1.安裝,在命令行輸入:pip install requests-html,安裝成功后,在Pycharm引入即可。
2.代碼如下所示:
from requests_html import HTMLSession import requests session = HTMLSession() r = session.get('http://www.win4000.com/wallpaper_2358_0_10_1.html') images = r.html.find('ul.clearfix > li > a') #獲取到網頁上所有a標簽url def save_Image(url,title): #定義一個函數,用於保存圖片到指定目錄下(E盤下需手動新建bg文件夾) html_response = requests.get(url) with open('E:/bg/'+title+'.jpg','wb') as file: file.write(html_response.content) #查找頁面中背景圖,找到鏈接,訪問查看大圖,並獲取大圖地址 for image in images: image_url = image.attrs['href'] #獲取到每張圖片屬性值為href的url if '/wallpaper_detail' in image_url: r = session.get(image_url) item_url = r.html.find('img.pic-large',first=True) #獲取到href下的src的url url = item_url.attrs['src'] title = item_url.attrs['title'] print(url+title) save_Image(url,title)
3.在指定目錄即可查看到爬下來的圖片