Requests库网络爬虫实例

1.京东商品页抓取

url = "https://item.jd.com/2330392.html"
try:
    r = requests.get(url)
    r.raise_for_status()
    r.encoding = r.apparent_encoding
    print(r.text[:1000])
except:
    print("爬虫失败")

2.亚马逊商品页抓取(修改User-Agent,模拟浏览器)

url = "https://www.amazon.cn/gp/product/B0094DVNT6"
try:
    kv = {'User-Agent' : 'Mozilla/5.0'}
    r = requests.get(url, headers=kv)
    r.raise_for_status()
    r.encoding = r.apparent_encoding
    print(r.text[:1000])
except:
    print("爬虫失败")

3.百度搜索

keyword = "Python"
try:
    kv = {'wd' : keyword}
    r = requests.get("http://www.baidu.com/s", params = kv)
    print(r.requests.url)
    r.raise_for_status()
    print(len(r.text))
except:
    print("爬虫失败")