[学习笔记]抓取百度百科词条的爬虫

0.学习笔记来源

https://www.imooc.com/video/10688

1.抓取步骤

2.如何确定抓取策略：

• 1.url格式
• 2.数据格式
• 3.页面编码

点击右键审查元素

查看关键的标签对和网页的编码

3.百度百科相关词条信息

注意：目前是定向爬虫，爬取的数据策略可能随着网站更新而变化

4.启动模块-main

# coding=utf-8
#!/usr/bin/python

from baike_spider import url_manager, html_download, html_parser, html_outputer


class SpiderMain(object):

    def __init__(self):
        # URL 管理器
        self.urls = url_manager.UrlManager()
        # URL 下载器
        self.downloader = html_download.HtmlDownload()
        # URL 解析器
        self.parser = html_parser.HtmlParser()
        # URL 输出器
        self.outputer = html_outputer.HtmlOutputer()

    # 爬虫的调度程序
    def craw(self, root_url):
        count = 1
        self.urls.add_new_url(root_url)

        while self.urls.has_new_url():
            try:
                # 获取待爬取的 URL
                new_url = self.urls.get_new_url()
                print("craw %d : %s" % (count, new_url))

                html_content = self.downloader.downloader(new_url)
                new_urls, new_data = self.parser.parse(new_url, html_content)
                self.urls.add_new_urls(new_urls)
                self.outputer.collect_data(new_data)

                # 只爬取 1000 条的数据
                if(count == 1000):
                    break

                count = count + 1
            except:
                print("craw failed")

        self.outputer.output_html()

if __name__ == '__main__':
    # 入口 URL:百度百科的 Python 相关的百度词条
    root_url = "https://baike.baidu.com/item/Python/407313"
    obj_spider = SpiderMain()
    # 启动爬虫
    obj_spider.craw(root_url)

5.URL 管理器

# coding=utf-8
#!/usr/bin/python

# URL 管理器


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)
            #print("add_new_url", 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):
        # 取出并且移除
        new_url = self.new_urls.pop()
        self.old_urls.add(new_url)

        #print("get_new_url", new_url)
        return new_url

6.HTML 下载器

# coding=utf-8
#!/usr/bin/python

'''
HTML 下载器
'''
import urllib.request


class HtmlDownload(object):

    def downloader(self, url):
        if url is None:
            return None

        response = urllib.request.urlopen(url)
        if response.getcode() != 200:
            print("response.getcode() =", response.getcode())
            return None

        return response.read()

7.Html 解析器

# coding=utf-8
#!/usr/bin/python

'''
Html 解析器

传入 url 解析新的url列表（title 和 summary）
'''
from bs4 import BeautifulSoup
import re
from urllib.parse import urlparse
from urllib.parse import urljoin
import urllib.parse


class HtmlParser(object):

    def _get_new_urls(self, page_url, soup):
        new_urls = set()

        # 获取所有的链接，例如a 标签
        '''
        <a class="lock-lemma" target="_blank" href="/view/10812319.htm" 
        '''
        links = soup.find_all('a', href=re.compile(r"/item/"))

        for link in links:
            new_url = link['href']
            # 拼接 url
            # python 2x
            # new_full_url = urlparse.urljoin(page_url, new_url)
            new_full_url = urllib.parse.urljoin(page_url, new_url)
            new_urls.add(new_full_url)

        return new_urls

    def _get_new_data(self, page_url, soup):
        res_data = {}

        # Url
        res_data['url'] = page_url

        # F12 右键Pyton-查看(N)
        '''
        <dd class="lemmaWgt-lemmaTitle-title">
        <h1>Python</h1>
        <h2>（计算机程序设计语言）</h2>
        <a href="javascript:;" class="edit-lemma cmn-btn-hover-blue cmn-btn-28 j-edit-link" style="display: inline-block;"><em class="cmn-icon wiki-lemma-icons wiki-lemma-icons_edit-lemma"></em>编辑</a>
        <a class="lock-lemma" target="_blank" href="/view/10812319.htm" title="锁定"><em class="cmn-icon wiki-lemma-icons wiki-lemma-icons_lock-lemma"></em>锁定</a>
        </dd>
        '''
        title_node = soup.find(
            'dd', class_='lemmaWgt-lemmaTitle-title').find("h1")

        res_data['title'] = title_node.get_text()

