python爬虫之urllib,伪装,超时设置,异常处理的方法

from urllib import request
# urlretrieve() -- 将一个网页爬取到本地
request.urlretrieve("http://www.baidu.com",filename="demo.html")

# urlclearup() -- 清除urlretrieve()所产生的缓存
request.urlcleanup()

# info() -- 返回一个httpMessage对象,表示远程服务器的头信息
data = request.urlopen("http://www.taobao.com")
print(data.info())

# getcode() -- 获取当前网页的状态码data.geturl()
print(data.getcode())

# 获取当前爬取页面的网址
print(data.geturl())

Server: Tengine
Date: Wed, 09 May 2018 09:55:16 GMT
Content-Type: text/html; charset=utf-8
Transfer-Encoding: chunked
Connection: close
Vary: Accept-Encoding
X-Snapshot-Age: 1
Content-MD5: tkjcPUrHBAIt2N/YXcuwZg==
Vary: Ali-Detector-Type, X-CIP-PT
Cache-Control: max-age=0, s-maxage=89
ETag: W/"29b8-16340528168"
Via: cache22.l2cm9[0,304-0,H], cache17.l2cm9[0,0], cache1.cn372[0,200-0,H], cache2.cn372[1,0]
Age: 70
X-Cache: HIT TCP_MEM_HIT dirn:-2:-2 mlen:-1
X-Swift-SaveTime: Wed, 09 May 2018 09:54:59 GMT
X-Swift-CacheTime: 36
Timing-Allow-Origin: *
EagleId: 3c1cf2e515258597167937091e
Set-Cookie: thw=cn; Path=/; Domain=.taobao.com; Expires=Thu, 09-May-19 09:55:16 GMT;
Strict-Transport-Security: max-age=31536000


200
https://www.taobao.com/

for i in range(0,10):
 try:
  data = urllib.request.urlopen("http://www.baidu.com",timeout=0.05).read()
  print(len(data))
 except Exception as e:
  print("出现异常:"+str(e))

114980
114888
114809
114839
114824
114611
出现异常:<urlopen error timed out>
出现异常:<urlopen error timed out>
出现异常:<urlopen error timed out>
115003

from urllib import request
file = request.urlopen("http://www.baidu.com").read().decode()

from urllib import request 
url = "http://www.baidu.com" 
headers = ("User-Agent"," Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.139 Safari/537.36") #这里模拟浏览器 
opener = request.build_opener() 
opener.addheaders = [headers]
data = opener.open(url).read()
print(data)

from urllib import request 
url = "http://www.baidu.com" 
headers = ("User-Agent"," Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.139 Safari/537.36") #这里模拟浏览器 
opener = request.build_opener() 
opener.addheaders = [headers]
request.install_opener(opener)
data = request.urlopen(url).read().decode("utf-8")
print(data)

from urllib import request 
url = "http://www.baidu.com" 
headers = {}"User-Agent":" Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.139 Safari/537.36"} #这里模拟浏览器,通过字典
req = request.Request(url=rul,headers=headers)
data = request.urlopen(req).read().decode("utf-8")
print(data)

301 重定向
403 禁止访问
404 没有找到页面
500 服务器内部出现问题
200 成功

HttpError 是 URLError子类
 HttpError 有异常状态码和异常原因
 URLError 只有异常原因,没有异常状态码
 所以,在异常处理的时候,不能使用URLError来代替
 如果想要代替,必须要进行判断,判断是否有状态码属性

 会产生URLError的情况:
  1.连接不上服务器
  2.远程的url不存在
  3.本地网络
  4.HttpError(是子类,也会出发会产生URLError

from urllib import error,request
try: # 可能会出现异常的代码

 data = request.urlopen("http://www.aliyu.com").read()
 print(data)

except error.URLError as e: # 进行异常的处理

 if hasattr(e,"code"): # 判断是否有状态码

  print(e.code) # 状态码

 if hasattr(e,"reason"): # 判断是否有异常原因

  print(e.reason) # 异常原因