Python爬虫入门-多线程爬取高清电脑壁纸

Python爬虫多线程爬取电脑壁纸

爬取的思路与我之前写的Java爬虫博客一致，这里不再分析，需要详解的看我另一篇博客

JAVA爬虫多线程高速爬取高清电脑壁纸

直接看代码吧，里面有注释，初次学习Python，如有问题请多指教

import requests
import threading
from bs4 import BeautifulSoup

str1 = 'http://desk.zol.com.cn/showpic/1920x1080_'
str2 = '_101.html'
def get(url, i):
    print(threading.current_thread().name)
    r = requests.get(url)  # 获取网页代码
    r.headers = {
        'Pragma': 'no-cache',
        'Cache-Control': 'no-cache',
        'Upgrade-Insecure-Requests': '1',
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.109 Safari/537.36',
        'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
        'Accept-Language': 'zh-CN,zh;q=0.9',
        'Connection': 'close',
    }
    # 得到img标签最后得到图片的URL
    soup = BeautifulSoup(r.text, 'lxml')
    imgurl = soup.img['src']
    r = requests.get(imgurl)
    path = 'E:/picture/' + str(i) + '.jpg'
    # 下载图片
    with open(path, 'wb') as f:
        f.write(r.content)
        f.close()
        print("img: " + str(i) + ".jpg  download successfully!")
# 使用多线程下载一个线程下载一张图片，
if __name__ == '__main__':
    ts = []
    for i in range(91200, 92200):
        url = str1 + str(i) + str2;
        t = threading.Thread(target=get, args=(url, i))
        ts.append(t)
    for i in ts:
        try:
            i.start()
        except:
            continue # 防止单个线程出现异常而导致主线程不会启动后面的线程