Python爬虫----实例： 抓取百度百科Python词条相关1000个页面数据

一、分析目标

如果分析目标与上述不同，请自行修改，因为页面会随意更新数据格式等相关信息

二、调试程序

spider_main.py

#!/usr/bin/python
# -*- coding: UTF-8 -*-
import url_manager
import html_downloader
import html_outputer
import html_parser


class SpiderMain(object):
    # 初始各个对象， 其中UrlManager、HtmlDownloader、HtmlParser、HtmlOutputer四个对象需要之后创建
    def __init__(self):
        self.urls = url_manager.UrlManager()  # URL管理器
        self.downloader = html_downloader.HtmlDownloader()  # 下载器
        self.parser = html_parser.HtmlParser()  # 解析器
        self.outputer = html_outputer.HtmlOutputer()  # 输出器

    def craw(self, root_url):
        count = 1
        # 将root_url添加到url管理器
        self.urls.add_new_url(root_url)

        # 只要添加的url里有新的url
        while self.urls.has_new_url():
            try:
                new_url = self.urls.get_new_url()
                print 'craw %d : %s' % (count, new_url)

                # 启动下载器，将获取到的url下载下来
                html_cont = self.downloader.download(new_url)

                # 调用解析器解析下载的这个页面
                new_urls, new_data = self.parser.parse(new_url, html_cont)

                # 将解析出的url添加到url管理器， 将数据添加到输出器里
                self.urls.add_new_urls(new_urls)
                self.outputer.collect_data(new_data)

                if count == 1000:
                    break
                count = count + 1
            except:
                print 'craw failed'
        self.outputer.output_html()


if __name__ == "__main__":
    root_url = "http://baike.baidu.com/link?url=92QjmNSCiMatDE-Sb65QLtad37q_bmvugik4DziB3VSQ7VeceqRseYIuCyy78_eg_wYbvbe9d7P7ZvgbW1swUaBLXiChLXEplFzOpoN3EEkTlr5UALue9WdbjyAqJEPS"  # 这个URL根据实际情况的url进行修改
    obj_spider = SpiderMain()
    obj_spider.craw(root_url)  # 启动爬虫

-------------------------------------------------------------------
url_manager.py  (URL管理器）

#!/usr/bin/env python2
# -*- coding: UTF-8 -*-

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

-----------------------------------------------------------------------

html_downloader.py （HTML下载器）

#!/usr/bin/python
# -*- 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()

-----------------------------------------------------------------

html_parser.py （HTML解析器）

#!/usr/bin/python
# -*- coding: UTF-8 -*-
import urlparse
import re
from bs4 import BeautifulSoup


class HtmlParser(object):
    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

    def _get_new_urls(self, page_url, soup):
        new_urls = set()
        links = soup.find_all('a', href=re.compile("/view/\d+\.htm"))
        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()

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

        return res_data

--------------------------------------------------------

html_outputer.py （HTML输出器）

#!/usr/bin/python
# -*- 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)

    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>")
        fout.close()