python的第一个小爬虫requests

1:我们刚开始爬:

import requests
url = "http://www.ip138.com/ips138.asp?ip="
try:
   r = requests.get(url+"202.204.80.112")
   r.raise_for_status()				返回状态码   成功200 不是的话主动抛出异常
   r.encoding = r.apparent_encoding
   print(r.text[-500:])
except:
   print("爬取失败")

2:我们爬取带有关键字的网页

import requests
keyword = "python"
url = "http://www.baidu.com"
try:
   kv = {'wd': keyword}
   r = requests.get(url, params=kv)
   r.raise_for_status()
   r.encoding = r.apparent_encoding
   print(r.text)
except:
   print("爬取失败")

import requests
keyword = "python"
url = "http://www.so.com"
try:
   kv = {"q": keyword}
   r = requests.get(url, params=kv)
   r.raise_for_status()
   r.encoding = r.apparent_encoding
   print(r.text)
except:
   print("爬取失败")

3:我们爬取图片

import os
import requests

path = "D:\\abc\\"
url = "http://img.lanrentuku.com/img/allimg/1403/13962495222859.jpg"
# url = "http://image.nationalgeographic.com.cn/2017/0211/20170211061910157.jpg"
root = path + url.split('/')[-1]
try:
   if not os.path.exists(path):
      os.mkdir(path)				判断文件夹是否存在  如果不存在我们就新建一个
   if not os.path.exists(root):
      r = requests.get(url)
      r.raise_for_status()
      with open(root, 'wb')as f:		我们打开我们root文件  二进制写入
         f.write(r.content)
         f.close()
         print("文件保存成功")
   else:
      print("文件已存在")
except:
   print("爬取图片失败")