基础爬虫的组成部分
python基础爬虫由五部分组成，分别是URL管理器、HTML下载器、HTML解析器、数据存储器以及爬虫调度器。
1、URL管理器
实现思路：
1、设置未爬取和已爬取的URL集合；
2、判断是否有未爬取的URL；
3、获取一个未爬取的URL
4、将新的URL添加到未爬取的URL集合中；
5、获取未爬取和已爬取的URL集合大小；
#看下面一个例子
# -*- coding: utf-8 -*-
class UrlManager(object):
"""docstring for UrlManager"""
def __init__(self):
self.new_urls = set()#未爬取URL集合
self.old_urls = set()#已爬取URL集合
def has_new_url(self):
"""
判断是否有未爬取的URL
：return
"""
return self.new_urls_size()!=0
def get_new_url(self):
new_url = self.new_urls.pop()
self.old_urls.add(new_url)
return new_url
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)
def add_new_url(self,urls):
if urls is None or len(urls)==0:
return
for url in urls:
self.add_new_url(url)
def new_url_size(self):
return len(self.new_urls)
def old_url_size(self):
return len(self.old_urls)
2、HTML下载器
用于下载网页，注意网页的编码，下载器需要用到Requests模块
# -*- coding: utf-8 -*-
import requests
class HtmlDownloader(object):
"""docstring for HtmlDownloader"""
def download(self, url):
if url is None:
return None
user_agent = 'Mozilla/4.0(compatible;MSTE 5.5; Windows NT)'
headers = {'User-Agent':user_agent}#模拟浏览器访问
r = requests.get(url,headers= headers)
if r.status_code == 200:
r.encoding = 'utf-8'
return r.text
return None
3、HTML解析器
用BeautifulSoup4进行HTML解析，以百度百科词条为例
# -*- coding: utf-8 -*-
import re
import urlparse
from bs4 import BeautifulSoup
class HtnlPareser(object):
"""docstring for HtnlPareser"""
def pareser(self, page_url,html_cont):
if page_url is None or html_cont is None:
return
soup = BeautifulSoup(html_cont,'html.pareser',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()
#抽取符合要求的a标记
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_url.add(new_full_url)
return new_urls
def _get_new_data(self,page_url,sopu):
data = {}
data['url']=page_url
title = soup.find('dd',class_='lemmaWgt-lemmaTitle-title').find('h1')
data['title']=title.get_text()
summary = soup.find('div',class_='lemma-summary')
data['summary']=summary.get_text()
return data
4、数据存储器
数据存储器主要包括两个方法：stroe_data(data)用于将解析出来的数据存储在内存中，output_html用于将存储的数据输出为指定的文件格式，我们使用的是将数据输出为HTML格式
# -*- coding: utf-8 -*-
import codecs
class DataOutput(object):
"""docstring for DataOutput"""
def __init__(self):
self.datas=[]
def syore_data(self,data):
if data is None:
return
self.datas.append(data)
def output_html(self):
fout = codecs.open('baike.html','w',encoding='utf-8')
fout.write("<html>")
fout.write("<head><meta charset='utf-8'/></head>")
fout.write("<body>")
fout.write("<table>")
for data in self.datas:
fout.write("<tr>")
fout.write("<td>%</td>"%data['url'])
fout.write("<td>%</td>"%data['title'])
fout.write("<td>%</td>"%data['summary'])
fout.write("</tr>")
self.datas.remove(data)
fout.write("</table>")
fout.write("</body>")
fout.write("</html>")
5、爬虫调度器
爬虫调度器首先要做的是初始化各个模块，然后再内部实现按照流程控制各个模块工作。以下是爬取百度百科的爬虫控制器
# -*- coding: utf-8 -*-
from DataOutput import DataOutput
from HtmlDownloader import HtmlDownloader
from HtmlPareser import HtmlPareser
from UrlManager import UrlManager
class SpiderMan(object):
"""docstring for SpiderMan"""
def __init__(self):
self.manager = UrlManager()
self.downloader = HtmlDownloader()
self.parser = HtmlPareser()
self.output = DataOutput()
def crawl(self,root_url):
self.mannager.add_new_url(root_url)
while(self.manager.has_new_url() and self.manager.old_url_size()<100):
try:
new_url = self.manager.get_new_url()
html = self.downloader.download(new_url)
new_url,data = self.parser.parser(new_url,html)
self.manager.add_new_url(new_urls)
self.output.store_data(data)
print("已经抓取%s个链接"%self.manager.old_url_size())
except Exception:
print ("crawl failed")
self.output.output_html()
if __name__ == '__main__':
spider_man = SpiderMan()
sprder_man.crawl('http://baike.baidu.com/view/284853.html')
网友评论