python爬虫学习笔记1

from urllib import request
from urllib import parse
'''
resp = request.urlopen("https://www.baidu.com")
print(resp.read())
print(resp.getcode())#返回状态码200正常301跳转400服务器问题
request.urlretrieve('http://www.baidu.com/', 'baidu.html')#下载网页或者图片都行
params = {'name':'张三', 'age':18,'greet':'hello world'}
result = parse.urlencode(params)#转url编码url不识别中文和空格
print(result)
#例如
url = 'http://www.baidu.com/s'
params = {"wd":"刘德华"}
qs = parse.urlencode(params)
url = url + "?" + qs
resp = request.urlopen(url)
print(resp.read())
#正常会出错查询这个http://baidu.com/s?刘德华
qs = "name=%E5%BC%A0%E4%B8%89&age=18&greet=hello+world"
print(parse.parse_qs(qs))
#这个与上面程序相反解码

url = 'http://www.baidu.com/s;hello?wd=python&username=abc#1'
result = parse.urlparse(url)#解析这个域名分割然后求出每个项
print('scheme:', result.scheme)
print('netloc', result.netloc)
print('path', result.path)
print('params', result.params)
print('query',result.query)
print('fragment',result.fragment)    
result1 = parse.urlsplit(url)#解析这个域名分割然后求出每个项
print('scheme:', result1.scheme)
print('netloc', result1.netloc)
print('path', result1.path)
#print('params', result1.params)#urlsplit没这个参数
print('query',result1.query)
print('fragment',result1.fragment)    
#urlparse 比 urlsplit多获取一个hello                                                                
'''