Question

python new_url = link['href'] 这句话是什么意思

#!/usr/bin/env python2
# -*- coding: UTF-8 -*-
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)
return new_urls, new_data

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)
new_urls.add(new_full_url)
return new_urls

def _get_new_data(self, page_url, soup):
res_data = {}

# url

res_data['url'] = page_url
# <dd class="lemmaWgt-lemmaTitle-title"><h1>Python</h1>
title_node = soup.find('dd', class_= "lemmaWgt-lemmaTitle-title").find("h1")
res_data['title'] = title_node.get_text()

summary_node = soup.find('div', class_="lemma-summary")
res_data['summary'] = summary_node.get_text()
return res_data

Answer 1

不知道你这是什么版本的python，或者说用了些我完全不了解的库。<br>
就那一段来说，links = soup.find_all('a', href=re.compile(r"/view/\d+\.htm"))：<br>
应当是在soup里检索所有符合 re.compile(r"/view/\d+\.htm") 的结果，存放在结构 links 里。<br>
for link in links: # 循环 links 结构； link 好像是个字典<br>
new_url = link['href'] # new_url 应该是符合re.compile(r"/view/\d+\.htm") 的其中一个结果