学习python一周，学着写了一个爬虫，用来抓取360百科的词条，在这个过程中。因为一个小小的修改，程序出现一些问题，又花了几天时间研究，问了各路高手，都没解决，终于还是自己攻克了，事实上就是对list列表理解不够深入导致的。这个bug非常有借鉴意义，分享出现。

先看看终于抓取出的结果：

以下进入正题。先来看看文件结构。这里有5个模块：

• spider_main.py是入口函数
• url_manager.py是管理器，管理须要抓取的url和已经抓取的url
• html_downloader.py是下载器，下载相应url的网页
• html_parser.py是解析器，解析出新的url列表和当前的词条信息
• html_outputer.py是输出器。将抓取的词条title和解释summary输出成一个html表格

本程序使用的是最新的python3.4.4。使用的类库有：

• 官方的urllib
• 第三方的BeautifulSoup（自行下载安装）

一、spider_main.py

这个函数是入口函数，全部方法都是字面意思，能够到相应的类中查看

from baike360_spider import url_manager, html_downloader, html_parser, html_outputer


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):
        count = 1
        self.urls.add_new_url(root_url)
        while self.urls.has_new_url():
            try:
                new_url = self.urls.get_new_url()
                print(‘craw %d: %s‘ % (count, new_url))
                html_cont = self.downloader.download(new_url)
                new_urls, new_data = self.parser.parse(new_url, html_cont)
                self.urls.add_new_urls(new_urls)
                self.outputer.collect_data(new_data)

                if count == 5:
                    break
                count += 1
            except Exception as e:
                print(‘craw failed‘)
                print(e)

        self.outputer.output_html()

if __name__ == ‘__main__‘:
    root_url = ‘http://baike.so.com/doc/1790119-1892991.html‘
    obj_spider = SpiderMain()
    obj_spider.craw()

二、url_manager.py

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

三、html_downloader.py

import urllib.request


class HtmlDownloader(object):
    def download(self, url):
        if url is None:
            return
        res = urllib.request.urlopen(url)
        if res.getcode() != 200:
            return
        return res.read()

import re
from urllib.parse import urljoin

from bs4 import BeautifulSoup


class HtmlParser(object):
    def __init__(self):
        self.new_urls = set()
        # self.res_data = dict()

    def _get_new_urls(self, page_url, soup):
        # new_urls = set()
        # /doc/5912108-6125016.html或/doc/3745498.html
        links = soup.find_all(‘a‘, href=re.compile(r‘/doc/[\d-]+\.html‘))
        for link in links:
            new_url = link[‘href‘]
            new_full_url = urljoin(page_url, new_url)
            # print(new_full_url)
            self.new_urls.add(new_full_url)
        return self.new_urls

    def _get_new_data(self, page_url, soup):
        res_data = dict()
        # url
        res_data[‘url‘] = page_url
        # <span class="title">Python</span>
        title_node = soup.find(‘span‘, class_=‘title‘)
        res_data[‘title‘] = title_node.get_text()
        # <div class="card_content" id="js-card-content">
        summary_node = soup.find(‘div‘, class_=‘card_content‘).find(‘p‘)
        res_data[‘summary‘] = summary_node.get_text()
        # print("dd: ", self.res_data)
        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

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(‘output.html‘, ‘w‘, encoding=‘utf-8‘)
        fout.write(‘<html>‘)
        fout.write("<head><meta http-equiv=\"content-type\" content=\"text/html;charset=utf-8\"></head>")
        fout.write(‘<body>‘)
        fout.write(‘<table border=1 cellspacing=0>‘)
        for data in self.datas:
            fout.write(‘<tr>‘)
            fout.write(‘<td><a href="%s">%s</a></td>‘ % (data[‘url‘], data[‘title‘]))
            fout.write(‘<td>%s</td>‘ % data[‘summary‘])
            fout.write(‘</tr>‘)
        fout.write(‘</table>‘)
        fout.write(‘</body>‘)
        fout.write(‘</html>‘)
        fout.close()

原因分析：