python请求网页、获取网页信息_python中运用urllib.request简单抓取网页数据

fromurllib import request, parsefromurllib.error import HTTPError, URLErrorfromhttp import cookiejar

import jsonclass session(object):

def __init__(self):

#1、实例化cookie对象

cookie_obj=cookiejar.CookieJar()

#2、handler处理

handler=request.HTTPCookieProcessor(cookie_obj)

#3、opener 遇到有cookie的response的时候,调用handler内部的一个函数, 存储到cookie objectself.opener=request.build_opener(handler)

defget(self,url, headers=None):return get(url, headers, self.opener)

def post(self, url, form, headers=None):returnpost(url, form, headers, self.opener)

defget(url, headers=None, opener=None):return urlrequests(url, headers=headers, opener=opener)

def post(url, form, headers=None, opener=None):return urlrequests(url, form, headers=headers, opener=opener)

#b. post(url, form, headers=None)

#1. 传入url

#2. user_agent

#3. headers

#4. 定义Request

#5. urlopen

#6. 返回byte数组

def urlrequests(url, form=None, headers=None, opener=None):

user_agent= 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36'# 如果用户需要自行传入headers, 则覆盖之前的headersif headers ==None:

headers={'User-Agent': user_agent

}

html_bytes= b''

try:ifform:

# POST

#2.1转换成str

form_str=parse.urlencode(form)

#print(form_str)

#2.2转换成bytes

form_bytes= form_str.encode('utf-8')

req= request.Request(url, data=form_bytes, headers=headers)else:

req= request.Request(url, headers=headers)ifopener:

response=opener.open(req)else:

response=request.urlopen(req)

html_bytes=response.read()

except HTTPErrorase:

print(e)

except URLErrorase:

print(e)returnhtml_bytesif __name__ == '__main__':

#测试--带cookies的请求

url= 'http://www.renren.com/ajaxLogin/login?1=1&uniqueTimestamp=201872221746'form={'email': '18573151260','icode': '','origURL': 'http: // www.renren.com / home','domain': 'renren.com','key_id': '1','captcha_type': 'web_login','password': '60a075bc14562c91baf36094ffe93d8fa9c1809a8501a43a7da131e1f119ae91','rkey': 'f9cd77eb1280ab74763c1f1552dc11c7','f': 'http%3A%2F%2Fwww.renren.com%2F967453528'}

#实例化对象

s=session()

#post请求

res=s.post(url,form)

#获取的数据转为字典

res_dict=json.loads(res)

#获取url，此时cookie以通过s对象传入cookies_obj中

home_url= res_dict['homeUrl']

#打开url,此时将cookie_obj中的cookie

response=s.opener.open(home_url

#打印获取的数据

print(response.read().decode('utf-8'))

# url= 'http://www.baidu.com/'# html_byte= get(url)

# print(html_byte.decode('utf-8'))