python爬蟲實戰項目-爬取壁紙 一. 需求 二. 解決方案 參考:

一. 需求

比較喜歡動漫，想從網站下通過爬蟲程序，下載一些動漫的壁紙

https://desk.zol.com.cn/bizhi/8366_103760_2.html

二. 解決方案

代碼:

from concurrent.futures import ThreadPoolExecutor
import requests
import re
import json

def download(imgsrc):
    """下載圖片到本地"""
    name = imgsrc.split("/")[-1]
    print(f"準備開始下載{name}")
    # 1. 發送網絡請求
    resp_img = requests.get(imgsrc)
    # 2. 此時拿不到resp.text
    # resp.content -> 拿到文件的字節
    with open(f"img/{name}", mode="wb") as f:
        f.write(resp_img.content)
    print(f"{name}下載完畢")


def main():
    url = "https://desk.zol.com.cn/bizhi/8366_103760_2.html"
    resp = requests.get(url)

    obj = re.compile(r"var deskPicArr.*?=(?P<deskPicArr>.*?);", re.S)

    result = obj.search(resp.text)
    deskPicStr = result.group("deskPicArr") # 從正則.*?提取的內容一定是字符串

    # 把類似字典的字符串變成真的字符串
    deskPic = json.loads(deskPicStr)

    with ThreadPoolExecutor(3) as t:
        for item in deskPic['list']:
            oriSize = item.get("oriSize")
            imgsrc = item.get("imgsrc")
            imgsrc = imgsrc.replace("##SIZE##", oriSize)
            t.submit(download, imgsrc)
    print("all over!")


if __name__ == '__main__':
    main()

測試記錄:

參考:

1. https://www.bilibili.com/video/BV1wa41197X9