爬虫--爬取人人网案例之封装篇（三）

首先，这个是封装函数：

from urllib import request,parse
from urllib.error import HTTPError,URLError
# 保存cookie
from http import cookiejar

class session(object):
    def __init__(self):
        # 通过对象保存cookie
        cookie_object = cookiejar.CookieJar()
        # handler 对应着一个操作  (HTTPCookieProcessor:就是HTTP Cookie 的处理器)
        handler = request.HTTPCookieProcessor(cookie_object)
        # opener 遇到有cookie的response的时候，调用handler内部的一个函数，存储到cookie object
        self.opener = request.build_opener(handler)

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

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

# 一、get(url, headers = None)
# 定义get方法，获取参数，返回爬取信息
def get(url, headers = None, opener=None):
    return urlrequests(url, headers = headers, opener=opener)

# 二、post(url, form, headers = None)
# 定义post方法，获取参数，返回爬取信息
def post(url, form, headers = None, opener=None):
    return urlrequests(url, form, headers, opener=opener)


'''
封装步骤：
#1. 传入url
#2. user_agent
#3. headers
#4. 定义Request
#5. urlopen
#6. 返回byte数组
'''

# 封装爬取信息方法
def urlrequests(url, form = None, headers = None, opener=None):
    # 获取网页response中的User-Agent信息
    user_agent = 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.181 Safari/537.36'
    # 如果用户需用自行转入headers， 则覆盖之前的headers
    # 判断headers是否为空
    if headers == None:
        # 如果没有传入headers参数，即为None的时候，则把user_agent信息以值的形式传递
        headers = {
            'User-Agent':user_agent
        }
    # 定义一个变量接收数据
    html_bytes = b''
    # 错误类型的判断  隐藏错误信息
    try:
        # 判断请求类型
        if form:
            # POST类型
            # 2.1 转换成str (导入parse)
            form_str = parse.urlencode(form, encoding='utf-8')
            # 2.2 转换成bytes
            form_bytes = form_str.encode('utf-8')
            # 使用request.Request获取url,data,headers
            req = request.Request(url, data=form_bytes, headers=headers)
        else:
            # GET类型
            # 使用request.Request获取url和headers
            req = request.Request(url, headers=headers)
        if opener:
            response = opener.open(req)
        else:
            response = request.urlopen(req)
        # 读取获取的信息
        html_bytes = response.read()
    except HTTPError as e:
        print(e)
    except URLError as e:
        print(e)
    # 将读取的信息进行返回
    return html_bytes

if __name__ == '__main__':
    # post测试数据
    # url = 'http://fanyi.baidu.com/sug'
    # form ={
    #     'kw':'哈哈'
    # }
    # html_bytes = post(url, form=form)
    # print(html_bytes.decode('utf-8'))

    # get测试数据
    url = 'http://www.baidu.com'
    html_byte = get(url)
    print(html_byte)

测试文件如下：

from fengzhuang_all import session
import json
# url
url = 'http://www.renren.com/ajaxLogin/login?1=1&uniqueTimestamp=2018721441132'
# form
form = {
    'email': '******',
    'icode': '',
    'origURL': 'http://www.renren.com/home',
    'domain': 'renren.com',
    'key_id': '1',
    'captcha_type': 'web_login',
    'password': '*************',
    'rkey': 'da25ffa69b1d73a097a822c8b033003e',
    'f': 'http%3A%2F%2Fwww.renren.com%2F967454193%2Fprofile',
}
# 实例化session
s = session()
# 调用session类中的post方法
html_bytes = s.post(url, form)
#html_bytes = post(url, form=form)
# 打印结果（可以打印看一下）
#print(html_bytes)
# 通过json获取一个字典类型
res_dict = json.loads(html_bytes.decode('utf-8'))
# print(res_dict)#{'code': True, 'homeUrl': 'http://www.renren.com/home'}
# 获取登录地址
home_url = res_dict['homeUrl']
# 访问页面
html_bytes = s.get(home_url)
print(html_bytes.decode('utf-8'))