import requests

from bs4 import BeautifulSoup

import re





class CsdnHelper:

    csdn_login_url = 'https://passport.csdn.net/account/login?ref=toolbar'

    headers = {

        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36',

        'Content-Type': 'application/x-www-form-urlencoded',

        'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',

        'DNT': '1',

        'Referer': 'https://passport.csdn.net/account/login?ref=toolbar',

        'Accept-Encoding': 'gzip, deflate, br',

        'Accept-Language': 'zh-CN,zh;q=0.8,en;q=0.6,ja;q=0.4',

    }



    def __init__(self):

        self._session = requests.session()

        self._session.headers = CsdnHelper.headers



    def login(self, username, password):

        form_data = self._prepare_login_form_data(username, password)

        response = self._session.post(CsdnHelper.csdn_login_url, data=form_data)

        print(response.text)

        if 'UserNick' in response.cookies:

            print(response.cookies['UserNick'])

        else:

            raise Exception('登录失败')



    def _prepare_login_form_data(self, username, password):

        response = self._session.get(CsdnHelper.csdn_login_url)

        login_page = BeautifulSoup(response.text, 'lxml')

        login_form = login_page.find('form', id='fm1')



        lt = login_form.find('input', attrs={'name': 'lt'})['value']

        execution = login_form.find('input', attrs={'name': 'lt'})['value']

        eventId = login_form.find('input', attrs={'name': 'lt'})['value']

        form = {

            'username': username,

            'password': password,

            'lt': lt,

            'execution': execution,

            '_eventId': eventId

        }



        return form



    def _get_blog_count(self):



        blog_base_url = 'http://write.blog.csdn.net/postlist/'

        response = self._session.get(blog_base_url)

        blog_page = BeautifulSoup(response.text, 'lxml')

        span = blog_page.find('div', class_='page_nav').span

        pattern = re.compile(r'(\d+)条 共(\d*)页')

        result = pattern.match(span.string)

        blog_count = int(result.group(1))

        page_count = int(result.group(2))

        return (blog_count, page_count)



    def print_blogs(self):

        blog_count, page_count = self._get_blog_count()

        for index in range(1, page_count + 1):

            url = f'http://write.blog.csdn.net/postlist/0/0/enabled/{index}'

            response = self._session.get(url)

            page = BeautifulSoup(response.text, 'lxml')

            links = page.find_all('a', href=re.compile(r'http://blog.csdn.net/u011054333/article/details/(\d+)'))

            print(f'----------第{index}页----------')

            for link in links:

                blog_name = link.string

                blog_url = link['href']

                print(f'文章名称:{blog_name} 文章链接:{blog_url}')





if __name__ == '__main__':

    csdn_helper = CsdnHelper()

    username = XXX

    password = XXX

    csdn_helper.login(username, password)