python3使用urllib模块制作网络爬虫

import urllib
#要伪装成的浏览器(我这个是用的chrome)
headers = ('User-Agent','Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/46.0.2490.86 Safari/537.36')
url='http://hotels.ctrip.com/'
opener = urllib.request.build_opener()
#将要伪装成的浏览器添加到对应的http头部
opener.addheaders=[headers]
#读取相应的url
data = opener.open(url).read()
#将获得的html解码为utf-8
data=data.decode('utf-8')
print(data)

2、urllib.parse主要是用来解析url

主要方法：

urllib.parse.urlparse(urlstring)

功能：将对应的URL解析成六部分，并以元组的数据格式返回来。(在功能上和urlsplit()几乎一模一样)

import urllib
o = urllib.parse.urlparse('http://www.cwi.nl:80/%7Eguido/Python.html')
print(o)
print(o.path)
print(o.scheme)
print(o.port)
print(o.geturl())

from urllib.parse import urljoin
a=urljoin('http://www.cwi.nl/%7Eguido/Python.html', 'FAQ.html')
print(a)

try:
  data=urllib.request.urlopen(url)
  print(data.read().decode('utf-8'))
except urllib.error.HTTPError as e:
  print(e.code)
except urllib.error.URLError as e:
  print(e.reason)