Python网络爬虫信息提取mooc代码实例

import requests
url="https//itemjd.com/2646846.html"
try:
 r=requests.get(url)
 r.raise_for_status()
 r.encoding=r.apparent_encoding
 print(r.text[:1000])
except:
 print("爬取失败")

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")

#百度的关键词接口：http://www.baidu.com/s"python"
try:
 kv={'wd':keyword}
 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")
--------------------------------------------------
import requests
keyword="python"
try:
 kv={'q':keyword}
 r=requests.get("http://www.so.com/s",params=kv)
 print(r.request.url)
 r.raise_for_status()
 print(len(r.text))
except:
 print("爬取失败")

import requests
import os
url="http://image.nationalgeographic.com.cn/2017/0211/20170211061910157.jpg"
root="F://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("文件已经存在")
except:
 print("爬取失败")

url="http://www.ip138.com/iplookup.asp"
try:
 r=requests.get(url+'202.204.80.112'+'&action=2')
 r.raise_for_status()
 r.encoding=r.apparent_encoding
 print(r.text[-500:])
except:
 print("爬取失败")