淘宝商品页面的爬取.py(亲测有效)
import requests def getHTMLText(url): try: r = requests.get(url,timeout=30) r.raise_for_status() #如果状态不是200,引发HTTPError异常 r.encoding = r.apparent_encoding return r.text except: return "产生异常" if __name__ == "__main__": url = "https://detail.tmall.com/item.htm?spm=a230r.1.14.22.2854442bmpEenU&id=602773281591&ns=1&abbucket=14" #所爬取商品的网址 print(getHTMLText(url))