Python爬取大量英雄联盟壁纸（多线程，小白版）

爬取链接
代码

import requests
import threading
import shutil
import re
import os
class myThread(threading.Thread):
    def __init__(self,word,page,urls,down_localhost):
        threading.Thread.__init__(self)
        self.word=word
        self.page=page
        self.urls=urls
        self.down_localhost=down_localhost
    def run(self):
        self.down_localhost = self.down_localhost + '\\' + word + str(self.page)
        if not os.path.exists(self.down_localhost):
            os.makedirs(self.down_localhost)
        for url in self.urls:
            download(readUrlTwo(url), self.down_localhost)
            print("第%s页 下载成功" % self.page)

def readUrlOne(url):
    pattern = re.compile(r'<a class="preview" href="(.*?)"  target="_blank"  ></a>', re.S)
    results = re.findall(pattern, requests.get(url).text)
    return results
def readUrlTwo(url):
    pattern = re.compile(r'<img id="wallpaper" src="(.*?)"', re.S)
    response = requests.get(url);
    results = re.search(pattern, response.text)
    return results.group(1)

def download_jpg(image_url,image_localhost):
    response=requests.get(image_url,stream=True)
    if response.status_code==200:
        with open(image_localhost,'wb') as f:
            response.raw.deconde_content=True
            shutil.copyfileobj(response.raw,f)
def download(url,path):
    filename=os.path.basename(url)
    imgpath=os.path.join(path,filename)
    print("开始下载 %s"%url)
    download_jpg(url,imgpath)
    print("下载完成 %s"%url)


down_loaclhost='E:\BaiduNetdiskDownload';
word=input('输入下载内容')
word1 = re.sub('\s', '%20', word)
number=input('输入现在页数')
number=int(number)
for page in range(1,number+1):
    url = 'https://wallhaven.cc/search?q=' + word1 + '&page=' + str(page);
    urls=readUrlOne(url)
    thread=myThread(word,page,urls,down_loaclhost)
    thread.start()

运行截图

爬取几页就是几个线程，暂时没有设置线程最大数，后期会涉及实现。