html_parser.py

coding=UTF-8

# HTML解释器
import re

from bs4 import BeautifulSoup

class htmlParser():
    def parse(self, url, html_cont):
        if 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(url, soup)
        new_data = self._get_new_datas(url, soup)
        return new_urls, new_data

    def _get_new_urls(self, url, soup):
        urls = set()
        # <a target="_blank" href="/item/%E8%A7%A3%E9%87%8A%E5%99%A8">解释器</a>
        links = soup.find_all('a', href=re.compile(r'/item/\S+'))
        for link in links:
            new_url = link['href']
            new_full_url = 'http://baike.baidu.com' + new_url
            urls.add(new_full_url)
        return urls

    def _get_new_datas(self, url, soup):
        rst_data = {}

        # url
        rst_data['url'] = url

        # <dd class="lemmaWgt-lemmaTitle-title"> <h1>Python</h1>
        title_node = soup.find('dd', class_="lemmaWgt-lemmaTitle-title").find('h1')  # class为关键字，需要后面加下划线
        rst_data['title'] = title_node.get_text()

        # <div class="lemma-summary">
        summary_node = soup.find('div', class_="lemma-summary")
        rst_data['summary'] = summary_node.get_text()

        return rst_data