# -*- coding: utf-8 -*
#html解析器
import re
import urlparse

from bs4 import BeautifulSoup


class HtmlParser(object):
    def parse(self, page_url, html_cont):
        if page_url is None or html_cont is None:
            return
        soup = BeautifulSoup(html_cont, 'html.parser', from_encoding='utf-8')
        new_urls = self._get_new_urls(page_url, soup)
        new_data = self._get_new_data(page_url, soup)

    def _get_new_urls(self, page_url, soup):
        new_urls = set()
        # 页面其他url的格式，在原url后面拼接上#1，#2，#3...
        links = soup.find_all('a',href=re.compile(r'#\d+'))
        for link in links:
            new_url = link['href']
            new_full_url = urlparse.urljoin(page_url,new_url)  #拼接成一个完整的url
            new_urls.add(new_full_url)
        return new_urls


    def _get_new_data(self, page_url, soup):
        res_data = {} #字典类型，存放数据
        #url
        res_data['url'] = page_url

        #获取title <dd class="lemmaWgt-lemmaTitle-title"><h1>Python</h1>
        #<div class="para-title level-2" label-module="para-title"><h2 class="title-text"><span class="title-prefix">Python</span>下载Python</h2>
        title_node = soup.find('dd',class_="lemmaWgt-lemmaTitle-title").find('h1')
        res_data['title']=title_node.get_text()
        print res_data['title']

        #获取summary <div class="lemma-summary" label-module="lemmaSummary">
        summary_node = soup.find('div',class_="lemma-summary")
        res_data['summary'] = summary_node.get_text()
        print res_data['summary']

        return res_data
        print res_data