1. 爬取京东手机信息
import requests
def getHTMLText(url):
try:
r = requests.get(url,timeout=30)
#如果状态不是200,引发HTTPError异常
r.raise_for_status()
r.encoding = r.apparent_encoding
print(r.text[:1000])
except:
return "爬取失败"
if __name__ == "__main__":
url = "https://item.jd.com/7081550.html"
print(getHTMLText(url))
2. 爬取亚马逊商品信息,需要修改user-agent的值
import requests
def getHTMLText(url):
try:
kv = {'user-agent':'Mozilla/5.0'}
r = requests.get(url,headers=kv,timeout=30)
#如果状态不是200,引发HTTPError异常
r.raise_for_status()
r.encoding = r.apparent_encoding
print(r.text[1000:2000])
except:
return "爬取失败"
if __name__ == "__main__":
url = "https://www.amazon.com/dp/B078HRHWH2/ref=sspa_dk_detail_4?psc=1&pd_rd_i=B078HRHWH2&pf_rd_m&#