简单易扩展的爬虫架构

已经写了好几篇的网络爬虫了，都是单个应用程序，那个下面介绍一下简单易扩展的爬虫架构；

应用场景是：爬取百度百科搜索关键字的1000个相关链接及相应的简介；

模块介绍：

首先是我们的主调度程序spidermain，用来决定从哪个地开始爬取及调用相关模块；

urlmanager 用来管理目标URL，对于新爬取的URL检查是否已爬取，并 对爬取过的URL做回收；

htmldownload 用来下载目标URL的网页源码；

htmlparser 用来分析目标URL网页源码，解析出源码中的URL及简介；

htmloutput 收集已经爬取过的网页内容，并输出；

spidermain.py 

#!/usr/bin/env python 
#coding:utf-8
import htmldownload
import htmlparser
import urlmanager
import htmloutput
from myLog import MyLog as mylog


class SpiderMain(object):
    def __init__(self):
        self.urls = urlmanager.UrlManager()
        self.downloader = htmldownload.HtmlDownLoad()
        self.parser = htmlparser.HtmlParser()
        self.outputer = htmloutput.HtmlOutPut()
        self.log = mylog()


    def crow(self,url):
        self.urls.add_new_url(url)
        count = 1
        while self.urls.has_new_url():
            try:
                new_url = self.urls.get_new_url()
                self.log.info(u"当前爬取的是%d 个URL:%s"%(count,new_url))
                html_content = self.downloader.download(new_url)
#                 print html_content
                new_urls,new_data = self.parser.parser(new_url,html_content)
                self.urls.add_new_urls(new_urls)
                self.outputer.collect_data(new_data)
                if count == 10 :
                    break
                count += 1
            except Exception,e:
                self.log.error(u"当前爬取的%d 个URL:%s,失败......"%(count,new_url))
                self.log.error(e)
        self.outputer.output_html()


if __name__ == "__main__":
    root_url = "https://baike.baidu.com/item/CSS/5457"
    obj_spider = SpiderMain()
    obj_spider.crow(root_url)

urlmanager.py 

#coding:utf-8

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
        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 has_new_url(self):
        return len(self.new_urls) != 0

    def get_new_url(self):
        new_url = self.new_urls.pop()
        self.old_urls.add(new_url)
        return new_url

htmldownload.py

#coding:utf-8
import urllib2
class HtmlDownLoad(object):

    def download(self,url):
        if url is None:
            return
        headers = {
            "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.94 Safari/537.36",
            "Referer":"https://baike.baidu.com/item"
        }
        req = urllib2.Request(url,headers=headers)
        response = urllib2.urlopen(req)
        if response.getcode() != 200:
            return None

        return response.read()

htmlparser.py

#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', attrs={'href': re.compile(r'/item/.*?')})
        for link in links:
            new_url = link.get('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 = {}
        title_node = soup.find('dd', attrs={'class': 'lemmaWgt-lemmaTitle-title'}).find('h1')
        res_data['title'] = title_node.get_text()

        summary_node = soup.find('div', attrs={'class': 'lemma-summary'}).find('div',attrs={'class':'para'})
        res_data['summary'] = summary_node.get_text()
        

        res_data['url'] = page_url
#         print res_data.get('summary'),res_data.get('title'),res_data.get('url')
        return res_data

    def parser(self, page_url, html_content):
        if page_url is None or html_content is None:
            return
        soup = BeautifulSoup(html_content,'lxml')
        new_urls = self._get_new_urls(page_url, soup)
        new_data = self._get_new_data(page_url, soup)
        return new_urls, new_data

htmloutput.py

#coding:utf-8
import codecs
class HtmlOutPut(object):
    def __init__(self):
        self.datas = []

    def collect_data(self,data):
        if data is None:
            return
        self.datas.append(data)

    def output_html(self):
#         print 'i am run '
        fout = codecs.open('output.html','w','utf-8')
        fout.write('<html>')
        fout.write('<body>')
        fout.write('<table style="border:2px solid #000;">')
        for data in self.datas:
            fout.write('<tr style="border:2px solid #000;">')
            fout.write('<td style="border:2px solid #000;200px">%s</td>'%data.get('url'))
            fout.write('<td style="border:2px solid #000;">%s</td>' % data.get('title'))
            fout.write('<td style="border:2px solid #000;">%s</td>' % data.get('summary'))
            fout.write("</tr>")
        fout.write('</table>')
        fout.write('</body>')
        fout.write('</html>')

经过扩展，可以轻易获取想要内容；

后续将会上传爬取JS渲染过的网页，一起学习进步！