python-baikespider/html_parser.py at master · liunanxuan/python-baikespider · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
#-*- coding:utf-8 -*-
from bs4 import BeautifulSoup
import re
import urlparse
class HtmlParser(object):

	def _get_new_urls(self,page_url,soup):
		new_urls = set()
		links = soup.find_all('a',href=re.compile(r"/view/\d+\.htm"))
		for link in links:
			new_url = link['href']
			new_full_url = urlparse.urljoin(page_url,new_url)
			#print new_full_url
			new_urls.add(new_full_url)
		return new_urls

	def _get_new_data(self,page_url,soup):
		res_data = {}
		res_data['url'] = page_url
		title_node = soup.find('dd',class_='lemmaWgt-lemmaTitle-title').find('h1')
		res_data['title'] = title_node.get_text()
		print res_data['title']
		summary_node = soup.find('div',class_="lemma-summary")
		res_data['summary'] = summary_node.get_text()
		#print res_data['summary']
		return res_data

	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)
		return new_urls,new_data