简单爬虫实现day2

 实战演练

 1. 分析目标

目标：百度百科Python词条相关词条网页-标题和简介

入口页：https://baike.baidu.com/item/Python/407313

URL格式：

　　- 词条页面URL：/item/Perl

数据格式：

　　- 标题：

　　　　<dd class="lemmaWgt-lemmaTitle-title> <h1> ... </h1> </dd>

　　- 简介：

　　　　<div class="lemma-summary" > ,,, </div>

页面编码：UTF-8

2. 调度程序

建立五个模块

   

打开siider_main.py爬虫总调度程序

#!/usr/bin/env python3
import url_manager
import html_downloader
import html_parser
import html_outputer
import pdb


class SpiderMain(object):
    """入口主函数"""

    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
        # 初始url
        self.urls.add_new_url(root_url)
        # 当存在可爬取的url时
        while self.urls.has_new_url():
            try:
                # 获取带爬取url
                new_url = self.urls.get_new_url()
                print('craw %d : %s' % (count, new_url))
                # 启动下载器下载页面
                html_cont = self.downloader.download(new_url)
                # 启动解析器将新的url和爬到的数据进行保存
                new_urls, new_data = self.parser.parse(new_url, html_cont)
                pdb.set_trace()
                # 将新的url添加
                self.urls.add_new_urls(new_urls)
                # 收集爬取数据
                self.outputer.collect_data(new_data)

                # 爬取100个页面
                if count == 100:
                    break
                count = count + 1
            except:
                print("%d craw failed" % count)
        # 输出内容
        self.outputer.output_html()

if __name__ == "__main__":
    root_url = "https://baike.baidu.com/item/Python/407313"
    obj_spider = SpiderMain()
    obj_spider.craw(root_url)

3. URL管理器

#!/usr/bin/env python3


class UrlManager(object):
    """URL管理器"""

    def __init__(self):

        # 将url保存到内存中
        self.new_urls = set()
        self.old_urls = set()

    # 控制url存储到内存的函数
    def add_new_url(self, root_url):
        url = root_url
        if url is None:
            return

        # 如果这个url既不在待爬取的url中也不在爬取过的url中说明它是一个新的url
        if url not in self.new_urls and url not in self.old_urls:
            self.new_urls.add(url)

    # 处理爬取到新的url的函数
    def add_new_urls(self, new_urls):
        urls = new_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):

        # 获取一个新的url，在new_urls中删除，在old_urls中添加
        new_url = self.new_urls.pop()
        self.old_urls.add(new_url)
        return new_url

4. HTML下载器

from urllib import request


class HtmlDownloader(object):

    def download(self, url):
        if url is None:
            return None
        response = request.urlopen(url)

        if response.getcode() != 200:
            return None
        return response.read()

5. HTML解析器

#!/usr/bin/env python3
from bs4 import BeautifulSoup
import re
import urllib.parse


class HtmlParser(object):

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

        # 构建网页解析器
        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

    def _get_new_urls(self, page_url, soup):
        new_urls = set()
        # /item/任意字符
        links = soup.find_all('a', href=re.compile(r"/item/"))
        for link in links:
            new_url = link['href']
            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

        # <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()

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

        # 三个属性：url、title、summary
        return res_data

6. HTMl输出器

#!/usr/bin/env python3
class HtmlOutputer(object):
    """docstring for HtmlOutputer"""

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

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

    def output_html(self):
        fout = open('output.html', 'w', encoding='utf-8')  # utf-8编码
        fout.write("<html>")
        fout.write("<head>")
        fout.write("<meta charset='utf-8'>")  # 给html声明
        fout.write("</head>")
        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()

7.最终爬取效果