python简单爬虫爬取百度百科python词条网页

目标分析：
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/xxxx

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

爬虫主入口文件

spider_main.py

# coding:utf-8
import url_manager
import html_downloader
import html_parser
import html_outputer

class SpiderMain(object):
    def __init__(self):
        # url管理器
        self.urls = url_manager.UrlManager()
        # 下载器
        self.downloader = html_downloader.HtmlDownloader()
        # 解析器
        self.parser = html_parser.HtmlParser()
        # 输出控制器
        self.outputer = html_outputer.HtmlOutputer()

    def craw(self, root_url):
        # 记录当前爬取的是第几个url
        count = 1
        self.urls.add_new_url(root_url)
        # 如果有待爬取的url就继续while循环
        '''
        while self.urls.has_new_url():
            try:
                new_url = self.urls.get_new_url()
                print 'craw %d : %s' % (count, new_url)
                # 下载url页面
                html_cont = self.downloader.download(new_url)
                # 进行url解析并获取url的数据
                new_urls, new_data = self.parser.parse(new_url, html_cont)
                # url解析及数据搜集
                self.urls.add_new_urls(new_urls)
                self.outputer.collect_data(new_data)

                if count >= 1000:
                    break
                count = count + 1
            except Exception as e:
                print 'craw failed'
                print e
        '''
        while self.urls.has_new_url():
            new_url = self.urls.get_new_url()
            print 'craw %d : %s' % (count, new_url)
            # 下载url页面
            html_cont = self.downloader.download(new_url)
            # print html_cont
            # 进行url解析并获取url的数据
            new_urls, new_data = self.parser.parse(new_url, html_cont)
            # url解析及数据搜集
            self.urls.add_new_urls(new_urls)
            self.outputer.collect_data(new_data)

            if count >= 10:
                break
            count = count + 1

        # 输出到指定页面
        self.outputer.output_html()

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

网页管理器

url_manager.py

# coding:utf-8

class UrlManager(object):
    def __init__(self):
        # 要爬取的url
        self.new_urls = set()
        # 爬取过的url
        self.old_urls = set()

    def add_new_url(self, url):
        if url is None:
            return
        # 如果url不在要爬取的url里面也不在爬取过的url里面就添加进来
        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

网页下载器

html_downloader.py

# coding:utf-8

import urllib2

class HtmlDownloader(object):
    def download(self, url):
        if url is None:
            return None

        response = urllib2.urlopen(url)

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

        return response.read()

网页分析器

html_parser.py

# coding:utf-8

from bs4 import BeautifulSoup
import re
import urlparse

class HtmlParser(object):

    def _get_new_urls(self, page_url, soup):
        # 得到所有的词条url
        links = soup.find_all('a', href=re.compile(r"/item/.*"))
        # print links
        new_urls = set()
        for link in links:
            new_url = link['href']
            new_full_url = urlparse.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" label-module="lemmaSummary">
        summary_node = soup.find('div', class_="lemma-summary")
        res_data['summary'] = summary_node.get_text()

        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

html_outputer.py

# coding:utf-8

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

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

    # ascii
    def output_html(self):
        fout = open('output.html', 'w')

        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'].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")

运行代码：

结果页面