爬虫入门

#coding:utf-8
import requests
url="http://www.baidu.com/s"
try:
    #kv={‘user-agent‘:‘Mozilla/5.0‘}
    kv={‘wd‘:‘Python‘}
    r=requests.get(url,params=kv)
    print r.status_code
    r.raise_for_status()
    r.encoding=r.apparent_encoding
    print len(r.text)
except:
    print ‘产生异常‘

#coding:utf-8
import requests
import os
url="http:image.nationalgeographic.com.cn/2017/0211/20170211061910157.jpg"
root="/Users/wangkun/Desktop/DEMO1/"
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‘

#coding:utf-8
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‘