1.URL管理器:
class UrlManager (object):
def __init__(self):
self.new_urls = set()
self.old_urls = set()
def add_new_url(self, url):
if url is None:
return # 如果没有新的URL则不进行添加
if url not in self.new_urls and url not in self.old_urls:
self.new_urls.add(url)
def add_new_urls(self, urls):
if urls is None or len(urls) == 0:
return
for url in urls:
self.add_new_url(url)
def get_new_url(self):
return len(self.new_urls) != 0
def has_new_url(self):
new_url = self.new_urls.pop()
self.old_urls.add(new_url)
return new_url
2.网页下载器:
import urllib.request
import urllib.response
class HtmlDownloader(object):
def download(self, url):
if url is None:
return None
response = urllib.request.urlopen(url)
if response.getcode() != 200:
return None
return response.read()
3.网页解析器:
# coding:utf-8
from bs4 import BeautifulSoup
import re
import urllib.parse
class HtmlParser(object):
def parser(self, page_url, html_content):
if page_url is None or html_content is None:
return
soup = BeautifulSoup(html_content, '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"/item/\d+.htm"))
links = soup.find_all('a', href=re.compile(r"/item/(.*)"))
for link in links:
new_url = link['href']
new_full_url = urllib.parse.urljoin(page_url, new_url)
new_urls.add(new_url)
return new_urls
def get_new_data(self, page_url, soup): 4.页面输出:
res_data = {}
# url
res_data['url'] = page_url
# 标题Python
(计算机程序设计语言)
# 简介
title_node = soup.find_all('dd', class='lemmaWgt-lemmaTitle-title').find('h1')
res_data['title'] = title_node.get_text()
summary_node = soup.find_all('div', class_='lemma-summary')
res_data['summmary'] = summary_node.get_text()
return res_data
class HtmlOutputer(object):def __init__(self):
self.datas=[]
def collectData(self, data):
if data is None:
return
self.datas.append(data)
def output_html(self):
fout = open('output.html', 'w')
fout.write("<html>")
fout.write("<body>")
fout.write("<table>")
for data in self.datas:
fout.write("<tr>")
fout.write("<td>%s</td>" % (data['url']).encode('utf-8'))
fout.write("<td>%s</td>" % (data['title']).encode('utf-8'))
fout.write("<td>%s</td>" % (data['summary']).encode('utf-8'))
fout.write("</tr>")
fout.write("</table>")
fout.write("</body>")
fout.write("</html>")
fout.close()