Python爬虫，爬取百度百科词条

看了慕课网的一个网络爬虫教程。模仿着写了一个简单的爬取百度百科的例子。

（1）安装Beautifulsoup4

Beautifulsoup是Python的一个网页解析库，使用起来很方便。http://cuiqingcai.com/1319.html这个链接是介绍如何使用。这个库是需要安装的，进入Pthon安装目录下面的Scripts目录，执行pip install beautifulsoup进行安装。

（2）爬虫具体实现

爬虫分为5个模块，调度模块、网页下载模块、网页解析模块、URL管理模块、输出模块。

URL管理模块，负责保存最新的网页URL，每次取出最新的URL进行爬取。

#coding=utf8
class UrlManager(object):


    def __init__(self):
        self.new_urls = set()
        self.old_urls = set()


    #添加新的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)

    #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)

    #是否有新的url
    def has_new_url(self):
        return len(self.new_urls) != 0

    #获取新的url
    def get_new_url(self):
        new_url = self.new_urls.pop()
        self.old_urls.add(new_url)

        return new_url

URL下载模块，负责把网页的内容下载下来，使用urllib2库进行下载。

#coding utf8

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()

URL解析模块，使用Beautifulsoup把当前网页的其他链接和网页简介解析出来。

# coding:utf-8
import urlparse

from bs4 import BeautifulSoup
import re


class HtmlParser(object):
    def parser(self, page_url, html_content):
        if page_url is None or html_content is None:
            return
        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

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

        links = soup.find_all('a', href=re.compile(r'/item/'))

        for link in links:
            new_url = link["href"]
            new_url_full = urlparse.urljoin(page_url, new_url)
            new_urls.add(new_url_full)

        return new_urls

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

        res_data['url'] = page_url

        # 
 
Python
        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

输出模块，负责把解析的网页内容保存起来。

#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 outpute_html(self):
        fout = open("outputer.html",'w')
        fout.write("")
        fout.write("")
        fout.write("")


        for data in self.datas:
            fout.write("")
            fout.write("")

        fout.write("")
        fout.write("")
        fout.write("
%s
" % data['url'])
            fout.write("
%s
" % data['title'].encode('utf-8'))
            fout.write("
%s
" % data['summary'].encode('utf-8'))
            fout.write("
")

最后是调度模块，把各个模块之间的功能调度起来

#coding:utf8
import url_manager
import html_downloader
import html_outputer
import html_parser

class SpiderMain(object):
    def __init__(self):
        self.urls = url_manager.UrlManager()
        self.downloader = html_downloader.HtmlDownloader()
        self.parser = html_parser.HtmlParser();
        self.outputer = html_outputer.HtmlOutputer()
    pass

    def craw(self, root_url):
        self.urls._add_new_url(root_url)

        count = 1;

        while self.urls.has_new_url():

            try:
                new_url = self.urls.get_new_url()
                print new_url

                #得到url的内容
                html_content = self.downloader.download(new_url)

                #得到url的内容和url
                new_urls,new_data = self.parser.parser(new_url,html_content)

                self.urls.add_new_urls(new_urls)

                self.outputer.collect_data(new_data)
            except:
                print "splider failed"

            if (count == 10):
                break

            count = count + 1;

        self.outputer.outpute_html()


if __name__ == "__main__":
    root_url = "https://baike.baidu.com/item/Python/407313"

    obj_splider = SpiderMain()
    obj_splider.craw(root_url)

工程目录如下：

源码路径如下，感兴趣的朋友可以去下载：

https://github.com/HelloKittyNII/Spider/tree/master/%E7%99%BE%E5%BA%A6%E7%99%BE%E7%A7%91%E7%88%AC%E8%99%AB/baike_spider