=fp&seed=jYVlG&page='+str(j) response = requests.get(url,headers=header) html = etree.HTML(response.text) first_url=html.xpath('//*[@id="thumbs"]/section[1]/ul/li/figure/a/@href') for i in first_url: result=requests.get(i, headers=header) img_url=re.findall('id="wallpaper" src="(.*?)"',result.text) with open("data/wallhaven壁纸/"+"小妹妹"+str(number)+".jpg", "wb") as f: f.write(requests.get(img_url[0], headers=header).content) number+=1 

这就很nice

本文地址：https://blog.csdn.net/weixin_44772112/article/details/109023988