python爬虫通用框架
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HTTP-Error异常
#print(r.status_code)
r.encoding = r.apparent_encoding
return r.text
except:
return "产生异常"
if __name__=="__main__":
url = "https://item.jd.com/5107323.html"
print(getHTMLText(url))