21天打造分布式爬虫（一）

#encoding:utf-8

from urllib import request

res = request.urlopen("https://www.cnblogs.com/")

print(res.readlines())


#urlopen的参数
#def urlopen(url, data=None, timeout=socket._GLOBAL_DEFAULT_TIMEOUT,
#            *, cafile=None, capath=None, cadefault=False, context=None):

#coding:utf-8

from urllib import request

res = request.urlretrieve("https://www.cnblogs.com/",‘cnblog.html‘)


#urlretrieve参数
#def urlretrieve(url, filename=None, reporthook=None, data=None):

#urlencode函数

# 简单用法
#from urllib import parse
# data = {‘name‘:‘德瑞克‘,‘age‘:100}
# qs = parse.urlencode(data)
# print(qs)    #name=%E5%BE%B7%E7%91%9E%E5%85%8B&age=100

#实际用例
from urllib import request,parse
url = "http://www.baidu.com/s"
params = {"wd":"博客园"}
qs = parse.urlencode(params)
url = url + "?" + qs
res = request.urlopen(url)
print(res.read())

from urllib import parse

qs = "name=%E5%BE%B7%E7%91%9E%E5%85%8B&age=100"
print(parse.parse_qs(qs))   #{‘name‘: [‘德瑞克‘], ‘age‘: [‘100‘]}

from urllib import request,parse

url = "https://www.baidu.com/s?wd=cnblog#2"
result = parse.urlparse(url)
print(result)
#ParseResult(scheme=‘https‘, netloc=‘www.baidu.com‘, path=‘/s‘, params=‘‘, query=‘wd=cnblog‘, fragment=‘2‘)

print(‘scheme:‘,result.scheme)   #协议
print(‘netloc:‘,result.netloc)   #域名
print(‘path:‘,result.path)       #路径
print(‘query:‘,result.query)     #查询参数

#结果
#scheme: https
# netloc: www.baidu.com
# path: /s
# query: wd=cnblog

class Request:

    def __init__(self, url, data=None, headers={},
                 origin_req_host=None, unverifiable=False,
                 method=None):

#利用Request类爬去拉勾网职位信息

from urllib import request,parse

url = "https://www.lagou.com/jobs/positionAjax.json?city=%E5%8C%97%E4%BA%AC&needAddtionalResult=false"

#请求头
headers = {
    "User-Agent":"Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.140 Safari/537.36",
    "Referer":"https://www.lagou.com/jobs/list_python?city=%E5%8C%97%E4%BA%AC&cl=false&fromSearch=true&labelWords=&suginput="
}
#post请求需要提交的数据
data = {
    ‘first‘:‘true‘,
    ‘pn‘:1,
    ‘kd‘:‘python‘
}
#post请求的data数据必须是编码后的字节类型
req = request.Request(url,headers=headers,data=parse.urlencode(data).encode(‘utf-8‘),method=‘POST‘)   #建立一个请求对象
res = request.urlopen(req)
#获取的信息是字节类型，需要解码
print(res.read().decode(‘utf-8‘))

#代理的使用
from urllib import request

url = "https://www.baidu.com/s?wd=cnblog"

#1.使用ProxyHandler传入代理构建一个handler
# handler = request.ProxyHandler({‘http‘:‘115.210.31.236.55:9000‘})
handler = request.ProxyHandler({‘http‘:‘115.210.31.236.55:9000‘})
#2.使用创建的handler构建一个opener
opener = request.build_opener(handler)
#3.使用opener去发送一个请求
res = opener.open(url)
print(res.read())