实战爬虫-五大基本模块

任务：爬取百度百科关于网络爬虫的100个词条，并以HTML格式存储

第一个模块-URL管理器：维护已经爬取的URL集合和未爬取的URL集合，并提供获取新URL链接的接口

URLManager.py

# _*_coding:utf-8 _*_
# @Time     :2017/11/12
# @Author   :luoyu_bie
# @File     :URLManager.py
# @Software :PyCharm Community Edition


class URLManager(object):
    def __init__(self):
        self.new_urls = set()
        self.old_urls = set()
    def new_url_size(self):
        '''
        获取未爬取URL集合的大小
        :return: 
        '''
        return len(self.new_urls)
    def old_url_size(self):
        '''
        获取已爬取URL的大小
        :return: 
        '''
        return len(self.old_urls)

    def has_new_url(self):
        '''
        判断是否有未爬取的URL
        :return: 
        '''
        return self.new_url_size() != 0
    def get_new_url(self):
        '''
        获取一个未爬取的URL
        :return: 
        '''
        new_url = self.new_urls.pop()
        self.old_urls.add(new_url)
        return new_url
    def add_new_url(self,url):
        '''
        将新的URL添加到未爬取的URL集合
        :param url: 单个url
        :return: 
        '''
        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):
        '''
        将新的URL添加到未爬取的URL集合
        :param urls: url集合
        :return: 
        '''
        if urls is None or len(urls)==0:
            return
        for url in urls:
            self.add_new_url(url)

第二个模块-HTML下载器：从URL管理器中获取未爬取的URL链接并下载HTML网页

HTMLDownloader.py

# _*_coding:utf-8 _*_
# @Time     :2017/11/12
# @Author   :luoyu_bie
# @File     :HTMLDownloader.py
# @Software :PyCharm Community Edition
import requests

class HtmlDownloader(object):
    def download(self,url):
        if url is None:
            return None
        user_agent = "Mozilla/5.0 (Windows NT 6.3; Win64; x64; rv:56.0) Gecko/20100101 Firefox/56.0"
        headers = {'User-Agent':user_agent}
        r = requests.get(url,headers=headers)
        if r.status_code == 200:
            r.encoding='utf-8'
            return r.text
        return None

第三个模块-HTML解析器：从HTML下载器下载的网页内容解析出新的URL交给URL管理器，解析出有效数据给到数据存储器，常用BeautifulSoup、xpath、re正则

HtmlParser.py

# _*_coding:utf-8 _*_
# @Time     :2017/11/12
# @Author   :luoyu_bie
# @File     :HtmlParser.py
# @Software :PyCharm Community Edition

import re
import urlparse
from bs4 import BeautifulSoup

class HtmlParser(object):
    def parser(self,page_url,html_cont):
        '''
        用于解析网页内容，抽取URL和数据
        :param page_url: 下载页面的url
        :param html_cont: 下载的页面的内容
        :return: 返回URL和数据
        '''
        soup = BeautifulSoup(html_cont,'lxml',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):
        '''
        抽取新的URL集合
        :param page_url:下载页面的URL 
        :param soup: 
        :return: 返回新的URL集合
        '''
        new_urls = set()
        links = soup.find_all('a',href=re.compile(r'/item/.*'))
        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):
        data = {}
        data['url']=page_url
        title = soup.find('dd',class_='lemmaWgt-lemmaTitle-title').find('h1')
        data['title'] = title.get_text()
        summaray = soup.find('div',class_='lemma-summary')
        data['summary']=summaray.get_text()
        return data

第四个模块-数据存储器：将HTML解析器解析出来的数据通过文件或数据库的形式存储起来

DataOutput.py

# _*_coding:utf-8 _*_
# @Time     :2017/11/12
# @Author   :luoyu_bie
# @File     :DataOutput.py
# @Software :PyCharm Community Edition

import codecs
class DataOutput(object):

    def __init__(self):
        self.datas=[]
    def store_data(self,data):
        if data is None:
            return
        self.datas.append(data)
    def output_html(self):
        #codecs自动编码，打开文件按照指定的编码写入或读取
        fout = codecs.open('baike.html','a',encoding='utf-8')
        fout.write("<html>")
        fout.write("<head><meta charset='utf-8'/></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>")
            self.datas.remove(data)
        fout.write("</table>")
        fout.write("</body>")
        fout.write("</html>")
        fout.close()

第五个模块-爬虫调度器：负责统筹调度其他四个模块的协调工作

SpiderMan.py

# _*_coding:utf-8 _*_
# @Time     :2017/11/12
# @Author   :luoyu_bie
# @File     :SpiderMan.py
# @Software :PyCharm Community Edition

from DataOutput import DataOutput
from HtmlParser import HtmlParser
from HTMLDownloader import HtmlDownloader
from URLManager import URLManager
class SpiderMan(object):
    def __init__(self):
        self.manager = URLManager()
        self.downloader = HtmlDownloader()
        self.parser = HtmlParser()
        self.output = DataOutput()
    def crawl(self,root_url):
        #添加入口URL
        self.manager.add_new_url(root_url)
        #判断URL管理器是否有新的URL，同时计算抓取了多少个url
        while(self.manager.has_new_url() and self.manager.old_url_size()<100):
            try:
                #从URL管理器获取新的URL
                new_url = self.manager.get_new_url()
                #HTML下载器下载网页
                html = self.downloader.download(new_url)
                #HTML解析器抽取网页数据
                new_urls,data = self.parser.parser(new_url,html)
                #将抽取的URL添加到URL管理器中
                self.manager.add_new_urls(new_urls)
                #数据存储器存储文件
                self.output.store_data(data)
                print "已经抓取%s个链接"%self.manager.old_url_size()
            except Exception,e:
                print "crawl failed"
            #数据存储器将数据输出成指定格式
            self.output.output_html()

if __name__ == "__main__":
    spider_man = SpiderMan()
    spider_man.crawl("https://baike.baidu.com/item/%E7%BD%91%E7%BB%9C%E7%88%AC%E8%99%AB")