        '''
        <div class="lemma-summary" label-module="lemmaSummary">
        <div class="para" label-module="para">Python<sup>[1]</sup><a class="sup-anchor" name="ref_[1]_21087">&nbsp;</a>
                    （英国发音：/ˈpaɪθən/ 美国发音：/ˈpaɪθɑːn/）, 是一种面向对象的解释型<a target="_blank" href="/item/%E8%AE%A1%E7%AE%97%E6%9C%BA%E7%A8%8B%E5%BA%8F%E8%AE%BE%E8%AE%A1%E8%AF%AD%E8%A8%80">计算机程序设计语言</a>，由荷兰人<a target="_blank" href="/item/Guido%20van%20Rossum">Guido van Rossum</a>于1989年发明，第一个公开发行版发行于1991年。</div><div class="para" label-module="para">Python是纯粹的<a target="_blank" href="/item/%E8%87%AA%E7%94%B1%E8%BD%AF%E4%BB%B6">自由软件</a>， <a target="_blank" href="/item/%E6%BA%90%E4%BB%A3%E7%A0%81/3969" data-lemmaid="3969">源代码</a>和<a target="_blank" href="/item/%E8%A7%A3%E9%87%8A%E5%99%A8">解释器</a>CPython遵循 <a target="_blank" href="/item/GPL">GPL</a>(<a target="_blank" href="/item/GNU">GNU</a> General Public License)协议。Python语法简洁清晰，特色之一是强制用空白符(white space)作为语句缩进。</div><div class="para" label-module="para">Python具有丰富和强大的库。它常被昵称为<a target="_blank" href="/item/%E8%83%B6%E6%B0%B4%E8%AF%AD%E8%A8%80">胶水语言</a>，能够把用其他语言制作的各种模块（尤其是<a target="_blank" href="/item/C/7252092" data-lemmaid="7252092">C</a>/<a target="_blank" href="/item/C%2B%2B">C++</a>）很轻松地联结在一起。常见的一种应用情形是，使用Python快速生成程序的原型（有时甚至是程序的最终界面），然后对其中有特别要求的部分，用更合适的语言改写，比如<a target="_blank" href="/item/3D%E6%B8%B8%E6%88%8F">3D游戏</a>中的图形渲染模块，性能要求特别高，就可以用C/C++重写，而后封装为Python可以调用的扩展类库。需要注意的是在您使用扩展类库时可能需要考虑平台问题，某些可能不提供<a target="_blank" href="/item/%E8%B7%A8%E5%B9%B3%E5%8F%B0">跨平台</a>的实现。</div><div class="para" label-module="para">7月20日，IEEE发布2017年编程语言排行榜：Python高居首位<sup>[2]</sup><a class="sup-anchor" name="ref_[2]_21087">&nbsp;</a>
                    。</div>
        </div>
        '''
        summary_node = soup.find('div', class_="lemma-summary")
        res_data['summary'] = summary_node.get_text()

        return res_data

    def parse(self, page_url, html_content):
        if page_url is None or html_content is None:
            return

        #print('parse html_content = ', html_content)
        soup = BeautifulSoup(
            html_content, '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

8.Html 输出器

# coding=utf-8
#!/usr/bin/python

'''
Html 输出器
'''


class HtmlOutputer(object):

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

    def collect_data(self, data):
        if data is None:
            return
        #print("collect_data = ", data)
        self.datas.append(data)

    def output_html(self):
        fout = open('output.html', 'w', encoding='utf-8')

        fout.write('<html>')
        fout.write('<body>')
        fout.write('<table>')

        for data in self.datas:
            fout.write('<tr>')
            fout.write("<td>%s</td>" % data['url'])
            fout.write("<td>%s</td>" % data['title'])
            fout.write("<td>%s</td>" % data['summary'])
            fout.write('</tr>')

        fout.write('</table>')
        fout.write('</body>')
        fout.write('</html>')

        fout.close()

9.运行结果

爬取1000个百科相关网页，并解析title和summary
file:///D:/EclipseProject/GrawDemo/baike_spider/output.html

10.Demo下载

https://github.com/sufadi/Python_BaikeSpider