python最简单的爬虫

主要5部分：主函数，url管理器，网页下载器，网页输出器，网页解析器

（用了set，但是下面的代码并没有突出set的优势。后续可改进）

主要入口函数， spider_main:

import url_manager, html_downloader, html_outputer, html_parser

class SpiderMain(object):
    def __init__(self):
        self.urls = url_manager.UrlManager()
        self.downloader = html_downloader.HtmlDownloader()
        self.parser = html_parser.HtmlParser()
        self.outputer = html_outputer.HtmlOutputer()


    def craw(self, root_url):
        count = 1
        self.urls.add_new_url(root_url)#根节点入队
        while self.urls.has_new_url():#类似广度优先搜索
            try:
                new_url = self.urls.get_new_url()#从队列中得到一个新的url
                print 'craw %d : %s' % (count, new_url)#哪个url正在被爬取
                html_cont = self.downloader.download(new_url)#把这个网页爬下来
                new_urls, new_data = self.parser.parse(new_url, html_cont)#解析内部的url和数据
                self.urls.add_new_urls(new_urls)#将又爬到的url添加到队列中
                self.outputer.collect_data(new_data)#收集数据
                self.outputer.output_html()#打印数据

                if count == 10:
                    break

                count += 1

            except Exception as e:
                print e
                print 'craw failed'

if __name__ == "__main__":
    root_url = "http://baike.baidu.com/view/21087.htm" #根节点
    obj_spider = SpiderMain()
    obj_spider.craw(root_url)

url管理器：

class UrlManager(object):
    def __init__(self):
        self.new_urls = set()
        self.old_urls = set()
    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):#添加新的url到队列中
        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):#批量添加
        if urls is None or len(urls) == 0:#没爬到或者爬到了空串
            return
        for url in urls:
            self.add_new_url(url)

    def has_new_url(self):#判断队列是否为空
        return len(self.new_urls) != 0

网页下载器：

import urllib2


class HtmlDownloader(object):
    def download(self, url):
        if url is None:
            return None
        response = urllib2.urlopen(url)#打开url，并获取返回值
        if response.getcode() != 200:
            return None
        return response.read()#返回网页的全部内容

网页解析器：

 

import re
import urlparse

from bs4 import BeautifulSoup


class HtmlParser(object):

    def _get_new_urls(self, page_url, soup):#从一堆文字中获取url（正则匹配）
        new_urls = set()
        links = soup.find_all('a', href = re.compile(r"/view/\d+\.htm"))#获取a标签中，href为指定格式的标签全部内容
        for link in links:
            new_url = link['href']#取其中的href
            new_full_url = urlparse.urljoin(page_url, new_url)#拼接成完整链接
            new_urls.add(new_full_url)
        return new_urls

    def _get_new_data(self, page_url, soup):#从一堆文字中获取数据
        res_data = {}#键值对组合，title键值对，summary键值对

        #url
        res_data['url'] = page_url

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

        #<div class="lemma-summary" label-module="lemmaSummary">
        summary_node = soup.find('div', class_ = "lemma-summary")
        res_data['summary'] = summary_node.get_text()
        #print res_data['summary']

        return res_data


    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

网页输出器：

class HtmlOutputer(object):

    def __init__(self):
        self.datas = []

    def collect_data(self, data):#将数据（键值对们）组成列表
        if data is None:
            return

        self.datas.append(data)

    def output_html(self):
        fout = open("F:\\output.html", 'w')
        fout.write("<html>")
        fout.write("<body>")
        fout.write("<table>")

        for data in self.datas:
            print data['title']
            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()