Python 网络爬虫 初试

//利用Python 抓取指定页面

import urllib.request

url = "http://www.baidu.com"

data = urllib.request.urlopen(url).read()

data = data.decode('UTF-8')

print(data)

//简单看下openurl 的返回值 有哪些属性

import urllib.request

url = "http://www.baidu.com"

data = urllib.request.urlopen(url).read()

data = data.decode('UTF-8')

a = urllib.request.urlopen(url)

type(a)

<class 'http.client.HTTPResponse'>

a.geturl

<bound method HTTPResponse.geturl of <http.client.HTTPResponse object at 0x103555d68>>

a.geturl()

'http://www.baidu.com'

a.info()

<http.client.HTTPMessage object at 0x10356e0f0>

a.getcode()

200

import urllib

import urllib.request

data = {}

data['word'] = 'Jecvay Notes'

url_values = urllib.parse.urlencode(data)

url = "http://www.baidu.com/s?"

full_url = url+url_values

data = urllib.request.urlopen(full_url).read()

data = data.decode('UTF-8')

print(data)