python3爬取1000个百度百科页面（二）

五、爬虫流程

六、代码结构：

        爬虫调度器（入口）--url管理器--url下载器--解析器--输出器

spider_main.py(入口)

from baike_spider import url_manager        # url管理器
from baike_spider import html_downloader    # url下载器
from baike_spider import html_parser        # html解析器
from baike_spider import html_outputer      # htmloutputer


class SpiderMain(object):
    def __init__(self):
        # 初始化各个对象
        self.urls = url_manager.UrlManager()
        self.downloader = html_downloader.HtmlDownloader()
        self.parser = html_parser.HtmlParser()
        self.outputer = html_outputer.HtmlOutputer()

    # 爬虫调度程序
    def craw(self, root_url):
        count = 1
        # 将入口url加入url管理器，add_new_url添加一个
        self.urls.add_new_url(root_url)
        
        # 启动爬虫循环，当url 管理器有url时 
        while self.urls.has_new_url():
            try:
                # 获取一个待爬取url
                new_url = self.urls.get_new_url()
                # 打印当前爬取的url,
                print("craw %d : %s" %(count, new_url))
                # 启动下载器下载页面并保存 
                html_cont = self.downloader.download(new_url)
                # 下载好页面后，解析器解析，得到新的url列表和新的数据，
                new_urls, new_data = self.parser.paser(new_url, html_cont)
                # 将新的url添加进url管理器，add_new_urls添加多个
                self.urls.add_new_urls(new_urls)
                # 收集数据
                self.outputer.collect_data(new_data)
                
                # 爬取1000个页面
                if count == 1000:
                    break
                count = count + 1
            except:
                print('craw failed')
        # 输出收集好的数据
        self.outputer.output_html()


# 爬虫总调度程序入口
if __name__ == '__main__':
    root_url = "https://baike.baidu.com/view/21087.htm"
    obj_spider = SpiderMain()
    obj_spider.craw(root_url)

url_manager.py(管理器)

class UrlManager(object):
    # 待爬取和已爬取的url
    def __init__(self):
        self.new_urls = set()
        self.old_urls = set()

    # 向管理器添加一个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)
    
    # 向管理器批量添加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)

    # 判断管理器是否有新的url
    def has_new_url(self):
        return len(self.new_urls) != 0

    # 从管理器中获取一个url
    def get_new_url(self):
        new_url = self.new_urls.pop()
        self.old_urls.add(new_url)
        return new_url

html_downloader.py(下载器)

import urllib.request


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

        return response.read()

html_parser.py(解析器)

from bs4 import BeautifulSoup
import re
import urllib.parse


class HtmlParser(object):
    # 获取新的url，即获取超链接
    def _get_new_urls(self, page_url, soup):
        new_urls = set()
        # /view/123.htm
        links = soup.find_all('a', href=re.compile(r'/item/'))
        for link in links:
            new_url = link['href']
            # 拼接成一个新的url
            # urllib.parse.urljoin将两个url拼接成一个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

        # 得到标题的标签
        # <dd class="lemmaWgt-lemmaTitle-title">
        # <h1>Python</h1>
        title_node = soup.find('dd', class_="lemmaWgt-lemmaTitle-title").find('h1')
        res_data['title'] = title_node.get_text()

        # 获取简介
        # lemma-summary
        # <div class="lemma-summary" label-module="lemmaSummary">
        # <div class="para" label-module="para">Python 是一门有条理的和强大的面向对象的程序设计语言，类似于Perl, Ruby, Scheme, Java.</div>
        # </div>
        # <div class="para" label-module="para">Python 是一门有条理的和强大的面向对象的程序设计语言，类似于Perl, Ruby, Scheme, Java.</div>
        summary_node = soup.find('div', class_="lemma-summary")
        res_data['summary'] = summary_node.get_text()

        return res_data

    def paser(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

html_outputer.py(输出器)

class HtmlOutputer(object):
    def __init__(self):
        self.datas = []

    # 收集数据
    def collect_data(self, data):
        if data is None:
            return
        self.datas.append(data)
    
    # 将收集的数据写入html中，
    def output_html(self):
        # python默认输出asci
        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>")
        
        # 表格
        fout.write("<table>")

        
        for data in self.datas:
            # 每行
            fout.write("<tr>")
            # 每个单元格
            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()

参考：http://www.imooc.com/learn/563

源码（附注释）：https://download.csdn.net/download/bailixuance/10712607