第一周 2（requests库实战）

1 京东商品页面爬取

import requests

url = 'https://item.jd.com/7694047.html'
try:
    r = requests.get(url, timeout=30)
    r.raise_for_status()
    r.encoding = r.apparent_encoding
    print(r.text)
except:
    print("Error")

　　

2 亚马逊商品页面的爬取

import requests

url = 'https://www.amazon.cn/gp/product/B01M8L5Z3Y'
try:
    kv = {'user-agent': "Mozilla/5.0"}
    r = requests.get(url, timeout=30, headers=kv)#使用headers
    r.raise_for_status()
    r.encoding = r.apparent_encoding
    print(r.text[1000:2000])
except:
    print("Error")

　　

3 百度/360搜索关键词提交

百度的关键词接口：
http://www.baidu.com/s?wd=keyword
360的关键词接口：
http://www.so.com/s?q=keyword

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

　　

import requests

try:
    kv = {'q': "Python"}
    r = requests.get('http://www.so.com/s', params=kv)
    r.raise_for_status()
    print(r.request.url)
    print(len(r.text))
except:
    print("爬取失败")

　　

4 网络图片的爬取和储存

图片爬取全代码

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.makdir(root)
    if not os.path.exists(path):
        r = requests.get(path, 'wb')
        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")

4 IP归属地的自动查询

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")