直接上代码
1.UrlManager 管理器
# coding:utf8
class UrlManager(object):
#初始化,待爬取URL和已爬取URL
def __init__(self):
self.new_urls = set()
self.old_urls = set()
#添加新URL进管理器
def add_new_url(self, url):
if url is None:
return
if url not in self.new_urls and url not in self.old_urls:
self.new_urls.add(url)
#批量添加URLS
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 has_new_url(self):
return len(self.new_urls) != 0
#pop方法可以把其中的一个URL给弹出,并且移除
def get_new_url(self):
new_url = self.new_urls.pop()
self.old_urls.add(new_url)
return new_url
2.Urldoawnloader 下载器
# coding:utf8
import urllib2
class HtmlDownloader(object):
def download(self, url):
if url is None:
return None
response = urllib2.urlopen(url)
if response.getcode() !=200:
return None
return response.read()
3.Parser 解析器
# -*- 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()
# /view/123.htm
links = soup.find_all('a', href=re.compile(r"/view/\d+\.htm"))
for link in links:
new_url = link['href']
#urljoin 函数可以将new_url 按page_url 的格式拼接成一个全新的url
new_full_url = urlparse.urljoin(page_url,new_url)
new_urls.add(new_full_url)
return new_urls
#获取的数据为 title and summary
def _get_new_data(self, page_url, soup):
res_data = {}
#url
res_data['url'] = page_url
#获取 title
#<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()
#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()
return res_data
4.Outputer 输出器
# coding:utf8
class HtmlOutputer(object):
def __init__(self):
self.datas = []
def collect_data(self,data):
if data is None:
return
self.datas.append(data)
def output_html(self):
fout = open('outputer.html','w')
fout.write("<html>")
fout.write('<body>')
fout.write('<table>')
#ascii
for data in self.datas
fout.write("<tr>")
fout.write('<td>%s</td>' % data['url'])
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()
总结:BeautifulSoup的使用方法为:创建BeautifulSoup对象->搜索节点find-all/find->访问节点(名称,属性,文字)。
形如;soup = BeautifulSoup(html_cont,’html.parser’,from_encoding=’utf-8’),第一个参数传网页,第二个参数传解析器,第三个参数编码。至此,可以完全爬取百度百科的Python词条。
不足之处欢迎指正。