小白学爬虫笔记3---几个基本实例

实例1：京东商品爬取

import requests
url = "https://item.jd.com/3739097.html"
try:
    r = requests.get(url)
    r.raise_for_status()
    r.encoding = r.apparent_encoding
    pring(r.text[:1000])
except:
    print("爬取失败")

实例2：亚马逊商品信息爬取

import requests
url = "https://www.amazon.cn/gp/product/B01M8L5Z3Y"
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[1000:2000])
except:
    print("爬取失败")

实例3：百度、360搜索关键词提交

import requests
keyword = 'Python'
try:
    kv = {'wd':keyword} #360搜索：'wd'→'q'
    r = requests.get("http://www.baidu.com/s",params = kv)
    print(r.request.url)
    r.raise_for_status()
    print(len(r.text))
except:
    print("爬取失败")

实例4：网络图片的爬取和存储

网络图片链接的格式

http://www.example.com/picture.jpg

import requests
import os
url = "http://image.nationalgeographic.com/cn/2017/0211/20170211061910157.jpg"
root = "D://pics//"
path = root + url.split('/')[-1]
try:
    if not os.path.exists(root):
        os.mkdir(root)
    if not os.path.exists(path):
        r = requests.get(url)
        with open(path, 'wb') as f:
            f.write(r.content)
            f.close()
            print("文件保存成功")
    else:
        print("文件已存在")
except:
    print("爬取失败")

实例5：IP地址归属地的查询

http://m.i8138.com/ip.asp?ip=ipaddress

import requests
url = "http://m.ip138.com/ip.asp?ip="
try:
    r = requests.get(url + '202.204.80.112')
    r.raise_for_status()
    r.encoding = r.apparent_encoding
    print(r.text[-500:])
except:
    print("爬取失败")